PreSight: Preoperative Outcome Prediction for Parkinson's Disease via Region-Prior Morphometry and Patient-Specific Weighting

2026-03-02

AI Summary

This study addresses the challenge of accurately predicting postoperative motor improvement in Parkinson’s disease patients prior to surgery, a task hindered by weak neuroimaging signals and high inter-patient heterogeneity. To this end, we propose an end-to-end interpretable model that integrates clinical priors, preoperative multimodal MRI, and deformation-based morphometry (DBM). The core innovation lies in a patient-specific weighting module that dynamically modulates the contribution of individual brain regions to outcome prediction, thereby enhancing personalized accuracy while preserving clinical interpretability. Evaluated on a real-world bicentric cohort of 400 patients, the model achieved an internal validation accuracy of 88.89% and an external test accuracy of 85.29%, significantly outperforming existing baselines. It also demonstrated superior probabilistic calibration and greater net benefit in decision curve analysis.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Preoperative improvement rate prediction for Parkinson's disease surgery is clinically important yet difficult because imaging signals are subtle and patients are heterogeneous. We address this setting, where only information available before surgery is used, and the goal is to predict patient-specific postoperative motor benefit. We present PreSight, a presurgical outcome model that fuses clinical priors with preoperative MRI and deformation-based morphometry (DBM) and adapts regional importance through a patient-specific weighting module. The model produces end-to-end, calibrated, decision-ready predictions with patient-level explanations. We evaluate PreSight on a real-world two-center cohort of 400 subjects with multimodal presurgical inputs and postoperative improvement labels. PreSight outperforms strong clinical, imaging-only, and multimodal baselines. It attains 88.89% accuracy on internal validation and 85.29% on an external-center test for responder classification and shows better probability calibration and higher decision-curve net benefit. Ablations and analyses confirm the contribution of DBM and the patient-specific weighting module and indicate that the model emphasizes disease-relevant regions in a patient-specific manner. These results demonstrate that integrating clinical prior knowledge with region-adaptive morphometry enables reliable presurgical decision support in routine practice.

Problem

• Parkinson's disease
• preoperative prediction
• surgical outcome
• patient heterogeneity
• motor improvement

Innovation

• region-prior morphometry
• patient-specific weighting
• preoperative outcome prediction
• deformation-based morphometry
• clinical decision support