My graduate training was in clinical psychology, but over the last 10 years I have increasingly focused on applied statistics and methodology. I serve (or have served) as a statistical consultant / co-investigator and data analyst on over 30 NIH-funded grants. Additionally, I direct the Data Core of the Center for the Study of Health and Risk Behaviors (CSHRB). CSHRB is housed in the Department of Psychiatry and Behavioral Sciences and consists of a dozen investigators, supported by a variety of primarily NIH grants. I have actively collaborated with biostatisticians and methodologists and have written a number of tutorial articles, introducing recent and / or novel methodologies to clinical researchers (e.g., Atkins, 2005, 2009; Atkins & Gallop, 2007; Atkins et al., 2012; 2013). More recently I have helped to lead interdisciplinary research focused on automating fidelity coding of motivational interviewing (MI). This work is only possible via collaborations with engineers and computer scientists who have the necessary expertise in speech signal processing and statistical text mining to work from the acoustic and semantic features of spoken language and build predictive models of MI fidelity codes. I have been a co-PI on this work, supported by an R01 from NIAAA and an R34 from NIDA, and my leadership role has centered on bridging the team’s different disciplines, drawing on both my clinical and statistical expertise. This research has made steady progress in both developing algorithms and methods for automating MI fidelity coding (Atkins et al., 2014; Can et al., 2012) and using innovative computational linguistic approaches to studying empathy in MI (Imel et al., 2014; Xiao et al., 2013). Most recently, we have written a position paper describing the advantages and possibilities of taking a ‘computational’ approach to studying behavioral interventions such as psychotherapy (Imel, Stevyers, & Atkins, 2014).
Atkins, D. C., Steyvers, M., Imel, Z. E., & Smyth, P. (2014). Scaling up the evaluation of psychotherapy: Evaluating motivational interviewing fidelity via statistical text classification. Implementation Science, 9, 49. doi: 10.1186/1748-5908-9-49
Baldwin, S. A., Imel, Z. E., Braithwaite, S. R., & Atkins, D. C. (2014). Analyzing Multiple Outcomes in Clinical Research Using Multivariate Multilevel Models. Journal of Consulting and Clinical Psychology, 82, 920-930. doi: 10.1037/a0035628
Imel, Z. E., Steyvers, M., & Atkins, D. C. (2014, May 26). Computational psychotherapy research: Scaling up the evaluation of patient-provider interactions. Psychotherapy. Advance online publication.
Lord, S. P, Can, D., Yi, M., Marín, R. A., Dunn, C. W., Imel, Z. E., Georgiou, P. G., Narayanan, S. S., Steyvers, M., & Atkins, D. C. (2015). Advancing methods for reliably assessing motivational interviewing fidelity using the Motivational Interviewing Skills Code. Journal of Substance Abuse Treatment, 49, 50-57.
Roy-Byrne, P., Bumgardner, K., Krupski, A., Dunn, C., Ries, R., Donovan, D., West, I. I., Maynard, C., Atkins, D. C., Cook, M., Joesch, J., M., & Zarkin, G. A. (2014). Brief Intervention for Problem Drug Use in Safety-Net Primary Care Settings. JAMA, 312, 482-501.
Current Research Grants:
NIH/NIAAA R01 AA018673. Automating Behavioral Coding via Text-mining and Speech Signal Processing
NIH/NIDA R34 DA034860. Development and Feasibility of Computer Based Fidelity Monitoring for Motivational Interviewing
Volkswagen Foundation (VolkswagenStiftung 88 374). The Language of Interaction: Quantitative Tools from Engineering, Computer Science, and Clinical Psychology