Zac E. Imel’s research while affiliated with University of Mary Washington and other places

Researchers have historically focused on understanding therapist multicultural competency and orientation through client self-report measures and behavioral coding. While client perceptions of therapist cultural competency and multicultural orientation and behavioral coding are important, reliance on these methods limits therapists receiving systematic, scalable feedback on cultural opportunities within sessions. Prior research demonstrating the feasibility of automatically identifying topics of conversation in psychotherapy suggests that natural language processing (NLP) models could be trained to automatically identify when clients and therapists are talking about cultural concerns and could inform training and provision of rapid feedback to therapists. Utilizing 103,170 labeled talk turns from 188 psychotherapy sessions, we developed NLP models that recognized the discussion of cultural topics in psychotherapy (F − 1 = 70.0; Spearman’s ρ = 0.78, p < .001). We discuss implications for research and practice and applications for future NLP-based feedback tools.

Objective: Counselor assessment of suicide risk is one key component of crisis counseling, and standards require risk assessment in every crisis counseling conversation. Efforts to increase risk assessment frequency are limited by quality improvement tools that rely on human evaluation of conversations, which is labor intensive, slow, and impossible to scale. Advances in machine learning (ML) have made possible the development of tools that can automatically and immediately detect the presence of risk assessment in crisis counseling conversations. Methods: To train models, a coding team labeled every statement in 476 crisis counseling calls (193,257 statements) for a core element of risk assessment. The authors then fine-tuned a transformer-based ML model with the labeled data, utilizing separate training, validation, and test data sets. Results: Generally, the evaluated ML model was highly consistent with human raters. For detecting any risk assessment, ML model agreement with human ratings was 98% of human interrater agreement. Across specific labels, average F1 (the harmonic mean of precision and recall) was 0.86 at the call level and 0.66 at the statement level and often varied as a result of a low base rate for some risk labels. Conclusions: ML models can reliably detect the presence of suicide risk assessment in crisis counseling conversations, presenting an opportunity to scale quality improvement efforts.

Mental health researchers have focused on promoting culturally sensitive clinical care (Herman et al., 2007; Whaley & Davis, 2007), emphasizing the need to understand how biases may impact client well-being. Clients report that their therapists commit racial microaggressions—subtle, sometimes unintentional, racial slights—during treatment (Owen et al., 2014). Yet, existing studies often rely on retrospective evaluations of clients and cannot establish the causal impact of varying ambiguity of microaggressions on clients. This study uses an experimental analogue design to examine offensiveness, emotional reactions, and evaluations of the interaction across three distinct levels of microaggression statements: subtle, moderate, and overt. We recruited 158 adult African American participants and randomly assigned them to watch a brief counseling vignette. We found significant differences between the control and three microaggression statements on all outcome variables. We did not find significant differences between the microaggression conditions. This study, in conjunction with previous correlational research, highlights the detrimental impact of microaggressions within psychotherapy, regardless of racially explicit content.

Recent scholarship has highlighted the value of therapists adopting a multicultural orientation (MCO) within psychotherapy. A newly developed performance-based measure of MCO capacities exists (MCO–performance task [MCO-PT]) in which therapists respond to video-based vignettes of clients sharing culturally relevant information in therapy. The MCO-PT provides scores related to the three aspects of MCO: cultural humility (i.e., adoption of a nonsuperior and other-oriented stance toward clients), cultural opportunities (i.e., seizing or making moments in session to ask about clients’ cultural identities), and cultural comfort (i.e., therapists’ comfort in cultural conversations). Although a promising measure, the MCO-PT relies on labor-intensive human coding. The present study evaluated the ability to automate the scoring of the MCO-PT transcripts using modern machine learning and natural language processing methods. We included a sample of 100 participants (n = 613 MCO-PT responses). Results indicated that machine learning models were able to achieve near-human reliability on the average across all domains (Spearman’s ρ = .75, p < .0001) and opportunity (ρ = .81, p < .0001). Performance was less robust for cultural humility (ρ = .46, p < .001) and was poorest for cultural comfort (ρ = .41, p < .001). This suggests that we may be on the cusp of being able to develop machine learning-based training paradigms that could allow therapists opportunities for feedback and deliberate practice of some key therapist behaviors, including aspects of MCO.

Background The opioid epidemic has resulted in expanded substance use treatment services and strained the clinical workforce serving people with opioid use disorder. Focusing on evidence-based counseling practices like motivational interviewing may be of interest to counselors and their supervisors, but time-intensive adherence tasks like recording and feedback are aspirational in busy community-based opioid treatment programs. The need to improve and systematize clinical training and supervision might be addressed by the growing field of machine learning and natural language-based technology, which can promote counseling skill via self- and supervisor-monitoring of counseling session recordings. Methods Counselors in an opioid treatment program were provided with an opportunity to use an artificial intelligence based, HIPAA compliant recording and supervision platform (Lyssn.io) to record counseling sessions. We then conducted four focus groups—two with counselors and two with supervisors—to understand the integration of technology with practice and supervision. Questions centered on the acceptability of the clinical supervision software and its potential in an OTP setting; we conducted a thematic coding of the responses. Results The clinical supervision software was experienced by counselors and clinical supervisors as beneficial to counselor training, professional development, and clinical supervision. Focus group participants reported that the clinical supervision software could help counselors learn and improve motivational interviewing skills. Counselors said that using the technology highlights the value of counseling encounters (versus paperwork). Clinical supervisors noted that the clinical supervision software could help meet national clinical supervision guidelines and local requirements. Counselors and clinical supervisors alike talked about some of the potential challenges of requiring session recording. Conclusions Implementing evidence-based counseling practices can help the population served in OTPs; another benefit of focusing on clinical skills is to emphasize and hold up counselors’ roles as worthy. Machine learning technology can have a positive impact on clinical practices among counselors and clinical supervisors in opioid treatment programs, settings whose clinical workforce continues to be challenged by the opioid epidemic. Using technology to focus on clinical skill building may enhance counselors’ and clinical supervisors’ overall experiences in their places of work.

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 (NLP) is a subfield of machine learning that may facilitate the evaluation of therapist–client interactions and provide feedback to therapists on client outcomes on a large scale. However, there have been limited studies applying NLP models to client-outcome prediction that have (a) used transcripts of therapist–client interactions as direct predictors of client-symptom improvement, (b) accounted for contextual linguistic complexities, and (c) used best practices in classical training and test splits in model development. Using 2,630 session recordings from 795 clients and 56 therapists, we developed NLP models that directly predicted client symptoms of a given session based on session recordings of the previous session (Spearman’s ρ = .32, p < .001). Our results highlight the potential for NLP models to be implemented in outcome-monitoring systems to improve quality of care. We discuss implications for future research and applications.

Objective: This paper highlights the facilitation of dyadic synchrony as a core psychotherapist skill that occurs at the non-verbal level and underlies many other therapeutic methods. We define dyadic synchrony, differentiate it from similar constructs, and provide an excerpt illustrating dyadic synchrony in a psychotherapy session. Method: We then present a systematic review of 17 studies that have examined the associations between dyadic synchrony and psychotherapy outcomes. We also conduct a meta-analysis of 8 studies that examined whether there is more synchrony between clients and therapists than would be expected by chance. Results: Weighted box score analysis revealed that the overall association of synchrony and proximal as well as distal outcomes was neutral to mildly positive. The results of the meta-analysis indicated that real client-therapist dyad pairs exhibited synchronized behavioral patterns to a much greater extent than a sample of randomly paired people who did not actually speak. Conclusion: Our discussion revolves around how synchrony can be facilitated in a beneficial way, as well as situations in which it may not be beneficial. We conclude with training implications and therapeutic practices.

Introduction With the increasing utilization of text-based suicide crisis counseling, new means of identifying at risk clients must be explored. Natural language processing (NLP) holds promise for evaluating the content of crisis counseling; here we use a data-driven approach to evaluate NLP methods in identifying client suicide risk. Methods De-identified crisis counseling data from a regional text-based crisis encounter and mobile tipline application were used to evaluate two modeling approaches in classifying client suicide risk levels. A manual evaluation of model errors and system behavior was conducted. Results The neural model outperformed a term frequency-inverse document frequency (tf-idf) model in the false-negative rate. While 75% of the neural model’s false negative encounters had some discussion of suicidality, 62.5% saw a resolution of the client’s initial concerns. Similarly, the neural model detected signals of suicidality in 60.6% of false-positive encounters. Discussion The neural model demonstrated greater sensitivity in the detection of client suicide risk. A manual assessment of errors and model performance reflected these same findings, detecting higher levels of risk in many of the false-positive encounters and lower levels of risk in many of the false negatives. NLP-based models can detect the suicide risk of text-based crisis encounters from the encounter’s content.