There is an increasing interest in applying artificial intelligence techniques to forecast epileptic seizures. In particular, machine learning algorithms could extract nonlinear statistical regularities from electroencephalographic (EEG) time series that can anticipate abnormal brain activity. The recent literature reports promising results in seizure detection and prediction tasks using machine and deep learning methods. However, performance evaluation is often based on questionable randomized cross-validation schemes, which can introduce correlated signals (e.g., EEG data recorded from the same patient during nearby periods of the day) into the partitioning of training and test sets. The present study demonstrates that the use of more stringent evaluation strategies, such as those based on leave-one-patient-out partitioning, leads to a drop in accuracy from about 80% to 50% for a standard eXtreme Gradient Boosting (XGBoost) classifier on two different data sets. Our findings suggest that the definition of rigorous evaluation protocols is crucial to ensure the generalizability of predictive models before proceeding to clinical trials.

Objective: Seizure prediction could greatly improve the quality of life of people suffering from epilepsy. Modern prediction systems leverage artificial intelligence (AI) techniques to automatically analyze neurophysiological data, most commonly the electroencephalogram (EEG), in order to anticipate upcoming epileptic events. However, the performance of these systems is normally assessed using randomized splitting methods, which can suffer from data leakage and thus result in an optimistic evaluation. In this review, we systematically surveyed the available scientific literature looking for research approaches that adopted more stringent assessment methods based on patient-independent testing. Approach: We queried three scientific databases (PubMed, Scopus, and Web of Science), focusing on AI techniques based on non-invasive EEG recorded from human subjects. We first summarize a standardized signal processing pipeline that could be deployed for the development and testing of cross-patient seizure prediction systems. We then analyze the research work that meets our selection criteria. Main results: 21 articles adopted patient-independent validation methods, constituting only 4% of the published work in the entire field of epileptic seizure prediction. Among eligible articles, the most common approach to deal with cross-patient scenarios was based on source domain adaptation techniques, which allow to fine-tune the predictive model on a limited set of data recorded from a set of independent target patients. Significance: Overall, our review indicates that epileptic seizure prediction remains an extremely challenging problem and significant research efforts are still needed to develop automated systems that can be deployed in realistic clinical settings. Our review protocol is based on the preferred reporting items for systematic review and meta-analysis protocols 2020 guidelines for conducting systematic reviews, considering NHLBI and ROBIS tools to mitigate the risk of bias, and it was pre-registered in PROSPERO (registration number: CRD4202452317).

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

Introduction: Obsessive-Compulsive Disorder (OCD) is one of the most common debilitating mental disorders with a prevalence rate of 2% to 3% in the general population. Previous studies have indicated abnormalities in the dorsolateral prefrontal cortex (DLPFC) of OCD patients; thus, we decided to use transcranial Direct Current Stimulation (tDCS) to decline these patients’ symptoms. Methods: A total of 24 patients with OCD participated in this study with the hope of improvement after the application of tDCS. The subjects were randomly assigned to three groups of Sham, Right DLPFC, and Left DLPFC. tDCS was applied for five consecutive days and in each session, patients were subjected to 2 mA current flow for two 15 minutes followed by a 10-minute rest in between (every session lasted for 40 minutes). Results: Subsequently, the changes in obsessive-compulsive level and cognitive functions were evaluated via Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) and Depression, Anxiety, and Stress Scale 21 (DASS-21) by comparing the results before (pre-test) and after (post-test) tDCS treatment. Conclusion: Ultimately, the scores of the Yale-Brown scale in the Left DLPFC group showed significant changes after treatment with tDCS (mean difference compared to the sham group: -6.18 and P≤0.05). Hereupon, this study demonstrated that transcranial direct current stimulation may cause improvements in symptoms of OCD.

Introduction: Sexual addiction is known as a disorder that afflicts a person with difficulty in controlling or delaying sexual behaviors. To prevent social, physical, and psychological consequences, validated screening tests are needed to diagnose this disorder. One of these tests is established by Carnes with the name of sexual addiction screening test-revised (SAST-R). In this study, SAST-R has been translated and verified in the Persian language. Methods: The original screening test was translated into the Persian language and also back-translated for matching by two separate expert teams. The data was collected through an online survey of 1268 participants who were in the age range of 18 to 65 years (Mean±SD 29.44±6.90), and 56.1% and 43.9% of the population were women and men, respectively. Three questionnaires, including the SAST-R, the hypersexual behavior consequences scale, and the Connor-Davidson resilience scale as the principal, convergent, and divergent tests were administered to the participants. Results: The reliability of the test’s internal consistency (Cronbach α=0.883), split-half (Cronbach α=0.779), and Guttman (lambda coefficients were between 0.773 to 0.883) tests were used. In addition, 4 methods of content validity (sexual hyperactivity specialist approved), convergent structure validity (P<0.001, R=0.731), the validity of divergent structure (P<0.09, R=-0.132), and factor validity (comparative fit index=0.884, goodness of fit index=0.873, root mean square error of approximation=0.047) were measured and confirmed the validity of the test. Conclusion: The Persian version of SAST-R is a reliable preclinical tool to assess the severity of sexual desire in patients.