Epilepsy classification using artificial intelligence: A web-based application

Review Medicine, General & Internal

Artificial Intelligence and Machine Learning in Clinical Medicine, 2023

Charlotte J. J. Haug et al.

Summary: This article introduces the history of artificial intelligence in medicine, its applications in image analysis, disease outbreak identification, and diagnosis, as well as the use of chatbots.

NEW ENGLAND JOURNAL OF MEDICINE (2023)

Add to Collection

Article Clinical Neurology

Web-based decision support system for patient-tailored selection of antiseizure medication in adolescents and adults: An external validation study

Levente Hadady et al.

Summary: The study validated that the use of the algorithm recommending ASMs based on individual characteristics is associated with better outcomes compared to using less desirable ASMs, including higher retention rates, higher seizure freedom rates, and fewer discontinuations due to adverse effects. The freely available decision support system proved to be beneficial for healthcare professionals in prescribing medication for individuals with epilepsy.

EUROPEAN JOURNAL OF NEUROLOGY (2022)

Add to Collection

Article Psychiatry

Machine learning applications to differentiate comorbid functional seizures and epilepsy from pure functional seizures

Ali A. Asadi-Pooya et al.

Summary: This study developed the best algorithm using machine learning methods to differentiate comorbid functional seizures and pure functional seizures, with the TabNet classifier performing the best. The results suggest that the algorithm could be useful in clinical practice, particularly in distinguishing patients with FS and those with comorbid epilepsy.

JOURNAL OF PSYCHOSOMATIC RESEARCH (2022)

Add to Collection

Article Clinical Neurology

Treatment response in newly diagnosed epilepsy: a syndromic approach

Ali A. Asadi-Pooya et al.

Summary: The objective of this study was to investigate the seizure outcome and associated factors in patients with newly diagnosed epilepsy using a syndromic approach. The results showed that approximately 52.7% of patients were seizure-free for at least one year after the first treatment plan. Drug-resistance was higher in patients with focal epilepsy and symptomatic generalized epilepsy. Implementation of appropriate personalized treatment plans is crucial for patients with epilepsy.

NEUROLOGICAL RESEARCH (2022)

Add to Collection

Review Mathematical & Computational Biology

EEG-Based Epileptic Seizure Detection via Machine/Deep Learning Approaches: A Systematic Review

Ijaz Ahmad et al.

Summary: This study provides an extensive systematic review of the recent developments in EEG-based machine/deep learning technologies for epileptic seizure diagnosis. It meticulously reviews and compares the current development in seizure diagnosis, various statistical feature extraction methods, ML/DL models, their performances, limitations, and core challenges. The study also discusses the criteria for selecting appropriate and efficient feature extraction techniques and ML/DL models. The findings will help researchers in choosing the most efficient ML/DL models with optimal feature extraction methods to improve the performance of EEG-based epileptic seizure detection.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2022)

Add to Collection

Review Medicine, General & Internal

Individualised prediction of drug resistance and seizure recurrence after medication withdrawal in people with juvenile myoclonic epilepsy: A systematic review and individual participant data meta-analysis

Remi Stevelink et al.

Summary: This study aimed to identify predictors of drug resistance and seizure recurrence in people with juvenile myoclonic epilepsy (JME) to allow for individualized prediction of treatment outcomes. The study found multiple factors associated with drug resistance and seizure recurrence and provided personalized prediction tools.

ECLINICALMEDICINE (2022)

Add to Collection

Article Biology

An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works

Afshin Shoeibi et al.

Summary: This paper provides a comprehensive overview of deep learning methods used for the detection and prediction of epileptic seizures using neuroimaging modalities. It discusses the application of computer-aided diagnosis systems based on deep learning and neuroimaging modalities, as well as the challenges and future directions in this field. The paper also includes research on rehabilitation tools and a comparison of research on epileptic seizure detection and prediction.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Clinical Neurology

Optimal choice of antiseizure medication: Agreement among experts and validation of a web-based decision support application

Sandor Beniczky et al.

Summary: The optimal choice of antiseizure medication depends on various factors, and the agreement among experts in selecting the medication is fair. The web-based decision-support application demonstrates moderate agreement with expert choices, with a high percentage of experts agreeing with the app's selections.

EPILEPSIA (2021)

Add to Collection

Review Behavioral Sciences

Machine learning models for decision support in epilepsy management: A critical review

Eliot D. Smolyansky et al.

Summary: Machine learning models show promising performance in predicting epilepsy management outcomes, but larger studies with external validation, standardized reporting, and prospective evaluation are needed for clinical application.

EPILEPSY & BEHAVIOR (2021)

Add to Collection

Article Behavioral Sciences

Ictal injury: Epilepsy vs. functional (psychogenic) seizures

Ali A. Asadi-Pooya et al.

Summary: The study aimed to compare the risk and types of ictal injuries among three groups of individuals with seizures (idiopathic generalized epilepsy, temporal lobe epilepsy, and febrile seizures). While the groups differed in demographic and clinical characteristics, there were no significant differences in rates of ictal injuries. Patients with temporal lobe epilepsy were more likely to report tongue injuries, but other types/locations of ictal injuries were reported to varying degrees by all three groups.

EPILEPSY & BEHAVIOR (2021)

Add to Collection

Article Clinical Neurology

Aura: epilepsy vs. functional (psychogenic) seizures

Ali A. Asadi-Pooya et al.

Summary: The study compared auras among different groups of epilepsy patients and found that patients with TLE were more likely to experience auras, with emotional, cognitive, epigastric, and olfactory/gustatory auras being common. Patients with FS were more likely to experience headache and dizziness/vertigo as auras.

SEIZURE-EUROPEAN JOURNAL OF EPILEPSY (2021)

Add to Collection

Article Clinical Neurology