The HeaRTWise (Health Economic Analysis of Return To Work and Societal Cost of Cardiovascular Diseases) project aims to enhance the accuracy of patient-specific predictions for occupational outcomes after cardiovascular diseases (CVDs).
CVDs are leading causes of death and disability globally, and return-to-work (RTW) is a crucial rehabilitation goal to reduce the burden of CVDs and associated costs. To identify predictors of RTW, machine learning (ML) techniques are applied on combined patient-level administrative data on health, occupational, and sociodemographic characteristics. The HeaRTWise project introduces a Bayesian extension of ML techniques that also incorporates data from smaller subsets of the population, providing a robust method for developing a prediction model. This innovative approach offers a unique opportunity to improve the accuracy of RTW prediction models, which can provide clear leads to enhance rehabilitation plans for CVD survivors and lead to significant cost savings associated with productivity loss.
Contact person of the project: Ellen Tisseghem