Can Intra-Operative Stimulation Data Predict Post-Operative Deep Brain Stimulation Outcomes? — A Machine Learning Approach Based on Probabilistic Maps
Abstract
Introduction - Deep Brain Stimulation is an established treatment for movement disorders. Data driven approaches like probabilistic mapping and predictive modeling are being increasingly used to optimize stimulation parameter selection. However, it remains unclear whether intra-operative test data alone can reliably inform such models. Clarifying the predictive value of intra operative data is essential, as it may influence data collection strategies and surgical and programming protocols. Objective - This study examined whether post-operative DBS effects can be accurately predicted using intra-operative data alone or if post-operative information is required. Methods - A dataset comprising 1117 intra-operative and 1553 post-operative stimulation tests from 35 patients (14 Essential Tremor, 21 Parkinson’s Disease) was analyzed. Volumes of tissue activated (VTAs) were simulated to generate probabilistic maps, from which mapping and target anatomy-related features were extracted to train predictive classification models (low and high improvement, side effects). Model performance was assessed across scenarios linking intra- and post-operative data. Results - Intra-operative data effectively identified regions associated with optimal stimulation, highlighting their utility in guiding parameter selection (predictive accuracy ~60%). However, the predictive relationship between VTAs, probabilistic maps, and clinical outcomes differed between intra- and post-operative contexts. When trained solely on intra-operative VTAs, the model performed at a near chance level (predictive accuracy ~35%). Discussion - The study demonstrates that while intra-operative data are useful for identifying optimal target regions, they are insufficient for accurately predicting post-operative DBS outcomes. Incorporating post-operative data remains crucial for reliable and clinically meaningful DBS effect prediction. Highlights • Intra-operative DBS maps locate optimal stimulation regions • Intra-operative DBS data alone poorly predict post-operative outcomes • Predictive VTA–effects relationships differ intra- vs post-operatively
Related
- Fear learning–induced brain dynamics predict individual extinction memory expression following transcranial magnetic stimulation
- Spinal energy balance can predict post-operative spine alignment in Lenke 1 Adolescent Idiopathic Scoliosis
- The Association of Intra-Operative Steroid Administration on Hearing Threshold and Speech Perception Outcomes in Adult Cochlear Implant Recipients: A Retrospective Cohort Study.
- Response to comment on “Using genomic data and machine learning to predict antibiotic resistance: A tutorial paper”
- Serum proteins predict incident inflammatory bowel disease 14 years before diagnosis: a machine-learning and Cox modelling in the UK Biobank
BibTeX
@article{bucciarelli2026intraoperative,
title = {{Can Intra-Operative Stimulation Data Predict Post-Operative Deep Brain Stimulation Outcomes? — A Machine Learning Approach Based on Probabilistic Maps}},
author = {Vittoria Bucciarelli and Teresa Nordin and Marc Stawiski and Karin Wårdell and Jérôme Coste and Jean-Jacques Lemaire and Philippe Derost and Bérengère Debilly and Raphael Guzman and Simone Hemm and Dorian Vogel},
journal = {Deep Brain Stimulation},
year = {2026},
month = sep,
doi = {10.1016/j.jdbs.2026.09.003},
url = {https://uca.hal.science/hal-05745590v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Can Intra-Operative Stimulation Data Predict Post-Operative Deep Brain Stimulation Outcomes? — A Machine Learning Approach Based on Probabilistic Maps
AU - Vittoria Bucciarelli
AU - Teresa Nordin
AU - Marc Stawiski
AU - Karin Wårdell
AU - Jérôme Coste
AU - Jean-Jacques Lemaire
AU - Philippe Derost
AU - Bérengère Debilly
AU - Raphael Guzman
AU - Simone Hemm
AU - Dorian Vogel
PY - 2026
DA - 2026/09/08
JO - Deep Brain Stimulation
DO - 10.1016/j.jdbs.2026.09.003
UR - https://uca.hal.science/hal-05745590v1
AB - Introduction - Deep Brain Stimulation is an established treatment for movement disorders. Data driven approaches like probabilistic mapping and predictive modeling are being increasingly used to optimize stimulation parameter selection. However, it remains unclear whether intra-operative test data alone can reliably inform such models. Clarifying the predictive value of intra operative data is essential, as it may influence data collection strategies and surgical and programming protocols. Objective - This study examined whether post-operative DBS effects can be accurately predicted using intra-operative data alone or if post-operative information is required. Methods - A dataset comprising 1117 intra-operative and 1553 post-operative stimulation tests from 35 patients (14 Essential Tremor, 21 Parkinson’s Disease) was analyzed. Volumes of tissue activated (VTAs) were simulated to generate probabilistic maps, from which mapping and target anatomy-related features were extracted to train predictive classification models (low and high improvement, side effects). Model performance was assessed across scenarios linking intra- and post-operative data. Results - Intra-operative data effectively identified regions associated with optimal stimulation, highlighting their utility in guiding parameter selection (predictive accuracy ~60%). However, the predictive relationship between VTAs, probabilistic maps, and clinical outcomes differed between intra- and post-operative contexts. When trained solely on intra-operative VTAs, the model performed at a near chance level (predictive accuracy ~35%). Discussion - The study demonstrates that while intra-operative data are useful for identifying optimal target regions, they are insufficient for accurately predicting post-operative DBS outcomes. Incorporating post-operative data remains crucial for reliable and clinically meaningful DBS effect prediction. Highlights • Intra-operative DBS maps locate optimal stimulation regions • Intra-operative DBS data alone poorly predict post-operative outcomes • Predictive VTA–effects relationships differ intra- vs post-operatively
SN - 2949-6691
SN - 2949-6691
ER -