Millions of Americans are receiving behavioral interventions for problematic alcohol use. In 2010, the Substance Abuse and Mental Health Services Administration documented over 1.8 million treatment episodes for drug and alcohol problems, many involving group or individual psychotherapy. What is the quality of these interventions? In truth, we have no idea. To evaluate the quality of behavioral interventions such as psychotherapy researchers rely on human evaluation through behavioral coding, which is a major impediment to scaling up and sustaining high-quality interventions for alcohol abuse in large-scale implementation. Human evaluation of behavioral interventions is a rate-limiting factor, and a technological solution is needed that incorporates human expertise but does not rely on human judgment as the evaluation tool. The current K02 career development proposal builds on interdisciplinary research focused on automating the evaluation of motivational interviewing (MI) fidelity for alcohol and substance use disorders. This collaborative research brings together speech signal processing experts from engineering and statistical text- mining experts from computer science with MI expert trainers and researchers. The work is currently supported by an R01 (AA018673) methods development grant and an R34 (DA034860) feasibility trial. Career development activities will encompass additional training, experience, and collaboration in three areas: 1) technical tools and methods (speech signal processing, statistical text-mining, and machine learning), 2) clinical process and change mechanisms of MI, and 3) large-scale implementation. A team of senior mentors, who are nationally and internationally recognized experts in each of the three core areas, will oversee the career development activities. These activities have been designed to deepen knowledge in key topics (course work, directed reading), develop applied skills (hands-on work with speech signal processing, statistical text-mining, and machine learning), advance integration of technology with clinical process (co- reviewing MI sessions from the view of computational tools and MI clinical theory), and prepare for large-scale implementation of automated MI fidelity coding and feedback (engage key stakeholders in large healthcare systems via the mental health research network). Research conducted during the K02 will: a) systematically explore how much and which portion(s) of MI sessions are needed for accurate fidelity assessment; b) conduct innovative process research on how tone and prosody of spoken language moderate the association of client change talk with patient outcome; and, c) incorporate cutting-edge visual design in developing an automated fidelity feedback report for MI therapists. This career development award will support, enhance, and move forward research developing automated clinical support tools to provide rapid feedback to MI therapists. The ultimate goal is to improve the quality of behavioral interventions for all Americans struggling with alcohol problems.
How do we know whether a psychotherapy session is a `good' psychotherapy session? Presently, we rely on human judgment in a process called behavioral coding to decide what is good or high-quality, but this greatly limits our ability to evaluate psychotherapy in the real world, as human judgment and coding is expensive and time-consuming. The current career development proposal supports ongoing technology development focused on using algorithms and software, instead of human judgment, to evaluate a particular type of psychotherapy for alcohol and substance use problems called motivational interviewing.
| Hirsch, Tad; Soma, Christina; Merced, Kritzia et al. (2018) ""It's hard to argue with a computer:"" Investigating Psychotherapists' Attitudes towards Automated Evaluation. DIS (Des Interact Syst Conf) 2018:559-571 |
| Caperton, Derek D; Atkins, David C; Imel, Zac E (2018) Rating motivational interviewing fidelity from thin slices. Psychol Addict Behav 32:434-441 |
| Hallgren, Kevin A; Dembe, Aaron; Pace, Brian T et al. (2018) Variability in motivational interviewing adherence across sessions, providers, sites, and research contexts. J Subst Abuse Treat 84:30-41 |
| Hirsch, Tad; Merced, Kritzia; Narayanan, Shrikanth et al. (2017) Designing Contestability: Interaction Design, Machine Learning, and Mental Health. DIS (Des Interact Syst Conf) 2017:95-99 |
| Imel, Zac E; Caperton, Derek D; Tanana, Michael et al. (2017) Technology-enhanced human interaction in psychotherapy. J Couns Psychol 64:385-393 |
| Pace, Brian T; Dembe, Aaron; Soma, Christina S et al. (2017) A multivariate meta-analysis of motivational interviewing process and outcome. Psychol Addict Behav 31:524-533 |
| Gaut, Garren; Steyvers, Mark; Imel, Zac E et al. (2017) Content Coding of Psychotherapy Transcripts Using Labeled Topic Models. IEEE J Biomed Health Inform 21:476-487 |
| Hallgren, Kevin A; Bauer, Amy M; Atkins, David C (2017) Digital technology and clinical decision making in depression treatment: Current findings and future opportunities. Depress Anxiety 34:494-501 |
| Xiao, Bo; Huang, Chewei; Imel, Zac E et al. (2016) A technology prototype system for rating therapist empathy from audio recordings in addiction counseling. PeerJ Comput Sci 2: |
| Hallgren, Kevin A; Atkins, David C; Witkiewitz, Katie (2016) Aggregating and Analyzing Daily Drinking Data in Clinical Trials: A Comparison of Type I Errors, Power, and Bias. J Stud Alcohol Drugs 77:986-991 |
Showing the most recent 10 out of 21 publications
