Society of Behavioral Medicine - Advanced Methods in Behavioral Informatics
- 1. Society of Behavioral Medicine: Advancing Methods in Behavioral Informatics Eric Hekler, PhD SBM Technology SIG Co-Chair Asst. Prof., College of Health Solutions Arizona State University @ehekler www.designinghealth.org
- 2. Take-Home Message SBM members are creating highly innovative methods for designing, evaluating, and implementing mHealth/eHealth behavioral interventions for real-world use.
- 3. Domains • Optimizing behavioral interventions • Just-in-time adaptive interventions • Theory taxonomy ontology real-world use • Fostering rapid, relevant and responsive research
- 5. Linda M. Collins The Methodology Center Penn State methodology.psu.edu
- 6. Statistical Reinforcement Learning Lab University of Michigan Danny Almirall Susan Murphy Inbal (Billie) Nahum-Shani • Research: – Adaptive Interventions – Sequential Multiple Assignment Randomized Trial (SMART)
- 7. Adaptive Intervention SMART Example Adaptive Example http://methodology.psu.edu/ra/smart/projects
- 8. (Am J Prev Med 2013;45(4):517–523) www.cbits.northwestern.edu David Mohr Northwestern
- 10. Statistical Reinforcement Learning Lab University of Michigan • Research: – Just In Time Adaptive Interventions (JITAI) – Micro-Randomized trial designs and data analysis methods for JITAI development https://community.isr.umich.edu/public/jitai/Workshop.aspx Inbal (Billie) Nahum-Shani Danny Almirall Pedja Klasnja Susan Murphy Ambuj Tewari
- 11. Just In Time Adaptive Intervention (JITAIs) • Individualized treatments delivered when-ever and where-ever the individual needs help, via a wearable device (e.g., smartphone). + • Advancing: • Micro-randomization trial designs • Data analysis methods for constructing good decision rules. • Online training algorithms that will personalize decision rules. https://community.isr.umich.edu/public/jitai/Workshop.aspx
- 12. Controller-Driven Just in Time Adaptive Interventions Daniel Rivera Co-PIs: Eric Hekler & Daniel Rivera, ASU Other Collaborators: Matthew Buman, Marc Adams, & Pedrag Klasnja www.designinghealth.org support from the National Science Foundation
- 13. Dynamical Model of Social Cognitive Theory Martin, Riley, Rivera, Hekler, et al. 2014
- 14. Informative Experiment for a Controller 14000 12000 10000 8000 6000 4000 2000 0 1 11 21 31 41 51 61 71 81 91 101 111 121 131 141 151 161 171 181 191 201 211 221 231 241 251 Steps per day Days Steps per Day Week Average Intervention 4 Intervention 3 Intervention 2 Intervention 1 Measurement www.designinghealth.org support from the National Science Foundation
- 15. Theory Taxonomy Ontology Use
- 16. Developed: BCT Taxonomy v1
- 17. Underway – BCT Theory Consortium Designing and evaluating theory-based interventions- Developing and testing a methodology for linking behaviour change techniques to theory Study 1: Evidence Synthesis Examining BCT-Theory links in published interventions Study 2: Expert Consensus Identifying and agreeing BCT-Theory links Study 3: BCT Clustering BCT clustering: Identifying implicit theories (published interventions and expert consensus) Study 4: Triangulation Triangulation of consensus, evidence synthesis and BCT clustering methods
- 18. The Team Marie Johnston Professor Emeritus University of Aberdeen Marijn de Bruin Chair in Health Psychology University of Aberdeen Susan Michie Professor of Health Psychology University College London Alex Rothman Professor of Psychology University of Minnesota Mike Kelly Director of Centre for Public Health NICE / University of Cambridge Lauren Connell Research Assistant University College London Rachel Carey Research Associate University College London
- 20. Behavioral Ontology v1 Larry An U. Michigan Susan Michie U. College London http://chcr.umich.edu/ http://www.ucl.ac.uk/behaviour-change
- 21. Preconception Care How do we build systems to intervene on dozens of health behaviors simultaneously? Screen young African American women on 108 health risks. Create individualized action plan. Conduct longitudinal, stage-based counseling to address specific risks (22 on average). Timothy Bickmore, Northeastern University
- 22. Rapid, Relevant, and Responsive Research
- 23. Rapid, Relevant, and Responsive Research Bill Riley Acting Director, OBSSR, NIH Riley WT, Glasgow RE, Etheredge L, Abernethy AP. Rapid, responsive, relevant (R3) research: a call for a rapid learning health research enterprise. Clinical and translational medicine. 2013;2(1):1-6.
- 25. Developing Methods: Agile Science www.agilescience.org
- 26. Creating the Tools www.agilescience.org
- 27. Sign Up to Be a Beta-Tester www.agilescience.org
- 28. Take-Home Message SBM members are creating highly innovative methods for designing, evaluating, and implementing mHealth/eHealth behavioral interventions for real-world use.
- 29. Slides Available www.designinghealth.org/presentations.html @ehekler ehekler@asu.edu
Editor's Notes
- #8: This is an example adaptive intervention for improving spoken communication among children with autism who are minimally verbal. However, often many questions must be answered in order to develop a high-quality adaptive intervention: Should treatment begin with CORE-DTT instead of JASP-EMT? For improved responders, is parent training really helpful? Do all slow responders require combined treatment? Sequential Multiple Assignment Randomized Trial (SMART) designs are used to answer such questions. This is an example SMART design for constructing a high-quality adaptive intervention for children with autism who are minimally verbal. Background: Earlier research has shown that even after early language-skills training, about one-third of school-aged children with Autism Spectrum Disorder remain minimally verbal. Study Design: The study utilizes a sequential multiple assignment randomized trial (SMART) design. All children with autism are randomized twice: once initially to understand which is the best first-stage treatment to improve spoken communication, and again at the end of week 6 to understand which is the best second-stage treatment depending on whether the child is a slow responder or an improved responder to first-stage treatment. The primary outcome is spontaneous spoken communication. Researchers plan to enroll 200 children in four cities: Los Angeles, Nashville, New York City, and Rochester (N.Y.) Primary Aim: This study will initially compare two types of intensive, daily instruction for children with autism spectrum disorder (ASD) who use only minimal verbal communication. The two interventions are JASP-EMT (a novel approach to improving communication) and CORE-DTT (the traditional approach to improving communication). Secondary Aim 1: Among children who are slow responders at week 6, the study will compare continued treatment versus an intervention that combines both types of instruction. Secondary Aim 2: Among children who are improved responders at week 6, the study will compare continued treatment versus augmenting the intervention with parent training. Grant Information: Funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD), and collaborated by the National Institute on Deafness and Other Communication Disorders (NIDCD). Grant #: RFA-HD-12-196 Additional Information: Website: http://www.npistat.org/catherine/aim-asd-new Clinical Trials #: NCT01751698 Lead PI: Connie Kasari, UCLA Methods PIs: Daniel Almirall and Susan A Murphy, Univ of Michigan Site PIs: Ann Kaiser (Vanderbilt, TN), Catherine Lord (New York, NY), Tristram Smith (Rochester, NY)
- #12: Say something about heartsteps as one of the projects in our lab; I assume Eric is familiar with this as he is an investigator