Epilepsy is a neurological disorder (the third most common, following stroke and migraines). A key aspect of its diagnosis is the presence of seizures that occur without a known cause and the potential for new seizures to occur. Machine learning has shown potential as a cost-effective alternative for rapid diagnosis. In this study, we review the current state of machine learning in the detection and prediction of epileptic seizures. The objective of this study is to portray the existing machine learning methods for seizure prediction. Internet bibliographical searches were conducted to identify relevant literature on the topic. Through cross-referencing from key articles, additional references were obtained to provide a comprehensive overview of the techniques. As the aim of this paper aims is not a pure bibliographical review of the subject, the publications here cited have been selected among many others based on their number of citations. To implement accurate diagnostic and treatment tools, it is necessary to achieve a balance between prediction time, sensitivity, and specificity. This balance can be achieved using deep learning algorithms. The best performance and results are often achieved by combining multiple techniques and features, but this approach can also increase computational requirements.

The rapid advancement of Next-Generation Sequencing (NGS) technologies has revolutionized the field of genomics, producing large volumes of data that necessitate sophisticated analytical techniques. This paper introduces a Deep Learning model designed to predict the pathogenicity of genetic variants, a vital component in advancing personalized medicine. The model is trained on a dataset derived from the analysis of NGS outputs, containing a combination of well-defined and ambiguous genetic variants. By employing a semi-supervised learning approach, the model efficiently utilizes both confidently labeled and less certain data. At the core of the methodology is the Feature Tokenizer Transformer architecture, which processes both numerical and categorical genomic information. The preprocessing pipeline includes key steps such as data imputation, scaling, and encoding to ensure high data quality. The results highlight the model’s impressive accuracy, particularly in detecting confidently labeled variants, while also addressing the impact of its predictions on less certain (soft-labeled) data.

Hippocampal dysfunction is the hallmark of mesial temporal lobe epilepsy (MTLE), the most common epileptic syndrome in adults and the most often refractory to medical therapy. Deep brain stimulation (DBS) may ameliorate drug-refractory MTLE, but it still cannot guarantee a seizure-free life. One major drawback is that the stimulation policy is informed by trial-and-error rather than by the operating mode of the brain. Thus, optimizing DBS parameters is still an unmet clinical need. Here, we propose the deployment of hippocampal interictal activity in a biohybrid approach to control limbic ictogenesis. Specifically, an electronic bridge establishes a graft-host interaction between the hippocampal subfield CA3 (graft) and the parahippocampal cortex (CTX – host) of distinct rodent brain slices, both treated with 4-aminopyridine; the electronic bridge relays the graft interictal events to the host via electrical pulses. We show that interictal activity generated by the graft CA3 controls limbic ictogenesis in the host CTX even in the absence of feedback from it, thus likely reflecting an intrinsic anti-ictogenic clock of this brain region. This work opens a translational perspective for MTLE treatment via biohybrid neuroprostheses relying on the intrinsic clock of incorporated hippocampal cells.