Personalized supervised and unsupervised intracranial sleep decoding during deep brain stimulation - Takeaways - MDSpire

Personalized supervised and unsupervised intracranial sleep decoding during deep brain stimulation

  • By

  • Clay Smyth

  • Md Fahim Anjum

  • Jin-Xiao Zhang

  • Jiaang Yao

  • Reza Abbasi-Asl

  • Philip Starr

  • Simon Little

  • January 22, 2026

  • 0 min

Share

  • 1

    Impaired sleep in Parkinson's Disease is a significant unmet need that may be addressed with adaptive Deep Brain Stimulation.

  • 2

    The study analyzed 283 hours of intracranial recordings to classify sleep stages in participants receiving deep brain stimulation.

  • 3

    Five-stage classification accuracy averaged 80.2% across Parkinson's Disease subjects, demonstrating effective sleep stage decoding.

  • 4

    Binary NREM classification using linear models achieved an average accuracy of 85.9%, indicating feasibility for current DBS devices.

  • 5

    The study supports personalized machine learning models for sleep classification during deep brain stimulation in Parkinson's Disease.

Original Source(s)

Personalized supervised and unsupervised intracranial sleep decoding during deep brain stimulation

  • by Clay Smyth, Md Fahim Anjum, Jin-Xiao Zhang, Jiaang Yao, Reza Abbasi-Asl, Philip Starr, Simon Little

  • January 22, 2026

Related Content

A multimodal machine learning model for predicting postoperative worsening of FOGQ in Parkinson’s disease following STN-DBS

The novel GLP-1/GIP dual receptor agonist DA5-CH is superior to tirzepatide and exendin-4 in the 6-OHDA Parkinson rat model

Baptist Health Foundation Presents Endowed Chair Ceremony for Aviva Abosch, M.D., Ph.D.

Aviva Abosch, M.D., Ph.D., a neurosurgeon at Baptist Health Miami Neuroscience Institute, part of Baptist Health Brain and Spine Care, was installed as the Esernia Endowed Chair in Surgical Treatment of Adult Epilepsy and Movement Disorders.

  • by

  • May 21, 2026

  • 5 min