From Uncertainty to Trust: Kernel Dropout for AI-Powered Medical Predictions

TL;DR

The paper tackles the challenge of trustworthy AI in healthcare by addressing uncertainty and data scarcity in medical predictions. It introduces a Bayesian deep learning model with kernel dropout and conjugate priors, allowing calibrated uncertainty estimation while leveraging pre-trained language models. Through experiments on SOAP, MT, and ROND datasets, the approach demonstrates improved reliability and uncertainty quantification, particularly in low-resource settings, and enables targeted human-in-the-loop intervention. The work advances practical AI deployment in medicine by providing probabilistic predictions that reflect confidence levels, thereby supporting safer and more efficient clinical decision-making.

Abstract

AI-driven medical predictions with trustworthy confidence are essential for ensuring the responsible use of AI in healthcare applications. The growing capabilities of AI raise questions about their trustworthiness in healthcare, particularly due to opaque decision-making and limited data availability. This paper proposes a novel approach to address these challenges, introducing a Bayesian Monte Carlo Dropout model with kernel modelling. Our model is designed to enhance reliability on small medical datasets, a crucial barrier to the wider adoption of AI in healthcare. This model leverages existing language models for improved effectiveness and seamlessly integrates with current workflows. Extensive evaluations of public medical datasets showcase our model's superior performance across diverse tasks. We demonstrate significant improvements in reliability, even with limited data, offering a promising step towards building trust in AI-driven medical predictions and unlocking its potential to improve patient care.

Figures (1)

• Figure 1: Uncertainty analysis across multiple datasets.