Category: Predictive Analytics

Deep learning-based Melanoma prediction from skin images

Summer of Research project by Sivaram Manoharan, supervised by Bernhard Pfahringer, University of Auckland. Melanoma is an extremely dangerous type of skin cancer most commonly caused by exposure to UV light. The highest incidence rate of Melanoma is in Australia and New Zealand, in addition to being the fourth most common cancer diagnosed in New …

A Prediction Algorithm for Familial Hypercholesterolaemia in New Zealand

Summer of Research project by Nick James, supervised by Dr. Patrick Gladding (University of Auckland). Familial Hypercholesterolaemia (FH) is a genetic condition which causes an increased risk of cardiovascular disease and premature death (3-4 times the risk of early death). It is estimated to affect 1:300 people in the general population of New Zealand. There …

A data mining project using the National Health and Nutrition Examination Survey dataset

Summer of Research project by Josh Atwal, supervised by Dr. Jichao Zhao (University of Auckland). Atrial fibrillation (AF) is the most common sustained heart rhythm disturbance. At present, 25% of the New Zealand population who are 40 years old or more will experience AF in their lifetime. AF increases morbidity and mortality. The aim of …

Countering bias in the health system

This week Dr Kevin Ross, General Manager of Precision Driven Health and Haze White, Māori Health Researcher, spoke to Radio New Zealand about countering ethnic bias in the health system to ensure the findings of NZ health data research is meaningful for all groups of the population. The key topic of discussion was the reality …

Feasibility of Analysis of Lab Result Patterns for Patient Results

This feasibility study, in partnership with Vensa Health, is answering the following questions: How can we accurately automate interpretation and dissemination of lab results to save clinician time, while keeping the clinical control in their hands in way that’s intuitive and flexible? Can collective best practices be gathered and help improve clinical decision making based …

A Deep Learning Platform for GP Referral Triage

Countering bias in the health system Heart disease is the leading cause of preventable mortality in Aotearoa, New Zealand. It is a disease which disproportionately affects certain groups such as Māori – who have higher rates of ischaemic heart disease (or coronary heart disease) and stroke but have lower access to health care. It is …

Interpretable Machine Learning

The “black box” metaphor is commonly used to refer to the lack of understanding of how modern Machine Learning (ML) systems make decisions. Researchers are working actively to remedy this situation which is especially problematic in Healthcare where legal accountability and ethics have to be taken into account in the decision-making process. Consequently, the industry …

Calculating Risk Over the Long Term

The practice of medicine is fast becoming a data science, and nowhere is this more apparent than with one of Precision Driven Health’s foundation projects – Epidemiology and the estimation of long-term surgical mortality. Principal investigator Dr Doug Campbell1 from Auckland District Health Board and his team are combining large national datasets of surgical operation …

Ensuring the Right Dosage

Ensuring patients are given the correct medication, in the right dosage, with proper instruction, is absolutely critical. However, the job of medication reconciliation is currently an onerous task that is tedious and time-consuming, even with the best software. Somebody needs to manually check every medication a patient is taking, to ensure that instructions are clear …

Harnessing Data to Investigate Surgical Outcomes

The NMDS is a set of patient health information collected on everyone who visits a health organisation in New Zealand. The information is anonymised and predominantly used for small scale administration and auditing. For this study, we utilised the records of all patients in NZ who had undergone surgery in 2013-2014 as our data set. …