Medical Model Synthesis Architectures: A Case Study

TL;DR

This paper introduces MedMSA, a framework using language models and probabilistic modeling to improve AI-driven clinical decision-making under uncertainty, emphasizing transparency and calibration.

Contribution

The paper presents a novel framework combining language models with formal probabilistic models for transparent, calibrated clinical predictions under uncertainty.

Findings

Proof-of-concept for differential diagnosis with uncertainty weighting

Framework supports verifiable inferences in clinical settings

Potential for safe AI-human clinical collaboration

Abstract

Medicine is rife with high-stakes uncertainty. Doctors routinely make clinical judgments and decisions that juggle many fundamental unknowns, like predictions about what might be causing a patients' symptoms or decisions about what treatment to try next. Despite increasing interest in developing AI systems that aid or even replace doctors in clinical settings, current systems struggle with calibrated reasoning under uncertainty, and are often deeply opaque about their reasoning. We propose a framework for AI systems that can make practically useful but formally transparent clinical predictions under uncertainty. Given a clinical situation, our framework (MedMSA) uses language models to retrieve relevant prior knowledge, but constructs a formal probabilistic model to support calibrated and verifiable inferences under uncertainty. We show how an initial proof-of-concept of this framework can be used for differential diagnosis, producing an uncertainty-weighted list of potential diagnoses that could explain a patients' symptoms, and discuss future applications and directions for applying this framework more generally for safe clinical collaborations.