A Generalized Machine Learning Model For Identifying Congenital Heart Defects (CHDs) Using ICD Codes.

Details

• Alternative Title:
  Birth Defects Research, 2025, v. 117, no. 2: A Generalized Machine Learning Model For Identifying Congenital Heart Defects (CHDs) Using ICD Codes.
• Journal Article:
  Birth Defects Research
• Personal Author:
  Shi, Haoming ; Book, Wendy M. ; Ivey, Lindsey C. ; Rodriguez, Fred H. ; Raskind-Hood, Cheryl ; Downing, Karrie F. ; Farr, Sherry L. ; McCracken, Courtney E. ; Leedom, Vinita O. ; Haynes, Susan E. ; Amouzou, Sandra ; Sameni, Reza ; Kamaleswaran, Rishikesan
• Description:
  International Classification of Diseases (ICD) codes utilized for congenital heart defect (CHD) case identification in datasets have substantial false-positive (FP) rates. Incorporating machine learning (ML) algorithms following case selection by ICD codes may improve the accuracy of CHD identification, enhancing surveillance efforts.
  
  Traditional ML methods were applied to four encounter-level datasets, 2010-2019, for 3334 patients with validated diagnoses and with at least one CHD ICD code identified. A 5-fold cross-validation approach was applied to the dataset to determine the set of overlapping important features best classifying CHD cases. Training and testing combinations were explored to determine the approach yielding the most accurate CHD classification.
  
  CHD ICD positive predictive values (PPVs) by site ranged from 53.2% to 84.0%. The ML algorithm achieved a PPV of 95% (1273/1340) for the four-site dataset with a false-negative (FN) rate of 33% (639/1912) by choosing an operating point prioritizing PPV from the PPV-FN rate curve. XGBoost reduced 2105 Clinical Classification Software (CCS) features to 137 that identified those with true-positive (TP) CHD and false-positive FP classification.
  
  Applying ML algorithms following case selection by CHD-related ICD codes improved the accuracy of identifying TP true-positive CHD cases.
• Content Notes:
  Author manuscript
• Subjects:
  • Humans
  • Heart Defects, Congenital
  • Machine Learning
  • International Classification of Diseases
  • Algorithms
  • Female
  • Male
  • False Positive Reactions
• Keywords:
  • Machine Learning
  • Congenital Heart Disease
  • Population Health
• Source:
  Birth Defects Research, 2025, v. 117, no. 2
• DOI:
  https://doi.org/10.1002/bdr2.2440
• ISSN:
  2472-1727
• Pubmed ID:
  39890469
• Pubmed Central ID:
  PMC12027675
• Document Type:
  Text
• Funding:
  NU50DD000098/DD/NCBDD CDC HHSUnited States/ ; UL1 TR002378/TR/NCATS NIH HHSUnited States/ ; CDC-RFA-DD19-1902B/Centers for Disease Control/ ; CC/CDC HHSUnited States/
• Genre:
  Journal Article
• Pages in Document:
  e2440 (25 pdf pages)
• Volume:
  117
• Issue:
  2
• Download URL:
  https://stacks.cdc.gov/view/cdc/261716/cdc_261716_DS1.pdf
• File Type:
  [PDF - 1.39 MB]
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha-512:3abbc59df4c9ad4758b550d49017157e47005898b7fe92bd37b5c30a0c30a3683d8bf395b0247cc2bb7c5a4c86dfc395476ba6f8f94eca2734d83da784fb097c