Background: Measurement of life space characterizes people’s engagement with their environment. Several studies have used GPS devices to capture life space. A challenge with device-based measures is that participants may forget to bring the device with them. Life-space measures that leverage the GPS data from participants’ mobile phones may address this challenge, but few studies have leveraged this approach to date. Objective: Our objective was to assess the #feasibility of implementing a mobile phone life-space assessment and characterize life space using Google Street View (GSV) imagery. We then aimed to evaluate the association of demographic data with life-space size and environmental features. Methods: We developed a mobile phone app to passively capture life space in older adults and sampled GSV images from participants’ life space to characterize the environments where they spent their time. For this cross-sectional study, we recruited 82 participants (n=34, 41.5% men) aged 65 years and older (mean 74.5, SD 6.5 years) in 2023 to 2024 from the REGARDS (Reasons for Geographic and Racial Differences in Stroke) study. They were followed for 2 weeks and invited to complete nightly questionnaires on their phones. We measured features of the built environment that captured walkability (sidewalks, benches, and streetlights), neighborhoods (houses), and green space based on an image segmentation algorithm. Differences in life-space size and environmental features across participant characteristics were tested using the Wilcoxon rank sum test. Results: Among 82 participants, 76 (92.7%) completed all 14 days of data collection. Median daily maximum distance from home was 6.6 (IQR 1.3-15.5) km. Median distance traveled over 2 weeks was 477.1 (IQR 234.4-817.13) km. Adults younger than 70 years, women, Black participants, and those with income more than US $75,000 per year had larger life space than those aged 70 years and older, men, White participants, and those with income less than US $75,000 (154.5 vs 58.1 km, =.04; 102.9 vs 46.0 km, =.07; 179.3 vs 62.8 km, =.03; and 145.5 vs 25.5 km, =.001, respectively), although not all of these comparisons met the α=.05 level of statistical significance based on the Wilcoxon rank sum test. We found no association between demographic characteristics and features of the life-space built environment (>.05 for all comparisons). Conclusions: In this #feasibility study, we demonstrated that personal mobile phones could be used to passively track older adults’ life space based on a digital health app developed on an open-source platform. There was wide variation in objectively measured life space, and we found sociodemographic patterning of life-space movement. Objective measurement of life space with participants’ mobile phones is feasible and should be evaluated in larger samples to better capture the relationship between health and time spent in different environments. Integration of a life-space assessment into older adults’ daily lives may allow for the use of life space as a health measure.

Background: Early mortality after long-term care facility (LTCF) admission is common; yet, prognostic tools are often derived from Western minimum dataset-based cohorts or require hospital electronic health record linkages that are unavailable at intake in many LTCFs. There is also limited evidence on explainable, admission-feasible machine learning–based prognostication in Asian LTCF settings. Objective: The aim of the study is to develop and temporally externally validate an interpretable machine learning model for predicting 6-month all-cause mortality among older adults newly admitted to LTCFs in Taiwan using routinely collected LTCF assessment data. Methods: We conducted a retrospective cohort study using the JUBO Long-Term Care Database, a nationwide private administrative registry covering 636 LTCFs (37.4% of the national LTCFs) in Taiwan. We included residents with first-time LTCF admission and prespecified nonoverlapping cohorts for temporal validation: development (January 1, 2020, to December 31, 2023; n=23,901) and external validation (January 1 to December 31, 2024; n=6216). The outcome measure was death within 180 days of admission. We compared a nonlinear ensemble model (hybrid of extreme gradient boosting and random forest [HybridXGBRF]) with 7 other algorithms, including tree-based and linear benchmarks. Discrimination (area under the receiver operating characteristic curve [AUROC]), classification metrics (accuracy, precision, recall, and ), and calibration (Brier score and calibration plots) were assessed. Model interpretability was examined using Shapley Additive Explanations. Results: In the development cohort, 5272 of 23,901 (22.1%) residents died within 180 days. In the 2024 temporal validation cohort, 1781 of 6216 (28.7%) residents died. In internal cross-validation, HybridXGBRF had the highest AUROC among the evaluated models (0.89, 95% CI 0.88‐0.89). In temporal validation, HybridXGBRF maintained strong discrimination (AUROC 0.90, 95% CI 0.89‐0.91), with an accuracy of 0.85 and an -score of 0.68. Calibration plots indicated close agreement between predicted and observed risks across most probability ranges, with mild divergences at higher predicted risks. Shapley Additive Explanations analysis identified frequent hospitalizations within 6 months, activities of daily living impairment, and weight loss as influential predictors. The model showed stable AUROC across sex and age strata (0.89‐0.90) and maintained high discrimination among residents with improving activities of daily living scores (AUROC 0.91, 95% CI 0.90‐0.92). Conclusions: An interpretable machine learning model using routinely collected Taiwanese LTCF assessment data achieved strong discrimination, acceptable calibration, and stable temporal validation performance without requiring hospital-based electronic health record linkage. The HybridXGBRF had the highest AUROC among the evaluated models, but performance differences from extreme gradient boosting were small. The model may serve as a risk-stratification tool to help identify residents who could benefit from structured care review, advance care planning, or palliative care assessment. Prospective implementation studies could determine its impact on care processes and resident- or family-centered outcomes.

Can self-adhering composites (SACs) match conventional composites (CCs) in dentistry? Research suggests SACs perform similarly but show higher microleakage. More studies needed! #Dentistry #ResearchSt...

Can self-adhering composites (SACs) match conventional composites (CCs) in dentistry? Research suggests SACs perform similarly but show higher microleakage. More studies needed! #Dentistry #ResearchSt...

This research explores how people decide whether online health advice feels trustworthy, helpful, and reliable. The simple question is, what makes the advice seem trustworthy or untrustworthy?

This research explores how people decide whether online health advice feels trustworthy, helpful, and reliable. The simple question is, what makes the advice seem trustworthy or untrustworthy?

The study linked contamination in bars and restaurants mainly to local cleaning practices rather than beer style or venue type

Are you living with a serious illness and approaching end of life? Would you be willing to share what matters most to you about this experience, through photographs? Find out more about IHF's Photovoi...