Ensuring Ground Truth Accuracy in Healthcare with the EVINCE framework

TL;DR

The paper introduces EVINCE, a novel framework using multiple Large Language Models in a debate setting to improve diagnosis accuracy and correct misdiagnoses, thereby enhancing healthcare data reliability.

Contribution

EVINCE is a new system that applies a structured debate among LLMs to optimize diagnosis accuracy and reduce training data errors in healthcare.

Findings

EVINCE effectively improves diagnosis accuracy.

The framework reduces misdiagnosis propagation.

Empirical results confirm EVINCE's effectiveness.

Abstract

Misdiagnosis is a significant issue in healthcare, leading to harmful consequences for patients. The propagation of mislabeled data through machine learning models into clinical practice is unacceptable. This paper proposes EVINCE, a system designed to 1) improve diagnosis accuracy and 2) rectify misdiagnoses and minimize training data errors. EVINCE stands for Entropy Variation through Information Duality with Equal Competence, leveraging this novel theory to optimize the diagnostic process using multiple Large Language Models (LLMs) in a structured debate framework. Our empirical study verifies EVINCE to be effective in achieving its design goals.