Linguistic measures of psychological distance track symptom levels and treatment outcomes in a large set of psychotherapy transcripts.

SignificanceUsing language to "distance" ourselves from distressing situations (i.e., by talking less about ourselves and the present moment) can help us manage emotions. Here, we translate this basic research to discover that such "linguistic distancing" is a replicable measure of mental health in a large set of therapy transcripts (N = 6,229). Additionally, clustering techniques showed that language alone could identify participants who differed on both symptom severity and treatment outcomes. These findings lay the foundation for 1) tools that can rapidly identify people in need of psychological services based on language alone and 2) linguistic interventions that can improve mental health.

Comparing Message-Based Psychotherapy to Once-Weekly, Video-Based Psychotherapy for Moderate Depression: Randomized Controlled Trial.

BACKGROUND: Despite the high prevalence of major depressive disorder and the related societal burden, access to effective traditional face-to-face or video-based psychotherapy is a challenge. An alternative that offers mental health care in a flexible setting is asynchronous messaging therapy. To date, no study has evaluated its efficacy and acceptability in a randomized controlled trial for depression. OBJECTIVE: The aim of this study was to compare the efficacy and acceptability of message-based psychotherapy for depression to once-weekly video-based psychotherapy. METHODS: In this 2-armed randomized controlled trial, individuals (N=83) with depressive symptomatology (Patient Health Questionnaire-9 ≥10) were recruited on the internet and randomly assigned to either a message-based intervention group (n=46) or a once-weekly video-based intervention group (n=37). Patients in the message-based treatment condition exchanged asynchronous messages with their therapist following an agreed-upon schedule. Patients in the video-based treatment condition met with their therapist once each week for a 45-minute video teletherapy session. Self-report data for depression, anxiety, and functional impairment were collected at pretreatment, weekly during treatment, at posttreatment, and at a 6-month follow-up. Self-reported treatment expectancy and credibility for the assigned intervention were assessed at pretreatment and therapeutic alliance at posttreatment. RESULTS: Findings from multilevel modeling indicated significant, medium-to-large improvements in depression (d=1.04; 95% CI 0.60-1.46), anxiety (d=0.61; 95% CI 0.22-0.99), and functional impairment (d=0.66; 95% CI 0.27-1.05) for patients in the message-based treatment condition. Changes in depression (d=0.11; 95% CI -0.43 to 0.66), anxiety (d=-0.01; 95% CI -0.56 to 0.53), and functional impairment (d=0.25; 95% CI -0.30 to 0.80) in the message-based treatment condition were noninferior to those in the video-based treatment condition. There were no significant differences in treatment credibility (d=-0.09; 95% CI -0.64 to 0.45), therapeutic alliance (d=-0.15; 95% CI -0.75 to 0.44), or engagement (d=0.24; 95% CI -0.20 to 0.67) between the 2 treatment conditions. CONCLUSIONS: Message-based psychotherapy could present an effective and accessible alternative treatment modality for patients who might not be able to engage in traditional scheduled services such as face-to-face or video-based psychotherapy. TRIAL REGISTRATION: ClinicalTrials.gov NCT05467787; https://www.clinicaltrials.gov/ct2/show/NCT05467787.

Assessing the quality of digital patient-therapist communication: the development and validation of a text-based facilitative interpersonal skills task.

OBJECTIVE: Text-based communication is becoming an increasingly salient feature of the psychotherapeutic landscape. Yet little is known about the factors distinguishing high- and low-quality therapeutic conversations taking place over this modality. Prior research on therapist effects has outlined several common factors associated with better clinical outcomes. But these common factors can only be researched in the context of text-based communication if they can be measured. Accordingly, we developed and validated a new behavioral task and coding system: the Facilitative Interpersonal Skills Performance Task for Text (FIS-T) to measure therapists' messaging quality across eight dimensions of facilitative interpersonal skill. METHODS: 1150 survey-takers rated the interpersonal dynamics and response difficulty of the FIS-T Task's text-based stimuli. The FIS-T was then administered to 64 therapists. RESULTS: The FIS-T stimuli displayed similar interpersonal dynamics to those elicited by the original FIS task, demonstrated a similar range of difficulties to those of the video-based stimuli of the original FIS Task, and showed high inter-rater reliability. CONCLUSIONS: The text-based FIS-T Task demonstrates high reliability and convergent validity with the original FIS Task, making it appropriate for use in assessing the common factors in text-based therapy. Future directions in the quality assessment of internet-delivered psychotherapies are discussed.

Modifiable predictors of nonresponse to psychotherapies for late-life depression with executive dysfunction: a machine learning approach.

The study aimed to: (1) Identify distinct trajectories of change in depressive symptoms by mid-treatment during psychotherapy for late-life depression with executive dysfunction; (2) examine if nonresponse by mid-treatment predicted poor response at treatment end; and (3) identify baseline characteristics predicting an early nonresponse trajectory by mid-treatment. A sample of 221 adults 60 years and older with major depression and executive dysfunction were randomized to 12 weeks of either problem-solving therapy or supportive therapy. We used Latent Growth Mixture Models (LGMM) to detect subgroups with distinct trajectories of change in depression by mid-treatment (6th week). We conducted regression analyses with LGMM subgroups as predictors of response at treatment end. We used random forest machine learning algorithms to identify baseline predictors of LGMM trajectories. We found that ~77.5% of participants had a declining trajectory of depression in weeks 0-6, while the remaining 22.5% had a persisting depression trajectory, with no treatment differences. The LGMM trajectories predicted remission and response at treatment end. A random forests model with high prediction accuracy (80%) showed that the strongest modifiable predictors of the persisting depression trajectory were low perceived social support, followed by high neuroticism, low treatment expectancy, and low perception of the therapist as accepting. Our results suggest that modifiable risk factors of early nonresponse to psychotherapy can be identified at the outset of treatment and addressed with targeted personalized interventions. Therapists may focus on increasing meaningful social interactions, addressing concerns related to treatment benefits, and creating a positive working relationship.

Comparing the streamlined psychotherapy "Engage" with problem-solving therapy in late-life major depression. A randomized clinical trial.

Effective psychotherapies for late-life depression are underutilized, mainly because of their complexity. "Engage" is a novel, streamlined psychotherapy that relies on neurobiology to identify core behavioral pathology of late-life depression and targets it with simple interventions, co-designed with community therapists so that they can be delivered in community settings. Consecutively recruited adults (≥60 years) with major depression (n = 249) were randomly assigned to 9 weekly sessions of "Engage" or to the evidence-based Problem-Solving Therapy (PST) offered by 35 trained community social workers and assessed by blind raters. "Engage" therapists required an average of 30% less training time to achieve fidelity to treatment than PST therapists and had one-third of the PST therapists' skill drift. Both treatments led to reduction of HAM-D scores over 9 weeks. The mixed effects model-estimated HAM-D ratings were not significantly different between the two treatments at any assessment point of the trial. The one-sided 95% CI for treatment-end difference was (-∞, 0.07) HAM-D points, indicating a non-inferiority margin of 1.3 HAM-D points or greater; this margin is lower than the pre-determined 2.2-point margin. The two treatment arms had similar response (HR = 1.08, 95% CI (0.76, 1.52), p = 0.67) and remission rates (HR = 0.89, 95% CI (0.57, 1.39), p = 0.61). We conclude that "Engage" is non-inferior to PST. If disseminated, "Engage" will increase the number of therapists who can reliably treat late-life depression and make effective psychotherapy available to large numbers of depressed older adults.

The Moderating Role of Working Alliance in the Association Between Depression and Suicide Ideation in Messaging Therapy.

Introduction: Suicide is one of the leading causes of death worldwide, and it can be prevented by psychotherapy. The objective of this study was to examine the risk factors predicting suicide ideation during messaging psychotherapy, and the moderating role of working alliance (WA) in the association between baseline depression and later suicide ideation. Materials and Methods: A large outpatient sample (n = 4,388) engaged in daily messaging with licensed clinicians from a telemedicine provider. Using a longitudinal design, depression and anxiety symptoms were assessed at baseline, using the Patient Health Questionnaire (PHQ-8) for depression and the Generalized Anxiety Disorder (GAD-7) for anxiety. The WA was measured with the short version of the Working Alliance Inventory after 3 weeks of therapy, and suicide ideation was assessed at baseline and after 6 weeks of therapy, by item 9 of the Patient Health Questionnaire (PHQ-9). Demographic measures were also assessed. Results: Results indicate that depression (ß = 0.09, p < 0.001), baseline suicide ideation (ß = 0.50, p < 0.001), and WA (ß = -0.08, p < 0.001), especially the task subscale (ß = -0.14, p < 0.001), significantly predicted suicide ideation after 6 weeks. WA (ß = -0.07, p < 0.001), especially the task (ß = -0.14, p < 0.001) and bond subscales (ß = 0.06, p = 0.002), moderated the association between depression at baseline and suicide ideation after 6 weeks, so that experiencing higher quality of WA decreased the association between depression and suicide ideation. Discussion and Conclusions: Suicide ideation may be reduced by experiencing the therapeutic relationship as beneficial, even among at-risk populations, which suffer from depressive symptoms. It is the first study to show this moderation effect in any platform of therapy.

Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions.

BACKGROUND: Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities is a critical factor in the treatment of depression. Assessing constructs relevant to BA currently requires the administration of standardized instruments, such as the Behavioral Activation for Depression Scale (BADS), which places a burden on patients and providers, among other potential limitations. Previous work has shown that depressed and nondepressed individuals may use language differently and that automated tools can detect these differences. The increasing use of online, chat-based mental health counseling presents an unparalleled resource for automated longitudinal linguistic analysis of patients with depression, with the potential to illuminate the role of reward exposure in recovery. OBJECTIVE: This work investigated how linguistic indicators of planning and participation in enjoyable activities identified in online, text-based counseling sessions relate to depression symptomatology over time. METHODS: Using distributional semantics methods applied to a large corpus of text-based online therapy sessions, we devised a set of novel BA-related categories for the Linguistic Inquiry and Word Count (LIWC) software package. We then analyzed the language used by 10,000 patients in online therapy chat logs for indicators of activation and other depression-related markers using LIWC. RESULTS: Despite their conceptual and operational differences, both previously established LIWC markers of depression and our novel linguistic indicators of activation were strongly associated with depression scores (Patient Health Questionnaire [PHQ]-9) and longitudinal patient trajectories. Emotional tone; pronoun rates; words related to sadness, health, and biology; and BA-related LIWC categories appear to be complementary, explaining more of the variance in the PHQ score together than they do independently. CONCLUSIONS: This study enables further work in automated diagnosis and assessment of depression, the refinement of BA psychotherapeutic strategies, and the development of predictive models for decision support.

Just in time crisis response: suicide alert system for telemedicine psychotherapy settings.

AbstractObjective: To design a Natural Language Processing (NLP) algorithm capable of detecting suicide content from patients' written communication to their therapists, to support rapid response and clinical decision making in telehealth settings. Method: A training dataset of therapy transcripts for 1,864 patients was established by detecting patient content endorsing suicidality using a proxy-model anchored on therapists' suicide prevention interventions; human expert raters then assessed the level of suicide risk endorsed by patients identified by the proxy-model (i.e., no risk, risk factors, ideation, method, or plan). A bag-of-words classification model was then iteratively built using the annotations from the expert raters to detect suicide risk level in 85,216 labeled patients' sentences from the training dataset. Results: The final NLP model identified risk-related content from non-risk content with good accuracy (AUC = 82.78). Conclusions: Risk for suicide could be reliably identified by the NLP algorithm. The risk detection model could assist telehealth clinicians in providing crisis resources in a timely manner. This modeling approach could also be applied to other psychotherapy research tasks to assist in the understanding of how the psychotherapy process unfolds for each patient and therapist.

Two-way messaging therapy for depression and anxiety: longitudinal response trajectories.

BACKGROUND: Telemedicine is a strategy for overcoming barriers to access evidence-based psychotherapy. Digital modalities that operate outside session-based treatment formats, such as ongoing two-way messaging, may further address these challenges. However, no study to date has established suitability criteria for this medium. METHODS: A large outpatient sample (n = 10,718) engaged in daily messaging with licensed clinicians from a telemedicine provider. Patients consisted of individuals from urban and rural settings in all 50 states of the US, who signed up to the telemedicine provider. Using a longitudinal design, symptoms changes were observed during a 12 week treatment course. Symptoms were assessed from baseline every three weeks using the Patient Health Questionnaire (PHQ-9) for depression, and the Generalized Anxiety Disorder (GAD-7) for anxiety. Demographics and engagement metrics, such as word count for both patients and therapists, were also assessed. Growth mixture modeling was used to tease apart symptoms trajectories, and identify predictors of treatment response. RESULTS: Two subpopulations had GAD-7 and PHQ-9 remission outcomes (Recovery and Acute Recovery, 30.7% of patients), while two others showed amelioration of symptoms (Depression and Anxiety Improvement, 36.9% of patients). Two subpopulations experienced no changes in symptoms (Chronic and Elevated Chronic, 32.4% of patients). Higher use of written communication, patient characteristics, and engagement metrics reliably distinguished patients with the greatest level of remission (Recovery and Acute Recovery groups). CONCLUSIONS: Remission of depression and anxiety symptoms was observed during delivery of psychotherapy through messaging. Improvement rates were consistent with face-to-face therapy, suggesting the suitability of two-way messaging psychotherapy delivery. Characteristics of improving patients were identified and could be used for treatment recommendation. These findings suggest the opportunity for further research, to directly compare messaging delivery with a control group of treatment as usual. TRIAL REGISTRATION: Clinicaltrials.gov Identifier: NCT03699488, Retrospectively Registered October 8, 2018.

A Study of Asynchronous Mobile-Enabled SMS Text Psychotherapy.

BACKGROUND: Many obstacles to obtaining psychotherapy continue to diminish its reach despite its documented positive effects. Using short message service (SMS) texting and Web platforms to enable licensed psychotherapists to deliver therapy directly to the lived context of the client is one possible solution. INTRODUCTION: Employing a feasibility study design, this pilot trial further evaluated the external validity for treatment outcomes of text therapy and extended findings to include mobile-enabled text platforms. MATERIALS AND METHODS: Adults seeking text therapy treatment for a variety of disorders were recruited from a text therapy service (N = 57). Clinical outcomes were measured using the General Health Questionnaire-12 (GHQ-12) through 15 weeks of treatment. A process variable, the therapeutic alliance, was measured with the Working Alliance Inventory. Treatment acceptability was assessed with ratings of satisfaction for several aspects of the treatment, including affordability, effectiveness, convenience, wait times to receiving treatment, and cost-effectiveness. RESULTS: Results indicate evidence for the effectiveness of the intervention (GHQ-12, Cohen's d = 1.3). Twenty-five (46%) participants experienced clinically significant symptom remission. Therapeutic alliance scores were lower than those found in traditional treatment settings, but still predicted symptom improvement (R2 = 0.299). High levels of satisfaction with text therapy were reported on dimensions of affordability, convenience, and effectiveness. Cost-effectiveness analyses suggest that text therapy is 42.2% the cost of traditional services and offers much reduced wait times. CONCLUSION: Mobile-enabled asynchronous text therapy with a licensed therapist is an acceptable and clinically beneficial medium for individuals with various diagnoses and histories of psychological distress.

GANEing on emotion and emotion regulation.

The function of emotion and its underlying neural mechanisms are often left underspecified. I extend the GANE (glutamate amplifies noradrenergic effects) model by examining its success in accounting for findings in emotion regulation. I also identify points of alignment with construction models of emotion and with the hypothesis that emotion states function to push neural activity toward rapid and efficient action.

At-home, telehealth-supported ketamine treatment for depression: Findings from longitudinal, machine learning and symptom network analysis of real-world data.

BACKGROUND: Improving safe and effective access to ketamine therapy is of high priority given the growing burden of mental illness. Telehealth-supported administration of sublingual ketamine is being explored toward this goal. METHODS: In this longitudinal study, moderately-to-severely depressed patients received four doses of ketamine at home over four weeks within a supportive digital health context. Treatment was structured to resemble methods of therapeutic psychedelic trials. Patients receiving a second course of treatment were also examined. Symptoms were assessed using the Patient Health Questionnaire (PHQ-9) for depression. We conducted preregistered machine learning and symptom network analyses to investigate outcomes (osf.io/v2rpx). RESULTS: A sample of 11,441 patients was analyzed, demonstrating a modal antidepressant response from both non-severe (n = 6384, 55.8 %) and severe (n = 2070, 18.1 %) baseline depression levels. Adverse events were detected in 3.0-4.8 % of participants and predominantly neurologic or psychiatric in nature. A second course of treatment helped extend improvements in patients who responded favorably to initial treatment. Improvement was most strongly predicted by lower depression scores and age at baseline. Symptoms of Depressed mood and Anhedonia sustained depression despite ongoing treatment. LIMITATIONS: This study was limited by the absence of comparison or control groups and lack of a fixed-dose procedure for ketamine administration. CONCLUSIONS: At-home, telehealth-supported ketamine administration was largely safe, well-tolerated, and associated with improvement in patients with depression. Strategies for combining psychedelic-oriented therapies with rigorous telehealth models, as explored here, may uniquely address barriers to mental health treatment.

Linguistic markers of anxiety and depression in Somatic Symptom and Related Disorders: Observational study of a digital intervention.

BACKGROUND: Somatic Symptom and Related Disorders (SSRD), including chronic pain, result in frequent primary care visits, depression and anxiety symptoms, and diminished quality of life. Treatment access remains limited due to structural barriers and functional impairment. Digital delivery offers to improve access and enables transcript analysis via Natural Language Processing (NLP) to inform treatment. Therefore, we investigated asynchronous message-delivered SSRD treatment, and used NLP methods to identify symptom reduction markers from emotional valence. METHODS: 173 individuals diagnosed with SSRD received interventions from licensed therapists via messaging 5 days/week for 8 weeks. Depression and anxiety symptoms were measured with the PHQ-9 and GAD-7 from baseline every three weeks. Symptoms trajectories were identified using unsupervised random forest clustering. Emotional valence expressed and use of emotional words were extracted from patients' de-identified transcripts, respectively using VADER and NCR Lexicon. Valence differences were examined using logistic regression. RESULTS: Two subpopulations were identified showing symptoms Improvement (n = 72; 41.62 %) and non-response (n = 101; 58.38 %). Improvement patients expressed more positive valence in the first week of treatment (OR = 1.84, CI: 1.12-3.02; p = .015) and were less likely to express negative valence by the end of treatment (OR = 0.05; CI: 0.30-0.83; p = .008). Non-response patients used more negative valence words, including pain. LIMITATIONS: Findings were derived from observational data obtained during an ecological intervention, without the inclusion of a control group. CONCLUSIONS: NLP identified linguistic markers distinguishing changes in anxiety and depression symptoms over treatment. Digital interventions offer new forms of delivery and provide the opportunity to automatically collect data for linguistic analysis.

Mental Health Counseling From Conversational Content With Transformer-Based Machine Learning.

Importance: Use of asynchronous text-based counseling is rapidly growing as an easy-to-access approach to behavioral health care. Similar to in-person treatment, it is challenging to reliably assess as measures of process and content do not scale. Objective: To use machine learning to evaluate clinical content and client-reported outcomes in a large sample of text-based counseling episodes of care. Design, Setting, and Participants: In this quality improvement study, participants received text-based counseling between 2014 and 2019; data analysis was conducted from September 22, 2022, to November 28, 2023. The deidentified content of messages was retained as a part of ongoing quality assurance. Treatment was asynchronous text-based counseling via an online and mobile therapy app (Talkspace). Therapists were licensed to provide mental health treatment and were either independent contractors or employees of the product company. Participants were self-referred via online sign-up and received services via their insurance or self-pay and were assigned a diagnosis from their health care professional. Exposure: All clients received counseling services from a licensed mental health clinician. Main Outcomes and Measures: The primary outcomes were client engagement in counseling (number of weeks), treatment satisfaction, and changes in client symptoms, measured via the 8-item version of Patient Health Questionnaire (PHQ-8). A previously trained, transformer-based, deep learning model automatically categorized messages into types of therapist interventions and summaries of clinical content. Results: The total sample included 166 644 clients treated by 4973 therapists (20 600 274 messages). Participating clients were predominantly female (75.23%), aged 26 to 35 years (55.4%), single (37.88%), earned a bachelor's degree (59.13%), and were White (61.8%). There was substantial variability in intervention use and treatment content across therapists. A series of mixed-effects regressions indicated that collectively, interventions and clinical content were associated with key outcomes: engagement (multiple R = 0.43), satisfaction (multiple R = 0.46), and change in PHQ-8 score (multiple R = 0.13). Conclusions and Relevance: This quality improvement study found associations between therapist interventions, clinical content, and client-reported outcomes. Consistent with traditional forms of counseling, higher amounts of supportive counseling were associated with improved outcomes. These findings suggest that machine learning-based evaluations of content may increase the scale and specificity of psychotherapy research.

Natural language processing for mental health interventions: a systematic review and research framework.

Neuropsychiatric disorders pose a high societal cost, but their treatment is hindered by lack of objective outcomes and fidelity metrics. AI technologies and specifically Natural Language Processing (NLP) have emerged as tools to study mental health interventions (MHI) at the level of their constituent conversations. However, NLP's potential to address clinical and research challenges remains unclear. We therefore conducted a pre-registered systematic review of NLP-MHI studies using PRISMA guidelines (osf.io/s52jh) to evaluate their models, clinical applications, and to identify biases and gaps. Candidate studies (n = 19,756), including peer-reviewed AI conference manuscripts, were collected up to January 2023 through PubMed, PsycINFO, Scopus, Google Scholar, and ArXiv. A total of 102 articles were included to investigate their computational characteristics (NLP algorithms, audio features, machine learning pipelines, outcome metrics), clinical characteristics (clinical ground truths, study samples, clinical focus), and limitations. Results indicate a rapid growth of NLP MHI studies since 2019, characterized by increased sample sizes and use of large language models. Digital health platforms were the largest providers of MHI data. Ground truth for supervised learning models was based on clinician ratings (n = 31), patient self-report (n = 29) and annotations by raters (n = 26). Text-based features contributed more to model accuracy than audio markers. Patients' clinical presentation (n = 34), response to intervention (n = 11), intervention monitoring (n = 20), providers' characteristics (n = 12), relational dynamics (n = 14), and data preparation (n = 4) were commonly investigated clinical categories. Limitations of reviewed studies included lack of linguistic diversity, limited reproducibility, and population bias. A research framework is developed and validated (NLPxMHI) to assist computational and clinical researchers in addressing the remaining gaps in applying NLP to MHI, with the goal of improving clinical utility, data access, and fairness.

Association of Health Care Work With Anxiety and Depression During the COVID-19 Pandemic: Structural Topic Modeling Study.

BACKGROUND: Stressors for health care workers (HCWs) during the COVID-19 pandemic have been manifold, with high levels of depression and anxiety alongside gaps in care. Identifying the factors most tied to HCWs' psychological challenges is crucial to addressing HCWs' mental health needs effectively, now and for future large-scale events. OBJECTIVE: In this study, we used natural language processing methods to examine deidentified psychotherapy transcripts from telemedicine treatment during the initial wave of COVID-19 in the United States. Psychotherapy was delivered by licensed therapists while HCWs were managing increased clinical demands and elevated hospitalization rates, in addition to population-level social distancing measures and infection risks. Our goal was to identify specific concerns emerging in treatment for HCWs and to compare differences with matched non-HCW patients from the general population. METHODS: We conducted a case-control study with a sample of 820 HCWs and 820 non-HCW matched controls who received digitally delivered psychotherapy in 49 US states in the spring of 2020 during the first US wave of the COVID-19 pandemic. Depression was measured during the initial assessment using the Patient Health Questionnaire-9, and anxiety was measured using the General Anxiety Disorder-7 questionnaire. Structural topic models (STMs) were used to determine treatment topics from deidentified transcripts from the first 3 weeks of treatment. STM effect estimators were also used to examine topic prevalence in patients with moderate to severe anxiety and depression. RESULTS: The median treatment enrollment date was April 15, 2020 (IQR March 31 to April 27, 2020) for HCWs and April 19, 2020 (IQR April 5 to April 27, 2020) for matched controls. STM analysis of deidentified transcripts identified 4 treatment topics centered on health care and 5 on mental health for HCWs. For controls, 3 STM topics on pandemic-related disruptions and 5 on mental health were identified. Several STM treatment topics were significantly associated with moderate to severe anxiety and depression, including working on the hospital unit (topic prevalence 0.035, 95% CI 0.022-0.048; P<.001), mood disturbances (prevalence 0.014, 95% CI 0.002-0.026; P=.03), and sleep disturbances (prevalence 0.016, 95% CI 0.002-0.030; P=.02). No significant associations emerged between pandemic-related topics and moderate to severe anxiety and depression for non-HCW controls. CONCLUSIONS: The study provides large-scale quantitative evidence that during the initial wave of the COVID-19 pandemic, HCWs faced unique work-related challenges and stressors associated with anxiety and depression, which required dedicated treatment efforts. The study further demonstrates how natural language processing methods have the potential to surface clinically relevant markers of distress while preserving patient privacy.

Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity.

Prior work has shown that analyzing the use of first-person singular pronouns can provide insight into individuals' mental status, especially depression symptom severity. These findings were generated by counting frequencies of first-person singular pronouns in text data. However, counting doesn't capture how these pronouns are used. Recent advances in neural language modeling have leveraged methods generating contextual embeddings. In this study, we sought to utilize the embeddings of first-person pronouns obtained from contextualized language representation models to capture ways these pronouns are used, to analyze mental status. De-identified text messages sent during online psychotherapy with weekly assessment of depression severity were used for evaluation. Results indicate the advantage of contextualized first-person pronoun embeddings over standard classification token embeddings and frequency-based pronoun analysis results in predicting depression symptom severity. This suggests contextual representations of first-person pronouns can enhance the predictive utility of language used by people with depression symptoms.

An Integrative Engagement Model of Digital Psychotherapy: Exploratory Focus Group Findings.

BACKGROUND: Digital mental health interventions, such as 2-way and asynchronous messaging therapy, are a growing part of the mental health care treatment ecosystem, yet little is known about how users engage with these interventions over the course of their treatment journeys. User engagement, or client behaviors and therapeutic relationships that facilitate positive treatment outcomes, is a necessary condition for the effectiveness of any digital treatment. Developing a better understanding of the factors that impact user engagement can impact the overall effectiveness of digital psychotherapy. Mapping the user experience in digital therapy may be facilitated by integrating theories from several fields. Specifically, health science's Health Action Process Approach and human-computer interaction's Lived Informatics Model may be usefully synthesized with relational constructs from psychotherapy process-outcome research to identify the determinants of engagement in digital messaging therapy. OBJECTIVE: This study aims to capture insights into digital therapy users' engagement patterns through a qualitative analysis of focus group sessions. We aimed to synthesize emergent intrapersonal and relational determinants of engagement into an integrative framework of engagement in digital therapy. METHODS: A total of 24 focus group participants were recruited to participate in 1 of 5 synchronous focus group sessions held between October and November 2021. Participant responses were coded by 2 researchers using thematic analysis. RESULTS: Coders identified 10 relevant constructs and 24 subconstructs that can collectively account for users' engagement and experience trajectories in the context of digital therapy. Although users' engagement trajectories in digital therapy varied widely, they were principally informed by intrapsychic factors (eg, self-efficacy and outcome expectancy), interpersonal factors (eg, the therapeutic alliance and its rupture), and external factors (eg, treatment costs and social support). These constructs were organized into a proposed Integrative Engagement Model of Digital Psychotherapy. Notably, every participant in the focus groups indicated that their ability to connect with their therapist was among the most important factors that were considered in continuing or terminating treatment. CONCLUSIONS: Engagement in messaging therapy may be usefully approached through an interdisciplinary lens, linking constructs from health science, human-computer interaction studies, and clinical science in an integrative engagement framework. Taken together, our results suggest that users may not view the digital psychotherapy platform itself as a treatment so much as a means of gaining access to a helping provider, that is, users did not see themselves as engaging with a platform but instead viewed their experience as a healing relationship. The findings of this study suggest that a better understanding of user engagement is crucial for enhancing the effectiveness of digital mental health interventions, and future research should continue to explore the underlying factors that contribute to engagement in digital mental health interventions. TRIAL REGISTRATION: ClinicalTrials.gov NCT04507360; https://clinicaltrials.gov/ct2/show/NCT04507360.

Automatic rating of therapist facilitative interpersonal skills in text: A natural language processing application.

Background: While message-based therapy has been shown to be effective in treating a range of mood disorders, it is critical to ensure that providers are meeting a consistently high standard of care over this medium. One recently developed measure of messaging quality-The Facilitative Interpersonal Skills Task for Text (FIS-T)-provides estimates of therapists' demonstrated ability to convey psychotherapy's common factors (e.g., hopefulness, warmth, persuasiveness) over text. However, the FIS-T's scoring procedure relies on trained human coders to manually code responses, thereby rendering the FIS-T an unscalable quality control tool for large messaging therapy platforms. Objective: In the present study, researchers developed two algorithms to automatically score therapist performance on the FIS-T task. Methods: The FIS-T was administered to 978 messaging therapists, whose responses were then manually scored by a trained team of raters. Two machine learning algorithms were then trained on task-taker messages and coder scores: a support vector regressor (SVR) and a transformer-based neural network (DistilBERT). Results: The DistilBERT model had superior performance on the prediction task while providing a distribution of ratings that was more closely aligned with those of human raters, versus SVR. Specifically, the DistilBERT model was able to explain 58.8% of the variance (R 2 = 0.588) in human-derived ratings and realized a prediction mean absolute error of 0.134 on a 1-5 scale. Conclusions: Algorithms can be effectively used to ensure that digital providers meet a consistently high standard of interactions in the course of messaging therapy. Natural language processing can be applied to develop new quality assurance systems in message-based digital psychotherapy.

Predictors of Disengagement and Symptom Improvement Among Adults With Depression Enrolled in Talkspace, a Technology-Mediated Psychotherapy Platform: Naturalistic Observational Study.

BACKGROUND: Depression is a common psychiatric condition with an estimated lifetime prevalence for major depression of 16.6% in the US adult population and is effectively treated through psychotherapy. The widespread availability of the internet and personal devices such as smartphones are changing the landscape of delivery of psychotherapy; however, little is known about whether and for whom this type of therapy is beneficial, and whether having synchronous video-based sessions provides additional benefits to clients above and beyond messaging-based therapy. OBJECTIVE: This study examined the outcomes associated with the use of a digital platform (Talkspace) for technology-mediated psychotherapy. We examined the duration of client engagement in therapy and client depression score trajectories over 16 weeks. We explored the association of client characteristics, therapist characteristics, and service plan type with time-to-disengagement and trajectories of change in depression scores. METHODS: This naturalistic observational study assessed data collected routinely by the platform between January 2016 and January 2018 and examined psychotherapy outcomes among a large representative sample of adult clients with clinically significant depression. Treatment disengagement was defined as a lack of client-initiated communication for more than 4 weeks. Clients completed the Patient Health Questionnaire-8 item (PHQ-8) at intake and every 3 weeks via an in-app survey. Cox regression analysis was used to examine the time until and predictors of disengagement. Changes in depression scores and predictors of change over time were examined using mixed-effects regression. RESULTS: The study included 5890 clients and 1271 therapists. Client scores on the PHQ-8 declined over time, with the average client improving from a score of 15 to below the clinical cutoff of 10 by week 6. At the same time point, 37% of clients had disengaged from the therapy. When combined into a final Cox regression model, those who were more likely to disengage were clients aged 18 to 25 years versus those aged ≥50 years (odds ratio [OR] 0.82, 95% CI 0.74-0.9; P<.001), had higher education (OR 1.14, 95% CI 1.06-1.22; P<.001), had been in therapy before (OR 1.09, 95% CI 1.02-1.17; P=.01), and were living with a partner but unmarried versus single (OR 1.14, 95% CI 1.02-1.27; P=.02). Having a therapist with >10 years of experience was related to lower odds of disengagement (OR 0.87, 95% CI 0.8-0.94; P=.01). When combined into a final regression model predicting improvement in depression scores over time, clients showing more improvement were those with an associate's degree or higher (linear estimate=-0.07, P=.002) and higher intake PHQ-8 scores (estimate=3.73, P<.001). There were no differences based on the plan type. CONCLUSIONS: Our findings add to the growing literature showing the benefits of technology-mediated psychotherapy over a relatively brief period (16 weeks).