Toward On-Demand Deep Brain Stimulation Using Online Parkinson's Disease Prediction Driven by Dynamic Detection

Efficient Approximation of Action Potentials with High-Order Shape Preservation in Unsupervised Spike Sorting

This paper presents a novel approximation unit added to the conventional spike processing chain which provides an appreciable reduction of complexity of the high-hardware cost feature extractors. The use of the Taylor polynomial is proposed and modelled employing its cascaded derivatives to non-uniformly capture the essential samples in each spike for reliable feature extraction and sorting. Inclusion of the approximation unit can provide 3X compression (i.e. from 66 to 22 samples) to the spike waveforms while preserving their shapes. Detailed spike waveform sequences based on in-vivo measurements have been generated using a customized neural simulator for performance assessment of the approximation unit tested on six published feature extractors. For noise levels σ_N between 0.05 and 0.3 and groups of 3 spikes in each channel, all the feature extractors provide almost same sorting performance before and after approximation. The overall implementation cost when including the approximation unit and feature extraction shows a large reduction (i.e. up to 8.7X) in the hardware costly and more accurate feature extractors, offering a substantial improvement in feature extraction design.

Machine learning in deep brain stimulation: A systematic review

Deep Brain Stimulation (DBS) is an increasingly common therapy for a large range of neurological disorders, such as abnormal movement disorders. The effectiveness of DBS in terms of controlling patient symptomatology has made this procedure increasingly used over the past few decades. Concurrently, the popularity of Machine Learning (ML), a subfield of artificial intelligence, has skyrocketed and its influence has more recently extended to medical domains such as neurosurgery. Despite its growing research interest, there has yet to be a literature review specifically on the use of ML in DBS. We have followed a fully systematic methodology to obtain a corpus of 73 papers. In each paper, we identified the clinical application, the type/amount of data used, the method employed, and the validation strategy, further decomposed into 12 different sub-categories. The papers overall illustrated some existing trends in how ML is used in the context of DBS, including the breath of the problem domain and evolving techniques, as well as common frameworks and limitations. This systematic review analyzes at a broad level how ML have been recently used to address clinical problems on DBS, giving insight into how these new computational methods are helping to push the state-of-the-art of functional neurosurgery. DBS clinical workflow is complex, involves many specialists, and raises several clinical issues which have partly been addressed with artificial intelligence. However, several areas remain and those that have been recently addressed with ML are by no means considered "solved" by the community nor are they closed to new and evolving methods.

Identification of effective features of LFP signal for making closed-loop deep brain stimulation in parkinsonian rats

Traditional deep brain stimulation (DBS) is one of the acceptable methods to relieve the clinical symptoms of Parkinson's disease in its advanced stages. Today, the use of closed-loop DBS to increase stimulation efficiency and patient satisfaction is one of the most important issues under investigation. The present study was aimed to find local field potential (LFP) features of parkinsonian rats, which can determine the timing of stimulation with high accuracy. The LFP signals from rats were recorded in three groups of parkinsonian rat models receiving stimulation (stimulation), without getting stimulation (off-stimulation), and sham-controlled group. The frequency domain and chaotic features of signals were extracted for classifying three classes by support vector machine (SVM) and neural networks. The best combination of features was selected using the genetic algorithm (GA). Finally, the effective features were introduced to determine the on/off stimulation time, and the optimal stimulation parameters were identified. It was found that a combination of frequency domain and chaotic features with an accuracy of about 99% was able to determine the time the DBS must switch on. In about 80.67% of the 1861 different stimulation parameters, the brain was able to maintain its state for about 3 min after stimulation discontinuation.

A Chopped Neural Front-End Featuring Input Impedance Boosting With Suppressed Offset-Induced Charge Transfer

Modern neuromodulation systems typically provide a large number of recording and stimulation channels, which reduces the available power and area budget per channel. To maintain the necessary input-referred noise performance despite growingly rigorous area constraints, chopped neural front-ends are often the modality of choice, as chopper-stabilization allows to simultaneously improve (1/f) noise and area consumption. The resulting issue of a drastically reduced input impedance has been addressed in prior art by impedance boosters based on voltage buffers at the input. These buffers precharge the large input capacitors, reduce the charge drawn from the electrodes and effectively boost the input impedance. Offset on these buffers directly translates into charge-transfer to the electrodes, which can accelerate electrode aging. To tackle this issue, a voltage buffer with ultra-low time-averaged offset is proposed, which cancels offset by periodic reconfiguration, thereby minimizing unintended charge transfer. This article explains the background and circuit design in detail and presents measurement results of a prototype implemented in a 180 nm HV CMOS process. The measurements confirm that signal-independent, buffer offset induced charge transfer occurs and can be mitigated by the presented buffer reconfiguration without adversely affecting the operation of the input impedance booster. The presented neural recorder front-end achieves state of the art performance with an area consumption of 0.036 mm², an input referred noise of [Formula: see text] (1 to 200 Hz) and [Formula: see text] (0.2 to 10 kHz), power consumption of 13.7 μW from 1.8 V supply, as well as CMRR and PSRR ≥ 83 dB at 50 Hz.

Machine Learning's Application in Deep Brain Stimulation for Parkinson's Disease: A Review

Deep brain stimulation (DBS) is a surgical treatment for advanced Parkinson's disease (PD) that has undergone technological evolution that parallels an expansion in clinical phenotyping, neurophysiology, and neuroimaging of the disease state. Machine learning (ML) has been successfully used in a wide range of healthcare problems, including DBS. As computational power increases and more data become available, the application of ML in DBS is expected to grow. We review the literature of ML in DBS and discuss future opportunities for such applications. Specifically, we perform a comprehensive review of the literature from PubMed, the Institute for Scientific Information's Web of Science, Cochrane Database of Systematic Reviews, and Institute of Electrical and Electronics Engineers' (IEEE) Xplore Digital Library for ML applications in DBS. These studies are broadly placed in the following categories: (1) DBS candidate selection; (2) programming optimization; (3) surgical targeting; and (4) insights into DBS mechanisms. For each category, we provide and contextualize the current body of research and discuss potential future directions for the application of ML in DBS.

A Framework for Adapting Deep Brain Stimulation Using Parkinsonian State Estimates

The mechanisms underlying the beneficial effects of deep brain stimulation (DBS) for Parkinson's disease (PD) remain poorly understood and are still under debate. This has hindered the development of adaptive DBS (aDBS). For further progress in aDBS, more insight into the dynamics of PD is needed, which can be obtained using machine learning models. This study presents an approach that uses generative and discriminative machine learning models to more accurately estimate the symptom severity of patients and adjust therapy accordingly. A support vector machine is used as the representative algorithm for discriminative machine learning models, and the Gaussian mixture model is used for the generative models. Therapy is effected using the state estimates obtained from the machine learning models together with a fuzzy controller in a critic-actor control approach. Both machine learning model configurations achieve PD suppression to desired state in 7 out of 9 cases; most of which settle in under 2 s.

Accurate, Very Low Computational Complexity Spike Sorting Using Unsupervised Matched Subspace Learning

This paper presents an adaptable dictionary-based feature extraction approach for spike sorting offering high accuracy and low computational complexity for implantable applications. It extracts and learns identifiable features from evolving subspaces through matched unsupervised subspace filtering. To provide compatibility with the strict constraints in implantable devices such as the chip area and power budget, the dictionary contains arrays of {-1, 0 and 1} and the algorithm need only process addition and subtraction operations. Three types of such dictionary were considered. To quantify and compare the performance of the resulting three feature extractors with existing systems, a neural signal simulator based on several different libraries was developed. For noise levels σ_N between 0.05 and 0.3 and groups of 3 to 6 clusters, all three feature extractors provide robust high performance with average classification errors of less than 8% over five iterations, each consisting of 100 generated data segments. To our knowledge, the proposed adaptive feature extractors are the first able to classify reliably 6 clusters for implantable applications. An ASIC implementation of the best performing dictionary-based feature extractor was synthesized in a 65-nm CMOS process. It occupies an area of 0.09 mm² and dissipates up to about 10.48 μW from a 1 V supply voltage, when operating with 8-bit resolution at 30 kHz operating frequency.

Toward a closed-loop deep brain stimulation in Parkinson's disease using local field potential in parkinsonian rat model

Deep brain stimulation (DBS) is an invasive method used for treating Parkinson's disease in its advanced stages. Nowadays, the initial adjustment of DBS parameters and their automatic matching proportion to the progression of the disease is viewed as one of the research areas discussed by the researchers, which is called closed-loop DBS. Various studies were conducted regarding finding the signal(s) which reflects different symptoms of the disease. Local Field Potential (LFP) is one of the signals that is suitable for using as feedback, because it can be recorded by the same implemented electrodes for stimulation. The present study aimed to identify the distinguishing features of patients from healthy individuals using LFP signals.

METHODS

In the present study, LFP was recorded from the rats in sham and parkinsonian model groups. After evaluating the signals in the frequency domain, sixty-six features were extracted from power spectral density of LFPs. The features were classified by Support Vector Machine (SVM) to determine the ability of features for separating parkinsonian rats from healthy ones. Finally, the most effective features were selected for distinguishing between the sham and parkinsonian model groups using a genetic algorithm.

RESULTS

The results indicated that the frequency domain features of LFP signals from rats have capacity of using them as a feedback for closed-loop DBS. The accuracy of the Support Vector Machine classification using all 66 features was 80.42% which increased to 84.41% using 38 features selected by genetic algorithm. The proposed method not only increase the accuracy, but it also reduce computation by decreasing the number of the effective features. The results indicate the significant capacity of the proposed method for identifying the effective high-frequency features to control the closed-loop DBS.

CONCLUSIONS

The ability of using LFP signals as feedback in closed-loop DBS was shown by extracting useful information in frequency bands below and above 100 Hz regarding LFP signals of parkinsonian rats and sham ones. Based on the results, features at frequencies above 100 Hz were more powerful and robust than below 100 Hz. The genetic algorithm was used for optimizing the classification problem.

An Adaptive Neural Spike Processor With Embedded Active Learning for Improved Unsupervised Sorting Accuracy

There is a need for integrated spike sorting processors in implantable devices with low power consumption that have improved accuracy. Learning the characteristics of the variable input neural signals and adapting the functionality of the sorting process can improve the accuracy. An adaptive spike sorting processor is presented accounting for the variation in the input signal noise characteristics and the variable difficulty in the selection of the spike characteristics, which significantly improves the accuracy. The adaptive spike processor was fabricated in 180-nm CMOS technology for proof of concept. It performs conditional detection, alignment, adaptive feature extraction, and online clustering with sorting threshold self-tuning capability. The chip was tested under different input signal conditions to demonstrate its adaptation capability providing a median classification accuracy of 84.5% and consuming 148 μW from a 1.8 V supply voltage.

Toward adaptive deep brain stimulation in Parkinson's disease: a review

Clinical deep brain stimulation (DBS) is now regarded as the therapeutic intervention of choice at the advanced stages of Parkinson's disease. However, some major challenges of DBS are stimulation induced side effects and limited pacemaker battery life. Side effects and shortening of pacemaker battery life are mainly as a result of continuous stimulation and poor stimulation focus. These drawbacks can be mitigated using adaptive DBS (aDBS) schemes. Side effects resulting from continuous stimulation can be reduced through adaptive control using closed-loop feedback, while those due to poor stimulation focus can be mitigated through spatial adaptation. Other advantages of aDBS include automatic, rather than manual, initial adjustment and programming, and long-term adjustments to maintain stimulation parameters with changes in patient's condition. Both result in improved efficacy. This review focuses on the major areas that are essential in driving technological advances for the various aDBS schemes. Their challenges, prospects and progress so far are analyzed. In addition, important advances and milestones in state-of-the-art aDBS schemes are highlighted – both for closed-loop adaption and spatial adaption. With perspectives and future potentials of DBS provided at the end.