The DOI matches its Crossref record; 85 of the 89 references it cites were found in a registry or an index.
The importance of being external. methodological insights for the external validation of machine learning models in medicine
Open accessAbstract
Background and Objective Medical machine learning (ML) models tend to perform better on data from the same cohort than on new data, often due to overfitting, or co-variate shifts. For these reasons, external validation (EV) is a necessary practice in the evaluation of medical ML. However, there is still a gap in the literature on how to interpret EV results and hence assess the robustness of ML models.Methods We fill this gap by proposing a meta-validation method, to assess the soundness of EV procedures. In doing so, we complement the usual way to assess EV by considering both dataset cardinality, and the similarity of the EV dataset with respect to the training set. We then investigate how the notions of cardinality and similarity can be used to inform on the reliability of a validation procedure, by integrating them into two summative data visualizations.Results We illustrate our methodology by applying it to the validation of a state-of-the-art COVID-19 diagnostic model on 8 EV sets, collected across 3 different continents. The model performance was moderately impacted by data similarity (Pearson ρ = 0.38, p< 0.001). In the EV, the validated model reported good AUC (average: 0.84), acceptable calibration (average: 0.17) and utility (average: 0.50). The validation datasets were adequate in terms of dataset cardinality and similarity, thus suggesting the soundness of the results. We also provide a qualitative guideline to evaluate the reliability of validation procedures, and we discuss the importance of proper external validation in light of the obtained results.Conclusions In this paper, we propose a novel, lean methodology to: 1) study how the similarity between training and validation sets impacts the generalizability of a ML model; 2) assess the soundness of EV evaluations along three complementary performance dimensions: discrimination, utility and calibration; 3) draw conclusions on the robustness of the model under validation. We applied this methodology to a state-of-the-art model for the diagnosis of COVID-19 from routine blood tests, and showed how to interpret the results in light of the presented framework.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148
Statistical power analysis for the behavioral sciences
Cohen, J. (1990) · Computers Environment and Urban Systems · doi:10.1016/0198-9715(90)90050-4 · Cited by 65,417
Statistical Power Analysis for the Behavioral Sciences
Cohen, J. (2013) · doi:10.4324/9780203771587 · Cited by 25,373
Receiver Operating Characteristic Curve in Diagnostic Test Assessment
Mandrekar, J. N. (2010) · Journal of Thoracic Oncology · doi:10.1097/jto.0b013e3181ec173d · Cited by 4,506
Wynants, L., Van Calster, B., Bonten, M. M., Collins, G. S., Debray, T. P., De Vos, M., Haller, M. C., Heinze, G., Moons, K. G., Riley, R. D., et al. (2020) · doi:10.1101/2020.03.24.20041020 · Cited by 3,070
Internal validation of predictive models
Steyerberg, E. W., Harrell, F. E., Borsboom, G. J. J. M., Eijkemans, M. J. C., Vergouwe, Y., & Habbema, J. D. F. (2001) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(01)00341-9 · Cited by 2,746
Automated detection of COVID-19 cases using deep neural networks with X-ray images
Öztürk, T., Talo, M., Yildirim, E. A., Baloğlu, U. B., Yıldırım, Ö., & Acharya, U. R. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103792 · Cited by 2,652
A Kernel Method for the Two-Sample-Problem
Gretton, A., Borgwardt, K. M., Rasch, M., Schölkopf, B., & Smola, A. J. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0069 · Cited by 2,167
(2010) · doi:10.5555/1756006.1859921 · Cited by 1,924
Machine learning algorithm validation with a limited sample size
Vabalas, A., Gowen, E., Poliakoff, E., & Casson, A. J. (2019) · PLOS ONE · doi:10.1371/journal.pone.0224365 · Cited by 1,901
Flagged first, then by citations
4 of the 89 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Evaluation of clinical prediction models (part 1): from development to external validation
Collins, G. S., Dhiman, P., Ma, J., Schlussel, M. M., Archer, L., Van Calster, B., Harrell, F. E., Martin, G. P., Moons, K. G. M., van Smeden, M., et al. (2024) · BMJ · doi:10.1136/bmj-2023-074819 · Cited by 798
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., Weicken, E., Asselbergs, F. W., Prior, F., Collins, G. S., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081554 · Cited by 957
“45 These might include reference or benchmarking datasets that are representative for the task in question (ie, approximating the expected real world variations).”
Feng, J., Phillips, R. V., Malenica, I., Bishara, A., Hubbard, A. E., Celi, L. A., & Pirracchio, R. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00611-y · Cited by 423
Salinas, M. P., Sepúlveda, J., Hidalgo, L., Peirano, D., Morel-Marambio, M., Uribe, P., Rotemberg, V. M., Briones, J., Mery, D., & Navarrete‐Dechent, C. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01103-x · Cited by 191
Targeted validation: validating clinical prediction models in their intended population and setting
Sperrin, M., Riley, R. D., Collins, P. G. S., & Martin, G. P. (2022) · Diagnostic and Prognostic Research · doi:10.1186/s41512-022-00136-8 · Cited by 121
Metadata
- Authors
- Cabitza, F., Campagner, A., Soares, F., García de Guadiana-Romualdo, L., Challa, F., Sulejmani, A., Seghezzi, M., & Carobene, A.
- Affiliations
- University of Milano-Bicocca (IT)
- Universidade Federal do Rio Grande do Sul (BR)
- Ethiopian Public Health Institute (ET)
- Ospedale Papa Giovanni XXIII (IT)
- IRCCS Ospedale San Raffaele (IT)
- Corresponding author
- Cabitza, Federico
- Venue
- Computer Methods and Programs in Biomedicine
- Publisher
- Elsevier BV
- Published
- 2021-09
- Volume
- 208
- Pages
- 106288
- ISSN
- 0169-2607 (ISSN-L)
- OpenAlex
- W3183421885
- Cited by
- 284
- References
- 89
- Citations by year
- 2026: 71 · 2025: 83 · 2024: 70 · 2023: 33 · 2022: 26 · 2021: 1
- FWCI
- 28.33
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- Computer Methods and Programs in Biomedicine (publishedVersion)
- PubMed (publishedVersion)
- BOA (University of Milano-Bicocca) (submittedVersion, other-oa)
- Topics
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- external validation, machine learning in medicine, covariate shift, overfitting, generalizability, dataset similarity, model robustness, COVID-19 diagnosis, routine blood tests, discrimination (statistics), calibration, clinical utility
- MeSH terms
- Machine Learning, COVID-19, SARS-CoV-2, Humans, Reproducibility of Results, Cohort Studies
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
