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

Abstract

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.

Keywords: Adaptive deep brain stimulation; Biomarkers; Closed-loop control; Machine learning; Parkinson’s disease.

Fig. 1

A development framework for closed-loop control supporting adaptive Deep Brain Stimulation (aDBS). The closed-loop control integrates three key components or units. The sensing unit refers to the sensing lead and signal acquisition. The processing unit refers to the stimulation strategy and model, and the supporting hardware characteristics. The stimulation model can rely on advanced algorithms based on machine learning (ML) methods. The stimulating unit refers to the stimulation parameters and the stimulating lead. For each unit, relevant associated parameters are presented

Fig. 2

Generic workflow associated with the application of supervised learning methods to achieve data-driven stimulation. In light grey (top) is the development pipeline and in dark grey (below) is the deployment pipeline

Fig. 4

Application of machine learning towards adaptive deep brain stimulation using closed-loop control. In the top panel, a list of challenges at different stages of DBS therapy implementation where ML methods can play an important role. The diagram represents a closed-loop feedback system for aDBS, based on LFPs sensing and electrophysiological biomarkers identification and interpretation