Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

• Published in: Experimental neurology Vol. 351; p. 113993
• Main Authors: Merk, Timon, Peterson, Victoria, Köhler, Richard, Haufe, Stefan, Richardson, R. Mark, Neumann, Wolf-Julian
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01-05-2022
• Subjects: Adaptive deep brain stimulation; Algorithms; Brain; Brain-computer interface; Brain-Computer Interfaces; Closed-loop DBS; Deep Brain Stimulation; Machine Learning; Movement disorders; Neural decoding; Real-time classification; Brain-computer interface; Real-time classification; Neural decoding; Closed-loop DBS; aDBS; Adaptive deep brain stimulation; cDBS; iDBS; Movement disorders; ML
• ISSN: 0014-4886; 1090-2430; 1090-2430
• DOI: 10.1016/j.expneurol.2022.113993

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.
•Brain signal decoding expands precision medicine approaches to neuromodulation.•Machine learning can facilitate intelligent adaptive deep brain stimulation (iDBS).•Complex classification and regression algorithms are being reviewed.•Future studies should adhere to real-time compatible methods.•Open science practices will accelerate therapeutic benefit for iDBS in patients.