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

Yand Wang; Chen Zhang; Lanyun Zhu; Yixin Chen; Qunbo Wang; Yutong Bai; Jurgen Germann; Yinghong Wen

cs.CVMar 2, 2026

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

Authors: Yand Wang, Chen Zhang, Lanyun Zhu, Yixin Chen, Qunbo Wang, Yutong Bai, Jurgen Germann, Yinghong Wen,

Organizations: Beijing Jiaotong University · Nanyang Technological University · Institute of Medical Technology, Peking University · Beijing Tiantan Hospital, Capital Medical University ·

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.

Figures & tables

Figure 1: Overview of PreSight . Given preoperative MRI and clinical records, PreSight predicts postoperative DBS responsiveness in PD. Clinical variables are converted into text prompts and encoded by a large language model into patient-specific embeddings, which modulate region-prior morphometric maps via a Patient-Specific Weighting Module . The resulting weighted deformation-based morphometry (DBM) features are fed into a classifier to determine responders and non-responders.

Figure 2: Multi-view visualization of parcellation and region-wise weights (axial, sagittal, coronal). Columns show MRI, atlas parcellation, region-wise weighting (opacity $\propto$ weight), and DBM visualizations (DBM, DBM+parcellation, DBM+weighting).

Method	Internal Test			External Test
	ACC (↑)	TPR (↑)	FPR(↓)	ACC (↑)	TPR (↑)	FPR(↓)
Clinical+XGBoost [ chen2016xgboost ]	63.89	83.33	75.00	55.88	52.94	41.18
Radiomics + LASSO [ aerts2014radiomics ]	69.44	79.17	50.00	58.82	64.71	47.06
Radiomics + SVM [ aerts2014radiomics ]	75.00	70.83	16.67	61.76	76.47	52.94
S3D [ wald2025revisiting ]	80.56	91.67	41.67	82.35	88.24	23.53
Swin UNETR [ tang2022self ]	77.78	95.83	58.33	73.53	82.35	35.29

Table 1: Comparison across input modalities and backbones. Higher is better for ACC/TPR (↑); lower is better for FPR (↓). All methods use identical patient-wise splits, preprocessing, and fixed decision thresholds chosen on the internal development split and transferred to the external cohort without fine-tuning or recalibration.

DBM	PSWM components		ACC
	Prior	Patient-specific	(%)
✓			77.78
✓	✓		80.56
✓		✓	83.33
✓	✓	✓	88.89
	✓	✓	72.22

Table 2: Ablation on DBM and the Patient-Specific Weighting Module (PSWM). ✓indicates the component is enabled.

Clinical Outcome Prediction

Clinical outcome prediction uses patient records, imaging, signals, and biomarkers to estimate risks, disease trajectories, treatment response, and survival.

See all 265 papers

Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model
Mar 31, 2026Siyuan Du, Siyi Li, Shuwei Bai +10Clinical Outcome Prediction Parkinson's Disease
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · Shanghai AI Laboratory, Shanghai, China · University of Science and Technology of China, Anhui, China +6
Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features
Jun 26, 2026Aixa X. AndradeClinical Outcome Prediction Explainable Medical Image Analysis
Lyda Hill Department of Bioinformatics · Department of Biomedical Engineering · University of Texas Southwestern Medical Center, Dallas, Texas, USA
From Visual Attribution to Clinical Reasoning: Explainable Parkinson's Disease Screening from Hand-Drawn Patterns
Sep 13, 2026Aritra Dey, Utsav Kumar Nareti, Chandranath Adak +3Parkinson's Disease Classification Parkinson's Disease
Dept. of CSE, Indian Institute of Technology Indore, India-453552 · Dept. of CSE, Indian Institute of Technology Patna, India-801106 · M. R. Bangur Hospital, West Bengal, India-700033 +1

Mar 31, 2026J/K move · Enter open · S save

Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model

Siyuan Du, Siyi Li, Shuwei Bai, Ang Li+9

College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · Shanghai AI Laboratory, Shanghai, China · University of Science and Technology of China, Anhui, China+6

Clinical Outcome Prediction Parkinson's Disease fMRI Foundation Models

Open paper AskPDF arXiv

Parkinson's disease (PD) affects over ten million people worldwide. Although temporal interference (TI) and deep brain stimulation (DBS) are promising therapies, inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost. Previous explorations either resort to limited statistical biomarkers that are insufficient to characterize variability, or employ AI-driven methods which is prone to overfitting and opacity. We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI. Critically, a generative virtual brain foundation model, pretrained on a collective dataset (2707 subjects, 5621 sessions) to capture universal disorder patterns, was finetuned on PD cohorts receiving TI (n=51) or DBS (n=55) to yield individualized virtual brains with high fidelity to empirical functional connectivity (r=0.935). By constructing counterfactual estimations between pathological and healthy neural states within these personalized models, we predicted clinical responses (TI: AUPR=0.853; DBS: AUPR=0.915), substantially outperforming baselines. External and prospective validations (n=14, n=11) highlight the feasibility of clinical translation. Moreover, our framework provides state-dependent regional patterns linked to response, offering hypothesis-generating mechanistic insights.

Abstract

Clinical Outcome Prediction

Explore similar work

Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model

Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features

From Visual Attribution to Clinical Reasoning: Explainable Parkinson's Disease Screening from Hand-Drawn Patterns