Scientists Use AI to Predict Engagement in Health Programs
In a study, a team from the Commonwealth Scientific and Industrial Research Organisation (CSIRO) used AI to accurately predict when a person will drop out of a weight loss program.
By analyzing data from over 59,000 participants in the CSIRO Total Wellbeing Diet, machine learning was able to predict disengagement from the program on a weekly basis.
Aida Brankovic, lead author of the study and research scientist from the CSIRO's Australian e-Health Research Centre, said the findings could have significant implications for keeping people engaged in weight loss programs and improving their health outcomes.
"Despite the growing application and adoption of technology in health interventions, one persistent challenge remains - engagement deterioration or non-usage attrition," she said in a media release.
"With this information, digital health interventions can become more tailored, supportive and offer users a greater chance of making long-term lifestyle changes. Importantly, the machine learning model used in this study can also be adjusted and applied to large cohorts of data in other online programs requiring engagement."
Two-thirds of Australian adults are overweight or obese, and according to the Australian Institute of Health and Welfare, 30 percent do not do enough physical exercise.
In 2020, carrying excess weight accounted for 8.4 percent of Australia's total disease burden.
Gilly Hendrie, co-author of the report, said engagement in health programs was key to addressing Australia's obesity crisis.
"Past habits really do predict future behaviour. But if we can predict when that behaviour will kick in and adapt so we can re-engage someone - we've got a better chance of helping them make long-lasting changes to their health and lifestyle," she said.
4155/v
