Towards Interpretable Renal Health Decline Forecasting via Multi-LMM Collaborative Reasoning Framework

TL;DR

This paper introduces a collaborative framework that improves open-source multimodal models for predicting renal health decline, achieving high accuracy and interpretability with clinically meaningful explanations.

Contribution

It proposes a novel framework integrating visual knowledge transfer, abductive reasoning, and memory mechanisms to enhance open-source LMMs for eGFR forecasting with interpretability.

Findings

Achieves performance comparable to proprietary models.

Provides plausible clinical reasoning explanations.

Enhances interpretability without sacrificing accuracy.

Abstract

Accurate and interpretable prediction of estimated glomerular filtration rate (eGFR) is essential for managing chronic kidney disease (CKD) and supporting clinical decisions. Recent advances in Large Multimodal Models (LMMs) have shown strong potential in clinical prediction tasks due to their ability to process visual and textual information. However, challenges related to deployment cost, data privacy, and model reliability hinder their adoption. In this study, we propose a collaborative framework that enhances the performance of open-source LMMs for eGFR forecasting while generating clinically meaningful explanations. The framework incorporates visual knowledge transfer, abductive reasoning, and a short-term memory mechanism to enhance prediction accuracy and interpretability. Experimental results show that the proposed framework achieves predictive performance and interpretability comparable to proprietary models. It also provides plausible clinical reasoning processes behind each prediction. Our method sheds new light on building AI systems for healthcare that combine predictive accuracy with clinically grounded interpretability.