Decision theory and metrics for evaluating predictive models

Written By Alyssa Pradhan
 

Decision theory and metrics for evaluating predictive models

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points.

  • 01:00 - Technical wrap - ChatGPT and Claude for healthcare, AI scribes

  • 07:40 - What is decision theory?

  • 33:20 - Evaluation of performance measures in predictive artificial intelligence models to support medical decisions

Some resources and papers we discuss:

Van Calster B et al Topic Group 6 of the STRATOS initiative. Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance. Lancet Digit Health. 2025 Dec;7(12):100916. doi: 10.1016/j.landig.2025.100916. Epub 2025 Dec 13. PMID: 41391983.

Vickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. BMJ. 2016 Jan 25;352:i6. doi: 10.1136/bmj.i6. PMID: 26810254; PMCID: PMC4724785.

 
 
Alyssa Pradhan
Next

In-context: January 5, 2026