Models for predicting treatment efficacy of antiepileptic drugs and prognosis of treatment withdrawal in epilepsy patients

Yang, Shijun; Wang, Bin; Han, Xing

doi:10.1186/s42494-020-00035-9

Cited by 11 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For some time now, machine learning algorithms have been available that process multiple datasets, including the duration of epilepsy, epilepsy syndrome, age of onset, cognitive impairment, and gene mutations. These algorithms may be helpful in the design of treatments; however, as in the case of clinical trials, larger sample sizes in such studies are required to increase their reliability [99,100].…”

Section: Discussionmentioning

confidence: 99%

Genetic Background of Epilepsy and Antiepileptic Treatments

Borowicz-Reutt,

Czernia,

Krawczyk

2023

IJMS

View full text Add to dashboard Cite

Advanced identification of the gene mutations causing epilepsy syndromes is expected to translate into faster diagnosis and more effective treatment of these conditions. Over the last 5 years, approximately 40 clinical trials on the treatment of genetic epilepsies have been conducted. As a result, some medications that are not regular antiseizure drugs (e.g., soticlestat, fenfluramine, or ganaxolone) have been introduced to the treatment of drug-resistant seizures in Dravet, Lennox-Gastaut, maternally inherited chromosome 15q11.2-q13.1 duplication (Dup 15q) syndromes, and protocadherin 19 (PCDH 19)-clusterig epilepsy. And although the effects of soticlestat, fenfluramine, and ganaxolone are described as promising, they do not significantly affect the course of the mentioned epilepsy syndromes. Importantly, each of these syndromes is related to mutations in several genes. On the other hand, several mutations can occur within one gene, and different gene variants may be manifested in different disease phenotypes. This complex pattern of inheritance contributes to rather poor genotype–phenotype correlations. Hence, the detection of a specific mutation is not synonymous with a precise diagnosis of a specific syndrome. Bearing in mind that seizures develop as a consequence of the predominance of excitatory over inhibitory processes, it seems reasonable that mutations in genes encoding sodium and potassium channels, as well as glutamatergic and gamma-aminobutyric (GABA) receptors, play a role in the pathogenesis of epilepsy. In some cases, different pathogenic variants of the same gene can result in opposite functional effects, determining the effectiveness of therapy with certain medications. For instance, seizures related to gain-of-function (GoF) mutations in genes encoding sodium channels can be successfully treated with sodium channel blockers. On the contrary, the same drugs may aggravate seizures related to loss-of-function (LoF) variants of the same genes. Hence, knowledge of gene mutation–treatment response relationships facilitates more favorable selection of drugs for anticonvulsant therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Genetic Background of Epilepsy and Antiepileptic Treatments

Borowicz-Reutt,

Czernia,

Krawczyk

2023

IJMS

View full text Add to dashboard Cite

show abstract

“…ML has been widely used to build seizure predictive models (100), where common algorithms such as SVM (101), random forests (102), and cluster analysis (32) are used. The principle of constructing predictive seizure models involves the preprocessing of interictal and preictal EEG datasets, followed by computational extraction of commonly used features, and then constructing classification models by ML.…”

Section: Ai Methods and The Model Performancementioning

confidence: 99%

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

2022

Self Cite

View full text Add to dashboard Cite

The recurrent and unpredictable nature of seizures can lead to unintentional injuries and even death. The rapid development of electroencephalogram (EEG) and Artificial Intelligence (AI) technologies has made it possible to predict seizures in real-time through brain-machine interfaces (BCI), allowing advanced intervention. To date, there is still much room for improvement in predictive seizure models constructed by EEG using machine learning (ML) and deep learning (DL). But, the most critical issue is how to improve the performance and generalization of the model, which involves some confusing conceptual and methodological issues. This review focuses on analyzing several factors affecting the performance of seizure prediction models, focusing on the aspects of post-processing, seizure occurrence period (SOP), seizure prediction horizon (SPH), and algorithms. Furthermore, this study presents some new directions and suggestions for building high-performance prediction models in the future. We aimed to clarify the concept for future research in related fields and improve the performance of prediction models to provide a theoretical basis for future applications of wearable seizure detection devices.

show abstract

“…Current drug suggestion models often rely on costly techniques such as whole-genome sequencing, which are not feasible for many healthcare settings [16−18]. Similarly, other omics data such as transcriptomic and proteomic data face similar limitations due to their associated costs [25]. To overcome these limitations, we have proposed a computational clinical decision-supporting system based on deep learning models that utilize patient medical history data.…”

Section: Limitations Of Our Modelsmentioning

confidence: 99%

A computational clinical decision-supporting system to suggest effective anti-epileptic drugs for pediatric epilepsy patients based on deep learning models using patient’s medical history

Cho,

Yu,

Shin

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Epilepsy, a chronic brain disorder characterized by abnormal brain activity that causes seizures and other symptoms, is typically treated using anti-epileptic drugs (AEDs) as the first-line therapy. However, due to the variations in their modes of action, identification of effective AEDs often relies on ad hoc trials, which is particularly challenging for pediatric patients. Thus, there is significant value in computational methods capable of assisting in the selection of AEDs, aiming to minimize unnecessary medication and improve treatment efficacy. Results In this study, we collected 7,507 medical records from 1,000 pediatric epilepsy patients and developed a computational clinical decision-supporting system for AED selection. This system leverages three multi-channel convolutional neural network (CNN) models tailored to three specific AEDs (vigabatrin, prednisolone, and clobazam). Each CNN model predicts whether a respective AED is effective on a given patient or not. The CNN models showed AUROCs of 0.90, 0.80, and 0.92 in 10-fold cross-validation, respectively. Evaluation on a hold-out test dataset further revealed positive predictive values (PPVs) of 0.92, 0.97, and 0.91 for the three respective CNN models, representing that suggested AEDs by our models would be effective in controlling epilepsy with a high accuracy and thereby reducing unnecessary medications for pediatric patients. Conclusion Our CNN models in the system demonstrated high PPVs for the three AEDs, which signifies the potential of our approach to support the clinical decision-making by assisting doctors in recommending effective AEDs within the three AEDs for patients based on their medical history. This would result in a reduction in the number of unnecessary ad hoc attempts to find an effective AED for pediatric epilepsy patients.

show abstract

Models for predicting treatment efficacy of antiepileptic drugs and prognosis of treatment withdrawal in epilepsy patients

Cited by 11 publications

References 27 publications

Genetic Background of Epilepsy and Antiepileptic Treatments

Genetic Background of Epilepsy and Antiepileptic Treatments

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

A computational clinical decision-supporting system to suggest effective anti-epileptic drugs for pediatric epilepsy patients based on deep learning models using patient’s medical history

Contact Info

Product

Resources

About