The DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
Artificial Intelligence and the Implementation Challenge
Open accessPublished version of a preprint
Abstract
BACKGROUND: Applications of artificial intelligence (AI) in health care have garnered much attention in recent years, but the implementation issues posed by AI have not been substantially addressed. OBJECTIVE: In this paper, we have focused on machine learning (ML) as a form of AI and have provided a framework for thinking about use cases of ML in health care. We have structured our discussion of challenges in the implementation of ML in comparison with other technologies using the framework of Nonadoption, Abandonment, and Challenges to the Scale-Up, Spread, and Sustainability of Health and Care Technologies (NASSS). METHODS: After providing an overview of AI technology, we describe use cases of ML as falling into the categories of decision support and automation. We suggest these use cases apply to clinical, operational, and epidemiological tasks and that the primary function of ML in health care in the near term will be decision support. We then outline unique implementation issues posed by ML initiatives in the categories addressed by the NASSS framework, specifically including meaningful decision support, explainability, privacy, consent, algorithmic bias, security, scalability, the role of corporations, and the changing nature of health care work. RESULTS: Ultimately, we suggest that the future of ML in health care remains positive but uncertain, as support from patients, the public, and a wide range of health care stakeholders is necessary to enable its meaningful implementation. CONCLUSIONS: If the implementation science community is to facilitate the adoption of ML in ways that stand to generate widespread benefits, the issues raised in this paper will require substantial attention in the coming years.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, health care has seen slow success in the implementation of AI use cases.”
From Barriers to and facilitators of artificial intelligence adoption in health care: scoping review (2024) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Clinicians expressed the need to understand both the scientific and clinical bases of the recommendations provided by the AI to confidently validate and apply the decision [19,20,36-38].”
From Barriers to and facilitators of artificial intelligence adoption in health care: scoping review (2024) · cites this paper as [20]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“However, successful utility requires successful adoption, and a number of studies have reported on the challenges encountered with implementing AI in health care [19-21].”
From Barriers to and facilitators of artificial intelligence adoption in health care: scoping review (2024) · cites this paper as [20]
In the citing paper
“Shaw et al. (2019) contend that decision support in health care can be useful only if its outputs are able to integrate with the human decision-making processes at the heart of health service delivery.”
From SHIFTing artificial intelligence to be responsible in healthcare: a systematic review (2022) · cites this paper as Shaw et al., 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Damschroder, L. J., Aron, D. C., Keith, R. E., Kirsh, S. R., Alexander, J. A., & Lowery, J. C. (2009) · Implementation Science · doi:10.1186/1748-5908-4-50 · Cited by 14,496 · cited 2×
“The value proposition of digital technology might be different for different stakeholder groups, and implementation frameworks direct attention to the implications of newly introduced technologies for patients, health care providers, managers, health policymakers, and others [8,25,26].”
BackgroundMethodDermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 1×
“Often, ML involves supervised methods that categorize data points, for example, as images of skin cancer or otherwise given datasets in which all data points (or at least a substantial subset) are associated with a label, ordinal, or category that is meant to be predicted or inferred [15].”
BackgroundNorth, D. C. (1991) · Journal of Economic Perspectives · doi:10.1257/jep.5.1.97 · Cited by 5,232
Artificial intelligence in healthcare: past, present and future
Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2017) · Stroke and Vascular Neurology · doi:10.1136/svn-2017-000101 · Cited by 4,837 · cited 1×
“We agree with a growing chorus of health care providers and researchers who suggest that ML will primarily serve to augment as opposed to replace the work of humans in the provision of health care in the near term [31], despite applications of automation in health care.”
BackgroundThe ethics of algorithms: Mapping the debate
Mittelstadt, B. D., Allo, P., Taddeo, M., Wachter, S., & Floridi, L. (2016) · Big Data & Society · doi:10.1177/2053951716679679 · Cited by 4,567 · cited 1×
“In cases where training data are partial or incomplete or only reflect a subset of a given population, the resulting model will only be relevant to the population of people represented in the dataset [47].”
BackgroundMaking sense of implementation theories, models and frameworks
Nilsen, P. (2015) · Implementation Science · doi:10.1186/s13012-015-0242-0 · Cited by 4,447 · cited 2×
“We have described use cases (and attendant value propositions) of ML in health care as more likely relating to decision support and less likely to automation, which begins to illustrate the implementation object of focus in ML initiatives [6,7].”
BackgroundMethodEvidence-Based Medicine: A New Approach to Teaching the Practice of Medicine
Guyatt, G. (1992) · JAMA · doi:10.1001/jama.1992.03490170092032 · Cited by 4,202
Machine Learning Applications in Cancer Prognosis and Prediction
Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., & Fotiadis, D. I. (2015) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2014.11.005 · Cited by 3,338 · cited 1×
“Given these labels and the statistical models they help to train, ML can be very effective at determining the category in which any newly available individual data point belongs, thereby being useful in the effort to, for example, identify malignant cancers based on particular images [16].”
BackgroundBig other: Surveillance Capitalism and the Prospects of an Information Civilization
Zuboff, S. (2015) · Journal of Information Technology · doi:10.1057/jit.2015.5 · Cited by 3,205 · cited 1×
“As the innovations enabled by ML have taken on a more powerful role in driving global economies, corporations have strategically sought to acquire larger amounts of more diverse data to boost their capacity to develop ML algorithms [61].”
BackgroundInstitutions and Organizations: Ideas, Interests, and Identities
Scott, W. R. (2007) · Cited by 2,943
Greenhalgh, T., Wherton, J., Papoutsi, C., Lynch, J., Hughes, G., A'Court, C., Hinder, S., Fahy, N., Procter, R., & Shaw, S. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.8775 · Cited by 2,887 · cited 7×
“The NASSS framework and other work in implementation science for digital health technologies emphasize the importance of attending to the particular value proposition that a new technology offers for health care stakeholders [8,9].”
BackgroundMethodInfluential2 How Actors Change Institutions: Towards a Theory of Institutional Entrepreneurship
Battilana, J., Leca, B. L., & Boxenbaum, E. (2009) · Academy of Management Annals · doi:10.1080/19416520903053598 · Cited by 2,598 · cited 1×
“The social sciences have worked to provide clear definitions of institutions through decades of research and theory [63-65].”
BackgroundEvidence based medicine: a movement in crisis?
Greenhalgh, T., Howick, J., Maskrey, N., & for the Evidence Based Medicine Renaissance Group (2014) · BMJ · doi:10.1136/bmj.g3725 · Cited by 1,766
Disease Prediction by Machine Learning Over Big Data From Healthcare Communities
Chen, M., Hao, Y., Hwang, K., Wang, L., & Wang, L. (2017) · IEEE Access · doi:10.1109/access.2017.2694446 · Cited by 1,311 · cited 1×
“Warning systems for disease outbreak [22] Identifying potential staff scheduling changes related to forecasted emergency room volumes [21] Producing a more accurate prediction of the likely outcome of a particular intervention [20] Decision support N/A d Use of robotics for operational tasks in…”
BackgroundSamek, W., Wiegand, T., & Müller, K.-R. (2017) · arXiv · doi:10.48550/arxiv.1708.08296 · Cited by 1,080
What every teacher needs to know about clinical reasoning
Eva, K. W. (2005) · Medical Education · doi:10.1111/j.1365-2929.2004.01972.x · Cited by 930 · cited 1×
“This example also pertains only to binary queries specifically about whether a patient has a single disease, which is different from the typical reasoning processes involved in differential diagnosis among clinicians, where multiple confounding, interdependent outcomes must be considered [13,14].”
BackgroundMachine learning in medicine: Addressing ethical challenges
Vayena, E., Blasimme, A., & Cohen, I. G. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002689 · Cited by 912 · cited 2×
“This point raises the overarching issue of the extent of automation that is possible through applications of ML, linked to speculation about whether ML will mostly augment or actually replace health care providers’ work [1,30].”
BackgroundHeath, D. R. (2019) · Journal of Information Technology Case and Application Research · doi:10.1080/15228053.2019.1673511 · Cited by 901
Chaudoir, S. R., Dugan, A. G., & Barr, C. H. (2013) · Implementation Science · doi:10.1186/1748-5908-8-22 · Cited by 800 · cited 1×
“The value proposition of digital technology might be different for different stakeholder groups, and implementation frameworks direct attention to the implications of newly introduced technologies for patients, health care providers, managers, health policymakers, and others [8,25,26].”
BackgroundCross-trial prediction of treatment outcome in depression: a machine learning approach
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., Cannon, T. D., Krystal, J. H., & Corlett, P. R. (2016) · The Lancet Psychiatry · doi:10.1016/s2215-0366(15)00471-x · Cited by 676 · cited 1×
“…changes related to forecasted emergency room volumes [21] Producing a more accurate prediction of the likely outcome of a particular intervention [20] Decision support N/A d Use of robotics for operational tasks in dementia care, such as meal delivery [24] Automatically altering insulin…”
BackgroundAdapting to Artificial Intelligence: Radiologists and Pathologists as Information Specialists
Jha, S., & Topol, E. J. (2016) · JAMA · doi:10.1001/jama.2016.17438 · Cited by 622
Is it time to drop the ‘knowledge translation’ metaphor? A critical literature review
Greenhalgh, T., & Wieringa, S. (2011) · Journal of the Royal Society of Medicine · doi:10.1258/jrsm.2011.110285 · Cited by 543 · cited 1×
“Clinical decision making is a complex process involving the integration of a variety of data sources, incorporating both tacit and explicit modes of intelligence [34-36].”
BackgroundGoogle DeepMind and healthcare in an age of algorithms
Powles, J., & Hodson, H. (2017) · Health and Technology · doi:10.1007/s12553-017-0179-1 · Cited by 511 · cited 1×
“As governments and other actors internationally become interested in developing applications of ML, health-related data are increasingly made available to private entities with the capability of producing AI applications that are relevant to peoples’ health [41-43].”
BackgroundAutomation bias and verification complexity: a systematic review
Lyell, D., & Coiera, E. (2017) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocw105 · Cited by 451 · cited 1×
“The implementation of decision support systems in health care that do not include applications of ML have been well studied and the difficulties include perceived challenges to autonomy, lack of time, and dissatisfaction with user interfaces [27,28].”
BackgroundUnderstanding HIV disclosure: A review and application of the Disclosure Processes Model
Chaudoir, S. R., Fisher, J. D., & Simoni, J. M. (2011) · Social Science & Medicine · doi:10.1016/j.socscimed.2011.03.028 · Cited by 393
Nilsen, P., Ståhl, C., Roback, K., & Cairney, P. (2013) · Implementation Science · doi:10.1186/1748-5908-8-63 · Cited by 346 · cited 2×
“We have described use cases (and attendant value propositions) of ML in health care as more likely relating to decision support and less likely to automation, which begins to illustrate the implementation object of focus in ML initiatives [6,7].”
BackgroundMethodEmerging paradigms of cognition in medical decision-making
Patel, V. L., Kaufman, D. R., & Arocha, J. F. (2002) · Journal of Biomedical Informatics · doi:10.1016/s1532-0464(02)00009-6 · Cited by 338 · cited 1×
“Clinical decision making is a complex process involving the integration of a variety of data sources, incorporating both tacit and explicit modes of intelligence [34-36].”
BackgroundVogus, T. J., & Welbourne, T. M. (2003) · Journal of Organizational Behavior · doi:10.1002/job.221 · Cited by 302
The legal and ethical concerns that arise from using complex predictive analytics in health care
Cohen, I. G., Amarasingham, R., Shah, A., Xie, B., & Lo, B. (2014) · Health Affairs · doi:10.1377/hlthaff.2014.0048 · Cited by 300 · cited 1×
“The phrase “predictive analytics” is very intuitive with regard to defining AI as a prediction technology, using advanced computer algorithms to predict health-related events from existing data in ways that exceed the ability of individual researchers applying individual analyses [12].”
BackgroundNormal Accidents: Living with High Risk Technologies - Updated Edition
PERROW, C. (2011) · Princeton University Press eBooks · doi:10.2307/j.ctt7srgf · Cited by 289
Forecasting Daily Patient Volumes in the Emergency Department
Jones, S. S., Thomas, A., Evans, R. S., Welch, S. J., Haug, P. J., & Snow, G. L. (2008) · Academic Emergency Medicine · doi:10.1111/j.1553-2712.2007.00032.x · Cited by 266 · cited 1×
“Warning systems for disease outbreak [22] Identifying potential staff scheduling changes related to forecasted emergency room volumes [21] Producing a more accurate prediction of the likely outcome of a particular intervention [20] Decision support N/A d Use of robotics for operational tasks in…”
BackgroundOn the Prospects for a (Deep) Learning Health Care System
Naylor, C. D. (2018) · JAMA · doi:10.1001/jama.2018.11103 · Cited by 250 · cited 1×
“Artificial intelligence (AI) has become a topic of central importance to the ways in which health care will change in the coming decades, with recent commentaries addressing potential transformations in clinical care [1,2], public health [3], and health system planning [4].”
BackgroundFraming the challenges of artificial intelligence in medicine
Yu, K.-H., & Kohane, I. S. (2019) · BMJ Quality & Safety · doi:10.1136/bmjqs-2018-008551 · Cited by 233 · cited 1×
“This raises the question about data provenance [30,48] and represents a set of issues related to the biases that are built into algorithms used to inform decision making.”
BackgroundHealth care robotics: qualitative exploration of key challenges and future directions
Cresswell, K., Cunningham-Burley, S., & Sheikh, A. (2018) · Journal of Medical Internet Research · doi:10.2196/10410 · Cited by 220 · cited 1×
“For example, stakeholder views on the introduction of automated robotics into a variety of health care settings found a widespread lack of interest and understanding and fear of the ways in which work would be disrupted and distributed [29].”
BackgroundAgency and implementation: Understanding the embedding of healthcare innovations in practice
May, C. (2013) · Social Science & Medicine · doi:10.1016/j.socscimed.2012.11.021 · Cited by 189 · cited 1×
“As opposed to focusing on strategies for the adoption of digital technologies in general, which has been addressed extensively in other literature [8-10], we focus on what we understand to be the most important risks arising from the implementation of ML in health care.”
BackgroundBeyond “implementation”: digital health innovation and service design
Shaw, J., Agarwal, P., Desveaux, L., Palma, D. C., Stamenova, V., Jamieson, T., Yang, R., Bhatia, R. S., & Bhattacharyya, O. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0059-8 · Cited by 186 · cited 2×
“Best practices of implementation for digital innovations [8,9,33] will be fundamental to the adoption of ML in health care.”
BackgroundSelf-citationA Socio-technical Approach to Preventing, Mitigating, and Recovering from Ransomware Attacks
Singh, H., & Sittig, D. F. (2016) · Applied Clinical Informatics · doi:10.4338/aci-2016-04-soa-0064 · Cited by 152 · cited 1×
“Strategies to prevent such security breaches on Web accessible health data are now being proposed in the literature [53,54], and the high profile of security issues makes this a particularly important issue as ML applications develop in health care and public health.”
BackgroundCybersecurity and healthcare: how safe are we?
Martin, G., Martin, P., Hankin, C., Darzi, A. W., & Kinross, J. K. (2017) · BMJ · doi:10.1136/bmj.j3179 · Cited by 149 · cited 1×
“This particular attack is estimated to have affected 200,000 systems in over 150 countries, indicating the potential scope of security problems as the value of data grows [52].”
BackgroundCritical Thinking Versus Clinical Reasoning Versus Clinical Judgment
Victor, J. (2012) · Nurse Educator · doi:10.1097/nne.0b013e318276dfbe · Cited by 141 · cited 1×
“This example also pertains only to binary queries specifically about whether a patient has a single disease, which is different from the typical reasoning processes involved in differential diagnosis among clinicians, where multiple confounding, interdependent outcomes must be considered [13,14].”
BackgroundDeep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data
Liu, Y., Logan, B., Liu, N., Xu, Z.-Y., Tang, J., & Wang, Y.-Z. (2017) · IEEE International Conference on Healthcare Informatics · doi:10.1109/ichi.2017.45 · Cited by 123 · cited 1×
“…ML can dynamically adapt survey questions to more quickly identify possible diseases [17], dynamically avoid potential communication breakdowns during speech conversation in the assessment of dementia [18], and even recommend treatments directly when using structured institutional data [19].”
BackgroundBig Data Analysis: New Algorithms for a New Society
Japkowicz, N., & Stefanowski, J. (2015) · Studies in big data · doi:10.1007/978-3-319-26989-4 · Cited by 121 · cited 1×
“Applications to support this effort are emerging in the literature [51].”
What every teacher needs to know about clinical reasoning
Eva Kevin, W. (2005) · Educación Médica · Cited by 113
Evidence-based medicine in primary care: qualitative study of family physicians
Tracy, C. S., Dantas, G. C., & Upshur, R. E. G. (2003) · BMC Family Practice · doi:10.1186/1471-2296-4-6 · Cited by 107 · cited 1×
“…decision making aspires to incorporate a sound understanding of the mechanisms by which diseases and their treatments function and the particular treatments that have demonstrated the greatest benefits under particular experimental circumstances (in addition to patient needs and values [35,39,40]).”
BackgroundYoussef, A. E. (2014) · The International Journal of Ambient Systems and Applications · doi:10.5121/ijasa.2014.2201 · Cited by 95 · cited 1×
“Cloud-based data analysis means that organizations would not need to own computational resources directly [55] but also introduces the potential challenges of data safety.”
BackgroundHealth Data and Privacy in the Digital Era
Gostin, L. O., Halabi, S., & Wilson, K. R. (2018) · JAMA · doi:10.1001/jama.2018.8374 · Cited by 91 · cited 1×
“Currently, data from wearable devices such as smart watches and mobile apps are not widely covered by health information legislation [44], and many health-related apps have unclear consenting processes related to the flow of data generated through their use [45].”
BackgroundLégaré, F., O'Connor, A. M. C., Graham, I. D., Saucier, D., Côté, L., Blais, J., Cauchon, M., & Paré, L. (2006) · Patient Education and Counseling · doi:10.1016/j.pec.2006.04.011 · Cited by 86
Studying Scale-Up and Spread as Social Practice: Theoretical Introduction and Empirical Case Study
Shaw, J., Shaw, S. E., Wherton, J. P., Hughes, G., & Greenhalgh, T. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.7482 · Cited by 84 · cited 1×
“Best practices of implementation for digital innovations [8,9,33] will be fundamental to the adoption of ML in health care.”
BackgroundSelf-citationUnderstanding the care.data conundrum: New information flows for economic growth
Vezyridis, P., & Timmons, S. (2017) · Big Data & Society · doi:10.1177/2053951716688490 · Cited by 79 · cited 2×
“The policy issues presented by ML in health care are beginning to garner more attention [42,43], but here we present one issue that we have not seen addressed in health care or public health literature: the challenge of scalability.”
BackgroundWadmann, S., & Hoeyer, K. (2018) · Big Data & Society · doi:10.1177/2053951717752964 · Cited by 60 · cited 2×
“The policy issues presented by ML in health care are beginning to garner more attention [42,43], but here we present one issue that we have not seen addressed in health care or public health literature: the challenge of scalability.”
BackgroundAutomatic Learning Algorithm for the MD-Logic Artificial Pancreas System
Miller, S., Nimri, R., Atlas, E., Grunberg, E. A., & Phillip, M. (2011) · Diabetes Technology & Therapeutics · doi:10.1089/dia.2010.0216 · Cited by 56 · cited 1×
“…tasks in dementia care, such as meal delivery [24] Automatically altering insulin treatment in response to monitored glucose-insulin dynamics [23] Automation a Tasks related to the assessment, intervention, and evaluation of health-related issues and procedures, generally performed by…”
MethodCyberattack on Britain’s National Health Service — A Wake-up Call for Modern Medicine
Clarke, R., & Youngstein, T. (2017) · New England Journal of Medicine · doi:10.1056/nejmp1706754 · Cited by 56 · cited 1×
“Strategies to prevent such security breaches on Web accessible health data are now being proposed in the literature [53,54], and the high profile of security issues makes this a particularly important issue as ML applications develop in health care and public health.”
BackgroundLearning the Dynamic Treatment Regimes from Medical Registry Data through Deep Q-network
Liu, N., Liu, Y., Logan, B. R., Xu, Z., Tang, J., & Wang, Y. (2019) · Scientific Reports · doi:10.1038/s41598-018-37142-0 · Cited by 53
Tracing the Potential Flow of Consumer Data: A Network Analysis of Prominent Health and Fitness Apps
Grundy, Q., Held, F. P., & Bero, L. A. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.7347 · Cited by 47 · cited 1×
“Currently, data from wearable devices such as smart watches and mobile apps are not widely covered by health information legislation [44], and many health-related apps have unclear consenting processes related to the flow of data generated through their use [45].”
BackgroundArtificial Intelligence in Public Health and Epidemiology
Thiébaut, R., Thiessard, F., & Informatics, S. E. F. T. I. Y. S. O. P. H. A. E. (2018) · Yearbook of Medical Informatics · doi:10.1055/s-0038-1667082 · Cited by 41
The Regulatory Challenge of Mobile Health: Lessons for Canada
Jogova, M., Shaw, J., & Jamieson, T. (2019) · Healthcare policy · doi:10.12927/hcpol.2019.25795 · Cited by 35 · cited 1×
“These include broad legislative frameworks related to emerging health-related technologies more generally [56] and to the innovation procurement systems that vary across health system settings [57,58].”
BackgroundSelf-citationTorbica, A., & Cappellaro, G. (2010) · Journal of Medical Marketing Device Diagnostic and Pharmaceutical Marketing · doi:10.1057/jmm.2009.48 · Cited by 34 · cited 1×
“These include broad legislative frameworks related to emerging health-related technologies more generally [56] and to the innovation procurement systems that vary across health system settings [57,58].”
BackgroundIdentifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease
Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F. (2017) · Computational Linguistics · doi:10.1162/coli_a_00290 · Cited by 30 · cited 1×
“…ML can dynamically adapt survey questions to more quickly identify possible diseases [17], dynamically avoid potential communication breakdowns during speech conversation in the assessment of dementia [18], and even recommend treatments directly when using structured institutional data [19].”
BackgroundSelf-citationAllen, B., Wade, E., & Dickinson, H. (2009) · Journal of Public Procurement · doi:10.1108/jopp-09-01-2009-b003 · Cited by 24 · cited 1×
“These include broad legislative frameworks related to emerging health-related technologies more generally [56] and to the innovation procurement systems that vary across health system settings [57,58].”
BackgroundDeep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry DataPreprint
Liu, N., Liu, Y., Logan, B. R., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09271 · Cited by 9 · cited 1×
“…ML can dynamically adapt survey questions to more quickly identify possible diseases [17], dynamically avoid potential communication breakdowns during speech conversation in the assessment of dementia [18], and even recommend treatments directly when using structured institutional data [19].”
Background
Research works printed but not linked: 8
- Ajay, A, 2019, The Economics of Artificial Intelligence: An Agenda
- 10.1016/j.socscimed.2012.11.021published · doi:10.1016/j.socscimed.2012.11.021published
- Agrawal, A, 2018, Prediction Machines: The Simple Economics of Artificial Intelligence
- RajpurkarPPolamreddiVBalakrishnanAResearchGate2017Cornell University LibraryMalaria likelihood prediction by effectively surveying households using deep reinforcement learning https://www.researchgate.net/publication/321324506_Malaria_Likelihood_Prediction_By_Effectively_Surveying_Households_Using_Deep_Reinforcement_Learning
- CaseyDBeyanOMurphyKFelzmannHRobot-Assisted Care for Elderly With Dementia: Is There a Potential for Genuine End-User Empowerment?Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts2015HRI'15 Extended AbstractsMarch 2-5, 2015Portland, OR2478
- RossiRAAhmedNKThe Network Data Repository with Interactive Graph Analytics and VisualizationProceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence2015AAAI'15January 25-30, 2015Austin Texas42923
- CulnaneCRubinsteinBTeagueVarXiv2017Health data in an open world https://arxiv.org/ftp/arxiv/papers/1712/1712.05627.pdf
- TsymbalAResearchGate2004Computer Science Department, Trinity College DublinThe problem of concept drift: definitions and related work https://www.researchgate.net/publication/228723141_The_Problem_of_Concept_Drift_Definitions_and_Related_Work
Cited by
Algorithmic bias: review, synthesis, and future research directions
Kordzadeh, N., & Ghasemaghaei, M. (2022) · European Journal of Information Systems · doi:10.1080/0960085x.2021.1927212 · Cited by 770
“…explains the sources, consequences, and mitigation strategies in a range of domains from employment and people analytics (Gal et al., 2017) and healthcare (Shaw et al., 2019) to education (Williams et al., 2018), credit markets (Fuster et al., 2018), and criminal justice (Mulligan et al., 2019).”
Barriers to and facilitators of artificial intelligence adoption in health care: scoping review
Hassan, M., Kushniruk, A., & Borycki, E. (2024) · JMIR Human Factors · doi:10.2196/48633 · Cited by 435
“Clinicians expressed the need to understand both the scientific and clinical bases of the recommendations provided by the AI to confidently validate and apply the decision [19,20,36-38].”
BackgroundInfluentialPetersson, L., Larsson, I., Nygren, J. M., Nilsen, P., Neher, M., Reed, J. E., Tyskbo, D., & Svedberg, P. (2022) · BMC Health Services Research · doi:10.1186/s12913-022-08215-8 · Cited by 434
“AI is thus not one single type of technology but rather many different types within various application areas, e.g., diagnosis and treatment, patient engagement and adherence, and administrative activities [5, 6].”
BackgroundRole of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review
Yin, J., Ngiam, K. Y., & Teo, H. H. (2021) · Journal of Medical Internet Research · doi:10.2196/25759 · Cited by 419
“Examples of key challenges that need to be addressed include data sharing and privacy issues, lack of algorithm transparency, the changing nature of health care work, financial concerns, and the demanding regulatory environment [1,3,9-13].”
BackgroundThe potential of artificial intelligence to improve patient safety: a scoping review
Bates, D. W., Levine, D., Syrowatka, A., Kuznetsova, M., Craig, K. J. T., Rui, A., Jackson, G. P., & Rhee, K. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00423-6 · Cited by 323
Metadata
- Authors
- Shaw, J., Rudzicz, F., Jamieson, T., & Goldfarb, A.
- Affiliations
- University of Toronto (CA)
- St. Michael's Hospital (CA)
- Corresponding author
- Shaw, James
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2019-07-10
- Volume
- 21
- Issue
- 7
- Pages
- e13659
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC6652121
- OpenAlex
- W2947151330
- Cited by
- 389
- References
- 58
- Citations by year
- 2026: 62 · 2025: 70 · 2024: 68 · 2023: 77 · 2022: 49 · 2021: 36 · 2020: 22 · 2019: 5
- FWCI
- 8.91
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- artificial intelligence in healthcare, machine learning implementation, NASSS framework, clinical decision support, explainability, algorithmic bias, privacy and consent, healthcare workforce, scalability, technology adoption, implementation science
- MeSH terms
- Machine Learning, Artificial Intelligence, Humans, Telemedicine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.