Transforming motivational interviewing into a computable model for automated patient diabetic counseling.

Project: Research project

Project Details

Description

The incidence of type 2 diabetes mellitus (T2DM) is staggeringly high in the United States, and it is expected to exponentially increase in the next few decades. Regulating health behavior that leads to T2DM is a key factor that can slow the down prevalence of T2DM and decrease any complications resulting from T2DM. Motivational Interviewing (MI) is one of the evidence-based approaches that providers can wield before considering more expensive and invasive methods. MI is a counseling technique, involving empathy and evoking “change talk” by the patient, that aims to resolve the ambivalence that prevents

clients from realizing personal goals. Together with the patient, the MI-trained provider can illicit the patients’ hesitancy of unhealthy behaviors that increase the severity of T2DM and eventually improve the patients’ health outcomes and lifestyle. Research has shown that MI is effective in modifying some of the health behaviors that relate to T2DM severity (e.g., regulation of sugar-sweetened beverages consumption and promoting physical activity). However, behavior change counseling is rarely implemented in clinical practice.


The use of speech interfaces in devices have been increasing used by consumers over the last few years. Coupled with advancements in intelligence-based dialogue methods, software agents can automate dialogue exchanges between machine and users, and could engage users using human language and conversational turns. If we could automate the counseling experience through a speech-based dialogue system we could delegate the task counseling task and overcome some of the challenges to implement MI – training, consistency, reimbursements, and lack of time.


The researchers presume that we can model and emulate the MI counseling method for machines to enact conversations to evoke patients’ ambivalence of harmful health behaviors surrounding sugar-sweetened beverages and encourage light physical activity. In

addition, we posit that motivational interviewing experts and end users who have diabetes or pre-diabetes can positively assess the usability of our software agent (“app”), code named “TROI”, to preform MI counseling for our use-cases.

StatusActive
Effective start/end date8/29/246/30/27

Funding

  • National Institute of Diabetes and Digestive and Kidney Diseases ( Award #1R21DK13481501A1): $223,697.00

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.