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.

Randomized Controlled Trial of a Web-Based Intervention to Disseminate Clinical Practice Guidelines for Posttraumatic Stress Disorder: The PTSD Clinicians Exchange.

Delivery of best-practice care for posttraumatic stress disorder (PTSD) is a priority for clinicians working with active duty military personnel and veterans. The PTSD Clinicians Exchange, an Internet-based intervention, was designed to assist in disseminating clinically relevant information and resources that support delivery of key practices endorsed in the Veterans Administration (VA)-Department of Defense (DoD) Clinical Practice Guidelines (CPG) for the Management of Posttraumatic Stress. We conducted a randomized controlled trial to examine the effectiveness of the Clinicians Exchange intervention in increasing familiarity and perceived benefits of 26 CPG-related and emerging practices. The intervention consisted of ongoing access to an Internet resource featuring best-in-class resources for practices, self-management of burnout, and biweekly e-mail reminders highlighting selected practices. Mental health clinicians (N = 605) were recruited from three service sectors (VA, DoD, community); 32.7% of participants assigned to the Internet intervention accessed the site to view resources. Individuals who were offered the intervention increased their practice familiarity ratings significantly more than those assigned to a newsletter-only control condition, d = 0.27, p = .005. From baseline to 12-months, mean familiarity ratings of clinicians in the intervention group increased from 3.0 to 3.4 on scale of 1 (not at all) to 5 (extremely); mean ratings for the control group were 3.2 at both assessments. Clinicians generally viewed the CPG practices favorably, rating them as likely to benefit their clients. The results suggest that Internet-based resources may aid more comprehensive efforts to disseminate CPGs, but increasing clinician engagement will be important.

Using Digital Technology to Reduce the Prevalence of Mental Health Disorders in Populations: Time for a New Approach.

Digital technology, which includes the collection, analysis, and use of data from a variety of digital devices, has the potential to reduce the prevalence of disorders and improve mental health in populations. Among the many advantages of digital technology is that it allows preventive and clinical interventions, both of which are needed to reduce the prevalence of mental health disorders, to be feasibly integrated into health care and community delivery systems and delivered at scale. However, the use of digital technology also presents several challenges, including how systems can manage and implement interventions in a rapidly changing digital environment and handle critical issues that affect population-wide outcomes, including reaching the targeted population, obtaining meaningful levels of uptake and use of interventions, and achieving significant outcomes. We describe a possible solution, which is to have an outcome optimization team that focuses on the dynamic use of data to adapt interventions for populations, while at the same time, addressing the complex relationships among reach, uptake, use, and outcome. We use the example of eating disorders in young people to illustrate how this solution could be implemented at scale. We also discuss system, practitioner-related, and other issues related to the adaptation of such an approach. Digital technology has great potential for facilitating the reduction of mental illness rates in populations. However, achieving this goal will require the implementation of new approaches. As a solution, we argue for the need to create outcome optimization teams, tasked with integrating data from various sources and using advanced data analytics and new designs to develop interventions/strategies to increase reach, uptake, use/engagement, and outcomes for both preventive and treatment interventions.

Optimizing eating disorder treatment outcomes for individuals identified via screening: An idea worth researching.

In recent years, online screens have been commonly used to identify individuals who may have eating disorders (EDs), many of whom may be interested in treatment. We describe a new empirical approach that takes advantage of current evidence on empirically supported, effective treatments, while at the same time, uses modern statistical frameworks and experimental designs, data-driven science, and user-centered design methods to study ways to expand the reach of programs, enhance our understanding of what works for whom, and improve outcomes, overall and in subpopulations. The research would focus on individuals with EDs identified through screening and would use continuously monitored data, and interactions of interventions/approaches to optimize reach, uptake, engagement, and outcome. Outcome would be assessed at the population, rather than individual level. The idea worth researching is to determine if an optimization outcome model produces significantly higher rates of clinical improvement at a population level than do current approaches, in which traditional interventions are only offered to the few people who are interested in and able to access them.

Beliefs and Attitudes About the Dissemination and Implementation of Internet-Based Self-Care Programs in a Large Integrated Healthcare System.

Behavioral intervention technologies (BITs) are online programs or mobile applications that deliver behavioral health interventions for self-care. The dissemination and implementation of such programs in U.S. healthcare systems has not been widely undertaken. To better understand these phenomena, we explored perspectives on BIT deployment in the Veterans Health Administration. Interviews from 20 providers, administrators, and policy makers were analyzed using qualitative methods. Eight themes were identified including the use of traditional healthcare delivery models, strategies for technology dissemination and implementation, internet infrastructure, leadership, health system structure, regulations, and strategic priorities. This research suggests policy, funding, and strategy development initiatives to promote the implementation and dissemination of BITs.

Maintenance and Reach of Exposure Psychotherapy for Posttraumatic Stress Disorder 18 Months After Training.

This study examined aspects of clinicians' work environment that facilitated sustained use of prolonged exposure (PE) therapy. Surveys were completed by 566 U.S. Department of Veterans Affairs clinicians 6 and 18 months after intensive training in PE. The number of patients treated with PE at 18 months (reach) was modeled as a function of clinician demographics, clinician beliefs about PE, and work context factors. There were 342 clinicians (60.4%) who used PE at 6 and 18 months after training, 58 (10.2%) who used PE at 18 but not 6 months, 95 (16.7%) who used PE at 6 but not 18 months, and 71 (12.5%) who never adopted PE. Median reach was 12% of clinicians' appointments with patients with posttraumatic stress disorder. Reach was predicted by flow of interested patients (incident response ratio [IRR] = 1.21 to 1.51), PE's perceived effectiveness (IRR = 1.04 to 1.31), working in a PTSD specialty clinic (IRR = 1.06 to 1.26), seeing more patients weekly (IRR = 1.04 to 1.25), and seeing fewer patients in groups (IRR = 0.83 to 0.99). Most clinicians trained in PE sustained use of the treatment, but on a limited basis. Strategies to increase reach of PE should address organizational barriers and patient engagement.

Reduction of Burnout in Mental Health Care Providers Using the Provider Resilience Mobile Application.

This pilot study examined the usability, acceptability, and effectiveness of a free Provider Resilience (PR) mobile application (app) designed by the National Center for Telehealth and Technology to reduce provider burnout. Outpatient mental health providers (N = 30) used the PR app for 1 month. Participants rated the PR app on the System Usability Scale with an overall score of 79.7, which is in the top quartile for usability. Results of paired sample t tests on the Professional Quality of Life Scale indicated significant decreases on the Burnout (t = 3.65, p < .001) and Compassion Fatigue (t = 4.54, p < .001) subscales. The Provider Resilience app shows promise in reducing burnout and compassion fatigue in mental health care providers.

Context Matters: Team and Organizational Factors Associated with Reach of Evidence-Based Psychotherapies for PTSD in the Veterans Health Administration.

Evidence-based psychotherapies for PTSD are often underused. The objective of this mixed-method study was to identify organizational and clinic factors that promote high levels of reach of evidence-based psychotherapies for PTSD 10 years into their dissemination throughout the Veterans Health Administration. We conducted 96 individual interviews with staff from ten outpatient PTSD teams at nine sites that differed in reach of evidence-based psychotherapies for PTSD. Major themes associated with reach included clinic mission, clinic leader and staff engagement, clinic operations, staff perceptions, and the practice environment. Strategies to improve reach of evidence-based psychotherapies should attend to organizational and team-level factors.

Advantages and psychometric validation of proximal intensive assessments of patient-reported outcomes collected in daily life.

OBJECTIVES: Ambulatory assessment data collection methods are increasingly used to study behavior, experiences, and patient-reported outcomes (PROs), such as emotions, cognitions, and symptoms in clinical samples. Data collected close in time at frequent and fixed intervals can assess PROs that are discrete or changing rapidly and provide information about temporal dynamics or mechanisms of change in clinical samples and individuals, but clinical researchers have not yet routinely and systematically investigated the reliability and validity of such measures or their potential added value over conventional measures. The present study provides a comprehensive, systematic evaluation of the psychometrics of several proximal intensive assessment (PIA) measures in a clinical sample and investigates whether PIA appears to assess meaningful differences in phenomena over time. METHODS: Data were collected on a variety of psychopathology constructs on handheld devices every 4 h for 7 days from 62 adults recently exposed to traumatic injury of themselves or a family member. Data were also collected on standard self-report measures of the same constructs at the time of enrollment, 1 week after enrollment, and 2 months after injury. RESULTS: For all measure scores, results showed good internal consistency across items and within persons over time, provided evidence of convergent, divergent, and construct validity, and showed significant between- and within-subject variability. CONCLUSIONS: Results indicate that PIA measures can provide valid measurement of psychopathology in a clinical sample. PIA may be useful to study mechanisms of change in clinical contexts, identify targets for change, and gauge treatment progress.

Comparison of the PTSD Checklist (PCL) Administered via a Mobile Device Relative to a Paper Form.

Mobile devices are increasingly used to administer self-report measures of mental health symptoms. There are significant differences, however, in the way that information is presented on mobile devices compared to the traditional paper forms that were used to administer such measures. Such differences may systematically alter responses. The present study evaluated if and how responses differed for a self-report measure, the PTSD Checklist (PCL), administered via mobile device relative to paper and pencil. Participants were 153 trauma-exposed individuals who completed counterbalanced administrations of the PCL on a mobile device and on paper. PCL total scores (d = 0.07) and item responses did not meaningfully or significantly differ across administrations. Power was sufficient to detect a difference in total score between administrations determined by prior work of 3.46 with a d = 0.23. The magnitude of differences between administration formats was unrelated to prior use of mobile devices or participant age. These findings suggest that responses to self-report measures administered via mobile device are equivalent to those obtained via paper and they can be used with experienced as well as naïve users of mobile devices.

Training in the implementation of prolonged exposure therapy: provider correlates of treatment outcome.

The authors examined the degree to which provider characteristics, such as profession, treatment orientation, prior experience in treating posttraumatic stress disorder (PTSD), prior experience with prolonged exposure (PE) therapy, and attitudes about PE, were related to the clinical outcomes of veterans receiving care from clinicians participating in the national Department of Veterans Affairs (VA) PE Training Program. Positive patient outcomes were achieved by providers of every profession, theoretical orientation, level of clinical experience treating PTSD, and prior PE training experience. With 1,105 providers and 32 predictors (13 provider variables), power was at least 90% power to detect an effect of ß = .15. Profession was the only provider characteristic significantly related to outcomes, but the mean effect (a 2 point difference on the PTSD Checklist) was too small to be clinically meaningful. The results support the intensive training model used in the VA PE training program and demonstrate that clinicians of varying backgrounds can be trained using interactive training workshops followed by case consultation to deliver PE effectively.

A Quantitative Test of an Implementation Framework in 38 VA Residential PTSD Programs.

This study examines the implementation of two evidence-based psychotherapies, Prolonged Exposure (PE) and Cognitive Processing Therapy (CPT), in the Department of Veterans Affairs residential Posttraumatic Stress Disorder treatment programs. Two hundred and one providers from 38 programs completed an online survey concerning implementation of PE delivered on an individual basis and CPT delivered in individual and group formats. For PE, a supportive organizational context (dedicated time and resources, and incentives and mandates) and overall positive view of the treatment were related to its implementation. For both group and individual CPT, only the supportive organizational context was significantly associated with outcome. Implications for implementation efforts are discussed.

Evaluation of an implementation model: a national investigation of VA residential programs.

This national investigation utilizes qualitative data to evaluate an implementation model regarding factors influencing provider use of two evidence-based treatments for posttraumatic stress disorder (PTSD). Semi-structured qualitative interviews with 198 mental health providers from 38 Department of Veterans Affairs' (VA) residential treatment programs were used to explore these issues regarding prolonged exposure (PE) and cognitive processing therapy (CPT) in VA residential PTSD programs. Several unique and some overlapping predictors emerged. Leadership was viewed as an influence on implementation for both CPT and PE, while a lack of dedicated time and resources was viewed as a deterrent for both. Compatibility of CPT with providers' existing practices and beliefs, the ability to observe noticeable patient improvement, a perceived relative advantage of CPT over alternative treatments, and the presence of a supportive peer network emerged as influential on CPT implementation. Leadership was associated with PE implementation. Implications for the design and improvement of training and implementation efforts are discussed.

Online self-administered training of PTSD treatment providers in cognitive-behavioral intervention skills: results of a randomized controlled trial.

Despite potential advantages in scalability and efficiency of web-based training for trauma providers, few controlled trials of feasibility and effectiveness of web-based mental health training have been performed. Our study compared web-based training in 3 intervention skills (motivation enhancement [ME], goal setting [GS], behavioral task assignment [BTA]) with web-based training plus telephone consultation, and a no-training control. The primary outcome measures included objective measures of skills acquisition (standardized patient assessments). Results showed significant differences among the training conditions. The overall tests of differences among the groups were statistically significant for ME and BTA skills (p < .001 and p = .005, respectively), but not for GS (p = .245). The web training plus consultation group improved in ME skills by 0.35 units compared to 0.12 units in the web only group (p < .001) and no change in the control group (p = .001). For BTA skills, the web training plus consultation improved by 0.27 units compared to 0.17 units in the web only group (p = .175) and no change in the control group (p = .004). Overall, these findings support the use of web-based dissemination for large-scale training programs for trauma providers in health care delivery systems. Further studies are needed to clarify the specific role of consultation as an adjunct to web-based training.

Factors related to clinician attitudes toward prolonged exposure therapy for PTSD.

This study examines pretraining attitudes toward prolonged exposure (PE) therapy in a sample of 1,275 mental health clinicians enrolled in a national PE training program sponsored by the U.S. Department of Veterans Affairs. Attitudes assessed via survey included values placed on outcomes targeted by PE, outcome expectancies (positive expectancies for patient improvement and negative expectancies related to patient deterioration, clinician time burden, and clinician emotional burden), and self-efficacy for delivering PE. Results indicated that clinicians were receptive to learning PE and had positive expectations about the treatment, but expressed concerns that PE might increase patient distress. Responses varied by clinician characteristics with psychologists, clinicians working in specialty PTSD treatment settings (as opposed to those in mental health clinics and other clinic types), and those with a primarily cognitive-behavioral orientation expressing attitudes that were most supportive of learning and implementing PE across various indicators. Implications for addressing attitudinal barriers to implementation of PE therapy are discussed.

Factors influencing readiness to deploy in disaster response: findings from a cross-sectional survey of the Department of Veterans Affairs Disaster Emergency Medical Personnel System.

BACKGROUND: The Disaster Emergency Medical Personnel System (DEMPS) program provides a system of volunteers whereby active or retired Department of Veterans Affairs (VA) personnel can register to be deployed to support other VA facilities or the nation during national emergencies or disasters. Both early and ongoing volunteer training is required to participate. METHODS: This study aims to identify factors that impact willingness to deploy in the event of an emergency. This analysis was based on responses from 2,385 survey respondents (response rate, 29%). Latent variable path models were developed and tested using the EQS structural equations modeling program. Background demographic variables of education, age, minority ethnicity, and female gender were used as predictors of intervening latent variables of DEMPS Volunteer Experience, Positive Attitude about Training, and Stress. The model had acceptable fit statistics, and all three intermediate latent variables significantly predicted the outcome latent variable Readiness to Deploy. RESULTS: DEMPS Volunteer Experience and a Positive Attitude about Training were associated with Readiness to Deploy. Stress was associated with decreased Readiness to Deploy. Female gender was negatively correlated with Readiness to Deploy; however, there was an indirect relationship between female gender and Readiness to Deploy through Positive Attitude about Training. CONCLUSIONS: These findings suggest that volunteer emergency management response programs such as DEMPS should consider how best to address the factors that may make women less ready to deploy than men in order to ensure adequate gender representation among emergency responders. The findings underscore the importance of training opportunities to ensure that gender-sensitive support is a strong component of emergency response, and may apply to other emergency response programs such as the Medical Reserve Corps and the American Red Cross.

Clinician perceptions of using a smartphone app with prolonged exposure therapy.

Clinician perceptions of clinical innovations affect their adoption and spread. This study investigated mental health clinicians' (n = 163) perceptions of a patient-facing smartphone application (app) for prolonged exposure (PE) therapy for posttraumatic stress disorder, before its public release. After reading a description of the app, participants rated perceptions of it based on diffusion of innovations theory constructs. Perceptions were generally favorable regarding the app's relative advantage over existing PE practices, compatibility with their values and needs, and complexity. Age (<40 years), smartphone ownership, and having used apps in care related to more favorable perceptions. Smartphone ownership, relative advantage, and complexity significantly predicted intention to use the app if it were available. These findings suggest that clinicians are receptive to using a PE app and that dissemination efforts should target sub-groups of PE clinicians to maximize adoption.

Anxiety sensitivity, finding the body, and posttraumatic stress disorder in suicide-bereaved treatment-seeking adults.

OBJECTIVE: Those bereaved by suicide are at greater risk of prolonged distress compared to those bereaved by other modes of death. Trauma- and emotion-related factors may increase this vulnerability. Finding the body of the deceased may intensify postsuicide distress. Anxiety sensitivity, fear of one's anxiety-related symptoms, has been positively associated with posttraumatic stress disorder (PTSD) in other trauma populations but has not been studied in the suicide bereaved. METHOD: This study examined the relationships among finding the body, anxiety sensitivity, and PTSD in a treatment-seeking, suicide-bereaved sample (N = 50). Pretreatment baseline data on demographics, the Anxiety Sensitivity Index, and the PTSD Checklist were analyzed. RESULTS: Younger age (r = -.31, p = .03), being a person of color (r = -.32, p = .02), and fewer days since the loss (r = -.30, p = .03) were associated with greater PTSD. Controlling for age, race, and days since the loss, PTSD was unrelated to finding the body, F(1, 45) = 0.01, p = .92, but was positively associated with anxiety sensitivity (pr = .32, p = .03). In simultaneous regression analyses, age, race, days since the loss, finding the body, and anxiety sensitivity accounted for 33% of the variance in PTSD, F(2, 44) = 4.29, p = .003; anxiety sensitivity was the only significant predictor of PTSD symptoms (ß = .36, t = 2.35, p = .02). CONCLUSIONS: Anxiety sensitivity has important implications for the development and maintenance of PTSD in the suicide bereaved and should be assessed and targeted in suicide postvention. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

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.