Leveraging large language models for heuristic usability assessment of medical software: Insights with the Radiation Planning Assistant
While ChatGPT did not reveal any critical usability failures, its heuristic assessment proved valuable in prompting discussion, identifying minor refinements, and enriching both developer and user engagement with the RPA's interface design. This study demonstrates that LLMs can serve as an effective, low-cost complement to conventional heuristic evaluation, supporting early-stage usability review and stakeholder dialogue in the development of medical software.
Authors
- Christine Chung (ORCID: https://orcid.org/0000-0002-3093-6913)
- William V. Shaw (ORCID: https://orcid.org/0000-0001-5492-6122)
- Laurence E. Court (ORCID: https://orcid.org/0000-0002-3241-6145)
- Carlos E. S. Cárdenas
- L.J. Strauss (ORCID: https://orcid.org/0000-0002-2607-7941)
- T. Netherton
- Elaine G. Smith
- Pavel Govyadinov (ORCID: https://orcid.org/0000-0001-7980-2791)
- Lauren Netherton
- Nanette Joubert
- Saurabh Sudhakaran Nair
- Lifei Zhang (ORCID: https://orcid.org/0000-0002-7790-9509)
- Meena Khan
- Jan Seuntjens
- Andrea Marais
- Wanda van Heerden
- Shona Badre
- Monica Serban
- Graeme L. Lazarus
- Christoph Trauernicht
- Thekiso Khotle
- Jacobus Smit
Institutions
- The University of Texas MD Anderson Cancer Center (US)
- Stellenbosch University (ZA)
- University of the Free State (ZA)
- Johannesburg Hospital (ZA)
- Groote Schuur Hospital (ZA)
- Princess Margaret Cancer Centre (CA)
- Tygerberg Hospital (ZA)
- University of Alabama at Birmingham (US)
- Research ICT Africa (ZA)
- Wentworth Hospital (ZA)
- University of Houston (US)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2026-02-01
- DOI
- https://doi.org/10.1002/acm2.70495
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00