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.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2016.7591074 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Presence of sibutramine and sildenafil in weight loss dietary supplements: a case series with analytical and clinical investigation.
Clin Toxicol (Phila)
January 2025
Laboratory of Pharmacokinetics and Toxicology, La Timone University Hospital, Marseille, France.
Introduction: The use of weight loss supplements is increasing, often driven by online marketing. However, many of these supplements are adulterated with undeclared pharmaceutical substances, potentially posing significant health risks. We investigated the presence of sibutramine and sildenafil in weight loss supplements and assessed the associated clinical outcomes.
View Article and Find Full Text PDFDevelopment and applications of a machine learning model for an in-depth analysis of pentylenetetrazol-induced seizure-like behaviors in adult zebrafish.
Neuroscience
January 2025
Laboratory of Experimental Neuropsychobiology, Department of Biochemistry and Molecular Biology, Federal University of Santa Maria, Santa Maria, RS, Brazil; Graduate Program in Biological Sciences: Toxicological Biochemistry, Federal University of Santa Maria, Santa Maria, RS, Brazil; The International Zebrafish Neuroscience Research Consortium (ZNRC), Slidell, LA, United States. Electronic address:
Epilepsy, a neurological disorder causing recurring seizures, is often studied in zebrafish by exposing animals to pentylenetetrazol (PTZ), which induces clonic- and tonic-like behaviors. While adult zebrafish seizure-like behaviors are well characterized, manual assessment remains challenging due to its time-consuming nature, potential for human error/bias, and the risk of overlooking subtle behaviors. Aiming to circumvent these issues, we developed a machine learning model for automating the analysis of subtle abnormal and seizure-like behaviors in PTZ-exposed adult zebrafish.
View Article and Find Full Text PDFNeuromonitoring-guided anesthesia depth versus four-minute anesthesia-to-stimulation time interval in electroconvulsive therapy for depressive disorders - A single-blinded, prospective, randomized and controlled study.
J Affect Disord
January 2025
Department of Anesthesiology and Intensive Care Medicine, Medical University of Innsbruck, Austria. Electronic address:
Background: Anesthesia depth influences seizure quality in patients undergoing electroconvulsive therapy (ECT). EEG-based neuromonitoring has been shown to detect adequate anesthesia depth for ECT. Anesthesia depth-guided ECT management may therefore be a reliable alternative to the predetermined anesthesia-to-stimulation time interval.
View Article and Find Full Text PDFAcute Neurotoxicity in Children Treated for Acute Lymphoblastic Leukemia and Lymphoblastic Lymphoma: A 10-Year Single-Centre Experience.
Children (Basel)
December 2024
Department of Oncology and Hematology, Children's Hospital Zagreb, Klaićeva 16, 10000 Zagreb, Croatia.
: Recent advances in childhood acute lymphoblastic leukemia (ALL) and lymphoblastic lymphoma (LL) management provide higher survival rates at the cost of increased toxicities. Acute neurotoxicity affects up to 10% of patients, requiring rapid recognition and treatment. : A retrospective observational study was performed to determine the frequency, clinical manifestations, radiological characteristics, treatment options and outcome of acute neurological adverse events in pediatric patients with lymphoid malignancies at the Department of Oncology and Hematology, Children's Hospital Zagreb, Croatia.
View Article and Find Full Text PDFUsing artificial intelligence to optimize anti-seizure treatment and EEG-guided decisions in severe brain injury.
Neurotherapeutics
January 2025
Department of Neurology, Massachusetts General Hospital, Boston MA, USA. Electronic address:
Electroencephalography (EEG) is invaluable in the management of acute neurological emergencies. Characteristic EEG changes have been identified in diverse neurologic conditions including stroke, trauma, and anoxia, and the increased utilization of continuous EEG (cEEG) has identified potentially harmful activity even in patients without overt clinical signs or neurologic diagnoses. Manual annotation by expert neurophysiologists is a major resource limitation in investigating the prognostic and therapeutic implications of these EEG patterns and in expanding EEG use to a broader set of patients who are likely to benefit.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!