Julia E. Hoffman

Background: Evidence-based digital health programs have shown efficacy in being primary tools to improve emotional and mental health, as well as offering supplementary support to individuals undergoing psychotherapy for anxiety, depression, and other mental health disorders. However, information is lacking about the dose response to digital mental health interventions. Objective: The objective of the study was to examine the effect of time in program and program usage on symptom change among individuals enrolled in a real-world comprehensive digital mental health program (myStrength) who are experiencing severe anxiety or depression. Methods: Eligible participants (N=18,626) were adults aged 18 years and older who were enrolled in myStrength for at least four weeks as part of their employee wellness benefit program, who completed baseline, the 2-week, 2-month, and 6-month surveys querying symptoms of anxiety (Generalized Anxiety Disorder–7 [GAD-7]) and depression (Patient Health Questionnaire–9 [PHQ-9]). Linear growth curve models were used to analyze the effect of average weekly program usage on subsequent GAD-7 and PHQ-9 scores for participants with scores indicating severe anxiety (GAD-7≥15) or depression (PHQ-9≥15). All models were adjusted for baseline score and demographics. Results: Participants in the study (N=1519) were 77.4% female (1176/1519), had a mean age of 45 years (SD 14 years), and had an average enrollment time of 3 months. At baseline, participants reported an average of 9.39 (SD 6.04) on the GAD-7 and 11.0 (SD 6.6) on the PHQ-9. Those who reported 6-month results had an average of 8.18 (SD 6.15) on the GAD-7 and 9.18 (SD 6.79) on the PHQ-9. Participants with severe scores (n=506) experienced a significant improvement of 2.97 (SE 0.35) and 3.97 (SE 0.46) at each time point for anxiety and depression, respectively (t=–8.53 and t=–8.69, respectively; Ps<.001). Those with severe baseline scores also saw a reduction of 0.27 (SE 0.08) and 0.25 (SE 0.09) points in anxiety and depression, respectively, for each additional program activity per week (t=–3.47 and t=–2.66, respectively; Ps<.05). Conclusions: For participants with severe baseline scores, the study found a clinically significant reduction of approximately 9 points for anxiety and 12 points for depression after 6 months of enrollment, suggesting that interventions targeting mental health must maintain active, ongoing engagement when symptoms are present and be available as a continuous resource to maximize clinical impact, specifically in those experiencing severe anxiety or depression. Moreover, a dosing effect was shown, indicating improvement in outcomes among participants who engaged with the program every other day for both anxiety and depression. This suggests that digital mental health programs that provide both interesting and evidence-based activities could be more successful in further improving mental health outcomes.

BACKGROUND Evidence-based digital health programs have shown efficacy in being primary tools to improve emotional and mental health, as well as offering supplementary support to individuals undergoing psychotherapy for anxiety, depression, and other mental health disorders. However, information is lacking about the dose response to digital mental health interventions. OBJECTIVE The objective of the study was to examine the effect of time in program and program usage on symptom change among individuals enrolled in a real-world comprehensive digital mental health program (myStrength) who are experiencing severe anxiety or depression. METHODS Eligible participants (N=18,626) were adults aged 18 years and older who were enrolled in myStrength for at least four weeks as part of their employee wellness benefit program, who completed baseline, the 2-week, 2-month, and 6-month surveys querying symptoms of anxiety (Generalized Anxiety Disorder–7 [GAD-7]) and depression (Patient Health Questionnaire–9 [PHQ-9]). Linear growth curve models were used to analyze the effect of average weekly program usage on subsequent GAD-7 and PHQ-9 scores for participants with scores indicating severe anxiety (GAD-7≥15) or depression (PHQ-9≥15). All models were adjusted for baseline score and demographics. RESULTS Participants in the study (N=1519) were 77.4% female (1176/1519), had a mean age of 45 years (SD 14 years), and had an average enrollment time of 3 months. At baseline, participants reported an average of 9.39 (SD 6.04) on the GAD-7 and 11.0 (SD 6.6) on the PHQ-9. Those who reported 6-month results had an average of 8.18 (SD 6.15) on the GAD-7 and 9.18 (SD 6.79) on the PHQ-9. Participants with severe scores (n=506) experienced a significant improvement of 2.97 (SE 0.35) and 3.97 (SE 0.46) at each time point for anxiety and depression, respectively (t=–8.53 and t=–8.69, respectively; Ps<.001). Those with severe baseline scores also saw a reduction of 0.27 (SE 0.08) and 0.25 (SE 0.09) points in anxiety and depression, respectively, for each additional program activity per week (t=–3.47 and t=–2.66, respectively; Ps<.05). CONCLUSIONS For participants with severe baseline scores, the study found a clinically significant reduction of approximately 9 points for anxiety and 12 points for depression after 6 months of enrollment, suggesting that interventions targeting mental health must maintain active, ongoing engagement when symptoms are present and be available as a continuous resource to maximize clinical impact, specifically in those experiencing severe anxiety or depression. Moreover, a dosing effect was shown, indicating improvement in outcomes among participants who engaged with the program every other day for both anxiety and depression. This suggests that digital mental health programs that provide both interesting and evidence-based activities could be more successful in further improving mental health outcomes.

Background: Proactive detection of mental health needs among people with diabetes mellitus could facilitate early intervention, improve overall health and quality of life, and reduce individual and societal health and economic burdens. Passive sensing and ecological momentary assessment are relatively newer methods that may be leveraged for such proactive detection. Objective: The primary aim of this study was to conceptualize, develop, and evaluate a novel machine learning approach for predicting mental health risk in people with diabetes mellitus. Methods: A retrospective study was designed to develop and evaluate a machine learning model, utilizing data collected from 142,432 individuals with diabetes enrolled in the Livongo for Diabetes program. First, participants’ mental health statuses were verified using prescription and medical and pharmacy claims data. Next, four categories of passive sensing signals were extracted from the participants’ behavior in the program, including demographics and glucometer, coaching, and event data. Data sets were then assembled to create participant-period instances, and descriptive analyses were conducted to understand the correlation between mental health status and passive sensing signals. Passive sensing signals were then entered into the model to train and test its performance. The model was evaluated based on seven measures: sensitivity, specificity, precision, area under the curve, F1 score, accuracy, and confusion matrix. SHapley Additive exPlanations (SHAP) values were computed to determine the importance of individual signals. Results: In the training (and validation) and three subsequent test sets, the model achieved a confidence score greater than 0.5 for sensitivity, specificity, area under the curve, and accuracy. Signals identified as important by SHAP values included demographics such as race and gender, participant’s emotional state during blood glucose checks, time of day of blood glucose checks, blood glucose values, and interaction with the Livongo mobile app and web platform. Conclusions: Results of this study demonstrate the utility of a passively informed mental health risk algorithm and invite further exploration to identify additional signals and determine when and where such algorithms should be deployed.

BACKGROUND Proactive detection of mental health needs among people with diabetes mellitus could facilitate early intervention, improve overall health and quality of life, and reduce individual and societal health and economic burdens. Passive sensing and ecological momentary assessment are relatively newer methods that may be leveraged for such proactive detection. OBJECTIVE The primary aim of this study was to conceptualize, develop, and evaluate a novel machine learning approach for predicting mental health risk in people with diabetes mellitus. METHODS A retrospective study was designed to develop and evaluate a machine learning model, utilizing data collected from 142,432 individuals with diabetes enrolled in the Livongo for Diabetes program. First, participants’ mental health statuses were verified using prescription and medical and pharmacy claims data. Next, four categories of passive sensing signals were extracted from the participants’ behavior in the program, including demographics and glucometer, coaching, and event data. Data sets were then assembled to create participant-period instances, and descriptive analyses were conducted to understand the correlation between mental health status and passive sensing signals. Passive sensing signals were then entered into the model to train and test its performance. The model was evaluated based on seven measures: sensitivity, specificity, precision, area under the curve, F1 score, accuracy, and confusion matrix. SHapley Additive exPlanations (SHAP) values were computed to determine the importance of individual signals. RESULTS In the training (and validation) and three subsequent test sets, the model achieved a confidence score greater than 0.5 for sensitivity, specificity, area under the curve, and accuracy. Signals identified as important by SHAP values included demographics such as race and gender, participant’s emotional state during blood glucose checks, time of day of blood glucose checks, blood glucose values, and interaction with the Livongo mobile app and web platform. CONCLUSIONS Results of this study demonstrate the utility of a passively informed mental health risk algorithm and invite further exploration to identify additional signals and determine when and where such algorithms should be deployed.

Background: Technology is rapidly advancing our understanding of how people with diabetes mellitus experience stress. Objective: The aim of this study was to explore the relationship between stress and sequelae of diabetes mellitus within a unique data set composed of adults enrolled in a digital diabetes management program, Livongo, in order to inform intervention and product development. Methods: Participants included 3263 adults under age 65 who were diagnosed with diabetes mellitus and had access to Livongo through their employer between June 2015 and August 2018. Data were collected at time of enrollment and 12 months thereafter, which included demographic information, glycemic control, presence of stress, diabetes distress, diabetes empowerment, behavioral health diagnosis, and utilization of behavioral health-related medication and services. Analysis of variance and chi-square tests compared variables across groups that were based on presence of stress and behavioral health diagnosis or utilization. Results: Fifty-five percent of participants (1808/3263) reported stress at the time of at least 1 blood glucose reading. Fifty-two percent of participants (940/1808) also received at least 1 behavioral health diagnosis or intervention. Compared to their peers, participants with stress reported greater diabetes distress, lower diabetes empowerment, greater insulin use, and poorer glycemic control. Participants with stress and a behavioral health diagnosis/utilization additionally had higher body mass index and duration of illness. Conclusions: Stress among people with diabetes mellitus is associated with reduced emotional and physical health. Digital products that focus on the whole person by offering both diabetes mellitus self-management tools and behavioral health skills and support can help improve disease-specific and psychosocial outcomes.

BACKGROUND Technology is rapidly advancing our understanding of how people with diabetes mellitus experience stress. OBJECTIVE The aim of this study was to explore the relationship between stress and sequelae of diabetes mellitus within a unique data set composed of adults enrolled in a digital diabetes management program, Livongo, in order to inform intervention and product development. METHODS Participants included 3263 adults under age 65 who were diagnosed with diabetes mellitus and had access to Livongo through their employer between June 2015 and August 2018. Data were collected at time of enrollment and 12 months thereafter, which included demographic information, glycemic control, presence of stress, diabetes distress, diabetes empowerment, behavioral health diagnosis, and utilization of behavioral health-related medication and services. Analysis of variance and chi-square tests compared variables across groups that were based on presence of stress and behavioral health diagnosis or utilization. RESULTS Fifty-five percent of participants (1808/3263) reported stress at the time of at least 1 blood glucose reading. Fifty-two percent of participants (940/1808) also received at least 1 behavioral health diagnosis or intervention. Compared to their peers, participants with stress reported greater diabetes distress, lower diabetes empowerment, greater insulin use, and poorer glycemic control. Participants with stress and a behavioral health diagnosis/utilization additionally had higher body mass index and duration of illness. CONCLUSIONS Stress among people with diabetes mellitus is associated with reduced emotional and physical health. Digital products that focus on the whole person by offering both diabetes mellitus self-management tools and behavioral health skills and support can help improve disease-specific and psychosocial outcomes.

Background: Digital technology is increasingly being used to enhance health care in various areas of medicine. In the area of serious mental illness, it is important to understand the special characteristics of target users that may influence motivation and competence to use digital health tools, as well as the resources and training necessary for these patients to facilitate the use of this technology. Objective: The aim of this study was to conduct a quantitative expert consensus survey to identify key characteristics of target users (patients and health care professionals), barriers and facilitators for appropriate use, and resources needed to optimize the use of digital health tools in patients with serious mental illness. Methods: A panel of 40 experts in digital behavioral health who met the participation criteria completed a 19-question survey, rating predefined responses on a 9-point Likert scale. Consensus was determined using a chi-square test of score distributions across three ranges (1-3, 4-6, 7-9). Categorical ratings of first, second, or third line were designated based on the lowest category into which the CI of the mean ratings fell, with a boundary >6.5 for first line. Here, we report experts’ responses to nine questions (265 options) that focused on (1) user characteristics that would promote or hinder the use of digital health tools, (2) potential benefits or motivators and barriers or unintended consequences of digital health tool use, and (3) support and training for patients and health care professionals. Results: Among patient characteristics most likely to promote use of digital health tools, experts endorsed interest in using state-of-the-art technology, availability of necessary resources, good occupational functioning, and perception of the tool as beneficial. Certain disease-associated signs and symptoms (eg, more severe symptoms, substance abuse problems, and a chaotic living situation) were considered likely to make it difficult for patients to use digital health tools. Enthusiasm among health care professionals for digital health tools and availability of staff and equipment to support their use were identified as variables to enable health care professionals to successfully incorporate digital health tools into their practices. The experts identified a number of potential benefits of and barriers to use of digital health tools by patients and health care professionals. Experts agreed that both health care professionals and patients would need to be trained in the use of these new technologies. Conclusions: These results provide guidance to the mental health field on how to optimize the development and deployment of digital health tools for patients with serious mental illness.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Digital health tools (DHTs) are increasingly being used to enhance healthcare. However, developing a DHT for patients with serious mental illness (SMI) poses unique challenges, given certain disease characteristics associated with this population. Currently, there are no standardized guidelines for designing DHTs for patients with SMI. Objective: To assess expert opinion on (1) product features that support patient initial/sustained engagement in using a DHT, (2) mitigation of patient characteristics that can interfere with product engagement and outcomes, and (3) incorporation of goal setting and rewards/reinforcement into DHTs. Methods: The survey followed the expert consensus methodology. A panel of selected experts completed a 19-question survey and rated predefined responses on a 9-point Likert scale. A chi-square test of score distribution across 3 ranges of values (1–3, 4–6, 7–9) was used to determine the presence of consensus. CIs of the mean ratings were used to designate first-, second-, or third-line categorical ratings, with a lower limit boundary >6.5 for first-line rating. Results of questions pertaining to product features and patient engagement are reported here. Results: The experts strongly agreed that ease of use was the most valuable feature for promoting initial engagement with DHTs (mean [SD] rating, 8.7 [0.5]). For sustained engagement, the experts strongly endorsed both ease of use and ease of incorporating the DHT into the fabric of the patient’s life. To mitigate predefined patient characteristics that can interfere with product engagement and outcomes, the experts consistently recommended an intuitive user interface. Additional recommendations were made on a number of design element considerations such as short, simple, and few tasks; limited inclusion of jargon; and use of visualization. The experts emphasized the need to test the DHTs in the intended user population and to provide in-person training. Integrating goal setting into the design of a DHT was considered feasible by 71% of the experts. For effective engagement with DHTs, individualization of goals and rewards was deemed important. Conclusions: For optimal use of DHTs by individuals with SMI, it is imperative to tailor the design elements to the unique needs of this population. In this study, the experts provided recommendations on several design features of DHTs that would be useful in promoting patient engagement. The experts also identified strategies to mitigate negative effects that can result from illness-related and other contextual characteristics. These expert panel recommendations can guide future development of DHTs for persons with psychiatric illness.

BACKGROUND Digital technology is increasingly being used to enhance health care in various areas of medicine. In the area of serious mental illness, it is important to understand the special characteristics of target users that may influence motivation and competence to use digital health tools, as well as the resources and training necessary for these patients to facilitate the use of this technology. OBJECTIVE The aim of this study was to conduct a quantitative expert consensus survey to identify key characteristics of target users (patients and health care professionals), barriers and facilitators for appropriate use, and resources needed to optimize the use of digital health tools in patients with serious mental illness. METHODS A panel of 40 experts in digital behavioral health who met the participation criteria completed a 19-question survey, rating predefined responses on a 9-point Likert scale. Consensus was determined using a chi-square test of score distributions across three ranges (1-3, 4-6, 7-9). Categorical ratings of first, second, or third line were designated based on the lowest category into which the CI of the mean ratings fell, with a boundary >6.5 for first line. Here, we report experts’ responses to nine questions (265 options) that focused on (1) user characteristics that would promote or hinder the use of digital health tools, (2) potential benefits or motivators and barriers or unintended consequences of digital health tool use, and (3) support and training for patients and health care professionals. RESULTS Among patient characteristics most likely to promote use of digital health tools, experts endorsed interest in using state-of-the-art technology, availability of necessary resources, good occupational functioning, and perception of the tool as beneficial. Certain disease-associated signs and symptoms (eg, more severe symptoms, substance abuse problems, and a chaotic living situation) were considered likely to make it difficult for patients to use digital health tools. Enthusiasm among health care professionals for digital health tools and availability of staff and equipment to support their use were identified as variables to enable health care professionals to successfully incorporate digital health tools into their practices. The experts identified a number of potential benefits of and barriers to use of digital health tools by patients and health care professionals. Experts agreed that both health care professionals and patients would need to be trained in the use of these new technologies. CONCLUSIONS These results provide guidance to the mental health field on how to optimize the development and deployment of digital health tools for patients with serious mental illness.

Background: A majority of Americans (58%) now use smartphones, making it possible for mobile mental health apps to reach large numbers of those who are living with untreated, or under-treated, mental health symptoms. Although early trials suggest positive effects for mobile health (mHealth) interventions, little is known about the potential public health impact of mobile mental health apps. Objective: The purpose of this study was to characterize reach, use, and impact of “PTSD Coach”, a free, broadly disseminated mental health app for managing posttraumatic stress disorder (PTSD) symptoms. Methods: Using a mixed-methods approach, aggregate mobile analytics data from 153,834 downloads of PTSD Coach were analyzed in conjunction with 156 user reviews. Results: Over 60% of users engaged with PTSD Coach on multiple occasions (mean=6.3 sessions). User reviews reflected gratitude for the availability of the app and being able to use the app specifically during moments of need. PTSD Coach users reported relatively high levels of trauma symptoms (mean PTSD Checklist Score=57.2, SD=15.7). For users who chose to use a symptom management tool, distress declined significantly for both first-time users (mean=1.6 points, SD=2.6 on the 10-point distress thermometer) and return-visit users (mean=2.0, SD=2.3). Analysis of app session data identified common points of attrition, with only 80% of first-time users reaching the app’s home screen and 37% accessing one of the app’s primary content areas. Conclusions: These findings suggest that PTSD Coach has achieved substantial and sustained reach in the population, is being used as intended, and has been favorably received. PTSD Coach is a unique platform for the delivery of mobile mental health education and treatment, and continuing evaluation and improvement of the app could further strengthen its public health impact.