Ideal algorithms in healthcare: Explainable, dynamic, precise, autonomous, fair, and reproducible
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
Established guidelines describe minimum requirements for reporting algorithms in healthcare; it is equally important to objectify the characteristics of ideal algorithms that confer maximum potential benefits to patients, clinicians, and investigators. We propose a framework for ideal algorithms, including 6 desiderata: explainable (convey the relative importance of features in determining outputs), dynamic (capture temporal changes in physiologic signals and clinical events), precise (use high-resolution, multimodal data and aptly complex architecture), autonomous (learn with minimal supervision and execute without human input), fair (evaluate and mitigate implicit bias and social inequity), and reproducible (validated externally and prospectively and shared with academic communities). We present an ideal algorithms checklist and apply it to highly cited algorithms. Strategies and tools such as the predictive, descriptive, relevant (PDR) framework, the Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence (SPIRIT-AI) extension, sparse regression methods, and minimizing concept drift can help healthcare algorithms achieve these objectives, toward ideal algorithms in healthcare.
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.
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
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“hoc analyses on a trained, complex model to understand what relationships the model has learned [18].”
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“This method was used to evaluate racial bias in an algorithm that predicts healthcare needs [83].”
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Moons, K. G. M., Altman, D. G., Reitsma, J. B., Ioannidis, J. P. A., Macaskill, P., Steyerberg, E. W., Vickers, A. J., Ransohoff, D. F., & Collins, G. S. (2015) · Annals of Internal Medicine · doi:10.7326/m14-0698 · Cited by 5,147 · cited 1×
“Noninterventional studies that involve prediction models should comply with the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement [87,88].”
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Brunton, S. L., Proctor, J. L., & Kutz, J. N. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1517384113 · Cited by 4,796
1,500 scientists lift the lid on reproducibility
Baker, M. (2016) · Nature · doi:10.1038/533452a · Cited by 4,209
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015 · cited 2×
“Federated learning offers opportunities to ensure the external validity, generalizability, and reproducibility of algorithms via collaborative machine learning without data sharing [89– 92].”
The Future of Digital Health with Federated Learning
Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B., Maier-Hein, K., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.08119 · Cited by 3,495
Definitions, methods, and applications in interpretable machine learning
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900654116 · Cited by 2,167 · cited 2×
“Examination of relevancy can resolve trade-offs between predictive and descriptive accuracy [16].”
Burnout and Medical Errors Among American Surgeons
Shanafelt, T. D., Balch, C. M., Bechamps, G., Russell, T., Dyrbye, L., Satele, D., Collicott, P., Novotny, P. J., Sloan, J., & Freischlag, J. (2010) · Annals of Surgery · doi:10.1097/sla.0b013e3181bfdab3 · Cited by 2,099 · cited 1×
“Regrettably, clinicians demonstrate variable performance in predicting risk for postoperative complications, and surgeons frequently commit judgment errors that confer preventable harm [70–72].”
Hidden in Plain Sight — Reconsidering the Use of Race Correction in Clinical Algorithms
Vyas, D. A., Eisenstein, L. G., & Jones, D. S. (2020) · New England Journal of Medicine · doi:10.1056/nejmms2004740 · Cited by 1,731
Diagnostic error in internal medicine
Graber, M. L., Franklin, N., & Gordon, R. (2005) · Archives of Internal Medicine · doi:10.1001/archinte.165.13.1493 · Cited by 1,549
Artificial intelligence in surgery: promises and perils
Hashimoto, D. A., Rosman, G., Rus, D., & Meireles, O. R. (2018) · Annals of Surgery · doi:10.1097/sla.0000000000002693 · Cited by 1,468 · cited 1×
“Precision is important because human diseases are complex and nonlinear [30,31].”
Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J., Denniston, A. K., The SPIRIT-AI and CONSORT-AI Working Group, SPIRIT-AI and CONSORT-AI Steering Group, Chan, A.-W., Darzi, A., Holmes, C., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-1034-x · Cited by 1,421
Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020) · BMJ · doi:10.1136/bmj.m689 · Cited by 1,152 · cited 1×
“Hundreds of retrospective studies are classified as artificial intelligence (AAU : PleasenotethatAIhasbeendefinedasartificialintelligenceinthesentenceHundredsofretrospectivestudiesare::::Pleasecheckandcorrectifnecessary: I) clinical trials, but few are methodologically rigorous [9,10].”
A clinically applicable approach to continuous prediction of future acute kidney injury
Tomašev, N., Glorot, X., Rae, J. W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., et al. (2019) · Nature · doi:10.1038/s41586-019-1390-1 · Cited by 1,086 · cited 1×
“By contrast, large volume electronic health record (EHR) data are well suited to dynamic predictive analytics that capture trends over time; physiologic time series data have been used to predict mortality and specific conditions such as acute kidney injury [20–23].”
Clinical decision support in the era of artificial intelligence
Shortliffe, E. H., & Sepúlveda, M. J. (2018) · JAMA · doi:10.1001/jama.2018.17163 · Cited by 920
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737416 · Cited by 881
Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist.
Norgeot, B., Quer, G., Beaulieu-Jones, B. K., Torkamani, A., Dias, R., Gianfrancesco, M., Arnaout, R., Kohane, I. S., Saria, S., Topol, E., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-1041-y · Cited by 665 · cited 1×
“We note, though, recent studies showing no great superiority of deep learning over regression in this field of classifying illness severity of individual patients using readily available clinical data [15,17].”
A targeted real-time early warning score (TREWScore) for septic shock.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015) · Science Translational Medicine · doi:10.1126/scitranslmed.aab3719 · Cited by 598 · cited 1×
“…monitoring is often reserved for high-risk patients that are most likely to manifest time-sensitive clinically significant physiologic changes, for whom continuous data have a proven ability to stand alone [55–60] and to add information to EHR data elements [36,59,61–64] in predictive analytics.”
Cruz Rivera, S., Liu, X., Chan, A.-W., Denniston, A. K., Calvert, M. J., Ashrafian, H., Beam, A. L., Collins, G. S., Darzi, A., Deeks, J. J., et al. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30219-3 · Cited by 486
Shahian, D. M., Jacobs, J. P., Badhwar, V., Kurlansky, P. A., Furnary, A. P., Cleveland, J. C., Lobdell, K. W., Vassileva, C., Wyler von Ballmoos, M. C., Thourani, V. H., et al. (2018) · The Annals of Thoracic Surgery · doi:10.1016/j.athoracsur.2018.03.002 · Cited by 459 · cited 1×
“For example, if a decision support tool incorporates the observation that Black patients have increased risk for mortality after coronary artery bypass, then model outputs could decrease the likelihood that Black patients will garner the benefits of an indicated procedure [81,82].”
Bihorac, A., Ozrazgat-Baslanti, T., Ebadi, A., Motaei, A., Madkour, M., Pardalos, P. M., Lipori, G., Hogan, W. R., Efron, P. A., Moore, F., et al. (2019) · Annals of Surgery · doi:10.1097/sla.0000000000002706 · Cited by 377 · cited 2×
“Fortunately, the widespread availability of high-volume EHR data and open-source machine learning code promotes algorithm autonomy [68,69].”
Self-citationMachine learning for real-time prediction of complications in critical care: a retrospective study
Meyer, A., Zverinski, D., Pfahringer, B., Kempfert, J., Kuehne, T., Sündermann, S. H., Stamm, C., Hofmann, T., Falk, V., & Eickhoff, C. (2018) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(18)30300-x · Cited by 350
Complications in surgical patients.
Healey, M. A. (2002) · Archives of Surgery · doi:10.1001/archsurg.137.5.611 · Cited by 343
The development of a machine learning inpatient acute kidney injury prediction model.
Koyner, J. L., Carey, K. A., Edelson, D. P., & Churpek, M. M. (2018) · Critical Care Medicine · doi:10.1097/ccm.0000000000003123 · Cited by 323
Dybowski, R., Gant, V, Weller, P., & Chang, R. (1996) · The Lancet · doi:10.1016/s0140-6736(96)90609-1 · Cited by 240
An examination of American College of Surgeons NSQIP surgical risk calculator accuracy.
Cohen, M. E., Liu, Y., Ko, C. Y., & Hall, B. L. (2017) · Journal of the American College of Surgeons · doi:10.1016/j.jamcollsurg.2016.12.057 · Cited by 176
Shickel, B., Loftus, T. J., Adhikari, L., Ozrazgat-Baslanti, T., Bihorac, A., & Rashidi, P. (2019) · Scientific Reports · doi:10.1038/s41598-019-38491-0 · Cited by 165
Self-citationArtificial Intelligence in Medicine
Schwartz, W. B., Patil, R. S., & Szolovits, P. (1987) · New England Journal of Medicine · doi:10.1056/nejm198703123161109 · Cited by 152 · cited 1×
“Precision is important because human diseases are complex and nonlinear [30,31].”
Kim, S., Kim, W., & Park, R. W. (2011) · Healthcare Informatics Research · doi:10.4258/hir.2011.17.4.232 · Cited by 132
Brennan, M., Puri, S., Ozrazgat-Baslanti, T., Feng, Z., Ruppert, M., Hashemighouchani, H., Momcilovic, P., Li, X., Wang, D. Z., & Bihorac, A. (2019) · Surgery · doi:10.1016/j.surg.2019.01.002 · Cited by 131 · cited 1×
“94, exhibiting accuracy greater than that of physicians [69,70].”
Self-citationDelahanty, R. J., Kaufman, D., & Jones, S. S. (2018) · Critical Care Medicine · doi:10.1097/ccm.0000000000003011 · Cited by 105
Adhikari, L., Ozrazgat-Baslanti, T., Ruppert, M., Madushani, R. W. M. A., Paliwal, S., Hashemighouchani, H., Zheng, F., Tao, M., Lopes, J. M., Li, X., et al. (2019) · PLOS ONE · doi:10.1371/journal.pone.0214904 · Cited by 98
Self-citationMoss, T. J., Lake, D. E., Calland, J. F., Enfield, K. B., Delos, J. B., Fairchild, K. D., & Moorman, J. R. (2016) · Critical Care Medicine · doi:10.1097/ccm.0000000000001738 · Cited by 98
Self-citationO'Reilly-Shah, V. N., Gentry, K. R., Walters, A. M., Zivot, J., Anderson, C. T., & Tighe, P. J. (2020) · British Journal of Anaesthesia · doi:10.1016/j.bja.2020.07.040 · Cited by 62 · cited 2×
“Several other methods for promoting algorithm fairness have been described [4].”
Self-citationRaymond, B. L., Wanderer, J. P., Hawkins, A. T., Geiger, T. M., Ehrenfeld, J. M., Stokes, J. W., & McEvoy, M. D. (2019) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000003718 · Cited by 60 · cited 1×
“Several accurate predictive analytic decision support algorithms have been developed and validated to augment clinical risk predictions, but most are hindered by time-consuming manual data entry requirements and lack of integration with clinical workflow [67,73–77].”
Eye of the beholder: risk calculators and barriers to adoption in surgical trainees.
Leeds, I. L., Rosenblum, A. J., Wise, P. E., Watkins, A. C., Goldblatt, M. I., Haut, E. R., Efron, J. E., & Johnston, F. M. (2018) · Surgery · doi:10.1016/j.surg.2018.07.002 · Cited by 42 · cited 1×
“Manual data entry by the end user imposes time constraints that hinder the clinical application of nonautonomous decision support algorithms [67].”
Hyde, L. Z., Valizadeh, N., Al-Mazrou, A. M., & Kiran, R. P. (2019) · The American Journal of Surgery · doi:10.1016/j.amjsurg.2018.11.017 · Cited by 37
Procedure-based postoperative risk prediction using NSQIP data.
Clark, D. E., Fitzgerald, T. L., & Dibbins, A. W. (2018) · Journal of Surgical Research · doi:10.1016/j.jss.2017.09.003 · Cited by 32
Bagnall, N. M., Pring, E. T., Malietzis, G., Athanasiou, T., Faiz, O. D., Kennedy, R. H., & Jenkins, J. T. (2018) · International Journal of Colorectal Disease · doi:10.1007/s00384-018-3141-4 · Cited by 27 · cited 1×
“To perform a complex task, such as differentiating between an anastomotic leak and other pro-inflammatory postoperative complications, it is potentially advantageous to incorporate high-resolution, multimodal patient data and machine learning modeling [35–39].”
Cited by
Amugongo, L. M., Kriebitz, A., Boch, A., & Lütge, C. (2025) · AI and Ethics · doi:10.1007/s43681-023-00331-3 · Cited by 68
“In the literature, the use of checklists to assess the integration of guidelines in AI development has been proposed [6, 70, 94].”
InfluentialKoçak, B., Keleş, A., & Köse, F. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.232604 · Cited by 12
Why and How to Monitor Deployed AI Systems in Health Care
Keyes, T., Callahan, A., Pandya, A. S., Ambers, N., Banda, J. M., Fuentes, M., Lugtu, C., Masariya, P., Nallan, S., O’Brien, C., et al. (2026) · NEJM Catalyst · doi:10.1056/cat.25.0372 · Cited by 10
Metadata
- Authors
- Loftus, T. J., Tighe, P. J., Ozrazgat-Baslanti, T., Davis, J. P., Ruppert, M. M., Ren, Y., Shickel, B., Kamaleswaran, R., Hogan, W. R., Moorman, J. R., Upchurch, G. R., Rashidi, P., & Bihorac, A.
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2022-01-18
- Volume
- 1
- Issue
- 1
- Pages
- e0000006
- ISSN
- 2767-3170 (ISSN-L)
- OpenAlex
- W4205844722
- Cited by
- 57
- References
- 43
- FWCI
- 2.84
- Type
- journal article
- Language
- en
- Open access
- gold
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.