Background:Temporomandibular disorders (TMDs) are common chronic conditions involving orofacial pain and functional limitations. Digital therapeutics (DTx) have demonstrated efficacy in TMD management; yet, the behavioral and clinical mechanisms underlying treatment response remain poorly characterized, particularly whether behavioral modification or DTx engagement intensity drives therapeutic benefit. Objective:This study aimed to investigate the behavioral mechanisms, responder profiles, and moderators of clinical response to a DTx intervention for TMD through a post hoc analysis integrating self-reported, server-derived, and clinician-rated outcome measures. Methods:We performed a post hoc secondary analysis of a multicenter, double-blind, sham-controlled randomized superiority trial conducted at 2 tertiary care centers in South Korea. The per-protocol cohort comprised 93 participants (DTx: n=44; sham: n=49). Five complementary analyses were applied: responder logistic regression at ≥30%, ≥50%, and ≥70% Visual Analog Scale (VAS) pain-reduction thresholds; subgroup comparison by Oral Behaviors Checklist (OBC) modifier status; causal mediation analysis using the potential outcomes framework with bootstrap CIs; week-4 sensitivity analysis; and moderator analysis testing the treatment×Patient Health Questionnaire-4 (PHQ-4) interaction on VAS change. Results:DTx assignment was consistently associated with clinically meaningful pain reduction across all 3 responder thresholds (adjusted odds ratios [ORs] 5.39, 95% CI 1.72-16.94 at ≥30%; 3.21, 95% CI 1.14-8.99 at ≥50%; and 3.45, 95% CI 1.12-10.63 at ≥70%; all P<.05). Mediation analysis suggested that approximately 29.1% of the total VAS treatment effect may be transmitted via OBC-defined behavioral modification (natural indirect effect -6.91 mm; 95% CI -13.23 to -0.58; P=.03), with the mediated proportion rising from 19.6% to 30.2% as responder thresholds became more stringent. Participants with OBC modifiers achieved substantially greater pain reduction than nonmodifiers (-45.71 vs -22.61 mm; difference -23.11; 95% CI -36.97 to -9.24; P<.01) despite no significant differences in any objective DTx engagement metric. Treatment ORs were 33%-42% higher at week 4 than at the 6-week end point (week-4 ORs 7.15, 95% CI 2.39-21.32 at ≥30%; 4.48, 95% CI 1.68-11.94 at ≥50%; and 4.91, 95% CI 1.74-13.87 at ≥70%), suggesting that week 4 may be a candidate time point for future adaptive protocols. Baseline psychological distress (PHQ-4 ≥3) appeared to moderate the treatment response (interaction β=-19.63; 95% CI -37.86 to -1.39; P=.04). Conclusions:Sham-controlled randomized trials in TMD that empirically differentiate behavioral realization from digital engagement volume remain scarce. Behavioral modification, rather than engagement volume, appears to be an important pathway associated with DTx efficacy and may mediate approximately 29% of the pain-reduction effect under exploratory causal assumptions. This advances mechanism-based evaluation of DTx beyond engagement-based surrogates. Week 4 may represent a promising candidate for future adaptive protocols, and baseline psychological distress may warrant investigation for precision patient selection. These preliminary findings should be corroborated by future prospective studies and further mechanistic investigations.
Background:Digital interventions offer scalable alternatives to traditional face-to-face diabetes education, but often face challenges related to inconsistent clinical effectiveness, and declining user engagement. However, whether a digital structured education program integrated with behavioral nudge tools can improve metabolic, behavioral, and psychological outcomes in adults with type 2 diabetes remains unclear. Objective:This study aimed to evaluate the effectiveness of a digital structured education program integrated with behavioral nudge tools in improving metabolic, behavioral, and psychological outcomes among adults with type 2 diabetes. Methods:This multicenter randomized controlled trial was conducted in the endocrinology departments of 4 hospitals in China. Adults with type 2 diabetes were randomly assigned to an intervention group receiving a digital structured education program integrated with behavioral nudge tools (n=146) or a control group receiving standard digital diabetes education (n=147). Assessments were conducted at baseline and 12-week follow-up. The primary outcome was hemoglobin A1c (HbA1c) at 12 weeks, adjusted for baseline HbA1c, and study center. Secondary outcomes included fasting blood glucose (FBG), weight, BMI, waist circumference, blood pressure, lipid profiles, self-management behaviors, self-efficacy, and habit strength. Results:Among 293 participants (mean age 49.19, SD 10.02 y), 287 (97.9%) completed follow-up. At 12 weeks, the intervention group demonstrated significantly greater improvements than the control group in HbA1c (adjusted mean difference -0.38%, 95% CI -0.68% to -0.09%; P=.01), FBG (adjusted mean difference -0.75, 95% CI -1.27 to -0.44 mmol/L; P<.001), weight (adjusted mean difference -0.84, 95% CI -1.61 to -0.07 kg; P=.03), BMI (adjusted mean difference -0.38, 95% CI -0.65 to -0.11 kg/m²; P=.01), systolic blood pressure (adjusted mean difference -2.71, 95% CI -4.62 to -0.79 mm Hg; P=.01), diastolic blood pressure (adjusted mean difference -2.92, 95% CI -4.47 to -1.37 mm Hg; P<.001), and total cholesterol (adjusted mean difference -0.27, 95% CI -0.48 to -0.05 mmol/L; P=.02). The intervention was also associated with significantly greater improvements in self-management behaviors, self-efficacy, and habit strength (all P<.05). Conclusions:Digital structured education integrated with behavioral nudge tools improved metabolic outcomes and strengthened psychological and behavioral determinants of self-management among adults with type 2 diabetes over a 12-week period. These findings suggest that a digital structured education program integrated with behavioral nudge tools may enhance diabetes self-management beyond standard digital diabetes education. Further studies with longer follow-up and real-world implementation are warranted to evaluate the sustainability, generalizability, and long-term clinical impact of this integrated intervention.
Background:Consumer wearables are increasingly being integrated into health research for data collection. Although they are attractive to use, the accuracy of their photoplethysmography (PPG)-based measurements can be influenced by user characteristics such as sex, age, BMI, and skin tone. However, our knowledge regarding the validity of these measurements in certain populations, such as those with darker skin tones, seems limited. This is concerning as uncorrected differences in measurement accuracy can lead to health disparities when consumer wearable measurements are used more frequently. A potential cause for the gap in our knowledge regarding consumer wearable validity is the underrepresentation of certain population groups in studies validating PPG-based consumer wearables. Objective:This scoping review aimed to map the representation of different sex, age, BMI, and skin tone groups in studies assessing the validity of PPG-based pulse rate, heart rate variability, blood pressure, peripheral blood oxygen saturation (SpO2), and respiratory rate measurements of consumer wearables. Methods:A literature search was conducted in Scopus, PubMed, and IEEE Xplore in July 2025. Papers were eligible if they assessed the validity of consumer wearable PPG-based measurements, expressed as the agreement with a reference method. From the included papers, the study population distribution of sex, age, BMI, and Fitzpatrick scale was extracted. To evaluate the representation, percentages of people in specific age, BMI, and skin tone groups were estimated based on reported means and SDs. The median percentage of participants in each population group, as well as the total percentage, is reported. Results:After the removal of duplicates, 734 papers were screened for eligibility. Following title and abstract screening, 238 papers remained, of which 186 passed full-text screening and were included in the review. Most of the studies (n=160) focused on pulse rate. Sex, age, BMI, and Fitzpatrick scale were reported by 179 (96.0%), 178 (96.0%), 101 (54.0%), and 35 (19.0%) out of 186 studies, respectively. While the median representation was 0% (IQR 0%-8%) for both older adults (>65 y) and individuals with obesity (BMI>30 kg/m2; IQR 0%-13%), aggregate participation across all studies was higher (1290/6367, 20.0% and 473/3428, 14.0%, respectively). Individuals with underweight (BMI<18.5 kg/m2) remained rare (median 3%, IQR 0%-7%), and the aggregate was 7.0% (225/3428). The median percentage of people with darker skin tones (Fitzpatrick type V and VI) participating in a study was 0%. Conclusions:Based on our results, it can be concluded that older adults and people with underweight, obesity, or darker skin tones are generally underrepresented in studies assessing the validity of consumer wearable PPG-based measurements. Future validation studies should focus more on the representativeness of the study population. This can be achieved by setting a benchmark for representativeness and including study population representatives during the study design process.
Background:Behavior change support systems aim to shape, modify, or strengthen attitudes or behaviors without using coercion or deception. One of the main software features of persuasive system design is self-monitoring, which provides the means for users to continuously track their own performance or status, thereby facilitating goal attainment. Objective:The aim of this study is to examine whether self-input of weight (self-monitoring frequency) and its interaction with time influence weight loss in adults using a mobile health behavior change support system (mHBCSS). We hypothesized that higher self-monitoring frequency would be associated with greater weight loss, with effects varying across the intervention period. Methods:This secondary analysis used data from the intervention group of a randomized, open, waitlist-controlled trial in adults with obesity (BMI 30-40 kg/m²). Participants used the mHBCSS for 12 months, and analyses included only participants who maintained self-monitoring for at least 6 months (N=75). Weight changes were analyzed across 9 time periods. Quantile regression (QR) was applied to examine effects on the 25th, 50th (median), and 75th percentiles of weight loss. The models included self-monitoring frequency, time periods, and their interaction. A sensitivity analysis using a multiple imputation procedure was performed to assess the robustness of the QR. Results:The time period variable was significant at the 25th weight loss percentile (QR coefficient: -1.164, 95% CI -1.453 to -0.756) and at the 50th weight loss percentile (QR coefficient: -0.603, 95% CI -0.733 to -0.493). The interaction variable was significant at the 50th (QR coefficient: -0.018, 95% CI -0.047 to -0.003) and 75th (QR coefficient: -0.036, 95% CI -0.051 to -0.027) weight loss percentiles. Self-monitoring frequency alone was not statistically significant. Conclusions:The study demonstrates that the effect of self-monitoring on weight loss is time-dependent. While a higher frequency of self-monitoring is associated with greater weight loss early in the intervention, its influence decreases as time progresses. These findings emphasize the importance of sustained engagement with self-monitoring rather than focusing solely on frequency, suggesting that interventions should incorporate strategies to maintain consistent self-monitoring use throughout the behavior change process.
Background:Pediatric ear, nose, and throat (ENT) surgery is common, but generates perioperative anxiety for caregivers and distress in children. Limited time for perioperative education and reliance on unverified online information can reduce family preparedness and increase stress. Few studies have evaluated co-designed mobile health (mHealth) apps to support and engage families in the perioperative ENT journey. Objective:This study aimed to compare caregiver anxiety between an mHealth app-supported care pathway and standard supportive and educational care alone in the perioperative ENT context. Secondary objectives explored between-group differences in caregiver anxiety at follow-up, family preparation, child distress, and social-impact indicators. Methods:A 2-arm, parallel-group, open-label randomized controlled trial (RCT) enrolled caregivers of children undergoing ENT surgery (tonsillectomy, adenoidectomy, tympanostomy tube insertion). The intervention was an mHealth app co-designed through a user-centered participatory approach and developed following Schnall and colleagues' Information Systems Research Framework, with content based on caregivers' informational needs. RCT participants were recruited at the hospital during their presurgery visit, when a health care provider introduced the study and provided instructions on how to use the app. No additional human support was scheduled thereafter. A sample size of 180 participants (90 per group) was estimated to detect the expected between-group difference in caregiver anxiety. Participants were randomly assigned in a 1:1 ratio to app use or standard care alone. The primary outcome was the between-group difference in caregiver state anxiety (State-Trait Anxiety Inventory [STAI-Y]). Secondary outcomes included between-group differences in child distress (modified version of the Yale Preoperative Anxiety Scale [mYPAS]), child preparation for surgery, family preparation for hospital admission and surgery, and social impact indicators. Outcomes were assessed online through questionnaires, which included both self-reported measures and evaluations completed by a nurse on the day of surgery. App engagement metrics were also collected. Reporting followed the CONSORT-EHEALTH (Consolidated Standards of Reporting Trials of Electronic and Mobile Health Applications and Online Telehealth) guidelines. Results:The study enrolled 227 caregivers, with 111 allocated to the control group (CG) and 116 to the experimental group (EG), achieving the target sample size. No statistically significant differences were observed between the groups for the primary or secondary outcomes (all P>.05). In the EG, 75% (n=87) of the participants accessed at least 1 item of in-app content. Higher baseline anxiety was linked to lower app use (ρ=-0.22, 95% CI -0.39 to -0.04; P=.02), while greater use was linked to lower child distress (ρ=-0.23, 95% CI -0.40 to -0.04; P=.02). Conclusions:Although the hypotheses were not confirmed, these findings provide valuable insights for future perioperative mHealth research. The lack of effectiveness may reflect limited exposure to the intervention, outcome selection and timing, and contextual factors such as caregivers' independent information-seeking. These findings support a greater focus on implementation processes and on identifying the caregivers most likely to benefit from mHealth-supported education.
Background:Optimal bowel preparation (BP) is crucial for a successful colonoscopy. Although multiple factors influence BP quality, including patient adherence to laxatives and dietary instructions, the stool state during BP should be properly evaluated to perform a colonoscopy of sufficient quality. Therefore, we developed a smartphone app to evaluate a patient's stool state during BP and a viewer to enable real-time monitoring by medical staff. Objective:This study aimed to assess the feasibility of performing colonoscopies of appropriate quality using the app-and-viewer system. Methods:This prospective observational study was conducted between November 2022 and December 2023, involving patients scheduled for colonoscopy at 10 Japanese institutions, comprising 6 tertiary hospitals, 3 regional general hospitals, and 1 community-based clinic. Patients who (1) underwent a colonoscopy at participating institutions, (2) were aged between 20 and 70 years, and (3) owned smartphones compatible with Android or iOS were included in the study. The patients downloaded the app on their smartphones and captured images of their stools during BP, while the medical staff reviewed the evaluation of the stools by the app via the viewer system. The primary end point was defined as the proportion of patients with a Boston Bowel Preparation Scale (BBPS) score of ≥6 among those who successfully used the app. Secondary end points included mean BBPS score, rate of an excellent BBPS score (≥8), adenoma detection rate, cecal intubation rate, and withdrawal time in negative colonoscopy. Additionally, we evaluated the usability of the app, medical staff workload burden with the app, and viewer usage via questionnaire surveys. Results:A total of 343 patients were enrolled, and 326 were ultimately included in the analysis. Overall, 99.1% (323/326, 95% CI 97.3%-99.8%) of the patients achieved the primary end point. The mean BBPS score was 8.5 (SD 1.0), and the proportion of excellent BBPS scores was 87.4% (285/326). The adenoma detection rate, cecal intubation rate, and mean withdrawal time in negative colonoscopy were 46.9% (153/326, 95% CI 41.4%-52.5%), 99.7% (325/326, 95% CI 98.3%-99.9%), and 10.7 (SD 5.9) minutes, respectively. In the questionnaire survey, 98.5% (321/326) of the patients reported that the tutorial was easy to understand, 96.0% (313/326) found stool image capture easy, and 87.8% (286/326) reported reduced anxiety regarding BP. Furthermore, 90.5% (295/326) of the patients indicated that they would like to use the app again for future colonoscopies. Among medical staff, 92.5% (62/67) considered the viewer system necessary, 89.6% (60/67) found it easy to use, and 89.6% (60/67) reported a reduction in workload burden. Conclusions:AI-based stool state assessment using the app and the viewer during BP was feasible across diverse BP methods and clinical environments. Favorable BP outcomes and high usability among patients and medical staff support the potential use of this approach in real-world colonoscopy practice.
BACKGROUND:Artificial intelligence (AI)-based tools for oral cancer screening have shown promising performance in curated or retrospective image datasets, although such evidence may not fully reflect performance in real-world mobile community screening workflows. In remote or resource-limited settings, intraoral images are often acquired by trained non-specialist personnel under variable field conditions, making workflow-integrated image quality assurance, risk stratification, and expert oversight essential for human-supervised AI-assisted screening. OBJECTIVE:This study aimed to evaluate the prospective field performance of a parameter-locked, mobile AI-assisted oral lesion triage system embedded within a human-supervised routine community oral cancer screening workflow. METHODS:We conducted a prospective community-based field evaluation in eastern Taiwan from June 17 to December 31, 2025. Trained non-specialist personnel acquired standard white-light intraoral images using handheld mobile devices during routine oral cancer screening activities. The AI system incorporated on-site image quality assessment and lesion-level risk stratification into green, yellow, and red triage categories. Images that remained technically inadequate after repeated acquisition attempts were classified as ungradable and excluded from performance analysis. Three board-certified oral and maxillofacial specialists established an operational clinical reference standard through structured image review and consensus adjudication. The primary outcome was lesion-level identification of high-risk lesions requiring specialist referral, defined as red versus non-red triage. Diagnostic performance was estimated with Wilson 95% confidence intervals; precision-recall performance and pre-consensus inter-rater agreement among specialists were also assessed. RESULTS:Among 602 screened participants, 4283 interpretable intraoral images were included in expert adjudication and lesion-level analysis. The AI system flagged 68 red lesions; 12 were confirmed as high risk by expert adjudication, and 4 additional high-risk lesions were identified during expert review, yielding 16 high-risk events for the primary red-triage analysis. For high-risk lesion identification, sensitivity was 75.0% (95% CI 50.5%-89.8%) and positive predictive value was 17.6% (95% CI 10.4%-28.4%); specificity, negative predictive value, and accuracy were 98.6%, 99.9%, and 98.5%, respectively. ROC-AUC values were 0.957 for red, 0.931 for yellow, and 0.964 for green triage; precision-recall analysis showed PR-AUC values of 0.8235 for red, 0.9052 for yellow, and 0.9476 for green triage. Pre-consensus specialist agreement was high, with a Fleiss' kappa of 0.921 and a Gwet's AC1 of 0.981. CONCLUSIONS:A parameter-locked mobile AI-assisted oral lesion triage system was feasibly integrated into a real-world community oral cancer screening workflow operated by trained non-specialist personnel. In this low-prevalence field setting, red triage showed moderate sensitivity and modest positive predictive value, supporting its potential role as human-supervised referral-prioritization support rather than autonomous diagnosis or standalone clinical decision-making. Further multicenter studies with blinded assessment, participant-level outcomes, workflow-efficiency measures, and longitudinal follow-up are needed before clinical impact and scalability can be determined. CLINICALTRIAL:
Background:Mindfulness interventions are considered an effective strategy for preventing mental health problems among health care workers (HCWs). While prior reviews have often included facilitator-guided or multicomponent interventions, it is unclear whether self-guided digital mindfulness interventions can also be effective without professional or in-person support. Objective:This systematic review aimed to investigate the effects of self-guided digital mindfulness interventions on the mental health and well-being of HCWs. Methods:This work was conducted as part of the DeLiGHT project. We searched electronic databases, including PubMed (MEDLINE), Embase, Cochrane CENTRAL, PsycINFO, PsycARTICLES, and the Japan Medical Abstract Society database, from inception in 2010 to July 25, 2023. To ensure timeliness, we performed an updated search on December 27, 2025. Database searching yielded 37,851 abstracts and 145 studies that examined the effectiveness of digital health interventions for workers in the initial 2023 screen. In the present study, we limited the included studies to those that met the following criteria: randomized controlled trials (RCTs) using self-guided digital mindfulness interventions (eg, smartphone apps or web-based programs) delivered without face-to-face or professional support compared to waiting list controls or usual care among HCWs. The updated search in 2025 yielded 6328 additional records, of which 11 studies were examined. Study quality was assessed using the Cochrane Risk of Bias tool, with meta-analyses conducted using a random-effects model. Results:A total of 9 RCTs with 3088 participants were included in the final analysis. The study populations were diverse, covering North America, Europe, Oceania, and Asia. Interventions were delivered via various digital platforms, including commercial mindfulness apps (n=3), social networking service tools (n=3), and web-based programs (n=3), with an average duration of 6.17 weeks (range: 1.5-18 wk). Five studies assessed outcomes only postintervention, and 4 included short-term follow-up (4-12 wk); no long-term effects were evaluated. The meta-analysis showed a significant beneficial effect on depression (standardized mean difference [SMD]=-0.44, 95% CI -0.88 to -0.00; P=.049), anxiety (SMD=-0.29, 95% CI -0.51 to -0.06; P=.011), perceived stress (SMD=-0.42, 95% CI -0.77 to -0.06; P=.02), and well-being (SMD=0.20, 95% CI 0.09 to 0.30; P<.001) immediately postintervention. The adherence rates reported across studies were highly variable, ranging from 19% to 56%. According to the Cochrane Risk of Bias tool, most studies were rated as having some concerns or a high risk of bias. The certainty of evidence included in the analysis ranged from "Low" to "Very Low." Conclusions:Overall, low to very low certainty evidence suggests that self-guided digital mindfulness interventions may have short-term beneficial effects on depression, anxiety, perceived stress, and well-being among HCWs. Future high-quality studies are needed to examine the long-term effects and cross-cultural generalizability of these interventions.
Background:Delays in completing cancer screening diminish the preventive benefits of early detection, particularly among women receiving care in Federally Qualified Health Centers (FQHCs). Although many patients receive SMS reminders and complete screening, less is known about how quickly they complete testing or which patient-level and structural factors are associated with delays. Objective:This study examined factors associated with time to cancer screening completion among women aged 50 years or older who received SMS reminders and completed screening across a large FQHC network in Texas. The study also compared time to completion across three cancer screening tests: human papillomavirus (HPV) or the Papanicolaou test (hereinafter "Pap test"), mammography, and the fecal immunochemical test (FIT) or Cologuard screening. Methods:We conducted a secondary data analysis using electronic health record (EHR) data from a 56-clinic FQHC network in Texas. The initial cohort included 1803 women aged 50 years or older who (1) were overdue for HPV or Pap testing, mammography, or FIT or Cologuard screening, and (2) received at least three SMS reminders. Of those, 551 completed the screening and constituted the analytic cohort for this study. The outcome was the number of days from the initial SMS reminder to documented completion of the overdue screening test in the EHR. Kaplan-Meier methods were used to estimate time to completion by screening modality. A multivariable Cox proportional hazards model assessed associations of screening modality, sociodemographic, and clinical characteristics, and self-reported health-related social needs with the rate of screening completion. Results:Overall, 40.8% (n=212) of patients overdue for HPV or Pap testing completed their screening, while 21.1% (n=138) of those overdue for mammography and 32.1% (n=201) of those overdue for FIT or Cologuard screening completed their respective screening. Median time to completion was 72.5 (95% CI 64-86) days for HPV or Pap screening and 52.0 days for both mammography (95% CI 43-64) and FIT or Cologuard screening (95% CI 52-53). In the adjusted model, screening completion was faster for FIT or Cologuard screening (hazard ratio [HR] 1.65, 95% CI 1.34-2.05) and mammography (HR 1.41, 95% CI 1.11-1.78) than for HPV or Pap screening. Patient-reported transportation limitation was associated with slower screening completion (HR 0.74, 95% CI 0.55-0.99). Conclusions:These findings demonstrate meaningful variation in both the completion and timeliness of overdue cancer screening across screening modalities. Although HPV or Pap testing had the highest overall completion rate, time to completion was significantly shorter for mammography and FIT or Cologuard screening. The association between transportation limitations and delayed screening further underscores the influence of access-related barriers on timely preventive care. This suggests that efforts to improve cancer screening should extend beyond patient outreach to incorporate modality-specific strategies and interventions that address structural barriers to screening completion.
Abstract Background Suicide is a leading cause of preventable mortality worldwide, with more than 700,000 deaths annually. Although suicidal ideation fluctuates rapidly, conventional risk assessments rely on retrospective self-report collected infrequently, and the detection of short-term suicide risk remains limited. Passive digital sensing using smartphones and wearable devices enables continuous monitoring of behavioral and physiological signals associated with suicide-related outcomes. However, current evidence remains fragmented, without a clear framework for translation into clinically interpretable risk indicators. Objective This scoping review synthesized and mapped passive digital markers associated with suicide-related outcomes via the layered hierarchical sensemaking framework (LHSF), which structures information from raw sensor data to high-level behavioral markers. We aimed to illustrate a clinically interpretable mapping of digital markers for suicide-specific digital phenotyping. Methods Following Arksey and O’Malley and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, this scoping review was conducted using the population-concept-context framework (population: not restricted; concept: passively collected digital data from smartphones or wearable devices; and context: suicide-related outcomes). PubMed, CINAHL, PsycINFO, and IEEE Xplore were searched for studies published between 2015 and 2025. Studies were included if they (1) collected passive digital data from smartphones or wearable devices, and (2) measured suicide-related outcomes. Narrative mapping was conducted using LHSF to distinguish between low-level features (ie, measurable properties extracted from sensors) and high-level behavioral markers (ie, clinically meaningful constructs interpreted from low-level features). Results Of 626 studies identified, 14 (2.2%) met inclusion criteria. Six (42.9%) used predictive modeling, and 8 (57.1%) conducted correlational analyses. Among predictive studies (area under the curve [AUC]=0.56-0.89), a lower heart rate variability predicted an elevated suicide risk in 1 study (AUC=0.89). Of correlational studies, 7 (87.5%) of 8 reported at least one significant association between passive sensor data and suicide-related outcomes. Mapped to the LHSF, low-level features spanned 7 domains, linked to high-level markers, such as autonomic dysregulation, sleep disturbance, social withdrawal, smartphone use patterns, and suicide-related expression. Physiological indicators of autonomic regulation were associated with suicide-related outcomes in all 4 studies examining them and achieved the highest predictive performance (AUC=0.89). Smartphone use metrics were significantly associated in both studies, whereas linguistic (2/3 studies, 66.7%) and location-based features (2/2 studies, 100%) were associated with at least one outcome, with nonsignificant findings for some indicators or studies. Sleep parameters and movement intensity showed few significant associations. Conclusions Physiological indicators were associated with suicide-related outcomes across all relevant studies and showed the highest predictive performance (AUC=0.89), followed by smartphone-derived behavioral features. Linguistic and location-based features showed mixed associations, whereas sleep- and activity-related indicators showed few significant associations. Future research should prioritize multimodal data integration, algorithmic refinement, and external validation to strengthen clinical utility in digital suicide phenotyping based on the LHSF.
Background:Physical activity (PA) alleviates many treatment-related side effects in gynecologic cancer survivors, yet long-term PA levels remain low. Mobile health interventions can support self-management and increase PA levels; however, evidence from real-world, year-long engagement with smartphone apps in this population is still limited. Objective:The aim of this study is to describe 12-month user engagement with the PA component of a smartphone app implemented within a partially nurse-led routine follow-up in a real-world cohort of gynecologic cancer survivors. Methods:This descriptive study analyzed server-generated log data from the intervention arm of the prospective, multicenter, quasi-experimental LETSGO (Lifestyle and Empowerment Techniques in Survivorship of Gynecologic Oncology) trial (NCT04122235). Between December 2019 and July 2022, 378 cancer survivors (ovarian, endometrial, cervical, vulvar, or vaginal cancer) from 5 Norwegian hospitals were enrolled in the intervention arm and were offered the app plus a Garmin Vivofit 4 activity tracker alongside standard consultations. Primary outcomes for this study were (1) weekly PA registrations (objective step counts from the activity tracker and self-reported PAs) and (2) temporal patterns of step logging during each cancer survivor's first 52 weeks postenrollment. Secondary analyses compared baseline characteristics of app users (≥2 wk of PA logging) and nonusers. Results:Of 378 eligible participants (mean age 63, SD 13 y; BMI 28.5, SD 6.4 kg/m²), 272 (72%) logged at least 2 weeks of PA, and 225 (60%) synchronized objective step data. Mean daily steps were 5657 (SD 2799; median 5533, IQR 3499-7498). Step tracking dominated app use (mean 21, SD 16 logged wk), followed by self-reported walking (mean 23, SD 19 wk) and resistance training (mean 15, SD 16 wk). Weekly step-logger counts fell around study weeks 16, 32, and 44, but rebounded by 30 to 50 participants within 3 weeks, indicating episodic rather than permanent disengagement. App users were younger (mean difference -6.7 y, 95% CI -9.6 to -3.9; P<.001), more often employed (χ²1=12.7; P<.001), and more likely to have higher education (χ²2=13.6; P<.001) than nonusers. Tumor type and treatment modality were not associated with engagement. Conclusions:In a routine-care setting, nearly three-quarters of gynecologic cancer survivors engaged repeatedly with an app-supported PA module over 12 months, although mean PA levels were modest and participation was more prevalent among younger, employed, and more highly educated participants. Engagement followed an ebb-and-flow pattern, suggesting that built-in re-engagement prompts and equity-focused onboarding are needed to sustain and broaden participation. These findings support the feasibility of blended mobile health follow-up while highlighting the importance of adaptive strategies to promote long-term PA adherence and bridge the digital divide among cancer survivors.
BACKGROUND:On a population level, mental health apps are accessible and effective. However, nondigitally native adults with chronic pain are a large and growing population who have been neglected during the development process of these interventions. Although technology use is rapidly growing among this population, their engagement with mobile health-related apps is lagging because usability is often not optimized for their needs and preferences. OBJECTIVE:This study aimed to identify design preferences and determinants of engagement with mental health apps by nondigitally native adults who have chronic pain and coexisting symptoms of depression or anxiety. METHODS:In this qualitative study, participants completed a semistructured interview regarding their experience with, and perceptions of, mobile devices, apps, and digital health interventions. Participants were 45 years or older; scored ≥10 on the 9-item Patient Health Questionnaire, 7-item Generalized Anxiety Disorder, or both; endorsed pain on most days or every day in the past 3 months; and were living in the United States. The interview guide was informed by the Consolidated Framework for Implementation Research and the Behavioral Intervention Technology model. Codes were organized into themes. Recruitment continued until thematic saturation was achieved. RESULTS:A total of 42 participants were interviewed (mean age 57, SD 8 years; n=32, 76% women). Participants strongly preferred apps that are free, describe strong privacy policies, and add functional value to their lives. They were more motivated by "real-life" goal achievement and tangible health improvements than by gamification within an app, and many were wary of allowing apps to passively collect certain types of data, especially to make inferences about their mental health. Most participants were unaware of apps designed to address chronic pain, but they were interested in the concept, particularly to help track their mood and pain and then identify associations between their symptoms, app activity, and other life events. Despite their daily use of apps, many participants described frequent challenges related to app navigation. While on-demand access to app tools was preferred, most participants appreciated the potential value of occasional push notifications if their timing was thoughtful and customizable. Participants cautioned against an overly cheerful, "infantile," or informal tone for an app that addresses serious issues such as mental health and chronic pain. CONCLUSIONS:Mental health apps for nondigitally native adults should highlight tangible health improvements that can be achieved from app engagement (more so than gamification), potentially using a multidomain tracking feature, if appropriate. This population is available to receive just-in-time adaptive interventions, but the frequency and timing should be thoughtful, customizable, and not wholly reliant on passively collected personal data. Health-related apps designed to address conditions that are more common with increasing age should account for these preferences.
BACKGROUND:Emerging data suggest that text message-based mobile health interventions may enhance physical activity levels in patients with cardiovascular disease enrolled in cardiac rehabilitation. The optimal characteristics of texts that lead to maximal patient engagement and drive meaningful behavioral change are not well understood. OBJECTIVE:This study aimed to understand how text- and participant-level characteristics impact physical activity levels after text delivery. METHODS:The VALENTINE (Virtual Application-Supported Environment to Increase Exercise) study was a randomized controlled trial designed to evaluate a mobile health intervention delivered to low- and moderate-risk adults enrolled in cardiac rehabilitation. Embedded within this study was a microrandomized trial focused on the effect of texts on physical activity levels among intervention participants. Participants in the intervention group received texts through a smartwatch (Apple Watch or Fitbit Versa) that were tailored to the time of day, day of the week (weekday vs weekend), weather, and time since enrollment in cardiac rehabilitation. Texts also differed in content type (walking vs antisedentary) and in the level of personalization (inclusion of the participant's name or not). Delivery was randomized at 4 user-selected time points daily, with participants having a 25% probability of receiving a text at any time point. The primary outcome was step count 60 minutes after a decision point. This analysis focuses on the text- and participant-level factors that moderated the intervention's effect on the primary outcome. Given potential measurement differences determined a priori, analyses were stratified by device type and phase of cardiac rehabilitation and adjusted for age, sex, and baseline activity status using a generalization of regression analysis. RESULTS:More than 70,552 randomizations occurred in 108 participants (mean age 59.5, SD 10.7 years; n=36, 33.3% female; n=19, 17.6% non-White; n=68, 63% Apple Watch users) over 6 months. Overall, no text characteristics (including personalization with the participant's name) or participant characteristics (including baseline physical activity) consistently impacted text responsiveness for either device type. Although the findings were not consistently significant between device types and across phases of the trial, there was a trend toward increased responsiveness to texts that promoted walking (compared to antisedentary texts) and that were delivered to younger (aged <65 years) and male participants. CONCLUSIONS:In this randomized clinical trial, we found that tailored texts improved physical activity levels among cardiac rehabilitation enrollees in the initiation phase, but this effect was not explained by text- or participant-level moderators. Additional work is needed to explore the impact of tailoring based on an extended set of personal and environmental factors to optimize the delivery and efficacy of text message-based interventions. TRIAL REGISTRATION:ClinicalTrials.gov NCT04587882; https://clinicaltrials.gov/study/NCT04587882. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID):RR2-10.1016/j.ahj.2022.02.012.
Background:Fatigue and chronic fatigue syndrome (CFS) have a considerable impact on quality of life, thus motivating people to develop skills for better management of their fatigue. While the number of commercial apps in this domain has increased, there has been limited exploration of their functionalities. Objective:This paper aims to address this research gap through a functionality review of 17 top-rated iOS and Android apps for fatigue, with the aim to articulate design implications for technologies focused on supporting the management of fatigue. Methods:We conducted a systematic search on the 2 most common app marketplaces, which resulted in the initial identification of 427 Apple apps and 1218 Google apps. From these, 17 apps were selected for review after applying a screening process to shortlist the top-rated apps. The functionalities of these apps were then coded through a week-long usage of each app for an expert evaluation leveraging authors' human-computer interaction (HCI) expertise. We looked for functionalities such as tracking and visualization seen in previous research on functionality reviews, in addition to interventional functionalities, which were informed by research on fatigue. Results:Findings reveal the prevalence of functionalities for tracking fatigue (8/17, 47%), related symptoms (8/17, 47%), for visualizing tracked content (10/17, 59%), for assessing the user's condition (2/17, 12%), and for providing interventions for the management of fatigue (12/17, 71%). Functionalities providing interventions for self-management of fatigue are surprisingly limited, with the most relevant ones including pacing (2/17, 12%) alongside energy estimation (2/17, 12%). Conclusions:The top-ranked apps for fatigue in the major marketplaces support 3 main functionalities under the scope of tracking fatigue along with related data, and visualizing such data, with limited provision of self-management interventions. Drawing from these findings, we articulate implications for the sensitive design of technologies to support the management of fatigue, including supporting hybrid tracking, combined visualizations to support sense-making of fatigue data with related factors, and supporting energy estimates and pacing interventions.
Background:Cancer affects multiple physical, psychological, and social aspects of an individual's life. Cancer survivors frequently report unmet needs long after diagnosis and require ongoing support. AI is increasingly embedded in patient-facing digital health technologies (DHTs) in oncology, yet its impact on different domains of patients' and survivors' health-related quality of life (HRQOL) remains unclear. Objective:This systematic review aims to (1) examine how AI has been integrated into patient-facing DHTs designed to support cancer survivors, (2) narratively synthesize the potential effects of these technologies on HRQOL and provide preliminary quantitative estimates through an exploratory meta-analysis, and (3) explore broader changes in additional patient-reported outcomes (PROs; secondary aim). Methods:PubMed, PsycINFO, Embase, Scopus, CINAHL, and the Cochrane Library were searched for articles published between January 2020 and August 2025. Reference lists of included articles were hand-searched for additional eligible studies. Eligible studies enrolled cancer survivors of any age and disease stage, evaluated a patient-facing DHT with AI components, and assessed HRQOL. Nonoriginal research and non-English reports were excluded. Risk of bias was assessed in all controlled studies using RoB 2 (revised Cochrane risk of bias 2) or ROBINS-I V2 (Risk of Bias in Non-Randomized Studies-of Interventions, Version 2), according to study design. Data on HRQOL and other PROs were synthesized narratively, and exploratory random-effects meta-analyses were conducted for HRQOL domains. Results:Eight reports from 7 studies from China and the United States (N=2867 participants) met the inclusion criteria, and 3 (n=292 participants) contributed to the exploratory meta-analysis. All studies included adults with various cancers at different stages and times since diagnosis. Most studies showed low risk of bias or some concerns (RoB 2), but one was evaluated as having a serious risk of bias (ROBINS-I V2). AI applications ranged from symptom monitoring to targeted education. The narrative synthesis suggested positive effects on selected HRQOL domains, particularly general health, with more pronounced effects in studies conducted in China. Exploratory meta-analyses demonstrated provisional moderate positive effects on global health (Hedges g=0.77, 95% CI 0.15-1.40) and social functioning (Hedges g=0.75, 95% CI 0.08-1.42), but no effects on physical functioning, role functioning, or emotional well-being. Other PROs indicated generally high user satisfaction and adherence, improved mental health outcomes, and reductions in physical symptoms. Only minor and mild adverse events were reported. Conclusions:Current evidence, although limited, suggests that AI-enabled patient-facing DHTs may benefit survivors' HRQOL and other PROs, particularly in early survivorship. However, our findings are based on small and heterogeneous studies and should therefore be interpreted with caution. Robust trials with adequate sample sizes, longer follow-up, and appropriate control conditions, including DHTs without AI components, are needed to determine the specific contribution of AI.
Background:Sustaining self-management is critical for optimizing clinical outcomes in individuals with type 2 diabetes mellitus (T2DM). Although digital health interventions (DHIs) have shown benefits for glycemic control and self-care, much of this evidence has focused on efficacy, and the behavioral mechanisms through which DHIs produce sustained effects remain insufficiently understood. Clarifying these mechanisms could inform the development of theory-driven interventions. Objective:This study examined the longitudinal behavioral pathways through which Artificial Intelligence-based Health Education Accurately Linking System, a WeChat (Tencent)-based digital health program, influences T2DM self-management, using the Extended Multi-Theory Model (MTM) of health behavior change. Methods:An explanatory sequential mixed methods prospective longitudinal cohort study was conducted among adults with T2DM (aged ≥18 y and proficient in WeChat use), recruited from 45 primary health care institutions in Beijing, China, between July 2023 and July 2024. Self-management behavior was assessed as the primary outcome using the Summary of Diabetes Self-Care Activities, and psychosocial determinants using the Extended MTM Scale and the Diabetes-related Skills Scale. Exploratory and confirmatory factor analyses assessed the construct validity of the Extended MTM Scale. Structural equation modeling examined longitudinal pathways among Artificial Intelligence-based Health Education Accurately Linking System users across baseline and 3, 6, and 12 months. For the qualitative phase, a purposive subsample was selected through maximum variation sampling based on baseline glycated hemoglobin; interviews were analyzed thematically until thematic saturation, and integrated with quantitative findings using a joint display. Results:Of the 406 enrolled participants, 391 completed baseline assessments. The Extended MTM Scale demonstrated a 6-factor, 22-item structure with excellent internal consistency (Cronbach α=0.928) and satisfactory construct validity. The structural equation modeling showed satisfactory fit (CFI=0.984, RMSEA=0.036). Changes in the social environment (β=0.23, 95% CI 0.07-0.38; P=.003) and physical environment (β=0.25, 95% CI 0.10-0.40; P=.001) at baseline, and diabetes-related skills at month 6 (β=0.16, 95% CI 0.03-0.29; P=.01), were directly associated with self-management behavior at month 12, whereas behavioral confidence and emotional transformation showed no significant direct effects. Social environment changes were indirectly associated with behavioral confidence through participatory dialogue at month 3 (β=0.20, 95% CI 0.04-0.36; P=.01; β=0.66, 95% CI 0.57-0.74; P<.001). Thematic analysis of 17 interviews identified 3 domains: environmental context, cognitive processes, and attitudes and skills. Environmental factors converged across both data strands, while qualitative data expanded on the cognitive and attitudinal processes underlying sustained self-management. Conclusions:This study is among the first to apply the Extended MTM framework to DHI-supported T2DM self-management, with environmental factors emerging as key drivers alongside selected cognitive, attitudinal, and skills-related processes. Complementing efficacy-focused research, it illuminates the psychosocial pathways underlying sustained self-management and refines the Extended MTM in digital health contexts. These insights can inform the design of theory-driven DHIs in primary care.
Background:Patients with chronic diseases often struggle to maintain sufficient physical activity (PA) and reduce sedentary behavior in daily life. Just-in-time adaptive interventions (JITAIs), delivered through mobile health technologies such as mobile apps, wearable devices, sensors, and ecological momentary assessment, offer timely and personalized support based on individuals' changing needs. However, the evidence base for their use in promoting PA and reducing sedentary behavior among patients with chronic diseases remains fragmented. Objective:This review aimed to describe study characteristics and design features of JITAIs, summarize reported evaluation findings related to PA and sedentary behavior, and identify barriers and facilitators related to engagement and use of JITAIs. Methods:A comprehensive literature search was conducted in PubMed, Embase, Web of Science, CINAHL, and Scopus from database inception to June 2025. Two researchers independently screened the records, selected eligible studies, and performed data charting to ensure rigor and consistency. Results:A total of 14 studies were included in this review. Of these, 6 primarily targeted PA, 1 focused solely on sedentary behavior, and 5 addressed both PA and sedentary behavior. Of the remaining, 6 studies provided preliminary evidence supporting the positive effects of JITAIs in promoting PA among individuals with chronic diseases, while 3 studies suggested positive effects on reducing sedentary behavior. Barriers and facilitators influencing the use of JITAIs in this population were identified. Barriers included technological usability and literacy, burden and intrusiveness of the intervention, perceived value and acceptability, external and contextual barriers, and privacy and data security concerns. Facilitators included enhanced motivation and behavioral engagement, increased awareness and self-monitoring, usability and integration into daily life, timely and personalized support, and support from health care professionals and the care environment. Conclusions:This scoping review identified preliminary evidence suggesting that JITAIs may help reduce sedentary behavior and promote PA among patients with chronic diseases. However, more large-scale, high-quality randomized controlled trial studies are needed to strengthen evidence and generalizability.
BACKGROUND:Adolescents with depressive symptoms are at increased risk of social functional impairment and are more likely to develop major depressive disorder. Digital interventions offer advantages, such as high accessibility, especially for adolescents. However, evidence on the effectiveness of web-based psychological interventions in alleviating depressive symptoms among adolescents remains limited. OBJECTIVE:This study aims to develop a brief web-based psychological intervention tailored to the developmental and psychological characteristics of Chinese adolescents and to evaluate its effectiveness and influencing factors. METHODS:In a 2-arm randomized controlled trial, adolescents aged 12 to 18 years with depressive symptoms were recruited from high schools in China. Eligible participants were randomly assigned in a 1:1 ratio to the intervention group (n=212) or the control group (n=224). Participants in the intervention group received a 4-week brief web-based emotional cognitive training program, whereas those in the control group received a web-based psychoeducation program. Nonprofessional helpers provided minimal support through text messages or phone calls. The primary outcome was depressive symptom severity. Secondary outcomes included the depressive symptom remission rate, changes in anxiety symptoms, suicidal ideation, and resilience. Data were collected at baseline (T0), postintervention (T1), and at 1- and 3-month follow-ups (T2 and T3). Statistical analyses included analysis of covariance (ANCOVA), logistic regression analysis, and mediation analysis. RESULTS:Two-way repeated-measures ANCOVA revealed a significant time effect (F3,1461=82.515; P<.001; η2p=0.140) on depressive symptom severity, with significantly lower scores at T1, T2, and T3 than at T0. No significant group effect (F1,1461=1.039; P=.31; η2p=0.001) or time-by-group interaction (F3,1461=2.424; P=.06; η2p=0.005) for depressive symptom severity was observed. Post hoc exploratory analysis showed that among adolescents with anxiety symptoms, the intervention group exhibited a higher depressive symptom remission rate at T1 than the control group (adjusted odds ratio 1.39, 95% CI 1.05-1.85; P=.02; number needed to treat=7). Additionally, the intervention group showed significantly greater improvements in the interpersonal support dimension of resilience at T1 (least squares mean difference=1.79, 95% CI 0.53-3.06; Cohen d=0.37, 95% CI 0.11-0.63; P=.006; false discovery rate-adjusted P=.04). Exploratory mediation analysis identified a significant indirect effect between the intervention and depressive symptom remission via the interpersonal support dimension of resilience at T1 (indirect effect=0.08, 95% CI 0.02-0.14; P=.009). CONCLUSIONS:The brief web-based psychological intervention showed no significant difference from web-based psychoeducation in reducing depressive symptoms across the 3-month follow-up period. Post hoc exploratory analyses detected a potential between-group difference in depressive symptom remission among adolescents with comorbid anxiety symptoms, with interpersonal support showing a significant mediating association. These exploratory findings may provide new insights into identifying the target population suitable for brief web-based psychological interventions and inform the development of tailored interventions in the future. TRIAL REGISTRATION:Chinese Clinical Trial Registry ChiCTR2400090235; https://www.chictr.org.cn/showproj.html?proj=243991.
Background:Poststroke cognitive impairment (PSCI) is a common and disabling complication after stroke; however, early screening remains challenging due to limited access to neuropsychological testing and the high cost of neuroimaging. Portable, tablet-based eye-tracking technology may offer a scalable, low-cost solution for early PSCI detection. Objective:This study aimed to evaluate the clinical utility of a tablet-based, AI-driven eye-tracking system for early screening of PSCI at 3 months after acute ischemic stroke. We sought to quantify oculomotor-cognitive associations and develop a practical nomogram for individualized risk prediction. Methods:We prospectively enrolled 142 hospitalized patients with acute cerebral infarction between May 2023 and October 2024, of whom 122 completed the 3-month follow-up and were included in the final analysis, along with 20 healthy community-dwelling controls. All patients underwent tablet-based eye tracking (visual paired comparison and antisaccade tasks) during the acute phase, as well as baseline and 3-month neuropsychological assessments. PSCI was defined using validated cutoffs. Multivariable logistic regression was used to identify independent predictors, and a nomogram was constructed. Internal validation was performed using bootstrap resampling (1000 samples). Results:At 3 months, out of 122 patients, 47 (38.5%) met PSCI criteria. Compared with patients with non-PSCI (n=75), patients with PSCI showed significantly prolonged correct saccade latency (median 322.96, IQR 209.45-445.59 ms vs 194.55, IQR 141.50-299.75 ms; Z=-4.03, P<.001), increased uncorrected error rate (median 30.00%, IQR 15.00%-42.00% vs 5.00%, IQR 0.00%-28.00%; Z=-4.24, P<.001), and reduced novelty preference ratio (median 1.44, IQR 0.97-1.70 vs 2.12, IQR 1.27-4.56; Z=-3.44, P=.001). Multivariable analysis identified 4 independent predictors of 3-month PSCI: older age (odds ratio [OR] 1.067 per year, 95% CI 1.009-1.129; P=.02), lower education level (OR 0.841 per year, 95% CI 0.708-0.999; P=.049), higher NIHSS (National Institutes of Health Stroke Scale) scores (OR 1.557 per point, 95% CI 1.075-2.256; P=.02), and prolonged correct saccade latency (OR 1.004 per ms, 95% CI 1.000-1.007; P=.04). A nomogram incorporating these 4 factors achieved good discriminative performance (area under the receiver operating characteristic curve 0.86, 95% CI 0.793-0.927) with satisfactory calibration. Conclusions:Age, education, admission NIHSS, and correct saccade latency were identified as possible independent predictors of 3-month PSCI in this cohort. The tablet-based eye-tracking system, when combined with clinical variables, may represent a feasible approach for early PSCI screening. A nomogram based on these variables demonstrated high accuracy and potential clinical utility for early PSCI identification. This approach may facilitate early identification of high-risk patients and enable timely, personalized interventions in resource-limited settings.
