The myth of generalisability in clinical research and machine learning in health care

The Lancet Digital Health

Volumn 2, Issue 9, 2020, Pages e489-e492

  Futoma, Joseph ^a   Simons, Morgan ^b   Panch, Trishan ^c,d   Doshi Velez, Finale ^a   Celi, Leo Anthony ^c,e,f  

^a HARVARD UNIVERSITY   (United States)

^b NEW YORK UNIVERSITY MEDICAL CENTER   (United States)

^c HARVARD SCHOOL OF PUBLIC HEALTH   (United States)

^d Wellframe   (United States)

^e BETH ISRAEL DEACONESS MEDICAL CENTER   (United States)

^f Massachusetts Institute of Technology Cambridge   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLINICAL RESEARCH; MACHINE LEARNING; REVIEW;

EID: 85089745841     PISSN: None     EISSN: 25897500     Source Type: Journal    
DOI: 10.1016/S2589-7500(20)30186-2     Document Type: Review

References (34)

1. Truog, RD, Mitchell, C, Daley, GQ, The toughest triage—allocating ventilators in a pandemic. N Engl J Med 382 (2020), 1973–1975.
2. Wynants, L, Van Calster, B, Collins, GS, et al. Prediction models for diagnosis and prognosis of covid-19 infection: systematic review and critical appraisal. BMJ, 369, 2020, m1328.
3. Wang, Y, Yao, Q, Kwok, JT, Ni, LM, Generalizing from a few examples: a survey on few-shot learning. arXiv, 2020 published online March 29. https://doi.org/10.1145/3386252 (preprint).
4. Altman, DG, Royston, P, What do we mean by validating a prognostic model?. Stat Med 19 (2000), 453–473.
5. Justice, AC, Covinsky, KE, Berlin, JA, Assessing the generalizability of prognostic information. Ann Intern Med 130 (1999), 515–524.
6. Bluemke, DA, Moy, L, Bredella, MA, et al. Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers—from the radiology editorial board. Radiology 294 (2020), 487–489.
7. Leisman, DE, Harhay, MO, Lederer, DJ, et al. Development and reporting of prediction models: guidance for authors from editors of respiratory, sleep, and critical care journals. Crit Care Med 48 (2020), 623–633.
8. Luo, W, Phung, D, Tran, T, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res, 18, 2016, e323.
9. Ross, C, Hospitals are using AI to predict the decline of Covid-19 patients—before knowing it works. April 24, 2020. Stat. https://www.statnews.com/2020/04/24/coronavirus-hospitals-use-ai-to-predict-patient-decline-before-knowing-it-works. (Accessed 31 May 2020)
10. Gulshan, V, Rajan, RP, Widner, K, et al. Performance of a deep-learning algorithm vs manual grading for detecting diabetic retinopathy in India. JAMA Ophthalmol 137 (2019), 987–993.
11. Zech, JR, Badgeley, MA, Liu, M, Costa, AB, Titano, JJ, Oermann, EK, Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med, 15, 2018, e1002683.
12. Nagendran, M, Chen, Y, Lovejoy, CA, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ, 368, 2020, m689.
13. Bedoya, AD, Clement, ME, Phelan, M, Steorts, RC, O'Brien, C, Goldstein, BA, Minimal impact of implemented early warning score and best practice alert for patient deterioration. Crit Care Med 47 (2019), 49–55.
14. Downey, CL, Tahir, W, Randell, R, Brown, JM, Jayne, DG, Strengths and limitations of early warning scores: a systematic review and narrative synthesis. Int J Nurs Stud 76 (2017), 106–119.
15. Gerry, S, Bonnici, T, Birks, J, et al. Early warning scores for detecting deterioration in adult hospital patients: systematic review and critical appraisal of methodology. BMJ, 369, 2020, m1501.
16. Komorowski, M, Celi, LA, Badawi, O, Gordon, AC, Faisal, AA, The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med 24 (2018), 1716–1720.
17. Hampton, JR, Evidence-based medicine, opinion-based medicine, and real-world medicine. Perspect Biol Med 45 (2002), 549–568.
18. Sherman, RE, Anderson, SA, Dal Pan, GJ, et al. Real-world evidence—what is it and what can it tell us?. N Engl J Med 375 (2016), 2293–2297.
19. Panch, T, Pollard, TJ, Mattie, H, Lindemer, E, Keane, PA, Celi, LA, “Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets. NPJ Digit Med, 3, 2020, 87.
20. Gluud, LL, Bias in clinical intervention research. Am J Epidemiol 163 (2006), 493–501.
21. Jüni, P, Altman, DG, Egger, M, Systematic reviews in health care: assessing the quality of controlled clinical trials. BMJ 323 (2001), 42–46.
22. Rothwell, PM, Factors that can affect the external validity of randomised controlled trials. PLoS Clin Trials, 1, 2006, e9.
23. Rothwell, PM, External validity of randomised controlled trials: “To whom do the results of this trial apply?”. Lancet 365 (2005), 82–93.
24. Cooper, GF, Aliferis, CF, Ambrosino, R, et al. An evaluation of machine-learning methods for predicting pneumonia mortality. Artif Intell Med 9 (1997), 107–138.
25. Davis, SE, Lasko, TA, Chen, G, Siew, ED, Matheny, ME, Calibration drift in regression and machine learning models for acute kidney injury. J Am Med Inform Assoc 24 (2017), 1052–1061.
26. Nestor, B, McDermott, MBA, Boag, W, et al. Feature robustness in non-stationary health records: caveats to deployable model performance in common clinical machine learning tasks. Proc Mach Learn Res 106 (2019), 1–23.
27. Parisi, GI, Kemker, R, Part, JL, Kanan, C, Wermter, S, Continual lifelong learning with neural networks: a review. Neural Netw 113 (2019), 54–71.
28. US FDA. Proposed regulatory framework for modifications to artificial intelligence/machine learning (AI/ML)-based software as a medical device (SaMD): discussion paper and request for feedback. https://www.fda.gov/files/medical%20devices/published/US-FDA-Artificial-Intelligence-and-Machine-Learning-Discussion-Paper.pdf, 2019. (Accessed 31 May 2020)
29. Lee, CS, Lee, AY, Clinical applications of continual learning machine learning. Lancet Digit Health 2 (2020), e279–e281.
30. Wynants, L, Kent, DM, Timmerman, D, Lundquist, CM, Van Calster, B, Untapped potential of multicenter studies: a review of cardiovascular risk prediction models revealed inappropriate analyses and wide variation in reporting. Diagn Progn Res, 3, 2019, 6.
31. Riley, RD, Ensor, J, Snell, KIE, et al. External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges. BMJ, 353, 2016, i3140.
32. Agniel, D, Kohane, IS, Weber, GM, Biases in electronic health record data due to processes within the healthcare system: retrospective observational study. BMJ, 361, 2018, k1479.
33. Wiens, J, Guttag, J, Horvitz, E, A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions. J Am Med Inform Assoc 21 (2014), 699–706.
34. Sharafoddini, A, Dubin, JA, Maslove, DM, Lee, J, A new insight into missing data in intensive care unit patient profiles: observational study. JMIR Med Inform, 7, 2019, e11605.