CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support

2026-05-19

AI Summary

This study addresses the critical gap in reliable uncertainty quantification for AI models predicting levodopa equivalent daily dose (LEDD) in Parkinson’s disease management, which hinders confident clinical decision-making. The authors propose CASCADE, a novel framework that seamlessly bridges classification and continuous dose prediction by directly mapping the epistemic uncertainty of a screening classifier—via Venn–Abers predictors—into nonconformity scores, eliminating the need for auxiliary residual regression. Integrating conformal prediction with a two-stage modeling strategy, CASCADE yields prediction intervals that are 38.9% narrower than standard methods for high-confidence patients while adaptively widening for uncertain cases to maintain robust coverage guarantees.

Abstract

Effective medication management in Parkinson's Disease (PD) is challenging due to heterogeneous disease progression, variable patient response, and medication side effects. While AI models can forecast levodopa equivalent daily dose (LEDD) as a measure of medication needs, standard uncertainty quantification often fails to communicate the reliability of these predictions, treating high and low confidence clinical decisions identically. We introduce CASCADE (Calibrated Adaptive Scaling via Conformal And Distributional Estimation), a novel conformal prediction framework that propagates epistemic uncertainty from a screening classifier to adapt downstream predictions. Unlike standard conformal methods that rely on auxiliary residual regression, we leverage epistemic uncertainty from a primary classification task (identifying whether a medication change is needed) to dynamically scale the prediction intervals of a secondary regression task (predicting how much change). By mapping Venn-Abers multi-probabilistic uncertainty directly to non-conformity scores, our framework achieves continuous risk adaptation. We demonstrate that this ``cascade effect'' produces highly efficient intervals for confident patients (38.9% narrower than standard conformal baselines) while automatically expanding intervals to ensure robust coverage for uncertain cases, bridging the gap between discrete clinical decision-making and continuous dose forecasting in PD.

Problem

• Parkinson's Disease
• uncertainty quantification
• clinical decision support
• conformal prediction
• medication management

Innovation

• conformal prediction
• epistemic uncertainty
• Venn-Abers calibration
• adaptive prediction intervals
• two-stage decision support