Raquel Martinez

Monitoring autonomic nervous system responses offers significant potential for personalized health applications and early intervention. This study presents a machine learning framework for binary classification of physiological activation states using electrocardiogram (ECG) and respiratory (RESP) signals from the WESAD dataset. Stress and amusement were grouped as Activation, whereas baseline and meditation were grouped as Non-Activation. The processing pipeline incorporates R-peak detection, temporal segmentation, handcrafted feature extraction, and subject-independent evaluation. Conventional machine learning classifiers and deep learning architectures were evaluated, together with a proposed Hybrid Multi-Scale Temporal Convolutional–Conformer (MST-Conformer) combining temporal representations learned from ECG and RESP waveforms with handcrafted physiological features. Performance was assessed using 15-fold Leave-One-Subject-Out (LOSO) cross-validation. Adding respiration-derived features to ECG-derived features improved conventional machine learning performance, increasing the highest balanced accuracy from 0.752 to 0.807 and AUC from 0.802 to 0.886. The complete Hybrid MST-Conformer incorporating 27 physiological features achieved a mean accuracy of 0.825, balanced accuracy of 0.820, F1-score of 0.763, and AUC of 0.904. Subject-level analysis also revealed substantial physiological heterogeneity. These results support the potential of combining learned temporal representations with handcrafted physiological information for subject-independent physiological activation classification.

Cerebral palsy (CP) is a neuromotor disorder that affects movement and posture, causing functional limitations and musculoskeletal deformities that persist into adulthood. Variability in motor expression makes identifying the functional level a clinical challenge; achieving greater accuracy in this assessment enables detection of risk factors for postural deterioration. This study analysed a sample of 56 adults with CP to evaluate the ability of different machine learning (ML) models to discriminate between levels IV and V of the Gross Motor Function Classification System (GMFCS), using a total of 78 clinical variables such as spasticity, range of motion, deformities, and postural asymmetries. Different supervised learning models were compared, and a relabelling procedure was applied to improve classification consistency. The results indicate that there is valuable information in the collected standardised variables for classifying levels IV and V. The best performances were subsequently obtained by the neural network and the linear logistic regression, achieving the latter, which has explanatory properties interesting for clinicians, accuracy, F1-score and AUC metrics of 92.83%, 93.44% and 99.35%, respectively. These findings suggest that ML could emerge as a useful and explanatory tool for functional assessment of CP in adults and for the design of personalised rehabilitation strategies.

Stress is a prevalent global concern impacting individuals across various life aspects. This paper investigates stress detection using electroencephalographic (EEG) signals, which have proven valuable for studying neural correlates of stress. Stress was induced in students, and physiological data was recorded as part of the experimental setup. Different feature sets were extracted and four machine learning models, including LightGBM, Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), were utilized for classification tasks. The findings indicate that the mean and standard deviation of 19 channels consistently outperform other feature sets. LightGBM demonstrates superior performance across all scenarios compared to CNN, KNN, and SVM. Overall, this study presents an effective stress detection approach using EEG signals and demonstrates the potential of integrating simple statistical features for enhanced classification accuracy. The findings contribute to the advancement of stress monitoring technologies, with potential applications in wearables and BCIs for real-time stress management.

More than half of patients with high spinal cord injury (SCI) suffer from episodes of autonomic dysreflexia (AD), a condition that can lead to lethal situations, such as cerebral haemorrhage, if not treated correctly. Clinicians assess AD using clinical variables obtained from the patient’s history and physiological variables obtained invasively and non-invasively. This work aims to design a machine learning-based system to assist in the initial diagnosis of AD. For this purpose, 29 patients with SCI participated in a test at Cruces University Hospital in which data were collected using both invasive and non-invasive methods. The system proposed in this article is based on a two-level hierarchical classification to diagnose AD and only uses 35 features extracted from the non-invasive stages of the experiment (clinical and physiological features). The system achieved a 93.10% accuracy with a zero false negative rate for the class of having the disease, an essential condition for treating patients according to medical criteria.

The main objective of this work is to perform a preliminary study of the potential of using physiological signals as biomarkers for the identification of Autonomic Dysreflexia (AD) in patients suffering from a spinal cord injury. For this purpose, a test was done in which patients' bladder was filled with a saline solution for producing effects related to dysreflexia in their organism. Two biosignals were collected from the patients' body during this test: the electrocardiogram and the GSR sweating signal. Later, the research team extracted global features from the complete signal records and local features using a sliding window analysis approach. Finally, these features were analysed to see how strongly they were correlated to different dysreflexia states. This analysis showed that more than half of the extracted features belong to the first quartile, 41 out of 79, some of them even reaching a 99.9% correlation score.