Large Language Model-Derived Priors Can Improve Bayesian Survival Analyses: A Glioblastoma Application

TL;DR

This paper demonstrates that AI-generated priors can effectively enhance Bayesian survival analysis for glioblastoma, offering a faster and potentially more reliable alternative to expert elicitation.

Contribution

It introduces a method for using generative AI to create priors for Bayesian models in medical survival analysis, validated on real glioblastoma data.

Findings

AI-generated priors were preferred over expert elicited priors.

AI priors led to stable posterior estimates in sensitivity analysis.

The approach accelerates prior construction in Bayesian modeling.

Abstract

This report describes an application of artificial intelligence (AI) to the Bayesian analysis of glioblastoma survival data. It has been suggested that AI can be used to construct prior distributions for parameters in Bayesian models rather than using the difficult, unreliable, and time-consuming process of eliciting expert opinion from radiation oncologists. Here, we show how generative AI can quickly propose sensible prior distributions of the hazard ratio comparing two glioblastoma therapies, for a standard Bayesian survival model on real data. Three Chatbots generated two alternative priors each which were evaluated by a radiation oncologist and then used in a sensitivity analysis to assess posterior stability. The results suggest that, for this cancer survival analysis, priors from generative AI are a preferred alternative method to expert elicitation.