Uncertainty-Aware Prediction of Parkinson's Disease Medication Needs: A Two-Stage Conformal Prediction Approach

2025-08-13

AI Summary

Parkinson’s disease (PD) drug management faces challenges from heterogeneous disease progression and inter-individual variability in treatment response; current trial-and-error approaches lack quantification of predictive uncertainty, often leading to suboptimal dosing. This study proposes the first two-stage conformal prediction framework for PD medication demand forecasting—introducing statistically guaranteed conformal inference to this domain for the first time. It jointly addresses modeling of zero-inflated Levodopa Equivalent Daily Dose (LEDD) data and dynamic uncertainty quantification. Trained on 631 real-world inpatient records, the method produces time-evolving, statistically valid prediction intervals. Compared with conventional models, it achieves significantly shorter interval widths, higher empirical coverage accuracy, and enhanced clinical interpretability. The framework delivers individualized, dopamine-responsive dose adjustment support that balances short-term precision with long-term robustness—aiding neurologists in evidence-based, uncertainty-aware clinical decision-making.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Sequential Decision Making
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Consent frameworks and practices on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Parkinson's Disease (PD) medication management presents unique challenges due to heterogeneous disease progression and treatment response. Neurologists must balance symptom control with optimal dopaminergic dosing based on functional disability while minimizing side effects. This balance is crucial as inadequate or abrupt changes can cause levodopa-induced dyskinesia, wearing off, and neuropsychiatric effects, significantly reducing quality of life. Current approaches rely on trial-and-error decisions without systematic predictive methods. Despite machine learning advances, clinical adoption remains limited due to reliance on point predictions that do not account for prediction uncertainty, undermining clinical trust and utility. Clinicians require not only predictions of future medication needs but also reliable confidence measures. Without quantified uncertainty, adjustments risk premature escalation to maximum doses or prolonged inadequate symptom control. We developed a conformal prediction framework anticipating medication needs up to two years in advance with reliable prediction intervals and statistical guarantees. Our approach addresses zero-inflation in PD inpatient data, where patients maintain stable medication regimens between visits. Using electronic health records from 631 inpatient admissions at University of Florida Health (2011-2021), our two-stage approach identifies patients likely to need medication changes, then predicts required levodopa equivalent daily dose adjustments. Our framework achieved marginal coverage while reducing prediction interval lengths compared to traditional approaches, providing precise predictions for short-term planning and wider ranges for long-term forecasting. By quantifying uncertainty, our approach enables evidence-based decisions about levodopa dosing, optimizing symptom control while minimizing side effects and improving life quality.

Problem

• Predict Parkinson's medication needs with uncertainty awareness
• Address zero-inflation in PD inpatient medication data
• Provide reliable confidence measures for clinical decisions

Innovation

• Two-stage conformal prediction for medication needs
• Handles zero-inflation in Parkinson's inpatient data
• Provides reliable prediction intervals with statistical guarantees