The app was found to have led to a significant decrease in levels of a blood sugar biomarker for diabetes called A1C, improvement in physical activity and reduced weight.
According to previous findings, physical activity for 150 minutes weekly and reducing weight by 5%-7% minimises the chances of diabetes development by 58%.
The Sweetch app is designed for prediction, prevention and outcome improvement of chronic diseases such as diabetes, hypertension, ischemic heart disease, hyperlipidemia and obesity.
Its machine learning technology is said to predict and decrease diabetes risk by providing personalised intervention through realistic recommendations and continuous adaptation based on the user’s past behavioural patterns.
The way Sweetch works is expected to help in better patient adherence.
Sweetch CEO Dana Chanan said: “About one-third of Americans, Europeans and Chinese suffer from chronic diseases associated with unhealthy lifestyle habits.
“While helping such numbers of people cannot be managed effectively through human-based coaching, Sweetch ’s technology has achieved clinically significant results with no human involvement to enable large-scale intervention at a low cost.”
Conducted over three months, the clinical trial included 55 pre-diabetic adults at various obesity levels. Retention rates in the subjects using Sweetch were observed to be 86% with a clinically meaningful decrease in A1C of 0.1%.
John Hopkins University researchers said: “The fact that the study demonstrated both weight and A1C reductions at only three months suggests that long-term effects will be comparable, if not superior, to existing interventions.
“Most importantly, Sweetch ‘s machine learning technology enables fully automated intervention; hence, supporting larger-scale deployment with greater cost-effectiveness potential when compared with human-based diabetes prevention solutions.”