CSIRO logo

The challenge

Identifying at-risk patients for the Australian Government's Health Care Homes trial

The Australian Government's stage one trial of Health Care Homes, which started in October 2017, aims to provide better coordinated care for people with chronic and complex health conditions, and their families and caregivers.

Enrolled patients receive improved, patient-centred, coordinated and flexible care, supported by an innovative funding model.

The challenge lies in identifying which patients would benefit most from the Health Care Homes program.

Our response

A predictive risk algorithm to identify patients at risk of hospitalization

Partnering with Precedence Health Care and Sonic Health Services, our data scientists developed and validated a predictive risk model to help identify patients who would be eligible for the Health Care Homes trial, based on their risk of hospitalization in the next 12 months.

Developed using de-identified primary care data, the model takes into account patient demographics, their socio-economic index of relative advantage/disadvantage, physiological information, medications, chronic conditions, pathology categories according to abnormal levels in test results, and lifestyle factors such as alcohol and tobacco use.

The results

Our model has been installed in more than 150 practices and services around Australia

As of November 2018, our predictive risk tool has been installed in more than 150 health services around Australia participating in the Health Care Homes program. Patients identified by our algorithm were then contacted by the participating health service and invited to undertake a further assessment of their eligibility and Health Care Homes tier level.

Patients assigned to a health care home are looked after by a committed care team, led by their usual doctor, and have access to a shared care plan, better access, flexibility, and better coordinated care.

After the two-year Health Care Homes trial, an independent evaluation will be carried out.

Predicting hospitalization

Our predictive risk model is helping to identify patients at risk of hospitalization in the next 12 months.