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

Automatic sleep-wake classification and Parkinson's disease recognition using multifeature fusion with support vector machine

AIMS

Sleep disturbance is a prevalent nonmotor symptom of Parkinson's disease (PD), however, assessing sleep conditions is always time-consuming and labor-intensive. In this study, we performed an automatic sleep-wake state classification and early diagnosis of PD by analyzing the electrocorticography (ECoG) and electromyogram (EMG) signals of both normal and PD rats.

METHODS

The study utilized ECoG power, EMG amplitude, and corticomuscular coherence values extracted from normal and PD rats to construct sleep-wake scoring models based on the support vector machine algorithm. Subsequently, we incorporated feature values that could act as diagnostic markers for PD and then retrained the models, which could encompass the identification of vigilance states and the diagnosis of PD.

RESULTS

Features extracted from occipital ECoG signals were more suitable for constructing sleep-wake scoring models than those from frontal ECoG (average Cohen's kappa: 0.73 vs. 0.71). Additionally, after retraining, the new models demonstrated increased sensitivity to PD and accurately determined the sleep-wake states of rats (average Cohen's kappa: 0.79).

CONCLUSION

This study accomplished the precise detection of substantia nigra lesions and the monitoring of sleep-wake states. The integration of circadian rhythm monitoring and disease state assessment has the potential to improve the efficacy of therapeutic strategies considerably.

Slow-wave sleep dysfunction in mild parkinsonism is associated with excessive beta and reduced delta oscillations in motor cortex

Increasing evidence suggests slow-wave sleep (SWS) dysfunction in Parkinson's disease (PD) is associated with faster disease progression, cognitive impairment, and excessive daytime sleepiness. Beta oscillations (8-35 Hz) in the basal ganglia thalamocortical (BGTC) network are thought to play a role in the development of cardinal motor signs of PD. The role cortical beta oscillations play in SWS dysfunction in the early stage of parkinsonism is not understood, however. To address this question, we used a within-subject design in a nonhuman primate (NHP) model of PD to record local field potentials from the primary motor cortex (MC) during sleep across normal and mild parkinsonian states. The MC is a critical node in the BGTC network, exhibits pathological oscillations with depletion in dopamine tone, and displays high amplitude slow oscillations during SWS. The MC is therefore an appropriate recording site to understand the neurophysiology of SWS dysfunction in parkinsonism. We observed a reduction in SWS quantity (p = 0.027) in the parkinsonian state compared to normal. The cortical delta (0.5-3 Hz) power was reduced (p = 0.038) whereas beta (8-35 Hz) power was elevated (p = 0.001) during SWS in the parkinsonian state compared to normal. Furthermore, SWS quantity positively correlated with delta power (r = 0.43, p = 0.037) and negatively correlated with beta power (r = -0.65, p < 0.001). Our findings support excessive beta oscillations as a mechanism for SWS dysfunction in mild parkinsonism and could inform the development of neuromodulation therapies for enhancing SWS in people with PD.

Excessive cortical beta oscillations are associated with slow-wave sleep dysfunction in mild parkinsonism

Increasing evidence associates slow-wave sleep (SWS) dysfunction with neurodegeneration. Using a within-subject design in the nonhuman primate model of Parkinson's disease (PD), we found that reduced SWS quantity in mild parkinsonism was accompanied by elevated beta and reduced delta power during SWS in the motor cortex. Our findings support excessive beta oscillations as a mechanism for SWS dysfunction and will inform development of neuromodulation therapies for enhancing SWS in PD.

Machine learning for adaptive deep brain stimulation in Parkinson's disease: closing the loop

Parkinson's disease (PD) is the second most common neurodegenerative disease bearing a severe social and economic impact. So far, there is no known disease modifying therapy and the current available treatments are symptom oriented. Deep Brain Stimulation (DBS) is established as an effective treatment for PD, however current systems lag behind today's technological potential. Adaptive DBS, where stimulation parameters depend on the patient's physiological state, emerges as an important step towards "smart" DBS, a strategy that enables adaptive stimulation and personalized therapy. This new strategy is facilitated by currently available neurotechnologies allowing the simultaneous monitoring of multiple signals, providing relevant physiological information. Advanced computational models and analytical methods are an important tool to explore the richness of the available data and identify signal properties to close the loop in DBS. To tackle this challenge, machine learning (ML) methods applied to DBS have gained popularity due to their ability to make good predictions in the presence of multiple variables and subtle patterns. ML based approaches are being explored at different fronts such as the identification of electrophysiological biomarkers and the development of personalized control systems, leading to effective symptom relief. In this review, we explore how ML can help overcome the challenges in the development of closed-loop DBS, particularly its role in the search for effective electrophysiology biomarkers. Promising results demonstrate ML potential for supporting a new generation of adaptive DBS, with better management of stimulation delivery, resulting in more efficient and patient-tailored treatments.

Adaptive Deep Brain Stimulation for sleep stage targeting in Parkinson's disease

BACKGROUND

Sleep dysfunction is disabling in people with Parkinson's disease and is linked to worse motor and non-motor outcomes. Sleep-specific adaptive Deep Brain Stimulation has the potential to target pathophysiologies of sleep.

OBJECTIVE

Develop an adaptive Deep Brain Stimulation algorithm that modulates stimulation parameters in response to intracranially classified sleep stages.

METHODS

We performed at-home, multi-night intracranial electrocorticography and polysomnogram recordings to train personalized linear classifiers for discriminating the N3 NREM sleep stage. Classifiers were embedded into investigational Deep Brain Stimulators for N3 specific adaptive DBS.

RESULTS

We report high specificity of embedded, autonomous, intracranial electrocorticography N3 sleep stage classification across two participants and provide proof-of-principle of successful sleep stage specific adaptive Deep Brain Stimulation.

CONCLUSION

Multi-night cortico-basal recordings and sleep specific adaptive Deep Brain Stimulation provide an experimental framework to investigate sleep pathophysiology and mechanistic interactions with stimulation, towards the development of therapeutic neurostimulation paradigms directly targeting sleep dysfunction.