The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Artificial Intelligence in Clinical Decision Support: Challenges for Evaluating AI and Practical Implications: A Position Paper from the IMIA Technology Assessment & Quality Development in Health Informatics Working Group and the EFMI Working Group for Assessment of Health Information Systems
Open accessAbstract
Objectives: This paper draws attention to: i) key considerations for evaluating artificial intelligence (AI) enabled clinical decision support; and ii) challenges and practical implications of AI design, development, selection, use, and ongoing surveillance. Method: A narrative review of existing research and evaluation approaches along with expert perspectives drawn from the International Medical Informatics Association (IMIA) Working Group on Technology Assessment and Quality Development in Health Informatics and the European Federation for Medical Informatics (EFMI) Working Group for Assessment of Health Information Systems. Results: There is a rich history and tradition of evaluating AI in healthcare. While evaluators can learn from past efforts, and build on best practice evaluation frameworks and methodologies, questions remain about how to evaluate the safety and effectiveness of AI that dynamically harness vast amounts of genomic, biomarker, phenotype, electronic record, and care delivery data from across health systems. This paper first provides a historical perspective about the evaluation of AI in healthcare. It then examines key challenges of evaluating AI-enabled clinical decision support during design, development, selection, use, and ongoing surveillance. Practical aspects of evaluating AI in healthcare, including approaches to evaluation and indicators to monitor AI are also discussed. Conclusion: Commitment to rigorous initial and ongoing evaluation will be critical to ensuring the safe and effective integration of AI in complex sociotechnical settings. Specific enhancements that are required for the new generation of AI-enabled clinical decision support will emerge through practical application.
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
“The literature recommends the identification of potential sources of risk, extreme situations, and failures before the onset of the study26,57,58.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [57]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Implementers are encouraged to clearly define the context and boundaries within which the monitoring is to be performed57.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [57]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, obtaining independent datasets can be difficult in clinical laboratory medicine [126,128].”
From Machine learning-based clinical decision support using laboratory data (2024) · cites this paper as [128]
Experimental — accuracy not yet measuredIn the citing paper
“Field-testing can give researchers the opportunity to assess the performance of algorithms in different population groups and clinical settings.62”
From Addressing bias in big data and AI for health care: A call for open science (2021) · cites this paper as [62]
In the citing paper
“It is recommended that findings are communicated in an understandable and meaningful way to healthcare professionals, but also to administrators and policymakers57.”
From Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022) · cites this paper as [57]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
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
The DeLone and McLean Model of Information Systems Success: A Ten-Year Update
(2003) · Journal of Management Information Systems · doi:10.1080/07421222.2003.11045748 · Cited by 11,791
Information Systems Success: The Quest for the Dependent Variable
DeLone, W. H., & McLean, E. R. (1992) · Information Systems Research · doi:10.1287/isre.3.1.60 · Cited by 10,697
Artificial intelligence in healthcare
Yu, K.-H., Beam, A. L., & Kohane, I. S. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0305-z · Cited by 2,817
Artificial intelligence, bias and clinical safety
Challen, R., Denny, J., Pitt, M., Gompels, L., Edwards, T., & Tsaneva-Atanasova, K. (2019) · BMJ Quality & Safety · doi:10.1136/bmjqs-2018-008370 · Cited by 956
Computer-aided Diagnosis of Acute Abdominal Pain
de Dombal, F. T., Leaper, D. J., Staniland, J. R., McCann, A. P., & Horrocks, J. C. (1972) · BMJ · doi:10.1136/bmj.2.5804.9 · Cited by 673
The coming of age of artificial intelligence in medicine
Patel, V. L., Shortliffe, E. H., Stefanelli, M., Szolovits, P., Berthold, M. R., Bellazzi, R., & Abu-Hanna, A. (2009) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2008.07.017 · Cited by 625
Recursive Functions of Symbolic Expressions and Their Computation by Machine (1960)
McCarthy, J. (2021) · Ideas That Created the Future · doi:10.7551/mitpress/12274.003.0023 · Cited by 532
Shortliffe, E. H., Davis, R., Axline, S. G., Buchanan, B. G., Green, C. C., & Cohen, S. N. (1975) · Computers and Biomedical Research · doi:10.1016/0010-4809(75)90009-9 · Cited by 493 · cited 1×
“In the 1970’s, there was a big wave of the so called first generation of AI in medicine [13], such as Shortliffe’s work with MYCIN [14], Kulikowski’s individualized clinical decision models [15], and de Dombal’s computer-aided diagnosis of acute abdominal pain [16] which incorporated newer statistical reasoning method…”
MethodEvaluation Methods in Medical Informatics
Friedman, C. P., & Wyatt, J. C. (1997) · Computers and Medicine · doi:10.1007/978-1-4757-2685-5 · Cited by 448
Agniel, D., Kohane, I. S., & Weber, G. M. (2018) · BMJ · doi:10.1136/bmj.k1479 · Cited by 391
An Intelligence in Our Image: The Risks of Bias and Errors in Artificial Intelligence
Osoba, O., & Welser, W. (2017) · doi:10.7249/rr1744 · Cited by 326
Kim, M. O., Coiera, E., & Magrabi, F. (2017) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocw154 · Cited by 263
Self-citationSTARE-HI—Statement on reporting of evaluation studies in Health Informatics
TALMON, J., AMMENWERTH, E., BRENDER, J., DEKEIZER, N., NYKANEN, P., & RIGBY, M. (2009) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2008.09.002 · Cited by 234
Self-citationFraming 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
Evaluating medical expert systems: what to test and how?
Wyatt, J., & Spiegelhalter, D. (1990) · Medical Informatics · doi:10.3109/14639239009025268 · Cited by 195
Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care
Kanagasingam, Y., Xiao, D., Vignarajan, J., Preetham, A., Tay-Kearney, M.-L., & Mehrotra, A. (2018) · JAMA Network Open · doi:10.1001/jamanetworkopen.2018.2665 · Cited by 185
Schloemer, T., & Schröder-Bäck, P. (2018) · Implementation Science · doi:10.1186/s13012-018-0751-8 · Cited by 172
Treleaven, P. C., Galas, M., & Lalchand, V. (2013) · Communications of the ACM · doi:10.1145/2500117 · Cited by 159
The adolescence of AI in Medicine: Will the field come of age in the '90s?
Shortliffe, E. H. (1993) · Artificial Intelligence in Medicine · doi:10.1016/0933-3657(93)90011-q · Cited by 153
Evaluating the performance of a computer-based consultant
Yu, V. L., Buchanan, B. G., Shortliffe, E. H., Wraith, S. M., Davis, R., Scott, A. C., & Cohen, S. N. (1979) · Computer Programs in Biomedicine · doi:10.1016/0010-468x(79)90022-9 · Cited by 149
Handbook of Evaluation Methods for Health Informatics
(2006) · Elsevier eBooks · doi:10.1016/b978-0-12-370464-1.x5000-x · Cited by 115
Colmerauer, A., & Roussel, P. (1993) · The second ACM SIGPLAN conference on History of programming languages · doi:10.1145/154766.155362 · Cited by 108
Guideline for good evaluation practice in health informatics (GEP-HI)
Nykänen, P., Brender, J., Talmon, J., de Keizer, N., Rigby, M., Beuscart-Zephir, M.-C., & Ammenwerth, E. (2011) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2011.08.004 · Cited by 105
Self-citationAutomation bias in electronic prescribing
Lyell, D., Magrabi, F., Raban, M. Z., Pont, L. G., Baysari, M. T., Day, R. O., & Coiera, E. (2017) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-017-0425-5 · Cited by 103 · cited 1×
“Previous work has demonstrated the effects of automation bias with a prescribing DSS that was based on simple rules of logic [42].”
BackgroundSelf-citationThe fate of medicine in the time of AI
Coiera, E. W. (2018) · The Lancet · doi:10.1016/s0140-6736(18)31925-1 · Cited by 99
Ser, G., Robertson, A. R. R., & Sheikh, A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0077669 · Cited by 95
Benchmarking health IT among OECD countries: better data for better policy
Adler‐Milstein, J., Ronchi, E., Cohen, G. R., Winn, L. A. P., & Jha, A. K. (2013) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2013-001710 · Cited by 89
Conceptualising and creating a global learning health system
Friedman, C. P., & Rigby, M. (2012) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2012.05.010 · Cited by 84
Self-citationBad Health Informatics Can Kill – Is Evaluation the Answer?
Shaw, N. T., & Ammenwerth, E. (2005) · Methods of Information in Medicine · doi:10.1055/s-0038-1633915 · Cited by 82
Self-citationBrender, J., Talmon, J. L., de Keizer, N. F., Nykänen, P., Rigby, M., & Ammenwerth, E. (2013) · Applied Clinical Informatics · doi:10.4338/aci-2013-04-ra-0024 · Cited by 76
Self-citationArtificial Intelligence in Medicine: The Challenges Ahead
Coiera, E. W. (1996) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.1996.97084510 · Cited by 70
Minne, L., Eslami, S., de Keizer, N., de Jonge, E., de Rooij, S. E., & Abu-Hanna, A. (2012) · Intensive Care Medicine · doi:10.1007/s00134-011-2390-2 · Cited by 69
STARE-HI -Statement on Reporting of Evaluation Studies in Health Informatics
Ammenwerth, E., Brender, J., de Keizer, N. F., Nykänen, P., Rigby, M., & Talmon, J. L. (2009) · Yearbook of Medical Informatics · doi:10.1055/s-0038-1638633 · Cited by 55
Self-citationA methodology for evaluation of knowledge-based systems in medicine
Clarke, K., O’Moore, R. R., Smeets, R. P. A. M., Talmon, J. L., Brender, J., McNair, P., Nykänen, P., Grimson, J. B., & Barber, B. (1994) · Artificial Intelligence in Medicine · doi:10.1016/0933-3657(94)90040-x · Cited by 53
Self-citationWhat have we learnt after 15 years of research into the ‘weekend effect’?
Bray, B., & Steventon, A. (2016) · BMJ Quality & Safety · doi:10.1136/bmjqs-2016-005793 · Cited by 47
Computer aided diagnosis of acute abdominal pain
Hall, P. N. (1986) · BMJ · doi:10.1136/bmj.293.6553.1025-d · Cited by 45
Evaluating Medical Expert Systems: What To Test, And How ?
Wyatt, J. C., & Spiegelhalter, D. J. (1991) · Lecture notes in medical informatics · doi:10.1007/978-3-662-08131-0_22 · Cited by 41
How reliable are clinical systems in the UK NHS? A study of seven NHS organisations
Burnett, S. J., Franklin, B. D., Moorthy, K., Cooke, M. W., & Vincent, C. A. (2012) · BMJ Quality & Safety · doi:10.1136/bmjqs-2011-000442 · Cited by 37
Kulikowski, C. A. (2015) · Yearbook of Medical Informatics · doi:10.15265/iy-2015-016 · Cited by 36
Evaluation of decision support systems in medicine
Nykänen, P., Chowdhury, S. S., & Wigertz, O. B. (1991) · Computer Methods and Programs in Biomedicine · doi:10.1016/0169-2607(91)90047-w · Cited by 32
Self-citationFactors influencing the transferability of medical decision support systems
Nolan, J. J., McNair, P., & Brender, J. (1991) · International Journal of Bio-Medical Computing · doi:10.1016/0020-7101(91)90018-a · Cited by 30
Nordic eHealth Indicators: Organisation of Research, First Results and Plan for the Future
Hannele, H., Faxvaag, A., Gilstad, H., Audur, H. G., Jerlvall, L., Kangas, M., Koch, S., Nøhr, C. G., Pehrsson, T., Reponen, J., et al. (2013) · Studies in health technology and informatics · doi:10.3233/978-1-61499-289-9-273 · Cited by 26
Methodology for constructive assessment of IT-based systems in an organisational context
Brender, J. (1999) · International Journal of Medical Informatics · doi:10.1016/s1386-5056(99)00042-8 · Cited by 25
An Architecture for Knowledge-based Construction of Decision Models
Sonnenberg, F. A., Hagerty, C., & Kulikowski, C. A. (1994) · Medical Decision Making · doi:10.1177/0272989x9401400104 · Cited by 22
Reduced Verification of Medication Alerts Increases Prescribing Errors
Lyell, D., Magrabi, F., & Coiera, E. W. (2019) · Applied Clinical Informatics · doi:10.1055/s-0038-1677009 · Cited by 21
Self-citationDesiderata for sharable computable biomedical knowledge for learning health systems
Lehmann, H. P., & Downs, S. M. (2018) · Learning Health Systems · doi:10.1002/lrh2.10065 · Cited by 17
Wrong side of the tracks: Big Data and Protected CategoriesPreprint
DeDeo, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.4643 · Cited by 15
Benchmarking Deployment of Ehealth Among General Practitioners: Final Report
Lupiáñez‐Villanueva, F., Devaux, A., Valverde-Albacete, J., Folkvord, F., Fauli, C., Altenhofer, M., Hocking, L., & Harshfield, A. (2019) · Cited by 15
User-requirements driven learning
Karthaus, V., Thygesen, H., Egmont-Petersen, M., et al. (1995) · Computer Methods and Programs in Biomedicine · doi:10.1016/0169-2607(95)01658-g · Cited by 8
Open Source Platforms and Frameworks for Artificial Intelligence and Machine Learning
Bhattacharya, S., Czejdo, B., Agrawal, R. K., et al. (2018) · Proceedings of IEEE Southeastcon · doi:10.1109/secon.2018.8479098 · Cited by 8
Inventory of validation approaches in selected health telematics projects
Nykänen, P., Enning, J., Talmon, J. L., Hoyer, D., Sanz, F., Thayer, C., Roine, R. P., Vissers, M. C., & Eurlings, F. (1999) · International Journal of Medical Informatics · doi:10.1016/s1386-5056(99)00047-7 · Cited by 7
Self-citationATIM, accompanying measure on the assessment of information technology in medicine
van Gennip, E. M. S. J., Talmon, J. L., & Bakker, A. R. (1994) · Computer Methods and Programs in Biomedicine · doi:10.1016/0169-2607(94)90005-1 · Cited by 4
Results of discussions at the IMIA WG 13 and 15 working conference
van Gennip, E. M. S. J., & Lorenzi, N. M. (1999) · International Journal of Medical Informatics · doi:10.1016/s1386-5056(99)00029-5 · Cited by 3
Research works printed but not linked: 2
- [30]Feigenbaum E Aeditor Autoknowledge: from file server to knowledge serversMEDINFO; 1986; Amsterdam: Elsevier Science Publishers BV 1986
- [31]Nykänen P Zvarova J Big data challenges for personalised medicine. Editorial International Journal of Biomedicine and Healthcare 2015 3 01 1
Cited by
Ethical and regulatory challenges of AI technologies in healthcare: A narrative review
Mennella, C., Maniscalco, U., De Pietro, G., & Esposito, M. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26297 · Cited by 1,229
Addressing bias in big data and AI for health care: A call for open science
Norori, N., Hu, Q., Aellen, F. M., Faraci, F. D., & Tzovara, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100347 · Cited by 903
Application of Artificial Intelligence in Dentistry
Shan, T., Tay, F. R., & Gu, L. (2021) · Journal of Dental Research · doi:10.1177/0022034520969115 · Cited by 511
de Hond, A. A. H., Leeuwenberg, A. M., Hooft, L., Kant, I. M. J., Nijman, S. W. J., van Os, H. J. A., Aardoom, J. J., Debray, T. P. A., Schuit, E., van Smeden, M., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-021-00549-7 · Cited by 499
Wang, D., Wang, L., Zhang, Z., Wang, D., Zhu, H., Gao, Y., Fan, X., & Tian, F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445432 · Cited by 209
Metadata
- Authors
- Magrabi, F., Ammenwerth, E., McNair, J. B., De Keizer, N. F., Hyppönen, H., Nykänen, P., Rigby, M., Scott, P. J., Vehko, T., Wong, Z. S.-Y., & Georgiou, A.
- Affiliations
- Macquarie University (AU)
- UMIT TIROL - Private University for Health Sciences and Health Technology (AT)
- Aalborg University (DK)
- Amsterdam UMC, University of Amsterdam, Department of Medical Informatics, Amsterdam Public Health research institute, The Netherlands
- Finnish Institute for Health and Welfare (FI)
- Tampere University (FI)
- Keele University (GB)
- University of Portsmouth (GB)
- St. Luke's International University (JP)
- Corresponding author
- Magrabi, Farah
- ORCID
- Venue
- Yearbook of Medical Informatics
- Publisher
- Georg Thieme Verlag KG
- Published
- 2019-04-25
- Volume
- 28
- Issue
- 01
- Pages
- 128-134
- ISSN
- 0943-4747 (ISSN-L)
- 2364-0502
- PMC
- PMC6697499
- OpenAlex
- W2940562610
- Cited by
- 347
- References
- 53
- Citations by year
- 2026: 57 · 2025: 80 · 2024: 73 · 2023: 48 · 2022: 33 · 2021: 36 · 2020: 17 · 2019: 2
- FWCI
- 1.05
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Yearbook of Medical Informatics (publishedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Pure Amsterdam UMC (publishedVersion, cc-by)
- Keele Research Repository (Keele University) (submittedVersion, cc-by)
- VBN Forskningsportal (Aalborg Universitet) (submittedVersion, cc-by-nc-nd)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- Tampere University Institutional Repository (Tampere University) (submittedVersion, cc-by-nc-nd)
- Funders
- Japan Society for the Promotion of Science (18H03336)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- artificial intelligence, clinical decision support, AI evaluation, AI safety, AI monitoring, socio-technical systems, evaluation framework
- MeSH terms
- Machine Learning, Artificial Intelligence, Evaluation Studies as Topic, Program Evaluation, Decision Support Systems, Clinical
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.