Background
Microelectrode recordings along pre-planned trajectories are often used for accurate definition of the subthalamic nucleus (STN) borders during deep brain stimulation (DBS) surgery for Parkinson’s disease. Usually, the demarcation of the STN borders is detected manually by a neurophysiologist. The exact detection of the borders is difficult and especially detecting the transition between the STN and the substantia nigra pars reticulata. Consequently, demarcation may be inaccurate, leading to sub-optimal location of the DBS lead and inadequate clinical outcomes.
Methods
We present machine learning classification procedures that utilize microelectrode recordings power spectra and allow for real time, high accuracy discrimination between STN and substantia nigra pars reticulata.
Results
A support vector machine procedure was tested on microelectrode recordings from 58 trajectories that included both STN and substantia nigra pars reticulata that achieved a 97.6% consistency with human expert classification (evaluated by 10-fold cross validation). We used the same dataset as a training set to find the optimal parameters for a hidden Markov model using both microelectrode recordings features and trajectory history to enable a real-time classification of the ventral STN border (STN exit). Seventy-three additional trajectories were used to test the reliability of the learned statistical model in identifying the exit from the STN. The hidden Markov model procedure identified the STN exit with an error of 0.04 ± 0.18 mm and detection reliability (error < 1 mm) of 94%.
Conclusion
The results indicate that robust, accurate and automatic real-time electrophysiological detection of the ventral STN border is feasible.