Skip to main navigation Skip to search Skip to main content

An Investigative Study Exploring Machine Learning Approaches for Optimizing Deep Brain Stimulation Programming

  • Esther Ademola*
  • , Martin Reich
  • , Magda Gregorova
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This investigative study explores machine learning models for predicting dystonia improvement scores in Deep Brain Stimulation (DBS). Leveraging data from 85 subjects across seven European DBS centers, we employ various linear and non-linear modeling approaches. In contrast to previous studies utilizing probabilistic mapping, our direct utilization of the actual dataset yields improved results. The random forest model emerges as the most accurate predictor, with a mean deviation of 9.54 ± 6.08%. This implies that for a patient with an improvement score of 78%, the model predicts an improvement between 68% and 87%. This advancement in predictive accuracy holds potential implications for refining DBS programming, ultimately enhancing therapeutic outcomes for individuals with dystonia. In addition, regularization techniques play a pivotal role in determining feature importance thereby contributing to a nuanced understanding of factors influencing DBS therapy outcomes.

Original languageEnglish
Title of host publicationModelling and Development of Intelligent Systems - 9th International Conference, MDIS 2024, Revised Selected Papers
EditorsDana Simian, Laura Florentina Stoica
PublisherSpringer Science and Business Media Deutschland GmbH
Pages75-89
Number of pages15
ISBN (Print)9783031873850
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event9th International Conference on Modelling and Development of Intelligent Systems, MDIS 2024 - Sibiu, Romania
Duration: 17 Oct 202419 Oct 2024

Publication series

NameCommunications in Computer and Information Science
Volume2486 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference9th International Conference on Modelling and Development of Intelligent Systems, MDIS 2024
Country/TerritoryRomania
CitySibiu
Period17/10/2419/10/24

Keywords

  • Deep brain stimulation
  • dystonia
  • machine learning
  • regularization

Fingerprint

Dive into the research topics of 'An Investigative Study Exploring Machine Learning Approaches for Optimizing Deep Brain Stimulation Programming'. Together they form a unique fingerprint.

Cite this