Towards an Online Seizure Advisory System-An Adaptive Seizure Prediction Framework Using Active Learning Heuristics

Neuromorphic neuromodulation: Towards the next generation of closed-loop neurostimulation

Neuromodulation techniques have emerged as promising approaches for treating a wide range of neurological disorders, precisely delivering electrical stimulation to modulate abnormal neuronal activity. While leveraging the unique capabilities of AI holds immense potential for responsive neurostimulation, it appears as an extremely challenging proposition where real-time (low-latency) processing, low-power consumption, and heat constraints are limiting factors. The use of sophisticated AI-driven models for personalized neurostimulation depends on the back-telemetry of data to external systems (e.g. cloud-based medical mesosystems and ecosystems). While this can be a solution, integrating continuous learning within implantable neuromodulation devices for several applications, such as seizure prediction in epilepsy, is an open question. We believe neuromorphic architectures hold an outstanding potential to open new avenues for sophisticated on-chip analysis of neural signals and AI-driven personalized treatments. With more than three orders of magnitude reduction in the total data required for data processing and feature extraction, the high power- and memory-efficiency of neuromorphic computing to hardware-firmware co-design can be considered as the solution-in-the-making to resource-constraint implantable neuromodulation systems. This perspective introduces the concept of Neuromorphic Neuromodulation, a new breed of closed-loop responsive feedback system. It highlights its potential to revolutionize implantable brain-machine microsystems for patient-specific treatment.

Online Seizure Prediction System: A Novel Probabilistic Approach for Efficient Prediction of Epileptic Seizure with iEEG Signal

Background:

1% of people around the world are suffering from epilepsy. It is, therefore crucial to propose an efficient automated seizure prediction tool implemented in a portable device that uses the electroencephalogram (EEG) signal to enhance epileptic patients’ life quality.

Methods:

In this study, we focused on time-domain features to achieve discriminative information at a low CPU cost extracted from the intracranial electroencephalogram (iEEG) signals of six patients. The probabilistic framework based on XGBoost classifier requires the mean and maximum probability of the non-seizure and the seizure occurrence period segments. Once all these parameters are set for each patient, the medical decision maker can send alarm based on well-defined thresholds.

Results:

While finding a unique model for all patients is really challenging, and our modelling results demonstrated that the proposed algorithm can be an efficient tool for reliable and clinically relevant seizure forecasting. Using iEEG signals, the proposed algorithm can forecast seizures, informing a patient about 75 minutes before a seizure would occur, a period large enough for patients to take practical actions to minimize the potential impacts of the seizure.

Conclusion:

We posit that the ability to distinguish interictal intracranial EEG from pre-ictal signals at some low computational cost may be the first step towards an implanted portable semi-automatic seizure suppression system in the near future. It is believed that our seizure prediction technique can conceivably be coupled with treatment techniques aimed at interrupting the process even prior to a seizure initiates to develop.

Weak self-supervised learning for seizure forecasting: a feasibility study

This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to individual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train individualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.

Feature Selection Techniques for the Analysis of Discriminative Features in Temporal and Frontal Lobe Epilepsy: A Comparative Study

Background:

Because about 30% of epileptic patients suffer from refractory epilepsy, an efficient automatic seizure prediction tool is in great demand to improve their life quality.

Methods:

In this work, time-domain discriminating preictal and interictal features were efficiently extracted from the intracranial electroencephalogram of twelve patients, i.e., six with temporal and six with frontal lobe epilepsy. The performance of three types of feature selection methods was compared using Matthews’s correlation coefficient (MCC).

Results:

Kruskal Wallis, a non-parametric approach, was found to perform better than the other approaches due to a simple and less resource consuming strategy as well as maintaining the highest MCC score. The impact of dividing the electroencephalogram signals into various sub-bands was investigated as well. The highest performance of Kruskal Wallis may suggest considering the importance of univariate features like complexity and interquartile ratio (IQR), along with autoregressive (AR) model parameters and the maximum (MAX) cross-correlation to efficiently predict epileptic seizures.

Conclusion:

The proposed approach has the potential to be implemented on a low power device by considering a few simple time domain characteristics for a specific sub-band. It should be noted that, as there is not a great deal of literature on frontal lobe epilepsy, the results of this work can be considered promising.

Prediction of Seizure Recurrence. A Note of Caution

Great strides have been made recently in documenting that machine-learning programs can predict seizure occurrence in people who have epilepsy. Along with this progress have come claims that appear to us to be a bit premature. We anticipate that many people will benefit from seizure prediction. We also doubt that all will benefit. Although machine learning is a useful tool for aiding discovery, we believe that the greatest progress will come from deeper understanding of seizures, epilepsy, and the EEG features that enable seizure prediction. In this essay, we lay out reasons for optimism and skepticism.

Deep active learning for Interictal Ictal Injury Continuum EEG patterns

OBJECTIVES

Seizures and seizure-like electroencephalography (EEG) patterns, collectively referred to as "ictal interictal injury continuum" (IIIC) patterns, are commonly encountered in critically ill patients. Automated detection is important for patient care and to enable research. However, training accurate detectors requires a large labeled dataset. Active Learning (AL) may help select informative examples to label, but the optimal AL approach remains unclear.

METHODS

We assembled >200,000 h of EEG from 1,454 hospitalized patients. From these, we collected 9,808 labeled and 120,000 unlabeled 10-second EEG segments. Labels included 6 IIIC patterns. In each AL iteration, a Dense-Net Convolutional Neural Network (CNN) learned vector representations for EEG segments using available labels, which were used to create a 2D embedding map. Nearest-neighbor label spreading within the embedding map was used to create additional pseudo-labeled data. A second Dense-Net was trained using real- and pseudo-labels. We evaluated several strategies for selecting candidate points for experts to label next. Finally, we compared two methods for class balancing within queries: standard balanced-based querying (SBBQ), and high confidence spread-based balanced querying (HCSBBQ).

RESULTS

Our results show: 1) Label spreading increased convergence speed for AL. 2) All query criteria produced similar results to random sampling. 3) HCSBBQ query balancing performed best. Using label spreading and HCSBBQ query balancing, we were able to train models approaching expert-level performance across all pattern categories after obtaining ∼7000 expert labels.

CONCLUSION

Our results provide guidance regarding the use of AL to efficiently label large EEG datasets in critically ill patients.