Multimodal In-Vehicle Hypoglycemia Warning for Drivers With Type 1 Diabetes: Design and Evaluation in Simulated and Real-World Driving.

BACKGROUND: Hypoglycemia threatens cognitive function and driving safety. Previous research investigated in-vehicle voice assistants as hypoglycemia warnings. However, they could startle drivers. To address this, we combine voice warnings with ambient LEDs. OBJECTIVE: The study assesses the effect of in-vehicle multimodal warning on emotional reaction and technology acceptance among drivers with type 1 diabetes. METHODS: Two studies were conducted, one in simulated driving and the other in real-world driving. A quasi-experimental design included 2 independent variables (blood glucose phase and warning modality) and 1 main dependent variable (emotional reaction). Blood glucose was manipulated via intravenous catheters, and warning modality was manipulated by combining a tablet voice warning app and LEDs. Emotional reaction was measured physiologically via skin conductance response and subjectively with the Affective Slider and tested with a mixed-effect linear model. Secondary outcomes included self-reported technology acceptance. Participants were recruited from Bern University Hospital, Switzerland. RESULTS: The simulated and real-world driving studies involved 9 and 10 participants with type 1 diabetes, respectively. Both studies showed significant results in self-reported emotional reactions (P<.001). In simulated driving, neither warning modality nor blood glucose phase significantly affected self-reported arousal, but in real-world driving, both did (F2,68=4.3; P<.05 and F2,76=4.1; P=.03). Warning modality affected self-reported valence in simulated driving (F2,68=3.9; P<.05), while blood glucose phase affected it in real-world driving (F2,76=9.3; P<.001). Skin conductance response did not yield significant results neither in the simulated driving study (modality: F2,68=2.46; P=.09, blood glucose phase: F2,68=0.3; P=.74), nor in the real-world driving study (modality: F2,76=0.8; P=.47, blood glucose phase: F2,76=0.7; P=.5). In both simulated and real-world driving studies, the voice+LED warning modality was the most effective (simulated: mean 3.38, SD 1.06 and real-world: mean 3.5, SD 0.71) and urgent (simulated: mean 3.12, SD 0.64 and real-world: mean 3.6, SD 0.52). Annoyance varied across settings. The standard warning modality was the least effective (simulated: mean 2.25, SD 1.16 and real-world: mean 3.3, SD 1.06) and urgent (simulated: mean 1.88, SD 1.55 and real-world: mean 2.6, SD 1.26) and the most annoying (simulated: mean 2.25, SD 1.16 and real-world: mean 1.7, SD 0.95). In terms of preference, the voice warning modality outperformed the standard warning modality. In simulated driving, the voice+LED warning modality (mean rank 1.5, SD rank 0.82) was preferred over the voice (mean rank 2.2, SD rank 0.6) and standard (mean rank 2.4, SD rank 0.81) warning modalities, while in real-world driving, the voice+LED and voice warning modalities were equally preferred (mean rank 1.8, SD rank 0.79) to the standard warning modality (mean rank 2.4, SD rank 0.84). CONCLUSIONS: Despite the mixed results, this paper highlights the potential of implementing voice assistant-based health warnings in cars and advocates for multimodal alerts to enhance hypoglycemia management while driving. TRIAL REGISTRATION: ClinicalTrials.gov NCT05183191; https://classic.clinicaltrials.gov/ct2/show/NCT05183191, ClinicalTrials.gov NCT05308095; https://classic.clinicaltrials.gov/ct2/show/NCT05308095.

The Bitemporal Lens Model-toward a holistic approach to chronic disease prevention with digital biomarkers.

Objectives: We introduce the Bitemporal Lens Model, a comprehensive methodology for chronic disease prevention using digital biomarkers. Materials and Methods: The Bitemporal Lens Model integrates the change-point model, focusing on critical disease-specific parameters, and the recurrent-pattern model, emphasizing lifestyle and behavioral patterns, for early risk identification. Results: By incorporating both the change-point and recurrent-pattern models, the Bitemporal Lens Model offers a comprehensive approach to preventive healthcare, enabling a more nuanced understanding of individual health trajectories, demonstrated through its application in cardiovascular disease prevention. Discussion: We explore the benefits of the Bitemporal Lens Model, highlighting its capacity for personalized risk assessment through the integration of two distinct lenses. We also acknowledge challenges associated with handling intricate data across dual temporal dimensions, maintaining data integrity, and addressing ethical concerns pertaining to privacy and data protection. Conclusion: The Bitemporal Lens Model presents a novel approach to enhancing preventive healthcare effectiveness.

Effectiveness and User Perception of an In-Vehicle Voice Warning for Hypoglycemia: Development and Feasibility Trial.

BACKGROUND: Hypoglycemia is a frequent and acute complication in type 1 diabetes mellitus (T1DM) and is associated with a higher risk of car mishaps. Currently, hypoglycemia can be detected and signaled through flash glucose monitoring or continuous glucose monitoring devices, which require manual and visual interaction, thereby removing the focus of attention from the driving task. Hypoglycemia causes a decrease in attention, thereby challenging the safety of using such devices behind the wheel. Here, we present an investigation of a hands-free technology-a voice warning that can potentially be delivered via an in-vehicle voice assistant. OBJECTIVE: This study aims to investigate the feasibility of an in-vehicle voice warning for hypoglycemia, evaluating both its effectiveness and user perception. METHODS: We designed a voice warning and evaluated it in 3 studies. In all studies, participants received a voice warning while driving. Study 0 (n=10) assessed the feasibility of using a voice warning with healthy participants driving in a simulator. Study 1 (n=18) assessed the voice warning in participants with T1DM. Study 2 (n=20) assessed the voice warning in participants with T1DM undergoing hypoglycemia while driving in a real car. We measured participants' self-reported perception of the voice warning (with a user experience scale in study 0 and with acceptance, alliance, and trust scales in studies 1 and 2) and compliance behavior (whether they stopped the car and reaction time). In addition, we assessed technology affinity and collected the participants' verbal feedback. RESULTS: Technology affinity was similar across studies and approximately 70% of the maximal value. Perception measure of the voice warning was approximately 62% to 78% in the simulated driving and 34% to 56% in real-world driving. Perception correlated with technology affinity on specific constructs (eg, Affinity for Technology Interaction score and intention to use, optimism and performance expectancy, behavioral intention, Session Alliance Inventory score, innovativeness and hedonic motivation, and negative correlations between discomfort and behavioral intention and discomfort and competence trust; all P<.05). Compliance was 100% in all studies, whereas reaction time was higher in study 1 (mean 23, SD 5.2 seconds) than in study 0 (mean 12.6, SD 5.7 seconds) and study 2 (mean 14.6, SD 4.3 seconds). Finally, verbal feedback showed that the participants preferred the voice warning to be less verbose and interactive. CONCLUSIONS: This is the first study to investigate the feasibility of an in-vehicle voice warning for hypoglycemia. Drivers find such an implementation useful and effective in a simulated environment, but improvements are needed in the real-world driving context. This study is a kickoff for the use of in-vehicle voice assistants for digital health interventions.

Can digital health researchers make a difference during the pandemic? Results of the single-arm, chatbot-led Elena+: Care for COVID-19 interventional study.

Background: The current paper details findings from Elena+: Care for COVID-19, an app developed to tackle the collateral damage of lockdowns and social distancing, by offering pandemic lifestyle coaching across seven health areas: anxiety, loneliness, mental resources, sleep, diet and nutrition, physical activity, and COVID-19 information. Methods: The Elena+ app functions as a single-arm interventional study, with participants recruited predominantly via social media. We used paired samples T-tests and within subjects ANOVA to examine changes in health outcome assessments and user experience evaluations over time. To investigate the mediating role of behavioral activation (i.e., users setting behavioral intentions and reporting actual behaviors) we use mixed-effect regression models. Free-text entries were analyzed qualitatively. Results: Results show strong demand for publicly available lifestyle coaching during the pandemic, with total downloads (N = 7'135) and 55.8% of downloaders opening the app (n = 3,928) with 9.8% completing at least one subtopic (n = 698). Greatest areas of health vulnerability as assessed with screening measures were physical activity with 62% (n = 1,000) and anxiety with 46.5% (n = 760). The app was effective in the treatment of mental health; with a significant decrease in depression between first (14 days), second (28 days), and third (42 days) assessments: F2,38 = 7.01, p = 0.003, with a large effect size (η2G = 0.14), and anxiety between first and second assessments: t54 = 3.7, p = <0.001 with a medium effect size (Cohen d = 0.499). Those that followed the coaching program increased in net promoter score between the first and second assessment: t36 = 2.08, p = 0.045 with a small to medium effect size (Cohen d = 0.342). Mediation analyses showed that while increasing number of subtopics completed increased behavioral activation (i.e., match between behavioral intentions and self-reported actual behaviors), behavioral activation did not mediate the relationship to improvements in health outcome assessments. Conclusions: Findings show that: (i) there is public demand for chatbot led digital coaching, (ii) such tools can be effective in delivering treatment success, and (iii) they are highly valued by their long-term user base. As the current intervention was developed at rapid speed to meet the emergency pandemic context, the future looks bright for other public health focused chatbot-led digital health interventions.

Wearable-based accelerometer activity profile as digital biomarker of inflammation, biological age, and mortality using hierarchical clustering analysis in NHANES 2011-2014.

Repeated disruptions in circadian rhythms are associated with implications for health outcomes and longevity. The utilization of wearable devices in quantifying circadian rhythm to elucidate its connection to longevity, through continuously collected data remains largely unstudied. In this work, we investigate a data-driven segmentation of the 24-h accelerometer activity profiles from wearables as a novel digital biomarker for longevity in 7,297 U.S. adults from the 2011-2014 National Health and Nutrition Examination Survey. Using hierarchical clustering, we identified five clusters and described them as follows: "High activity", "Low activity", "Mild circadian rhythm (CR) disruption", "Severe CR disruption", and "Very low activity". Young adults with extreme CR disturbance are seemingly healthy with few comorbid conditions, but in fact associated with higher white blood cell, neutrophils, and lymphocyte counts (0.05-0.07 log-unit, all p < 0.05) and accelerated biological aging (1.42 years, p < 0.001). Older adults with CR disruption are significantly associated with increased systemic inflammation indexes (0.09-0.12 log-unit, all p < 0.05), biological aging advance (1.28 years, p = 0.021), and all-cause mortality risk (HR = 1.58, p = 0.042). Our findings highlight the importance of circadian alignment on longevity across all ages and suggest that data from wearable accelerometers can help in identifying at-risk populations and personalize treatments for healthier aging.

Development of a digital biomarker and intervention for subclinical depression: study protocol for a longitudinal waitlist control study.

BACKGROUND: Depression remains a global health problem, with its prevalence rising worldwide. Digital biomarkers are increasingly investigated to initiate and tailor scalable interventions targeting depression. Due to the steady influx of new cases, focusing on treatment alone will not suffice; academics and practitioners need to focus on the prevention of depression (i.e., addressing subclinical depression). AIM: With our study, we aim to (i) develop digital biomarkers for subclinical symptoms of depression, (ii) develop digital biomarkers for severity of subclinical depression, and (iii) investigate the efficacy of a digital intervention in reducing symptoms and severity of subclinical depression. METHOD: Participants will interact with the digital intervention BEDDA consisting of a scripted conversational agent, the slow-paced breathing training Breeze, and actionable advice for different symptoms. The intervention comprises 30 daily interactions to be completed in less than 45 days. We will collect self-reports regarding mood, agitation, anhedonia (proximal outcomes; first objective), self-reports regarding depression severity (primary distal outcome; second and third objective), anxiety severity (secondary distal outcome; second and third objective), stress (secondary distal outcome; second and third objective), voice, and breathing. A subsample of 25% of the participants will use smartwatches to record physiological data (e.g., heart-rate, heart-rate variability), which will be used in the analyses for all three objectives. DISCUSSION: Digital voice- and breathing-based biomarkers may improve diagnosis, prevention, and care by enabling an unobtrusive and either complementary or alternative assessment to self-reports. Furthermore, our results may advance our understanding of underlying psychophysiological changes in subclinical depression. Our study also provides further evidence regarding the efficacy of standalone digital health interventions to prevent depression. Trial registration Ethics approval was provided by the Ethics Commission of ETH Zurich (EK-2022-N-31) and the study was registered in the ISRCTN registry (Reference number: ISRCTN38841716, Submission date: 20/08/2022).

Development of "LvL UP 1.0": a smartphone-based, conversational agent-delivered holistic lifestyle intervention for the prevention of non-communicable diseases and common mental disorders.

Background: Non-communicable diseases (NCDs) and common mental disorders (CMDs) are the leading causes of death and disability worldwide. Lifestyle interventions via mobile apps and conversational agents present themselves as low-cost, scalable solutions to prevent these conditions. This paper describes the rationale for, and development of, "LvL UP 1.0″, a smartphone-based lifestyle intervention aimed at preventing NCDs and CMDs. Materials and Methods: A multidisciplinary team led the intervention design process of LvL UP 1.0, involving four phases: (i) preliminary research (stakeholder consultations, systematic market reviews), (ii) selecting intervention components and developing the conceptual model, (iii) whiteboarding and prototype design, and (iv) testing and refinement. The Multiphase Optimization Strategy and the UK Medical Research Council framework for developing and evaluating complex interventions were used to guide the intervention development. Results: Preliminary research highlighted the importance of targeting holistic wellbeing (i.e., both physical and mental health). Accordingly, the first version of LvL UP features a scalable, smartphone-based, and conversational agent-delivered holistic lifestyle intervention built around three pillars: Move More (physical activity), Eat Well (nutrition and healthy eating), and Stress Less (emotional regulation and wellbeing). Intervention components include health literacy and psychoeducational coaching sessions, daily "Life Hacks" (healthy activity suggestions), breathing exercises, and journaling. In addition to the intervention components, formative research also stressed the need to introduce engagement-specific components to maximise uptake and long-term use. LvL UP includes a motivational interviewing and storytelling approach to deliver the coaching sessions, as well as progress feedback and gamification. Offline materials are also offered to allow users access to essential intervention content without needing a mobile device. Conclusions: The development process of LvL UP 1.0 led to an evidence-based and user-informed smartphone-based intervention aimed at preventing NCDs and CMDs. LvL UP is designed to be a scalable, engaging, prevention-oriented, holistic intervention for adults at risk of NCDs and CMDs. A feasibility study, and subsequent optimisation and randomised-controlled trials are planned to further refine the intervention and establish effectiveness. The development process described here may prove helpful to other intervention developers.

Smartphone-based cough monitoring as a near real-time digital pneumonia biomarker.

Background: Cough represents a cardinal symptom of acute respiratory tract infections. Generally associated with disease activity, cough holds biomarker potential and might be harnessed for prognosis and personalised treatment decisions. Here, we tested the suitability of cough as a digital biomarker for disease activity in coronavirus disease 2019 (COVID-19) and other lower respiratory tract infections. Methods: We conducted a single-centre, exploratory, observational cohort study on automated cough detection in patients hospitalised for COVID-19 (n=32) and non-COVID-19 pneumonia (n=14) between April and November 2020 at the Cantonal Hospital St Gallen, Switzerland. Cough detection was achieved using smartphone-based audio recordings coupled to an ensemble of convolutional neural networks. Cough levels were correlated to established markers of inflammation and oxygenation. Measurements and main results: Cough frequency was highest upon hospital admission and declined steadily with recovery. There was a characteristic pattern of daily cough fluctuations, with little activity during the night and two coughing peaks during the day. Hourly cough counts were strongly correlated with clinical markers of disease activity and laboratory markers of inflammation, suggesting cough as a surrogate of disease in acute respiratory tract infections. No apparent differences in cough evolution were observed between COVID-19 and non-COVID-19 pneumonia. Conclusions: Automated, quantitative, smartphone-based detection of cough is feasible in hospitalised patients and correlates with disease activity in lower respiratory tract infections. Our approach allows for near real-time telemonitoring of individuals in aerosol isolation. Larger trials are warranted to decipher the use of cough as a digital biomarker for prognosis and tailored treatment in lower respiratory tract infections.

Trends in voice characteristics in patients with heart failure (VENTURE) in Switzerland: Protocol for a longitudinal observational pilot study.

INTRODUCTION: Heart Failure (HF) is a major health and economic issue worldwide. HF-related expenses are largely driven by hospital admissions and re-admissions, many of which are potentially preventable. Current self-management programs, however, have failed to reduce hospital admissions. This may be explained by their low predictive power for decompensation and high adherence requirements. Slight alterations in the voice profile may allow to detect decompensation in HF patients at an earlier stage and reduce hospitalizations. This pilot study investigates the potential of voice as a digital biomarker to predict health status deterioration in HF patients. METHODS AND ANALYSIS: In a two-month longitudinal observational study, we collect voice samples and HF-related quality-of-life questionnaires from 35 stable HF patients. Patients use our developed study application installed on a tablet at home during the study period. From the collected data, we use signal processing to extract voice characteristics from the audio samples and associate them with the answers to the questionnaire data. The primary outcome will be the correlation between voice characteristics and HF-related quality-of-life health status. ETHICS AND DISSEMINATION: The study was reviewed and approved by the Cantonal Ethics Committee Zurich (BASEC ID:2022-00912). Results will be published in medical and technical peer-reviewed journals.

Machine learning for non-invasive sensing of hypoglycaemia while driving in people with diabetes.

AIM: To develop and evaluate the concept of a non-invasive machine learning (ML) approach for detecting hypoglycaemia based exclusively on combined driving (CAN) and eye tracking (ET) data. MATERIALS AND METHODS: We first developed and tested our ML approach in pronounced hypoglycaemia, and then we applied it to mild hypoglycaemia to evaluate its early warning potential. For this, we conducted two consecutive, interventional studies in individuals with type 1 diabetes. In study 1 (n = 18), we collected CAN and ET data in a driving simulator during euglycaemia and pronounced hypoglycaemia (blood glucose [BG] 2.0-2.5 mmol L-1 ). In study 2 (n = 9), we collected CAN and ET data in the same simulator but in euglycaemia and mild hypoglycaemia (BG 3.0-3.5 mmol L-1 ). RESULTS: Here, we show that our ML approach detects pronounced and mild hypoglycaemia with high accuracy (area under the receiver operating characteristics curve 0.88 ± 0.10 and 0.83 ± 0.11, respectively). CONCLUSIONS: Our findings suggest that an ML approach based on CAN and ET data, exclusively, enables detection of hypoglycaemia while driving. This provides a promising concept for alternative and non-invasive detection of hypoglycaemia.

Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data.

OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment. Using these data, we developed a machine learning (ML) approach to detect hypoglycemia (<3.9 mmol/L) noninvasively in unseen individuals and solely based on wearable data. RESULTS: Twenty-two individuals were included in the final analysis (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 males). Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data. Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia. CONCLUSIONS: Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning.

Nighttime Continuous Contactless Smartphone-Based Cough Monitoring for the Ward: Validation Study.

BACKGROUND: Clinical deterioration can go unnoticed in hospital wards for hours. Mobile technologies such as wearables and smartphones enable automated, continuous, noninvasive ward monitoring and allow the detection of subtle changes in vital signs. Cough can be effectively monitored through mobile technologies in the ward, as it is not only a symptom of prevalent respiratory diseases such as asthma, lung cancer, and COVID-19 but also a predictor of acute health deterioration. In past decades, many efforts have been made to develop an automatic cough counting tool. To date, however, there is neither a standardized, sufficiently validated method nor a scalable cough monitor that can be deployed on a consumer-centric device that reports cough counts continuously. These shortcomings limit the tracking of coughing and, consequently, hinder the monitoring of disease progression in prevalent respiratory diseases such as asthma, chronic obstructive pulmonary disease, and COVID-19 in the ward. OBJECTIVE: This exploratory study involved the validation of an automated smartphone-based monitoring system for continuous cough counting in 2 different modes in the ward. Unlike previous studies that focused on evaluating cough detection models on unseen data, the focus of this work is to validate a holistic smartphone-based cough detection system operating in near real time. METHODS: Automated cough counts were measured consistently on devices and on computers and compared with cough and noncough sounds counted manually over 8-hour long nocturnal recordings in 9 patients with pneumonia in the ward. The proposed cough detection system consists primarily of an Android app running on a smartphone that detects coughs and records sounds and secondarily of a backend that continuously receives the cough detection information and displays the hourly cough counts. Cough detection is based on an ensemble convolutional neural network developed and trained on asthmatic cough data. RESULTS: In this validation study, a total of 72 hours of recordings from 9 participants with pneumonia, 4 of whom were infected with SARS-CoV-2, were analyzed. All the recordings were subjected to manual analysis by 2 blinded raters. The proposed system yielded a sensitivity and specificity of 72% and 99% on the device and 82% and 99% on the computer, respectively, for detecting coughs. The mean differences between the automated and human rater cough counts were -1.0 (95% CI -12.3 to 10.2) and -0.9 (95% CI -6.5 to 4.8) coughs per hour within subject for the on-device and on-computer modes, respectively. CONCLUSIONS: The proposed system thus represents a smartphone cough counter that can be used for continuous hourly assessment of cough frequency in the ward.

Breathing as an Input Modality in a Gameful Breathing Training App (Breeze 2): Development and Evaluation Study.

BACKGROUND: Slow-paced breathing training can have positive effects on physiological and psychological well-being. Unfortunately, use statistics indicate that adherence to breathing training apps is low. Recent work suggests that gameful breathing training may help overcome this challenge. OBJECTIVE: This study aimed to introduce and evaluate the gameful breathing training app Breeze 2 and its novel real-time breathing detection algorithm that enables the interactive components of the app. METHODS: We developed the breathing detection algorithm by using deep transfer learning to detect inhalation, exhalation, and nonbreathing sounds (including silence). An additional heuristic prolongs detected exhalations to stabilize the algorithm's predictions. We evaluated Breeze 2 with 30 participants (women: n=14, 47%; age: mean 29.77, SD 7.33 years). Participants performed breathing training with Breeze 2 in 2 sessions with and without headphones. They answered questions regarding user engagement (User Engagement Scale Short Form [UES-SF]), perceived effectiveness (PE), perceived relaxation effectiveness, and perceived breathing detection accuracy. We used Wilcoxon signed-rank tests to compare the UES-SF, PE, and perceived relaxation effectiveness scores with neutral scores. Furthermore, we correlated perceived breathing detection accuracy with actual multi-class balanced accuracy to determine whether participants could perceive the actual breathing detection performance. We also conducted a repeated-measure ANOVA to investigate breathing detection differences in balanced accuracy with and without the heuristic and when classifying data captured from headphones and smartphone microphones. The analysis controlled for potential between-subject effects of the participants' sex. RESULTS: Our results show scores that were significantly higher than neutral scores for the UES-SF (W=459; P<.001), PE (W=465; P<.001), and perceived relaxation effectiveness (W=358; P<.001). Perceived breathing detection accuracy correlated significantly with the actual multi-class balanced accuracy (r=0.51; P<.001). Furthermore, we found that the heuristic significantly improved the breathing detection balanced accuracy (F1,25=6.23; P=.02) and that detection performed better on data captured from smartphone microphones than than on data from headphones (F1,25=17.61; P<.001). We did not observe any significant between-subject effects of sex. Breathing detection without the heuristic reached a multi-class balanced accuracy of 74% on the collected audio recordings. CONCLUSIONS: Most participants (28/30, 93%) perceived Breeze 2 as engaging and effective. Furthermore, breathing detection worked well for most participants, as indicated by the perceived detection accuracy and actual detection accuracy. In future work, we aim to use the collected breathing sounds to improve breathing detection with regard to its stability and performance. We also plan to use Breeze 2 as an intervention tool in various studies targeting the prevention and management of noncommunicable diseases.

Factors Influencing Adherence to mHealth Apps for Prevention or Management of Noncommunicable Diseases: Systematic Review.

BACKGROUND: Mobile health (mHealth) apps show vast potential in supporting patients and health care systems with the increasing prevalence and economic costs of noncommunicable diseases (NCDs) worldwide. However, despite the availability of evidence-based mHealth apps, a substantial proportion of users do not adhere to them as intended and may consequently not receive treatment. Therefore, understanding the factors that act as barriers to or facilitators of adherence is a fundamental concern in preventing intervention dropouts and increasing the effectiveness of digital health interventions. OBJECTIVE: This review aimed to help stakeholders develop more effective digital health interventions by identifying factors influencing the continued use of mHealth apps targeting NCDs. We further derived quantified adherence scores for various health domains to validate the qualitative findings and explore adherence benchmarks. METHODS: A comprehensive systematic literature search (January 2007 to December 2020) was conducted on MEDLINE, Embase, Web of Science, Scopus, and ACM Digital Library. Data on intended use, actual use, and factors influencing adherence were extracted. Intervention-related and patient-related factors with a positive or negative influence on adherence are presented separately for the health domains of NCD self-management, mental health, substance use, nutrition, physical activity, weight loss, multicomponent lifestyle interventions, mindfulness, and other NCDs. Quantified adherence measures, calculated as the ratio between the estimated intended use and actual use, were derived for each study and compared with the qualitative findings. RESULTS: The literature search yielded 2862 potentially relevant articles, of which 99 (3.46%) were included as part of the inclusion criteria. A total of 4 intervention-related factors indicated positive effects on adherence across all health domains: personalization or tailoring of the content of mHealth apps to the individual needs of the user, reminders in the form of individualized push notifications, user-friendly and technically stable app design, and personal support complementary to the digital intervention. Social and gamification features were also identified as drivers of app adherence across several health domains. A wide variety of patient-related factors such as user characteristics or recruitment channels further affects adherence. The derived adherence scores of the included mHealth apps averaged 56.0% (SD 24.4%). CONCLUSIONS: This study contributes to the scarce scientific evidence on factors that positively or negatively influence adherence to mHealth apps and is the first to quantitatively compare adherence relative to the intended use of various health domains. As underlying studies mostly have a pilot character with short study durations, research on factors influencing adherence to mHealth apps is still limited. To facilitate future research on mHealth app adherence, researchers should clearly outline and justify the app's intended use; report objective data on actual use relative to the intended use; and, ideally, provide long-term use and retention data.

A Scalable Risk-Scoring System Based on Consumer-Grade Wearables for Inpatients With COVID-19: Statistical Analysis and Model Development.

BACKGROUND: To provide effective care for inpatients with COVID-19, clinical practitioners need systems that monitor patient health and subsequently allow for risk scoring. Existing approaches for risk scoring in patients with COVID-19 focus primarily on intensive care units (ICUs) with specialized medical measurement devices but not on hospital general wards. OBJECTIVE: In this paper, we aim to develop a risk score for inpatients with COVID-19 in general wards based on consumer-grade wearables (smartwatches). METHODS: Patients wore consumer-grade wearables to record physiological measurements, such as the heart rate (HR), heart rate variability (HRV), and respiration frequency (RF). Based on Bayesian survival analysis, we validated the association between these measurements and patient outcomes (ie, discharge or ICU admission). To build our risk score, we generated a low-dimensional representation of the physiological features. Subsequently, a pooled ordinal regression with time-dependent covariates inferred the probability of either hospital discharge or ICU admission. We evaluated the predictive performance of our developed system for risk scoring in a single-center, prospective study based on 40 inpatients with COVID-19 in a general ward of a tertiary referral center in Switzerland. RESULTS: First, Bayesian survival analysis showed that physiological measurements from consumer-grade wearables are significantly associated with patient outcomes (ie, discharge or ICU admission). Second, our risk score achieved a time-dependent area under the receiver operating characteristic curve (AUROC) of 0.73-0.90 based on leave-one-subject-out cross-validation. CONCLUSIONS: Our results demonstrate the effectiveness of consumer-grade wearables for risk scoring in inpatients with COVID-19. Due to their low cost and ease of use, consumer-grade wearables could enable a scalable monitoring system. TRIAL REGISTRATION: Clinicaltrials.gov NCT04357834; https://www.clinicaltrials.gov/ct2/show/NCT04357834.

TripletCough: Cougher Identification and Verification From Contact-Free Smartphone-Based Audio Recordings Using Metric Learning.

Cough, a symptom associated with many prevalent respiratory diseases, can serve as a potential biomarker for diagnosis and disease progression. Consequently, the development of cough monitoring systems and, in particular, automatic cough detection algorithms have been studied since the early 2000s. Recently, there has been an increased focus on the efficiency of such algorithms, as implementation on consumer-centric devices such as smartphones would provide a scalable and affordable solution for monitoring cough with contact-free sensors. Current algorithms, however, are incapable of discerning between coughs of different individuals and, thus, cannot function reliably in situations where potentially multiple individuals have to be monitored in shared environments. Therefore, we propose a weakly supervised metric learning approach for cougher recognition based on smartphone audio recordings of coughs. Our approach involves a triplet network architecture, which employs convolutional neural networks (CNNs). The CNNs of the triplet network learn an embedding function, which maps Mel spectrograms of cough recordings to an embedding space where they are more easily distinguishable. Using audio recordings of nocturnal coughs from asthmatic patients captured with a smartphone, our approach achieved a mean accuracyof 88 % ( ± 10 % SD) on two-way identification tests with 12 enrollment samples and accuracy of 80 % and an equal error rate (EER) of 20 % on verification tests. Furthermore, our approach outperformed human raters with regard to verification tests on average by 8% in accuracy, 4% in false acceptance rate (FAR), and 12% in false rejection rate (FRR). Our code and models are publicly available.

Corrigendum: Elena+ Care for COVID-19, a Pandemic Lifestyle Care Intervention: Intervention Design and Study Protocol.

[This corrects the article DOI: 10.3389/fpubh.2021.625640.].

Detecting Receptivity for mHealth Interventions in the Natural Environment.

Just-In-Time Adaptive Intervention (JITAI) is an emerging technique with great potential to support health behavior by providing the right type and amount of support at the right time. A crucial aspect of JITAIs is properly timing the delivery of interventions, to ensure that a user is receptive and ready to process and use the support provided. Some prior works have explored the association of context and some user-specific traits on receptivity, and have built post-study machine-learning models to detect receptivity. For effective intervention delivery, however, a JITAI system needs to make in-the-moment decisions about a user's receptivity. To this end, we conducted a study in which we deployed machine-learning models to detect receptivity in the natural environment, i.e., in free-living conditions. We leveraged prior work regarding receptivity to JITAIs and deployed a chatbot-based digital coach - Ally - that provided physical-activity interventions and motivated participants to achieve their step goals. We extended the original Ally app to include two types of machine-learning model that used contextual information about a person to predict when a person is receptive: a static model that was built before the study started and remained constant for all participants and an adaptive model that continuously learned the receptivity of individual participants and updated itself as the study progressed. For comparison, we included a control model that sent intervention messages at random times. The app randomly selected a delivery model for each intervention message. We observed that the machine-learning models led up to a 40% improvement in receptivity as compared to the control model. Further, we evaluated the temporal dynamics of the different models and observed that receptivity to messages from the adaptive model increased over the course of the study.

Reliability of Commercial Voice Assistants' Responses to Health-Related Questions in Noncommunicable Disease Management: Factorial Experiment Assessing Response Rate and Source of Information.

BACKGROUND: Noncommunicable diseases (NCDs) constitute a burden on public health. These are best controlled through self-management practices, such as self-information. Fostering patients' access to health-related information through efficient and accessible channels, such as commercial voice assistants (VAs), may support the patients' ability to make health-related decisions and manage their chronic conditions. OBJECTIVE: This study aims to evaluate the reliability of the most common VAs (ie, Amazon Alexa, Apple Siri, and Google Assistant) in responding to questions about management of the main NCD. METHODS: We generated health-related questions based on frequently asked questions from health organization, government, medical nonprofit, and other recognized health-related websites about conditions associated with Alzheimer's disease (AD), lung cancer (LCA), chronic obstructive pulmonary disease, diabetes mellitus (DM), cardiovascular disease, chronic kidney disease (CKD), and cerebrovascular accident (CVA). We then validated them with practicing medical specialists, selecting the 10 most frequent ones. Given the low average frequency of the AD-related questions, we excluded such questions. This resulted in a pool of 60 questions. We submitted the selected questions to VAs in a 3×3×6 fractional factorial design experiment with 3 developers (ie, Amazon, Apple, and Google), 3 modalities (ie, voice only, voice and display, display only), and 6 diseases. We assessed the rate of error-free voice responses and classified the web sources based on previous research (ie, expert, commercial, crowdsourced, or not stated). RESULTS: Google showed the highest total response rate, followed by Amazon and Apple. Moreover, although Amazon and Apple showed a comparable response rate in both voice-and-display and voice-only modalities, Google showed a slightly higher response rate in voice only. The same pattern was observed for the rate of expert sources. When considering the response and expert source rate across diseases, we observed that although Google remained comparable, with a slight advantage for LCA and CKD, both Amazon and Apple showed the highest response rate for LCA. However, both Google and Apple showed most often expert sources for CVA, while Amazon did so for DM. CONCLUSIONS: Google showed the highest response rate and the highest rate of expert sources, leading to the conclusion that Google Assistant would be the most reliable tool in responding to questions about NCD management. However, the rate of expert sources differed across diseases. We urge health organizations to collaborate with Google, Amazon, and Apple to allow their VAs to consistently provide reliable answers to health-related questions on NCD management across the different diseases.