nzRISK: A surgical risk calculator for New Zealand patients
For patients and clinicians, deciding whether to go ahead with major surgery or not can be difficult. Your surgeon and anaesthetist will discuss both the benefits and risks of having surgery to help with the shared decision making process.
In the past, many clinicians have found it difficult to accurately assess the risk of having surgery for their patients because of current risk assessment tools. Many of these tools are 20-30 years old and are based on a small number of patients’ data from either the UK or USA, therefore they are not tailored to a New Zealand population.
The aim of this project was to find a method that describes post-operative risk more accurately and then develop a surgical risk calculator. The research is wide-reaching and is expected to improve estimates of surgical mortality needed for informed consent, improved shared decision-making, triaging of high-risk patients, quantifying healthcare performance and avoiding low value surgical operations.
We developed nzRISK, a multi-variate risk model that requires 7 inputs such as a patient’s age, gender, ethnicity and what procedure they are having, and then produces a risk score for that patient at one month, one year and two years after surgery. This risk score helps clinicians categorise patients as low, medium or high risk in terms of surgical mortality risk.
The nzRISK calculator was developed using unbiased, local data from 360,000 patients and is applicable to all non-cardiac surgery in New Zealand. This is the most appropriate risk calculator for all non-cardiac surgeries in New Zealand.
At Auckland City Hospital, one of the earliest uses of nzRISK has been to embed it into pre-operative pathways to simplify the process for patients, so they can bypass some of the repeat visits to hospital. This has allowed clinicians to spend more time with the higher risk patients, improving efficiency and the patient experience.
PI: Dr Doug Campbell, Auckland District Health Board
Research team: Luke Boyle, Orion Health
Dr Tim Short, Auckland District Health Board
Dr Alan Merry, University of Auckland
Prof Thomas Lumley, University of Auckland
- Scientific article in the journal Neurosurgery, May 2020: Development and validation of a multivariate prediction model of perioperative mortality in neurosurgery: The New Zealand neurosurgical risk tool (NZRISK-NEURO)
- Scientific article in the British Journal of Surgery, August 2019: National risk prediction model for perioperative mortality in non-cardiac surgery
- Presentation at the HiNZ conference, Nov 2018: Machine learning for improved risk prediction in high risk surgical cohorts
- Read more about this project: Harnessing data to investigate surgical outcomes