Eating disorder symptoms and comorbid mental health risk among teens recruited to a digital intervention research study via two online approaches.

INTRODUCTION: It is crucial to identify and evaluate feasible, proactive ways to reach teens with eating disorders (EDs) who may not otherwise have access to screening or treatment. This study aimed to explore the feasibility of recruiting teens with EDs to a digital intervention study via social media and a publicly available online ED screen, and to compare the characteristics of teens recruited by each approach in an exploratory fashion. METHOD: Teens aged 14-17 years old who screened positive for a clinical/subclinical ED or at risk for an ED and who were not currently in ED treatment completed a baseline survey to assess current ED symptoms, mental health comorbidities, and barriers to treatment. Bivariate analyses were conducted to examine differences between participants recruited via social media and those recruited after completion of a widely available online EDs screen (i.e., National Eating Disorders Association [NEDA] screen). RESULTS: Recruitment of teens with EDs using the two online approaches was found to be feasible, with 934 screens completed and a total of 134 teens enrolled over 6 months: 77% (n = 103) via social media 23% (n = 31) via the NEDA screen. Mean age of participants (N = 134) was 16 years old, with 49% (n = 66) identifying as non-White, and 70% (n = 94) identifying as a gender and/or sexual minority. Teens from NEDA reported higher ED psychopathology scores (medium effect size) and more frequent self-induced vomiting and driven exercise (small effect sizes). Teens from NEDA also endorsed more barriers to treatment, including not feeling ready for treatment and not knowing where to find a counselor or other resources (small effect sizes). DISCUSSION: Online recruitment approaches in this study reached a large number of teens with an interest in a digital intervention to support ED recovery, demonstrating the feasibility of these outreach methods. Both approaches reached teens with similar demographic characteristics; however, teens recruited from NEDA reported higher ED symptom severity and barriers to treatment. Findings suggest that proactive assessment and intervention methods should be developed and tailored to meet the needs of each of these groups. PUBLIC SIGNIFICANCE: This study examined the feasibility of recruiting teens with EDs to a digital intervention research study via social media and NEDA's online screen, and demonstrated differences in ED symptoms among participants by recruitment approach.

Machine Learning and Bayesian Network Analyses Identifies Psychiatric Disorders and Symptom Associations with Insomnia in a national sample of 31,285 Treatment-Seeking College Students.

Background: A better understanding of the structure of relations among insomnia and anxiety, mood, eating, and alcohol-use disorders is needed, given its prevalence among young adults. Supervised machine learning provides the ability to evaluate the discriminative accuracy of psychiatric disorders associated with insomnia. Combined with Bayesian network analysis, the directionality between symptoms and their associations may be illuminated. Methods: The current exploratory analyses utilized a national sample of college students across 26 U.S. colleges and universities collected during population-level screening before entering a randomized controlled trial. Firstly, an elastic net regularization model was trained to predict, via repeated 10-fold cross-validation, which psychiatric disorders were associated with insomnia severity. Seven disorders were included: major depressive disorder, generalized anxiety disorder, social anxiety disorder, panic disorder, post-traumatic stress disorder, anorexia nervosa, and alcohol use disorder. Secondly, using a Bayesian network approach, completed partially directed acyclic graphs (CPDAG) built on training and holdout samples were computed via a Bayesian hill-climbing algorithm to determine symptom-level interactions of disorders most associated with insomnia [based on SHAP (SHapley Additive exPlanations) values)] and were evaluated for stability across networks. Results: Of 31,285 participants, 20,597 were women (65.8%); mean (standard deviation) age was 22.96 (4.52) years. The elastic net model demonstrated clinical significance in predicting insomnia severity in the training sample [R2 = .449 (.016); RMSE = 5.00 [.081]), with comparable performance in accounting for variance explained in the holdout sample [R2 = .33; RMSE = 5.47). SHAP indicated the presence of any psychiatric disorder was associated with higher insomnia severity, with major depressive disorder demonstrated to be the most associated disorder. CPDAGs showed excellent fit in the holdout sample and suggested that depressed mood, fatigue, and self-esteem were the most important depression symptoms that presupposed insomnia. Conclusion: These findings offer insights into associations between psychiatric disorders and insomnia among college students and encourage future investigation into the potential direction of causality between insomnia and major depressive disorder. Trial registration: Trial may be found on the National Institute of Health RePORTER website: Project Number: R01MH115128-05.

Rates and correlates of study enrolment and use of a chatbot aimed to promote mental health services use for eating disorders following online screening.

OBJECTIVE: We developed a chatbot aimed to facilitate mental health services use for eating disorders (EDs) and offered the opportunity to enrol in a research study and use the chatbot to all adult respondents to a publicly available online ED screen who screened positive for clinical/subclinical EDs and reported not currently being in treatment. We examined the rates and correlates of enrolment in the study and uptake of the chatbot. METHOD: Following screening, eligible respondents (≥18 years, screened positive for a clinical/subclinical ED, not in treatment for an ED) were shown the study opportunity. Chi-square tests and logistic regressions explored differences in demographics, ED symptoms, suicidality, weight, and probable ED diagnoses between those who enroled and engaged with the chatbot versus those who did not. RESULTS: 6747 respondents were shown the opportunity (80.0% of all adult screens). 3.0% enroled, of whom 90.2% subsequently used the chatbot. Enrolment and chatbot uptake were more common among respondents aged ≥25 years old versus those aged 18-24 and less common among respondents who reported engaging in regular dietary restriction. CONCLUSIONS: Overall enrolment was low, yet uptake was high among those that enroled and did not differ across most demographics and symptom presentations. Future directions include evaluating respondents' attitudes towards treatment-promoting tools and removing barriers to uptake.

Development and usability testing of a cognitive-behavioral therapy-guided self-help mobile app and social media group for the post-acute treatment of anorexia nervosa.

OBJECTIVE: Anorexia nervosa (AN) is often treated in the acute setting, but relapse after treatment is common. Cognitive-behavioral therapy (CBT) is useful in the post-acute period, but access to trained providers is limited. Social support is also critical during this period. This study utilized a user-centered design approach to develop and evaluate the usability of a CBT-based mobile app and social networking component for post-acute AN support. METHOD: Participants (N = 19) were recently discharged from acute treatment for AN. Usability testing of the intervention was conducted over three cycles; assessments included the System Usability Scale (SUS), the Usefulness, Satisfaction, and Ease of Use Questionnaire (USE), the Mobile Application Rating Scale (MARS), a social media questionnaire, and a semi-structured interview. RESULTS: Interview feedback detailed aspects of the app that participants enjoyed and those needing improvement. Feedback converged on three themes: Logistical App Feedback, boosting recovery, and Real-World App/Social Media Use. USE and MARS scores were above average and SUS scores were "good" to "excellent" across cycles. CONCLUSION: This study provides evidence of feasibility and acceptability of an app and social networking feature for post-acute care of AN. The intervention has potential for offering scalable support for individuals with AN in the high-risk period following discharge from acute care.

Adaptations of an Online Cognitive-Behavioral Therapy Intervention for Binge-Purge Type Eating Disorders in Publicly-Insured and Uninsured Adults: A Pilot Study.

Background Publicly-insured and uninsured individuals-many of whom are marginalized because of race/ethnicity, disability and/or sexual preferences-experience barriers to accessing evidence-based interventions for eating disorders (EDs). Additionally, EBIs have not been developed with or for diverse populations, exacerbating poor treatment uptake. Mobile technology is perfectly positioned to bridge this gap and increase access to low-cost, culturally-sensitive EBIs. Methods This study leverages a user-centered design approach to adapt an existing coached cognitive-behavioral therapy-based digital program and evaluate its usability in a sample of 11 participants with (sub)clinical binge-purge type EDs who are publicly-insured ( n = 10) or uninsured ( n = 1). Participants were primarily Non-Hispanic White ( n = 8) women ( n = 8). Two semi-structured interviews occurred with participants: one to assess treatment needs and the other to obtain app-specific feedback. Interviews were coded using inductive thematic analysis. Results Interview 1 feedback converged on three themes: Recovery Journey, Treatment Experiences, and Engagement with and Expectations for Online Programs. Participants endorsed facing barriers to healthcare, such as poor insurance coverage and a lack of trained providers, and interest in a coach to increase treatment accountability. Interview 2 feedback converged on three themes: Content Development, Participant Experiences with Mental Health, and Real-World Use. Participants liked the content but emphasized the need to improve diverse representation (e.g., gender, body size). Conclusions Overall, user feedback is critical to informing adaptations to the original EBI so that the intervention can be appropriately tailored to the needs of this underserved population, which ultimately has high potential to address critical barriers to ED treatment. Trial Registration This study was reviewed and approved by the Institutional Review Board (IRB) at the University California, San Francisco (IRB #22-35936) and the IRB at Washington University in St. Louis (IRB ID 202304167).

Action recommendations review in community-based therapy and depression and anxiety outcomes: a machine learning approach.

BACKGROUND: While the positive impact of homework completion on symptom alleviation is well-established, the pivotal role of therapists in reviewing these assignments has been under-investigated. This study examined therapists' practice of assigning and reviewing action recommendations in therapy sessions, and how it correlates with patients' depression and anxiety outcomes. METHODS: We analyzed 2,444 therapy sessions from community-based behavioral health programs. Machine learning models and natural language processing techniques were deployed to discern action recommendations and their subsequent reviews. The extent of the review was quantified by measuring the proportion of session dialogues reviewing action recommendations, a metric we refer to as "review percentage". Using Generalized Estimating Equations modeling, we evaluated the correlation between this metric and changes in clients' depression and anxiety scores. RESULTS: Our models achieved 76% precision in capturing action recommendations and 71.1% in reviewing them. Using these models, we found that therapists typically provided clients with one to eight action recommendations per session to engage in outside therapy. However, only half of the sessions included a review of previously assigned action recommendations. We identified a significant interaction between the initial depression score and the review percentage (p = 0.045). When adjusting for this relationship, the review percentage was positively and significantly associated with a reduction in depression score (p = 0.032). This suggests that more frequent review of action recommendations in therapy relates to greater improvement in depression symptoms. Further analyses highlighted this association for mild depression (p = 0.024), but not for anxiety or moderate to severe depression. CONCLUSIONS: An observed positive association exists between therapists' review of previous sessions' action recommendations and improved treatment outcomes among clients with mild depression, highlighting the possible advantages of consistently revisiting therapeutic homework in real-world therapy settings. Results underscore the importance of developing effective strategies to help therapists maintain continuity between therapy sessions, potentially enhancing the impact of therapy.

Internalizing psychopathology and its links to suicidal ideation, dysfunctional attitudes, and help-seeking readiness in a national sample of college students.

BACKGROUND: Recent evidence suggests that multiple emotional disorders may be better assessed using dimensional models of psychopathology. The current study utilized a cross-sectional population survey of college students (N = 8613 participants) to examine the extent to which broad psychopathology factors accounted for specific associations between emotional problems and clinical and behavioral validators: suicidality, dysfunctional attitudes, and treatment seeking. METHODS: Confirmatory factor models were estimated to identify the best structure of psychopathology. Models were then estimated to examine the broad and specific associations between each psychopathology indicator and the clinical and behavioral validators. RESULTS: The hierarchical model of psychopathology with internalizing problems at the top, fear, and distress at the second level, and five specific symptom dimensions at the third level evidenced the best fit. The associations between symptom indicators of psychopathology and clinical and behavioral validators were relatively small and inconsistent. Instead, much of the association between clinical and behavioral validators and emotional problems operated at a higher-order level. LIMITATIONS: The cross-sectional nature of the survey precludes the ability to make conclusions regarding causality. CONCLUSIONS: Researchers should focus on investigating the shared or common components across emotional disorders, particularly concerning individuals presenting with higher rates of suicidal ideation dysfunctional attitudes, and help-seeking behavior. Using higher-order dimensions of psychopathology could simplify the complex presentation of multiple co-occurring disorders and suggest valid constructs for future investigations.

Prevalence, characteristics, and correlates of probable avoidant/restrictive food intake disorder among adult respondents to the National Eating Disorders Association online screen: a cross-sectional study.

BACKGROUND: Avoidant/restrictive food intake disorder (ARFID) is a serious, albeit under-researched, feeding or eating disorder. This exploratory study utilized data from adult respondents to the National Eating Disorders Association online eating disorder screen to validate items assessing the presence of ARFID and examine the prevalence, clinical characteristics, and correlates of a positive ARFID screen. METHODS: Among 50,082 adult screen respondents between January 2022 and January 2023, the prevalence of a positive ARFID screen was calculated. Chi-square tests and t-tests compared demographics, eating disorder attitudes and behaviors, suicidal ideation, current eating disorder treatment status, and eating disorder treatment-seeking intentions between respondents with possible ARFID and other eating disorder diagnostic and risk categories. Clinical characteristics of respondents with possible ARFID were also examined. RESULTS: 2378 (4.7%) adult respondents screened positive for ARFID. Respondents with possible ARFID tended to be younger, male, and have lower household income, and were less likely to be White and more likely to be Hispanic/Latino than most other diagnostic/risk groups. They had lower weight/shape concerns and eating disorder behaviors than most other diagnoses and higher BMI than those with AN. 35% reported suicidal ideation, 47% reported intentions to seek treatment for an eating disorder, and 2% reported currently being in treatment. The most common clinical feature of ARFID was lack of interest in eating (80%), followed by food sensory avoidance (55%) and avoidance of food due to fear of aversive consequences (31%). CONCLUSIONS: Findings from this study indicated that ARFID was prevalent among adult screen respondents and more common among individuals who were younger, male, non-White, Hispanic, and lower income relative to those with other eating disorders, at risk for an eating disorder, or at low risk. Individuals with possible ARFID frequently reported suicidal ideation and were rarely in treatment for an eating disorder. Further research is urgently needed to improve advances in the assessment and treatment of ARFID and improve access to care in order to prevent prolonged illness duration.

This study examined data from adult respondents to a publicly available online eating disorders screen adult to examine the prevalence, clinical characteristics, and correlates of a positive ARFID screen. 4.7% of respondents screened positive for ARFID. A positive ARFID screen was more common among respondents who were younger, male, non-White, Hispanic, and lower income relative to those in other eating disorder diagnostic/risk categories. Respondents with possible ARFID frequently reported suicidal ideation and were rarely in treatment for an eating disorder. Lack of interest in food or eating was the most common clinical feature among those with possible ARFID.

Using Social Influence Strategies to Improve Rates of Online Mental Health Survey Participation: Results from Two Experiments.

Online surveys are routinely used in mental health screening and treatment follow-up assessment, though they can yield low response rates. We tested the effects of social psychology-informed influence strategies for increasing rates of participation in an online mental health screening survey (Experiment 1) and a treatment follow-up survey (Experiment 2). In Experiment 1 (N = 45,569), embedding one or any combination of three motivational appeals (personal gain, community gain, and inclusivity) in screening survey invitation and reminder emails unexpectedly led to lower rates of survey participation compared to when the appeals were not included (overall participation rate = 12.02%, ORs = 0.75 to 0.97, ps < .001). In Experiment 2 (N = 873), a video of a TikTok influencer encouraging survey participation embedded in treatment follow-up survey invitation and reminder emails did not significantly affect survey completion compared to a humorous gif unrelated to survey participation (overall participation rate = 47.88%, OR = 1.18, p = .200). Moderator analyses revealed that the video led to higher rates of participation than the gif among White participants (OR = 1.39, p = .031) and non-Hispanic participants (OR = 1.35, p = .029) only, whereas the video led to lower rates of participation than the gif among students who did not disclose their race (OR = 0.31, p = .010). Results suggested that efforts to improve online survey participation should be balanced with possible downsides (e.g., added email length) and should be evaluated for differential performance among population subgroups prior to widespread implementation.

Reach and uptake of digital mental health interventions based on cognitive-behavioral therapy for college students: A systematic review.

Background: Mental health problems are increasing in prevalence among college students, yet few students receive treatment due to barriers such as insufficient resources in college counseling centers. Digital mental health interventions (DMHIs) have potential to overcome barriers and offer accessible, evidence-based care to college students. However, to evaluate the true public health impact of evidence-based DMHIs, it is important to assess the reach and uptake rates of DMHIs on college campuses. Objectives: We conducted a systematic review to examine the reach (i.e., % of invited students who express interest) and uptake (i.e., % of enrolled participants who initiate an intervention) of DMHIs based on cognitive-behavioral therapy (CBT) for college students. Methods: Eight databases were searched. Inclusion criteria included: (1) college population; (2) experimental design; (3) CBT-based intervention; (4) intervention targeting specific mental health conditions; and (5) digital intervention. Reach and uptake rates were calculated from data reported. A systematic narrative review framework was used to synthesize results. Results: Of 10,315 articles screened, 90 were included. Seventeen studies (19%) reported sufficient data to calculate reach; 35 studies (39%) reported uptake rates. Of studies that reported reach or uptake, most evaluated unguided (n = 20) or guided (n = 16) self-help programs. Measurement methods varied widely. Overall reach was low, whereas uptake was high among enrolled participants. Discussion: Despite evidence that improving reach and uptake can increase the public health impact of DMHIs, most studies did not report on either outcome. Suggested practices to improve these outcomes, and their reporting, are discussed.

Preferred treatment focus among college students with eating disorders and comorbid mental health problems in a digital cognitive-behavioral guided self-help program.

OBJECTIVE: To examine the mental health problems that college students with eating disorders (EDs) and comorbid depression and/or anxiety disorders preferred to target first in a digital treatment program and explore correlates of preferred treatment focus. METHODS: Four hundred and eighty nine college student users of a digital cognitive-behavioral guided self-help program targeting common mental health problems (76.7% female, Mage = 20.4 ± 4.4, 64.8% White) screened positive for an ED and ≥one other clinical mental health problem (i.e., depression, generalized anxiety disorder, social phobia, and/or panic disorder). Students also reported on insomnia, post-traumatic stress, alcohol use, and suicide risk. Before treatment, they indicated the mental health problem that they preferred to target first in treatment. Preferred treatment focus was characterized by diagnostic profile (i.e., ED + Depression, ED + Anxiety, ED + Depression + Anxiety), symptom severity, and demographics. RESULTS: 58% of students with ED + Anxiety, 47% of those with ED + Depression, and 27% of those with ED + Depression + Anxiety chose to target EDs first. Across diagnostic profiles, those who chose to target EDs first had more severe ED symptoms than those who chose to target anxiety or depression (ps < .05). Among students with ED + Depression + Anxiety, those who chose to target EDs first had lower depression symptoms than those who chose to target depression, lower generalized anxiety than those who chose to target anxiety, and lower suicidality than those who chose to target anxiety or depression (ps < .01). CONCLUSIONS: Students with EDs and comorbid depression and/or anxiety disorders showed variable preferred treatment focus across diagnostic profiles. Research should explore specific symptom presentations associated with preferred treatment focus. PUBLIC SIGNIFICANCE: Findings indicate that a sizable percentage of college students with depression/anxiety who also have EDs prefer to target EDs first in treatment, highlighting the importance of increasing availability of ED interventions to college students. Students with EDs and comorbid depression and/or anxiety disorders showed variable preferred treatment focus across diagnostic profiles, and preference to target EDs was associated with greater ED psychopathology across diagnostic profiles.

Evaluation of a combined, online intervention for binge-type eating disorders and high body weight in young adults.

BACKGROUND: Binge-type eating disorders (EDs; i.e., bulimia nervosa, binge eating disorder) are common among young adults with high body weight, yet few interventions target both conditions. This study tested an online guided self-help intervention that provided cognitive behavioral therapy (CBT) tools for EDs and behavioral weight loss (BWL) content to young adults with binge-type EDs and high body weight. METHOD: 60 adults aged 18-39 with clinical/subclinical binge-type EDs and high body weight were randomized to a combined condition or a CBT-only condition. Participants received self-help content for 8 weeks and self-reported ED attitudes, frequency of binge eating and compensatory behaviors, and weight at baseline, 4-weeks, and 8-weeks. Linear mixed models and negative binomial models compared changes between conditions in ED attitudes, ED behaviors, and weight at each timepoint. Chi-square test and independent samples t-test compared program completion and session engagement between conditions. RESULTS: No significant differences in weight change or ED symptom change emerged between the conditions. Both conditions achieved significant reductions in ED attitudes, binge episodes, and compensatory behaviors from baseline to 8-weeks (ps < .05). Neither condition demonstrated significant weight loss from baseline to 8-weeks. Program completion (47 %) and session engagement (57 %) were equally high across conditions. DISCUSSION: Both conditions achieved ED symptom change; however, neither condition was associated with weight change. Research is needed to identify the types of strategies and doses of BWL that promote clinically significant weight and ED symptom change in young adults.

Psychotherapy utilization by United States college students.

Objective: We studied current psychotherapy utilization rates among college students with mental health problems and identified characteristics associated with differential utilization. Participants: Nationwide online survey of students screening positive for at least one clinical mental health problem (N = 18,435). Methods: Rates and correlates of psychotherapy utilization were analyzed descriptively and with logistic regression. Results: Sample-wide, 19% reported receiving psychotherapy. Being male (vs. female), being Asian, Black or African American, or Multiracial (vs. White), greater financial difficulty, lower parent education, lower year in school, and attending a public (vs. private) institution were associated with lower utilization. Holding a gender minority (vs. female) identity and holding a sexual minority (vs. heterosexual) identity were associated with higher utilization. Utilization fell from Fall 2019 to Spring 2020, early during the COVID-19 pandemic, and subsequently rebounded. Conclusions: This study estimates current psychotherapy utilization among students with mental health problems and identifies possibly underserved populations.

The relation of food insecurity to eating disorder characteristics and treatment-seeking among adult respondents to the National Eating Disorders Association online screen.

BACKGROUND: Food insecurity (FI), characterized by limited or uncertain access to adequate food, has been associated with eating disorders (EDs). This study explored whether FI was associated with ED behaviors, ED diagnosis, current treatment status, and treatment-seeking intentions among adults who completed an online ED screen. METHODS: Respondents to the National Eating Disorders Association online screening tool self-reported demographics, FI, height and weight, past 3-month ED behaviors, and current treatment status. Respondents were also asked an optional question about treatment-seeking intentions. Hierarchical regressions evaluated relations between FI and ED behaviors, treatment status, and treatment-seeking intentions. Logistic regressions explored differences in probable ED diagnosis by FI status. RESULTS: Of 8714 respondents, 25 % screened at risk for FI. FI was associated with greater binge eating (R2Change = 0.006), laxative use (R2Change = 0.001), and presence of dietary restriction (R2Change = 0.001, OR: 1.32) (ps < .05). Having FI was associated with greater odds of screening positive for a probable ED or as high risk for an ED (ps < .05). FI was not associated with current treatment status or treatment-seeking intentions (ps > .05). CONCLUSIONS: Findings add to existing literature supporting a relation between FI and EDs. Implications include a need to disseminate EDs screening and treatment resources to populations affected by FI and to tailor treatments to account for barriers caused by FI.

Prevalence, Characteristics, and Correlates of Avoidant/Restrictive Food Intake Disorder among Adult Respondents to the National Eating Disorders Association Online Screen: A Cross-Sectional Study.

Background: Avoidant/restrictive food intake disorder (ARFID) is a serious, albeit under-researched, feeding or eating disorder. This exploratory study utilized data from adult respondents to the National Eating Disorders Association (NEDA) online eating disorder screen to validate items assessing the presence of ARFID and examine the prevalence, clinical characteristics, and correlates of a positive ARFID screen compared to other probable eating disorder/risk categories. Methods: Among 47,705 adult screen respondents between January 2022 and January 2023, the prevalence of a positive ARFID screen was calculated. Chi-square tests and t-tests compared demographics, eating disorder attitudes and behaviors, suicidal ideation, current eating disorder treatment status, and eating disorder treatment-seeking intentions between respondents with possible ARFID and other eating disorder diagnostic and risk categories. Clinical characteristics of respondents with possible ARFID were also examined. Results: 2,378 (5.0%) adult respondents screened positive for ARFID. Respondents with possible ARFID tended to be younger, male, and have lower household income, and were less likely to be White and more likely to be Hispanic/Latino than most other diagnostic/risk groups. They had lower weight/shape concerns and eating disorder behaviors than all other diagnoses but higher BMI than those with AN. 35% reported suicidal ideation, 47% reported intentions to seek treatment for an eating disorder, and 2% reported currently being in treatment. The most common clinical feature of ARFID was lack of interest in eating (80%), followed by food sensory avoidance (55%) and avoidance of food due to fear of aversive consequences (31%). Conclusions: Findings from this study indicated that ARFID was prevalent among adult screen respondents and more common among individuals who were younger, male, non-White, Hispanic, and lower income relative to those with other eating disorders or at risk for an eating disorder. Individuals with possible ARFID frequently reported suicidal ideation and were rarely in treatment for an eating disorder. Further research is urgently needed to improve advances in the assessment and treatment of ARFID and improve access to care in order to prevent prolonged illness duration.

Adapting a mobile app to support patients with anorexia nervosa following post-acute care: perspectives from eating disorder treatment center stakeholders.

Introduction: Anorexia nervosa (AN) is a harmful, life-threatening illness. Patients with severe AN often receive acute treatment but, upon discharge, experience high relapse rates. Evidence-based, outpatient treatment following acute care is critical to preventing relapse; however, numerous barriers (e.g., location, financial limitations, low availability of providers) preclude individuals from accessing treatment. mHealth technologies may help to address these barriers, but research on such digital approaches for those with AN is limited. Further, such technologies should be developed with all relevant stakeholder input considered from the outset. As such, the present study aimed to garner feedback from eating disorder (ED) treatment center providers on (1) the process of discharging patients to outpatient services, (2) their experiences with technology as a treatment tool, and (3) how future mHealth technologies may be harnessed to offer the most benefit to patients in the post-acute period. Methods: Participants (N = 11, from 7 ED treatment centers across the United States) were interviewed. To analyze the data for this study, each interview was manually transcribed and analyzed using components of Braun and Clarke's six-phase thematic analysis framework (Braun & Clarke, 2006). Results: Participants indicated proactively securing outpatient care for their patients, but mentioned several barriers their patients face in accessing evidence-based ED treatment. All participants had some experience using various technologies for treatment (e.g., teletherapy, self-monitoring apps), and mentioned a high level of interest in the development of a new app to be used by patients recently discharged from acute treatment for AN. Participants also offered suggestions of effective and relevant content for a potential app and adjunctive social networking component for post-acute care of AN. Discussion: Overall, participants expressed positive attitudes toward the integration of an app into the care flow, suggesting the high potential benefit of harnessing technology to support individuals recovering from AN.

Machine Learning Model to Predict Assignment of Therapy Homework in Behavioral Treatments: Algorithm Development and Validation.

BACKGROUND: Therapeutic homework is a core element of cognitive and behavioral interventions, and greater homework compliance predicts improved treatment outcomes. To date, research in this area has relied mostly on therapists' and clients' self-reports or studies carried out in academic settings, and there is little knowledge on how homework is used as a treatment intervention in routine clinical care. OBJECTIVE: This study tested whether a machine learning (ML) model using natural language processing could identify homework assignments in behavioral health sessions. By leveraging this technology, we sought to develop a more objective and accurate method for detecting the presence of homework in therapy sessions. METHODS: We analyzed 34,497 audio-recorded treatment sessions provided in 8 behavioral health care programs via an artificial intelligence (AI) platform designed for therapy provided by Eleos Health. Therapist and client utterances were captured and analyzed via the AI platform. Experts reviewed the homework assigned in 100 sessions to create classifications. Next, we sampled 4000 sessions and labeled therapist-client microdialogues that suggested homework to train an unsupervised sentence embedding model. This model was trained on 2.83 million therapist-client microdialogues. RESULTS: An analysis of 100 random sessions found that homework was assigned in 61% (n=61) of sessions, and in 34% (n=21) of these cases, more than one homework assignment was provided. Homework addressed practicing skills (n=34, 37%), taking action (n=26, 28.5%), journaling (n=17, 19%), and learning new skills (n=14, 15%). Our classifier reached a 72% F1-score, outperforming state-of-the-art ML models. The therapists reviewing the microdialogues agreed in 90% (n=90) of cases on whether or not homework was assigned. CONCLUSIONS: The findings of this study demonstrate the potential of ML and natural language processing to improve the detection of therapeutic homework assignments in behavioral health sessions. Our findings highlight the importance of accurately capturing homework in real-world settings and the potential for AI to support therapists in providing evidence-based care and increasing fidelity with science-backed interventions. By identifying areas where AI can facilitate homework assignments and tracking, such as reminding therapists to prescribe homework and reducing the charting associated with homework, we can ultimately improve the overall quality of behavioral health care. Additionally, our approach can be extended to investigate the impact of homework assignments on therapeutic outcomes, providing insights into the effectiveness of specific types of homework.

Longitudinal relationships between sub-clinical depression, sub-clinical eating disorders and health-related quality of life in early adolescence.

OBJECTIVE: A comprehensive understanding of the relationship between depressive symptoms and eating disorder (ED) symptoms requires consideration of additional variables that may influence this relationship. Health-related quality of life (HRQOL) has been associated with both depression and EDs; however, there is limited evidence to demonstrate how all three variables interact over time. This study sought to explore the bi-directional relationships between depressive symptoms, ED symptoms and HRQOL in a large community sample of young adolescents METHOD: Adolescents (N = 1393) aged between 11 and 14 years (M = 12.50, SD = 0.38) completed an online survey measuring depressive symptoms, ED symptoms and HRQOL. Two-level autoregressive cross-lagged models with three variables (i.e., depressive symptoms, HRQOL and ED) assessed across two time points (T1 and T2) were created to address the study aims. RESULTS: HRQOL was found to predict depressive symptoms and depressive symptoms were found to predict ED symptoms. Components of HRQOL (i.e., social relationships and ability to cope) were found to share a differential relationship with depressive symptoms. Inability to cope predicted depressive symptoms and depressive symptoms predicted negative social relationships. EDs were found to predict reduced HRQOL and negative social relationships. DISCUSSION: Findings suggest prevention and early intervention programs designed to address adolescent depression should focus on improving HRQOL. Future research should assess the relationship between HRQOL and individual ED symptoms (e.g., body-related ED symptoms, restrictive symptoms) as a means of exploring relationships that may have been masked by assessing ED symptoms using a total score. PUBLIC SIGNIFICANCE: This study sought to explore how eating disorders, depressive symptoms, and health-related quality of life (HRQOL) relate over time in a sample of young adolescents. Findings indicate adolescents who self-reported lower levels of HRQOL, including a reduced ability to cope, are at risk of experiencing depressive symptoms. Adolescents should be provided with the tools to develop problem-focused coping strategies as a means of reducing depressive symptoms.

Moderators and mediators of a digital cognitive behavior therapy-guided self-help intervention for eating disorders: Informing future design efforts.

OBJECTIVE: The Student Bodies-Eating Disorders intervention (SB-ED), a digital cognitive behavior therapy-guided self-help intervention for college women with an eating disorder, is effective for reducing eating disorder psychopathology. The purpose of this study was to evaluate moderators and mediators of the SB-ED intervention. To our knowledge, this is the first evaluation of clinical mediators of a digital intervention for women with eating disorders. METHOD: This is an exploratory secondary analysis of a cluster randomized trial comparing the SB-ED intervention to referral to usual care among 690 women at 27 United States colleges. Moderators included body mass index (BMI), race, ethnicity, weight/shape concerns, eating disorder impairment, thin ideal internalization, depression, anxiety, and motivation for treatment, assessed at baseline. Thin ideal internalization and depressive symptoms were tested as predictors at postintervention and mediators at 2-year follow-up. Outcome was change in global eating disorder psychopathology. RESULTS: BMI moderated the effect of the intervention at follow-up (but not posttreatment), with individuals with a lower BMI experiencing more continued improvements in eating disorder psychopathology following the intervention than individuals with a higher BMI. Thin ideal internalization mediated the effect of the intervention at follow-up, and depression partially mediated the effect of the intervention at follow-up. CONCLUSIONS: Results of the mediator analyses suggest that helping college women reduce inflated internalization of the thin ideal and improve depressive symptoms leads to improvements in eating disorder psychopathology. Results also suggest opportunities to optimize the intervention so individuals across the BMI spectrum experience ongoing improvements over time. (PsycInfo Database Record (c) 2023 APA, all rights reserved).