Training-free Design of Deep Networks as Ensembles of Clinical Experts

Abstract

Artificial intelligence (AI) techniques such as deep learning hold tremendous potential for improving clinical practice. However, clinical data complexity and the need for extensive specialized knowledge represent major challenges in the current, human-driven model design. Moreover, as human interpretation of a clinical problem is inherently encoded in the model, the conventional single model paradigm is subjective and cannot fully capture the prediction uncertainty. Here, we present a fast and accurate framework for automated clinical deep learning, TEACUP (training-free assembly as clinical uncertainty predictor). The core of TEACUP is a newly developed metric that faithfully characterizes the quality of deep networks without incurring any cost for training of these networks. When compared to conventional, training-based approaches, TEACUP reduces computation costs by more than 90% while achieving improved performance across distinct clinical tasks. This efficiency allows TEACUP to create ensembles of expert AI models, mimicking the recommended clinical practice of using multiple human experts when interpreting medical data. By combining multiple perspectives, TEACUP provides more robust predictions and uncertainty quantification, paving the way for more reliable clinical AI.