Virtual Coach Research Articles

Emotional Virtual Characters for Improving Motivation and Performance in VR Exergames

Motivation and high effort in exergames are still open to optimization. In reality, coaches can stimulate athletes' engagement by infecting them with their emotions. However, whether these emotion-influencing effects also occur with virtual coaches remains unclear. In the present study, we measured the emotional state, motivation, and performance (punch speed) of 47 participants playing a VR exergame with an emotional (happy/angry) or neutral virtual coach. Results show that the happy and angry coach significantly affected the players' emotions. Furthermore, interacting with the emotional coaches leads to higher motivation, whereas the angry coach causes a reduction of feeling related. Also, we found a significant positive correlation between the increase in anger and punch speed. Our results show that adding an emotional component to virtual coaches into exergames is promising for increasing motivation and performance. This study highlights the positive effects of emotional virtual characters for improving VR exergames and, therefore, players' health.

Development and Validation of a Kinematically Accurate Upper-Limb Exoskeleton Digital Twin for Stroke Rehabilitation.

Rehabilitation robotics combined with virtual reality using head-mounted displays enable naturalistic, immersive, and motivating therapy for people after stroke. There is growing interest in employing digital twins in robotic neurore-habilitation, e.g., in telerehabilitation for virtual coaching and monitoring, as well as in immersive virtual reality applications. However, the kinematic matching of the robot's visualization with the real robot movements is hardly validated, potentially affecting the users' experience while immersed in the virtual environment due to a visual-proprioceptive mismatch. The kinematic mismatch may also limit the validity of assessment measures recorded with the digital twin. We present the development and low-cost kinematic validation of a digital twin of a seven active degrees-of-freedom exoskeleton for stroke rehabilitation. We validated the kinematic accuracy of the digital twin end-effector by performing two tasks-a planar reaching task and a 3D functional task-performed by a single healthy participant. We computed the end-effector position and rotation from the forward kinematics of the robot, the digital twin, and data recorded from the real robot using a low-cost tracking system based on HTC VIVE trackers and compared them pair-wise. We found that the digital twin closely matches the forward kinematics and tracked movement of the real robot and thus provides a reliable platform for future research on digital twins for stroke rehabilitation.

Virtual Delivery of Parent Coaching Interventions in Early Childhood Mental Health: A Scoping Review.

Parent-coaching interventions positively impact child development. Virtual delivery of such interventions is supported by literature reviews and a practice guideline, however, none of these focused on children under age six. A scoping review of virtually-delivered parent-coaching interventions for disruptive behaviour, anxiety, and parent-child relationship concerns in children under age six was conducted between Dec. 15, 2020 and April 22, 2021. Iterative searches of the databases PubMed, CINAHL, and PsycINFO were complemented by reference list searches and clinician expert review (N = 1146). After relevance screening and duplicate removal, collaboratively-developed inclusion criteria were applied to records, followed by data extraction from eligible articles (n = 30). Most literature documented behavioural-based interventions targeting disruptive behaviour which were delivered individually, by therapists, to White, non-Hispanic parents. Evidence supports feasibility and efficacy of virtually-delivered parent-coaching interventions to improve child disruptive behaviour (strong), anxiety (moderate), and parent-child relationship (weak). There is a significant gap in the literature regarding the virtual delivery of attachment-based parent-coaching interventions. In sum, virtual parent coaching can be an efficacious approach for children under age six, particularly for behavioural challenges.

Virtual Coaching and the Reduction of Radial Head Subluxation: A Case Series.

After the establishment of the virtual pediatric emergency medicine clinic at our institution, we noted that several physicians independently began to instruct caregivers virtually on reducing a radial head subluxation. We thus conducted a case series to investigate the number, success, and follow-ups for the virtual reduction of radial head subluxation. The electronic medical records at our institution were searched from the inception of the virtual clinic in May 2020 until August 2022 (inclusive), for visits and discharge diagnosis containing the word "elbow" or "arm." Fourteen charts were retrieved; however, 2 were excluded because they were not a suspected radial head subluxation. A virtual reduction was attempted for eight (66.7%) of the 12 patients. In 6 of 8 patients (75.0%), the reduction was deemed successful, and for 2 patients (25.0%), it was deemed unsuccessful. Of the latter, one was found to have a nondisplaced radial neck fracture. All 4 patients (33.3%) for whom a virtual reduction was not attempted were referred to the emergency department. Virtual video coaching of pulled elbow reduction was completed at our institution with overall good success rate. All the physicians involved noted the essential need and benefits of video conferencing for successfully reducing radial head subluxation. We note that a pediatric population may be more amenable to video-based appointments than other populations due to their caregivers' familiarity with digital technology. Finally, as nonphysician models of healthcare delivery for virtual urgent care visits expand, we propose a checklist based on our experience to ensure patient safety.

Exploring Virtual Coach Education in USA Lacrosse

In 2020, USA Lacrosse moved all coach training workshops to a virtual format in response to the COVID-19 pandemic. Knowing that in-person coach training has been heavily studied regarding the motivation of the coaches who participate, the shift to virtual delivery of coach education prompted the researchers to examine how the workshops themselves supported the basic needs, motivation, and engagement of coach learners. Aligned with self-determination theory’s conception of motivation and the three basic needs of autonomy, competence, and relatedness, the researchers drew upon observation and survey data that were collected to determine the success of the virtual training. Using this information, the researchers found that the coach trainers used a variety of need-supportive behaviors and very few need-thwarting behaviors. Surveys revealed that the coaches displayed high levels of autonomous motivation, low levels of controlled motivation, and favorable engagement. These results are discussed in conjunction with the literature that is focused on in-person training programs as well as best practices in technology-enhanced learning to provide input into how virtual programming may be of benefit to coach learners and how coach trainers can best support coaches’ needs in a virtual environment.

Exploring tailored virtual emotion regulation approaches for individuals with emotional eating

BackgroundEmotional eating is a complex problem fostering obesity and resulting from maladaptive emotion regulation. Traditional behavioural weight loss interventions have shown insignificant effect. They can be improved by targeting the specific needs of individuals with emotional eating.ObjectiveThe current study explored a tailored online approach with the aim to positively influence affect (positive and negative) and emotion regulation by applying one of three exercises: body scan, opposite action, and positive reappraisal.DesignAn embedded mixed-method design (questionnaire data (t0, t1, t2) and perceived usefulness of exercises in t2) was used to evaluate the effects of a two-week online quasi-experimental pilot study.Subjects/settingIn total, 80 participants with self-reported emotional eating difficulties (DEBQ-E; Memo = 3.48, SD = .64, range 1.62–4.92) finished baseline measurements; 15 completed the intervention. The study sample was predominantly female (95%), from 18 till 66 (Mage = 38,0 ± SD = 14.25).ResultsParticipants reported that the exercises helped them to pay attention to their physical sensations, and to see positive aspects in negative matters. The exercises were considered difficult by the participants, with too little explanation, and dull, due to minor variation. The observed changes revealed small, and moreover, not significant improvements of the three exercises on positive and negative affect and overall emotion dysregulation. Although the quantitative results did not reach significance, the qualitative data highlighted which aspects of the tailored exercises may have contributed to mood and emotion regulation outcomes. A notable observation in the present study is the substantial dropout rate, with the number of participants decreasing from 80 at baseline (T0) to 15 at the post-intervention stage (T2).ConclusionsFuture studies should identify tailored online exercises in emotion regulation skills in more detail and explore the contexts in which they are most effective in a personalized virtual coach virtual coach to be developed for individuals with emotional eating. Given the high dropout rate, more emphasis should be given to a proper presentation of the exercises, as well as more explanation of their usefulness and how to perform them.

The Promises and Pitfalls of Using (Mostly) Low-Touch Coaching Interventions to Improve College Student Outcomes

Abstract We present results from a five-year effort to design promising virtual coaching interventions to improve college student achievement. Across nearly 20,000 students at three campuses, we find some improvement on study time, but no effect on academic outcomes. We interpret the results with unique survey data and a model of student effort. Treated students learn that more effort is needed to attain good grades and develop stronger preferences for high grades, but these effects are too small to translate into academic benefits. More comprehensive, social and better-timed interventions are needed for helping students outside the classroom.

Brief Report: Telehealth Music-Enhanced Reciprocal Imitation Training in Autism: A Single-Subject Feasibility Study of a Virtual Parent Coaching Intervention.

Telehealth delivery increases accessibility of parent-mediated interventions that teach parents skills and support autistic children's social communication. Reciprocal Imitation Training (RIT), an evidence-based Naturalistic Developmental Behavioral Intervention (NDBI) focused on imitation skills, a common difficulty in autism, holds promise for telehealth-based parent training. Imitation is also a core component of musical play during childhood and the affordances of musical play/song naturally shape parent-child interactions. We evaluate the feasibility of a music-based, telehealth adaptation of RIT-music-enhanced RIT (tele-meRIT)-as a novel format for coaching parents in NDBI strategies. This single-subject, multiple baseline design study included 4 autistic children (32-53months old) and their mothers. Parent-child dyads were recorded during 10-min free play probes at baseline, weekly tele-meRIT sessions, and one-week and one-month follow-up. Probes were coded for parents' RIT implementation fidelity, parent vocal musicality, and children's rate of spontaneous imitation. No parent demonstrated implementation fidelity during baseline. All parents increased their use of RIT strategies, met fidelity by the end of treatment, and maintained fidelity at follow-up. Parent vocal musicality also increased from baseline. Intervention did not consistently increase children's imitation skills. A post-intervention evaluation survey indicated high parent satisfaction with tele-meRIT and perceived benefits to their children's social and play skills more broadly. Implementing tele-meRIT is feasible. Although tele-meRIT additionally involved coaching in incorporating rhythmicity and song into play interactions, parents achieved fidelity in the RIT principles, suggesting one avenue by which music can be integrated within evidence-based parent-mediated NDBIs.

Improving treatment adherence in patients with cancer in low and middle-income countries, through digital health self-care interventions.

114 Background: The WHO notes that adherence to treatment for people living with chronic conditions, including cancer is of global concern. This poor adherence is brought about in low- and middle-income countries like Nigeria, by patient factors such as poor health literacy, overshadowing religious beliefs, and forgetfulness, as well as systemic factors like fragmented patient care due to physician burnout. The aim of this study was to evaluate the effectiveness of digital self-care interventions via CompleteHealth in improving treatment adherence in people living with cancer. Methods: This was a retrospective study done on 63 patients on treatment for metastatic castrate-resistant prostate cancer, enrolled on mDoc’s digital CompleteHealth platform between January to December 2022. Each patient was assigned a virtual health coach who provided self-care support, monitored their health metrics, encouraged regular physical activity, and maintained normal body weight. Synchronous and asynchronous digital nudges were provided via the multiple channels of the digital CompleteHealth platform such as the web app, SMS, and phone calls. The patients also had access to virtual fitness, nutrition, and emotional wellness coaches as required. Results: 56/63 patients (88%) completed their full course of 6 months of treatment. The adherence was at 78.4%, which represents the average percentage of members who refilled medication as at when due, allowing for 30 days or less between fillings. Allowing for 90 days in between fillings, adherence was at 90.5%. Conclusions: The use of digital health interventions via virtual health coaching for self-care support has been demonstrated through CompleteHealth to improve treatment adherence in patients living with cancer significantly. There is therefore a place to scale up the use of digital health coaching to further improve this statistic, as it is likely to impact treatment outcomes positively.

A randomised controlled test of emotional attributes of a virtual coach within a virtual reality (VR) mental health treatment

We set out to test whether positive non-verbal behaviours of a virtual coach can enhance people's engagement in automated virtual reality therapy. 120 individuals scoring highly for fear of heights participated. In a two-by-two factor, between-groups, randomised design, participants met a virtual coach that varied in warmth of facial expression (with/without) and affirmative nods (with/without). The virtual coach provided a consultation about treating fear of heights. Participants rated the therapeutic alliance, treatment credibility, and treatment expectancy. Both warm facial expressions (group difference = 7.44 [3.25, 11.62], p = 0.001, {eta}_{p}^{2}=0.10) and affirmative nods (group difference = 4.36 [0.21, 8.58], p = 0.040, {eta}_{p}^{2} = 0.04) by the virtual coach independently increased therapeutic alliance. Affirmative nods increased the treatment credibility (group difference = 1.76 [0.34, 3.11], p = 0.015, {eta}_{p}^{2} = 0.05) and expectancy (group difference = 2.28 [0.45, 4.12], p = 0.015, {eta}_{p}^{2} = 0.05) but warm facial expressions did not increase treatment credibility (group difference = 0.64 [− 0.75, 2.02], p = 0.363, {eta}_{p}^{2} = 0.01) or expectancy (group difference = 0.36 [− 1.48, 2.20], p = 0.700, {eta}_{p}^{2} = 0.001). There were no significant interactions between head nods and facial expressions in the occurrence of therapeutic alliance (p = 0.403, {eta}_{p}^{2} = 0.01), credibility (p = 0.072, {eta}_{p}^{2} = 0.03), or expectancy (p = 0.275, {eta}_{p}^{2} = 0.01). Our results demonstrate that in the development of automated VR therapies there is likely to be therapeutic value in detailed consideration of the animations of virtual coaches.

CIRCumcision learning experience using simulation: A pilot learning platform for safe neonatal circumcision training offered either virtually or in person

BackgroundTo our knowledge, no formal training combining didactic learning, simulation, and hands-on performance is available for practitioners performing neonatal circumcision. The absence of structured training may result in avoidable complications such as bleeding and penile injury. Herein, we present the results of a pilot neonatal circumcision training platform, offered either virtually or in person.Material and methodsCIRCLES (CIRCumcision Learning Experience using Simulation) consist of 1. online didactic learning; 2. live simulation practice (in person or virtual coaching), and 3. clinical performance. Outcome measures included pre- and post-knowledge scores, self-efficacy questionnaires, and skill assessments of simulation and clinical performance (Likert rating). Face validity for training success was determined by an 80% passing score on the knowledge test and > 75% (mostly independent) performance.ResultsFor this pilot, we restricted enrolment to seven pediatric residents and one nurse practitioner. Wilcoxon Sum Rank test for non-parametric paired samples for pre-and post-knowledge tests showed a median increase of 20 points in post-knowledge tests (p=0.011). Upon completion of the simulation training, all participants (8/8) have chosen to perform circumcision with the GOMCO clamp. Both in-person (4/4) and virtual participants (4/4) performed >75% of simulation and clinical circumcision independently. Post-training self-efficacy Z scores were higher than pre-training scores, except for the management of bleeding.ConclusionThe pilot CIRCLES learning shows face validity for both in-person and virtual training for neonatal circumcision. We plan to extend this platform to include more trainees and to offer them to established practitioners. The availability of formal training may ultimately reduce adverse outcomes.

Enhancing knowledge of Diabetes self-management and quality of life in people with Diabetes Mellitus by using Guru Diabetes Apps-based health coaching.

Virtual diabetes coaching through applications has the potential to improve self-management in people with Type 2 Diabetes Mellitus. However, applications designed for Asian's diabetic have never been studied. Therefore, our study aimed to identify the effect of Guru Diabetes Apps-Based Health Coaching on the level of glycemic hemoglobin, knowledge, and quality of life in Indonesians, as one of Asian ethnicities. This study used an experimental design. Participants with T2DM were recruited from three primary care health centers. The intervention included 3 months of virtual health coaching through the Guru Diabetes application. The daily monitoring of glycemic blood glucose, blood pressure, body weight, nutrition intake, and activity provided were used as baseline to conduct virtual in-person coaching. The glycemic hemoglobin level, knowledge level, and quality of life were assessed at baseline and post-enrollment. A multilevel modeling approach was used for statistical analysis. A total of 66 respondents were enrolled, and 62 respondents (93.93%) remained in the study at 3 months. After completing the intervention, the HbA1c level decreased in all groups, however it did not differ among the groups. On the other hand, the results indicate significant improvement in the average diabetes self-management knowledge score (pre = 14.97 vs post = 19.07, p < 0.05) and quality of life score (pre = 54.34 vs post = 60.28, p < 0.05), with significant difference among the groups (p < 0.05). Participants in the Android Application-Based Health Coaching experienced a significant improvement in diabetes self-management knowledge and quality of life scores at 3 months. In conclusion, the Guru Diabetes Apps-Based Health Coaching has the potential to support people with T2DM in performing diabetes self-management at home.

Aging with Pride: Innovations in Dementia Empowerment and Action (IDEA)

BackgroundSexual and gender minority (SGM) older adults and their care partners, compared to the general population, face unique vulnerabilities that exacerbate living with dementia, including elevated disparities in comorbidities, social isolation, and structural inequities, such as discrimination and lack of access to supports. MethodsThis paper describes the virtual adaptation process of the first-ever randomized controlled clinical trial intervention, Aging with Pride: Innovations in Dementia Empowerment and Action (IDEA), that was designed for SGM older adults living with dementia and their care partners and built upon the foundation of RDAD and NHAS. ResultsThe virtual adaptation of IDEA was guided by the goals of accessibility, quality, ease of delivery, sustainability, and cultural relevance. The implementation required the development of a HIPPA-compliant online virtual platform, coach and participant virtual training, and modification of necessary intervention elements and materials, as needed. Based on the preliminary findings, the participants and intervention coaches responded well to the virtual adaptation of IDEA. When comparing to in-person delivery, the virtual delivery decreased attrition among both intervention participants and coaches. DiscussionThe virtual adaptation of the IDEA intervention resulted in preliminary, unexpected, yet potentially important benefits, including the ability to expand the reach of the intervention and decreased attrition. Virtual interventions are an emerging field for people living with dementia and their care partners and additional systematic research is needed to fully assess the benefits and limitations as well as to evaluate if specific subgroups are better served by differing delivery modalities.

Predict The Caloric Expenditure and Pose Estimation Through the Assistance of The Virtual Gym Coach

This research paper introduces a novel virtual gym assistant leveraging Google's Mediapipe library, designed for diverse multimodal machine learning and deep learning pipelines. The system offers real-time guidance by analyzing user movements during specific exercises using posture estimation algorithms. Developed with Mediapipe's deep algorithms and pose estimation module, the system captures user movements through the identification of body landmarks, facilitating rep counting for each exercise. Angles and landmarks are then processed and transmitted to various machine learning models, enabling the classification of correct postures and reps. Through machine learning algorithms, the system evaluates the accuracy of user-performed reps. Utilizing diverse fitness datasets and custom data, the results demonstrate that the proposed system delivers precise and personalized feedback, enhancing exercise performance and minimizing the risk of injury. Additionally, the system calculates caloric expenditure, providing comprehensive support for users through the Virtual Gym Coach.

Effectiveness of a virtual health coach intervention for caregivers of persons with frontotemporal degeneration

AbstractBackgroundFrontotemporal degeneration (FTD) is a common cause of young‐onset dementia. A tremendous burden is placed on caregivers who often sacrifice their own self‐care needs in order to manage the cognitive decline and subsequent functional impairments of their loved one, contributing to extraordinarily high levels of stress and depression. Health coaching is a support intervention that is personalized and multidimensional, providing support for coping with stress while fostering self‐care. Here we report on the efficacy of a virtual health coach intervention (Virtual Caregiver Coach for You; ViCCY) aimed at increasing self‐care behaviors and reducing stress in FTD caregivers.MethodIn this pilot randomized control trial, 30 caregivers of persons with behavioral variant FTD (bvFTD) were randomly assigned to either the intervention group (ViCCY) which included 10 coaching sessions over 6 months plus targeted health information through the internet or the control group receiving standard care augmented with the targeted health information through the internet. Caregiver self‐report measures on self‐care (primary outcome), stress, depression and coping were collected at enrollment, 3 and 6 months. Using linear mixed‐effects models, we evaluated differences in change over time between the intervention and control groups.ResultsThere were no significant differences in baseline characteristics between the groups. There was a significant group‐by‐time interaction for self‐care monitoring (t58 = 2.37, p = 0.0210) and self‐care confidence (t58 = 2.32, p = 0.0239) on the Self‐Care Inventory, demonstrating that caregivers who received the ViCCY intervention improved in their self‐care over time. The intervention group also reported lower self‐neglect over time compared to the control group (Health Care Self Neglect Scale: t58 = ‐2.38, p = 0.0417). No differences were observed between the groups on the secondary outcome measures of stress, depression and coping.ConclusionsbvFTD caregivers are a unique population who defer their own self‐care in response to the stress of caregiving. This RCT shows promise for remotely delivered health coaching as an innovative way to increase support that is urgently needed to reduce poor outcomes in this distressed and underserved caregiver population.

THE EFFECT OF A DIGITAL HEALTH INTERVENTION ON PEOPLE WITH DIAGNOSED AND UNDIAGNOSED HYPERTENSION: A RETROSPECTIVE COHORT ANALYSIS

Objective: This study aims to show that a digital health intervention can help people with diagnosed or undiagnosed hypertension reduce their blood pressure and control their disease. Design and method: This retrospective study was conducted in January 2023 on people who reported a diagnosis of hypertension (self-reported group) or who logged in a systolic blood pressure of &gt; = 140 mmHg or a diastolic blood pressure of &gt; = 90 mmHg (undiagnosed group) who were enrolled on CompleteHealth™ between January and June 2022. CompleteHealth™ is a digital platform that allows members to access both a coach-led multidisciplinary care team and a platform for monitoring and tracking their health. The care team (comprising nutritionists, behavioural wellness coaches, and a fitness coach) engages with the members through an omnichannel approach. It provides regular digital nudges on monitoring their blood pressure, health education, and nutritional advice. The members work with their health coaches to create personalised action plans to achieve their health goals, e.g increased exercise, weight loss, and better diets. Results: 1,203 people in both groups enrolled on CompleteHealth™ over the study period and entered a baseline and follow-up value for their blood pressure. 242 (20.12%) of these people self-reported a diagnosis of hypertension, while 961 (79.88%) presented with a baseline blood pressure of &gt;140/90 mmHg. In the self-reported group, 93 people (38.43%) had controlled blood pressure at baseline, which rose to 150 (61.98%) at the end of the study. The group saw their average blood pressure fall from 149/95 mmHg to 131/85 mmHg at the end of the study. The undiagnosed group saw the number of people with controlled blood pressure rise from 68 (7.08%) to 695 (72.32%), while the average blood pressure of the group fell from 140/94 mmHg to 129/82 mmHg at the end of the study. Conclusions: While there is a need for further awareness about hypertension, especially to encourage testing and diagnosis, we have been able to show that the combination of a digital health intervention and virtual health coaching can help people who have hypertension or elevated blood pressure control their blood pressure.

Evaluation of a mobile behavior change program for weight loss in breast cancer survivors: A prospective single-arm pilot study.

12070 Background: Post-diagnosis weight gain is common among women with early-stage breast cancer and is associated with increased risk of recurrence, breast cancer death, and all-cause mortality. Intentional weight loss following diagnosis is difficult to maintain. Targeted lifestyle interventions focusing on behavioral changes and education that can be implemented long-term are needed. Methods: This was a prospective single-arm pilot study in patients with history of early-stage breast cancer (NCT04753268). Key eligibility criteria included body mass index (BMI) ≥27.5 kg/m2, stage I-III breast cancer, and completion of active cancer treatment ≥6 months prior to study enrollment. Patients were recruited at the Dempsey Center in Lewiston, ME and via social media. Participants were given access to the Noom mobile application, which utilizes cognitive behavioral therapy, motivational interviewing, and self-determination theory to induce behavior change using an educational curriculum of daily articles, virtual health coaching, social networking, food records, and physical activity logs. The primary endpoint was change in self-reported weight from baseline to 26 weeks. Secondary endpoints included change in physical activity measured using step count and the Global Physical Activity Questionnaire (GPAQ), change in diet patterns analyzed using the Nutrition Data System for Research, patient-reported outcome (PRO) measures, and metrics for engagement with the mobile application. Results: 31 patients were enrolled; 24 at the Dempsey Center and 7 via social media. Mean age was 56.8 and mean baseline BMI was 33.5 kg/m2. Mean weight change was -4.8 kg (range +0.6 to -19.9 kg, p &lt; 0.001) and mean percent weight change was -5.6%; 11/31 patients (35.5%) lost ≥5% of their initial weight. Average daily step count increased by 54.7% (p = 0.004). Mean GPAQ score for physical activity increased from 990 to 1773 (p = 0.01), and the proportion of patients who met physical activity guidelines increased from 45.1% to 74.2%. Mean energy intake did not change significantly over 26 weeks (p = 0.779). Improvements were observed in PROMIS-Physical Functioning T-scores and Body Image Scale scores (p = 0.04, p &lt; 0.001 respectively). Metrics of engagement with Noom that were predictive of weight loss ≥5% included total articles read (p = 0.012), total weights logged (p = 0.006), total food records logged (p = 0.001), messages sent to coach (p = 0.001), and number of times the application was opened (p = 0.014). Conclusions: In this pilot study, breast cancer survivors lost weight and became more physically active using a commercially-available mobile application. This digital weight loss program is a scalable intervention, and these findings support future studies investigating impact on breast cancer outcomes. Clinical trial information: NCT04753268 .

0374 Does adding a chatbot and human support enhance treatment adherence to and efficacy of digital CBTi? A randomized controlled trial

Abstract Introduction Digital cognitive behavioral therapy for insomnia (dCBTi) has been shown to be efficacious; however, treatment adherence and efficacy are suboptimal compared to CBTi delivered in person. The present study evaluated whether the addition of different types of coaching support (i.e., phone coaching by a therapist trained in CBTi, phone coaching by a research assistant not trained in CBTi, and virtual coaching by a chatbot that simulates human dialogue) would improve treatment adherence to and efficacy of dCBTi. It was hypothesized that the addition of any form of coaching will have beneficial effects, with therapist coaching achieving the best outcomes. Methods A single-blind, parallel, randomized controlled trial was conducted. One-hundred-fifty adults with insomnia, indicated by Insomnia Severity Index (ISI) &amp;gt;=10, were randomly assigned to one of the five conditions: dCBTi with three 20-min therapist phone coaching sessions (C1), dCBTi with three 20-min non-therapist phone coaching sessions (C2), dCBTi with chatbot virtual coaching (C3), dCBTi without any coaching (C4), and the sleep hygiene and sleep diary control (C5). dCBTi is a smartphone application adopting a six-session CBTi with components of sleep hygiene, sleep restriction, stimulus control, relaxation, and cognitive therapy. Participants completed sleep diaries, ISI, dysfunctional beliefs about sleep (DBAS), sleep-related behavior questionnaire (SRBQ), and measures of mood, fatigue, and quality of life at pre-intervention, post-intervention, and 4-week follow-up. Results Mixed modeling analysis showed that participants in C1, C2, C3, and C4 had greater improvements in insomnia symptoms, sleep efficiency, DBAS, SRBQ, mood, and fatigue than C5. Participants in C1 had significantly greater treatment adherence and improvement in DBAS and SRBQ than those in C4; those in conditions with any form of coaching had greater treatment adherence than those in C4. However, improvements in insomnia symptoms were not significantly different between conditions with or without coaching. Conclusion Adding human support, especially therapist phone coaching, improved treatment adherence to dCBTi but not efficacy. Nonetheless, adding therapist coaching led to greater improvements in the mechanisms of change, i.e., reductions in dysfunctional beliefs and behaviors related to insomnia, which may promote greater maintenance of treatment efficacy at longer follow-up. Clinicaltrials.gov registration#: NCT05136638 Support (if any) HKU Fund for Translation Research #104005654

Cardiac rehabilitation using a virtual trainer in patients with heart failure

Abstract Funding Acknowledgements Type of funding sources: Other. Main funding source(s): European Union’s Horizon 2020. Background/Introduction According to WHO cardiovascular diseases (CVDs) are the leading cause of mortality. Heart attacks and strokes account for more than four out of every five CVD fatalities. Early identification of patients at risk to developing cardiovascular diseases and prompt initiation of appropiate treatment can prevent premature deaths. After a patient overcomes an acute cardiovascular event, he is referred for rehabilitation to help him restore most of his normal cardiac functions. Purpose This study is part of a European project called vCare (Virtual Coaching Activities for Rehabilitation in Elderly), which aimed to test a rehabilitation program carried out by patients at home with the help of a virtual coach. In Romania, we evaluated the effectiveness of the cardiac rehabilitation program using the vCare system in reducing cardiovascular risk and improving quality of life in patients with heart failure (HF). Methods We conducted a prospective interventional pilot study in which we enrolled a total of 30 patients with HF who were divided into 3 groups: 10 patients in the experimental group (EG), 10 patients in ambulatory group (AG) and another 10 in the control group (CG). The follow-up period lasted 3 months. The patients in the EG performed cardiac rehabilitation (CR) at home using vCare app, patients in the AG underwent conventional CR at Bagdasar Arseni Hospital and those in the CG only received advice at discharge to perform regular physical activity at home and reduced cardiovascular risk factors. At the time of inclusion (time 0) all patients were clinically examined, blood tests and echocardiography were performed and also ECG exercices test for the assessment of exercices capacity and personalization of the CR program in the case of those from EG and AG. Furthermore they filled out several questionnaires (Minnesota, HADS scale, Fagerstrom). At the end of the rehabilitation program (time 1) all patients were reassessed in the same way as at enrollment. Results Patients with HF in EG had an increase in quality of life by up to 30% from time 0 to time 1, in exercices capacity by 4% and a significant decrease in cardiovascular risk factors was identified. Similar data were observed in patients from the AG, while in patients from the CG, a decrease in exercices capacity and a worsening of anxiety and depression were found. Conclusions Patients with HF who perform cardiac rehabilitation using vCare system had similar results compared to the AG and better results compared to CG, especially in terms of quality of life and their activities of daily life. This kind of cardiac rehabilitation can represent a safe and efficient solution for ensuring continuity of medical care and access to personalized motor treatments for patients with cardiological disease.

A Digital Lifestyle Program for Psychological Distress, Wellbeing and Return-to-Work: A Proof-of-Concept Study

ObjectiveTo demonstrate proof-of-concept for a chatbot-led digital lifestyle medicine program in aiding rehabilitation for return-to-work. DesignRetrospective cohort study with pre-post measures. SettingCommunity setting, Australia. Participants78 adult participants (mean age 46 years, 32% female) with an active workers’ compensation claim (N=78). InterventionsA 6-week digital lifestyle medicine program led by an artificially intelligent virtual health coach and weekly telehealth calls with a health coach. Main Outcome MeasuresAdherence (% program completions) and engagement (% of daily and weekly sessions completed), changes in depression, anxiety and distress (K10), psychological wellbeing (WHO-5), return-to-work confidence and anxiety and change in work status. ResultsSixty participants completed the program (72%), with improvements in psychological distress (P≤.001, r=.47), depression (P<.001, r=.55), anxiety (P<.001, r=.46) and wellbeing (P<.001, r=.62) were noted, as well as increased confidence about returning to work (P≤.001, r=.51) and improved work status (P≤.001). Anxiety about returning to work remained unchanged. Participants completed an average of 73% of daily virtual coach sessions and 95% of telehealth coaching sessions. ConclusionsArtificial intelligence technology may be able to provide a practical, supportive, and low-cost intervention to improve psychosocial outcomes among individuals on an active workers’ compensation claim. Further, controlled research is needed to confirm these findings.