Public Data for: Computer Assisted Verbal Autopsy: Comparing Large Language Models to Physicians for Assigning Causes to 6939 Deaths in Sierra Leone from 2019-2022

Domain:

healthcare

Record type:

dataset

Creator:

WenAssLeeKam

Editor:

CenOpeWen

Publisher:

Har

Host:

Public data on 6939 deaths in Sierra Leone from 2019-2022 acquired through verbal autopsy. The data was collected for a study comparing GPT and OpenVA models to physician coding of deaths. Public data only. For the full dataset, please send a request to contact@openmortality.org for potential approval. Code is available at cghr-toronto/wen-et-al-2025….

Visit

doi.org dataverse.harvard.edu

Licenses

info:eu-repo/semantics/openAccess Creative Commons Zero v1.0 Universal https://creativecommons.org/publicdomain/zero/1.0/legalcode

Computer Assisted Verbal Autopsy: Comparing Large Language Models to Physicians for Assigning Causes to 6939 Deaths in Sierra Leone from 2019-2022

Abstract Background Verbal autopsies (VAs) collect information on deaths in low an

Additional file 1 of Computer assisted verbal autopsy: comparing large language models to physicians for assigning causes to 6939 deaths in Sierra Leone from 2019–2022

Additional file 1. (.pdf) titled ”Central Medical Evaluation Agreement 10 (CMEA-10) codes” with desc