Artificial intelligence in preclinical epilepsy research: Current state, potential, and challenges

Preclinical translational epilepsy research uses animal models to better understand the mechanisms underlying epilepsy and its comorbidities, as well as to analyze and develop potential treatments that may mitigate this neurological disorder and its associated conditions. Artificial intelligence (AI) has emerged as a transformative tool across various fields, including neuroscience research. AI can assist in the acquisition and analysis of data throughout the experimental process. Currently, the integration of AI techniques, including machine learning (ML), assumes an important role in preclinical epilepsy research. For analytical purposes, the techniques described in this review are categorized into three principal domains based on their objectives. Diagnosis involves identification, characterization, and/or prediction of epileptic seizures utilizing experimental data such as EEG recordings. Identification of comorbidities associated with epilepsy using AI represents a significant advancement in preclinical research. This approach can lead to a comprehensive understanding of the interplay between epilepsy and related disorders. The treatment domain involves the utilization of ML models to conduct simulations and computational analyses to comprehend the underlying mechanisms of epilepsy, discern potential drug targets, and evaluate the efficacy of experimental medications, thereby facilitating the translation of discoveries into clinical settings. This paper aimed to present, explain, and scrutinize some of the AI techniques used in recent years within preclinical epilepsy research. Moreover, advantages, challenges, ethical considerations, reporting issues, and future perspectives will be discussed. PLAIN LANGUAGE SUMMARY: Researchers study epilepsy using animal models to understand its mechanisms and develop novel therapeutic strategies. Artificial intelligence (AI) is becoming an important tool in this work, helping with data collection and analysis. In this critical review, AI techniques are grouped into three main areas: diagnosis of seizures, identification of health disorders associated with epilepsy, and exploration of new treatments. AI enables scientists to spot patterns in brain activity, find connections between epilepsy and other conditions, and test potential medications. This review also examines the advantages, challenges, and future of using AI in this field.