Explicit causal reasoning is needed to prevent prognostic models being victims of their own success

Affiliations

Comment

Matthew Sperrin et al. J Am Med Inform Assoc. 2019.

. 2019 Dec 1;26(12):1675-1676.

doi: 10.1093/jamia/ocz197.

¹ Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom.

No abstract available

Comment in

Explicit causal reasoning is preferred, but not necessary for pragmatic value.
Lenert MC, Matheny ME, Walsh CG. Lenert MC, et al. J Am Med Inform Assoc. 2019 Dec 1;26(12):1677-1678. doi: 10.1093/jamia/ocz198. J Am Med Inform Assoc. 2019. PMID: 31722412 Free PMC article. No abstract available.

Prognostic models will be victims of their own success, unless….
Lenert MC, Matheny ME, Walsh CG. Lenert MC, et al. J Am Med Inform Assoc. 2019 Dec 1;26(12):1645-1650. doi: 10.1093/jamia/ocz145. J Am Med Inform Assoc. 2019. PMID: 31504588 Free PMC article.

1. Lenert MC, Matheny ME, Walsh CG.. Prognostic models will be victims of their own success, unless. J Am Med Informatics Assoc 2019; 2612: 1645–1650. - PMC - PubMed
1. Hernan MA, Robins JM.. Causal Inference. Boca Raton, FL: Chapman & Hall/CRC; 2019.
1. Cheong‐See F, Allotey J, Marlin N.. Prediction models in obstetrics: understanding the treatment paradox and potential solutions to the threat it poses. BJOG 2016; 1237: 1060–4. doi: 10.1111/1471-0528.13859/pdf. - PubMed
1. Sperrin M, Martin GP, Pate A, et al. Using marginal structural models to adjust for treatment drop-in when developing clinical prediction models. Stat Med 2018; 3728: 4142–54. - PMC - PubMed
1. Jenkins DA, Sperrin M, Martin GP, et al. Dynamic models to predict health outcomes: current status and methodological challenges. Diagn Progn Res 2018; 2: 23. - PMC - PubMed