An approach to make general practitioner referrals suitable for artificial intelligence deployment.
| Title: | An approach to make general practitioner referrals suitable for artificial intelligence deployment. |
|---|---|
| Authors: | Lesiawan E; Advanced Physician Trainee, Health New Zealand - Te Whatu Ora, New Zealand.; Sutherland B; General Practitioner, Kawau Bay Health, Warkworth, Auckland, New Zealand.; Schumacher C; Professor of Economics, School of Economics and Finance, Massey Business School, Albany, Auckland, New Zealand.; Cave A; Digital Hospital Implementation Lead, Data & Digital, Integration & Delivery, Health New Zealand - Te Whatu Ora Northern, New Zealand.; Armstrong G; Cardiologist, Health New Zealand - Te Whatu Ora Waitematā, Auckland, New Zealand. |
| Source: | The New Zealand medical journal [N Z Med J] 2025 Dec 12; Vol. 138 (1627), pp. 96-126. Date of Electronic Publication: 2025 Dec 12. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Pasifika Medical Association Group Country of Publication: New Zealand NLM ID: 0401067 Publication Model: Electronic Cited Medium: Internet ISSN: 1175-8716 (Electronic) Linking ISSN: 00288446 NLM ISO Abbreviation: N Z Med J Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2022- : Auckland : Pasifika Medical Association Group; Original Publication: Wellington : New Zealand Medical Association |
| MeSH Terms: | Referral and Consultation* ; Artificial Intelligence* ; General Practitioners* ; Decision Support Systems, Clinical*; Humans ; Decision Trees ; New Zealand ; Machine Learning |
| Abstract: | Outpatient referrals for hospital specialist assessment are an increasing workload that carry significant risk if not attended to in a timely manner. This viewpoint discusses how decision support (including artificial intelligence and machine learning) may address this problem. Of the many possible approaches, we choose a combination of two that illustrate the breadth of available tools and how they combine to complement each other. To understand the issues and inform this discussion, a survey of general practitioners' views was conducted (Appendix 2), an audit of declined referrals was undertaken (Appendix 3) and draft decision trees were constructed (Appendix 4). To have data suitable for automated decision support, the current referral needs to change from free text to a structured format that ensures every patient has a complete minimum dataset. Regarding triaging decisions, at present there is human variability, but the decision support tools will need to be trained on a set of referrals that have an agreed gold-standard decision. In order to maintain patient safety throughout, the process needs to be incremental. We suggest that one way to assure patient safety is to combine simple decision trees with sophisticated contemporary machine learning.; (© PMA.) |
| Competing Interests: | Nil. |
| Entry Date(s): | Date Created: 20251211 Date Completed: 20251211 Latest Revision: 20260310 |
| Update Code: | 20260310 |
| DOI: | 10.26635/6965.6979 |
| PMID: | 41380127 |
| Database: | MEDLINE |
Journal Article