State-of-the-art healthcare technologies are incorporating advanced Artificial Intelligence (AI) models, allowing for rapid and easy disease diagnosis. However, most AI models are considered “black boxes,” because there is no explanation for the decisions made by these models. Users may find it challenging to comprehend and interpret the results. Explainable AI (XAI) can explain the machine learning (ML) outputs and contribution of features in disease prediction models. Electroencephalography (EEG) is a potential predictive tool for understanding cortical impairment caused by an ischemic stroke and can be utilized for acute stroke prediction, neurologic prognosis, and post-stroke treatment. This study aims to utilize ML models to classify the ischemic stroke group and the healthy control group for acute stroke prediction in active states. Moreover, XAI tools (Eli5 and LIME) were utilized to explain the behavior of the model and determine the significant features that contribute to stroke prediction models. In this work, we studied 48 patients admitted to a hospital with acute ischemic stroke and 75 healthy adults who had no history of identified other neurological illnesses. EEG was obtained within three months following the onset of ischemic stroke symptoms using frontal, central, temporal, and occipital cortical electrodes (Fz, C1, T7, Oz). EEG data were collected in an active state (walking, working, and reading tasks). In the results of the ML approach, the Adaptive Gradient Boosting models showed around 80% accuracy for the classification of the control group and the stroke group. Eli5 and LIME were utilized to explain the behavior of the stroke prediction model and interpret the model locally around the prediction. The Eli5 and LIME interpretable models emphasized the spectral delta and theta features as local contributors to stroke prediction. From the findings of this explainable AI research, it is expected that the stroke-prediction XAI model will help with post-stroke treatment and recovery, as well as help healthcare professionals, make their diagnostic decisions more explainable.

Electroencephalography (EEG) is immediate and sensitive to neurological changes resulting from sleep stages and is considered a computing tool for understanding the association between neurological outcomes and sleep stages. EEG is expected to be an efficient approach for sleep stage prediction outside a highly equipped clinical setting compared with multimodal physiological signal-based polysomnography. This study aims to quantify the neurological EEG-biomarkers and predict five-class sleep stages using sleep EEG data. We investigated the three-channel EEG sleep recordings of 154 individuals (mean age of 53.8 ± 15.4 years) from the Haaglanden Medisch Centrum (HMC, The Hague, The Netherlands) open-access public dataset of PhysioNet. The power of fast-wave alpha, beta, and gamma rhythms decreases; and the power of slow-wave delta and theta oscillations gradually increases as sleep becomes deeper. Delta wave power ratios (DAR, DTR, and DTABR) may be considered biomarkers for their characteristics of attenuation in NREM sleep and subsequent increase in REM sleep. The overall accuracy of the C5.0, Neural Network, and CHAID machine-learning models are 91%, 89%, and 84%, respectively, for multi-class classification of the sleep stages. The EEG-based sleep stage prediction approach is expected to be utilized in a wearable sleep monitoring system.

Electroencephalography (EEG) is a non-invasive method employed to discern human behaviors by monitoring the neurological responses during cognitive and motor tasks. Machine learning (ML) represents a promising tool for the recognition of human activities (HAR), and eXplainable artificial intelligence (XAI) can elucidate the role of EEG features in ML-based HAR models. The primary objective of this investigation is to investigate the feasibility of an EEG-based ML model for categorizing everyday activities, such as resting, motor, and cognitive tasks, and interpreting models clinically through XAI techniques to explicate the EEG features that contribute the most to different HAR states. The study involved an examination of 75 healthy individuals with no prior diagnosis of neurological disorders. EEG recordings were obtained during the resting state, as well as two motor control states (walking and working tasks), and a cognition state (reading task). Electrodes were placed in specific regions of the brain, including the frontal, central, temporal, and occipital lobes (Fz, C1, C2, T7, T8, Oz). Several ML models were trained using EEG data for activity recognition and LIME (Local Interpretable Model-Agnostic Explanations) was employed for interpreting clinically the most influential EEG spectral features in HAR models. The classification results of the HAR models, particularly the Random Forest and Gradient Boosting models, demonstrated outstanding performances in distinguishing the analyzed human activities. The ML models exhibited alignment with EEG spectral bands in the recognition of human activity, a finding supported by the XAI explanations. To sum up, incorporating eXplainable Artificial Intelligence (XAI) into Human Activity Recognition (HAR) studies may improve activity monitoring for patient recovery, motor imagery, the healthcare metaverse, and clinical virtual reality settings.

Current DNA sequence datasets have become extremely large, making it a great challenge for single-processor and main-memory-based computing systems to mine interesting patterns. Such limited hardware resources make the performance of most Apriori-like algorithms inefficient. However, recent implementation of a MapReduce framework has overcome these limitations. Furthermore, mining with maximal contiguous frequent patterns to express the function and structure of DNA sequences is a useful technique, capable of capturing the common data characteristics among related sequences. In this paper, we proposed an efficient approach for mining maximal contiguous frequent patterns in large DNA sequence data using MapReduce framework which can handle a massive DNA sequence datasets with a large number of nodes on a Hadoop platform. Our extensive experimental results show that the proposed approach can mine the complete set of maximal contiguous frequent patterns very efficiently.

Background/Objectives: Cardiovascular disease (CVD) remains a leading cause of mortality and disability worldwide, with timely diagnosis critical for preventing long-term functional impairment. Electrocardiograms (ECGs) provide essential biomarkers of cardiac function, but their interpretation is often complex, particularly across multi-institutional datasets. Methods: This study presents an explainable federated learning framework with long short-term memory (FL-LSTM) for multi-class heart disease classification, capable of distinguishing arrhythmia, ischemia, and healthy states while preserving patient privacy. Results: The model was trained and evaluated on three heterogeneous ECG datasets, achieving 92% accuracy, 99% AUC, and 91% F1 score, outperforming existing federated approaches. Model interpretability is provided via SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), highlighting clinically relevant ECG biomarkers such as P-wave height, R-wave height, QRS complex, RR interval, and QT interval. Conclusions: By integrating temporal modeling, federated learning, and interpretable AI, the framework enables secure and collaborative cardiac diagnosis while supporting transparent clinical decision-making in distributed healthcare settings.

Computational Grids consist of heterogeneous collections of geographically distributed computing resources and have supported numerous scientific applications that require substantial amounts of computing power and storage space. From the point of view of scientists who want to leverage these Grid computing resources, effectively locating appropriate computing resources with minimized allocation overheads is crucial to successfully execute large-scale scientific applications. However, Grid resource availability is highly unstable and current Grid Information Service (GIS) does not provide accurate state information of computing resources. This can make it very difficult for users and systems (Schedulers, Resource brokers) to schedule the jobs in the Grid system and to map tasks on appropriate available resources. In this paper, we present SCOUT system that can provide scientific users with current state information about Grid computing resources including the number of available CPU cores and average response time to get resources allocated. With the help of SCOUT, we can periodically profile resource availability of the Computing Elements (CE) in Grids and monitor their average response time and performance. It provides a mechanism to find out the number of available CPU cores required for the applications to execute their tasks within shortest expected time which can accelerate the productivity of leveraging Grid computing resources for solving complex and challenging scientific problems. We have performed resource profiling based on SCOUT system on two different VO(Virtual Organization)s during one month period and based on that information, we could successfully perform large-scale drug repositioning simulations over 2,000 CPU cores.