A Deep Learning Platform for GP Referral TriageHeart 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.
Lead researchers on this project:
- Dr Edmond Zhang, Principal Investigator, Senior Data Scientist, Orion Health
- Reece Robinson, Associate Investigator, VP Engineering, Orion Health
- Dr Patrick Gladding, Clinical Lead, Cardiologist, Waitemata District Health Board
Other researchers on this project:
- Associate Professor Peter van de Weijer, Triage Expert, Director Women’s Health, Auckland District Health Board
- Professor Bernhard Pfahringer, Machine Learning Expert, Professor of Computer Science, University of Waikato
- Dr Yun Sing Koh, Machine Learning Expert, Senior Lecturer of Computer Science, University of Auckland
- Delwyn Armstrong, Clinical Data Expert, Head of Analytics, Waitemata District Health Board
- Haze White, Maori health researcher, Wai-Research
- Elica Mehr, Maori health researcher, Wai-Research
- Susan Smith, Referrals Expert, GP, Eastmed Doctors
- Umit Holland, Project Coordinator, CNS Researcher, Waitemata District Health Board
- Bronwen Gilson, Clinical Data Expert, Information Analyst, Waitemata District Health Board
- Steve Nicholas, Product Expert, eReferrals Director, Orion Health
- Kevin Bayes, Machine Learning Engineer, Senior Lead Engineer, Orion Health
- May Lin Tye, Business Analyst, Orion Health
- Anna Spyker, Machine Learning Engineer, Software Engineer, Orion Health
- Michael Hosking, Clinical Coding Expert, Clinical Product Specialist, Orion Health
- Ning Hua, Data Scientist, Orion Health
- Dominic Yuen, Software Engineer, Orion Health
- Aaron Zhang, Data Science Intern, University of Auckland
TimelineAugust 2018 – August 2020
Further readingDeep Learning for Triaging GP Referrals
Publications and PresentationsE. Zhang, R. Robinson and B. Pfahringer, “Deep Holistic Representation Learning from EHR,” 2018 12th International Symposium on Medical Information and Communication Technology (ISMICT), Sydney, NSW, 2018, pp. 1-6. doi: 10.1109/ISMICT.2018.8573698
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 that intervention occurs early to prevent serious illness, but the data shows that the New Zealanders most susceptible to this disease – Māori and Pasifika – may suffer from bias in the health system. This is partly due to inefficient triaging, with some patients being unnecessarily accepted for a hospital clinic appointment and as a result bumping those more in need further down the queue.
Under a paper-based system it was impossible to really understand how primary-care referrals were being prioritised, but the switch to electronic referrals has enabled the ability for Precision Driven Health researchers to get a better understanding of who is being prioritised for early referral to a cardiologist.
We have little control over the referrals generated by GPs in the community, but our research can provide the opportunity to address and counter bias. We can do this by acknowledging and identifying biases in the model and then testing model biases with Māori involvement. We are working with Māori health researchers and He Kamaka Waiora to develop strategies to address and counter any implicit bias in terms of unequal access to specialists for key populations.
Our aim is to create a machine learning-based triage decision support system that will improve better health outcomes for patients through efficient and timely processing of their referrals. The first step is a GP referral triage system using available patient records from Waitemata District Health Board.
Subsequent stages will focus on the automation of this process, which can be easily adapted for another hospital or population. This will involve either the reuse of statistical knowledge learned from the Waitemata DHB dataset or training the model from scratch, leveraging Orion Health Amadeus CORE.
It is expected that the automated triaging tool that emerges from this research can also be applied to other DHBs in New Zealand as well as overseas institutions. The ultimate result being that the most at-risk patients will be prioritised and that over time ethnic bias in the health system can be eradicated.