Epilepsy is regarded as a structural and functional network disorder, affecting around 50 million people worldwide. A correct disease diagnosis can lead to quicker medical action, preventing adverse effects. This paper reports the design of a classifier for epilepsy diagnosis in patients after a first ictal episode, using electroencephalogram (EEG) recordings. The dataset consists of resting-state EEG from 629 patients, of which 504 were retained for the study. The patient’s cohort exists out of 291 patients with epilepsy and 213 patients with other pathologies. The data were split into two sets: 80% training set and 20% test set. The extracted features from EEG included functional connectivity measures, graph measures, band powers and brain asymmetry ratios. Feature reduction was performed, and the models were trained using Machine Learning (ML) techniques. The models’ evaluation was performed with the area under the receiver operating characteristic curve (AUC). When focusing specifically on focal lesional epileptic patients, better results were obtained. This classification task was optimized using a 5-fold cross-validation, where SVM using PCA for feature reduction achieved an AUC of 0.730 ± 0.030. In the test set, the same model achieved 0.649 of AUC. The verified decrease is justified by the considerable diversity of pathologies in the cohort. An analysis of the selected features across tested models shows that functional connectivity and its graph measures have the most considerable predictive power, along with full-spectrum frequency-based features. To conclude, the proposed algorithms, with some refinement, can be of added value for doctors diagnosing epilepsy from EEG recordings after a suspected first seizure.

No abstract

Introduction: Healthcare policies and clinical decisions heavily rely on research publications from high-impact medical journals. A lack of author diversity in medical publications poses a risk to underrepresented groups. To promote equity in healthcare medical decisions, fostering collaborations within research groups is crucial. This study integrates scientometrics with network analysis to uncover intricate co-authorship networks and examine diversity and inclusion in scientific collaboration. Methods: The authors' metadata from five high-impact medical journals were collected, and a weighted graph of co-authorships was constructed. The study addresses four research questions: identifying influential authors, exploring research output communities, analyzing collaboration patterns, and examining the evolution of collaboration over time. Results: Central nodes are significantly more likely to be male or from high-income countries. Further, when evaluated over time, the graph reveals concerning trends in diversity where collaboration with authors from lower income countries is not growing. All code is publicly available on GitHub. Discussion: The findings underscore the need to promote diversity within research niches and question the role of gatekeepers in facilitating inclusivity. Future studies should expand the scope of network analysis and explore additional factors such as funding sources and guidelines. Conclusion: Overall, this study contributes a framework for auditing diversity and inclusion in scientific collaboration, aiming to promote transparency and a more equitable medical knowledge production system.

No abstract