Personalising Digital Health Behaviour Change Interventions using Machine Learning and Domain Knowledge
This work addresses the challenge of improving patient adherence to health interventions, but it is incremental as it builds on existing methods with simulated data.
The researchers tackled the problem of personalizing digital health behavior change interventions by developing a virtual coaching system that predicts patient behavior and uses counterfactual examples for personalization, with results based on simulated patient data to enable system evaluation.
We are developing a virtual coaching system that helps patients adhere to behavior change interventions (BCI). Our proposed system predicts whether a patient will perform the targeted behaviour and uses counterfactual examples with feature control to guide personalisation of BCI. We use simulated patient data with varying levels of receptivity to intervention to arrive at the study design which would enable evaluation of our system.