Principled Uncertainty in Clinical AI: End-to-End Bayesian Modelling and Algorithmic Equity Auditing Across Multimodal Patient Data
2026-06-08 • Computers and Society
Computers and Society
AI summaryⓘ
The authors developed a special AI system for medical data that not only makes predictions but also tells how uncertain those predictions are. Their method uses Bayesian techniques to measure two types of uncertainty and combines information from different data sources. They tested their system on simulated patients and found that higher uncertainty often identified groups of patients who might be underserved, like those in rural areas or with lower income. This suggests that understanding AI uncertainty can help highlight fairness issues across different patient groups. The authors show this uncertainty is useful beyond just improving AI accuracy—it can guide equity in healthcare.
Bayesian uncertaintymultimodal clinical dataprobabilistic deep learningaleatoric uncertaintyepistemic uncertaintymodel calibrationExpected Calibration Erroralgorithmic equityvariational encoderslate fusion
Authors
Oladimeji Anthonio, Dimeji Abdulsobur Olawuyi, Oloruntoba Ajayi, Temiloluwa Aderemi, Joseph Odamo
Abstract
Clinical artificial intelligence (AI) systems routinely produce predictions without principled quantification of uncertainty, limiting their trustworthiness in high-stakes medical environments. This paper presents an integrated research programme addressing two interconnected problems: (1) the development of a fully end-to-end Bayesian uncertainty modelling framework for multimodal clinical data, and (2) the application of calibrated uncertainty estimates as a formal measure of algorithmic equity across patient subgroups. We construct a probabilistic deep learning architecture comprising modality-specific variational encoders, a precision-weighted late fusion mechanism, and a decomposed uncertainty output head that separates aleatoric from epistemic uncertainty. The system is trained with a composite Bayesian loss incorporating binary cross-entropy, Kullback-Leibler divergence regularisation, and an uncertainty calibration penalty. We evaluate model calibration using Expected Calibration Error (ECE = 0.096) and conduct a subgroup equity audit across facility type, socioeconomic status, age group, and biological sex on a dataset of 1,000 simulated patients. Results demonstrate that epistemic uncertainty systematically identifies underserved populations: primary/rural facility patients show a 15.3% uncertainty equity gap (p < 0.001, effect size = 0.698), low socioeconomic status patients exhibit a 6.8% gap (p < 0.001), and elderly patients show a 3.9% gap (p < 0.001), whilst no significant sex-based disparity is detected. These findings establish that calibrated uncertainty is not merely a technical property of probabilistic models but constitutes an actionable equity signal with direct clinical relevance.