Early Diagnosis of Primary Immunodeficiency Disease Using Clinical Data and Machine Learning.
Common variable immunodeficiency (CVID)
Electronic health record (EHR)
Immunodeficiency
Machine learning
Primary immunodeficiency diseases (PIDD)
Specific antibody deficiency
Journal
The journal of allergy and clinical immunology. In practice
ISSN: 2213-2201
Titre abrégé: J Allergy Clin Immunol Pract
Pays: United States
ID NLM: 101597220
Informations de publication
Date de publication:
11 2022
11 2022
Historique:
received:
16
02
2022
revised:
19
08
2022
accepted:
22
08
2022
pubmed:
16
9
2022
medline:
15
11
2022
entrez:
15
9
2022
Statut:
ppublish
Résumé
Primary immunodeficiency diseases (PIDD) are a group of immune-related disorders that have a current median delay of diagnosis between 6 and 9 years. Early diagnosis and treatment of PIDD has been associated with improved patient outcomes. To develop a machine learning model using elements within the electronic health record data that are related to prior symptomatic treatment to predict PIDD. We conducted a retrospective study of patients with PIDD identified using inclusion criteria of PIDD-related diagnoses, immunodeficiency-specific medications, and low immunoglobulin levels. We constructed a control group of age-, sex-, and race-matched patients with asthma. The primary outcome was the diagnosis of PIDD. We considered comorbidities, laboratory tests, medications, and radiological orders as features, all before diagnosis and indicative of symptom-related treatment. Features were presented sequentially to logistic regression, elastic net, and random forest classifiers, which were trained using a nested cross-validation approach. Our cohort consisted of 6422 patients, of whom 247 (4%) were diagnosed with PIDD. Our logistic regression model with comorbidities demonstrated good discrimination between patients with PIDD and those with asthma (c-statistic: 0.62 [0.58-0.65]). Adding laboratory results, medications, and radiological orders improved discrimination (c-statistic: 0.70 vs 0.62, P < .001), sensitivity, and specificity. Extending to the advanced machine learning models did not improve performance. We developed a prediction model for early diagnosis of PIDD using historical data that are related to symptomatic care, which has potential to fill an important need in reducing the time to diagnose PIDD, leading to better outcomes for immunodeficient patients.
Sections du résumé
BACKGROUND
Primary immunodeficiency diseases (PIDD) are a group of immune-related disorders that have a current median delay of diagnosis between 6 and 9 years. Early diagnosis and treatment of PIDD has been associated with improved patient outcomes.
OBJECTIVE
To develop a machine learning model using elements within the electronic health record data that are related to prior symptomatic treatment to predict PIDD.
METHODS
We conducted a retrospective study of patients with PIDD identified using inclusion criteria of PIDD-related diagnoses, immunodeficiency-specific medications, and low immunoglobulin levels. We constructed a control group of age-, sex-, and race-matched patients with asthma. The primary outcome was the diagnosis of PIDD. We considered comorbidities, laboratory tests, medications, and radiological orders as features, all before diagnosis and indicative of symptom-related treatment. Features were presented sequentially to logistic regression, elastic net, and random forest classifiers, which were trained using a nested cross-validation approach.
RESULTS
Our cohort consisted of 6422 patients, of whom 247 (4%) were diagnosed with PIDD. Our logistic regression model with comorbidities demonstrated good discrimination between patients with PIDD and those with asthma (c-statistic: 0.62 [0.58-0.65]). Adding laboratory results, medications, and radiological orders improved discrimination (c-statistic: 0.70 vs 0.62, P < .001), sensitivity, and specificity. Extending to the advanced machine learning models did not improve performance.
CONCLUSIONS
We developed a prediction model for early diagnosis of PIDD using historical data that are related to symptomatic care, which has potential to fill an important need in reducing the time to diagnose PIDD, leading to better outcomes for immunodeficient patients.
Identifiants
pubmed: 36108921
pii: S2213-2198(22)00925-4
doi: 10.1016/j.jaip.2022.08.041
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
3002-3007.e5Informations de copyright
Copyright © 2022 The Authors. Published by Elsevier Inc. All rights reserved.