@article{74796427a5674452ae0687f1141569ef,
title = "A machine learning model identifies patients in need of autoimmune disease testing using electronic health records",
abstract = "Systemic autoimmune rheumatic diseases (SARDs) can lead to irreversible damage if left untreated, yet these patients often endure long diagnostic journeys before being diagnosed and treated. Machine learning may help overcome the challenges of diagnosing SARDs and inform clinical decision-making. Here, we developed and tested a machine learning model to identify patients who should receive rheumatological evaluation for SARDs using longitudinal electronic health records of 161,584 individuals from two institutions. The model demonstrated high performance for predicting cases of autoantibody-tested individuals in a validation set, an external test set, and an independent cohort with a broader case definition. This approach identified more individuals for autoantibody testing compared with current clinical standards and a greater proportion of autoantibody carriers among those tested. Diagnoses of SARDs and other autoimmune conditions increased with higher model probabilities. The model detected a need for autoantibody testing and rheumatology encounters up to five years before the test date and assessment date, respectively. Altogether, these findings illustrate that the clinical manifestations of a diverse array of autoimmune conditions are detectable in electronic health records using machine learning, which may help systematize and accelerate autoimmune testing.",
author = "Forrest, {Iain S.} and Petrazzini, {Ben O.} and {\'A}ine Duffy and Park, {Joshua K.} and O{\textquoteright}Neal, {Anya J.} and Jordan, {Daniel M.} and Ghislain Rocheleau and Nadkarni, {Girish N.} and Cho, {Judy H.} and Blazer, {Ashira D.} and Ron Do",
note = "Funding Information: We thank Liron Marnin at the University of Maryland School of Medicine for providing inspiration for this study. This work was supported in part by the Mount Sinai Data Warehouse (MSDW) resources and staff expertise provided by Scientific Computing and Data at the Icahn School of Medicine at Mount Sinai. ISF is supported by the National Institute of General Medical Sciences of the National Institutes of Health (NIH) (T32-GM007280). RD is supported by the National Institute of General Medical Sciences of NIH (R35-GM124836) and the National Heart, Lung, and Blood Institute of the NIH (R01-HL139865 and R01-HL155915). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Funding Information: We thank Liron Marnin at the University of Maryland School of Medicine for providing inspiration for this study. This work was supported in part by the Mount Sinai Data Warehouse (MSDW) resources and staff expertise provided by Scientific Computing and Data at the Icahn School of Medicine at Mount Sinai. ISF is supported by the National Institute of General Medical Sciences of the National Institutes of Health (NIH) (T32-GM007280). RD is supported by the National Institute of General Medical Sciences of NIH (R35-GM124836) and the National Heart, Lung, and Blood Institute of the NIH (R01-HL139865 and R01-HL155915). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Publisher Copyright: {\textcopyright} 2023, The Author(s).",
year = "2023",
month = dec,
doi = "10.1038/s41467-023-37996-7",
language = "English",
volume = "14",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "Nature Publishing Group",
number = "1",
}