Machine Learning and Natural Language Processing to Improve Classification of Atrial Septal Defects in Electronic Health Records
This study demonstrates that it is feasible to use patients' clinical notes and machine learning to perform more fine-grained classification compared to ICD codes, particularly with higher PPV for CHD. The proposed approach can improve CHD surveillance.
Authors
- Lindsey C. Ivey (ORCID: https://orcid.org/0009-0008-5882-2361)
- Wendy Book (ORCID: https://orcid.org/0000-0002-3599-0329)
- Chad J. Robichaux (ORCID: https://orcid.org/0009-0002-8403-5499)
- Fred H. Rodriguez (ORCID: https://orcid.org/0000-0002-4833-3483)
- Haoming Shi (ORCID: https://orcid.org/0000-0002-0228-6116)
- Karrie F. Downing (ORCID: https://orcid.org/0000-0002-3063-1781)
- Reza Sameni (ORCID: https://orcid.org/0000-0003-4913-6825)
- Cheryl Raskind‐Hood (ORCID: https://orcid.org/0000-0002-3301-0980)
- Abeed Sarker (ORCID: https://orcid.org/0000-0001-7358-544X)
- Yuting Guo (ORCID: https://orcid.org/0000-0002-8919-0888)
Institutions
- Centers for Disease Control and Prevention (US)
- Georgia Institute of Technology (US)
- Emory University (US)
- National Center on Birth Defects and Developmental Disabilities (US)
Publication Details
- Journal
- Birth Defects Research
- Published
- 2025-03-01
- DOI
- https://doi.org/10.1002/bdr2.2451
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Center for Advancing Translational Sciences