Novel Modelling to improve decision-making for neighbourhood design to reduce chronic disease risk

This study innovatively uses a flexible and applicable approach (Bayesian Networks) to show where neighbourhood features operate uniquely or not, which features can be prioritised, which are cost effective, and how much of each feature is needed to achieve improvement in reducing risk of chronic disease.

Using novel Bayesian Network analysis, we will develop a practical, user-friendly, generalisable, and scalable tool to inform urban planning initiatives to help decision makers to prioritise initiatives for the greatest health and economic benefits in diverse neighbourhood types to prevent cardiometabolic risk and reduce health inequities.

Funded by: National Health and Medical Research Council

• Luis Salvador-Carulla
• Gavin Turrell
• Suzanne Carroll
• Margaret Cargo
• Nasser Bagheri
• Katie Speer
• Mark Daniel