Using machine learning to identify pediatric ophthalmologists.

Journal: Journal of AAPOS : the official publication of the American Association for Pediatric Ophthalmology and Strabismus
PMID: 39566680

Abstract

This cross-sectional study used data from the American Academy of Ophthalmology IRIS Registry (Intelligent Research in Sight) and machine learning algorithms to identify pediatric ophthalmologists based on physician coding patterns. A random forest model achieved an area under the receiver operating characteristic curve of 0.98, sensitivity of 0.98, and specificity of 0.88 when classifying pediatric eye specialists in the test validation cohort. Algorithm-based approaches to identify pediatric ophthalmologists using procedure codes may offer new avenues to determine the scope, scale, and trajectory of pediatric eye care delivery.

Authors

  • Isdin Oke
    Department of Ophthalmology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts.
  • Tobias Elze
    Schepens Eye Research Institute, Harvard Medical School, Boston, Massachusetts; Complex Structures in Biology and Cognition, Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany. Electronic address: tobias-elze@tobias-elze.de.
  • Joan W Miller
    Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts.
  • Alice C Lorch
  • Mei-Sing Ong
    Department of Population Medicine Harvard Medical School & Harvard Pilgrim Health Care Institute Boston MA.
  • Ann Chen Wu
    Center for Healthcare Research in Pediatrics, Department of Population Medicine, Harvard Medical School, Harvard University and Harvard Pilgrim Health Care, Boston, Massachusetts ann.wu@childrens.harvard.edu.
  • David G Hunter
    Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts; Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts.

Keywords

External Resources

Popular Topics
Recent Journals