JMIR mHealth and uHealth

Wearable-derived physiological features have been associated with disease risk, but most current studies focus on single conditions, limiting understanding of cross-disease patterns. This study adopts a trans-diagnostic approach to examine whether wearable data capture shared and condition-specific physiological signatures across multiple chronic conditions spanning physical and mental health, and then evaluates the utility of these features for disease classification. A total of 9,301 patients with at least 21 days of consecutive FitBit data from the All of Us Controlled Tier Dataset version 8 were analyzed. Disease subcohorts included cardiovascular disease (CVD), diabetes, obstructive sleep apnea (OSA), major depressive disorder (MDD), anxiety, bipolar disorder, and attention-deficit/ hyperactivity disorder (ADHD), chosen based on prevalence and relevance. Logistic regression and XGBoost models were fitted for each disease subcohort versus the control cohort. We found that compared to using just baseline demographic and lifestyle features, incorporating wearable-derived features enabled improved classification performance in all subcohorts for both models, except for ADHD where improvement was mainly observed for ROC-AUC in logistic regression model likely due to the smaller sample size in ADHD subcohort. The largest performance gains were observed in MDD (increase in ROC-AUC of 0.077 for Logistic regression, 0.071 for XGBoost; p < 0.001) and anxiety (increase in ROC-AUC of 0.077 for logistic regression, 0.108 for XGBoost; p < 0.001). This study provides one of the first comprehensive transdiagnostic evaluations of wearable-derived features for disease classification, highlighting their potential to enhance risk stratification in the real-world setting as a practical complement to clinical assessments and providing a foundation to explore more fine-grained wearable data. Author summaryWearable devices such as fitness trackers and smartwatches are becoming increasingly popular and affordable, providing continuous measurements of heart rate, physical activity, and sleep. Alongside the growing digitization of health records, this creates new opportunities for large-scale, real-world health studies. In this study, we analyzed wearable-derived physiological patterns across a range of chronic conditions spanning both physical and mental health to better understand how these signals relate to disease risk. We found that incorporating wearable-derived heart rate, activity and sleep features improved disease risk classification across several conditions, with particularly strong gains for major depressive disorder and anxiety. By examining how individual features contributed to model predictions, we also identified meaningful associations between physiological signals and disease risk. For example, both duration and day-to-day variation of deep and rapid eye movement (REM) sleep were associated with increased risk in certain conditions. Our study supports the development of real-time, automated tools to assess disease risk alongside clinical care.

Study objectives Consumer sleep technologies (CSTs) enable low-burden longitudinal sleep monitoring, and their output measures are often interpreted as equivalent to polysomnography (PSG) measures. We applied a measurement reliability-aware approach to determine whether CST-derived 'sleep' measures (1) are interchangeable or device-specific, (2) can reliably assess trait-like sleep characteristics of an individual, (3) can be reduced to latent principal components of sleep, and (4) can be used for classification and biomarker discovery. Methods Data from 74 older adults (20 people living with dementia [PLWD]) were collected at-home (upto 14 nights; Total=752nights) using four tools simultaneously: research-grade actigraphy (Axivity), a wearable (Withings Watch), a nearable (Withings Sleep Analyzer) and Sleep Diary, followed by one in-lab PSG assessment. We used repeated-measures correlation analyses, intraclass correlation coefficients (ICC), principal component analysis (PCA) and binary classification models to address our objectives. Results Single-night between-device correlations and correlations with PSG were moderate (0.3[&le;]r<0.7) for some duration- and timing-related measures, but other associations were weak (r<0.3). Seventy-one percent of sleep measures reached acceptable reliability (ICC[&ge;]0.7) within seven nights of aggregation, but the required aggregation window varied across measures, tools and between PLWD and Controls. Reliability-filtered PCA yielded stable and interpretable principal components, but Duration was the only component showing moderate between-device association. Principal components were successfully used to classify PLWD vs Controls but feature importance varied across devices. Conclusions Aggregation of CST derived measures across 7-14 nights, yielded reliable measures, most of which were device-specific, with duration being the only essential aspect transferable between devices.

Cardiovascular age is a powerful risk-communication tool that translates complex physiological data into an intuitive number, yet traditional estimates require clinical testing. Consumer wearables now estimate cardiorespiratory fitness age from photoplethysmography-derived heart rate data, enabling continuous, passive health monitoring, but whether such estimates capture substantive lifestyle variation has not been examined. We characterized Cardio Age, a wearable-derived cardiorespiratory fitness age estimate, in 442 Ultrahuman Ring users across a 12-month window ending February 2026, separating independent lifestyle correlates from direct or indirect algorithmic inputs. The mean Cardio Age gap (CA gap; mean Cardio Age minus chronological age) was -1.84{+/-}2.97 years, with 82.6% of participants exhibiting younger estimated cardiovascular ages. Independent lifestyle metrics with no algorithmic link to Cardio Age showed significant associations: sleep efficiency (r = -0.194, p < 0.001), rapid eye movement (REM) sleep (r = -0.203, p < 0.001), sleep duration (r = -0.200, p < 0.001), and daily steps (r = -0.145, p = 0.003). A monotonic body mass index (BMI) dose-response was observed, with underweight participants showing a mean CA gap of -3.73 years versus -0.52 for obese participants. Extreme-group comparisons revealed that users with the youngest cardiovascular ages slept 37 minutes longer, achieved 22 more minutes of REM sleep, and had 1.8% higher sleep efficiency than those with the oldest cardiovascular ages (all p < 0.05). Sustained improvers over 12 months showed a mean CA reduction of 3.24 years, accompanied by decreased resting heart rate (-0.8 bpm, p < 0.001) and increased estimated VO2 max (+1.3 mL/kg/min, p < 0.001), indicating that Cardio Age tracks physiological changes over time.

Background: Digital phenotyping using wearable devices and ecological momentary assessment (EMA) enables continuous, real-world monitoring of physiological and emotional states, but identifying high-risk stress states in real time remains challenging. We examined day-level associations between emotional distress and heart rate variability (HRV), and assessed whether daily physical activity modifies this relationship using longitudinal wearable and EMA data. Methods: The Smart Momentary Interactive Longitudinal Evaluation Study (SMILES) was a prospective cohort study conducted among STEM graduate students in the U.S. in 2025. Participants wore an Oura Ring Generation 3 continuously for five months and completed daily EMA surveys assessing emotional distress. The primary outcome was nightly HRV measured as the root mean square of successive differences and log-transformed for analysis. Quantile regression within a quadratic inference function framework was used to estimate associations at the 25th, 50th, and 75th percentiles of HRV, accounting for within-participant correlation and time-varying covariates. Findings: Thirty-one participants contributed 1,724 person-days of observation. High emotional distress was associated with lower HRV across the HRV distribution, with the strongest association observed at the lower HRV quantile ({beta} = -0.094, 95\% CI: [-0.111, -0.078]). A significant interaction between daily step count and emotional distress was observed across quantiles, such that higher physical activity was associated with higher HRV on high emotional distress days but not on low-to-moderate distress days. Interpretation: Integration of wearable-derived physiological data with EMA enables real-time identification of high-risk stress states in naturalistic settings. The observed buffering effect of physical activity during periods of elevated emotional distress suggests that wearable-guided, personalized just-in-time adaptive interventions, such as physical activity prompts, could be deployed to improve autonomic regulation and mental health.

Actigraphy is a non-invasive and cost-effective method for monitoring behavioral rhythms under real-world conditions by collecting time-resolved measurements of locomotor activity, light exposure, and temperature. Although several open-source packages support specific aspects of actigraphy analysis, aspects such as preprocessing, metric calculation, and mathematical modeling are often distributed across separate software packages, limiting interoperability and increasing programming overhead. Here we introduce circStudio, a Python package that unifies actigraphy data processing and mathematical modeling of circadian rhythms within a single framework. Built from the pyActigraphy codebase and integrating circadian models from the Arcascope circadian package, circStudio provides flexible preprocessing tools, support for multiple actigraphy file formats through adaptor classes, standalone functions for computing commonly used actigraphy metrics, and implementations of several mathematical models of circadian rhythms. The package enables users to move efficiently from raw wearable data to physiologically interpretable circadian outputs. Ultimately, circStudio aims to facilitate reproducible workflows and to provide a flexible foundation for research applications across circadian biology, sleep science, and digital health.

Study ObjectivesTo evaluate wearable sleep staging across sleep apnea severity, including very severe sleep apnea defined as an apnea-hypopnea index (AHI)[&ge;] 50 events/h, and to assess how training-set composition affects performance in this subgroup. MethodsWe analyzed 552 overnight recordings, 318 from the Sleep Lab Dataset and 234 from the Hospital Dataset. In the Hospital Dataset, 26.5% had very severe sleep apnea. We developed a deep learning model for sleep staging using RR intervals from wrist-worn photoplethysmography and three-axis accelerometry. Baseline performance was assessed by cross-validation under 5-stage and 4-stage staging. We examined night-level associations with AHI severity. We also compared the baseline model with an ablation model trained on the same number of recordings but with more Sleep Lab Dataset and lower-AHI Hospital Dataset recordings, evaluating both models in the very severe subgroup. ResultsIn 5-stage classification, Cohens kappa was 0.586 in the Sleep Lab Dataset and 0.446 in the Hospital Dataset. Under 4-stage staging, the gap narrowed, with kappa values of 0.632 and 0.525, respectively. In the Hospital Dataset, performance declined with increasing AHI severity. Among 62 recordings with very severe sleep apnea, reducing high-AHI representation in training lowered kappa from 0.365 to 0.303. ConclusionsWearable sleep staging performance declined across greater sleep apnea severity in this clinical cohort. Clinical utility may benefit from training data that better represent the target severity spectrum and from selecting staging granularity to match the intended use case. Statement of SignificanceRepeated laboratory polysomnography is impractical for long-term sleep apnea management. Wearable sleep staging could support scalable monitoring, yet its reliability in clinically severe sleep apnea has remained unclear. This study developed and evaluated a wearable sleep staging approach in both sleep-laboratory and hospital cohorts. The hospital cohort included many severe and very severe cases. Performance was lower in the hospital cohort and declined with greater sleep apnea severity. A coarser staging scheme reduced the gap between cohorts, and models trained without representative very severe cases performed worse in this target population. These findings highlight the value of severity-aware model development and motivate future multi-night home validation with reliability cues.

Time compositions of physical behaviours are associated with premature mortality, but the moderating role of sleep remains unclear. Using data from the UK Biobank accelerometry subsample, we examined associations of time reallocations between five device-measured physical behaviours (sleep, sedentary behaviour (SB), standing, light-intensity (LPA) and moderate-to-vigorous physical activity (MVPA)) with all-cause, cardiovascular disease (CVD) and physical activity-related cancer mortality, and the potential effect modification by sleep duration and regularity. Compositional Cox regression was used to examine associations of behavioural reallocations with mortality. In 58,149 adults, 2,209 deaths occurred over a mean follow-up of 8.0 years. Among participants who meet sleep duration guidelines, reallocating 30 minutes from sleep to standing, LPA or MVPA was favourably associated with all-cause mortality with HRs of 0.86 (95%CI 0.79, 0.93), 0.87 (0.80, 0.95), and 0.80 (0.73, 0.87), respectively. Reallocating 30 minutes from sleep to SB, standing, or LPA was adversely associated with CVD risk (HRs 1.08 (1.02, 1.15), 1.10 (1.01, 1.20), and 1.11 (1.03, 1.20)) among those not meeting guidelines. Beneficial associations of reallocating SB to sleep were evident only amongst short (<7h/day) or regular (SRI>87.8) sleepers across mortality outcomes. Our findings support incorporating sleep characteristics into future personalised behavioural interventions design and behavioural targets.

ObjectiveLong term monitoring of obstructive sleep apnea (OSA) severity may be relevant for several clinical applications. We developed a method for estimating the apnea-hypopnea index (AHI) using wrist-worn, reflective photoplethysmography (PPG). ApproachA neural network was developed to detect respiratory events using PPG and PPG-derived sleep stages as input. The development database encompassed retrospective data from three polysomnographic datasets (N=3111), including a dataset with concurrent reflective PPG recordings from a wrist-worn device (N=969). The model was pre-trained with (transmissive) finger-PPG signals from all overnight recordings and then fine-tuned to wrist-PPG characteristics using transfer learning. Validation was performed on the test portion of the development set and on a fourth, external hold-out dataset containing both wrist-PPG and PSG data (N=171). Performance was evaluated in terms of AHI estimation accuracy and OSA severity classification. Main ResultsThe fine-tuned wrist-PPG model demonstrated strong agreement with the PSG-derived gold-standard AHI, achieving intra-class correlation coefficients of 0.87 in the test portion of the development set and 0.91 in the external hold-out validation set. Diagnostic performance was high, with accuracies above 80% for all severity thresholds. SignificanceThe study highlights the potential of reflective PPG-based AHI estimation, achieving high estimation performance in comparison with PSG. These measurements can be performed with relatively comfortable sensors integrated in convenient wrist-worn wearables, enabling long-term assessment of sleep disordered breathing, both in a diagnostic phase, and during therapy follow-up.

Abstract Background: Insufficient physical activity, excessive sedentary time, and suboptimal sleep are linked to premature mortality and chronic disease and may contribute to social inequalities in health, but most evidence is self-reported. Device-measured, nationally representative data capturing the full 24-hour movement spectrum remain scarce, particularly among older adults. This study examined social, economic, and environmental disparities in 24-hour movement behaviours in the 2021-23 English Longitudinal Study of Ageing (ELSA) accelerometry sub-study. Methods: A subset of 5,382 ELSA participants (71.9%) was invited to wear an Axivity AX3 wrist accelerometer for eight days, with 4,354 (80.9%) agreeing. Raw data were processed using machine learning to derive step count, sleep duration, moderate-to-vigorous and light physical activity, sedentary time, and time in bed. Cross-sectional associations with sex, age, education, marital status, wealth, and urbanicity were examined using linear regression. Findings: Data from 3,648 participants (mean age 68.5 {+/-} 9.3 years; 44.3% men) were included in wear time analyses (median 6.6 days, IQR 6.0-6.9), with 3,161 (86.7%) having sufficient wear time for movement behaviour analyses. Older, unmarried, or lower education/wealth participants were less active, more sedentary, and slept less. Rural participants were more active than urban participants. Women accumulated fewer steps and less moderate-to-vigorous physical activity and sedentary time, but more light activity and longer sleep than men. Interpretation: Social, economic, and environmental disparities exist across the full 24-hour movement spectrum, highlighting population groups for targeted interventions. Follow-up data will clarify how 24-hour movement behaviours influence healthy ageing and contribute to social inequalities in health.

Background: Alcohol misuse is common in the UK Armed Forces (AF) community, with prevalence higher than in the general population. To date, digital health initiatives to address alcohol misuse have largely focused on men, who represent around 88% of the UK AF. However, women who have served in the UK AF also drink disproportionately more than women in the general population. Objective: This two-arm participant-blinded (single-blinded) confirmatory randomized controlled trial (RCT) aimed to assess the efficacy of a brief alcohol intervention (DrinksRation) compared to a web application which included NHS-focused drinking advice (BeAlcoholSmart) in reducing weekly self-reported alcohol consumption between baseline and 84-day follow-up among women who have served in the UK AF. Methods: A smartphone app (DrinksRation) was compared with government guidance on alcohol use. The app included features tailored to the needs of women who have served and was designed to enhance motivation to reduce alcohol consumption. The trial enrolled women who had completed at least one day of paid service in the UK Armed Forces. Recruitment, consent, and data collection were completed automatically through the platform. The primary outcome was the between-group difference in change in self-reported weekly alcohol consumption from baseline to day 84, measured using the Timeline Follow-Back method. The secondary outcome was the between-group difference in change in Alcohol Use Disorders Identification Test (AUDIT) score from baseline to day 84. Process evaluation outcomes included app engagement and usability, with usability assessed using the mHealth App Usability Questionnaire. Results: A total of 88 women UK AF veterans were included in the final analysis (control=37; intervention=51). At 84 days post-baseline, participants in the intervention group (DrinksRation) showed a greater reduction in weekly alcohol consumption compared to controls (BeAlcoholSmart) (adjusted mean difference in change from baseline = -11.6 units; 95% CI: -19.7 to -3.6; p=0.005). AUDIT scores decreased more in the intervention group (adjusted mean difference in change = -3.9; 95% CI: -6.9 to -1.0; p=0.01). Usability scores at day 28 were significantly higher for the intervention group across all domains. No serious adverse events or technical issues were reported. Conclusions: DrinksRation reduced alcohol consumption and hazardous drinking among women who have served in the UK Armed Forces. Engagement was strong, usability was high, and no safety concerns were identified. These findings support the potential of tailored digital interventions to address alcohol misuse in women who have served in the UK Armed Forces. Registration: ClinicalTrials.gov (trial registration: NCT05970484).

Loneliness--the perceived discrepancy between desired and actual social connection--is a common and aversive psychological state associated with a range of adverse health outcomes. Several theoretical models suggest that these associations may operate partly through health behaviors. In this preregistered study, we used data from the All of Us Research Program to evaluate associations of loneliness and functional rurality (FR), a study-specific contextual index of reduced neighborhood accessibility, with Fitbit-derived physical activity and sleep outcomes. Final samples included 16,912 participants for physical activity analyses and 13,937 for sleep analyses. In adjusted models, higher FR was associated with greater loneliness ({beta} = 0.061, 95% CI [0.045, 0.077], p = 9.63 x 10-14). FR and loneliness were independently associated with fewer daily steps and lower moderate-to-vigorous physical activity. Loneliness was also associated with shorter sleep duration, greater sleep duration variability, higher odds of short sleep, and higher odds of low sleep efficiency. FR was not associated with sleep duration or sleep duration variability but showed a small positive association with mean sleep efficiency and lower odds of low sleep efficiency. Interaction analyses provided little evidence that FR modified the associations of loneliness with most outcomes, although the FR x loneliness interaction was significant for sleep duration variability, indicating that loneliness was more strongly associated with irregular sleep duration in higher-FR contexts. Sensitivity analyses using stricter valid-day thresholds, winsorization, quartile-based exposure coding, and a backward 30-day window yielded directionally similar findings. These results suggest that FR and loneliness are independently associated with lower physical activity, whereas loneliness shows a more consistent relationship with adverse sleep patterns.

In this article, we present the cgmstats package for the analysis of continuous glucose monitoring (CGM) data. The use of wearable CGMs is growing rapidly. The latest generation of CGM systems do not require fingerstick calibration, are minimally invasive, and are frequently used in research studies. CGM sensors are typically worn for up to 2 weeks and record interstitial glucose measurements every minute to every 15 minutes, depending on the sensor used. CGM systems generate hundreds of measurements per day and thousands of measurements in one person over a single wear. There is a need for tools that allow researchers to efficiently organize and summarize the wealth of data on glucose patterns produced by CGM systems. The cgmstats package generates CGM summary measures for data from a variety of CGM systems and allows the user to flexibly define ranges and generate data visualizations. In this article, we provide an overview of the cgmstats package and examples of its use. The cgmstats package supports rigorous and reproducible analyses of CGM data.

Objectives: Heart failure is a leading cause of mortality, necessitating identification of patients at increased risk needing intervention. In this study, we investigated if Fitbit data can reveal physiological trends associated with hospital visit risk. Materials and methods: Individuals with heart failure (n=249) were randomized into three arms for prospective 180-day monitoring. All arms received a Fitbit and wireless weight scale. Arm 1 received devices only; Arm 2 received a mobile app with surveys; Arm 3 received the app plus financial incentives. Results: 51 participants had hospital visits during the study period. These individuals took fewer steps (p=.002) and reported increased symptom severity (p=.044). Resting heart rate increased three days prior to a visit (p=.022). Baseline steps revealed a higher visit probability for less active participants (p=.003). Discussion and conclusion: Passive physiological monitoring can effectively identify individuals at risk of health exacerbation, demonstrating the potential of wearable devices for timely clinical intervention.

BackgroundMixed-format lifestyle questionnaires contain both structured variables and free-text responses, but it remains unclear whether language-derived variables provide incremental predictive value beyond structured data, and under which representational condition. It was investigated whether variables derived from patient-reported free text improve ALS-versus-control classification beyond structured questionnaire data, and whether their value depends on how temporal information is represented. MethodsA leakage-free machine-learning pipeline was developed to classify ALS versus controls from questionnaire-derived data, including a schema-guided LLM-based text-to-table extraction and a compact longitudinal encoding strategy. Three feature configurations were compared: Pool1, containing structured baseline variables only; Pool2, adding compact summaries derived from first-time-point (T1) free-text responses; and Pool3, further incorporating compact descriptors of change between T1 and T2. Logistic Regression, linear Support Vector Classification, and Random Forest were evaluated using repeated stratified holdout (10 seeds) and repeated stratified 5-fold cross-validation. Final ablation analyses were performed to isolate the contribution of the compact text block and the compact temporal block. ResultsAfter leakage correction, performance estimates became more conservative, indicating that previous results had been optimistic. In the final configuration, Pool3 achieved the best performance, with Random Forest reaching a holdout accuracy of 0.673, F1-weighted score of 0.666, and Matthews correlation coefficient of 0.323; cross-validated F1-weighted score and Matthews correlation coefficient were 0.654 and 0.312, respectively. Pool2 did not show a robust improvement over Pool1. Ablation analysis showed that removing the compact temporal block markedly reduced Pool3 performance, whereas removing the compact text block had little overall effect. These findings indicate that the primary value of language-based processing in small clinical cohorts lies not in static feature enrichment, but in enabling compact representations of longitudinal change. ConclusionsIn this setting, the main predictive gain did not arise from static text-derived variables alone, but from representing questionnaire information as compact longitudinal change descriptors. These findings suggest that, in small clinical cohorts, the value of language-based processing may lie more in summarizing trajectories than in expanding static feature spaces.

BackgroundThe mechanisms underpinning associations between sleep and psychiatric conditions are poorly understood, partly due to challenges with longitudinal sleep studies outside the laboratory. Children and young people with rare genetic conditions caused by micro-deletions or -duplications (Copy Number Variants or CNVs) have increased risk of disrupted sleep and poorer neurodevelopmental (ND) outcomes. The Sleep Detectives study aims to investigate this by tracking behavioural and neurophysiological signatures of sleep health in young people with ND risk or ND-CNVs. To optimally achieve this, we have worked with families with ND-CNVs and charity partners to co-design our tools, methods, study protocol, and materials. MethodWe established a Lived Experience Advisory Group (LEAP) with nine parents and 13 children and young people with ND-CNVs, alongside representatives of UK charities Max Appeal and Unique. Together, the research team and LEAP co-designed two in-person family workshops in which we collected feedback on the acceptability of sleep monitoring devices, the design of bespoke cognitive tasks, and overall study protocol. Informal interviews and surveys were conducted with LEAP members and researchers, to enable the team to reflect and learn from their Patient/Public Involvement (PPI) experiences. ResultsKey outputs included pre-workshop invitation and briefing materials and insights that iteratively refined the main study design, including the need for flexibility to increase accessibility, selection of sleep devices, customisation of cognitive tasks, and choice of language in documents. The PPI process was highly valued by LEAP members, workshop attendees, and the research team. One investigator described the PPI work as "reinvigorating my love of research by helping me focus on science that matters". Participating families also established peer support networks. ConclusionsInvolving families affected by ND-CNVs in co-designing the Sleep Detectives study maximised opportunities for acceptability, accessibility and scalability. The research team gained inspiration and deeper understanding of the impact of ND-CNVs on families. Families gained awareness about research, established connections with each other and peer support, and were enthusiastic about future research involvement. This experience empowered families to engage more deeply with the research process and helped the PPI work to be more impactful and inclusive. Plain English summaryChildren and young people with rare genetic conditions caused by small deletion or duplication of genetic material are more likely to experience sleep difficulties such as insomnia, restless sleep, and tiredness. They also show an increased likelihood of neurodevelopmental conditions such as learning disability and autism, and mental health issues such as anxiety. The Sleep Detectives team wanted to explore how these genetic conditions affect childrens sleep, cognition and psychiatric health. To make sure that the project design was well suited to the children and young people that would be invited to participate, the team worked closely with families to design the study. Parents and caregivers of affected children and young people were invited to join a Lived Experience Advisory Panel (LEAP), together with charity representatives and Sleep Detective researchers, to co-design two hands-on workshops, and advise on study design. Children and young people and parents/caregivers attending the workshops tried out and provided feedback on tools and devices that the research team were developing. They also advised on the arrangements and support families might need whilst taking part, and on the study protocol. This collaborative approach helped ensure the study design was optimally suited for the recruitment and participation of children and young people and their families. This report documents our public involvement work for the Sleep Detectives study, illustrating the difference the partnership between researchers and families has made to the project, and the wider benefits for all concerned.

Background: LLMs enable patient-facing conversational agents, creating a pathway toward digital twins that capture older adults' lived experiences and behavioral responses across time. A central barrier is personality drift---inconsistent trait expression across repeated interactions---which undermines reliability of generated trajectories and intervention-response simulation in geriatric care. Objective: To develop ELDER-SIM, a multi-role elderly-care conversational platform for building personality-stable digital twin agents, and to propose a psychometric validation framework for quantifying personality consistency in LLM-based agents. Methods: ELDER-SIM was implemented via n8n workflow orchestration with local LLM inference (Ollama/vLLM), integrating (1) Big Five (OCEAN) trait specifications, (2) a Cognitive Conceptualization Diagram (CCD) grounded in Beck's CBT framework, and (3) a MySQL-based long-term memory module. Ablation studies across four conditions---Baseline, +Memory, +CCD, and +LoRA (fine-tuned on 19,717 instruction pairs from CHARLS)---were evaluated via Cronbach's $\alpha$, ICC, and role discrimination accuracy. Results: Personality measurement reliability was acceptable to excellent across conditions (Cronbach's : 0.70-0.94), with consistently high test-retest stability (ICC: 0.85- 2 0.96). Role discrimination improved stepwise from 83.3% (Baseline) to 88.9% (+Memory), 94.4% (+CCD), and 97.2% (+LoRA). CCD produced the largest gain in internal consistency (mean 0.702[-&gt;]0.892), while LoRA achieved the highest overall internal consistency ( 0.940) and ICC (0.958). Conclusions: ELDER-SIM provides a psychometrically validated approach for constructing personality-consistent elderly digital twin agents. Structured cognitive modeling and domain adaptation reduce personality drift, supporting reliable longitudinal simulation for elderly mental health care and reproducible in silico evaluation before clinical deployment.

BackgroundCardiovascular disease (CVD) prevention is limited by the major challenge of low long-term adherence to effective lifestyle regimens. Arterial stiffness (measured by carotid-femoral pulse wave velocity, cfPWV) and maximal cardiorespiratory fitness (measured by VO2max), are modifiable risk factors for CVD but require sustained lifestyle change. Wearable technology provides continuous measurement and offers a scalable platform to deliver health interventions. A combination of continuous monitoring with a wearable device and an artificial intelligence (AI) -based coach personalized for individual data and preferences could be a powerful, low-barrier tool for achieving sustainable cardiovascular health benefits by directly addressing the adherence challenge. ObjectiveWe will study the comparative effectiveness of a wearable and an interactive app-based AI coaching intervention promoting moderate exercise on improving gold-standard cfPWV and VO2max. This will be compared to a supervised high-intensity interval training (HIIT) group (benchmark with known benefits for VO2max) and a control group using only Oura Ring (passive monitoring). We will also conduct a detailed Process Evaluation (structured interviews) to study the feasibility and experience of interacting with the AI coach. MethodsThis randomized controlled trial recruited 165 eligible sedentary participants aged 30-65 years. Co-primary outcomes cfPWV and VO2max were measured at baseline and will be repeated after 12 weeks. Participants were equally randomized into three groups: an AI-based coaching group (steady-state exercise), a HIIT group (supervised exercise) and a control group (usual low activity). The AI-based coaching group receives personalized guidance using large language model (LLM) technology. All participants wear Oura Ring and are blinded to cardiovascular health metrics provided by the ring. ResultsThe recruitment for the study began in October 2024 and will end when 165 men and women have been recruited. Data collection for the study is scheduled to conclude early 2026. Data collection is ongoing. ConclusionsThis study will evaluate if a highly scalable, AI-based coaching intervention can achieve comparable gains in CV structural health (cfPWV) and functional capacity VO2max relative to a resource-intensive supervised HIIT benchmark. The findings will provide essential evidence on the use of digital health tools to promote sustainable exercise adherence. ClinicalTrials.gov registration identifierNCT06644014 (Registered: 2024-10-15)

Background: Continuous adhesive patch electrocardiographic (ECG) wearables are increasingly prescribed. Patient experience with these devices can influence adherence, but research in this area is limited. This study aimed to explore the perceptions and experiences of patients receiving wearable cardiac monitoring technology as part of their routine care through the lens of treatment burden. Methods: This was a qualitative study with semi-structured phone interviews conducted between February and May 2024. We recruited participants from primary care and outpatient clinics using maximum variation sampling to ensure diversity in sex, ethnicity, and education levels. Interviews were audio-recorded, transcribed, and analysed using reflexive thematic analysis. Results: Sixteen participants (mean age 51 years, 63% female) were interviewed (average duration: 33 minutes). Three themes were developed: 1) ?Experience using the device: Burden vs Ease of Use?, which captured participants? perceptions of how easily they could integrate the device in their daily lives; 2) ?Individual variability in responses to ECG self-monitoring? covered participants? emotional and cognitive response to knowing their heart rhythm was monitored; and 3) ?The care process shapes patient experiences? reflected support preferences during the set-up and monitoring period and the uncertainty regarding timely clinical and device feedback. Conclusions: Patients valued cardiac wearables for facilitating diagnosis and felt reassured knowing they were clinically monitored. However, gaps in information provided to patients seemed to cause anxiety for some participants. These concerns could be mitigated through clearer clinician communication and patient education at the time of prescription.

Scientists have for decades attempted to automate the manual sleep staging problem not only for human polysomnography data but also for rodent data. No model has, however, succeeded in fully replacing the manual procedure across clinics and laboratories. We hypothesize that this is due to the models limited ability to generalize to data from unseen laboratories. Our findings show that despite the high performance of four state-of-the-art models reported in initial publications, the published models struggle to generalize to other laboratories. We further show a significant improvement in model performance across labs by re-training them on a diverse dataset from five different sites. To assess the contribution of variability in manual scoring, ten experts from five laboratories all labelled the same nine mouse sleep recordings. The result revealed substantial scoring variability, particularly for rapid eye movement (REM) sleep, both within and between labs. In conclusion our study demonstrates that key challenges in the generalizability of state-of-the-art sleep scoring models are signal variability and label noise. Our study highlights the need for a standardized set of mouse sleep scoring guidelines to enable consistency and collaboration across the field. Until such a consensus is reached, we present four sufficiently robust models trained on diverse datasets that can serve as standardized tools across labs.

Background/Objective: Common measures of physical activity (PA) based on duration and intensity do not fully capture its complexity. Adding additional PA components of muscle strength, mechanical strain, and turning actions, can provide a more complete view of activity behavior. Furthermore, PA behaviors differ between men and women. Therefore, the goal of this study is to identify and cluster similar long-term PA patterns over time for each PA component, examined separately for men and women. Methods: We used data from 4963 participants (52% women; mean age 66 years, SD = 8.6) of the Longitudinal Aging Study Amsterdam (1992 to 2019). PA component scores were assigned to self-reported activities, and Sequence Analysis with Optimal Matching was used to identify and cluster similar activity patterns over a period of 10 years, separately for each component and stratified by sex. Results: PA components varied by sex and displayed a unique mix of trajectories, including predominately low, medium, or high activity, increasing or decreasing patterns, and trajectories characterized by early or late mortality. Importantly, trajectories remained independent, indicating that changes in one PA component were not linked to changes in others. Conclusion: Older men and women follow distinct and independent long term PA trajectories across components, underscoring that PA behaviour cannot be described by a single dimension. Significance/Implications: The observed independence and heterogeneity of trajectories suggest that muscle strength, mechanical strain, and turning actions capture meaningful and distinct aspects of PA that are not reflected by traditional measures alone. Future PA-strategies could incorporate these dimensions and acknowledge sex-specific patterns to better reflect natural movement. The independence of components suggests that future interventions should target multiple dimensions, as changes in one component may not translate to others. Such an approach may support more tailored and sustainable PA interventions in later life.