Integrated Electrochemical Aptamer Biosensing and Colorimetric pH Monitoring via Hydrogel Microneedle Assays for Assessing Antibiotic Treatment.

Current methods for therapeutic drug monitoring (TDM) have a long turnaround time as they involve collecting patients' blood samples followed by transferring the samples to medical laboratories where sample processing and analysis are performed. To enable real-time and minimally invasive TDM, a microneedle (MN) biosensor to monitor the levels of two important antibiotics, vancomycin (VAN) and gentamicin (GEN) is developed. The MN biosensor is composed of a hydrogel MN (HMN), and an aptamer-functionalized flexible (Flex) electrode, named HMN-Flex. The HMN extracts dermal interstitial fluid (ISF) and transfers it to the Flex electrode where sensing of the target antibiotics happens. The HMN-Flex performance is validated ex vivo using skin models as well as in vivo in live rat animal models. Data is leveraged from the HMN-Flex system to construct pharmacokinetic profiles for VAN and GEN and compare these profiles with conventional blood-based measurements. Additionally, to track pH and monitor patient's response during antibiotic treatment, an HMN is developed that employs a colorimetric method to detect changes in the pH, named HMN-pH assay, whose performance has been validated both in vitro and in vivo. Further, multiplexed antibiotic and pH detection is achieved by simultaneously employing the HMN-pH and HMN-Flex on live animals.

Crowdsourced data as a strategic approach to include the human dimension in outdoor environmental quality assessments.

Outdoor environments extend living spaces as venues for various activities. Comfortable open public spaces can positively impact citizens' health and well-being, thereby improving the livability and resilience of cities. Considering the visitors' perception of these environments in comfort studies is crucial for ensuring their well-being and promoting the use of these spaces. However, traditional survey methods may be time- and resource-consuming to gather significant sample sizes, usually focusing on selected homogeneous samples. Crowdsourced data, then, has emerged as an alternative for assessing human perception, as it eases the collection of subjective feedback and potentially amplifies impact and inclusivity. This study presents a strategic approach for analyzing publicly available and willingly reported crowdsourced data from a digital mapping platform in outdoor comfort evaluations, aiming to verify whether these data are informative regarding environmental quality perception and to identify the environmental factors that people are most sensitive to. Urban parks located in New York City served as a case study. A multi-source, interdisciplinary information framework combined crowdsourced reviews with environmental data used to determine prevailing thermal conditions. Overall perception of parks was well-rated, revealing that their attractions and activities are probably the most appealing characteristics for park attendance. Regarding environmental perception, acoustic and thermal factors are clearly the most influential. Acoustics were well-rated, while the main aspect regarding the thermal domain is the recognition of shading as a mitigator for hot conditions. Environmental data provided complementary insights, particularly concerning the range of thermal sensations experienced in urban parks. The findings confirm that willingly reported crowdsourced data can provide valuable insights into urban crowd environmental perception, presenting a potentially suitable and effective method to include the human perspective in environmental quality assessments, as well as to evaluate and predict environmental-related risks.

Continuous Patient-Independent Estimation of Respiratory Rate and Blood Pressure Using Robust Spectro-Temporal Features Derived From Photoplethysmogram Only.

Objective: A patient-independent approach for continuous estimation of vital signs using robust spectro-temporal features derived from only photoplethysmogram (PPG) signal. Methods: In the pre-processing stage, we remove baseline shifts and artifacts of the PPG signal using Incremental Merge Segmentation with adaptive thresholding. From the cleaned PPG, we extract multiple parameters independent of individual patient PPG morphology for both Respiration Rate (RR) and Blood Pressure (BP). In addition, we derived a set of novel spectral and statistical features strongly correlated to BP. We proposed robust correlation-based feature selection methods for accurate RR estimates. For fewer computations and accurate measurements of BP, the most significant features are selected using correlation and mutual information measures in the feature engineering part. Finally, RR and BP are estimated using breath counting and a neural network regression model, respectively. Results: The proposed approach outperforms the current state-of-the-art in both RR and BP. The RR algorithm results in mean absolute errors (median, 25th-75th percentiles) of 0.4 (0.1-0.7) for CapnoBase dataset and 0.5(0.3-2.8) for BIDMC dataset without discarding any data window. Similarly, BP approach has been validated on a large dataset derived from MIMIC-II ([Formula: see text]1700 records) which has errors (mean absolute, standard deviation) of 5.0(6.3) and 3.0(4.0) for systolic and diastolic BP, respectively. The results meet the American Association for the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS) Class A criteria. Conclusion: By using robust features and feature selection methods, we alleviated patient dependency to have reliable estimates of vitals.

On urban microclimate spatial-temporal dynamics: Evidence from the integration of fixed and wearable sensing and mapping techniques.

Urban Heat Island (UHI) is acknowledged to generate harmful consequences on human health, and it is one of the main anthropogenic challenges to face in modern cities. Due to the urban dynamic complexity, a full microclimate decoding is required to design tailored mitigation strategies for reducing heat-related vulnerability. This study proposes a new method to assess intra-urban microclimate variability by combining for the first time two dedicated monitoring systems consisting of fixed and mobile techniques. Data from three fixed weather stations were used to analyze long-term trends, while mobile devices (a vehicle and a wearable) were used in short-term monitoring campaigns conducted in summer and winter to assess and geo-locate microclimate spatial variations. Additionally, data from mobile devices were used as input for Kriging interpolation in the urban area of Florence (Italy) as case study. Mobile monitoring sessions provided high-resolution spatial data, enabling the detection of hyperlocal variations in air temperature. The maximum air temperature amplitudes were verified with the wearable system: 3.3 °C in summer midday and 4.3 °C in winter morning. Physiological Equivalent Temperature (PET) demonstrated to be similar when comparing green areas and their adjacent built-up zone, showing up the microclimate mitigation contribution of greenery in its surrounding. Results also showed that mixing the two data acquisition and varied analysis techniques succeeded in investigating the UHI and the site-specific role of potential mitigation actions. Moreover, mobile dataset was reliable for elaborating maps by interpolating the monitored parameters. Interpolation results demonstrated the possibility of optimizing mobile monitoring campaigns by focusing on targeted streets and times of day since interpolation errors increased by 10% only with properly reduced and simplified input samples. This allowed an enhanced detection of the site-specific granularity, which is important for urban planning and policymaking, adaptation, and risk mitigation actions to overcome the UHI and anthropogenic climate change effects.

Environmentally stable and rapidly polymerized tin-tannin catalytic system hydroxyethyl cellulose hydrogel for wireless wearable sensing.

In recent years, flexible sensors constructed mainly from hydrogels have played an indispensable role in several fields. However, the traditional hydrogel preparation process involves complex and time-consuming steps and the freezing or volatilization of water in the water gel in extreme environments greatly limits the further use of the sensor. Therefore, an ionic conductive hydrogel (SnHTD) was designed, which was composed of tannic acid (TA), metal ions Sn2+, hydroxyethyl cellulose (HEC), and acrylamide (AM) in a deep eutectic solvent (DES) and water binary solvent. It is worth noting that the gel time is shortened to less than 3 min by introducing the Sn-TA redox system. The addition of DES makes the hydrogel have a wide temperature tolerance range (-20 to 60 °C) and the ability to store for a long time (30 days). The introduction of HEC increased the tensile stress of hydrogel from 140.17 kPa to 219.89 kPa. Additionally, the hydrogel also has high conductivity, repeatable adhesion and UV shielding properties. In general, this research opens up a new way for room temperature polymerization of environmentally resistant hydrogel materials and effectively meets the growing demand for wireless wearable sensing.

DISPEL: A Python Framework for Developing Measures From Digital Health Technologies.

Goal: This paper introduces DISPEL, a Python framework to facilitate development of sensor-derived measures (SDMs) from data collected with digital health technologies in the context of therapeutic development for neurodegenerative diseases. Methods: Modularity, integrability and flexibility were achieved adopting an object-oriented architecture for data modelling and SDM extraction, which also allowed standardizing SDM generation, naming, storage, and documentation. Additionally, a functionality was designed to implement systematic flagging of missing data and unexpected user behaviors, both frequent in unsupervised monitoring. Results: DISPEL is available under MIT license. It already supports formats from different data providers and allows traceable end-to-end processing from raw data collected with wearables and smartphones to structured SDM datasets. Novel and literature-based signal processing approaches currently allow to extract SDMs from 16 structured tests (including six questionnaires), assessing overall disability and quality of life, and measuring performance outcomes of cognition, manual dexterity, and mobility. Conclusion: DISPEL supports SDM development for clinical trials by providing a production-grade Python framework and a large set of already implemented SDMs. While the framework has already been refined based on clinical trials' data, ad-hoc validation of the provided algorithms in their specific context of use is recommended to the users.

Power-MF: robust fetal QRS detection from non-invasive fetal electrocardiogram recordings.

Objective.Perinatal asphyxia poses a significant risk to neonatal health, necessitating accurate fetal heart rate monitoring for effective detection and management. The current gold standard, cardiotocography, has inherent limitations, highlighting the need for alternative approaches. The emerging technology of non-invasive fetal electrocardiography shows promise as a new sensing technology for fetal cardiac activity, offering potential advancements in the detection and management of perinatal asphyxia. Although algorithms for fetal QRS detection have been developed in the past, only a few of them demonstrate accurate performance in the presence of noise and artifacts.Approach.In this work, we proposePower-MF, a new algorithm for fetal QRS detection combining power spectral density and matched filter techniques. We benchmarkPower-MFagainst three open-source algorithms on two recently published datasets (Abdominal and Direct Fetal ECG Database: ADFECG, subsets B1 Pregnancy and B2 Labour; Non-invasive Multimodal Foetal ECG-Doppler Dataset for Antenatal Cardiology Research: NInFEA).Main results.Our results show thatPower-MFoutperforms state-of-the-art algorithms on ADFECG (B1 Pregnancy: 99.5% ± 0.5% F1-score, B2 Labour: 98.0% ± 3.0% F1-score) and on NInFEA in three of six electrode configurations by being more robust against noise.Significance.Through this work, we contribute to improving the accuracy and reliability of fetal cardiac monitoring, an essential step toward early detection of perinatal asphyxia with the long-term goal of reducing costs and making prenatal care more accessible.

A laser-Engraved Wearable Electrochemical Sensing Patch for Heat Stress Precise Individual Management of Horse.

In point-of-care diagnostics, the continuous monitoring of sweat constituents provides a window into individual's physiological state. For species like horses, with abundant sweat glands, sweat composition can serve as an early health indicator. Considering the salience of such metrics in the domain of high-value animal breeding, a sophisticated wearable sensor patch tailored is introduced for the dynamic assessment of equine sweat, offering insights into pH, potassium ion (K+), and temperature profiles during episodes of heat stress and under normal physiological conditions. The device integrates a laser-engraved graphene (LEG) sensing electrode array, a non-invasive iontophoretic module for stimulated sweat secretion, an adaptable signal processing unit, and an embedded wireless communication framework. Profiting from an admirable Truth Table capable of logical evaluation, the integrated system enabled the early and timely assessment for heat stress, with high accuracy, stability, and reproducibility. The sensor patch has been calibrated to align with the unique dermal and physiological contours of equine anatomy, thereby augmenting its applicability in practical settings. This real-time analysis tool for equine perspiration stands to revolutionize personalized health management approaches for high-value animals, marking a significant stride in the integration of smart technologies within the agricultural sector.

Erratum: Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations.

[This corrects the article DOI: 10.3389/fbioe.2024.1285845.].

Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations.

Portable measurement systems using inertial sensors enable motion capture outside the lab, facilitating longitudinal and large-scale studies in natural environments. However, estimating 3D kinematics and kinetics from inertial data for a comprehensive biomechanical movement analysis is still challenging. Machine learning models or stepwise approaches performing Kalman filtering, inverse kinematics, and inverse dynamics can lead to inconsistencies between kinematics and kinetics. We investigated the reconstruction of 3D kinematics and kinetics of arbitrary running motions from inertial sensor data using optimal control simulations of full-body musculoskeletal models. To evaluate the feasibility of the proposed method, we used marker tracking simulations created from optical motion capture data as a reference and for computing virtual inertial data such that the desired solution was known exactly. We generated the inertial tracking simulations by formulating optimal control problems that tracked virtual acceleration and angular velocity while minimizing effort without requiring a task constraint or an initial state. To evaluate the proposed approach, we reconstructed three trials each of straight running, curved running, and a v-cut of 10 participants. We compared the estimated inertial signals and biomechanical variables of the marker and inertial tracking simulations. The inertial data was tracked closely, resulting in low mean root mean squared deviations for pelvis translation (≤20.2 mm), angles (≤1.8 deg), ground reaction forces (≤1.1 BW%), joint moments (≤0.1 BWBH%), and muscle forces (≤5.4 BW%) and high mean coefficients of multiple correlation for all biomechanical variables (≥0.99). Accordingly, our results showed that optimal control simulations tracking 3D inertial data could reconstruct the kinematics and kinetics of individual trials of all running motions. The simulations led to mutually and dynamically consistent kinematics and kinetics, which allows researching causal chains, for example, to analyze anterior cruciate ligament injury prevention. Our work proved the feasibility of the approach using virtual inertial data. When using the approach in the future with measured data, the sensor location and alignment on the segment must be estimated, and soft-tissue artifacts are potential error sources. Nevertheless, we demonstrated that optimal control simulation tracking inertial data is highly promising for estimating 3D kinematics and kinetics for a comprehensive biomechanical analysis.

Wearable Sensing Device Integrated with Prestored Reagents for Cortisol Detection in Sweat.

Wearable sweat sensors have achieved rapid development since they hold great potential in personalized health monitoring. However, a typical difficulty in practical processes is the control of working conditions for biorecognition elements, e.g., pH level and ionic strength in sweat may decrease the affinity between analytes and recognition elements. Here, we developed a wearable sensing device for cortisol detection in sweat using an aptamer as the recognition element. The device integrated functions of sweat collection, reagent prestorage, and signal conversion. Especially, the components of prestored reagents were optimized according to the inherent characteristics of sweat samples and electrodes, which allowed us to keep optimal conditions for aptamers. The sweat samples were transferred from the inlet of the device to the reagent prestored chamber, and the dry preserved reagents were rehydrated with sweat and then arrived at the aptamer-modified electrodes. Sweat samples of volunteers were analyzed by the wearable sensing device, and the results showed a good correlation with those of the ELISA kit. We believe that this convenient and reliable wearable sensing device has significant potential in self-health monitoring.

Laser-Induced Graphene-Based Sensors in Health Monitoring: Progress, Sensing Mechanisms, and Applications.

The rising global population and improved living standards have led to an alarming increase in non-communicable diseases, notably cardiovascular and chronic respiratory diseases, posing a severe threat to human health. Wearable sensing devices, utilizing micro-sensing technology for real-time monitoring, have emerged as promising tools for disease prevention. Among various sensing platforms, graphene-based sensors have shown exceptional performance in the field of micro-sensing. Laser-induced graphene (LIG) technology, a cost-effective and facile method for graphene preparation, has gained particular attention. By converting polymer films directly into patterned graphene materials at ambient temperature and pressure, LIG offers a convenient and environmentally friendly alternative to traditional methods, opening up innovative possibilities for electronic device fabrication. Integrating LIG-based sensors into health monitoring systems holds the potential to revolutionize health management. To commemorate the tenth anniversary of the discovery of LIG, this work provides a comprehensive overview of LIG's evolution and the progress of LIG-based sensors. Delving into the diverse sensing mechanisms of LIG-based sensors, recent research advances in the domain of health monitoring are explored. Furthermore, the opportunities and challenges associated with LIG-based sensors in health monitoring are briefly discussed.

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation.

Objective: Recent deep learning techniques hold promise to enable IMU-driven kinetic assessment; however, they require large extents of ground reaction force (GRF) data to serve as labels for supervised model training. We thus propose using existing self-supervised learning (SSL) techniques to leverage large IMU datasets to pre-train deep learning models, which can improve the accuracy and data efficiency of IMU-based GRF estimation. Methods: We performed SSL by masking a random portion of the input IMU data and training a transformer model to reconstruct the masked portion. We systematically compared a series of masking ratios across three pre-training datasets that included real IMU data, synthetic IMU data, or a combination of the two. Finally, we built models that used pre-training and labeled data to estimate GRF during three prediction tasks: overground walking, treadmill walking, and drop landing. Results: When using the same amount of labeled data, SSL pre-training significantly improved the accuracy of 3-axis GRF estimation during walking compared to baseline models trained by conventional supervised learning. Fine-tuning SSL model with 1-10% of walking data yielded comparable accuracy to training baseline model with 100% of walking data. The optimal masking ratio for SSL is 6.25-12.5%. Conclusion: SSL leveraged large real and synthetic IMU datasets to increase the accuracy and data efficiency of deep-learning-based GRF estimation, reducing the need for labeled data. Significance: This work, with its open-source code and models, may unlock broader use cases of IMU-driven kinetic assessment by mitigating the scarcity of GRF measurements in practical applications.

Biomimetic Wearable Sensors: Emerging Combination of Intelligence and Electronics.

Owing to the advancement of interdisciplinary concepts, for example, wearable electronics, bioelectronics, and intelligent sensing, during the microelectronics industrial revolution, nowadays, extensively mature wearable sensing devices have become new favorites in the noninvasive human healthcare industry. The combination of wearable sensing devices with bionics is driving frontier developments in various fields, such as personalized medical monitoring and flexible electronics, due to the superior biocompatibilities and diverse sensing mechanisms. It is noticed that the integration of desired functions into wearable device materials can be realized by grafting biomimetic intelligence. Therefore, herein, the mechanism by which biomimetic materials satisfy and further enhance system functionality is reviewed. Next, wearable artificial sensory systems that integrate biomimetic sensing into portable sensing devices are introduced, which have received significant attention from the industry owing to their novel sensing approaches and portabilities. To address the limitations encountered by important signal and data units in biomimetic wearable sensing systems, two paths forward are identified and current challenges and opportunities are presented in this field. In summary, this review provides a further comprehensive understanding of the development of biomimetic wearable sensing devices from both breadth and depth perspectives, offering valuable guidance for future research and application expansion of these devices.

Novel Sandwich-Structured Flexible Composite Films with Enhanced Piezoelectric Performance.

Piezoelectric poly(vinylidene fluoride) (PVDF) and its copolymers have been widely investigated for applications in wearable electric devices and sensing systems, owing to their intrinsic piezoelectricity and superior flexibility. However, their weak piezoelectricity poses major challenges for practical applications. To overcome these challenges, we propose a two-step synthesis approach to fabricate sandwich-structured piezoelectric films (BaTiO3@PDA/PVDF/BaTiO3@PDA) with significantly enhanced ferroelectric and piezoelectric properties. As compared to pristine PVDF films or conventional 0-3 composite films, a maximum polarization (Pmax) of 11.24 µC/cm2, a remanent polarization (Pr) of 5.83 µC/cm2, and an enhanced piezoelectric coefficient (d33 ∼ 14.6 pC/N) were achieved. Simulation and experimental results have demonstrated that the sandwich structure enhances the ability of composite films to withstand higher poling electric fields in comparison with 0-3 composites. The sandwich-structured piezoelectric films are further integrated into a wireless sensor system with a high force sensitivity of 288 mV/N, demonstrating great potential for movement monitoring applications. This facile approach shows great promise for the large-scale production of composite films with remarkable flexibility, ferroelectricity, and piezoelectricity for wearable sensing devices.

A Privacy and Energy-Aware Federated Framework for Human Activity Recognition.

Human activity recognition (HAR) using wearable sensors enables continuous monitoring for healthcare applications. However, the conventional centralised training of deep learning models on sensor data poses challenges related to privacy, communication costs, and on-device efficiency. This paper proposes a federated learning framework integrating spiking neural networks (SNNs) with long short-term memory (LSTM) networks for energy-efficient and privacy-preserving HAR. The hybrid spiking-LSTM (S-LSTM) model synergistically combines the event-driven efficiency of SNNs and the sequence modelling capability of LSTMs. The model is trained using surrogate gradient learning and backpropagation through time, enabling fully supervised end-to-end learning. Extensive evaluations of two public datasets demonstrate that the proposed approach outperforms LSTM, CNN, and S-CNN models in accuracy and energy efficiency. For instance, the proposed S-LSTM achieved an accuracy of 97.36% and 89.69% for indoor and outdoor scenarios, respectively. Furthermore, the results also showed a significant improvement in energy efficiency of 32.30%, compared to simple LSTM. Additionally, we highlight the significance of personalisation in HAR, where fine-tuning with local data enhances model accuracy by up to 9% for individual users.

In Situ Spray Polymerization of Conductive Polymers for Personalized E-textiles.

E-textiles, also known as electronic textiles, seamlessly merge wearable technology with fabrics, offering comfort and unobtrusiveness and establishing a crucial role in health monitoring systems. In this field, the integration of custom sensor designs with conductive polymers into various fabric types, especially in large areas, has presented significant challenges. Here, we present an innovative additive patterning method that utilizes a dual-regime spray system, eliminating the need for masks and allowing for the programmable inscription of sensor arrays onto consumer textiles. Unlike traditional spray techniques, this approach enables in situ, on-the-fly polymerization of conductive polymers, enabling intricate designs with submillimeter resolution across fabric areas spanning several meters. Moreover, it addresses the nozzle clogging issues commonly encountered in such applications. The resulting e-textiles preserve essential fabric characteristics such as breathability, wearability, and washability while delivering exceptional sensing performance. A comprehensive investigation, combining experimental, computational, and theoretical approaches, was conducted to examine the critical factors influencing the operation of the dual-regime spraying system and its role in e-textile fabrication. These findings provide a flexible solution for producing e-textiles on consumer fabric items and hold significant implications for a diverse range of wearable sensing applications.

Prediction of Physical Activity Patterns in Older Patients Rehabilitating After Hip Fracture Surgery: Exploratory Study.

BACKGROUND: Building up physical activity is a highly important aspect in an older patient's rehabilitation process after hip fracture surgery. The patterns of physical activity during rehabilitation are associated with the duration of rehabilitation stay. Predicting physical activity patterns early in the rehabilitation phase can provide patients and health care professionals an early indication of the duration of rehabilitation stay as well as insight into the degree of patients' recovery for timely adaptive interventions. OBJECTIVE: This study aims to explore the early prediction of physical activity patterns in older patients rehabilitating after hip fracture surgery at a skilled nursing home. METHODS: The physical activity of patients aged ≥70 years with surgically treated hip fracture was continuously monitored using an accelerometer during rehabilitation at a skilled nursing home. Physical activity patterns were described in our previous study, and the 2 most common patterns were used in this study for pattern prediction: the upward linear pattern (n=15) and the S-shape pattern (n=23). Features from the intensity of physical activity were calculated for time windows with different window sizes of the first 5, 6, 7, and 8 days to assess the early rehabilitation moment in which the patterns could be predicted most accurately. Those features were statistical features, amplitude features, and morphological features. Furthermore, the Barthel Index, Fracture Mobility Score, Functional Ambulation Categories, and the Montreal Cognitive Assessment score were used as clinical features. With the correlation-based feature selection method, relevant features were selected that were highly correlated with the physical activity patterns and uncorrelated with other features. Multiple classifiers were used: decision trees, discriminant analysis, logistic regression, support vector machines, nearest neighbors, and ensemble classifiers. The performance of the prediction models was assessed by calculating precision, recall, and F1-score (accuracy measure) for each individual physical activity pattern. Furthermore, the overall performance of the prediction model was calculated by calculating the F1-score for all physical activity patterns together. RESULTS: The amplitude feature describing the overall intensity of physical activity on the first day of rehabilitation and the morphological features describing the shape of the patterns were selected as relevant features for all time windows. Relevant features extracted from the first 7 days with a cosine k-nearest neighbor model reached the highest overall prediction performance (micro F1-score=1) and a 100% correct classification of the 2 most common physical activity patterns. CONCLUSIONS: Continuous monitoring of the physical activity of older patients in the first week of hip fracture rehabilitation results in an early physical activity pattern prediction. In the future, continuous physical activity monitoring can offer the possibility to predict the duration of rehabilitation stay, assess the recovery progress during hip fracture rehabilitation, and benefit health care organizations, health care professionals, and patients themselves.

Longitudinal interactions between residual symptoms and physiological stress in the remitted symptom network structure of depression.

Residual symptoms and stress are amongst the most reliable predictors of relapse in remitted depression. Standard methodologies often preclude continuous stress sampling or the evaluation of complex symptom interactions. This limits knowledge acquisition relative to the day-to-day interactions between residual symptoms and stress. The study aims to explore the interactions between physiological stress and residual symptoms network structure in remitted depression. Twenty-two individuals remitted from depression completed baseline, daily diary (DD), and post-DD assessments. Self-reported stress and residual symptoms were measured at baseline and post-DD. Daily diaries required participants to use a wearable electrodermal activity (EDA) device during waking hours and complete residual symptom measures twice daily for 3-weeks. Two-step multilevel vector auto-regression models were used to estimate contemporaneous and dynamic networks. Depressed mood and concentration problems were central across networks. Skin conductance responses (SCRs), suicide, appetite, and sleep problems were central in the temporal and energy loss in the contemporaneous network. Increased SCRs predicted decreased energy loss. Residual symptoms and stress showed bi-directional interactions. Overall, depressed mood and concentration problems were consistently central, thus potentially important intervention targets. Non-obtrusive bio-signal measures should be used to provide the clinical evidence-base for modelling the interactions between depressive residual symptoms and stress. Practical implications are discussed throughout related to focusing on symptom-specific interactions in clinical practice, simultaneously reducing residual symptom and stress occurrences, EDA as pioneering signal for stress detection, and the central role of specific residual symptoms in remitted depression.

Human-centred artificial intelligence for mobile health sensing: challenges and opportunities.

Advances in wearable sensing and mobile computing have enabled the collection of health and well-being data outside of traditional laboratory and hospital settings, paving the way for a new era of mobile health. Meanwhile, artificial intelligence (AI) has made significant strides in various domains, demonstrating its potential to revolutionize healthcare. Devices can now diagnose diseases, predict heart irregularities and unlock the full potential of human cognition. However, the application of machine learning (ML) to mobile health sensing poses unique challenges due to noisy sensor measurements, high-dimensional data, sparse and irregular time series, heterogeneity in data, privacy concerns and resource constraints. Despite the recognition of the value of mobile sensing, leveraging these datasets has lagged behind other areas of ML. Furthermore, obtaining quality annotations and ground truth for such data is often expensive or impractical. While recent large-scale longitudinal studies have shown promise in leveraging wearable sensor data for health monitoring and prediction, they also introduce new challenges for data modelling. This paper explores the challenges and opportunities of human-centred AI for mobile health, focusing on key sensing modalities such as audio, location and activity tracking. We discuss the limitations of current approaches and propose potential solutions.