Wu, E. et al. How medical AI devices are evaluated: limitations and recommendations from an FDA-approved analysis. nut. medicine. 27582–584 (2021).
Kakarmath, S. et al. Best practices for authors of healthcare-related artificial intelligence papers. npj digital med. 3134 (2020).
Steyerberg, EW & Vergouwe, Y. Towards better clinical predictive models: 7 steps for development and ABCD for validation. EUR. Hart J. 351925–1931 (2014).
Van Karster, B. et al. Calibration: The Achilles heel of predictive analytics. BMC Med. 17230 (2019).
Vickers, AJ, Van Calster, B. & Steyerberg, EW A net-benefit approach to the evaluation of predictive models, molecular markers, and diagnostic tests. BMJMore 352i6 (2016).
Harrell, F. Multivariable modeling strategies. of: regression modeling strategy. Springer series of statistics. (Springer, Cham, 2015).
Steierberg, EW Clinical prediction model (Springer Nature, 2009).
Efron, B. & Tibshirani, RJ Introducing Bootstrap (CRC Press, 1994).
Futoma, J., Simons, M., Panch, T., Doshi-Velez, F. & Celi, LA The myth of generalizability in clinical research and machine learning in healthcare. lancet digital health 2e489–e492 (2020).
Wan, B., Caffo, B. & Vedula, SS A unified framework for the generalizability of clinical predictive models. front. Artif. intelligence. Fivehttps://doi.org/10.3389/frai.2022.872720 (2022).
de Hond, AAH etc. Predicting Readmission or Death After ICU Discharge: External Validation and Retraining of Machine Learning Models. critical. Caremed. 51291–300 (2023).
Austin, PC, etc. Geographic and Temporal Validity of Predictive Models: Various approaches were useful in examining model performance. J. Clin. Plague. 7976–85 (2016).
Steyerberg, EW, Nieboer, D., Debray, TPA & van Houwelingen, HC Assessing heterogeneity in a meta-analysis of individual participant data for predictive models: an overview and diagrams. in statistics 384290–4309 (2019).
Debray, TP et al. A new framework for enhancing the interpretation of external validation studies of clinical predictive models. J. Clin. Plague. 68279–289 (2015).
Cowley, LE, Farewell, DM, Maguire, S. & Kemp, AM Methodological criteria for the development and evaluation of clinical prediction rules: a review of the literature. signs of diagnosis.resolution 316 (2019).
Wynants, L. et al. Predictive models for covid-19 diagnosis and prognosis: a systematic review and critical evaluation. BMJMore 369m1328 (2020).
Gulati, G. et al. Generalizability of clinical predictive models for cardiovascular disease: 158 independent external validations of 104 unique models. Circumferential cardiovascular. Quar.result 15e008487 (2022).
Futoma, J., Simons, M., Panch, T., Doshi-Velez, F. & Celi, LA The myth of generalizability in clinical research and machine learning in healthcare. lancet digit health 2e489–e492 (2020).
Burns, ML & Kheterpal, S. The Age of Machine Learning Has Arrived: Local Impact and Nationwide Generalizability. Anesthesiology 132939–941 (2020).
de Hond, AAH etc. Guidelines and Quality Standards for Artificial Intelligence-Based Predictive Models in Healthcare: A Scoping Review. npj digital med. Five2 (2022).
Sperrin, M., Riley, RD, Collins, GS & Martin, GP Targeted Validation: Validation of Clinical Predictive Models in Intended Populations and Settings. signs of diagnosis.resolution 624 (2022).
Van Calster, B., Steyerberg, EW, Wynants, L. & van Smeden, M. There is no such thing as a validated predictive model. BMC Med. twenty one70 (2023).
Collins, GS, Reitsma, JB, Altman, DG & Moons, KGM Transparent Reporting of Multivariable Predictive Models for Individual Prognosis or Diagnosis (TRIPOD): The TRIPOD statement. EUR. Urol. 671142–1151 (2015).