The Ministry of Health New Zealand uses big data analytics to accurately determine current and predict future diabetic population to improve diabetes policy planning.
In collaboration with experts from the New Zealand Society for the Study of Diabetes (NZSSD), the ministry created a Virtual Diabetes Register (VDR) that pulls and filters health data from six major databases.
The six data sources were: hospital admissions coded for diabetes, outpatient attendees for diabetes and diabetes retinal screening, prescriptions of specific antidiabetic therapies, laboratory orders for measuring diabetes management and primary health (general practitioner) enrollments.
According to Emmanuel Jo, Principal Technical Specialist at Health Workforce New Zealand, Ministry of Health, the previous way of measuring diabetes using national surveys was inefficient, expensive and had a high error rate.
The new analytical model, using SAS software, significantly improved the accuracy and robustness of the system, combining several data sources to generate greater insights.
Interestingly, analytics showed that Indian and Pacific people have the highest diabetes prevalence rate, said Dr. Paul Drury, Clinical Director of the Diabetes Auckland Centre and Medical Director of NZSSD. Health policies can therefore be focused on this group.
“We have 20 different District Health Boards, and the data can show them how many diabetic people are in their area,” Drury said.
“GPs should know already how many they have, but the VDR is also able to help them predict who may be at risk so they can be prepared. By knowing the populations where diabetes is more prevalent, more resources can be directed at them to provide clinical quality improvements,” he added
Patient privacy is protected by regulating access to data in the VDR.