Automated transformation of unstructured cardiovascular diagnostic reports into structured datasets using sequentially deployed large language models
We developed and validated a novel approach using paired large and moderate-sized LLMs to transform free-text echocardiographic reports into tabular datasets.
Authors
- Rohan Khera (ORCID: https://orcid.org/0000-0001-9467-6199)
- Aline F Pedroso (ORCID: https://orcid.org/0000-0002-1876-8304)
- Cynthia Brandt (ORCID: https://orcid.org/0000-0001-8179-1796)
- Lovedeep Singh Dhingra (ORCID: https://orcid.org/0000-0002-5664-4126)
- Girish N. Nadkarni (ORCID: https://orcid.org/0000-0001-6319-4314)
- Philip Adejumo (ORCID: https://orcid.org/0000-0002-9289-8377)
- Arya Aminorroaya (ORCID: https://orcid.org/0000-0003-3197-2657)
- Hua Xu (ORCID: https://orcid.org/0000-0002-5274-4672)
- Sumukh Vasisht Shankar (ORCID: https://orcid.org/0009-0005-3034-0641)
- Evangelos K. Oikonomou (ORCID: https://orcid.org/0000-0003-4362-0720)
Institutions
- Yale New Haven Hospital (US)
- Yale University (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- European Heart Journal - Digital Health
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1093/ehjdh/ztaf030
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- National Institutes of Health
- National Heart, Lung, and Blood Institute