Search

Machine learning has been shown to outperform traditional statistical methods for risk prediction model development. We aimed to develop machine learning-based risk prediction models for cardiovascular mortality and hospitalisation for ischemic heart disease (IHD) using self-reported questionnaire data. The 45 and Up Study was a retrospective population-based study in New South Wales, Australia (2005–2009). Self-reported healthcare survey data on 187,268 participants without a history of cardiovascular disease was linked to hospitalisation and mortality data. We compared different machine learning algorithms, including traditional classification methods (support vector machine (SVM), neural network, random forest and logistic regression) and survival methods (fast survival SVM, Cox regression and random survival forest). A total of 3687 participants experienced cardiovascular mortality and 12,841 participants had IHD-related hospitalisation over a median follow-up of 10.4 years and 11.6 years respectively. The best model for cardiovascular mortality was a Cox survival regression with L1 penalty at a re-sampled case/non-case ratio of 0.3 achieved by under-sampling of the non-cases. This model had the Uno's and Harrel's concordance indexes of 0.898 and 0.900 respectively. The best model for IHD hospitalisation was a Cox survival regression with L1 penalty at a re-sampled case/non-case ratio of 1.0 with Uno's and Harrel's concordance indexes of 0.711 and 0.718 respectively. Machine learning-based risk prediction models developed using self-reported questionnaire data had good prediction performance. These models may have the potential to be used in initial screening tests to identify high-risk individuals before undergoing costly investigation. • Risk prediction models were developed for CVD mortality and IHD hospitalisation. • These models were developed using machine learning methods. • These models used exclusively self-reported variables for risk prediction. • These models may allow for cost-effective CVD risk screening and monitoring. [ABSTRACT FROM AUTHOR]

High blood pressure (BP) is the leading preventable risk factor for death, but only one in three patients achieve target BP control. A key contributor to this problem is poor population awareness of high BP, as the majority of patients are asymptomatic. The Shop-To-Stop Hypertension study is a multicenter, cluster-randomized controlled trial to identify, refer and follow adults in need of hypertension care, whilst raising population-wide awareness. In participants with high BP measured by SiSU Health Stations located in major hardware chain stores across New South Wales, Australia, we will determine whether text message-based nudges will encourage repeat BP checks and visits to their doctor. Based on pilot data, we anticipate 65,340 participants will be screened over 12 months, of which 18% will have high BP. Thirty hardware stores will be randomized (1:1) to: (i) Intervention: participants detected with high BP (≥140/≥90 mmHg) will receive text message-based nudges to return for a repeat SiSU Health Station BP check and to visit their general practitioner (GP) to check and manage their BP; (ii) Control: participants with high BP will not receive text messages. The primary outcome is the difference in the proportion of participants with high BP having a repeat BP check at hardware Health Stations in the intervention vs. control group at 12 months. This novel setting for screening utilises a novel 'citizen science' approach inviting the general public to perform their own BP screening at health kiosks and foster behavioral change. This will allow screening in a low-stress environment. • Large, multicenter cluster-randomized trial with 12 months duration. • Identify, refer and follow adults in need of hypertension care, whilst raising population-wide awareness. • Primary outcome: difference in the proportion of participants having a repeat BP check at a health kiosk. • Combines screening with phone text message reminders to foster behavioral change to enter the care pathway. • Findings may increase hypertension diagnosis and health engagement with patients by facilitating a pathway to improved BP control. [ABSTRACT FROM AUTHOR]