Responsive deep brain stimulation guided by ventral striatal electrophysiology of obsession durably ameliorates compulsion

Treatment-resistant obsessive-compulsive disorder (OCD) occurs in approximately one-third of OCD patients. Obsessions may fluctuate over time but often occur or worsen in the presence of internal (emotional state and thoughts) and external (visual and tactile) triggering stimuli. Obsessive thoughts and related compulsive urges fluctuate (are episodic) and so may respond well to a time-locked brain stimulation strategy sensitive and responsive to these symptom fluctuations. Early evidence suggests that neural activity can be captured from ventral striatal regions implicated in OCD to guide such a closed-loop approach. Here, we report on a first-in-human application of responsive deep brain stimulation (rDBS) of the ventral striatum for a treatment-refractory OCD individual who also had comorbid epilepsy. Self-reported obsessive symptoms and provoked OCD-related distress correlated with ventral striatal electrophysiology. rDBS detected the time-domain area-based feature from invasive electroencephalography low-frequency oscillatory power fluctuations that triggered bursts of stimulation to ameliorate OCD symptoms in a closed-loop fashion. rDBS provided rapid, robust, and durable improvement in obsessions and compulsions. These results provide proof of concept for a personalized, physiologically guided DBS strategy for OCD.

Embedded Machine Learning Using a Multi-Thread Algorithm on a Raspberry Pi Platform to Improve Prosthetic Hand Performance

High accuracy and a real-time system are priorities in the development of a prosthetic hand. This study aimed to develop and evaluate a real-time embedded time-domain feature extraction and machine learning on a system on chip (SoC) Raspberry platform using a multi-thread algorithm to operate a prosthetic hand device. The contribution of this study is that the implementation of the multi-thread in the pattern recognition improves the accuracy and decreases the computation time in the SoC. In this study, ten healthy volunteers were involved. The EMG signal was collected by using two dry electrodes placed on the wrist flexor and wrist extensor muscles. To reduce the complexity, four time-domain features were applied to extract the EMG signal. Furthermore, these features were used as the input of the machine learning. The machine learning evaluated in this study were k-nearest neighbor (k-NN), Naive Bayes (NB), decision tree (DT), and support vector machine (SVM). In the SoC implementation, the data acquisition, feature extraction, machine learning, and motor control process were implemented using a multi-thread algorithm. After the evaluation, the result showed that the pairing of the MAV feature and machine learning DT resulted in higher accuracy among other combinations (98.41%) with a computation time of ~1 ms. The implementation of the multi-thread algorithm in the pattern recognition system resulted in significant impact on the time processing.