Imaging Pearls ❯ Deep Learning ❯ AI and Healthcare (Overview)
|
-- OR -- |
|
- The consensus of conference participants was that AIH supports but does not currently replace clinician-provided care or patient self-management. The ubiquity of smartphones and Internet connections brings access to AIH tools to almost everyone. Where care access is limited by resources, including in wealthy countries with staff shortages, AI is a valuable alternative — if handled correctly. Patients can now enjoy round-the-clock access to extensive medical information and insights far more sophisticated than online health information platforms such as WebMD. This is a sea change in a field in which, traditionally, patients have not only faced barriers in accessing their own medical data but also lacked inexpensive means to reason with those data.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3) - Infusing the spirit of the conference was a strong desire to avoid past mistakes in applying new technology and policies to medicine. For example, in the United States, electronic medical records have tended to serve billing needs more often than enhancing care. In addition, major privacy laws such as the European Union’s General Data Protection regulation and the U.S. Health Insurance Portability and Accountability Act Privacy Rule are widely misunderstood and add administrative complexity that hinders AIH research. Early AIH experiences showed that even powerful new technology will fail to catch on broadly and institutionally if health care staffers, payers, patients, or caregivers do not trust it or if they worry about liability.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3) - We recommend that health systems, health plans, and physician groups review and, if deemed appropriate, adopt AI to augment clinical practice. “Low-hanging fruit” includes enhancement of the doctor–patient interaction,bincluding capture of the recorded patient visit,bprioritizing and analysis of test and imaging results, differential diagnosis, plan for therapy and discussion of alternatives, instructions for the patient and caregivers, appointment scheduling and other administrative functions,band responses to patient questions at optimal levels of literacy.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3) - A. When providers use AIH: Case law is still developing around the world, but at this point it seems that the clinician remains legally responsible for medical actions and decisions, even when AI is used in health care. However, if AIH is to be widely adopted, technology companies must accept somevportion of the legal liability if an AIH systemvleads to harm and it is at fault. Also, the next generation of clinicians must be trained on how best to use AI to supplement their medical expertise.
B. When patients use AIH: Clarify that, similarly, the technology companies must move toward accepting some responsibility for outcomes when patients use the AI directly, just as with any other direct-to consumer health tool or resource.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3) - Because it is so important to train AIH models with broad and diverse data, AI models will likely rely extensively on data generated during the course of clinical care. When it comes to arrangements for ingesting patient data into AI models, conference participants strongly supported the use of “opt-out” — that is, the default is for patient data to be included — rather than “opt-in,” which could lead to further disparities in data collection because of historical mistrust of some populations toward medical science. Participants do, however, recognize that opt-out consent cannot fully eliminate the potential for harmful bias because populations harboring this mistrust may disproportionately exercise their right to opt-out, leaving them underrepresented. Whether opt-in or opt-out, consent cannot substitute for appropriate technical safeguards for privacy and responsible data use practices that will make AIH tools trustworthy and reduce the public’s urge to opt-out.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3) - Remember that it may be advantageous for patients to avoid a visit to a provider by using an AI-powered alternative, shifting some time-held practices, and disrupting the financial models underlying health care. Health systems should strive not just to improve provider care with AI but eventually to substitute for some of it. A participant noted that many in their country would actively like to avoid doctors — a widespread sentiment elsewhere as well.
To Do No Harm — and the Most Good — with AI in Health Care
Carey Beth Goldberg
NEJM AI 2024; 1 (3)
- “Furthermore, in our experience, the environment in which some health care organizations operate often leads these organizations to focus on near-term financial results at the cost of investment in longer-term, innovative forms of technology such as AI. Health care organizations that prioritize innovation link investment decisions to “total mission value,” which includes both financial and nonfinancial factors such as quality improvement, patient safety, patient experience, clinician satisfaction, and increased access to care.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. - “We think that the need for AI to help improve health care delivery should no longer be questioned, for many reasons. Take the case of the exponential increase in the collective body of medical knowledge required to treat a patient. In 1980, this knowledge doubled every 7 years; in 2010, the doubling period was fewer than 75 days.1 Today, what medical students learn in their first 3 years would be only 6 percent of known medical information at the time of their graduation. Their knowledge could still be relevant but might not always be complete, and some of what they were taught will be outdated. AI has the potential to supplement a clinical team’s knowledge in order to ensure that patients everywhere receive the best care possible. Bringing that potential to reality has not been easy, but thereare some successes.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. - “AI is broadly defined as a machine or computing platform that is capable of making intelligent decisions. Two types of AI have generally been pursued in health care delivery: machine learning, which involves computational techniques that learn from examples instead of operating from predefined rules, and natural language processing, which is the ability of a computer to transform human language and unstructured text into machine-readable structured data that reliably reflect the intent of the language.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. - “AI is also being used in prior authorization, a process that involves substantial manual labor, with only 21% of prior authorizations automated.9 The process can be costly because it requires doctors and registered nurses to review requests for authorization. From the payer’s perspective, the objective is to ensure that patients are receiving clinically appropriate treatment. Therefore, prior authorization is meant to be a check on what the provider has ordered.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. - “Another use of AI in clinical operations is tackling clinician burnout. Physicians now spend more than 50% of their time updating electronic health records (EHRs), and this use of time is a documented contributor to burnout. Multiple providers are piloting natural language processing to reduce this burden. If these efforts are successful, natural language processing could turn unstructured data such as clinicians’ notes into the structured data needed for the EHR as well as for other uses, such as documenting quality metrics or filling in appropriate Current Procedural Terminology codes. This application of AI would give clinicians more time to spend with patients and on tasks that require human judgment.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. - “For example, starting with a strategic vision, one of the greatest challenges is properly defining the costs and benefits of deploying AI. Historically, the decision to invest in AI has been based on financial return. This calculation should be expanded to include nonfinancial factors as well. Otherwise, AI adoption could continue to lag in certain domains in which a large portion of its effect is nonfinancial, such as quality and safety.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58. 
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58.- “I adoption in health care delivery has lagged behind adoption in other business sectors, but the past few years have shown the potential and promise of AI, which has already begun to shape the operations of payers and providers in some areas. If the promise of AI is realized, the quality of and access to health care delivery will be improved. The promise remains, but realizing it in practice has not been easy.”
Artificial Intelligence in U.S. Health Care Delivery
Nikhil R. Sahni and Brandon Carrus
N Engl J Med 2023;389:348-58.
- Artificial-intelligence doctors As we collect more data from genome, proteome, and metabolome screening, we will need intelligent algorithms to put sensible num- bers to the data, find patterns that evade human eye, and even identify new biomarkers102,103. All these technological approaches will require high computing power to find patterns and predict the possible outcomes of abnormal signals.
The future of early cancer detection
Rebecca C. Fitzgerald et al.
Nature Medicine | VOL 28 | APRIL 2022 | 666–677 - The US Food & Drug Administration has addressed regulatory chal- lenges by publishing an action plan on the implementation of AI in diagnostic and medical devices106. This includes mitigating against susceptibility to differences in input data compared with data that an AI model was trained on, which can lead to inaccurate predictions. Accuracy needs to be maintained across populations and time; for example, data will change with wear and tear of scanners, and adversarial attacks are another challenge. In parallel, work is also required to ensure that AI is coupled with user-friendly soft- ware and to address the incentives and barriers to adoption of AI from patients and clinicians.
The future of early cancer detection
Rebecca C. Fitzgerald et al.
Nature Medicine | VOL 28 | APRIL 2022 | 666–677 - For early cancer detection, the percentage of confidence that comes with a diagnostic decision made by the algorithm might appear straightforward (for example, 80% confidence that lung can- cer is present), but the process behind this number is very complex and understandably may not be apparent to the user. It is therefore not difficult to understand that there might be resistance to adop- tion of such strategies and the fear of overdiagnosis. It is important to understand that AI will not remove the need for physicians and experts to interpret the findings, provide a global picture of patient health, spot related diseases, and come up with a final diagnosis.
The future of early cancer detection
Rebecca C. Fitzgerald et al.
Nature Medicine | VOL 28 | APRIL 2022 | 666–677 - What the introduction of AI algorithams might do, providing that data management and safety regulations are in place, is reduce the cost and time needed to diagnose the disease. This will enable health practitioners to spend more time developing efficient and holistic treatment protocols, and will make state-of-art diagnostics more affordable. Furthermore, AI can be a training tool that pro- vides immediate specialist feedback to generalists so that, in time, they may perform at an expert level.
The future of early cancer detection
Rebecca C. Fitzgerald et al.
Nature Medicine | VOL 28 | APRIL 2022 | 666–677 - “For early cancer detection, the percentage of confidence that comes with a diagnostic decision made by the algorithm might appear straightforward (for example, 80% confidence that lung can- cer is present), but the process behind this number is very complex and understandably may not be apparent to the user. It is therefore not difficult to understand that there might be resistance to adoption of such strategies and the fear of overdiagnosis. It is important to understand that AI will not remove the need for physicians and experts to interpret the findings, provide a global picture of patient health, spot related diseases, and come up with a final diagnosis. What the introduction of AI algorithams might do, providing that data management and safety regulations are in place, is reduce the cost and time needed to diagnose the disease. This will enable health practitioners to spend more time developing efficient and holistic treatment protocols, and will make state-of-art diagnostics more affordable. Furthermore, AI can be a training tool that pro- vides immediate specialist feedback to generalists so that, in time, they may perform at an expert level."
The future of early cancer detection
Rebecca C. Fitzgerald et al.
Nature Medicine | VOL 28 | APRIL 2022 | 666–677 
- “ A novel method of leveraging AI combines computer vision and natural language processing to ambiently function in the background, monitoring for critical care gaps. This AI Quality workflow uses a visual classifier to predict the likelihood of a finding of interest, such as a lung nodule, and then leverages natural language processing to review a radiologist’s report, identifying discrepancies between imaging and documentation. Comparing artificial intelligence predictions with natural language processing report extractions with artificial intelligence in the background of computer-aided detection decisions may offer numerous potential benefits, including streamlined workflow, improved detection quality, an alternative approach to thinking of AI, and possibly even indemnity against malpractice.”
Is AI the Ultimate QA?
Edmund M. Weisberg, Linda C. Chu, Benjamin D. Nguyen, Pelu Tran, Elliot K. Fishman
J Digit Imaging. 2022 Feb 15. doi: 10.1007/s10278-022-00598-8. 
Is AI the Ultimate QA?
Edmund M. Weisberg, Linda C. Chu, Benjamin D. Nguyen, Pelu Tran, Elliot K. Fishman
J Digit Imaging. 2022 Feb 15. doi: 10.1007/s10278-022-00598-8.- “We view the use of AI running in the background as a QA tool to be a win/win situation. The process should make radiologists comfortable, not impeding their workflow at all, while also convincing them of its value through consistent demonstration. The QA system we have outlined offers a novel way of approaching the reading of CT scans and represents what might be an easy starting point for those hesitant but interested in exploring AI opportunities. Can AI become the ultimate QA? It is not there yet, clearly, but the prospect of such a role for AI in radiology seems closer than ever.”
Is AI the Ultimate QA?
Edmund M. Weisberg, Linda C. Chu, Benjamin D. Nguyen, Pelu Tran, Elliot K. Fishman
J Digit Imaging. 2022 Feb 15. doi: 10.1007/s10278-022-00598-8. - “While time will tell the true impact of AI, it is likely that, in time, AI will change everything about medicine, with some of the most substantial impacts in fields like radiology, pathology, and dermatology in the nearer term. While articles reporting the impact on pathology and dermatology discuss increased accuracy and potential change in workflow,there is never a discussion of replacing pathologists or dermatologists. However, with radiology, there is a larger problem. Many clinicians look at radiology images, from plain films to computed tomography (CT) and magnetic resonance imaging (MRI) examinations,and view them as simply images to be interpreted, instead ofas a potential opportunity for expert consultant radiologists to bring value to patient care.”
The future of radiology: What if artificial intelligence is really as good as predicted?
Rowe SP, Soyer P, Fishman EK.
Diagn Interv Imaging. 2022 May 12:S2211-5684(22)00089-4. - "But, what happens when AI becomes as good or better than a radiologist? Would that be the moment when the cardiologists, emergency room doctors, and orthopedic surgeons decide that there is noneed for radiologists as they will be able to read imaging examinationsas accurately due to the availability of AI in their practices? After all, they interact directly with the patient while a significant number of radiologists are at home or reading centers far away from the delivery of care.”
The future of radiology: What if artificial intelligence is really as good as predicted?
Rowe SP, Soyer P, Fishman EK.
Diagn Interv Imaging. 2022 May 12:S2211-5684(22)00089-4. - "There are multiple approaches that radiologists might take to stave off extinction by AI. First and foremost, we need to stay engaged with our referring provides. AI algorithms often lack “explainability”and may produce answers that defy the logic of human minds. A radiologist that has the trust of their referrers and can serve as an “interpreter” of AI output as well as a gatekeeper of false-positive and false-negative findings will have substantial value. This can come in the context of attending multi-disciplinary conferences and tumor boards as well as being available in person or by phone to consult on cases.”
The future of radiology: What if artificial intelligence is really as good as predicted?
Rowe SP, Soyer P, Fishman EK.
Diagn Interv Imaging. 2022 May 12:S2211-5684(22)00089-4. - “No one can predict the future. The rise of AI will see the creation of the transhuman intelligence and the “technological singularity”, the point beyond which no meaningful prediction about technology can be made. Society may be so fundamentally transformed that we cannot even guess at the implications for radiology or any other field in medicine. In the short-term, radiologists should focus on maximizing their relevancy by improving their visibility and value to referring clinicians and contributing to meaningful, cutting-edge research with new and evolving modalities. In the long-term, we will have to wait and see what happens”
The future of radiology: What if artificial intelligence is really as good as predicted?
Rowe SP, Soyer P, Fishman EK.
Diagn Interv Imaging. 2022 May 12:S2211-5684(22)00089-4.
- “By necessity, radiomics and AI tools are initially developed in controlled environments, which poorly reflect clinical practice. Furthermore, it is generally assumed that a radiologist’s interpretation should serve as ground truth. While the years of training and experience are difficult to mimic by the tools, there are equally certain quantitative abilities in which radiomics- and AI-based tools may outperform radiologists. This article reminds us that methodology must be standardized and validated, but studies need not always be designed to mimic radiologist interpretation but to assess clinical outcomes.”
Radiomics and Artificial Intelligence: From Academia to Clinical Practice
Peter Steiger
Radiology 2022; 00:1–2 (in press) - "Radiomics has demonstrated its utility in many studies because of its ability to quantify texture- and appearance- related properties of volumes of interest, thus augmenting the more qualitative interpretation of the radiologist. These studies have been difficult to reproduce, however, because of the lack of standardization and the variation between scanners and methodology. This has also stood in the way of broader clinical adoption. Radiomics shares this challenge with artificial intelligence (AI), where numerous studies in many different indications have shown prom- ise, but few have found clinical utility beyond breast, lung, and, more recently, prostate imaging. A recent review of U.S. Food and Drug Administration (FDA)–approved devices with an AI component found that there was a total of 39 radiology-related approvals since 2015, with 35 of them focusing on assisting radiologists with diagnosis, 29 of which were for breast, lung, and prostate imaging.”
Radiomics and Artificial Intelligence: From Academia to Clinical Practice
Peter Steiger
Radiology 2022; 00:1–2 (in press) - “Advances in neural networks pushed forward the possibility boundaries of AI at the cost of interpretability. When neural networks are used, it is often difcult to understand how a specic prediction was generated, meaning without substantial effort, some AI algorithms are so-called “black boxes.” As a result, if there is no one proactively looking to identify problems with a neural network-generated algorithm, there is a substantial risk that the AI will generate solutions with aws only discoverable after they have been deployed – for examples, see work on “algorithmic bias”. This lack of transparency can reduce trust in AI and reduce adoption by health care providers, especially considering that doctors and hospitals will likely be held accountable for decisions that involve AI. The importance of complementary innovation in trustworthy AI, for example through technologies or processes that facilitate AI algorithm interpretation, is widely recognized.”
Why is AI adoption in health care lagging?
Avi Goldfarb and Florenta Teodoridis
Brookings March 2022 - “The performance of AI algorithms is also contingent on the quality of data available. Thus a second barrier to adoption is limited access to data. Medical data is often difcult to collect and difcult to access. Medical professionals often resent the data collection process when it interrupts their workow, and the collected data is often incomplete. It is also difcult to pool such data across hospitals or across health care providers. Electronic Healthcare Record (EHR) systems are largely not compatible across government-certied providers that service different hospitals and health care facilities. The result is data collection that is localized rather than integrated to document a patient’s medical history across his health care providers. Without large, high-quality data sets, it can be difcult to build useful AIs. This, in turn, means that health care providers may be slower to take up the technology.”
Why is AI adoption in health care lagging?
Avi Goldfarb and Florenta Teodoridis
Brookings March 2022 - "Innovation in algorithmic transparency, data collection, and regulation are examples of the types of complementary innovations necessary before AI adoption becomes widespread. In addition, another concern that we believe deserves equal attention is the role of decisionmakers. There is an implicit assumption that AI adoption will accelerate to benet society if issues such as those related to algorithm development, data availability and access, and regulations are solved. However, adoption is ultimately dependent on health care decisionmakers. Not infrequently, medical professionals are the decisionmakers, and AI algorithms threaten to replace the tasks they perform.”
Why is AI adoption in health care lagging?
Avi Goldfarb and Florenta Teodoridis
Brookings March 2022 - "One interpretation of these patterns is that hospitals with an integrated salary model, and hence professional managers, have leaders that recognize the clinical and administrative benets of AI, while other hospitals might have leaders that do not recognize the benets. However, we have seen that there are several reasons why AI adoption might be slow in hospitals. In other words, even if professional managers are more likely to adopt AI, they are not necessarily right to engage in adoption at this stage. For example, while it may be that doctor-led hospitals have not adopted AI because they view it as a threat to their jobs, it may also be that doctor-led hospitals have leaders who have a better grasp of the other adoption challenges—algorithmic limitations, data access limitations, and regulatory barriers.”
Why is AI adoption in health care lagging?
Avi Goldfarb and Florenta Teodoridis
Brookings March 2022 - “The policy implications related to challenges in data collection and the lack of trust in algorithms are more related to continued funding of research than new regulation. Governments and nonprots are already directing substantial research funds to these questions, particularly around lack of trust. In terms of misaligned incentives, complementary innovation in management processes is difcult to achieve through policy. Antitrust policy to ensure competition could help, as competition has been shown to improve management quality. Otherwise, there are few policy tools that could change these incentives.Overall, relative to the level of hype, AI adoption has been slow in health care. Policymakers can help generate useful adoption with some innovative approaches to privacy and the path to regulatory approval. However, it might be the familiar tools that are most useful: clarify the rules, fund research, and enable competition.”
Why is AI adoption in health care lagging?
Avi Goldfarb and Florenta Teodoridis
Brookings March 2022
- “All this leads to broader adoption where AI/ML may become a necessity and standard of care- akin to seat belts in cars, once an optional feature that became standard.”
What’s Needed to Bridge the Gap Between US FDA Clearance and Real-world Use of AI Algorithms
MingDe Lin
Acad Radiol 2022; 29:567–568 - “AI has also made strides in the field of genomics, despite the complexity of modeling 3D genomic interactions. When applied to data on circulating cell-free DNA, AI has enabled noninvasive cancer detection, prognosis and tumor origin identification. Deep learning has enhanced CRISPR-based gene editing efforts, helping to predict guide-RNA activity and identify anti-CRISPR protein families. Additionally, AI-based analysis of microbial transcriptomic and genomic data has been used to quickly detect antibiotic resistance in pathogens. This advance allows doctors to rapidly select the most effective treatments, potentially reducing mortality and preventing the unnecessary use of broad-spectrum antibiotics.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | - “There are still open questions about exactly how AI assistance affects human performance. For instance, AI assistance has some- times been shown to improve clinical experts’ sensitivity while lowering their specificity, and some studies, both prospective and retrospective, have found that combined AI–human performance could not surpass the performance of AI alone. Furthermore, some clinicians may benefit more from AI assistance than others; studies suggest that less experienced clinicians, such as trainees, benefit more from AI input than their more experienced peers.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | - “Another issue affecting images as well as many other types of medical data is a shortage of the labels required for supervised learning. Labels are often hand-assigned by medical experts, but this approach can prove difficult due to dataset size, time constraints or shortage of expertise. In other cases, labels can be provided by non-expert humans, for example, via crowdsourcing. However, such labels may be less accurate, and crowdsourced labeling projects face complications associated with privacy, as the data must be shared with many labelers. Labels can also be applied by other AI models, as in some weak-supervision setups, but these labels again carry the risk of noise. Currently, the difficulty of obtaining quality labels is a major blockade for supervised learning projects, driving interest in platforms that make labeling more efficient and weakly supervised and unsupervised setups that require less labeling effort.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | - Accountability. Regulatory challenges. Recent work highlights regulatory issues regarding the deployment of AI models for healthcare. Beyond accuracy, regulators can look at a variety of criteria to evaluate models. For example, they may require validation studies showing that AI systems are robust and generalizable across clinical settings and patient populations and ensure that systems protect patient privacy. Additionally, because the usefulness of AI systems can depend heavily on how humans provide input and interpret output, regulators may require testing of human factors and adequate training for the human users of medical AI systems.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | - “The proliferation of AI also raises concerns around accountabil- ity, as it is currently unclear whether developers, regulators, sellers or healthcare providers should be held accountable if a model makes mistakes even after being thoroughly clinically validated. Currently, doctors are held liable when they deviate from the standard of care and patient injury occurs. If doctors are generally skeptical of medical AI, then individual doctors may be adversely influenced to ignore AI recommendations that conflict with standard practice, even if those recommendations may be personalized and beneficial for a specific patient. However, if the standard of care shifts so that doctors routinely use AItools,then there will be a strong medicolegal incentive for doctors to follow AI recommendations.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | 
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 |- "AI can make healthcare more accessible to under- served groups, but it also risks reinforcing existing inequities, because AI models can perpetuate biases lurking in the data. Medical AI systems can fail to generalize to new kinds of data they were not trained on; thus, training on datasets that underrepresent marginalized groups is well known to result in biased systems that underperform on those groups. Systems that explicitly factor race into their predictions are also at risk of perpetuating prejudice, because racial categories are difficult to define and obscure the diversity within racial groups.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 | - "Opportunities also exist in AI–human collaboration, an alternative to the AI-versus-human competitions common in research; we would like to see collaborative setups receive more study, as they may provide better results than either AI or humans alone and are more likely to reflect real medical practice. Despite the potential of the field, major technical and ethical questions remain for medical AI. As these pivotal issues are systematically addressed, the potential of AI to markedly improve the future of medicine may be realized.”
AI in health and medicine
Pranav Rajpurkar, Emma Chen, Oishi Banerjee and Eric J. Topol
NATURE MEDICINE | VOL 28 | January 2022 | 31–38 |
- ”The continued misperception of AI as a replacement for radiologists is much more of a threat than the development and integration of AI into the practice of diagnostic imaging, as our study suggests that it may erode medical student enthusiasm for the field. This has to potential to reduce incoming talent into the field and ultimately result in a “brain drain.” Radiology has always been at the forefront of technology utilization and education in medicine – MRI, CT, and picture archiving and communication systems are just a few examples. Similarly, AI (and associated data science principles) should be integrated into medical education curricula to enable students to take advantage of this technology as well as dispel any incorrect notions about AI's deleterious effects on the field.”
Medical Student Perspectives on the Impact of Artificial Intelligence on the Practice of Medicine
Christian J. Park, Paul H. Yi, Eliot L. Siegel, MD
Current Problems in Diagnostic Radiology,Volume 50, Issue 5, 2021, Pages 614-619, - Quote on AI
- ‘AI is perhaps the most transformational technology of our time, and healthcare is perhaps AI’s most pressing application.’
- Satya Nadella, chief executive officer, Microsoft - Quote on AI
- ‘We think that AI is poised to transform medicine, delivering new, assistive technologies that will empower doctors to better serve their patients. Machine learning has dozens of possible application areas, but healthcare stands out as a remarkable opportunity to benefit people.’
- Google Health - “Healthcare systems around the world face significant challenges in achieving the ‘quadruple aim’ for healthcare: improve population health, improve the patient’s experience of care, enhance caregiver experience and reduce the rising cost of care. Ageing populations, growing burden of chronic diseases and rising costs of healthcare globally are challenging governments, payers, regulators and providers to innovate and transform models of healthcare delivery. Moreover, against a backdrop now catalysed by the global pandemic, healthcare systems find themselves challenged to ‘perform’ (deliver effective, high-quality care) and ‘transform’ care at scale by leveraging real-world data driven insights directly into patient care.”
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - "In particular, cloud computing is enabling the transition of effective and safe AI systems into mainstream healthcare delivery. Cloud computing is providing the computing capacity for the analysis of considerably large amounts of data, at higher speeds and lower costs compared with historic ‘on premises’ infrastructure of healthcare organisations. Indeed, we observe that many technology providers are increasingly seeking to partner with healthcare organisations to drive AI-driven medical innovation enabled by cloud computing and technology-related transformation.”
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - "AI’s strength is in its ability to learn and recognise patterns and relationships from large multidimensional and multimodal datasets; for example, AI systems could translate a patient’s entire medical record into a single number that represents a likely diagnosis. Moreover, AI systems are dynamic and autonomous, learning and adapting as more data become available.”
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - > ’Supervised learning’ leverages labelled data (annotated information); for example, using labelled X-ray images of known tumours to detect tumours in new images.
> ‘Unsupervised learning’ attempts to extract information from data without labels; for example, categorising groups of patients with similar symptoms to identify a common cause.
> ’In reinforcement learning’ RL, computational agents learn by trial and error, or by expert demonstration. The algorithm learns by developing a strategy to maximise rewards. Of note, major breakthroughs in AI in recent years have been based on RL.
> Deep learning (DL) is a class of algorithms that learns by using a large, many-layered collection of connected processes and exposing these processors to a vast set of examples. DL has emerged as the predominant method in AI today driving improvements in areas such as image and speech recognition.
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - > ’Supervised learning’ leverages labelled data (annotated information); for example, using labelled X-ray images of known tumours to detect tumours in new images.
> ‘Unsupervised learning’ attempts to extract information from data without labels; for example, categorising groups of patients with similar symptoms to identify a common cause.
> ’In reinforcement learning’ RL, computational agents learn by trial and error, or by expert demonstration. The algorithm learns by developing a strategy to maximise rewards. Of note, major breakthroughs in AI in recent years have been based on RL.
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - “We hold the view that AI amplifies and augments, rather than replaces, human intelligence. Hence, when building AI systems in healthcare, it is key to not replace the important elements of the human interaction in medicine but to focus it, and improve the efficiency and effectiveness of that interaction. Moreover, AI innovations in healthcare will come through an in-depth, human- centred understanding of the complexity of patient journeys and care pathways.”
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94- “We hold the view that AI amplifies and augments, rather than replaces, human intelligence. Hence, when building AI systems in healthcare, it is key to not replace the important elements of the human interaction in medicine but to focus it, and improve the efficiency and effectiveness of that interaction. Moreover, AI innovations in healthcare will come through an in-depth, human- centred understanding of the complexity of patient journeys and care pathways.”
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - AI today (and in the near future)
Currently, AI systems are not reasoning engines ie cannot reason the same way as human physicians, who can draw upon ‘common sense’ or ‘clinical intuition and experience’. Instead, AI resembles a signal translator, translating patterns from datasets. AI systems today are beginning to be adopted by healthcare organisations to automate time consuming, high volume repetitive tasks. Moreover, there is considerable progress in demonstrating the use of AI in precision diagnostics (eg diabetic retinopathy and radiotherapy planning).
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - AI in the medium term (the next 5–10 years)
In the medium term, we propose that there will be significant progress in the development of powerful algorithms that are efficient (eg require less data to train), able to use unlabelled data, and can combine disparate structured and unstructured data including imaging, electronic health data, multi-omic, behavioural and pharmacological data. In addition, healthcare organisations and medical practices will evolve from being adopters of AI platforms, to becoming co-innovators with technology partners in the development of novel AI systems for precision therapeutics.
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - AI in the long term (>10 years) In the long term, AI systems will become more intelligent, enabling AI healthcare systems achieve a state of precision medicine through AI-augmented healthcare and connected care. Healthcare will shift from the traditional one-size-fits-all form of medicine to a preventative, personalised, data-driven disease management model that achieves improved patient outcomes (improved patient and clinical experiences of care) in a more cost- effective delivery system.
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - Healthcare leaders should consider (as a minimum) these issues when planning to leverage AI for health:
> processes for ethical and responsible access to data: healthcare data is highly sensitive, inconsistent, siloed and not optimised for the purposes of machine learning development, evaluation, implementation and adoption
> access to domain expertise / prior knowledge to make sense and create some of the rules which need to be applied to the datasets (to generate the necessary insight)
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94 - Healthcare leaders should consider (as a minimum) these issues when planning to leverage AI for health:
> access to sufficient computing power to generate decisions in real time, which is being transformed exponentially with the advent of cloud computing
> research into implementation: critically, we must consider, explore and research issues which arise when you take the algorithm and put it in the real world, building ‘trusted’ AI algorithms embedded into appropriate workflows.
Artificial intelligence in healthcare: transforming the practice of medicine
Junaid Bajwa, Usman Munir, Aditya Nori and Bryan Williams
Future Healthcare Journal 2021 Vol 8, No 2: e188–94
- “ML and AI have already begun to impact radiology practices, and it is inevitable that they will revolutionize much of what we do. As this revolution takes place, it will be important for us to try to understand the underpinnings of decisions that were made by (or with the assistance of) ML and AI. Our patients may demand that we have some understanding of these processes before we apply ML and AI to their care. The use of ML and AI algorithms that are capable of introspection may allow us to understand key aspects of how ML and AI decisions were made. Such algorithms may also provide us insight into our own decision-making processes and may help improve aspects of our practice management that are not controlled by ML and AI.”
The Age of Artificial Intelligence: Does “Why” Still Matter?,
Jack Smith, Elliot K. Fishman, Steven P. Rowe
JACR Volume 18, Issue 1, Part A, Pages 87-89, 2021, - “Many people will remain skeptical of any ML and AI algorithm for which the decision-making process is completely opaque. Skepticism can be a good thing, because there are many companies selling snake oil and claiming that algorithms are ML- and AI-driven even when they are not. Fifty years ago, when most advertisement planning models were developed, social scientists were doing much of the heavy lifting. Social scientists knew how to make a small sliver of the population think or do something. Now, computer scien- tists, engineers, and physical scientists like physicists are using new algorithmic techniques and large-scale data to do the same thing.”
The Age of Artificial Intelligence: Does “Why” Still Matter?,
Jack Smith, Elliot K. Fishman, Steven P. Rowe
JACR Volume 18, Issue 1, Part A, Pages 87-89, 2021, - "We still need to make sure that there are no inherent biases in the ML and AI algorithms. We have seen cases in which we fed in certain kinds of information and the machine skewed in one direction. If things that have happened previously are too strongly reinforced, you can inadvertently choke off new possibilities. For example, we ran a campaign for a prominent business school. The campaign became targeted to certain zip codes. Those zip codes happened to be in high-income areas, and many people from them had previously attended the school being advertised. That kind of bias can keep you from reaching out to new people that would bring new ideas. Humans still need to review the output from ML and AI algorithms to monitor for such bias.”
The Age of Artificial Intelligence: Does “Why” Still Matter?,
Jack Smith, Elliot K. Fishman, Steven P. Rowe
JACR Volume 18, Issue 1, Part A, Pages 87-89, 2021,
- “Advances in machine learning and contactless sensors have given rise to ambient intelligence—physical spaces that are sensitive and responsive to the presence of humans. Here we review how this technology could improve our understanding of the metaphorically dark, unobserved spaces of healthcare. In hospital spaces, early applications could soon enable more efficient clinical workflows and improved patient safety in intensive care units and operating rooms. In daily living spaces, ambient intelligence could prolong the independence of older individuals and improve the management of individuals with a chronic disease by understanding everyday behaviour. Similar to other technologies, transformation into clinical applications at scale must overcome challenges such as rigorous clinical validation, appropriate data privacy and model transparency. Thoughtful use of this technology would enable us to understand the complex interplay between the physical environment and health-critical human behaviours.”
Illuminating the dark spaces of healthcare with ambient intelligence
Albert Haque , Arnold Milstein, Li Fei-Fei
Nature 585, 193-202 (2020) - “In 2018, approximately 7.4% of the US population required an overnight hospital stay. In the same year, 17 million admission episodes were reported by the National Health Service (NHS) in the UK. Yet, healthcare workers are often overworked, and hospitals understaffed and resource-limited. We discuss a number of hospital spaces in which ambient intelligence may have an important role in improving the quality of healthcare delivery, the productivity of clinicians, and business operations. These improvements could be of great assistance during healthcare crises, such as pandemics, during which time hospitals encounter a surge of patients.”
Illuminating the dark spaces of healthcare with ambient intelligence
Albert Haque , Arnold Milstein, Li Fei-Fei
Nature 585, 193-202 (2020) - “One promising use case of ambient intelligence in ICUs is the computer-assisted monitoring of patient mobilization. ICU-acquired weaknesses are a common neuromuscular impairment in critically ill patients, potentially leading to a twofold in one-year mortality rate and 30% higher hospital costs . Early patient mobilization could reduce the relative incidence of ICU-acquired weaknesses by 40% . Currently, the standard mobility assessment is through direct, in-person observation, measurement requires a nuanced understanding of patient movements . For example, localized wearable devices can detect pre-ambulation manoeuvres (for example, the costs . increase in one-year mortality rate and 30% higher hospital costs . Early patient although its use is limited by cost impracticality, observer bias and human error . Proper transition from sitting to standing), but are unable to detect external assistance or interactions with the physical space (for example, sitting on chair versus bed) . Contactless, ambient sensors could provide the continuous and nuanced understanding needed to accurately measure patient mobility in ICUs. “
Illuminating the dark spaces of healthcare with ambient intelligence
Albert Haque , Arnold Milstein, Li Fei-Fei
Nature 585, 193-202 (2020) - “Ambient intelligence is an emerging discipline that brings intelligence to our everyday environments and makes those environments sensitive to us. Ambient intelligence (AmI) research builds upon advances in sensors and sensor networks, pervasive computing, and artificial intelligence. Because these contributing fields have experienced tremendous growth in the last few years, AmI research has strengthened and expanded. Because AmI research is maturing, the resulting technologies promise to revolutionarize daily human life by making people’s surroundings flexible and adaptive.”
Ambient intelligence: Technologies, applications, and opportunities
Diane J. Cook a, Juan C. Augusto b,∗, Vikramaditya R. Jakkula
Pervasive and Mobile Computing 5 (2009) 277–298 - “Deep learning and radiomics are two broad categories of artificial intelligence (AI) research that have the potential to facilitate automatic disease detection and to provide quantitative imaging biomarkers for individualized disease assessment. The large volumes of digital data inherent in radiology images make radiology a natural field for AI research. Cinematic Rendering is a recently described post-processing technique that uses sophisticated illumination modeling to achieve more photorealistic images, and these images, in turn, have the potential to aid treatment planning. Here we review these AI and advanced visualization techniques and highlight how they can be used to improve the detection and management of pancreatic cancers.”
Pancreatic Cancer Imaging: A New Look at an Old Problem
Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
Current Problems in Diagnostic Radiology (in press) - “The scope of AI can be specific, performing narrowly defined tasks (narrow AI) such as image interpretation, or more general, applying knowledge and skills in different contexts (general AI) such as making a diagnosis and predicting disease outcome. On the other hand, machine learning can also be designated “supervised”, in which a dataset is provided for the algorithm to evaluate its performance, or “unsupervised”, in which the machine is allowed to extract unknown potential features in developing an algorithm.”
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755. - AI, machine learning, and deep neural network tools can assist medical decision making and management, and have already permeated into at least three different levels: AI-assisted image interpretation; AI-assisted diagnosis; and AI-assisted prediction and prognostication.
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755. 
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755.
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755.- Challenges to AI in Medicine
• access to data • access to data across all populations (unbiased data)
• standards of care (changing the standard of care)
• legal responsibility of AI decision
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755. - “If AI keeps its promise of benefit and it is integrated more into practice, standards of care must require AI use, and traditional forms of therapeutics will be forced to change. We will see a time when all medicine and allied health work as a team with AI. Those who refuse to partner with AI might be replaced by it.”
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755. - "But as AI takes on more autonomous decision making, it might be argued by some doctors that they should not be responsible for that which they cannot control. Similarly, it seems unfair for doctors to be held responsible for an AI decision when they are unable to deduce how and why that decision was made. Such matters are outside the scope of clinicians’ expertise and best dealt with legally as a product liability claim.”
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755. - "Before AI tools can be put into daily use in medicine, data quality and ownership, transparency in governance, trust-building in black box medicine,and legal responsibility for mishaps are some of the hurdles that need to be resolved. Much effort is needed to translate algorithms into problem solving tools in clinical settings and demonstrate improvement in clinical outcomes with saving of resources.”
Artificial intelligence in health care: preparing for the fifth Industrial Revolution
Sung JJ, Stewart CL, Freedman B.
[published online ahead of print, 2020 Sep 6]. Med J Aust. 2020;10.5694/mja2.50755.
- “The emergence of AI has provoked understandable anxiety: If a computer can read a CT as well as a human, never getting tired or needing bathroom breaks, what does the future look like for radiologists? I’ll tell you what it looks like: exciting. Image interpretation is only part of what we radiologists do. If computers can help us perform that activity more accurately and more efficiently, terrific. Computer-enhanced systems, including AI, are tools—a milestone in the evolution of radiology— but they are not doctors.”
Radiology and Technology: Where We’ve Been, Where We’re Going—And Why I Am So Excited
William R. Brody
Radiology: Artificial Intelligence 2020; 2(3):e190205 - “Advanced AI technology has the potential to improve the efficiency and accuracy of medical care, but, as Francis Peabody pointed out in 1927, “The treatment of a disease may be entirely impersonal; the care of a patient must be completely personal.”25 The healing patient-clinician relationship is an essential aspect of health care. Without forethought and planning, the implementation of new technologies might diminish the patient-clinician relationship in the name of efficiency, accuracy, or cost reduction. As such, clinicians, technology developers, administrators, and patient advocates should take steps to maintain the centrality of the healing relationship in medical care as AI technologies are developed and further integrated into the health care system.”
STATE OF THE ART AND SCIENCE
How Will Artificial Intelligence Affect Patient-Clinician Relationships?
Matthew Nagy, Bryan Sisk
AMA J Ethics. 2020;22(5):E395-400 - "Future AI technologies will likely decrease the clinician’s tedious charting responsibilities both before, during, and after the patient encounter. Rather than the clinician spending an inordinate amount of time analyzing data related to a patient’s condition, AI could potentially sift through millions of patient-specific data points and provide a differential diagnosis, prognosis, and treatment options both more quickly and more accurately than clinicians. During the clinical visit, voice recognition technology might eliminate manual note entry into the electronic health record. Similarly, clinicians might be able to order medications or tests verbally while in conversation with the patient, allowing for fewer peripheral tasks and greater attention to the patient’s needs.”
STATE OF THE ART AND SCIENCE
How Will Artificial Intelligence Affect Patient-Clinician Relationships?
Matthew Nagy, Bryan Sisk
AMA J Ethics. 2020;22(5):E395-400
- Objective — To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians.
Conclusions — Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions.
Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies
Myura Nagendran et al.
BMJ 2020;368:m689 doi: 10.1136/bmj.m689 (Published 25 March 2020) - “Deep learning AI is an innovative and fast moving field with the potential to improve clinical outcomes. Financial investment is pouring in, global media coverage is widespread, and in some cases algorithms are already at marketing and public adoption stage. However, at present, many arguably exaggerated claims exist about equivalence with or superiority over clinicians, which presents a risk for patient safety and population health at the societal level, with AI algorithms applied in some cases to millions of patients.”
Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies
Myura Nagendran et al.
BMJ 2020;368:m689 doi: 10.1136/bmj.m689 (Published 25 March 2020) - "Overpromising language could mean that some studies might inadvertently mislead the media and the public, and potentially lead to the provision of inappropriate care that does not align with patients’ best interests. The development of a higher quality and more transparently reported evidence base moving forward will help to avoid hype, diminish research waste, and protect patients.”
Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies
Myura Nagendran et al.
BMJ 2020;368:m689 doi: 10.1136/bmj.m689 (Published 25 March 2020)
- “With all of the allure, hype, fear, and promise of AI as a transformational force in healthcare, we explore the top ten ways AI will impact primary care and the Quadruple Aim for key stakeholders: primary care physi- cians, patients, health systems, and payers.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - “AI-driven predictive modeling with EHR data can now outperform traditional predictive models in forecasting in-hospital mortality, 30-day unplanned readmission, prolonged length of stay, and all of a patient’s final discharge diagnoses.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30- "Nearly one in four Americans own a wearable device that racks vital signs or other health measures.The wearable device market is expected to reach $52 billion by 2022. Primary care physicians may be able to use data from such devices to diagnose or treat disease at earlier stages; however, the data’s sheer volume and incompatibility with current EHRs make this unfeasible without the help of AI.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - "AI-powered algorithms for diagnosing disease is now outperforming physicians in detecting skin cancer, breast cancer, colorectal cancer, brain cancer, and cardiac arrhythmias. In regions with lack of access to specialty care, these tools in the hands of primary care doctors can provide significant benefit to patients.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - “For AI to add the most value and for physicians to embrace it, these innovations should support, not supplant, the patient– physician relationship. Healthcare is fundamentally a social enterprise, powered by committed, caring, and collaborative connections between the humans involved. AI implemented poorly risks pushing humanity to the margins; implemented wisely, AI can free up physicians’ cognitive and emotional space for their patients, even helping them to become better at being human.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - “EHRs were quickly installed without strong evidence to guide their design, implementation, and regulation, and have contributed to a highly transactional model, with care signified by tick boxes, communication by smartphrases, and where screen-time has replaced face-time as he primary act of healthcare. It is no wonder widespread burnout among physicians has resulted.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - “As AI becomes the second great wave of technological innovations to offer power and possibility for modern healthcare, a key question is: will AI augment, rather than subvert, relationships? Or will managing and being managed by AI add yet another technological master and burden to the lives of physicians? The human challenge will be to have the wisdom and willingness to discern AI’s optimal role, and to determine when it strengthens and when it undermines human healing. Ongoing research will be needed to determine the impact of AI in achieving the Quadruple Aim of better care, better health, lower costs, and improved well-being of the workforce.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - “Undivided attention with compassion is the most powerful diagnostic and therapeutic tool physicians can provide their patients. AI will be most effective when it enhances physicians’ ability to focus their full attention on the patient by shifting the physicians’ responsibilities away from transactional tasks toward personalized care that lies at the heart of human healing.”
Ten Ways Artificial Intelligence Will Transform Primary Care
Steven Y. Lin, Megan R. Mahoney, Christine A. Sinsky
J Gen Intern Med 34(8):1626–30 - Ten Ways Artificial Intelligence Will Transform Primary Care
- RISK PREDICTION AND INTERVENTION
- POPULATION HEALTH MANAGEMENT
- MEDICAL ADVICE AND TRIAGE
- RISK-ADJUSTED PANELING AND RESOURCING
- DEVICE INTEGRATION
- DIGITAL HEALTH COACHING - Ten Ways Artificial Intelligence Will Transform Primary Care
- CHART REVIEW AND DOCUMENTATION
- CLINICAL DECISION MAKING
- DIAGNOSTICS
- PRACTICE MANAGEMENT
- Top Discoveries in Medicine 2019
- OBJECTIVE. Although extensive attention has been focused on the enormous potential of artificial intelligence (AI) technology, a major question remains: how should this fundamentally new technology be regulated? The purpose of this article is to provide an overview of the pathways developed by the U.S. Food and Drug Administration to regulate the incorporation of AI in medical imaging.
CONCLUSION. AI is the new wave of innovation in health care. The technology holds promising applications to revolutionize all aspects of medicine.
Concepts in U.S. Food and Drug Administration Regulation of Artificial Intelligence for Medical Imaging Kohli A et al.
AJR 2019; 213:886–888 - “Geoffrey Hinton (Toronto) said “if you work as a radiologist, you’re like the coyote that’s already over the edge of the cliff, but hasn’t yet looked down so doesn’t realise there’s no ground underneath him. People should stop training radiologists now. It’s just completely obvious that within 5 years, deep learning is going to do better than radiologists. We’ve got plenty of radiologists already ”.
What the radiologist should know about artificial intelligence – an ESR white paper
Insights into Imaging (2019) 10:44 https://doi.org/10.1186/s13244-019-0738-2 - “Deep learning is a subset of machine learning and is the basis of most AI tools for image interpretation. Deep learning means that the computer has multiple layers of algorithms interconnected and stratified into hierarchies of importance (like more or less meaningful data). These layers accumulate data from inputs and provide an output that can change step by step once the AI system learns new features from the data. Such multi-layered algorithms form large artificial neural networks.”
What the radiologist should know about artificial intelligence – an ESR white paper
Insights into Imaging (2019) 10:44 https://doi.org/10.1186/s13244-019-0738-2
- “The United States is the global leader in AI radiology publication productivity, accounting for almost half of total radiology AI output. Other countries have increased their productivity. Notably, China has increased its productivity exponentially to close to 20% of all AI publications. The top three most productive radiology subspecialties were neuroradiology, body and chest, and nuclear medicine.”
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3 
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3- ”Of note, China has increased its productivity exponentially, from less than 5% to close to 20% of all AI publications. China’s ability to exponentially increase productivity is likely due to the country’s unique research infrastructure. The availability of large centralized data and rapid implementation across commercial industries have already helped the nation become very productive in AI research in a short period. In addition, Chinese government di- rectives and funding for the advancement of AI have generated an incredible mobilization.”
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3 - “Exponential growth in AI radiology research has occurred worldwide, with the United States leading overall AI research productivity. China has made the second biggest contribution, largely driven by unique research infrastructure ideal for AI research and significant government funding support. The future success of the United States will depend on continued government funding and prioritization of AI radiology research within the research community.”
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3 - ”Exponential growth in AI radiology research has occurred worldwide, with the United States leading overall AI research productivity. China has made the second big- gest contribution, largely driven by unique research infrastructure ideal for AI research and significant government funding support. The future success of the United States will depend on continued government funding and prioritization of AI radiology research within the research community.”
Global Trend in Artificial Intelligence–Based Publications in Radiology From 2000 to 2018
West E et al.
AJR 2019; 213:1–3
- AI and the Future
- Last December, the developers of AlphaZero published their explanation of the process by which the program mastered chess—a process, it turns out, that ignored human chess strategies developed over centuries and classic games from the past. Having been taught the rules of the game, AlphaZero trained itself entirely by self-play and, in less than 24 hours, became the best chess player in the world—better than grand masters and, until then, the most sophisticated chess-playing computer program in the world. It did so by playing like neither a grand master nor a preexisting program. It conceived and executed moves that both humans and human-trained machines found counterintuitive, if not simply wrong. The founder of the company that created AlphaZero called its performance “chess from another dimension” and proof that sophisticated AI “is no longer constrained by the limits of human knowledge.”
The Metamorphosis
HENRY A. KISSINGER,ERIC SCHMIDT,Daniel HUTTENLOCHER
The Atlantic August 2019 - “Google Home and Amazon’s Alexa are digital assistants already installed in millions of homes and designed for daily conversation: They answer queries and offer advice that, especially to children, may seem intelligent, even wise. And they can become a solution to the abiding loneliness of the elderly, many of whom interact with these devices as friends.The more data AI gathers and analyzes, the more precise it becomes, so devices such as these will learn their owners’ preferences and take them into account in shaping their answers. And as they get “smarter,” they will become more intimate companions. As a result, AI could induce humans to feel toward it emotions it is incapable of reciprocating.”
The Metamorphosis
HENRY A. KISSINGER,ERIC SCHMIDT,Daniel HUTTENLOCHER
The Atlantic August 2019 - The three of us differ in the extent to which we are optimists about AI. But we agree that it is changing human knowledge, perception, and reality—and, in so doing, changing the course of human history. We seek to understand it and its consequences, and encourage others across disciplines to do the same.
The Metamorphosis
HENRY A. KISSINGER,ERIC SCHMIDT,Daniel HUTTENLOCHER
The Atlantic August 2019 - “Distinguishing between “data-driven” and “AI-driven” isn’t just semantics. Each term reflects different assets, the former focusing on data and the latter processing ability. Data holds the insights that can enable better decisions; processing is the way to extract those insights and take actions. Humans and AI are both processors, with very different abilities. To understand how best to leverage each its helpful to review our own biological evolution and how decision-making has evolved in industry.”
What AI-Driven Decision Making Looks Like
Eric Colson
Harvard Business Review July 2019 - In response to this new data- rich environment we’ve adapted our workflows. IT departments support the flow of information using machines (databases, distributed file systems, and the like) to reduce the unmanageable volumes of data down to digestible summaries for human consumption. The summaries are then further processed by humans using the tools like spreadsheets, dashboards, and analytics applications. Eventually, the highly processed, and now manageably small, data is presented for decision-making. This is the “data-driven” workflow. Human judgment is still the central processor, but now it uses summarized data as a new input.
What AI-Driven Decision Making Looks Like
Eric Colson
Harvard Business Review July 2019 - “We need to evolve further,and bring AI into the workflow as a primary processor of data. For routine decisions that only rely on structured data, we’re better off delegating decisions to AI. AI is less prone to human’s cognitive bias. (There is a very real risk of using biased data that may cause AI to find specious relationships that are unfair. Be sure to understand how the data is generated in addition to how it is used.) AI can be trained to find segments in the population that best explain variance at fine-grain levels even if they are unintuitive to our human perceptions. AI has no problem dealing with thousands or even millions of groupings. And AI is more than comfortable working with nonlinear relationships, be they exponential, power laws, geometric series, binomial distributions, or otherwise.”
What AI-Driven Decision Making Looks Like
Eric Colson
Harvard Business Review July 2019 - “They key is that humans are not interfacing directly with data but rather with the possibilities produced by AI’s processing of the data. Values, strategy and culture is our way to reconcile our decisions with objective rationality. This is best done explicitly and fully informed. By leveraging both AI and humans we can make better decisions that using either one alone.”
What AI-Driven Decision Making Looks Like
Eric Colson
Harvard Business Review July 2019 - “This evolution is unlikely to occur within the individual organization, just as evolution by natural selection does not take place within individuals. Rather, it’s a selection process that operates on a population. The more efficient organizations will survive at higher rate. Since it’s hard to for mature companies to adapt to changes in the environment, I suspect we’ll see the emergence of new companies that embrace both AI and human contributions from the beginning and build them natively into their workflows.”
What AI-Driven Decision Making Looks Like
Eric Colson
Harvard Business Review July 2019 - “In radiology, for instance, some algorithms have performed image-bases diagnosis as well as or better than human experts. Yet it’s unclear if patients and medical institutions will trust AI to automate that job entirely. A University of California at San Diego pilot in which AI successfully diagnosed childhood diseases more accurately than junior-level pediatricians still required senior doctors to personally review and sign off on the diagnosis. The real aim is always going to be to use AI to collaborate with clinicians seeking higher precision — not try to replace them.”
The Health Care Benefits of Combining Wearables and AI
Moni Miyashita and Michael Brady
Harvard Business Review May 2019
- “Despite broad awareness of these trends, medical education continues to be largely information based, as if physicians are still the only source of medical knowledge. The reality of this web-enabled era is different. Patients readily garner more information, both correct and incorrect, to bring to clinical encounters and expect meaningful discussions with their physicians. These expectations challenge physicians not only to keep current but also to be able to communicate options to patients in a language that speaks meaningfully to their individual concerns and preferences.”
Reimagining Medical Education in the Age of AI
Steven A. Wartman, and C. Donald Combs
AMA Journal of Ethics February 2019, Volume 21, Number 2: E146-152 - In addition, the skills required of practicing physicians will increasingly involve facility in collaborating with and managing artificial intelligence (AI) applications that aggregate vast amounts of data, generate diagnostic and treatment recommendations, and assign confidence ratings to those recommendations. The ability to correctly interpret probabilities requires mathematical sophistication in stochastic processes, something current medical curricula address inadequately. In part, the need for more sophisticated mathematical understanding is driven by the analytics of precision and personalized medicine, which rely on AI to predict which treatment will work for a particular disease in a particular subgroup of patients.
Reimagining Medical Education in the Age of AI
Steven A. Wartman, and C. Donald Combs
AMA Journal of Ethics February 2019, Volume 21, Number 2: E146-152 - “As we pointed out earlier, the increasing incongruence between the organizing and retention capacities of the human mind and medicine’s growing complexity should compel significant re-engineering of medical school curricula. Curricula should shift from a focus on information acquisition to an emphasis on knowledge management and communication. Nothing manifests this need for change better than the observation that every patient is becoming a big data challenge. For clinicians, the need to understand probabilities—such as confidence ratings for diagnostic or therapeutic recommendations generated by an AI clinical decision support system—will likely increase as personalized medicine continues to enlarge its role in practice.”
Reimagining Medical Education in the Age of AI
Steven A. Wartman, and C. Donald Combs
AMA Journal of Ethics February 2019, Volume 21, Number 2: E146-152 - Accordingly, we advocate new curricula that respond to the challenges of AI while being less detrimental to learners’ mental health. These curricula should emphasize 4 major features: Knowledge capture, not knowledge retention; Collaboration with and management of AI applications; A better understanding of probabilities and how to apply them meaningfully in clinical decision making with patients and families; and The cultivation of empathy and compassion.
Reimagining Medical Education in the Age of AI
Steven A. Wartman, and C. Donald Combs
AMA Journal of Ethics February 2019, Volume 21, Number 2: E146-152 - * Knowledge capture, not knowledge retention
* Collaboration with and management of AI applications
* A better understanding of probabilities and how to apply them meaningfully in clinical decision making with patients and families; and
* The cultivation of empathy and compassion.
Reimagining Medical Education in the Age of AI
Steven A. Wartman, and C. Donald Combs
AMA Journal of Ethics February 2019, Volume 21, Number 2: E146-152
- The Role of AI in the Diagnosis and Management of PDAC (2025)
- Early detection of pancreatic cancer (FELIX)
- Define the best management plan for the patient and the sequence (Surgery, Chemotherapy, Immunology, Radiation Therapy)
- Predict ultimate survival for the patient based on a variable set of parameters - “Not surprisingly, though, as AI supercharges business and society, CEOs are under the spotlight to ensure their company’s responsible use of AI systems beyond complying with the spirit and letter of applicable laws. Ethical debates are well underway about what’s “right” and “wrong” when it comes to high-stakes AI applications such as autonomous weapons and surveillance systems. And there’s an outpouring of concern and skepticism regarding how we can imbue AI systems with human ethical judgment, when moral values frequently vary by culture and can be difficult to code in software.”
Leading your organization to responsible AI
Roger Burkhardt, Nicolas Hohn, and Chris Wigley
McKinsey & Company (May 2019) - “AI development always involves trade-offs. For instance, when it comes to model development, there is often a perceived trade-off between the accuracy of an algorithm and the transparency of its decision making, or how easily predictions can be explained to stakeholders. Too great a focus on accuracy can lead to the creation of “black box” algorithms in which no one can say for certain why an AI system made the recommendation it did. Likewise, the more data that models can analyze, the more accurate the predictions, but also, often, the greater the privacy concerns.”
Leading your organization to responsible AI
Roger Burkhardt, Nicolas Hohn, and Chris Wigley
McKinsey & Company (May 2019) - “Data serve as the fuel for AI. In general, the more data used to train systems, the more accurate and insightful the predictions. However, pressure on analytics teams to innovate can lead to the use of third-party data or the repurposing of existing customer data in ways that, while not yet covered by regulations, are considered inappropriate by consumers. For example, a healthcare provider might buy data about its patients—such as what restaurants they frequent or how much TV they watch—from data brokers to help doctors better assess each patient’s health risk.”
Leading your organization to responsible AI
Roger Burkhardt, Nicolas Hohn, and Chris Wigley
McKinsey & Company (May 2019)
- The use of artificial intelligence, and the deep-learning subtype in particular, has been enabled by the use of labeled big data, along with markedly enhanced computing power and cloud storage, across all sectors. In medicine, this is beginning to have an impact at three levels: for clinicians, predominantly via rapid, accurate image interpretation; for health systems, by improving workflow and the potential for reducing medical errors; and for patients, by enabling them to process their own data to promote health. The current limitations, including bias, privacy and security, and lack of transparency, along with the future directions of these applications will be discussed in this article. Over time, marked improvements in accuracy, productivity, and workflow will likely be actualized, but whether that will be used to improve the patient–doctor relationship or facilitate its erosion remains to be seen.
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | - The use of artificial intelligence, and the deep-learning subtype in particular, has been enabled by the use of labeled big data, along with markedly enhanced computing power and cloud storage, across all sectors. In medicine, this is beginning to have an impact at three levels: for clinicians, predominantly via rapid, accurate image interpretation; for health systems, by improving workflow and the potential for reducing medical errors; and for patients, by enabling them to process their own data to promote health. The current limitations, including bias, privacy and security, and lack of transparency, along with the future directions of these applications will be discussed in this article.
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | - The second is the generation of data in massive quantities, from sources such as high-resolution medical imaging, biosensors with continuous output of physiologic metrics, genome sequenc- ing, and electronic medical records. The limits on analysis of such data by humans alone have clearly been exceeded, necessitating an increased reliance on machines. Accordingly, at the same time that there is more dependence than ever on humans to provide healthcare, algorithms are desperately needed to help.
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | - “Similarly, DNNs have been applied across a wide variety of medical scans, including bone films for fractures and estimation of aging, classification of tuberculosis, and vertebral compression fractures; computed tomography scans for lung nodule, liver masses, pancreatic cancer, and coronary calcium score; brain scans for evidence of hemorrhage, head trauma, and acute referrals; magnetic resonance imaging; echocardiograms; and mammographies. “
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | - “Similarly, DNNs have been applied across a wide variety of medical scans, including bone films for fractures and estimation of aging, classification of tuberculosis, and vertebral compression fractures; computed tomography scans for lung nodule, liver masses, pancreatic cancer, and coronary calcium score; brain scans for evidence of hemorrhage, head trauma, and acute referrals; magnetic resonance imaging; echocardiograms; and mammographies.”
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | - “Furthermore, the lack of large datasets of carefully annotated images has been limiting across various disciplines in medicine. Ironically, to compensate for this deficiency, generative adversarial networks have been used to synthetically produce large image datasets at high resolution, including mammograms, skin lesions, echocardiograms, and brain and retina scans, that could be used to help train DNNs.”
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 | 
High-performance medicine: the convergence of human and artificial intelligence
Eric J. Topol
NATURE MEDICINE | VOL 25 | January 2019 | 44–56 |
Harvard Business Review Jan-Feb 2018
- In 2013 the MD Anderson Cancer Center launched a “moon shot” project: diagnose and recommend treatment plans for certain forms of cancer using IBM’s Watson cognitive system. But in 2017, the project was put on hold after costs topped $62 million—and the system had yet to be used on patients.
- Determining the use cases
The second area of assessment evaluates the use cases in which cognitive applications would generate substantial value and contribute to business success. Start by asking key questions such as: How critical to your overall strategy is addressing the targeted problem? How difficult would it be to implement the proposed AI solution—both technically and organizationally? Would the benefits from launching the application be worth the effort? Next, prioritize the use cases according to which offer the most short- and long-term value, and which might ultimately be integrated into a broader platform or suite of cognitive capabilities to create competitive advantage.
- Artificial Intelligence in Practice (AI): Applications
- Congestive heart failure
- Alzheimer's disease
- Pneumonia
- Lung nodule evaluation
- Wrist fractures
- Pancreatic cancer - Artificial Intelligence in Practice (AI): Applications
- Plain x-ray
- Ultrasound
- CT
- MRI
- PET/CT - “Although elegant, Lakhani and Sundaram have a software result, not a hardware result. In most software research, the only individuals with the algorithm are the researchers. Without the AI algorithm, the results cannot be reproduced. Many AI publications are transient—they are proof-of-concept; they cannot be validated. As a radiologist, you cannot implement the AI research in your clinical practice without the algorithm, and the algorithms are largely discarded. In this setting, there is near zero chance that practice guidelines will be changed.”
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021 - New AI research in radiology is amazing. Our dis- cipline has tried for 30 or more years for computers to help us analyze our images. Prior non-AI approaches have mostly not succeeded. In my research lab, technologists and pre- and postdoctoral students analyzed thousands of cardiac MRI cases by drawing circles at the borders of the heart for the last 20 years. Yet in 6 months or less, AI neural networks are now trained to draw those circles better and more consistently than any of our prior efforts. My reaction to seeing new AI developments is equivalent to “shock and awe.”
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021 - “Our first policy affecting AI research is regarding pre-print servers, such as arXiv.org. AI researchers frequently put their latest algorithms on arXiv to claim "I’m first" supremacy. arXiv publications are not peer reviewed. They do however look like normal publications—especially to laypersons. Preprint servers are used by AI researchers to rapidly share software, algorithms, and ideas.”
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021 - The policy of Radiology is to discourage authors from placing their results on preprint servers. There are two reasons for this. First, if the results are already avail- able, the incremental benefit of publication in Radiology is low. Second, the vast majority of submissions for publication undergo substantial changes due to peer review and editorial processes.
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021 - “Our second policy affecting AI research is to strongly encourage making the computer algorithms available to other researchers. Authors of AI research should make a git archive of their source code or make it available on the author’s web page. Git archive providers such as GitHub, Bitbucket, or Source Forge are already available and in use by some research- ers. Authors should place a link to the web page for their code in their Materials and Methods section. They should also provide a unique identifier for the revision of the code used in the publication.”
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021 - When AI truly succeeds in medical imaging, we will stop calling it AI. The AI portions will simply be integrated tools in our PACS, scanner, or workstation—not separate features.
Editor’s Note: Publication of AI Research in Radiology
Bluemke DA
Radiology 2018 (in press)
https://doi.org/10.1148/radiol.2018184021
- "Artificial neural networks are inspired by the ability of brains to learn complicated patterns in data by changing the strengths of synaptic connections between neurons. Deep learning uses deep networks with many intermediate layers of artificial "neurons" between the input and the output, and, like the visual cortex, these artificial neurons learn a hierarchy of progressively more complex feature detectors. By learning feature detectors that are optimized for classification, deep learning can substantially outperform systems that rely on features supplied by domain experts or that are designed by hand."
Deep Learning—A Technology With the Potential to Transform Health Care
Geoffrey Hinton
published online August 30, 2018]. JAMA. doi:10.1001/jama .2018.11100 - "Understandably, clinicians, scientists, patients, and regulators would all prefer to have a simple explanation for how a neural net arrives at its classification of a particular case. In the example of predicting whether a patient has a disease, they would like to know what hidden factors the network is using. However, when a deep neural network is trained to make predictions on a big data set, it typically uses its layers of learned, nonlinear features to model a huge number of complicated but weak regularities in the data. It is generally infeasible to interpret these features because their meaning depends on complex interactions with uninterpreted features in other layers."
Deep Learning—A Technology With the Potential to Transform Health Care
Geoffrey Hinton
published online August 30, 2018]. JAMA. doi:10.1001/jama .2018.11100 - As data sets get bigger and computers become more powerful, the results achieved by deep learning will get better, even with no improvement in the basic learning techniques, although these techniques are being improved. The neural networks in the human brain learn from fewer data and develop a deeper, more abstract understanding of the world. In contrast to machine-learning algorithms that rely on provision of large amounts of labeled data, human cognition can find structure in unlabeled data, a process commonly termed unsupervised learning.
Deep Learning—A Technology With the Potential to Transform Health Care
Geoffrey Hinton
published online August 30, 2018]. JAMA. doi:10.1001/jama .2018.11100 - "The creation of a smorgasbord of complex feature detectors based on unlabeled data appears to set the stage for humans to learn a classifier from only a small amount of labeled data. How the brain does this is still a mystery, but will not remain so. As new unsupervised learning algorithms are discovered, the data efficiency of deep learning will be greatly augmented in the years ahead, and its potential applications in health care and other fields will increase rapidly."
Deep Learning—A Technology With the Potential to Transform Health Care
Geoffrey Hinton
published online August 30, 2018]. JAMA. doi:10.1001/jama .2018.11100 - "In 1976, Maxmen predicted that artificial intelligence (AI) in the 21st century would usher in "the post-physician era," with health care provided by paramedics and computers. Today, the mass extinction of physicians remains unlikely. However, as outlined by Hinton2 in a related Viewpoint, the emergence of a radically different approach to AI, called deep learning, has the potential to effect major changes in clinical medicine and health care delivery."
On the prospects for a (deep) learning health care system
NaylorCD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - "Deep learning had intuitive appeal for health- related applications, given its demonstrable strengths in intricate pattern recognition and predictive model building from big high-dimensional data sets. These analytic capabilities have already proven useful for basic and applied researchers, ranging across health disciplines. Thus far, clinical application of deep learning has been most rapid in image-intensive fields such as radiology, radiotherapy, pathology, ophthalmology, dermatology, and image-guided surgery."
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - "In many cases, interpretation of images by deep learning systems has outperformed that by individual clinicians when measured against a consensus of expert readers or gold standards such as pathologic findings. Clinically relevant applications have widened beyond image processing to include risk stratification for a broad range of patient populations (eBox in the Supplement), and health care organizations are capitalizing on deep learning and other machine-learning tools to improve logistics, quality management, and financial oversight. "
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - "Digital imaging in all its forms is becoming more powerful and more integral to medicine and health care. Unlike deep learning, expert human interpretation fails to capitalize on all the patterns, or "regularities," that can be extracted from very large data sets and used for interpretation of still and moving images. Deep learning and related machine- learning methods can also learn from massively greater numbers of images than any human expert, continue learning and adapting over time, mitigate interobserver variability, and facilitate better decision making and more effective image-guided therapy."
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - Deep learning shows promise for streamlining routine work by health care professionals and empowering patients, thereby promoting a safer, more humane, and participatory paradigm for health care. Different sources offer varying estimates of the amount of time wasted by health care professionals on tasks amenable to some automation (eg, high-quality image screening) that could then be rededicated to more or better care. A growing number of research studies also suggest specific possibilities for reduction in errors and improved work flow in the clinical setting with appropriate deployment of AI.
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - Deep learning has enormous capacity to inform the process of discovery in health research and to facilitate hypothesis generation by identifying novel associations. Established and start-up companies are using deep learning to select or design novel molecules for testing as pharmaceuticals or biologics, with in silico exploration preceding in vitro examination and in vivo experimentation. Researchers across disciplines have also found unexpected clusters within data sets by comparing the intensity of activation of feature detectors in the hidden layers of deep neural nets. As always, however, basic and clinical experimentation remains essential to establish causation and causal pathways.
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - "In the longer term, deep learning can relate those personalized features to the clinical course of similar patients, using data from millions of patient records containing billions of medical events. Thus, while concerns are understandably raised that automation could de- humanize clinical care, these advances could provide professionals and patients alike with vastly better and more specific information, and, as Fogel and Kvedar argue, give physicians more time "to focus on the tasks that are uniquely human: building relationships, exercising empathy, and using human judgment to guide and advise."
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - Deep learning is diffusing rapidly through a combination of open- source and proprietary programs. Technology giants are making massive investments in the development of software libraries for deep learning, some of which are open sourced. These huge enterprises, as well as start-ups, are applying deep learning tools to health care all over the world. Moreover, many academic and nonprofit teams are publishing and sharing algorithms freely, and local development is now widespread.
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103 - However, unlike a standardized diagnostic test or drug, the performance of deep learning and other machine-learning methods improves with exposure to larger or more relevant data sets, or with easily made modifications to the architecture of the models or training procedures. Regulators and technology assessors will need to distinguish issues inherent in decision-support algorithms from those attributable to misuse by clinical decision makers. Procurement agencies and health care administrators will need to be uncharacteristically nimble to keep up..
On the prospects for a (deep) learning health care system
Naylor CD
[published online August 30, 2018]. JAMA. doi:10.1001/jama.2018.11103
Deep Learning Approach for Evaluating Knee MR Images: Achieving High Diagnostic Performance for Cartilage Lesion Detection
FangLiu et al.
Radiology 2018 (in press)
- "By now, it’s almost old news: big data will transform medicine. It’s essential to remember, however, that data by themselves are useless. To be useful, data must be analyzed, interpreted, and acted on. Thus, it is algorithms —
not data sets — that will prove transformative."
Predicting the Future — Big Data, Machine Learning, and Clinical Medicine
Obermeyer Z, Emanuel EJ
N Engl J Med 375;13 September 29, 2016
- “But where machine learning shines is in handling enormous numbers of predictors — sometimes, remarkably, more predictors than observations — and combining them in nonlinear and highly interactive ways.This capacity al- lows us to use new kinds of data, whose sheer volume or complexity would previously have made analyzing them unimaginable.”
Predicting the Future — Big Data, Machine Learning, and Clinical Medicine Obermeyer Z, Emanuel EJ N Engl J Med 375;13 September 29, 2016 - “Another key issue is the quantity and quality of input data. Machine learning algorithms are highly data hungry, often re- quiring millions of observations to reach acceptable performance levels.In addition, biases in data collection can substantially affect both performance and generalizability. Lactate might be a good predictor of the risk of death, for example, but only a small, nonrepresentative sample of patients have their lactate levels checked.”
Predicting the Future — Big Data, Machine Learning, and Clinical Medicine Obermeyer Z, Emanuel EJ N Engl J Med 375;13 September 29, 2016 - “Machine learning has become ubiquitous and indispensable for solving complex problems in most sciences. In astronomy, algorithms sift through millions of images from telescope surveys to classify galaxies and find supernovas.”
Predicting the Future — Big Data, Machine Learning, and Clinical Medicine Obermeyer Z, Emanuel EJ N Engl J Med 375;13 September 29, 2016 - “Increasingly, the ability to transform data into knowledge will disrupt at least three areas of medicine. First, machine learning will dramatically improve the ability of health professionals to es- tablish a prognosis. Current prognostic models (e.g., the Acute Physiology and Chronic Health Evaluation [APACHE] score and the Sequential Organ Failure Assessment [SOFA] score) are restricted to only a handful of vari- ables, because humans must enter and tally the scores. But data could instead be drawn directly from EHRs or claims databases, allow- ing models to use thousands of rich predictor variables.”
Predicting the Future — Big Data, Machine Learning, and Clinical Medicine Obermeyer Z, Emanuel EJ N Engl J Med 375;13 September 29, 2016
Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology An Tang et al. Canadian Association of Radiologists Journal 69 (2018) 120e135
Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology An Tang et al. Canadian Association of Radiologists Journal 69 (2018) 120e135- “One of the first and most significant hurdles to getting a CPT code is the need for peer-reviewed research in the United States that demonstrates both the efficacy and safety of the procedure. The second hurdle is the need for the procedure to be widely performed by a large number of physicians in the United States. These two requirements will prevent many AI software programs from achieving a CPT code. But, let us presume that at least one AI tool makes the cut and gets a CPT code. It will then have to be valued by the Relative Value Scale Update Committee (RUC) to get assigned RVUs.”
Artificial Intelligence: Who Pays and How? Schoppe, Kurt Journal of the American College of Radiology (in press) - “The RUC values the professional component of a medical procedure based upon the work of a physician. The primary components of physi- cian work include the time it takes to perform the service, the level of technical skill required, and the mental effort and judgment necessary. For most AI tools I have seen, there is minimal to no physician work. Some AI processes run in the background and “prioritize” CT scans based on characteristics that may indicate an emergent finding. There is no physician work in this. Some AI processes may highlight specific imaging findings for the radiologist. This type of operation would be considered similar to computer-aided detection, and so would be valued similarly to prior CPT codes for computer-aided detection used in chest radiographs or mammography, though much of this work is either unreimbursed or bundled into the actual diagnostic procedure (eg, mammography and breast MRI).”
Artificial Intelligence: Who Pays and How? Schoppe, Kurt Journal of the American College of Radiology (in press) - “My opinion is that neither the government nor private payers will reimburse physicians and hospitals for using AI-driven software products. I believe that we will all purchase AI tools and treat them as an unreimbursed business expense. We will invest in AI software to ensure we are delivering high- quality work, to increase our efficiency, and to simplify clerical type tasks. In this way, paying for AI tools will merely be a cost of doing business like other operational expenses we incur.”
Artificial Intelligence: Who Pays and How? Schoppe, Kurt Journal of the American College of Radiology (in press)
- ”Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology’s contribution to patient care and population health, and will revolutionize radiologists’ workflows.”
Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology An Tang et al. Canadian Association of Radiologists Journal 69 (2018) 120e135
- “In conclusion, with the current fast pace in development of machine learning techniques, and deep learning in particular, there is prospect for a more widespread clinical adoption of machine learning in radiology practice. Machine learning and artificial intelligence are not expected to replace the radiologists in the foreseeable future. ese techniques can potentially facilitate radiology work ow, increase radiologist productivity, improve detection and interpretation of findings, reduce the chance of error, and enhance patient care and satisfaction.”
Current Applications and Future Impact of Machine Learning in Radiology Garry Choy et al. Radiology 2018; 00:1–11
- “Radiomics is a process designed to extract a large number of quantitative features from radiology images . Radiomics is an emerging field for machine learning that allows for conversion of radiologic images into mineable high-dimensional data. For instance, Zhang et al evaluated over 970 radiomics features extracted from MR images by using machine learning methods and correlated with features to predict local and distant treatment failure of advanced nasopharyngeal carcinoma.”
Current Applications and Future Impact of Machine Learning in Radiology Garry Choy et al. Radiology 2018; 00:1–11
- “Machine learning approaches to the interrogation of a wide spectrum of such data (sociodemographic, imaging, clinical, laboratory, and genetic) has the potential to further personalize health care, far beyond what would be possible through imaging applications alone. Precision medicine require the use of novel computational techniques to harness the vast amounts of data required to discover individualized disease factors and treatment decisions.”
Current Applications and Future Impact of Machine Learning in Radiology Garry Choy et al. Radiology 2018; 00:1–11
- AI in Healthcare
- AI in Healthcare
- “Deep learning is a type of representation learning in which the algorithm learns a composition of features that re ect a hierarchy of structures in the data. Complex representations are expressed in terms of simpler representations.”
Deep Learning: A Primer for Radiologists.”
Chartrand G et al. RadioGraphics 2017; 37:2113–2131 - “Although neural networks have been used for decades, in re- cent years three key factors have enabled the training of large neural networks: (a) the availability of large quantities of la- beled data, (b) inexpensive and powerful parallel computing hardware, and (c) improvements in training techniques and architectures.”
Deep Learning: A Primer for Radiologists.”
Chartrand G et al. RadioGraphics 2017; 37:2113–2131 - “Deep CNNs exploit the compositional structure of natural images so that shifts and deformations of objects in the images do not significantly affect the overall performance of the network.”
Deep Learning: A Primer for Radiologists.”
Chartrand G et al. RadioGraphics 2017; 37:2113–2131 - “The creation of these large databases of labeled medical images and many associated challenges will be fundamental to foster future research in deep learning applied to medical images.”
Deep Learning: A Primer for Radiologists.”
Chartrand G et al. RadioGraphics 2017; 37:2113–2131
