Computer assisted verbal autopsy: comparing large language models to physicians for assigning causes to 6939 deaths in Sierra Leone from 2019–2022
GPT models and InSilicoVA showed greater performance for specific CODs at the individual-level. GPT models demonstrated improvements over InterVA-5 and InSilicoVA models. This study provides foundational evidence for integrating LLM and algorithmic models with physician coding to improve the quality of VA data.
Authors
- Anteneh Assalif (ORCID: https://orcid.org/0000-0001-6928-1494)
- Asha Behdinan
- Rajeev Kamadod
- Ronald Carshon-Marsh (ORCID: https://orcid.org/0000-0002-1596-8626)
- Patrick Brown (ORCID: https://orcid.org/0000-0003-2541-3744)
- Catherine Meh (ORCID: https://orcid.org/0000-0003-2476-8439)
- Richard Wen (ORCID: https://orcid.org/0000-0002-8904-8152)
- Andy Sze-Heng Lee
- Rashid Ansumana
- Thomas Kai Sze Ng
- Prabhat Jha
Institutions
- St. Michael's Hospital (CA)
- Njala University (SL)
- St Michael's Hospital (GB)
- Centre for Global Health Research (CA)
Publication Details
- Journal
- BMC Medicine
- Published
- 2025-12-24
- DOI
- https://doi.org/10.1186/s12916-025-04584-z
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Bill and Melinda Gates Foundation