Large-scale Deep Learning Analysis to Identify Adult Patients at Risk for Combined and Common Variable Immunodeficiencies

Overview

Journal Commun Med (Lond)

Publisher Nature Portfolio

Specialty General Medicine

Date 2023 Dec 20

PMID 38123736

Authors

Giorgos Papanastasiou

Guang Yang

Dimitris I Fotiadis

Nikolaos Dikaios

Chengjia Wang

Ahsan Huda

Luba Sobolevsky

Jason Raasch

Elena Perez

Gurinder Sidhu

Donna Palumbo

Affiliations

Soon will be listed here.

Abstract

Background: Primary immunodeficiency (PI) is a group of heterogeneous disorders resulting from immune system defects. Over 70% of PI is undiagnosed, leading to increased mortality, co-morbidity and healthcare costs. Among PI disorders, combined immunodeficiencies (CID) are characterized by complex immune defects. Common variable immunodeficiency (CVID) is among the most common types of PI. In light of available treatments, it is critical to identify adult patients at risk for CID and CVID, before the development of serious morbidity and mortality.

Methods: We developed a deep learning-based method (named "TabMLPNet") to analyze clinical history from nationally representative medical claims from electronic health records (Optum® data, covering all US), evaluated in the setting of identifying CID/CVID in adults. Further, we revealed the most important CID/CVID-associated antecedent phenotype combinations. Four large cohorts were generated: a total of 47,660 PI cases and (1:1 matched) controls.

Results: The sensitivity/specificity of TabMLPNet modeling ranges from 0.82-0.88/0.82-0.85 across cohorts. Distinctive combinations of antecedent phenotypes associated with CID/CVID are identified, consisting of respiratory infections/conditions, genetic anomalies, cardiac defects, autoimmune diseases, blood disorders and malignancies, which can possibly be useful to systematize the identification of CID and CVID.

Conclusions: We demonstrated an accurate method in terms of CID and CVID detection evaluated on large-scale medical claims data. Our predictive scheme can potentially lead to the development of new clinical insights and expanded guidelines for identification of adult patients at risk for CID and CVID as well as be used to improve patient outcomes on population level.

References

Zong N, Wen A, Moon S, Fu S, Wang L, Zhao Y . Computational drug repurposing based on electronic health records: a scoping review. NPJ Digit Med. 2022; 5(1):77. PMC: 9198008. DOI: 10.1038/s41746-022-00617-6. View

Duarte R, Labopin M, Bader P, Basak G, Bonini C, Chabannon C . Indications for haematopoietic stem cell transplantation for haematological diseases, solid tumours and immune disorders: current practice in Europe, 2019. Bone Marrow Transplant. 2019; 54(10):1525-1552. DOI: 10.1038/s41409-019-0516-2. View

Tangye S, Al-Herz W, Bousfiha A, Chatila T, Cunningham-Rundles C, Etzioni A . Human Inborn Errors of Immunity: 2019 Update on the Classification from the International Union of Immunological Societies Expert Committee. J Clin Immunol. 2020; 40(1):24-64. PMC: 7082301. DOI: 10.1007/s10875-019-00737-x. View

Amaya-Uribe L, Rojas M, Azizi G, Anaya J, Gershwin M . Primary immunodeficiency and autoimmunity: A comprehensive review. J Autoimmun. 2019; 99:52-72. DOI: 10.1016/j.jaut.2019.01.011. View

Bonilla F, Khan D, Ballas Z, Chinen J, Frank M, Hsu J . Practice parameter for the diagnosis and management of primary immunodeficiency. J Allergy Clin Immunol. 2015; 136(5):1186-205.e1-78. DOI: 10.1016/j.jaci.2015.04.049. View

McCusker C, Upton J, Warrington R . Primary immunodeficiency. Allergy Asthma Clin Immunol. 2018; 14(Suppl 2):61. PMC: 6157160. DOI: 10.1186/s13223-018-0290-5. View

Emmaneel A, Bogaert D, Van Gassen S, Tavernier S, Dullaers M, Haerynck F . A Computational Pipeline for the Diagnosis of CVID Patients. Front Immunol. 2019; 10:2009. PMC: 6730493. DOI: 10.3389/fimmu.2019.02009. View

Wu P, Gifford A, Meng X, Li X, Campbell H, Varley T . Mapping ICD-10 and ICD-10-CM Codes to Phecodes: Workflow Development and Initial Evaluation. JMIR Med Inform. 2019; 7(4):e14325. PMC: 6911227. DOI: 10.2196/14325. View

Bousfiha A, Moundir A, Tangye S, Picard C, Jeddane L, Al-Herz W . The 2022 Update of IUIS Phenotypical Classification for Human Inborn Errors of Immunity. J Clin Immunol. 2022; 42(7):1508-1520. DOI: 10.1007/s10875-022-01352-z. View

10.

Alexander T, Greco R, Snowden J . Hematopoietic Stem Cell Transplantation for Autoimmune Disease. Annu Rev Med. 2020; 72:215-228. DOI: 10.1146/annurev-med-070119-115617. View

11.

Huda A, Castano A, Niyogi A, Schumacher J, Stewart M, Bruno M . A machine learning model for identifying patients at risk for wild-type transthyretin amyloid cardiomyopathy. Nat Commun. 2021; 12(1):2725. PMC: 8113237. DOI: 10.1038/s41467-021-22876-9. View

12.

Kobrynski L . Newborn Screening in the Diagnosis of Primary Immunodeficiency. Clin Rev Allergy Immunol. 2021; 63(1):9-21. DOI: 10.1007/s12016-021-08876-z. View

13.

Raymond L, Leiding J, Forbes-Satter L . Diagnostic Modalities in Primary Immunodeficiency. Clin Rev Allergy Immunol. 2022; 63(1):90-98. DOI: 10.1007/s12016-022-08933-1. View

14.

Duan L, Grunebaum E . Hematological Malignancies Associated With Primary Immunodeficiency Disorders. Clin Immunol. 2018; 194:46-59. DOI: 10.1016/j.clim.2018.06.011. View

15.

Ballow M, Sanchez-Ramon S, Walter J . Secondary Immune Deficiency and Primary Immune Deficiency Crossovers: Hematological Malignancies and Autoimmune Diseases. Front Immunol. 2022; 13:928062. PMC: 9340211. DOI: 10.3389/fimmu.2022.928062. View

16.

Rider N, Cahill G, Motazedi T, Wei L, Kurian A, Noroski L . PI Prob: A risk prediction and clinical guidance system for evaluating patients with recurrent infections. PLoS One. 2021; 16(2):e0237285. PMC: 7886140. DOI: 10.1371/journal.pone.0237285. View

17.

Landi I, Glicksberg B, Lee H, Cherng S, Landi G, Danieletto M . Deep representation learning of electronic health records to unlock patient stratification at scale. NPJ Digit Med. 2020; 3:96. PMC: 7367859. DOI: 10.1038/s41746-020-0301-z. View

18.

Anderson J, Cowan J, Condino-Neto A, Levy D, Prusty S . Health-related quality of life in primary immunodeficiencies: Impact of delayed diagnosis and treatment burden. Clin Immunol. 2022; 236:108931. DOI: 10.1016/j.clim.2022.108931. View

19.

Chapel H, Prevot J, Gaspar H, Espanol T, Bonilla F, Solis L . Primary immune deficiencies - principles of care. Front Immunol. 2015; 5:627. PMC: 4266088. DOI: 10.3389/fimmu.2014.00627. View

20.

Abyazi M, Bell K, Gyimesi G, Baker T, Byun M, Ko H . Convergence of cytokine dysregulation and antibody deficiency in common variable immunodeficiency with inflammatory complications. J Allergy Clin Immunol. 2021; 149(1):315-326.e9. PMC: 8678401. DOI: 10.1016/j.jaci.2021.06.008. View