Parkinsonian daytime sleep-wake classification using deep brain stimulation lead recordings

Area of Science:

• Neuroscience
• Biomedical Engineering
• Sleep Medicine

Background:

• Excessive daytime sleepiness is a significant non-motor symptom in Parkinson's disease (PD), diminishing patient quality of life.
• Current treatments for sleep disturbances in PD are limited, highlighting the need for novel therapeutic strategies.
• Subthalamic nucleus (STN) deep brain stimulation (DBS) effectively manages PD motor symptoms but its potential for sleep regulation is underexplored.

Purpose of the Study:

• To investigate the feasibility of classifying daytime sleep-wake states using local field potentials (LFPs) recorded from STN DBS leads.
• To establish a foundation for developing closed-loop DBS systems capable of detecting and potentially modulating sleep-related neural activity in PD.

Main Methods:

• Recordings of STN DBS leads were obtained from three nonhuman primates administered the neurotoxin MPTP to induce a parkinsonian state.
• Sleep-wake states were determined via continuous video monitoring, classifying epochs as either wake or sleep.
• Spectral power features from various frequency bands (delta, theta, low-beta, high-beta, gamma, high-frequency) were extracted and used to train a support vector machine classifier.

Main Results:

• The classifier achieved reasonable accuracy in distinguishing between wake and sleep states, with an average accuracy of 89.42% ± 0.68%.
• Classification performance metrics included sensitivity (90.68% ± 1.28%), specificity (88.16% ± 1.08%), and positive predictive value (88.70% ± 0.89%).
• These findings demonstrate the potential of using LFP signals from STN DBS leads for real-time sleep-wake monitoring.

Conclusions:

• Monitoring daytime sleep-wake states through STN DBS lead recordings is plausible.
• This approach could enable the development of closed-loop DBS systems for automatic detection and intervention of sleep disturbances in Parkinson's disease.
• Future clinical applications may involve promoting wakefulness by disrupting aberrant sleep-related neural oscillations in PD patients.