loading page

Multimodal prediction of obsessive-compulsive  disorder, comorbid depression, and energy of deep brain stimulation
  • +6
  • Saurabh Hinduja,
  • Ali Darzi,
  • Itir Onal Ertugrul,
  • Nicole Provenza,
  • Ron Gadot,
  • Eric Storch,
  • Sameer Sheth,
  • Wayne Goodman,
  • Jeffrey Cohn
Saurabh Hinduja
University of Pittsburgh
Author Profile
Ali Darzi
University of Pittsburgh
Author Profile
Itir Onal Ertugrul
Author Profile
Nicole Provenza
Author Profile
Eric Storch
Author Profile
Sameer Sheth
Author Profile
Wayne Goodman
Author Profile
Jeffrey Cohn
University of Pittsburgh

Corresponding Author:[email protected]

Author Profile

Abstract

To develop reliable, valid, and efficient measures of severity of OCD and comorbid depression and electrical deep brain stimulation (DBS), we trained and compared random forests regression models in a clinical trial of participants receiving DBS for refractory OCD. Six participants were recorded during open-ended interviews at pre- and post-surgery baselines and then at 3-month intervals following DBS activation. Ground-truth severity was assessed by clinical interview and self-report. Visual and auditory modalities included facial action units, head and facial landmarks, speech behavior and content, and voice acoustics. Mixed-effects random forest regression with Shapley feature reduction strongly predicted severity of OCD, comorbid depression, and total electrical energy delivered by the DBS electrodes (intraclass correlation, ICC, = 0.83, 0.87, and 0.81, respectively. When random effects were omitted from the regression, predictive power decreased to moderate for severity of OCD and comorbid depression and remained comparable for total electrical energy delivered (ICC = 0.60, 0.68, and 0.83, respectively). Multimodal measures of behavior outperformed ones from single modalities. Feature selection achieved large decreases in features and corresponding increases in prediction. The approach could contribute to closed-loop DBS that would automatically titrate DBS based on affect measures.
21 Apr 2024Submitted to TechRxiv