# Bayesian mediation analysis using patient-reported outcomes from AI chatbots to infer causal pathways in clinical trials

## TL;DR

This paper introduces a new method using AI chatbots and Bayesian analysis to better understand how treatments affect patient outcomes in clinical trials.

## Contribution

A novel Bayesian mediation framework is proposed to analyze patient-reported outcomes from AI chatbots in clinical trials.

## Key findings

- The Bayesian framework effectively decomposed total effects into direct and indirect components with low bias.
- Robust coverage of over 85% was achieved in estimating mediation pathway variables.
- The method supports scalable and adaptive causal pathway analysis in clinical trials.

## Abstract

The integration of artificial intelligence (AI) chatbots into clinical trials offers a transformative approach to collecting patient-reported outcomes (PROs). Despite the increasing use of AI chatbots for real-time, interactive data gathering, systematic frameworks for analyzing these rich datasets—especially in uncovering causal relationships—remain limited. This study addresses this gap by applying a Bayesian mediation framework to PROs collected via AI chatbot interactions, uncovering causal pathways linking treatment effects to outcomes through mediators like adverse events and patient-specific covariates. Using a simulation-based approach with GPT-4o, synthetic patient-chatbot dialogues were generated to evaluate the performance of the Bayesian mediation framework, which effectively decomposed total effects into direct and indirect components while quantifying uncertainty through credible intervals. The results demonstrated low bias (<0.05), robust coverage (>85%), in estimation of the direct, indirect effect and other variables of the mediation pathways, underscoring its potential to improve clinical trial data accuracy and depth. By integrating AI chatbot-based PRO collection with Bayesian mediation analysis, this study presents a scalable and adaptive framework for quantifying causal pathways, enhancing the quality of patient-reported data, and supporting personalized, data-driven decision-making in clinical trials.