Informative Priors Improve the Reliability of Multimodal Clinical Data Classification
This work addresses the need for improved reliability in machine learning for clinical decision support, though it appears incremental as it builds on existing Bayesian neural network methods.
The authors tackled the problem of unreliable uncertainty quantification in clinical decision support by designing a multimodal data-driven prior for Bayesian neural networks, resulting in a more reliable predictive model for acute care condition classification using MIMIC-IV and MIMIC-CXR data.
Machine learning-aided clinical decision support has the potential to significantly improve patient care. However, existing efforts in this domain for principled quantification of uncertainty have largely been limited to applications of ad-hoc solutions that do not consistently improve reliability. In this work, we consider stochastic neural networks and design a tailor-made multimodal data-driven (M2D2) prior distribution over network parameters. We use simple and scalable Gaussian mean-field variational inference to train a Bayesian neural network using the M2D2 prior. We train and evaluate the proposed approach using clinical time-series data in MIMIC-IV and corresponding chest X-ray images in MIMIC-CXR for the classification of acute care conditions. Our empirical results show that the proposed method produces a more reliable predictive model compared to deterministic and Bayesian neural network baselines.