LAVA: Language Model Assisted Verbal Autopsy for Cause-of-Death Determination
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909782088089600 |
|---|---|
| author | Chen, Yiqun T. McCormick, Tyler H. Liu, Li Datta, Abhirup |
| author_facet | Chen, Yiqun T. McCormick, Tyler H. Liu, Li Datta, Abhirup |
| contents | Verbal autopsy (VA) is a critical tool for estimating causes of death in resource-limited settings where medical certification is unavailable. This study presents LA-VA, a proof-of-concept pipeline that combines Large Language Models (LLMs) with traditional algorithmic approaches and embedding-based classification for improved cause-of-death prediction. Using the Population Health Metrics Research Consortium (PHMRC) dataset across three age categories (Adult: 7,580; Child: 1,960; Neonate: 2,438), we evaluate multiple approaches: GPT-5 predictions, LCVA baseline, text embeddings, and meta-learner ensembles. Our results demonstrate that GPT-5 achieves the highest individual performance with average test site accuracies of 48.6% (Adult), 50.5% (Child), and 53.5% (Neonate), outperforming traditional statistical machine learning baselines by 5-10%. Our findings suggest that simple off-the-shelf LLM-assisted approaches could substantially improve verbal autopsy accuracy, with important implications for global health surveillance in low-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LAVA: Language Model Assisted Verbal Autopsy for Cause-of-Death Determination Chen, Yiqun T. McCormick, Tyler H. Liu, Li Datta, Abhirup Computation and Language Applications Verbal autopsy (VA) is a critical tool for estimating causes of death in resource-limited settings where medical certification is unavailable. This study presents LA-VA, a proof-of-concept pipeline that combines Large Language Models (LLMs) with traditional algorithmic approaches and embedding-based classification for improved cause-of-death prediction. Using the Population Health Metrics Research Consortium (PHMRC) dataset across three age categories (Adult: 7,580; Child: 1,960; Neonate: 2,438), we evaluate multiple approaches: GPT-5 predictions, LCVA baseline, text embeddings, and meta-learner ensembles. Our results demonstrate that GPT-5 achieves the highest individual performance with average test site accuracies of 48.6% (Adult), 50.5% (Child), and 53.5% (Neonate), outperforming traditional statistical machine learning baselines by 5-10%. Our findings suggest that simple off-the-shelf LLM-assisted approaches could substantially improve verbal autopsy accuracy, with important implications for global health surveillance in low-resource settings. |
| title | LAVA: Language Model Assisted Verbal Autopsy for Cause-of-Death Determination |
| topic | Computation and Language Applications |
| url | https://arxiv.org/abs/2509.09602 |