Mobile Apps Research Articles

Utility of mobile phone app-assisted screening for heart failure and heart stress in primary care

Abstract Background As heart failure (HF) still has a similar prognosis to some of the most common cancers, a timely diagnosis of HF is of paramount importance. We sought to determine whether a mobile phone app can facilitate screening for HF in primary care. Material and methods The national echocardiographic society conducted a multicenter screening programme for HF in which general practitioners from 13 primary care centres used a mobile phone app to decide whether patients without a prior HF diagnosis should be referred to one of the 6 university hospitals for transthoracic echocardiography (TTE) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) testing. The app would recommend further testing (TTE and NT-proBNP) to patients with symptoms potentially associated with HF, atrial fibrillation, pathologic electrocardiogram (ECG), previous myocardial infarction or exposure to cardiotoxic cancer therapies, or at least two other risk factors listed in Figure (left panel). Patients with signs of HF were not eligible for the programme. The algorithms proposed in the 2021 ESC guidelines were used to diagnose HF across the entire spectrum of left ventricular ejection fraction (EF). Results Of the 930 screened outpatients (mean age 66±11 years, age range 21-91 years, 61% female), 318 symptomatic patients (34.2%) were diagnosed with new HF (Figure). HF with preserved (HFpEF) was diagnosed more frequently than HF with mildy reduced (HFmrEF) and reduced EF (HFrEF). Heart stress, defined as elevated plasma NT-proBNP in asymptomatic individuals with risk factors irrespective of the presence or absence of structural heart disease or cardiac dysfunction, was found in 22.3% (Figure, right panel). In multivariate regression analysis, advanced age, atrial fibrillation, pathological ECG, long-standing history of arterial hypertension and chronic kidney disease were independently associated with HF, while other risk factors were not (Figure, middle panel). Conclusions Screening in primary care based on symptoms and risk factors, facilitated by a mobile phone app, resulted in a new HF diagnosis in approximately one third of screened patients, with the majority of them having HFpEF. Recalibration of the referral criteria might further improve the performance of the app for screening purposes.

Trajectories of physical activity among participants of six-month mobile app-based disease management program for cardiovascular risk: a group-based trajectory modelling approach

Abstract Background Mobile app-based health promotion is an emerging preventive intervention for cardiovascular disease that allows for the frequent and longitudinal monitoring of physical activity (PA). Previous studies exploring PA trajectories categorized participants in a limited number of follow-up assessments and did not consider dynamic nature with changes that occur over the intervention period. Purpose This study explored the trajectories of PA during mobile app-based disease management programs in adults with cardiovascular risk using group-based trajectory modelling (GBTM). Methods Participants who completed a six-month disease management program using a mobile app were enrolled. The program promoted behavioural changes for the management of cardiovascular risk factors in individuals with one or more of hypertension, diabetes, or dyslipidaemia. Daily step count was measured using a wrist-worn activity tracker (Fitbit devices). Each participant was encouraged to wear a tracker for the monitoring of exercise and physical activity. To analyse relatively physically inactive participants, we included those with baseline step count <8,000 steps/day. GBTM was conducted to identify distinct patterns of longitudinal step count changes of baseline, 3-22 weeks, and 24 weeks. Participants with PA measurements <4 time points were excluded. The baseline characteristics and indicators related to mobile app usage during the first two weeks were compared among the trajectory groups. Results A total of 1,760 participants were included in the analysis (age: median 55 years; 83.8% men; body mass index (BMI): median 27.0 kg/m²; baseline step count: median 6,118 steps/day). GBTM identified four step count trajectory groups: rapid increase (T1, rapid increase in the first three months; 5%), gradual increase (T2, gradual increase in the first three months; 24%), moderate activity (T3, maintained at around 7,000 steps/day; 45%), and physically inactive (T4, around 4,500 steps/day throughout the program; 26%) (Figure 1). The trajectory groups that showed increasing PA patterns were older (T1: median 57 years; T2: 55 years; T3: 55 years; T4: 54 years; p=0.040) with a lower baseline BMI (T1: median 26.6 kg/m²; T2: 26.4 kg/m²; T3: 27.0 kg/m²; T4: 27.7 kg/m²; p<0.001) and were predominantly men (T1: 89.5%; T2: 87.4%; T3: 82.8%; T4: 81.1%; p=0.028). PA increasing patterns were associated with a longer time of mobile app use (T1: median 8.5 min/day; T2: 5.5 min/day; T3: 5.5 min/day; T4: 4.9 min/day; p=0.012) and more login times (T1: median of daily average 3.9/day; T2: 3.0/day; T3: 3.1/day; T4: 2.9/day; p=0.003) during the first two weeks of the program. Conclusions GBTM showed that 30% of participants in the mobile app-based intervention showed significant PA improvement during the first 12 weeks. Results of this study suggest that the response to PA intervention may be associated with lifestyle prior to the program and willingness to use the mobile app.Figure 1.Step count trajectories

Can mobile apps facilitate more sustainable and healthier diets? A systematic review

Abstract Background One third of all greenhouse gas emissions come from the food system, and current diets are insufficient to meet environmental and public health goals. Digital health apps offer promise to change behaviour, but little is known about the effects of different types of apps. This systematic review assessed the effectiveness of mobile apps in facilitating dietary changes across adults from high-income countries. Methods Seven electronic databases (MEDLINE, EMBASE, PsycINFO, CINAHL, Global Health, GreenFILE, Web of Science), two trial registries (Cochrane Trials and Clinicaltrials.gov), and Google were systematically searched for intervention studies aiming to facilitate dietary change. Interventions were characterised by their use of messaging (e.g., motivational statements) and personalised features (e.g., tailored nutrition advice). Outcomes for three food groups were synthesised through meta-analysis. Results Of the 5261 identified records, 21 met the eligibility criteria and were included. Interventions, recruiting 73,973 participants in total, lasted from three days to six months. Overall positive changes were observed in daily servings of fruit and vegetables (0.59, 95% CI 0.20, 0.99), legumes (0.05, 95% CI 0.01, 0.08), and meat (-0.14, 95% CI -0.23, -0.05), remaining significant after removing non-randomised controlled trials. Changes in fruit and vegetable intake were more pronounced for users of apps with messaging components (0.75, 95% CI 0.18, 1.32) and personalisation (0.67, 95% CI 0.16, 1.19), and meat intake changes were larger for messaging-based apps (-0.21, 95% CI -0.27, -0.15) than apps without these features. Conclusions Our findings suggest to practitioners and policymakers that mobile apps could be a useful and innovative way to change behaviour. Within a wider behaviour change approach, apps could help facilitate diets that meet food-based dietary guidelines, are predominantly plant-based, and are protective of environmental and human health. Key messages • Overall, the results from 21 studies showed positive dietary changes towards more fruits, vegetables, and legumes and less meat consumption following the use of mobile apps. • Apps including messaging and personalised elements appeared most effective and may be important for driving changes in fruits, vegetables, and meat consumption.

Acceptability of Digital Mental Health Interventions for Depression and Anxiety: Systematic Review.

Depression and anxiety disorders are common, and treatment often includes psychological interventions. Digital health interventions, delivered through technologies such as web-based programs and mobile apps, are increasingly used in mental health treatment. Acceptability, the extent to which an intervention is viewed positively, has been identified as contributing to patient adherence and engagement with digital health interventions. Acceptability, therefore, impacts the benefit derived from using digital health interventions in treatment. Understanding the acceptability of digital mental health interventions among patients with depression or anxiety disorders is essential to maximize the effectiveness of their treatment. This review investigated the acceptability of technology-based interventions among patients with depression or anxiety disorders. A systematic review was performed based on PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and PROSPERO (International Prospective Register of Systematic Reviews) guidelines. We searched PubMed, Web of Science, and Ovid in May 2022. Studies were included if they evaluated digital interventions for the treatment of depression or anxiety disorders and investigated their acceptability among adult patients. Studies were excluded if they targeted only specific populations (eg, those with specific physical health conditions), investigated acceptability in healthy individuals or patients under the age of 18 years, involved no direct interaction between patients and technologies, used technology only as a platform for traditional care (eg, videoconferencing), had patients using technologies only in clinical or laboratory settings, or involved virtual reality technologies. Acceptability outcome data were narratively synthesized by the direction of acceptability using vote counting. Included studies were evaluated using levels of evidence from the Oxford Centre for Evidence-Based Medicine. The risk of bias was assessed using a tool designed for this review and GRADE (Grading of Recommendations, Assessment, Development, and Evaluation). A total of 143 articles met the inclusion criteria, comprising 67 (47%) articles on interventions for depression, 65 (45%) articles on interventions for anxiety disorders, and 11 (8%) articles on interventions for both. Overall, 90 (63%) were randomized controlled trials, 50 (35%) were other quantitative studies, and 3 (2%) were qualitative studies. Interventions used web-based programs, mobile apps, and computer programs. Cognitive behavioral therapy was the basis of 71% (102/143) of the interventions. Digital mental health interventions were generally acceptable among patients with depression or anxiety disorders, with 88% (126/143) indicating positive acceptability, 8% (11/143) mixed results, and 4% (6/143) insufficient information to categorize the direction of acceptability. The available research evidence was of moderate quality. Digital mental health interventions seem to be acceptable to patients with depression or anxiety disorders. Consistent use of validated measures for acceptability would enhance the quality of evidence. Careful design of acceptability as an evaluation outcome can further improve the quality of evidence and reduce the risk of bias. Open Science Framework Y7MJ4; https://doi.org/10.17605/OSF.IO/SPR8M.

A comparative analysis of conventional echocardiographic findings among different heart failure stages and phenotypes: insights from the national echocardiographic society registry

Abstract Background The contemporary conceptualization of heart failure (HF) encompasses four developmental stages (at risk for HF, pre-HF, symptomatic HF, and advanced HF) and three distinct HF phenotypes categorized by left ventricular ejection fraction (LVEF) (HFpEF, HFmrEF, HFrEF). However, there is a need for a more comprehensive understanding of echocardiographic similarities and differences among pre-HF stages and various HF phenotypes. Material and Methods Our national echocardiographic society conducted a multicenter HF screening initiative. General practitioners in 13 primary care centers utilized the original mobile phone app to determine referrals for transthoracic echocardiography and N-terminal pro-B-type natriuretic peptide (NT-proBNP) testing in individuals without a prior HF diagnosis. The 2021 ESC guidelines' algorithms were used to diagnose HF phenotypes and 2016 EACVI/ASA recommendation² to assess diastolic function. This study defined "heart stress" (elevated NT-proBNP in asymptomatic individuals with risk factors, regardless of structural heart disease or cardiac dysfunction) and "patients at risk for HF" (normal NTproBNP and at least one HF risk factor). All patients were categorized into six groups: (I) no HF, no risk, (II) at risk for HF, (III) heart stress, (IV) HFpEF, (V) HFmrEF, and (VI) HFrEF. Echocardiographic findings were compared among groups (II) to (VI), using ANOVA, Kruskal-Wallis and Chi-squared test, when needed. Results In a cohort of 930 outpatients (mean age 66±11 years, 61% female), 34.2% were diagnosed with HF, 22.3% experienced heart stress, 37.8% were at risk for HF, and 12.8% had neither HF nor risk factors (Figure). While NT pro BNP showed progressive increase, LVEF showed a progressive decline across the groups, reaching its lowest in HFrEF patients (Table). Simultaneously, left ventricular mass index (LVMi), left atrial volume index (LAVi), and maximal velocity of tricuspid regurgitation (TR Vmax) significantly increased in a stepwise manner. Variations in predominant LV geometry were significant across groups (p<0.001): normal LV geometry in those without HF (60.8%), concentric LV remodeling in at-risk patients (38.6%), normal LV geometry in heart stress (49%), concentric LV hypertrophy (LVH) in HFpEF (27.7%), eccentric LVH in HFmrEF (42.3%), and both concentric and eccentric LVH in HFrEF (43.3% each). Diastolic dysfunction increased prevalence across the groups (12.9% vs 24.7% vs 37.6% vs 19.6% vs 51.1%, p<0.001). Remarkably, HFmrEF group had the highest proportion of undetermined diastolic function (14.7% vs 23.1% vs 27.9% vs 50% vs 26.7%, p<0.001). Conclusions The mobile phone app used in primary care setting allowed identification of significant number of individuals in the pre-HF stages, warranting further investigation. Distinct echocardiographic differences in pre-HF stages and HF phenotypes provide valuable insights for early detection and tailored treatments.

Prediction of mental health risk in adolescents via a smartphone app: a feasibility pilot study

Abstract Background The prevalence of mental health problems in adolescents is a global public health concern. Machine learning (ML) can analyse multidimensional data collected by phone sensors (passive tracking) and symptom self-reporting (active tracking) to model and predict mental health states. However, research in adolescents is lacking. This study investigated the feasibility of using ML to predict mental health in a non-clinical population of adolescents from active and passive data collected through the Mindcraft mobile app. Methods We recruited 103 secondary students (aged 14-18) who first completed the Strengths and Difficulties Questionnaire (SDQ) and then used the Mindcraft app for two weeks. The app integrates sensor data (location, steps, noise, light, battery, app usage) and self-reports. We extracted 85 sensor-based features and 19 from questionnaires to develop a gradient-boosted ensemble ML model. This model identifies students with abnormal SDQ scores and was evaluated using leave-one-out cross-validation. Results All students completed the active questionnaires; 67 also provided passive sensor data. 31 had abnormal SDQ scores. Using passive data, the ML model reached a balanced accuracy of 0.64 and an AUC score of 0.57. Incorporating both data types improved accuracy to 0.67 and AUC to 0.70. Feature importance scores showed step count and questionnaire on racing thoughts and hopefulness as most significant. Conclusions Our findings affirm the potential of integrating passive and active data collection to monitor mental health in real-world settings. Our ML model demonstrated moderate accuracy in predicting adolescents’ mental health risk measured with a behavioural screening questionnaire. This study will guide the development of a ML-driven, personalised mobile intervention for early symptom detection and mental health self-management, which might constitute an innovative and scalable tool for mental health prevention and intervention in adolescents. Key messages • This study shows the feasibility of using active and passive data to predict mental health risk in adolescents. • This study informs the development of a personalised machine learning-driven mobile intervention.

Narrative Literature Review: Digital-based Post-Operative Pain Management Innovation

Effective postoperative pain management is a key element in patient recovery after surgery, but often standard protocols do not take advantage of the potential of real-time data and digital technology for more responsive therapy adjustments. The aim of this study was to identify the latest innovations in digital-based postoperative pain management. A literature review examined the use of digital technology in postoperative pain management, focusing on smartphone apps, wearable devices, and real-time data analytics for monitoring patient pain with the keywords "Pain Management AND Digital Postoperative" OR "Digital Health AND Pain Management" AND "Technology" OR "Information Systems". The year of the source of the literature taken is 2019-2024. Database searches use Scopus, Pub Med, Sage Journal, and Google Scholar. The findings of this review suggest that the integration of digital technology in postoperative pain management can improve the personalization of care by allowing for more accurate and responsive therapy adjustments to changes in patients' pain conditions. Data-Based Approaches in the Digital Era are Virtual Reality (VR), PASHA Application (pain assessment, stimulating and healing application), A wireless intelligent PCA (Wi-PCA) AI (Artificial Intelligence), Cell Phone Application, Wearable Devices, Mhealth, NeuroCuple, LINE, Digital Intervention Group, The Panda App and A Digital Application. Wearable apps and devices effectively monitor pain and enable real-time therapy adjustments. Digital-based innovation can be used as an alternative nursing intervention for post-operative pain management.

Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study

ImportanceDecision-making in trauma patients remains challenging and often results in deviation from guidelines. Machine-Learning (ML) enhanced decision-support could improve hemorrhage resuscitation.AimTo develop a ML enhanced decision support tool to predict Need for Hemorrhage Resuscitation (NHR) (part I) and test the collection of the predictor variables in real time in a smartphone app (part II).Design, setting, and participantsDevelopment of a ML model from a registry to predict NHR relying exclusively on prehospital predictors. Several models and imputation techniques were tested. Assess the feasibility to collect the predictors of the model in a customized smartphone app during prealert and generate a prediction in four level-1 trauma centers to compare the predictions to the gestalt of the trauma leader.Main outcomes and measuresPart 1: Model output was NHR defined by 1) at least one RBC transfusion in resuscitation, 2) transfusion ≥ 4 RBC within 6 h, 3) any hemorrhage control procedure within 6 h or 4) death from hemorrhage within 24 h. The performance metric was the F4-score and compared to reference scores (RED FLAG, ABC). In part 2, the model and clinician prediction were compared with Likelihood Ratios (LR).ResultsFrom 36,325 eligible patients in the registry (Nov 2010—May 2022), 28,614 were included in the model development (Part 1). Median age was 36 [25–52], median ISS 13 [5–22], 3249/28614 (11%) corresponded to the definition of NHR. A XGBoost model with nine prehospital variables generated the best predictive performance for NHR according to the F4-score with a score of 0.76 [0.73–0.78]. Over a 3-month period (Aug—Oct 2022), 139 of 391 eligible patients were included in part II (38.5%), 22/139 with NHR. Clinician satisfaction was high, no workflow disruption observed and LRs comparable between the model and the clinicians.Conclusions and relevanceThe ShockMatrix pilot study developed a simple ML-enhanced NHR prediction tool demonstrating a comparable performance to clinical reference scores and clinicians. Collecting the predictor variables in real-time on prealert was feasible and caused no workflow disruption.

Smartphone application for improving self-awareness of adherence to edoxaban treatment: a randomised controlled trial (ADHERE-APP)

Abstract Background Adherence to oral anticoagulants is essential for stroke prevention in patients with atrial fibrillation (AF). This study aims to test the feasibility and effectiveness of the smartphone app-based intervention to improve drug adherence in patients with AF. Methods This prospective, randomised, open-label, multicentre trial (ADHERE-APP) enrolled a total of 502 patients at 9 university hospitals in South Korea from November 2021 to January 2023. Patients with AF aged ≥19 years requiring oral anticoagulation,and were treated with edoxaban were enrolled. Patients were randomized in a 1:1 ratio to the conventional treatment group and the app conditional feedback group. Patients in the app conditional feedback group used a smartphone application that pushed alarms for taking medication and measuring blood pressure (BP) and heart rate (HR) at specific times of the day. In addition to medication alarms, the habit of measuring one’s BP and HR could improve drug adherence by increasing self-awareness of the disease. The automatic BP machine was connected to the smartphone via Bluetooth and the measured BP and HR were automatically updated on the smartphone app. The primary endpoint was adherence to edoxaban as measured by pill count at 12 and 24 weeks. In addition, we evaluated the differential effect of the smartphone application by age on the primary endpoint. Results Among the 502 patients, the mean age was 66.0±10.0 years and 67.7% were male. Of the 372 patients who completed 12-weeks trial, edoxaban adherence at 12 weeks was high in both arms, with no difference in the primary outcome (96.5% [92.5%-100.0%] vs. 98.0% [93.2%-99.5%], P = 0.488). or in secondary outcomes, including the proportion of patients achieving adherence ≥ 80% or 95%. In patients aged >65 years, adherence to edoxaban was higher in the app conditional feedback group than in the conventional treatment group (95.8% [93.0%-99.5%] vs. 98.0% [95.8%-99.5%], P = 0.049). Conclusions Overall adherence to edoxaban was much higher than expected in patients with AF. There was no difference in edoxaban adherence between the app conditional feedback group and the conventional treatment group, however, in older patients, app feedback increased medication adherence.

Exploring the Potential of Electronic Patient-Generated Health Data for Evaluating Treatment Response to Intramuscular Steroids in Rheumatoid Arthritis: Case Series.

Mobile health devices are increasingly available, presenting exciting opportunities to remotely collect high-frequency, electronic patient-generated health data (ePGHD). This novel data type may provide detailed insights into disease activity outside usual clinical settings. Assessing treatment responses, which can be hampered by the infrequency of appointments and recall bias, is a promising, novel application of ePGHD. Drugs with short treatment effects, such as intramuscular steroid injections, illustrate the challenge, as patients are unlikely to accurately recall treatment responses at follow-ups, which often occur several months later. Retrospective assessment means that responses may be over- or underestimated. High-frequency ePGHD, such as daily, app-collected, patient-reported symptoms between clinic appointments, may bridge this gap. However, the potential of ePGHD remains untapped due to the absence of established definitions for treatment response using ePGHD or established methodological approaches for analyzing this type of data. This study aims to explore the feasibility of evaluating treatment responses to intramuscular steroid therapy in a case series of patients with rheumatoid arthritis tracking daily symptoms using a smartphone app. We report a case series of patients who collected ePGHD through the REmote Monitoring Of Rheumatoid Arthritis (REMORA) smartphone app for daily remote symptom tracking. Symptoms were tracked on a 0-10 scale. We described the patients' longitudinal pain scores before and after intramuscular steroid injections. The baseline pain score was calculated as the mean pain score in the 10 days prior to the injection. This was compared to the pain scores in the days following the injection. "Response" was defined as any improvement from the baseline score on the first day following the injection. The response end time was defined as the first date when the pain score exceeded the pre-steroid baseline. We included 6 patients who, between them, received 9 steroid injections. Average pre-injection pain scores ranged from 3.3 to 9.3. Using our definitions, 7 injections demonstrated a response. Among the responders, the duration of response ranged from 1 to 54 days (median 9, IQR 7-41), average pain score improvement ranged from 0.1 to 5.3 (median 3.3, IQR 2.2-4.0), and maximum pain score improvement ranged from 0.1 to 7.0 (median 4.3, IQR 1.7 to 6.0). This case series demonstrates the feasibility of using ePGHD to evaluate treatment response and is an important exploratory step toward developing more robust methodological approaches for analysis of this novel data type. Issues highlighted by our analysis include the importance of accounting for one-off data points, varying response start times, and confounders such as other medications. Future analysis of ePGHD across a larger population is required to address issues highlighted by our analysis and to develop meaningful consensus definitions for treatment response in time-series data.

Mobile-Based Platform With a Low-Calorie Dietary Intervention Involving Prepackaged Food for Weight Loss for People With Overweight and Obesity in China: Half-Year Follow-Up Results of a Randomized Controlled Trial.

Obesity is a rapidly increasing health problem in China, causing massive economic and health losses annually. Many techniques have emerged to help people with obesity better adhere to intervention programs and achieve their weight loss goals, including food replacement and internet-delivered weight loss consultations. Most studies on weight loss interventions mainly focused on the change in body weight or BMI; however, body fat, especially visceral fat mass, is considered the main pathogenic factor in obesity. In China, more reliable evidence is required on this topic. Moreover, it is unclear whether an integrated weight loss program combining food replacement products, mobile app-based platforms, and daily body composition monitoring using a wireless scale is useful and practical in China. In this 2-arm, parallel-designed, randomized study, we explored the effectiveness and safety of the Metawell (Weijian Technologies Inc) weight loss program in China, which combines prepackaged biscuits, a wireless scale, and a mobile app. Participants in the intervention group were guided to use food replacement products and a scale for weight loss and monitoring, whereas participants in the control group received printed material with a sample diet and face-to-face education on weight loss at enrollment. The intervention lasted for 3 months, and follow-up visits were conducted at months 3 and 6 after enrollment. Dual-energy x-ray absorptiometry and quantitative computed tomography were used to assess body fat. A multilevel model for repeated measurements was used to compare differences between the 2 groups. In total, 220 patients were randomly assigned to intervention (n=110) and control (n=110) groups. Participants in the intervention group had significantly greater decreases in BMI, total body fat, visceral adipose area, and subcutaneous adipose area (all P<.001) than those in the control group. However, the rate of change in lean mass was not significantly different between the 2 groups (P=.62). Further, 35 participants in the intervention group reported adverse events. Constipation was the most frequently reported adverse event (11/110), followed by dizziness (6/110), hypoglycemia (4/110), fatigue (3/110), and gastritis (3/35). The Metawell program was effective for weight loss. After the intervention, participants in the intervention group lost more body weight and body fat while retaining muscle mass than those in the control group.

User technology for AI-supported objective measurement of Work-related Quality of Life (MI-LQ)

Abstract Background Understanding and enhancing job satisfaction is crucial for improving Work-Related Quality of Life (WrQoL) in today’s office work environments. Our work uses multimodal data collection and analysis techniques to objectively assess WrQoL, thus mitigating respondent bias and survey fatigue. Leveraging machine learning (ML) and automated methods measuring WrQoL presents a promising approach in public health research, particularly concerning stress-related health outcomes. Methods Through a systematic literature search of 9,242 publications to identify WrQoL indicators, we selected over 100 publications for data extraction. A base model, including workload, commute, overtime, valence, and arousal was formulated. To amass a wide data set, Objective measurement tools (computers, smartphones, and wearables) complemented by questionnaire data. This data will inform ML algorithms to predict individual WrQoL indicators. Developed as an input/output data platform, an app-prototype will objectively assess WrQoL, facilitating a field study with office workers to refine the model. A mobile app prototype serves as a user interface and data relay for WrQoL metric analysis. Results Our research develops instruments for measuring WrQoL using smartphones, wearables, and specialized trackers for heart rate variability (HRV) analysis, alongside a software prototype for keyboard and mouse tracking for workload assessment of valence and arousal. Fitness trackers with photoplethysmography functionality are favored for HRV assessment. Conclusions The systematic search identified influences on WrQoL, translated into measurable indicators in a base model. Leveraging user tech for assessment and a ML and mobile app framework, this approach facilitates objective WrQoL determination. By presenting the relationship between digital service use and WrQoL indicators, this methodology promises new insights, informing stress and burnout prevention strategies within public health initiatives. Key messages • Progressive approach: ML-driven WrQoL assessment offers promising avenues for stress prevention in workplace health research. • Methodological Advancement: The novel framework for WrQoL assessment using digital tools contributes to effective workplace health promotion strategies, with potential for tailored interventions.

Exploring vocal biomarkers as non-invasive fine-tuning assays of cardiovascular health: heart failure model

Abstract Background Mobile health (mHealth) technologies offer a promising avenue for non-invasive heart failure monitoring through vocal biomarkers. The relationship between feature changes in anonymous and standardized voice recordings of heart failure patients and the NYHA scores of the same patients is assessed, aiming to identify vocal biomarkers as delicate indicators of chronic noncommunicable disease progression and/ or fluctuation. Methods In a cardiology outpatient setting, 55 chronic heart failure patients provided voice recordings via a mobile app, performing specific vocal tasks prospectively. We analyzed waveforms visually via Mel spectrograms and extracting features by audio processing, focusing on chroma centroids and tonnetz measurements across 147 clinical and laboratory parameters (Mean NYHA: 2.62, SD: 0.56). Applying Ordinary Least Squares (OLS) test, we assessed the relevance of spectral bandwidth mean (0.04), spectral bandwidth std (0.00), spectral roll-off std (0.011) between NYHA scores, given each p-score &amp;lt; 0.05. Results 147 voice recordings taken from 55 patients were analyzed to examine whether there were any correlations between changes in the voice recordings and NYHA scores. OLS test underscored the significance of spectral bandwidth mean (0.04), spectral bandwidth std (0.00), spectral roll-off std (0.011) between NYHA scores with p-value &amp;lt; 0.05. These findings show the potential role of multiple vocal features in reflecting heart failure progression and/or fluctuation. Analysis based on the clinical status progression from NYHA 2 to NYHA 3 over time showed notable changes in chroma centroids (mean = 0.006, std = 0.174, skew = 0.179, kurtosis = 0.205) and tonnetz (mean = 0.023, std = 0.131, skew = 0.023, kurtosis = 4.247). Conclusion This investigation highlights vocal biomarkers' potential in heart failure management, offering insights into non-invasive monitoring techniques and shows the importance of standardised recording procedures and patient engagement for data integrity. Future directions include quantifying vocal changes' correlation with clinical status and integrating additional parameters (e.g., edema, weight) to enhance predictive models for personalised care.Vocal features according to NYHA scores

Health promotion interventions for children and adolescents using e-health: a systematic review

Abstract Background The utilization of e-health in healthcare interventions has become increasingly prevalent due to its cost-effectiveness. Nevertheless, there is a paucity of evidence regarding the use of e-health in children, as the majority of e-health interventions are focused on adults. This study aimed to identify the components and effects of e-health intervention for the promotion of children’s health and to suggest strategies for their implementation. Methods A systematic review was conducted in accordance with the PRISMA guidelines. A literature review of relevant studies published between January 2013 and November 2023 was conducted. A search of databases including PubMed, EMBASE, CINAHL, MEDLINE, and Cochrane Review Library was conducted using a combination of medical subject headings (MeSH) and keywords. A qualitative appraisal of the studies was conducted using the revised Cochrane risk-of-bias tool for randomized trials (RoB 2). Results Sixteen studies were selected. Most studies showed good methodological quality. The majority of studies (n = 15) focused on improving children’s physical health, while only one study focused on mental health. There were a variety of components to the intervention, including internet education, web-based home-exercise, serious games, mobile apps, email counseling, and active video games, and only one type of intervention was provided, or a combination with additional methods such as phone calls and counseling. A review of the literature indicates that e-health interventions have been effective in increasing children’s physical activity, reducing weight, relieving stress, and reducing depression. Conclusions This study identified the effectiveness of e-health interventions for improving children’s physical and mental health. The use of e-health to promote children’s health should be actively developed and implemented in a variety of clinical and community settings. Key messages • E-health interventions have been demonstrated to be an effective means of improving the physical and mental health of children and adolescents. • It is recommended that health promotion interventions utilizing e-health be developed and tested in a variety of communities and settings for children and adolescents.

The future of nutrition education for health systems capacity building

Abstract In the ever-evolving landscape of global health, nutrition education plays a pivotal role in shaping the well-being of populations. The future of nutrition education encompasses a holistic understanding of health, considering not nutritional adequacy in health and disease, but also cultural, social, and environmental factors. Tomorrow’s health professionals must also be equipped to address the interconnectedness of nutrition with mental health, sustainability, and community dynamics. Nutrition education will increasingly involve collaboration across disciplines. Health professionals, educators, policymakers, and community leaders must work together to create a comprehensive ecosystem that fosters nutrition literacy. This collaboration extends beyond traditional healthcare settings to schools, workplaces, and local communities. Furthermore, digital transformation will also revolutionise nutrition education. Online platforms, mobile apps, and virtual simulations will enhance learning experiences whilst interactive modules, webinars, and gamified content will engage learners and facilitate continuous professional development. Moreover, telehealth and tele-nutrition will bridge geographical gaps, ensuring access to quality education globally. Cultural sensitivity in nutrition education is also needed across geo-demographic boundaries to appreciate diverse dietary practices, food taboos, and traditional knowledge. Nutrition education should also empower health professionals to advocate for policy change across food systems, promote sustainable practices, and address food insecurity and therefore understanding policy frameworks and participating in advocacy efforts will be key. Finally, embracing the future requires a commitment to lifelong learning to remain at the forefront of nutrition science and its cutting edge as the questions may remain the same but the answers vary significantly as we garner new evidence to navigate evolving global challenges.

Development of a first intervention for tobacco cessation for sexual and gender minority individuals in Romania

Abstract Background Data on tobacco use among SGM in Romania indicate high use rates, yet tailored smoking cessation efforts do not exist. We collected data from SGM individuals in Romania on tobacco use and cessation attitudes, facilitators and barriers to quitting, and intervention components acceptability to inform the first smoking cessation intervention for SGM in Romania, adapted from a U.S.-based intervention with mobile app support. Methods SGM individuals (≥ 18 years old, current smokers) recruited through community outreach in March 2024 completed a brief assessment and participated in a focus group regarding tobacco use, attitudes, norms, risks knowledge, facilitators and barriers to quitting, and intervention acceptability. Results Focus groups were held with 36 participants characterized as 45% cis male, 40% gender-diverse, 15% cis female; 40% gay, 33% bisexual, 10% queer, 8% pansexual; 6% lesbian, 3% heterosexual; M age=27, SD = 7.62. 70% smoked daily; median age of first cigarette was 17. Participants reported smoking up to 2 packs a day, with 50%-98% of people in their circles being smokers. Common reasons for smoking included to alleviate stress and “fit in.” Most did not receive support to quit from their social circles or within healthcare. While smoking was communal, quitting was individual and siloed, suggesting a preference for a group-based intervention, along with robust strategies to replace the function of smoking with adaptive habits. The app was evaluated positively, especially for its daily smoking tracking, reminders for alternative healthy activities, positive achievements, and forum for support. Conclusions Findings provide a solid platform for creating a first smoking cessation intervention for SGM individuals in Romania. Next steps include iterative testing of the mobile app to examine comprehension, usability, and satisfaction with content and functionality, in preparation for a randomized controlled trial testing the intervention’s efficacy.

Digital Health Literacy Enhancement Strategies Across Diverse Groups: A Scoping Review

Abstract Background The COVID-19 pandemic has accelerated the use of digital health technologies. Digital health literacy (DHL) is essential for effectively understanding and applying electronic health information. However, unequal access and use of these technologies require interventions to improve DHL for fair healthcare access. Objectives This scoping review aimed to identify strategies to enhance DHL in patients and the general population. Methods The review used the Joanna Briggs Institute Scoping Review Methodology and PRISMA-ScR guidelines. Eligibility criteria included a wide population, interventions aimed at improving DHL, with no restrictions on outcomes. The search strategy included electronic databases (MEDLINE, PsycINFO, Web of Science), and AI-based software, AS Review, was used for screening. Results The review found 5149 articles, 44 met the eligibility criteria. Studies focused on different demographic groups and health conditions. Most interventions were in North America and Europe. The study designs varied. Interventions via mobile apps, online platforms, and in-person sessions aimed at various conditions yielded positive results, including increases in DHL, self-management skills, and health-related behaviors. These interventions involved either independent interventions that focused on DHL or integrated interventions that were part of another intervention that aimed at a health outcome and had an element of DHL enhancement. Conclusions The review highlights the importance of DHL in informed decision-making and navigating digital health environments. While many interventions had positive outcomes, methodological limitations challenge the findings, emphasizing the need for more rigorous study designs. Future research should address sustainability, scalability, and the impact of DHL on health disparities, considering cultural sensitivity when developing interventions. Key messages • Scoping review identifies strategies to enhance Digital Health Literacy (DHL), crucial for effective use of health technology. • Despite positive outcomes, methodological limitations exist. Future research should focus on sustainability and scalability.

Cross-cultural study on social media usage and its correlation with mental health and family functioning

Social media has the potential to influence both mental health and family dynamics significantly. However, there is limited research on the relationship between social media usage, mental health, and family functioning. To address this gap, we developed a novel mobile app, Social Brain, and conducted a study with 563 social media users to evaluate their preferences for the app's interface and functionality. The user-preference app design was validated with a separate study involving 65 social media users.The Social Brain app provides personalized, visually engaging weekly reports on users’ mental health, family functioning, and social media usage patterns. Participants from Saudi Arabia, Malaysia, and the United Kingdom were recruited to use the app for four weeks. A detailed survey conducted with 25 participants revealed significant correlations: mental health was notably associated with marital and employment status, while family functioning was linked to marital status, nationality, employment status, and religion.Our results indicated a significant decrease in mean mental health scores after using the Social Brain app compared to pre-app usage assessments (2.11 ± 0.49 vs. 25.28 ± 5.72, P < 0.001). This finding highlights the need to view technology as a complement rather than a replacement for traditional mental health approaches. Our study offers valuable insights into the complex relationship between social media usage, mental health, and family functioning, suggesting pathways for future interventions at this intersection.

Unveiling User Sentiment: Aspect-Based Analysis and Topic Modeling of Ride-Hailing and Google Play App Reviews

Background: Mobile app usage is increasing in the digital age, with Ride-Hailing app becoming the primary example of this trend. To obtain valuable understanding of how people perceive and interact with mobile app, user reviews on platforms such as Google Play are usually analyzed. This analysis can assist developers to identify areas for improvement in both Ride-hailing and Google Play App. A promising method that can be used to analyze user perception in this instance is Aspect-Based Sentiment Analysis (ABSA). Objective: This research aimed to apply ABSA to user reviews using Bidirectional Encoder Representations from Transformers (BERT) models. In this context, aspect identification and topic modeling were performed by using Latent Dirichlet Allocation (LDA). The model extracted topics from the reviews and used Generative Artificial Intelligence (GenAI) to define the aspects of the topics to further enhance the analysis. For consistency and accuracy, the method included sentiment annotation by a human annotator. Methods: A total of two datasets were used in this research, with the first collected by scraping user reviews of Ride-Hailing App while the second was obtained from Kaggle, and to identify relevant topics, modeling was performed using LDA. These topics were then categorized into aspects using GenAI, covering areas, such as customer experience, service, payment, app features, task management, and event management. Subsequently, sentiment labeling was conducted using human annotators to provide a reliable baseline. BERT model was then used to classify sentiment with aspect hints, and the evaluation included calculations of accuracy, precision, recall, and F1-score. Results: The results showed that BERT model achieved the highest accuracy of 97% in sentiment analysis across all datasets. Conclusion: This research provided valuable understanding of user experience and established a strong ABSA framework for analyzing user reviews using LDA, Aspect Annotation, GenAI, and BERT sentiment models. Future research could expand this method to other app categories and incorporate real-time ABSA for continuous monitoring and dynamic feedback. Keywords: User Reviews, Aspect-Based Sentiment Analysis (ABSA), Sentiment Analysis, Topic Modeling, Generative Artificial Intelligence (GenAI)

Managing a 4000-participant cohort with a novel mobile app: data from the RisCoin study in Germany

Abstract Issue RisCoin, a prospective monocentric longitudinal observational study, aimed to identify risk factors for COVID-19 vaccine failure. Secondary aim is to monitor symptoms, SARS-CoV-2 infection, vaccination status of 3816 enrolled healthcare workers (HCW) and 180 patients with inflammatory bowel disease (IBD). Since the LMU University Hospital Munich served both as study sponsor and employer of the HCW, a secured approach was required. Description of the solution Participants accessed the study app (CentraXX, KAIROS GmbH, Germany) via pseudonymized Contact-ID with irreversible anonymization after 6 months. Key app features were the serological results report, bidirectional messaging, and weekly survey for self-reported data on vaccinations, infections, and symptoms. Active app use was defined as submitting &amp;gt;1 weekly survey during the study period 10.2021-12.2022. Results Over 15 months, our study team maintained 1964 two-way communications with 958 participants via the app. Of 3979 participants with app access, 3622 (91%) were active users, 2606 (65%) submitted 1 to 11 surveys, 1016 (26%) made ≥12 submissions (P75, “frequent users”). Frequent users were more likely to be IBD patients (p = 0.001), female (p &amp;lt; 0.001), aged 60 or older (p &amp;lt; 0.001). Staff in administration and nurses were more likely to be frequent users compared to physicians (p &amp;lt; 0.001). Main problems included the initial operational system disparities resulting in app crashes and continuous need for app reactivation. Both led to loss of active participants and required substantial staff resources to onboard and support participants during the study. Lessons The study app enabled secure, flexible, bidirectional communication with all participants. Despite technical issues, the majority actively used the app and provided valuable longitudinal data through weekly survey submissions. Key messages • A study-specific app provides a flexible and secure bidirectional anonymous communication for the study team and participants. • Adherence to app-based communication and data collection for pandemic monitoring was particularly high among patients, nurses and administrative staff.