In recent years, noncontact measurements of vital signs using cameras received a great amount of interest. However, some questions are unanswered: (i) Which vital sign is monitored using what type of camera? (ii) What is the performance and which factors affect it? (iii) Which health issues are addressed by camera-based techniques? Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) statement, we conduct a systematic review of continuous camera-based vital sign monitoring using Scopus, PubMed, and the Association for Computing Machinery (ACM) databases. We consider articles that were published between January 2018 and April 2021 in the English language. We include five vital signs: heart rate (HR), respiratory rate (RR), blood pressure (BP), body skin temperature (BST), and oxygen saturation (SpO₂). In total, we retrieve 905 articles and screened them regarding title, abstract, and full text. One hundred and four articles remained: 60, 20, 6, 2, and 1 of the articles focus on HR, RR, BP, BST, and SpO₂, respectively, and 15 on multiple vital signs. HR and RR can be measured using red, green, and blue (RGB) and near-infrared (NIR) as well as far-infrared (FIR) cameras. So far, BP and SpO₂ are monitored with RGB cameras only, whereas BST is derived from FIR cameras only. Under ideal conditions, the root mean squared error is around 2.60 bpm, 2.22 cpm, 6.91 mm Hg, 4.88 mm Hg, and 0.86 °C for HR, RR, systolic BP, diastolic BP, and BST, respectively. The estimated error for SpO₂ is less than 1%, but it increases with movements of the subject and the camera-subject distance. Camera-based remote monitoring mainly explores intensive care, post-anaesthesia care, and sleep monitoring, but also explores special diseases such as heart failure. The monitored targets are newborn and pediatric patients, geriatric patients, athletes (e.g., exercising, cycling), and vehicle drivers. Camera-based techniques monitor HR, RR, and BST in static conditions within acceptable ranges for certain applications. The research gaps are large and heterogeneous populations, real-time scenarios, moving subjects, and accuracy of BP and SpO₂ monitoring.

With the advances in sensor technology, big data, and artificial intelligence, unobtrusive in-home health monitoring has been a research focus for decades. Following up our research on smart vehicles, within the framework of unobtrusive health monitoring in private spaces, this work attempts to provide a guide to current sensor technology for unobtrusive in-home monitoring by a literature review of the state of the art and to answer, in particular, the questions: (1) What types of sensors can be used for unobtrusive in-home health data acquisition? (2) Where should the sensors be placed? (3) What data can be monitored in a smart home? (4) How can the obtained data support the monitoring functions? We conducted a retrospective literature review and summarized the state-of-the-art research on leveraging sensor technology for unobtrusive in-home health monitoring. For structured analysis, we developed a four-category terminology (location, unobtrusive sensor, data, and monitoring functions). We acquired 912 unique articles from four relevant databases (ACM Digital Lib, IEEE Xplore, PubMed, and Scopus) and screened them for relevance, resulting in $n=55$ papers analyzed in a structured manner using the terminology. The results delivered 25 types of sensors (motion sensor, contact sensor, pressure sensor, electrical current sensor, etc.) that can be deployed within rooms, static facilities, or electric appliances in an ambient way. While behavioral data (e.g., presence ($n=38$), time spent on activities ($n=18$)) can be acquired effortlessly, physiological parameters (e.g., heart rate, respiratory rate) are measurable on a limited scale ($n=5$). Behavioral data contribute to functional monitoring. Emergency monitoring can be built up on behavioral and environmental data. Acquired physiological parameters allow reasonable monitoring of physiological functions to a limited extent. Environmental data and behavioral data also detect safety and security abnormalities. Social interaction monitoring relies mainly on direct monitoring of tools of communication (smartphone; computer). In summary, convincing proof of a clear effect of these monitoring functions on clinical outcome with a large sample size and long-term monitoring is still lacking.

Despite their remarkable performance, deep neural networks remain unadopted in clinical practice, which is considered to be partially due to their lack of explainability. In this work, we apply explainable attribution methods to a pre-trained deep neural network for abnormality classification in 12-lead electrocardiography to open this “black box” and understand the relationship between model prediction and learned features. We classify data from two public databases (CPSC 2018, PTB-XL) and the attribution methods assign a “relevance score” to each sample of the classified signals. This allows analyzing what the network learned during training, for which we propose quantitative methods: average relevance scores over a) classes, b) leads, and c) average beats. The analyses of relevance scores for atrial fibrillation and left bundle branch block compared to healthy controls show that their mean values a) increase with higher classification probability and correspond to false classifications when around zero, and b) correspond to clinical recommendations regarding which lead to consider. Furthermore, c) visible P-waves and concordant T-waves result in clearly negative relevance scores in atrial fibrillation and left bundle branch block classification, respectively. Results are similar across both databases despite differences in study population and hardware. In summary, our analysis suggests that the DNN learned features similar to cardiology textbook knowledge.

Major depression (MD) significantly impacts individual well-being and society. The vagus nerve plays a pivotal role in the gut-brain axis, facilitating bidirectional communication between these systems. Recent meta-analyses suggest potential antidepressant effects of probiotics, although their mechanisms remain unclear. This study aimed to assess the impact of a multi-species probiotic (OMNi-BiOTiC® STRESS Repair) on vagus nerve function in 43 MD patients and 43 healthy controls (HC). Participants received either probiotics or placebo twice daily. Serum and stool samples were collected at baseline, 7 days, 28 days, and 3 months. Vagus nerve (VN) function was evaluated using 24-hour electrocardiography (ECG) for heart rate variability (HRV), alongside stool microbiome analysis via 16S rRNA sequencing. After 3 months, MD patients receiving probiotics demonstrated significantly improved morning VN function compared to HC. MD participants who were in the probiotic group showed a significant increase in Christensellales, particularly Akkermansia muciniphila along with improved sleep parameters (use of sleep medication, sleep latency) as measured by the Pittsburgh Sleep Quality Inventory (PSI). This study highlights potential physiological benefits of probiotics in MD, potentially mediated through VN stimulation. Understanding these mechanisms could lead to novel therapeutic approaches for MD management.

Aging affects the 12-lead electrocardiogram (ECG) and correlates with cardiovascular disease (CVD). AI-ECG models estimate aging effects as a novel biomarker but have only been evaluated on single ECGs—without utilizing longitudinal data. We validated an AI-ECG model, originally trained on Brazilian data, using a German cohort with over 20 years of follow-up, demonstrating similar performance (r ² = 0.70) to the original study (0.71). Incorporating longitudinal ECGs revealed a stronger association with cardiovascular risk, increasing the hazard ratio for mortality from 1.43 to 1.65. Moreover, aging effects were associated with higher odds ratios for atrial fibrillation, heart failure, and mortality. Using explainable AI methods revealed that the model aligns with clinical knowledge by focusing on ECG features known to reflect aging. Our study suggests that aging effects in longitudinal ECGs can be applied on population level as a novel biomarker to identify patients at risk early.

The continuing interest in unobtrusive electrocardiography requires the development of algorithms, compensating for an increased number of artifacts. In previous work, we proposed a framework for robust parameter estimation of signals following a piecewise Gaussian derivative model, well suited for describing all waves of a heartbeat. The framework is based on a numeric and analytic representation of applying the Wavelet Transform at arbitrary scale to the input model. For robustly estimating model parameters, it processes lines of zero-crossings in scale-space, showing high accuracy for various noise models in synthetic signals. An initial evaluation with electrocardiography signals revealed that our basic classifier for identifying the correct lines often fails, leading to false parameter estimates. In this work, we propose a general delineation method based on a solid mathematical framework that treats each heartbeat, wave and fiducial point in the same way, tailored only by intuitive parameters and not relying on any heuristically found decision rules. The steps include a novel line classifier based on pre-filtering using domain knowledge, followed by an exhaustive search among all possible combinations of zero-crossing lines and an error-measure quantifying their agreement with the model. The combination with highest agreement is processed by the parameter estimation framework, customized to the computation of all nine fiducial points. Evaluation using the expert-annotated QT database, shows high sensitivity (P: 99.91%, QRS: 99.92%, T: 99.89%) and mean errors below 1ms for all onset and offset fiducial points. The proposed combination of line classification and parameter estimation is well suited for delineating electrocardiograms.