Tackling prediction uncertainty in machine learning for healthcare
Abstract
Predictive machine-learning systems often do not convey the degree of confidence in the correctness of their outputs. To prevent unsafe prediction failures from machine-learning models, the users of the systems should be aware of the general accuracy of the model and understand the degree of confidence in each individual prediction. In this Perspective, we convey the need of prediction-uncertainty metrics in healthcare applications, with a focus on radiology. We outline the sources of prediction uncertainty, discuss how to implement prediction-uncertainty metrics in applications that require zero tolerance to errors and in applications that are error-tolerant, and provide a concise framework for understanding prediction uncertainty in healthcare contexts. For machine-learning-enabled automation to substantially impact healthcare, machine-learning models with zero tolerance for false-positive or false-negative errors must be developed intentionally.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Selective prediction has been commonly found to improve performance in non-text-based applications.
“This human-in-the-loop decision-making pipeline is known as selective prediction and has been commonly found to improve performance in non–text-based applications [25,26].”
From Identifying Deprescribing Opportunities With Large Language Models in Older Adults: Retrospective Cohort Study (2025) · cites this paper as [26]
Cites
Advances in neural information processing systems 7
Cios, K. J., & Shields, M. E. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,089 · see citing works
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258 · see citing works
The practical implementation of artificial intelligence technologies in medicine
He, J., Baxter, S. L., Xu, J., Xu, J., Zhou, X., & Zhang, K. (2019) · Nature Medicine · doi:10.1038/s41591-018-0307-0 · Cited by 2,246 · see citing works
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719 · see citing works
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 · see citing works
Basha, S. H. S., Dubey, S. R., Pulabaigari, V., & Mukherjee, S. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.008 · Cited by 587 · see citing works
Krause, J., Gulshan, V., Rahimy, E., Karth, P., Widner, K., Corrado, G. S., Peng, L., & Webster, D. R. (2018) · Ophthalmology · doi:10.1016/j.ophtha.2018.01.034 · Cited by 564 · see citing works
Second opinion needed: Communicating uncertainty in medical machine learning
Kompa, B., Snoek, J., & Beam, A. L. (2021) · npj Digital Medicine · doi:10.1038/s41746-020-00367-3 · Cited by 514 · see citing works
Trabelsi, A., Chaâbane, M. A., & Ben‐Hur, A. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz339 · Cited by 153 · see citing works
Automated Dermatological Diagnosis: Hype or Reality?
Navarrete-Dechent, C., Dusza, S. W., Liopyris, K., Marghoob, A. A., Halpern, A. C., & Marchetti, M. A. (2018) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2018.04.040 · Cited by 129 · see citing works
Active label cleaning for improved dataset quality under resource constraints
Bernhardt, M., de Castro, D. C., Tanno, R., Schwaighofer, A., Tezcan, K., Monteiro, M., Bannur, S., Lungren, M. P., Nori, A. V., Glocker, B., et al. (2021) · Nature Communications · doi:10.1038/s41467-022-28818-3 · Cited by 129 · see citing works
Quantification of harms in cancer screening trials: literature review
Heleno, B., Thomsen, M. F., Rodrigues, D., Jørgensen, K. J., & Brodersen, J. (2013) · BMJ · doi:10.1136/bmj.f5334 · Cited by 125 · see citing works
Deep Deterministic Uncertainty: A New Simple Baseline
Mukhoti, J., Kirsch, A., van Amersfoort, J., Torr, P. H. S., & Gal, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02336 · Cited by 116 · see citing works
Generalizability of deep learning models for dental image analysis
Krois, J., Ros, A. G. C., Chaurasia, A., Patil, R., Chaudhari, P. K., Gaudin, R., Gehrung, S., & Schwendicke, F. (2021) · Scientific Reports · doi:10.1038/s41598-021-85454-5 · Cited by 115 · see citing works
Sathitratanacheewin, S., Sunanta, P., & Pongpirul, K. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e04614 · Cited by 108 · see citing works
Local Temperature Scaling for Probability Calibration
Ding, Z., Han, X., Liu, P., & Niethammer, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00681 · Cited by 88 · see citing works
Tracking prototype and exemplar representations in the brain across learning
Bowman, C. R., Iwashita, T., & Zeithamová, D. (2020) · eLife · doi:10.7554/elife.59360 · Cited by 86 · see citing works
A Survey of Explainable AI Terminology
Clinciu, M., & Hastie, H. (2019) · doi:10.18653/v1/w19-8403 · Cited by 77 · see citing works
Deep Learning for the Diagnosis of Stage in Retinopathy of Prematurity
Chen, J., Coyner, A. S., Ostmo, S. R., Sönmez, K., Bajimaya, S., Pradhan, E., Valikodath, N. G., Cole, E. D., Al-Khaled, T., Chan, R. V. P., et al. (2021) · Ophthalmology Retina · doi:10.1016/j.oret.2020.12.013 · Cited by 68 · see citing works
Liang, X., Nguyen, D. T. D., & Jiang, S. B. (2020) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abb214 · Cited by 43 · see citing works
Kim, D., Chung, J. W., Choi, J., Succi, M. D., Conklin, J., Longo, M. G. F., Ackman, J. B., Little, B. P., Petranović, M., Kalra, M. K., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-29437-8 · Cited by 40 · see citing works
Self-citationDans, L. F., Silvestre, M. A. A., & Dans, A. L. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2010.09.009 · Cited by 39 · see citing works
Diagnosis of normal chest radiographs using an autonomous deep-learning algorithm
Dyer, T., Dillard, L., Harrison, M., Morgan, T. N., Tappouni, R. F. R., Malik, Q., & Rasalingham, S. (2021) · Clinical Radiology · doi:10.1016/j.crad.2021.01.015 · Cited by 37 · see citing works
Xin, K. Z., Li, D., & Yi, P. H. (2021) · Emergency Radiology · doi:10.1007/s10140-021-01954-x · Cited by 27 · see citing works
Dyer, T., Chawda, S. J., Alkilani, R., Morgan, T. N., Hughes, M., & Rasalingham, S. (2021) · Neuroradiology · doi:10.1007/s00234-021-02826-4 · Cited by 20 · see citing works
Boland, G. W. (2007) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2007.04.014 · Cited by 17 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Review of multimodal machine learning approaches in healthcare
Krones, F., Marikkar, U., Parsons, G., Szmul, A., & Mahdi, A. (2025) · Information Fusion · doi:10.1016/j.inffus.2024.102690 · Cited by 235 · see citing works
Large language models streamline automated machine learning for clinical studies
Tayebi Arasteh, S., Han, T., Lotfinia, M., Kuhl, C., Kather, J. N., Truhn, D., & Nebelung, S. (2024) · Nature Communications · doi:10.1038/s41467-024-45879-8 · Cited by 114 · see citing works
Savage, T., Wang, J., Gallo, R., Boukil, A., Patel, V., Safavi-Naini, S. A. A., Soroush, A., & Chen, J. H. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae254 · Cited by 92 · see citing works
Socrates, V., Wright, D. S., Huang, T., Fereydooni, S., Dien, C., Chi, L., Albano, J., Patterson, B., Sasidhar Kanaparthy, N., Wright, C. X., et al. (2025) · JMIR Aging · doi:10.2196/69504 · Cited by 17 · see citing works
Large Language Model Uncertainty Measurement and Calibration for Medical Diagnosis and Treatment
Savage, T., Wang, J., Gallo, R., Boukil, A., Patel, V., Ahmad Safavi-Naini, S. A., Soroush, A., & Chen, J. H. (2024) · doi:10.1101/2024.06.06.24308399 · Cited by 11 · see citing works
- Authors
- Chua, M., Kim, D., Choi, J., Lee, N. G., Deshpande, V., Schwab, J., Lev, M. H., Gonzalez, R. G., Gee, M. S., & Do, S.
- Affiliations
- Massachusetts General Hospital (US)
- Massachusetts Eye and Ear Infirmary (US)
- Harvard University (US)
- Corresponding author
- Do, Synho
- Venue
- Nature Biomedical Engineering
- Published
- 2022-12-29
- Volume
- 7
- Issue
- 6
- Pages
- 711-718
- ISSN
- 2157-846X (ISSN-L)
- OpenAlex
- W4313312731
- Cited by
- 114
- References
- 26
- Citations by year
- 2026: 28 · 2025: 49 · 2024: 28 · 2023: 9
- FWCI
- 1.48
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Nature Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- forecast uncertainty, uncertainty measures, machine learning in healthcare, radiology, model confidence, safety-critical systems, false positives and false negatives, error-tolerant applications, automated clinical decision support
- MeSH terms
- Machine Learning, Uncertainty
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
