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-m...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-04-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-023-37996-7 |
_version_ | 1797827461781651456 |
---|---|
author | Iain S. Forrest Ben O. Petrazzini Áine Duffy Joshua K. Park Anya J. O’Neal Daniel M. Jordan Ghislain Rocheleau Girish N. Nadkarni Judy H. Cho Ashira D. Blazer Ron Do |
author_facet | Iain S. Forrest Ben O. Petrazzini Áine Duffy Joshua K. Park Anya J. O’Neal Daniel M. Jordan Ghislain Rocheleau Girish N. Nadkarni Judy H. Cho Ashira D. Blazer Ron Do |
author_sort | Iain S. Forrest |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-09T12:48:41Z |
format | Article |
id | doaj.art-b64a1436928b48f396ea73f3b6b5a0c3 |
institution | Directory Open Access Journal |
issn | 2041-1723 |
language | English |
last_indexed | 2024-04-09T12:48:41Z |
publishDate | 2023-04-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Nature Communications |
spelling | doaj.art-b64a1436928b48f396ea73f3b6b5a0c32023-05-14T11:21:13ZengNature PortfolioNature Communications2041-17232023-04-0114111210.1038/s41467-023-37996-7A machine learning model identifies patients in need of autoimmune disease testing using electronic health recordsIain S. Forrest0Ben O. Petrazzini1Áine Duffy2Joshua K. Park3Anya J. O’Neal4Daniel M. Jordan5Ghislain Rocheleau6Girish N. Nadkarni7Judy H. Cho8Ashira D. Blazer9Ron Do10The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiDepartment of Microbiology and Immunology, University of Maryland School of MedicineThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiDivision of Rheumatology, Hospital for Special SurgeryThe Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount SinaiAbstract 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.https://doi.org/10.1038/s41467-023-37996-7 |
spellingShingle | Iain S. Forrest Ben O. Petrazzini Áine Duffy Joshua K. Park Anya J. O’Neal Daniel M. Jordan Ghislain Rocheleau Girish N. Nadkarni Judy H. Cho Ashira D. Blazer Ron Do A machine learning model identifies patients in need of autoimmune disease testing using electronic health records Nature Communications |
title | A machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
title_full | A machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
title_fullStr | A machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
title_full_unstemmed | A machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
title_short | A machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
title_sort | machine learning model identifies patients in need of autoimmune disease testing using electronic health records |
url | https://doi.org/10.1038/s41467-023-37996-7 |
work_keys_str_mv | AT iainsforrest amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT benopetrazzini amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT aineduffy amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT joshuakpark amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT anyajoneal amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT danielmjordan amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT ghislainrocheleau amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT girishnnadkarni amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT judyhcho amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT ashiradblazer amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT rondo amachinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT iainsforrest machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT benopetrazzini machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT aineduffy machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT joshuakpark machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT anyajoneal machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT danielmjordan machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT ghislainrocheleau machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT girishnnadkarni machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT judyhcho machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT ashiradblazer machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords AT rondo machinelearningmodelidentifiespatientsinneedofautoimmunediseasetestingusingelectronichealthrecords |