Category: Projects

Financial Evaluation of EDDI (Early Detection Decision Information)

Summer of Research project by James Zhang, University of Auckland, supervised by Dr Michael O’Sullivan Jnr (University of Auckland). New software could flag issues early during operations, helping surgeons and anaesthetists intervene before serious complications arise. We need to find out how much of a difference this software makes, and whether it will prevent complications …

Interpretable image-based machine learning models in healthcare

Summer of Research project by Harper Shen, University of Auckland, supervised by Quentin Thurier (Orion Health) and Dr Yun Sing Koh (University of Auckland). Neural networks can be great at solving problems, but they sometimes give wrong answers. Would you trust an algorithm that got life-saving information right 80% of the time? It is easier …

Clinical abbreviations detection and normalisation

Summer of Research project by Enno Huang, University of Auckland, supervised by Edmond Zhang (Orion Health and Precision Driven Health) and Yun Sing Koh (University of Auckland). “2 yo F here for an RPE w/a recent URI who c/o ear pain y/d.” If you can’t understand that sentence from a real paediatric note, you are …

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 train specialist medical algorithms, and medical-specific data is hard to obtain for research, but the payoff may well be worth it. Aaron Zhang’s research shows machine learning algorithms based on …

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, dosages and effects in health records could help researchers find relationships between certain medications and negative effects on patients. An adverse drug event (ADE) is when something bad happens to …

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 vital …

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 …

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 result in negative outcomes such as bias, complications and ultimately invalid conclusions. Finding ways to deal with missing data is at the heart of the project Value added by Multiple …

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 and used based on research conducted in other countries with larger populations. While we have many similarities with these populations, we are not an identical match. Which is why one …