Performance of a Computational Phenotyping Algorithm for Sarcoidosis Using Diagnostic Codes in Electronic Medical Records: Case Validation Study From 2 Veterans Affairs Medical Centers.

Mohamed Ismail Seedahmed Izabella Mogilnicka Siyang Zeng Gang Luo Mary A Whooley Charles E McCulloch Laura L Koth Mehrdad Arjomandi

Published in: JMIR formative research (2022)

ICD codes are reasonable classifiers for identifying sarcoidosis cases within EMRs with a PPV of 79%. Using a computational algorithm to capture index of suspicion data elements could significantly improve the case-identification accuracy.

Keyphrases

machine learning
deep learning
healthcare
high throughput
big data
electronic health record
neural network
single cell