In response to challenging circumstances, the human body can experience marked levels of anxiety and distress. To prevent stress-related complications, timely identification of stress symptoms is crucial, necessitating the need for continuous stress monitoring. Wearable devices offer a means of real-time and ongoing data collection, facilitating personalized stress monitoring. Based on our protocol for data pre-processing, this study proposes to analyze signals obtained from the Empatica E4 bracelet using machine-learning algorithms (Random Forest, SVM, and Logistic Regression) to determine the efficacy of the abovementioned techniques in differentiating between stressful and non-stressful situations. Photoplethysmographic and electrodermal activity signals were collected from 29 subjects to extract 27 features which were then fed into three different machine-learning algorithms for binary classification. Using MATLAB after applying the chi-square test and Pearson’s correlation coefficient on WEKA for features’ importance ranking, the results demonstrated that the Random Forest model has the highest stability (accuracy of 76.5%) using all the features. Moreover, the Random Forest applying the chi-test for feature selection reached consistent results in terms of stress evaluation based on precision, recall, and F1-measure (71%, 60%, 65%, respectively).

Falls and their aftermath pose significant healthcare challenges, impacting individuals across various age groups and occupational backgrounds. These incidents detrimentally affect functional mobility and overall quality of life, necessitating a comprehensive approach to fall detection systems in diverse populations. Therefore, wearable devices are necessary to continuously monitor activities. This work introduces a novel deep-learning model specifically optimized for edge devices capable of detecting falls. The wearable sensor integrates a pressure sensor, a three-axis gyroscope, and a three-axis accelerometer. The developed system works in real-time with the dual objective of identifying the activities carried out and classifying them as falls or daily life activities. We evaluated this approach using both our self-collected dataset and a publicly available one (SisFall). Furthermore, in our dataset, we also introduced the syncope between falls that the sensor must be able to detect. Results demonstrate that while maintaining low-cost, low-complexity of the model, low-power consumption, and high-speed data processing, combining usage of the three sensors and deep learning algorithm allows to obtain an accuracy of 99.38%, and inference time of 25 ms.

In response to challenging circumstances, the human body can experience marked levels of anxiety and distress. Wearable devices offer a means of real-time and ongoing data collection, facilitating personalized stress monitoring. Therefore, we collected physiological signals (blood pressure volume and electrodermal activities), using Empatica E4, from 29 subjects. A personalized protocol was developed to cause cognitive, mental, and psychological stressors since they are the ones that can be experienced in working or academic environment. We also propose a pipeline to clean and process these two signals to maximize the quality of further analysis. This study aids in the comprehension of the complex connection between stress and working situations by offering a sizable dataset made up of different physiological data. It additionally enables them to create cutting-edge stress-reduction techniques and improving professional achievement while lessening the negative impact of stress on welfare.

Insulin pumps and other smart devices have recently made significant advancements in the treatment of diabetes, a disorder that affects people all over the world. The development of medical AI has been influenced by AI methods designed to help physicians make diagnoses, choose a course of therapy, and predict outcomes. In this article, we thoroughly analyse how AI is being used to enhance and personalize diabetes treatment. The search turned up 77 original research papers, from which we've selected the most crucial information regarding the learning models employed, the data typology, the deployment stage, and the application domains. We identified two key trends, enabled mostly by AI: patient-based therapy personalization and therapeutic algorithm optimization. In the meanwhile, we point out various shortcomings in the existing literature, like a lack of multimodal database analysis or a lack of interpretability. The rapid improvements in AI and the expansion of the amount of data already available offer the possibility to overcome these difficulties shortly and enable a wider deployment of this technology in clinical settings.

The widespread adoption of wearable health monitoring devices has highlighted the need for robust algorithms to detect and mitigate motion artefacts in photoplethysmographic (PPG) signals. This paper introduces a novel approach to motion artifact segmentation, supported by the creation of a new dataset. PPG signals from publicly available repositories were curated and enhanced with precise segmentation masks, enabling rigorous model training and evaluation. Three deep learning architectures —UNet, LSTM-UNet, and Atrous-UNet— were assessed using a comprehensive set of metrics, including Dice Score, Intersection over Union, and Average Hausdorff Distance, to highlight the model performance beyond standard evaluations. This multi-metric approach underscored the importance of addressing diverse aspects such as boundary precision and overall robustness. Atrous-UNet emerged as the most effective model, offering a balance of high performance and computational efficiency suitable for real-time deployment. The models were validated on real-world data from open-source wearable devices, EmotiBit and Bangle.js 2 (accuracy above 80% for both), demonstrating generalizability across varying hardware and environmental conditions. Comparisons with expert and non-expert human annotators revealed that the models significantly outperformed the two groups in reliability and detection consistency. The models were optimized using quantization techniques to enable deployment on resource-constrained devices. Although this introduced some performance losses, the models retained robust artefact detection capabilities with an accuracy of over 78%.

Type 1 diabetes is a disease affecting beta cells of the pancreas and it’s responsible for a decreased insulin secretion, leading to an increased blood glucose level. The traditional method for glucose treatment is based on finger-stick measurement of the blood glucose concentration and consequent manual insulin injection. Nowadays insulin pumps and continuous glucose monitoring systems are replacing them, being simpler and automatized. This paper focuses on analyzing and improving the knowledge about which Machine Learning algorithms can work best with glycaemic data and tries to find out the relation between insulin pump settings and glycaemic control. The dataset is composed of 90 days of recordings taken from 16 children and adolescents. Three Machine Learning approaches, two for classification, Logistic Regression (LR) and Random Forest (RL), and one for regression, Multivariate Linear Regression (MLR), have been used for the purpose. Specifically, the pump settings analysis was performed based on the Time In Range (TIR) computation and comparison consequent to pump setting changes. RF and MLR have shown the best results, while, for the settings’ analysis, the data show a discrete correlation between changes and TIRs. This study provides an interesting closer look at the data recorded by the insulin pump and a suitable starting point for a thorough and complete analysis of them.