Badrick, TonyTseung, JasonFrogley, MaddisonChai, Sze YeeLidbury, Brett A.2026-06-112026-06-110009-8981PubMed:40147806ORCID:/0000-0003-2211-989X/work/217152015https://hdl.handle.net/1885/733810662A standard for reporting genetic pathology results currently does not exist as a consensus. While effective reports are produced, there is lack of consistency on which details to present or to emphasise, and the ultimate report often reflects an individual practitioner's preferences derived from anecdotal experience. Genetic knowledge is complex, so poor and/or inconsistent reporting could make the application of pathology results to patient management more challenging than necessary. The aim of this study was to combine expert knowledge with machine learning (ML) applications to design a template to encourage consistent and accurate genetic reporting. To investigate genetic reporting quality within Australasia, past melanoma genetics reports produced in response to RCPA Quality Assurance Program (RCPAQAP) audits were compiled for retrospective text analyses to determine word frequencies and patterns. These text pattern analyses were supported by an investigation of reporting criteria consistency for solid tumours, as well as a narrative review of the broader literature, by a genetic pathology expert to contextualise these results, with the ultimate results combined into a suggested template. These results will be augmented via further ML studies on report structure.The authors wish to thank RCPAQAP staff for assisting with labelling of pathology reports for machine learning, as well as Derek Holzhauser and Stella Lovell for project management. Thanks to the staff in the NCEPH (ANU) College of Health and Medicine Research Offices for general administrative support and the facilitation of contracts, payments and agreements between the ANU, the RCPAQAP and the Commonwealth Department of Health.enPublisher Copyright: © 2025 Elsevier B.V.EQAMachine learningMelanoma genetic reporting2025-05-1510.1016/j.cca.2025.120263105001273832