PRISM: A Framework Harnessing Unsupervised Visual Representations and Textual Prompts for Explainable MACE Survival Prediction from Cardiac Cine MRI

TL;DR

PRISM is a novel self-supervised framework that combines cardiac MRI imaging features with electronic health records using textual prompts, significantly improving MACE prediction accuracy across multiple clinical cohorts.

Contribution

It introduces a prompt-guided representation integration method that leverages unsupervised visual features and textual prompts for explainable survival analysis in cardiac prognosis.

Findings

PRISM outperforms classical and state-of-the-art models in survival prediction.

Identifies three imaging signatures linked to elevated MACE risk.

Highlights key clinical factors like hypertension, diabetes, and smoking as major contributors.

Abstract

Accurate prediction of major adverse cardiac events (MACE) remains a central challenge in cardiovascular prognosis. We present PRISM (Prompt-guided Representation Integration for Survival Modeling), a self-supervised framework that integrates visual representations from non-contrast cardiac cine magnetic resonance imaging with structured electronic health records (EHRs) for survival analysis. PRISM extracts temporally synchronized imaging features through motion-aware multi-view distillation and modulates them using medically informed textual prompts to enable fine-grained risk prediction. Across four independent clinical cohorts, PRISM consistently surpasses classical survival prediction models and state-of-the-art (SOTA) deep learning baselines under internal and external validation. Further clinical findings demonstrate that the combined imaging and EHR representations derived from PRISM provide valuable insights into cardiac risk across diverse cohorts. Three distinct imaging signatures associated with elevated MACE risk are uncovered, including lateral wall dyssynchrony, inferior wall hypersensitivity, and anterior elevated focus during diastole. Prompt-guided attribution further identifies hypertension, diabetes, and smoking as dominant contributors among clinical and physiological EHR factors.