Health Outcome Prediction Engine
Health Outcome Prediction Engine (HOPE)
HOPE for Stroke
HOPE for AAA (Abdominal Aortic Aneurysm)
HOPE for Patient Reported Outcome Measures
Treatment decisions for elective interventions such as hip replacement for osteoarthritis are currently based on clinicians’ assessment of likely benefit from surgery derived from their personal experience and knowledge of published evidence of effectiveness. In New Zealand eligibility for surgery is based on a prioritisation score derived from clinical assessment of the patient. The scoring usually takes little account of how various patient-specific factors might affect the net benefit the patient receives from surgery, and the cut-off remains somewhat arbitrary. Relevant patient-specific factors include comorbidities (e.g. obesity in the case of hip replacement), sex, age, the patient’s life expectancy etc. The result is that health outcomes and the total health gain from these procedures is highly variable, as is naturally their cost-effectiveness. Patients and payers of health services would value more accurate prediction of outcomes and cost-effectiveness.
This project produced a prototype electronic clinical decision support system to make precise health outcome predictions tailored to the specific circumstances of individual patients. This combined the existing knowledge base of the effectiveness and cost-effectiveness of one (or more) elective interventions with a supervised machine learning algorithm that iteratively increases the predictive accuracy of the initial model. Routine pre- and post-operative measurement of Patient Reported Outcome Measures will be implemented to provide the machine learning algorithm with key data inputs, along with other relevant variables drawn from structured electronic data held within the DHB data warehouse.
HOPE for Stroke encompassed a predictive model and clinical decision support system for stroke patient outcome prediction within Waitemata District Health Board.
HOPE for AAA involved creation of a model predicting more accurate population screening for abdominal aortic aneurysms within primary care settings.
Dr Peter Sandiford, Waitemata District Health Board
This project’s predictive model for abdominal aortic aneurysm screening was presented at the 2017 HiNZ conference
and was subsequently publicised in a press release
attracting media coverage.