Sunday, January 20, 2019

Using Artificial Intelligence to Treat Prediabetes

Prediabetes is a chronic disease that afflicts 84% of the adults in the U.S., and having prediabetes raises the risk for diabetes heart disease stroke and other problems. The  Centers for Disease Control and Prevention (CDC) established the Diabetes Prevention Program (DPP) to address prediabetes. That program is based on a study, funded by the National Institutes of Diabetes and Digestive and Kidney Disease (NIDDK). The study was done and reported on between 1996 and 2002. The services delivered in the DPP can potentially be replicated with the help of artificial intelligence.

The original DPP study indicated that for those with prediabetes, lifestyle modification plus diet and increased physical activity could reduce the risk of diabetes by 58%. The study was done using highly trained individuals -- registered dietitians, for example -- to deliver the one-on-one counseling. The one-on-one program was later translated into a group based program. This group based program was less costly than the original one-on-one program. Still, additional efforts are underway to reduce the cost of the program. One of these programs uses artificial intelligence and telemedicine to deliver the counseling.

The program is called the Lark Weight Loss Health Coach AI (HCAI). In a study, HCAI was used to determine the effectiveness of conversational artificial intelligence (AI) when used as a mobile app for smart phones. The study also measured the user acceptability of the methodology.

There were 70 participants in the study, and the study's standards met the CDC’s criteria for the CDC’s diabetes prevention program. The criteria were those used for the original DPP trials. Although more research needs to be done, the results were quite promising.

The investigators concluded that “the use of an AI health Coach is associated with weight loss comparable to in-person lifestyle interventions. It can also encourage behavior changes and have higher user acceptability. Research into AI and its application in telemedicine should be pursued, with clinical trials investigating effects on weight, health behaviors, and user engagement and acceptability.”

If this approach proves beneficial, it could increase the number of people with prediabetes who can get treatment while lowering the cost. Healthcare providers should keep abreast of this type of research, because it can be quite important in the future.


Post a Comment

Subscribe to Post Comments [Atom]

<< Home

Subscribe to Overfat Strategy Blog by Email