Machine Learning and Natural Language Processing to Improve Classification of Atrial Septal Defects in Electronic Health Records.

Details

• Alternative Title:
  Birth Defects Research, 2025, v. 117, no. 3: Machine Learning and Natural Language Processing to Improve Classification of Atrial Septal Defects in Electronic Health Records.
• Journal Article:
  Birth Defects Research
• Personal Author:
  Guo, Yuting ; Shi, Haoming ; Book, Wendy M. ; Ivey, Lindsey Carrie ; Rodriguez, Fred H. ; Sameni, Reza ; Raskind-Hood, Cheryl ; Robichaux, Chad ; Downing, Karrie F. ; Sarker, Abeed
• Description:
  International Classification of Disease (ICD) codes can accurately identify patients with certain congenital heart defects (CHDs). In ICD-defined CHD data sets, the code for secundum atrial septal defect (ASD) is the most common, but it has a low positive predictive value for CHD, potentially resulting in the drawing of erroneous conclusions from such data sets. Methods with reduced false positive rates for CHD among individuals captured with the ASD ICD code are needed for public health surveillance.
  
  We propose a two-level classification system, which includes a CHD and an ASD classification model, to categorize cases with an ASD ICD code into three groups: ASD, other CHD, or no CHD (including patent foramen ovale). In the proposed approach, a machine learning model that leverages structured data is combined with a text classification system. We compare performances for three text classification strategies: support vector machines (SVMs) using text-based features, a robustly optimized Transformer-based model (RoBERTa), and a scalable tree boosting system using non-text-based features (XGBoost).
  
  Using SVM for both CHD and ASD resulted in the best performance for the ASD and no CHD group, achieving F
  
  scores of 0.53 (±0.05) and 0.78 (±0.02), respectively. XGBoost for CHD and SVM for ASD classification performed best for the other CHD group (F
  
  score: 0.39 ±0.03).
  
  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.
• Content Notes:
  Author manuscript
• Subjects:
  • Humans
  • Natural Language Processing
  • Machine Learning
  • Electronic Health Records
  • Heart Septal Defects, Atrial
  • International Classification of Diseases
  • Support Vector Machine
  • Heart Defects, Congenital
• Keywords:
  • atrial septal defect
  • birth defects
  • congenital heart disease
  • natural language processing
• Source:
  Birth Defects Research, 2025, v. 117, no. 3
• DOI:
  https://doi.org/10.1002/bdr2.2451
• ISSN:
  2472-1727
• Pubmed ID:
  40035168
• Pubmed Central ID:
  PMC11955907
• Document Type:
  Text
• Funding:
  DD19-1902B/Centers for Disease Control and Prevention National Center on Birth Defects And Developmental Disabilities (NCBDD)/ ; UL1TR002378/TR/NCATS NIH HHSUnited States/ ; UL1 TR002378/TR/NCATS NIH HHSUnited States/ ; CC999999/ImCDC/Intramural CDC HHSUnited States/ ; Medical Informatics and Artificial Intelligence Core (MIAI)/
• Genre:
  Journal Article
• Pages in Document:
  e2451 (20 pdf pages)
• Volume:
  117
• Issue:
  3
• Download URL:
  https://stacks.cdc.gov/view/cdc/261631/cdc_261631_DS1.pdf
• File Type:
  [PDF - 863.33 KB]
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha-512:322f11bf33c952576ffef33e35fbfe2c3447cb43e9a38dbe4a56216d3189ab4aacef4ab2ea4463e60f8b38d4abb0ec785f5d0db15e149fec3a6b70dc1d1920df