Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Aug 16, 2020
Open Peer Review Period: Oct 26, 2020 - Dec 26, 2020
Date Accepted: Nov 19, 2021
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Use of Structural Topic Modeling to explore impacts of personal characteristics on successful engagement with a technology application; health 360x
ABSTRACT
Background:
Although technology promises to solve the challenge of targeting and tailoring interventions to the individual; engagement with technology is low among minority communities. Health coaches enhance engagement with technology but results vary
Objective:
We explored the role of coach and participant characteristics and their interactions on successful engagement with technology for self-management skills acquisition in high risk diabetics
Methods:
Longitudinal data and transcripts of participant-coach interactions were taken from a study evaluating the impact of Health 360x and coaching on self-management skills acquisition;as part of care coordination in the Morehouse Choice Accountable Care Organization (MCACO). Topic modeling, a natural language processing method that reliably uncovers conversation topics was used. Structural topic modeling allowed us to include metadata into our analysis. We validated the output by identifying topics based on high characteristic words, manually verifying highest scoring talk turns and labeling topics, logging example conversations. We used mixed effects logistic regression to quantify participant and coach characteristics and interactions
Results:
We identified 17,000 talk turns; 7196 in the ‘achieved’ group and 9,644 in the ‘not achieved’ group. There were important differences in the content of highest scoring topics depending on whether the coach-participant dyad achieved their goals or did not achieve their goal. The conversations in the coach-participant dyads who achieved their health goals were balanced versus in the ‘not achieved’ where the coaches tended to dominate the conversation. Female participants with female coaches were significantly more likely to achieve their health goals. Goal setting alone had a negative impact on attaining desired outcomes.
Conclusions:
Among diabetic patients who received the health 360x coach facilitated technology intervention for self management behavior change; i)Goal setting requires additional interventions in order to lead to improved outcomes ii)coach participant dyads who achieved behavioral goals, engaged in balanced conversational exchanges iii) better performance among female-female participant coach dyads may indicate cultural expectations that can be further explored in a society with growing diversity among patients and the healthcare workforce. Our use of topic modeling in this application is novel and it creates an opportunity to introduce this technique into every day patient provider encounters. The opportunity to create outputs that guide further physician action and patient action could drive better patient engagement and overall patient health outcomes. Clinical Trial: Not applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.