Research Projects

A Deep Learning Platform for GP Referral Triage

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 ...

A Patient’s Journey for an Elective Surgery

A Patient's Journey for an Elective Surgery

An Automated Approach Towards Prioritisation and Preoperative Assessment The path to an elective surgery can contain many difficulties for both patients and clinicians. It is ...

A Public Health Calculator Website for Kiwis

A Public Health Calculator Website for Kiwis

Calibrated for Kiwis As a small country in the South Pacific, our uniqueness is often overlooked by health science researchers. Medical assessment tools are created ...

Automated De-identification

Automated De-identification

Separating patients from their records The idea that a patient’s Electronic Health Record (EHR) has a secondary value, beyond the immediate treatment of a single ...

Automated Message Mapping

message map

This project involves automation of systems for mapping target fields to and from HL7 messages to enable automation of this previously laborious, manual process. PI: ...

Clinical Risk Assessments and Calculators

Clinical Risk Assessments and Calculators

Recent studies have indicated that the current risk calculators are out of date and not specific to local contexts and population. This project is testing ...

Deep Representation Learning from Electronic Health Records

Deep Representation Learning from Electronic Health Records

As Electronic Health Records (EHRs) become more ubiquitous, healthcare providers are beginning to appreciate the benefits of using this data for ‘secondary applications’, such as ...

Evaluating Biomedical Word Embeddings

Evaluating Biomedical Word Embeddings

Summer of Research project by student Aaron Zhang (The University of Auckland), supervised by Dr Edmond Zhang (Orion Health). It takes time and money to ...

Feasibility of Analysis of Lab Result Patterns for Patient Results

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 ...

Feature importance for adverse drug event named entity recognition

Feature importance for adverse drug event named entity recognition

Summer of Research project by Hamish Huggard, University of Auckland, supervised by Dr Edmond Zhang (Precision Driven Health and Orion Health). Automatically identifying drug names, ...

Health Outcome Prediction Engine

Health Outcome Prediction Engine

Health Outcome Prediction Engine (HOPE), comprising HOPE for Stroke HOPE for AAA (Abdominal Aortic Aneurysm) HOPE for Patient Reported Outcome Measures Treatment decisions for elective ...

Information Consent Best Practice

information consent best practice

Data-driven healthcare will result in a “tsunami” of information from existing and new data sources including patient-generated data from genetic testing, consumer devices such as ...

Integrating Primary and Secondary Healthcare Systems

integrating systems

Primary and secondary healthcare data has the potential to enhance the accuracy of healthcare decision making; however, it is often siloed and difficult to share ...

Interpretable Machine Learning

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 ...

Making Existing Data Sources Available

Making Existing Data Sources Available

New Zealand has excellent health data due to national ID number and high quality data scientists. We seek to link them together by making health ...

Missing Health Data Imputation

Missing Health Data Imputation

Medical professionals analysing electronic health data often have to deal with data sets that are incomplete. If this data is not handled correctly it can ...

See How They Grow

See How They Grow

In partnership with Cure Kids and the National Science Challenge A Better Start, PDH supports the work led by The University of Auckland’s Gayl Humphrey on ...

Smart Medication Reconciliation

Smart Medication Reconciliation

Automating for accuracy Patients’ regular medicines are often inaccurately prescribed when they transfer from hospital to home; a major source of medication errors and iatrogenic ...

Smart Search: Clinical Document Semantic Search

Smart Search: Clinical Document Semantic Search

A ‘Google’ for Electronic Health Records  Ten minutes can be an eternity for medical professionals that need to make split-second decisions to save lives. If ...

Spatio-Temporal Big Data Analysis of Adherence Behaviour in Chronic Disease

Spatio-Temporal Big Data Analysis of Adherence Behaviour in Chronic Disease

Many patients in New Zealand don’t receive the benefits from their medications due to poor medication behaviour, referred to as medication adherence. Previously, data related ...

Surgical Outcome Calculator

surgical outcome

Present methods for describing surgical outcomes greatly underestimate the risks to patients. The aim of this project is to find a method that describes post-operative ...

Vital Sign Monitoring and Decision Support System

Vital Sign Monitoring and Decision Support System

During admission to hospital, patients often show signs of acute physical deterioration before a serious event occurs. Current variation in vital signs charts, early warning ...