Data-Driven Priors for Uncertainty-Aware Deterioration Risk Prediction with Multimodal Data

2026-03-09

AI Summary

Existing clinical prediction models lack reliable uncertainty estimation under multimodal data, hindering their trustworthy deployment in high-stakes medical settings. To address this limitation, this work proposes MedCertAIn, a novel framework that introduces data-driven neural network priors into multimodal clinical prediction for the first time. By leveraging self-supervised learning, MedCertAIn jointly models clinical time-series data and chest X-ray images, establishing cross-modal similarity while incorporating modality-specific perturbations. Evaluated on the MIMIC-IV and MIMIC-CXR datasets, the proposed method significantly outperforms both deterministic and Bayesian baselines, achieving higher predictive accuracy alongside better-calibrated and more interpretable uncertainty quantification.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Safe predictions are a crucial requirement for integrating predictive models into clinical decision support systems. One approach for ensuring trustworthiness is to enable models'ability to express their uncertainty about individual predictions. However, current machine learning models frequently lack reliable uncertainty estimation, hindering real-world deployment. This is further observed in multimodal settings, where the goal is to enable effective information fusion. In this work, we propose $\texttt{MedCertAIn}$, a predictive uncertainty framework that leverages multimodal clinical data for in-hospital risk prediction to improve model performance and reliability. We design data-driven priors over neural network parameters using a hybrid strategy that considers cross-modal similarity in self-supervised latent representations and modality-specific data corruptions. We train and evaluate the models with such priors using clinical time-series and chest X-ray images from the publicly-available datasets MIMIC-IV and MIMIC-CXR. Our results show that $\texttt{MedCertAIn}$ significantly improves predictive performance and uncertainty quantification compared to state-of-the-art deterministic baselines and alternative Bayesian methods. These findings highlight the promise of data-driven priors in advancing robust, uncertainty-aware AI tools for high-stakes clinical applications.

Problem

• uncertainty estimation
• multimodal data
• clinical decision support
• predictive reliability
• risk prediction

Innovation

• data-driven priors
• uncertainty quantification
• multimodal fusion
• Bayesian neural networks
• clinical risk prediction