The negative effects of mental stress on human health has been known for decades. High-level stress must be detected at early stages to prevent these negative effects. After the emergence of wearable devices that could be part of our lives, researchers have started detecting extreme stress of individuals with them during daily routines. Initial experiments were performed in laboratory environments and recently a number of works took a step outside the laboratory environment to the real-life. We developed an automatic stress detection system using physiological signals obtained from unobtrusive smart wearable devices which can be carried during the daily life routines of individuals. This system has modality-specific artifact removal and feature extraction methods for real-life conditions. We further tested our system in a real-life setting with collected physiological data from 21 participants of an algorithmic programming contest for nine days. This event had lectures, contests as well as free time. By using heart activity, skin conductance and accelerometer signals, we successfully discriminated contest stress, relatively higher cognitive load (lecture) and relaxed time activities by using different machine learning methods.

Stress is one of the most significant health problems in today's world. Existing work has used heart rate variability (HRV) to detect stress and provide biofeedback in order to regulate it. There has been a growing interest in using wearable biosensors to measure HRV. Each of these sensors acquires heart rate data using different technologies for various bodily locations, therefore posing a challenge for researchers to decide upon a particular device in a research experiment. Previous work has only compared different sensing devices against a gold standard in terms of data quality, thus overlooking qualitative analysis for the usability and acceptability of such devices. This paper introduces a mixed-methods approach to compare the data quality and user acceptance of the six most common wearable heart rate monitoring biosensors. We conducted a 70-minute data collection procedure to obtain HRV data from 32 participants followed by a 10-minute semi-structured interview on sensors' wearability and comfort, long-term use, aesthetics, and social acceptance. We performed quantitative analysis consisting of correlation and agreement analysis on the HRV data and thematic analysis on qualitative data obtained from interviews. Our results show that the electrocardiography (ECG) chest strap achieved the highest correlation and agreement levels in all sessions and had the lowest amount of artifacts, followed by the photoplethysmography (PPG) wristband, ECG sensor board kit and PPG smartwatch. In all three sessions, wrist-worn devices showed a lower amount of agreement and correlation with the reference device. Qualitative findings from interviews highlight that participants prefer wrist and arm-worn devices in terms of aesthetics, wearability, and comfort, followed by chest-worn devices. Moreover, participants mentioned that the latter are more likely to invite social judgment from others, and they would not want to wear it in public. Participants preferred the chest strap for short-term use and the wrist and arm-worn sensors over long-time.

Researchers strive hard to develop effective ways to detect and cope with enduring highlevel daily stress as early as possible to prevent serious health consequences. Although research has traditionally been conducted in laboratory settings, a set of new studies have recently begun to be conducted in ecological environments with unobtrusive wearable devices. Since patterns of stress are ideographic, person-independent models have generally lower accuracies. On the contrary, person-specific models have higher accuracies but they require a long-term data collection period. In this study, we developed a hybrid approach of personal level stress clustering by using baseline stress self-reports to increase the success of person-independent models without requiring a substantial amount of personal data. We further added decision level smoothing to our unobtrusive smartwatch based stress level differentiation system to increase the performance by correcting false labels assigned by the machine learning algorithm. In order to test and evaluate our system, we collected physiological data from 32 participants of a summer school with wrist-worn unobtrusive wearable devices. This event is comprised of baseline, lecture, exam and recovery sessions. In the recovery session, a stress management method was applied to alleviate the stress of the participants. The perceived stress in the form of NASA-TLX questionnaires collected from the users as self-reports and physiological stress levels extracted using wearable sensors are examined separately. By using our system, we were able to differentiate the 3-levels of stress successfully. We further substantially increase our performance by personal stress level clustering and by applying high-level accuracy calculation and decision level smoothing methods. We also demonstrated the success of the stress reduction methods by analyzing physiological signals and self-reports.

Stress is an inescapable element of the modern age. Instances of untreated stress may lead to a reduction in the individual’s health, well-being and socio-economic situation. Stress management application development for wearable smart devices is a growing market. The use of wearable smart devices and biofeedback for individualized real-life stress reduction interventions has received less attention. By using our unobtrusive automatic stress detection system for use with consumer-grade smart bands, we first detected stress levels. When a high stress level is detected, our system suggests the most appropriate relaxation method by analyzing the physical activity-based contextual information. In more restricted contexts, physical activity is lower and mobile relaxation methods might be more appropriate, whereas in free contexts traditional methods might be useful. We further compared traditional and mobile relaxation methods by using our stress level detection system during an eight day EU project training event involving 15 early stage researchers (mean age 28; gender 9 Male, 6 Female). Participants’ daily stress levels were monitored and a range of traditional and mobile stress management techniques was applied. On day eight, participants were exposed to a ‘stressful’ event by being required to give an oral presentation. Insights about the success of both traditional and mobile relaxation methods by using the physiological signals and collected self-reports were provided.

Chronic stress leads to poor well-being, and it has effects on life quality and health. Society may have significant benefits from an automatic daily life stress detection system using unobtrusive wearable devices using physiological signals. However, the performance of these systems is not sufficiently accurate when they are used in unrestricted daily life compared to the systems tested in controlled real-life and laboratory conditions. To test our stress level detection system that preprocesses noisy physiological signals, extracts features, and applies machine learning classification techniques, we used a laboratory experiment and ecological momentary assessment based data collection with smartwatches in daily life. We investigated the effect of different labeling techniques and different training and test environments. In the laboratory environments, we had more controlled situations, and we could validate the perceived stress from self-reports. When machine learning models were trained in the laboratory instead of training them with the data coming from daily life, the accuracy of the system when tested in daily life improved significantly. The subjectivity effect coming from the self-reports in daily life could be eliminated. Our system obtained higher stress level detection accuracy results compared to most of the previous daily life studies.

While Artificial Intelligence (AI) promises significant enhancements for Clinical Decision Support Systems (CDSSs), the opacity of many AI models remains a major barrier to clinical adoption, primarily due to interpretability and trust challenges. Explainable AI (XAI) seeks to bridge this gap by making model reasoning understandable to clinicians, but technical XAI solutions have too often failed to address real-world clinician needs, workflow integration, and usability concerns. This study synthesizes persistent challenges in applying XAI to CDSS—including mismatched explanation methods, suboptimal interface designs, and insufficient evaluation practices—and proposes a structured, user-centered framework to guide more effective and trustworthy XAI-CDSS development. Drawing on a comprehensive literature review, we detail a three-phase framework encompassing user-centered XAI method selection, interface co-design, and iterative evaluation and refinement. We demonstrate its application through a retrospective case study analysis of a published XAI-CDSS for sepsis care. Our synthesis highlights the importance of aligning XAI with clinical workflows, supporting calibrated trust, and deploying robust evaluation methodologies that capture real-world clinician–AI interaction patterns, such as negotiation. The case analysis shows how the framework can systematically identify and address user-centric gaps, leading to better workflow integration, tailored explanations, and more usable interfaces. We conclude that achieving trustworthy and clinically useful XAI-CDSS requires a fundamentally user-centered approach; our framework offers actionable guidance for creating explainable, usable, and trusted AI systems in healthcare.