Hidden Semi-Markov Models in the Computerized Decoding of Microelectrode Recording Data for Deep Brain Stimulator Placement

作者：Taghva Alexander^*

来源：World Neurosurgery, 2011, 75(5-6): 758-U221.

DOI：10.1016/j.wneu.2010.11.008

• Deep brain stimulation
• Hidden Markov model
• Hidden semi-Markov model
• Microelectrode recording
• Supervised machine learning
• Variable duration hidden Markov model

OBJECTIVE: To describe an approach to the analysis of deep brain stimulation (DBS) of the subthalamic nucleus (STN) using a hidden semi-Markov model (HsMM) and early results of the analysis of microelectrode recordings for STN DBS.
METHODS: The author simulated the anatomy and electrophysiology of STN DBS and built a seven-state model to compare Hidden Markov model (HMM) and HsMM approaches.
RESULTS: Accuracy of these competing models was similar for correctly identifying brain nuclei; however, HsMMs showed superior specificity in detecting microelectrode passes traversing the STN.
CONCLUSIONS: Further clinical work must be done; however, based on these data, HsMMs may be best suited to computer-assisted anatomic delineation for DBS.

• 出版日期2011-6