# Data-Driven Priors for Uncertainty-Aware Risk Prediction of Clinical Deterioration using Multimodal Data

arXiv: https://arxiv.org/abs/2603.08459 · HTML: https://mlsanity.com/paper/2603.08459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks](https://mlsanity.com/paper/1912.10481/) (2019)
- [MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images](https://mlsanity.com/paper/2207.07027/) (2022)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks](https://mlsanity.com/paper/2211.12717/) (2022)
- [Leveraging Uncertainty Estimates for Predicting Segmentation Quality](https://mlsanity.com/paper/1807.00502/) (2018)
- [Tractable Function-Space Variational Inference in Bayesian Neural Networks](https://mlsanity.com/paper/2312.17199/) (2023)
- [Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial](https://mlsanity.com/paper/2305.04933/) (2023)
- [Function-Space Regularization in Neural Networks: A Probabilistic Perspective](https://mlsanity.com/paper/2312.17162/) (2023)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Should We Learn Most Likely Functions or Parameters?](https://mlsanity.com/paper/2311.15990/) (2023)
- [Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Data](https://mlsanity.com/paper/2309.16220/) (2023)
- [Early hospital mortality prediction using vital signals](https://mlsanity.com/paper/1803.06589/) (2018)
- [Benchmarking Uncertainty Quantification on Biosignal Classification Tasks under Dataset Shift](https://mlsanity.com/paper/2112.09196/) (2021)
- [Informative Priors Improve the Reliability of Multimodal Clinical Data Classification](https://mlsanity.com/paper/2312.00794/) (2023)

## Abstract (arXiv)

Safe predictions are a crucial requirement for integrating predictive models into clinical decision support systems. One approach to improving trustworthiness is to enable models to express uncertainty about individual predictions. However, current machine learning models frequently lack reliable uncertainty estimation, hindering real-world deployment. This limitation is particularly evident in multimodal settings, where models must effectively integrate heterogeneous information. In this work, we propose MedCertAIn, a predictive uncertainty framework that leverages multimodal clinical data to improve model performance and reliability for in-hospital mortality risk prediction as an indicator of patient deterioration. 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 MedCertAIn achieves competitive predictive performance and substantial gains in selective prediction compared with the evaluated deterministic and stochastic baselines. These findings highlight the promise of data-driven priors in advancing robust, uncertainty-aware AI tools for high-stakes clinical applications. Our implementation is publicly available at: https://github.com/jlaitue/medcertain.