From basic sciences and engineering to epileptology: A translational approach.

Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this article, we summarize the recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): (1) novel developments of structural magnetic resonance imaging; (2) latest electroencephalography signal-processing applications; (3) big data for the development of clinical tools; (4) the emerging field of hyperdimensional computing; (5) the new generation of artificial intelligence (AI)-enabled neuroprostheses; and (6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of AI reported in recent investigations and the need for multicenter data-sharing initiatives.

A 16-Channel Low-Power Neural Connectivity Extraction and Phase-Locked Deep Brain Stimulation SoC.

Growing evidence suggests that phase-locked deep brain stimulation (DBS) can effectively regulate abnormal brain connectivity in neurological and psychiatric disorders. This letter therefore presents a low-power SoC with both neural connectivity extraction and phase-locked DBS capabilities. A 16-channel low-noise analog front-end (AFE) records local field potentials (LFPs) from multiple brain regions with precise gain matching. A novel low-complexity phase estimator and neural connectivity processor subsequently enable energy-efficient, yet accurate measurement of the instantaneous phase and cross-regional synchrony measures. Through flexible combination of neural biomarkers such as phase synchrony and spectral energy, a four-channel charge-balanced neurostimulator is triggered to treat various pathological brain conditions. Fabricated in 65-nm CMOS, the SoC occupies a silicon area of 2.24 mm2 and consumes 60 µW, achieving over 60% power saving in neural connectivity extraction compared to the state-of-the-art. Extensive in-vivo measurements demonstrate multi-channel LFP recording, real-time extraction of phase and neural connectivity measures, and phase-locked stimulation in rats.

Fast and accurate decoding of finger movements from ECoG through Riemannian features and modern machine learning techniques.

Objective.Accurate decoding of individual finger movements is crucial for advanced prosthetic control. In this work, we introduce the use of Riemannian-space features and temporal dynamics of electrocorticography (ECoG) signal combined with modern machine learning (ML) tools to improve the motor decoding accuracy at the level of individual fingers.Approach.We selected a set of informative biomarkers that correlated with finger movements and evaluated the performance of state-of-the-art ML algorithms on the brain-computer interface (BCI) competition IV dataset (ECoG, three subjects) and a second ECoG dataset with a similar recording paradigm (Stanford, nine subjects). We further explored the temporal concatenation of features to effectively capture the history of ECoG signal, which led to a significant improvement over single-epoch decoding in both classification (p < 0.01) and regression tasks (p < 0.01).Main results.Using feature concatenation and gradient boosted trees (the top-performing model), we achieved a classification accuracy of 77.0% in detecting individual finger movements (six-class task, including rest state), improving over the state-of-the-art conditional random fields by 11.7% on the three BCI competition subjects. In continuous decoding of movement trajectory, our approach resulted in an average Pearson's correlation coefficient (r) of 0.537 across subjects and fingers, outperforming both the BCI competition winner and the state-of-the-art approach reported on the same dataset (CNN + LSTM). Furthermore, our proposed method features a low time complexity, with only<17.2 s required for training and<50 ms for inference. This enables about 250× speed-up in training compared to previously reported deep learning method with state-of-the-art performance.Significance.The proposed techniques enable fast, reliable, and high-performance prosthetic control through minimally-invasive cortical signals.

NeuralTree: A 256-Channel 0.227-µJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC.

Closed-loop neural interfaces with on-chip machine learning can detect and suppress disease symptoms in neurological disorders or restore lost functions in paralyzed patients. While high-density neural recording can provide rich neural activity information for accurate disease-state detection, existing systems have low channel counts and poor scalability, which could limit their therapeutic efficacy. This work presents a highly scalable and versatile closed-loop neural interface SoC that can overcome these limitations. A 256-channel time-division multiplexed (TDM) front-end with a two-step fast-settling mixed-signal DC servo loop (DSL) is proposed to record high-spatial-resolution neural activity and perform channel-selective brain-state inference. A tree-structured neural network (NeuralTree) classification processor extracts a rich set of neural biomarkers in a patient- and disease-specific manner. Trained with an energy-aware learning algorithm, the NeuralTree classifier detects the symptoms of underlying disorders (e.g., epilepsy and movement disorders) at an optimal energy-accuracy trade-off. A 16-channel high-voltage (HV) compliant neurostimulator closes the therapeutic loop by delivering charge-balanced biphasic current pulses to the brain. The proposed SoC was fabricated in 65nm CMOS and achieved a 0.227µJ/class energy efficiency in a compact area of 0.014mm2/channel. The SoC was extensively verified on human electroencephalography (EEG) and intracranial EEG (iEEG) epilepsy datasets, obtaining 95.6%/94% sensitivity and 96.8%/96.9% specificity, respectively. In-vivo neural recordings using soft µECoG arrays and multi-domain biomarker extraction were further performed on a rat model of epilepsy. In addition, for the first time in literature, on-chip classification of rest-state tremor in Parkinson's disease (PD) from human local field potentials (LFPs) was demonstrated.

Neural interface systems with on-device computing: machine learning and neuromorphic architectures.

Development of neural interface and brain-machine interface (BMI) systems enables the treatment of neurological disorders including cognitive, sensory, and motor dysfunctions. While neural interfaces have steadily decreased in form factor, recent developments target pervasive implantables. Along with advances in electrodes, neural recording, and neurostimulation circuits, integration of disease biomarkers and machine learning algorithms enables real-time and on-site processing of neural activity with no need for power-demanding telemetry. This recent trend on combining artificial intelligence and machine learning with modern neural interfaces will lead to a new generation of low-power, smart, and miniaturized therapeutic devices for a wide range of neurological and psychiatric disorders. This paper reviews the recent development of the 'on-chip' machine learning and neuromorphic architectures, which is one of the key puzzles in devising next-generation clinically viable neural interface systems.

Closed-Loop Neural Prostheses With On-Chip Intelligence: A Review and a Low-Latency Machine Learning Model for Brain State Detection.

The application of closed-loop approaches in systems neuroscience and therapeutic stimulation holds great promise for revolutionizing our understanding of the brain and for developing novel neuromodulation therapies to restore lost functions. Neural prostheses capable of multi-channel neural recording, on-site signal processing, rapid symptom detection, and closed-loop stimulation are critical to enabling such novel treatments. However, the existing closed-loop neuromodulation devices are too simplistic and lack sufficient on-chip processing and intelligence. In this paper, we first discuss both commercial and investigational closed-loop neuromodulation devices for brain disorders. Next, we review state-of-the-art neural prostheses with on-chip machine learning, focusing on application-specific integrated circuits (ASIC). System requirements, performance and hardware comparisons, design trade-offs, and hardware optimization techniques are discussed. To facilitate a fair comparison and guide design choices among various on-chip classifiers, we propose a new energy-area (E-A) efficiency figure of merit that evaluates hardware efficiency and multi-channel scalability. Finally, we present several techniques to improve the key design metrics of tree-based on-chip classifiers, both in the context of ensemble methods and oblique structures. A novel Depth-Variant Tree Ensemble (DVTE) is proposed to reduce processing latency (e.g., by 2.5× on seizure detection task). We further develop a cost-aware learning approach to jointly optimize the power and latency metrics. We show that algorithm-hardware co-design enables the energy- and memory-optimized design of tree-based models, while preserving a high accuracy and low latency. Furthermore, we show that our proposed tree-based models feature a highly interpretable decision process that is essential for safety-critical applications such as closed-loop stimulation.

Predicting task performance from biomarkers of mental fatigue in global brain activity.

Objective.Detection and early prediction of mental fatigue (i.e. shifts in vigilance), could be used to adapt neuromodulation strategies to effectively treat patients suffering from brain injury and other indications with prominent chronic mental fatigue.Approach.In this study, we analyzed electrocorticography (ECoG) signals chronically recorded from two healthy non-human primates (NHP) as they performed a sustained attention task over extended periods of time. We employed a set of spectrotemporal and connectivity biomarkers of the ECoG signals to identify periods of mental fatigue and a gradient boosting classifier to predict performance, up to several seconds prior to the behavioral response.Main results.Wavelet entropy and the instantaneous amplitude and frequency were among the best single features across sessions in both NHPs. The classification performance using higher order spectral-temporal (HOST) features was significantly higher than that of conventional spectral power features in both NHPs. Across the 99 sessions analyzed, average F1 scores of 77.5% ± 8.2% and 91.2% ± 3.6%, and accuracy of 79.5% ± 8.9% and 87.6% ± 3.9% for the classifier were obtained for each animal, respectively.Significance.Our results here demonstrate the feasibility of predicting performance and detecting periods of mental fatigue by analyzing ECoG signals, and that this general approach, in principle, could be used for closed-loop control of neuromodulation strategies.

ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification.

Classifiers that can be implemented on chip with minimal computational and memory resources are essential for edge computing in emerging applications such as medical and IoT devices. This paper introduces a machine learning model based on oblique decision trees to enable resource-efficient classification on a neural implant. By integrating model compression with probabilistic routing and implementing cost-aware learning, our proposed model could significantly reduce the memory and hardware cost compared to state-of-the-art models, while maintaining the classification accuracy. We trained the resource-efficient oblique tree with power-efficient regularization (ResOT-PE) on three neural classification tasks to evaluate the performance, memory, and hardware requirements. On seizure detection task, we were able to reduce the model size by 3.4× and the feature extraction cost by 14.6× compared to the ensemble of boosted trees, using the intracranial EEG from 10 epilepsy patients. In a second experiment, we tested the ResOT-PE model on tremor detection for Parkinson's disease, using the local field potentials from 12 patients implanted with a deep-brain stimulation (DBS) device. We achieved a comparable classification performance as the state-of-the-art boosted tree ensemble, while reducing the model size and feature extraction cost by 10.6× and 6.8×, respectively. We also tested on a 6-class finger movement detection task using ECoG recordings from 9 subjects, reducing the model size by 17.6× and feature computation cost by 5.1×. The proposed model can enable a low-power and memory-efficient implementation of classifiers for real-time neurological disease detection and motor decoding.

Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering.

OBJECTIVE: Accurate and reliable detection of tremor onset in Parkinson's disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor in PD. METHODS: We analyzed the local field potential (LFP) recordings from the subthalamic nucleus region in 12 patients with PD (16 recordings). To explore the optimal biomarkers and the best performing classifier, the performance of state-of-the-art machine learning (ML) algorithms and various features of the subthalamic LFPs were compared. We further used a Kalman filtering technique in feature domain to reduce the false positive rate. RESULTS: The Hjorth complexity showed a higher correlation with tremor, compared to other features in our study. In addition, by optimal selection of a maximum of five features with a sequential feature selection method and using the gradient boosted decision trees as the classifier, the system could achieve an average F1 score of up to 88.7% and a detection lead of 0.52 s. The use of Kalman filtering in feature space significantly improved the specificity by 17.0% (p = 0.002), thereby potentially reducing the unnecessary power dissipation of the conventional DBS system. CONCLUSION: The use of relevant features combined with Kalman filtering and machine learning improves the accuracy of tremor detection during rest. SIGNIFICANCE: The proposed method offers a potential solution for efficient on-demand stimulation for PD tremor.

Resting Tremor Detection in Parkinson's Disease with Machine Learning and Kalman Filtering.

Adaptive deep brain stimulation (aDBS) is an emerging method to alleviate the side effects and improve the efficacy of conventional open-loop stimulation for movement disorders. However, current adaptive DBS techniques are primarily based on single-feature thresholding, precluding an optimized delivery of stimulation for precise control of motor symptoms. Here, we propose to use a machine learning approach for resting-state tremor detection from local field potentials (LFPs) recorded from subthalamic nucleus (STN) in 12 Parkinson's patients. We compare the performance of state-of-the-art classifiers and LFP-based biomarkers for tremor detection, showing that the high-frequency oscillations and Hjorth parameters achieve a high discriminative performance. In addition, using Kalman filtering in the feature space, we show that the tremor detection performance significantly improves (F(1,15)=32.16, p<0.0001). The proposed method holds great promise for efficient on-demand delivery of stimulation in Parkinson's disease.

Migraine classification using somatosensory evoked potentials.

OBJECTIVE: The automatic detection of migraine states using electrophysiological recordings may play a key role in migraine diagnosis and early treatment. Migraineurs are characterized by a deficit of habituation in cortical information processing, causing abnormal changes of somatosensory evoked potentials. Here, we propose a machine learning approach to utilize somatosensory evoked potential-based biomarkers for migraine classification in a noninvasive setting. METHODS: Forty-two migraine patients, including 29 interictal and 13 ictal, were recruited and compared with 15 healthy volunteers of similar age and gender distribution. The right median nerve somatosensory evoked potentials were collected from all subjects. State-of-the-art machine learning algorithms including random forest, extreme gradient-boosting trees, support vector machines, K-nearest neighbors, multilayer perceptron, linear discriminant analysis, and logistic regression were used for classification and were built upon somatosensory evoked potential features in time and frequency domains. A feature selection method was employed to assess the contribution of features and compare it with previous clinical findings, and to build an optimal feature set by removing redundant features. RESULTS: Using a set of relevant features and different machine learning models, accuracies ranging from 51.2% to 72.4% were achieved for the healthy volunteers-ictal-interictal classification task. Following model and feature selection, we successfully separated the three groups of subjects with an accuracy of 89.7% for the healthy volunteers-ictal, 88.7% for healthy volunteers-interictal, 80.2% for ictal-interictal, and 73.3% for healthy volunteers-ictal-interictal classification tasks, respectively. CONCLUSION: Our proposed model suggests the potential use of somatosensory evoked potentials as a prominent and reliable signal in migraine classification. This non-invasive somatosensory evoked potential-based classification system offers the potential to reliably separate migraine patients in ictal and interictal states from healthy controls.

Neural variability quenching during decision-making: Neural individuality and its prestimulus complexity.

The spontaneous activity of the brain interacts with stimulus-induced activity which is manifested in event-related amplitude and its trial-to-trial variability (TTV). TTV describes the variability in the amplitude of the stimulus-evoked response across trials, and it is generally observed to be reduced, or quenched. While such TTV quenching has been observed on both the cellular and regional levels, its exact behavioral relevance and neuronal basis remains unclear. Applying a novel paradigm for testing neural markers of individuality in internally-guided decision-making, we here investigated whether TTV (i) represents an individually specific response by comparing individualized vs shared stimuli; and (ii) is mediated by the complexity of prestimulus activity as measured by the Lempel-Ziv Complexity index (LZC). We observed that TTV - and other electrophysiological markers such as ERP, ERSP, and ITC - showed first significant differences between individualized and shared stimuli (while controlling for task-related effects) specifically in the alpha and beta frequency bands, and secondly that TTV in the beta band correlated significantly with reaction time and eLORETA activity. Moreover, we demonstrate that the complexity (LZC) of neuronal activity is higher in the prestimulus period while it decreases during the poststimulus period, with the former also correlating specifically with poststimulus individualized TTV in alpha (but not with shared TTV). Together, our results show that the TTV represents a marker of 'neural individualization' which, being related to internal processes on both neural and psychological levels, is mediated by the information complexity of prestimulus activity. More generally, our results inform the pre-post-stimulus dynamics of rest-stimulus interaction, which is a basic and ubiquitous neural phenomenon in the brain and highly relevant for mental features including their individuality.

A 41.2 nJ/class, 32-Channel On-Chip Classifier for Epileptic Seizure Detection.

A 41.2 nJ/class, 32-channel, patient-specific onchip classification architecture for epileptic seizure detection is presented. The proposed system-on-chip (SoC) breaks the strict energy-area-delay trade-off by employing area and memoryefficient techniques. An ensemble of eight gradient-boosted decision trees, each with a fully programmable Feature Extraction Engine (FEE) and FIR filters are continuously processing the input channels. In a closed-loop architecture, the FEE reuses a single filter structure to execute the top-down flow of the decision tree. FIR filter coefficients are multiplexed from a shared memory. The 540 × 1850 µm2 prototype with a 1kB register-type memory is fabricated in a TSMC 65nm CMOS process. The proposed on-chip classifier is verified on 2253 hours of intracranial EEG (iEEG) data from 20 patients including 361 seizures, and achieves specificity of 88.1% and sensitivity of 83.7%. Compared to the state-of-the-art, the proposed classifier achieves 27 × improvement in Energy-AreaLatency product.

Hardware-friendly seizure detection with a boosted ensemble of shallow decision trees.

Efficient on-chip learning is becoming an essential element of implantable biomedical devices. Despite a substantial literature on automated seizure detection algorithms, hardware-friendly implementation of such techniques is not sufficiently addressed. In this paper, we propose to employ a gradientboosted ensemble of decision trees to achieve a reasonable trade-off between detection accuracy and implementation cost. Combined with the proposed feature extraction model, we show that these classifiers quickly become competitive with more complex learning models previously proposed for hardware implementation, with only a small number of low-depth (d <; 4) "shallow" trees. The results are verified on more than 3460 hours of intracranial EEG data including 430 seizures from 27 patients with epilepsy.

Compact low-power cortical recording architecture for compressive multichannel data acquisition.

This paper introduces an area- and power-efficient approach for compressive recording of cortical signals used in an implantable system prior to transmission. Recent research on compressive sensing has shown promising results for sub-Nyquist sampling of sparse biological signals. Still, any large-scale implementation of this technique faces critical issues caused by the increased hardware intensity. The cost of implementing compressive sensing in a multichannel system in terms of area usage can be significantly higher than a conventional data acquisition system without compression. To tackle this issue, a new multichannel compressive sensing scheme which exploits the spatial sparsity of the signals recorded from the electrodes of the sensor array is proposed. The analysis shows that using this method, the power efficiency is preserved to a great extent while the area overhead is significantly reduced resulting in an improved power-area product. The proposed circuit architecture is implemented in a UMC 0.18 [Formula: see text]m CMOS technology. Extensive performance analysis and design optimization has been done resulting in a low-noise, compact and power-efficient implementation. The results of simulations and subsequent reconstructions show the possibility of recovering fourfold compressed intracranial EEG signals with an SNR as high as 21.8 dB, while consuming 10.5 [Formula: see text]W of power within an effective area of 250 [Formula: see text]m × 250 [Formula: see text]m per channel.

Design techniques and analysis of high-resolution neural recording systems targeting epilepsy focus localization.

The design of a high-density neural recording system targeting epilepsy monitoring is presented. Circuit challenges and techniques are discussed to optimize the amplifier topology and the included OTA. A new platform supporting active recording devices targeting wireless and high-resolution focus localization in epilepsy diagnosis is also proposed. The post-layout simulation results of an amplifier dedicated to this application are presented. The amplifier is designed in a UMC 0.18µm CMOS technology, has an NEF of 2.19 and occupies a silicon area of 0.038 mm(2), while consuming 5.8 µW from a 1.8-V supply.