A predictive model for identification of pediatric individuals with common variable immunodeficiency through electronic medical records

[Display omitted] Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagn...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of allergy and clinical immunology Jg. 156; H. 1; S. 186 - 194
Hauptverfasser:	Alsaati, Nouf, Penney, Chris, Helbig, Ingo, Sullivan, Kathleen E.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Elsevier Inc 01.07.2025
Schlagworte:	Adolescent antibody deficiency artificial intelligence Child Child, Preschool Common Variable Immunodeficiency - diagnosis Electronic Health Records Female Humans inborn error of immunity Infant Machine Learning Male predictive algorithm Primary immunodeficiency inborn error of immunity antibody deficiency FN FP SVM machine learning IEI artificial intelligence EHR Primary immunodeficiency CVID predictive algorithm XGBoost CHOP TP ML
ISSN:	0091-6749, 1097-6825, 1097-6825
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	[Display omitted] Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis. Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population. Our selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach. Key features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions. In spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification.
AbstractList	Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis. Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population. Our selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach. Key features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions. In spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification. Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis.INTRODUCTIONCommon variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis.Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population.OBJECTIVEOur aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population.Our selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach.METHODSOur selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach.Key features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions.RESULTSKey features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions.In spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification.CONCLUSIONIn spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification. [Display omitted] Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis. Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population. Our selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach. Key features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions. In spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification.
Author	Penney, Chris Alsaati, Nouf Helbig, Ingo Sullivan, Kathleen E.
Author_xml	– sequence: 1 givenname: Nouf surname: Alsaati fullname: Alsaati, Nouf organization: Division of Allergy and Immunology, Children's Hospital of Philadelphia, Philadelphia, Pa – sequence: 2 givenname: Chris surname: Penney fullname: Penney, Chris organization: Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, Pa – sequence: 3 givenname: Ingo surname: Helbig fullname: Helbig, Ingo organization: Division of Neurology, Epilepsy NeuroGenetics Initiative (ENGIN), Children's Hospital of Philadelphia, Philadelphia, Pa – sequence: 4 givenname: Kathleen E. orcidid: 0000-0003-4018-1646 surname: Sullivan fullname: Sullivan, Kathleen E. email: sullivank@chop.edu organization: Division of Allergy and Immunology, Children's Hospital of Philadelphia, Philadelphia, Pa
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/40058414$$D View this record in MEDLINE/PubMed
BookMark	eNqFkc1u1DAUhS1URKeFF2CBvGQz4dr5GQexqSpakCqxgbXl2DfMHZJ4sJ1B8wS8Nk6n3XRRVpal8x1b37lgZ5OfkLG3AgoBovmwK3bGUiFB1gXIAkr5gq0EtJt1o2R9xlYArVg3m6o9Zxcx7iDfS9W-YucVQK0qUa3Y3yu-D-jIJjogH73Dgfc-cHI4JerJmkR-4r7n-5wyKZDlNDk6kJvNEPkfSltu_Tjm0MEEMt2AnMZxnnJVxgkne-RpG_z8c8txQJuCn3LJuDxqBh7Q-uDia_ayz3345uG8ZD9uPn-__rK--3b79frqbm0raNNaCuEE9D00pTWoQJq6VbZRDjqoFIJxTnTgpMPKgepapWppQUiswDqQsrxk70-9--B_zxiTHilaHAYzoZ-jLsWmbhSUQuTou4fo3OXf6n2g0YSjfpSXA-oUsMHHGLDXltK9rxQMDVqAXnbSO73spJedNEidd8qofII-tj8LfTpBmAUdCIOO936zyWwxaefpefzjE9wONC0j_MLj_-B_jH_CKw
CitedBy_id	crossref_primary_10_2500_aap_2025_46_250049
Cites_doi	10.1016/S2589-7500(23)00004-3 10.1186/s13023-020-01424-6 10.1155/2020/8416124 10.1016/j.jpeds.2008.12.020 10.1016/j.jaci.2004.01.761 10.3389/fimmu.2022.900055 10.1007/s10875-021-01179-0 10.1007/s00431-021-04287-6 10.3389/fimmu.2017.01190 10.18176/jiaci.0388 10.1186/ar4032 10.1016/j.jaci.2013.12.1077 10.3389/fimmu.2020.00982 10.1016/j.clim.2017.03.011 10.1126/scitranslmed.ade4510 10.1016/j.jaci.2021.04.015 10.1186/s13023-018-0941-0 10.1007/s10875-023-01590-9 10.2174/1389201019666180808163311 10.1111/cei.12369 10.1016/j.jaci.2018.06.013 10.3390/jcm12103401 10.1007/s10875-023-01598-1 10.1177/0004563214545791 10.1093/cid/civ486 10.1016/j.jaci.2022.10.005 10.1038/s41598-024-55424-8 10.1016/j.jaip.2022.08.041 10.3389/fimmu.2018.00694
ContentType	Journal Article
Copyright	2025 American Academy of Allergy, Asthma & Immunology Copyright © 2025 American Academy of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.
Copyright_xml	– notice: 2025 American Academy of Allergy, Asthma & Immunology – notice: Copyright © 2025 American Academy of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1016/j.jaci.2025.02.032
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine
EISSN	1097-6825
EndPage	194
ExternalDocumentID	40058414 10_1016_j_jaci_2025_02_032 S0091674925002635
Genre	Journal Article
GroupedDBID	--- --K --M -~X .1- .55 .FO .GJ .XZ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 354 3O- 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8F7 8FE 8FH 8P~ 9JM AAAJQ AABNK AAEDT AAEDW AAFWJ AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARKO AATTM AAXKI AAXUO AAYWO ABBQC ABFNM ABJNI ABLJU ABMAC ABMZM ABOCM ABWVN ABXDB ACDAQ ACGFO ACGFS ACIEU ACLOT ACPRK ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADFRT ADMUD ADNMO ADVLN ADXHL AEBSH AEIPS AEKER AENEX AEUPX AFFNX AFJKZ AFPUW AFRAH AFRHN AFTJW AFXIZ AGEKW AGHFR AGQPQ AGUBO AGYEJ AHHHB AHMBA AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV BPHCQ BVXVI C45 CAG CJTIS COF CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HDU HMK HMO HVGLF HZ~ IHE J1W J5H K-O KOM L7B LK8 LUGTX M27 M41 MO0 N4W N9A O-L O9- O9~ OAUVE OBH ODZKP OHH OHT OK0 OK1 OVD OZT P-8 P-9 P2P PC. PQQKQ PROAC Q38 R2- ROL RPZ SAE SCC SDF SDG SDP SEL SES SEW SJN SPCBC SSH SSI SSZ T5K TEORI TWZ UGJ UNMZH UV1 WH7 WOW WUQ X7M XFW YOC YQI YQJ Z5R ZGI ZXP ZY1 ~02 ~G- ~HD ~KM AGCQF AGRNS RIG 9DU AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
ID	FETCH-LOGICAL-c409t-211d10ff063cae802a598c68d0b048e0add1b0d2de4d08b98852c012e40cd0223
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001533794300018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0091-6749 1097-6825
IngestDate	Wed Oct 01 14:44:14 EDT 2025 Mon Jul 07 01:53:47 EDT 2025 Tue Nov 18 21:58:03 EST 2025 Sat Nov 29 07:49:58 EST 2025 Tue Jul 29 20:18:24 EDT 2025 Tue Oct 14 19:34:49 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	inborn error of immunity antibody deficiency FN FP SVM machine learning IEI artificial intelligence EHR Primary immunodeficiency CVID predictive algorithm XGBoost CHOP TP ML
Language	English
License	Copyright © 2025 American Academy of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c409t-211d10ff063cae802a598c68d0b048e0add1b0d2de4d08b98852c012e40cd0223
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0003-4018-1646
PMID	40058414
PQID	3175680311
PQPubID	23479
PageCount	9
ParticipantIDs	proquest_miscellaneous_3175680311 pubmed_primary_40058414 crossref_citationtrail_10_1016_j_jaci_2025_02_032 crossref_primary_10_1016_j_jaci_2025_02_032 elsevier_sciencedirect_doi_10_1016_j_jaci_2025_02_032 elsevier_clinicalkey_doi_10_1016_j_jaci_2025_02_032
PublicationCentury	2000
PublicationDate	2025-07-01
PublicationDateYYYYMMDD	2025-07-01
PublicationDate_xml	– month: 07 year: 2025 text: 2025-07-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Journal of allergy and clinical immunology
PublicationTitleAlternate	J Allergy Clin Immunol
PublicationYear	2025
Publisher	Elsevier Inc
Publisher_xml	– name: Elsevier Inc
References	Schaefer, Lehne, Schepers, Prasser, Thun (bib19) 2020; 15 Moynihan, Monaco, Ting, Narasimhalu, Hsieh, Kam (bib20) 2024; 14 Rider, Coffey, Kurian, Quinn, Orange, Modell (bib10) 2023; 151 Selenius, Martelius, Pikkarainen, Siitonen, Mattila, Pietikainen (bib1) 2017; 8 Johnson, Stephens, Mester, Knyazev, Kohn, Freund (bib12) 2024; 16 Slade, Bosco, Binh Giang, Kruse, Stirling, Cameron (bib4) 2018; 9 Thalhammer, Kindle, Nieters, Rusch, Seppanen, Fischer (bib31) 2021; 148 Odnoletkova, Kindle, Quinti, Grimbacher, Knerr, Gathmann (bib5) 2018; 13 Jolles, Borrell, Zouwail, Heaps, Sharp, Moody (bib16) 2014; 177 Hajjar, Al-Kaabi, Kutac, Dunn, Shearer, Orange (bib28) 2018; 142 Dicken J. Rare diseases, although limited, available evidence suggests medical and other costs can be substantial. US Government Accountability Office report to congressional committees. General Accounting Office, GAO-22-104235. Cunningham-Rundles, Sidi, Estrella, Doucette (bib9) 2004; 113 (bib26) 2021 Dabrowska, Grzesk, Urbanczyk, Mazalon, Grzesk, Styczynski (bib32) 2023; 12 Salzer, Warnatz, Peter (bib27) 2012; 14 Szczawinska-Poplonyk, Schwartzmann, Bukowska-Olech, Biernat, Gattner, Korobacz (bib29) 2022; 181 Graziano, Pecoraro, Mormile, Quaremba, Genovese, Buccelli (bib8) 2017; 180 Urschel, Kayikci, Wintergerst, Notheis, Jansson, Belohradsky (bib6) 2009; 154 Gathmann, Mahlaoui, Ceredih, Gerard, Oksenhendler, Warnatz (bib7) 2014; 134 Byington, Ampofo, Stockmann, Adler, Herbener, Miller (bib22) 2015; 61 Mayampurath, Ajith, Anderson-Smits, Chang, Brouwer, Johnson (bib11) 2022; 10 Ilkjaer, Johansen, Martin-Iguacel, Westh, Katzenstein, Hansen (bib13) 2023; 43 Pecoraro, Jolles, Crescenzi, Varricchi, Marone, Savoia (bib14) 2018; 19 bib25 London (bib34) 2022; 3 Eldeniz, Gul, Yorulmaz, Guner, Keles, Reisli (bib30) 2022; 13 Weifenbach, Schneckenburger, Lotters (bib2) 2020; 2020 Zietkiewicz, Wiesik-Szewczyk, Matyja-Bednarczyk, Napiorkowska-Baran, Zdrojewski, Jahnz-Rozyk (bib3) 2020; 11 Holding, Khan, Sewell, Jolles, Dore (bib15) 2015; 52 McKee, Kaufman, Gonzalez, Fitzgerald, Massey, Fung (bib18) 2023; 5 Yazdani, Habibi, Sharifi, Azizi, Abolhassani, Olbrich (bib24) 2020; 30 Dahl, Petersen, Ilkjaer, Westh, Katzenstein, Hansen (bib33) 2023; 43 Israeli, Golden, Atalig, Mekki, Rais, Storey (bib17) 2022; 42 Alter, Vidwan, Sobande, Omoloja, Bennett (bib21) 2011; 41 Gathmann (10.1016/j.jaci.2025.02.032_bib7) 2014; 134 Holding (10.1016/j.jaci.2025.02.032_bib15) 2015; 52 Hajjar (10.1016/j.jaci.2025.02.032_bib28) 2018; 142 Moynihan (10.1016/j.jaci.2025.02.032_bib20) 2024; 14 Eldeniz (10.1016/j.jaci.2025.02.032_bib30) 2022; 13 Yazdani (10.1016/j.jaci.2025.02.032_bib24) 2020; 30 Salzer (10.1016/j.jaci.2025.02.032_bib27) 2012; 14 McKee (10.1016/j.jaci.2025.02.032_bib18) 2023; 5 Schaefer (10.1016/j.jaci.2025.02.032_bib19) 2020; 15 Dabrowska (10.1016/j.jaci.2025.02.032_bib32) 2023; 12 Odnoletkova (10.1016/j.jaci.2025.02.032_bib5) 2018; 13 Cunningham-Rundles (10.1016/j.jaci.2025.02.032_bib9) 2004; 113 Pecoraro (10.1016/j.jaci.2025.02.032_bib14) 2018; 19 Byington (10.1016/j.jaci.2025.02.032_bib22) 2015; 61 Dahl (10.1016/j.jaci.2025.02.032_bib33) 2023; 43 Jolles (10.1016/j.jaci.2025.02.032_bib16) 2014; 177 Zietkiewicz (10.1016/j.jaci.2025.02.032_bib3) 2020; 11 London (10.1016/j.jaci.2025.02.032_bib34) 2022; 3 Thalhammer (10.1016/j.jaci.2025.02.032_bib31) 2021; 148 Rider (10.1016/j.jaci.2025.02.032_bib10) 2023; 151 Szczawinska-Poplonyk (10.1016/j.jaci.2025.02.032_bib29) 2022; 181 Weifenbach (10.1016/j.jaci.2025.02.032_bib2) 2020; 2020 Israeli (10.1016/j.jaci.2025.02.032_bib17) 2022; 42 Alter (10.1016/j.jaci.2025.02.032_bib21) 2011; 41 Selenius (10.1016/j.jaci.2025.02.032_bib1) 2017; 8 Graziano (10.1016/j.jaci.2025.02.032_bib8) 2017; 180 10.1016/j.jaci.2025.02.032_bib23 Urschel (10.1016/j.jaci.2025.02.032_bib6) 2009; 154 Mayampurath (10.1016/j.jaci.2025.02.032_bib11) 2022; 10 Johnson (10.1016/j.jaci.2025.02.032_bib12) 2024; 16 Ilkjaer (10.1016/j.jaci.2025.02.032_bib13) 2023; 43 (10.1016/j.jaci.2025.02.032_bib26) 2021 Slade (10.1016/j.jaci.2025.02.032_bib4) 2018; 9
References_xml	– volume: 154 start-page: 888 year: 2009 end-page: 894 ident: bib6 article-title: Common variable immunodeficiency disorders in children: delayed diagnosis despite typical clinical presentation publication-title: J. Pediatr – volume: 9 start-page: 694 year: 2018 ident: bib4 article-title: Delayed diagnosis and complications of predominantly antibody deficiencies in a cohort of Australian adults publication-title: Front Immunol – volume: 42 start-page: 394 year: 2022 end-page: 403 ident: bib17 article-title: A novel point-of-care rapid diagnostic test for screening individuals for antibody deficiencies publication-title: J Clin Immunol – volume: 180 start-page: 1 year: 2017 end-page: 4 ident: bib8 article-title: Delay in diagnosis affects the clinical outcome in a cohort of CVID patients with marked reduction of IgA serum levels publication-title: Clin Immunol – volume: 10 start-page: 3002 year: 2022 end-page: 3007.e3005 ident: bib11 article-title: Early diagnosis of primary immunodeficiency disease using clinical data and machine learning publication-title: J Allergy Clin Immunol Pract – volume: 11 start-page: 982 year: 2020 ident: bib3 article-title: Shorter diagnostic delay in Polish adult patients with common variable immunodeficiency and symptom onset after 1999 publication-title: Front Immunol – volume: 61 start-page: 1217 year: 2015 end-page: 1224 ident: bib22 article-title: Community surveillance of respiratory viruses among families in the Utah Better Identification of Germs-Longitudinal Viral Epidemiology (BIG-LoVE) study publication-title: Clin Infect Dis – volume: 52 start-page: 319 year: 2015 end-page: 326 ident: bib15 article-title: Using calculated globulin fraction to reduce diagnostic delay in primary and secondary hypogammaglobulinaemias: results of a demonstration project publication-title: Ann Clin Biochem – volume: 13 start-page: 201 year: 2018 ident: bib5 article-title: The burden of common variable immunodeficiency disorders: a retrospective analysis of the European Society for Immunodeficiency (ESID) registry data publication-title: Orphanet J Rare Dis – volume: 43 start-page: 2104 year: 2023 end-page: 2114 ident: bib33 article-title: Missed opportunities to diagnose common variable immunodeficiency: a population-based case-control study identifying indicator diseases for common variable immunodeficiency publication-title: J Clin Immunol – volume: 151 start-page: 272 year: 2023 end-page: 279 ident: bib10 article-title: A validated artificial intelligence-based pipeline for population-wide primary immunodeficiency screening publication-title: J Allergy Clin Immunol – volume: 16 start-page: eade4510 year: 2024 ident: bib12 article-title: Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease publication-title: Sci Transl Med – volume: 113 start-page: 747 year: 2004 end-page: 755 ident: bib9 article-title: Identifying undiagnosed primary immunodeficiency diseases in minority subjects by using computer sorting of diagnosis codes publication-title: J Allergy Clin Immunol – volume: 41 start-page: 256 year: 2011 end-page: 283 ident: bib21 article-title: Common childhood bacterial infections publication-title: Curr Probl Pediatr Adolesc Health Care – volume: 19 start-page: 728 year: 2018 end-page: 733 ident: bib14 article-title: Validation of calculated globulin (CG) as a screening test for antibody deficiency in an Italian university hospital publication-title: Curr Pharm Biotechnol – volume: 5 start-page: e217 year: 2023 end-page: e226 ident: bib18 article-title: Leveraging electronic medical record-embedded standardised electroencephalogram reporting to develop neonatal seizure prediction models: a retrospective cohort study publication-title: Lancet Digit Health – ident: bib25 article-title: CVID criteria 2024 – year: 2021 ident: bib26 article-title: A language and environment for statistical computing – volume: 8 start-page: 1190 year: 2017 ident: bib1 article-title: Unexpectedly high prevalence of common variable immunodeficiency in Finland publication-title: Front Immunol – volume: 134 start-page: 116 year: 2014 end-page: 126 ident: bib7 article-title: Clinical picture and treatment of 2212 patients with common variable immunodeficiency publication-title: J Allergy Clin Immunol – volume: 15 start-page: 145 year: 2020 ident: bib19 article-title: The use of machine learning in rare diseases: a scoping review publication-title: Orphanet J Rare Dis – volume: 3 year: 2022 ident: bib34 article-title: Artificial intelligence in medicine: overcoming or recapitulating structural challenges to improving patient care? publication-title: Cell Rep Med – volume: 30 start-page: 14 year: 2020 end-page: 34 ident: bib24 article-title: Common variable immunodeficiency: epidemiology, pathogenesis, clinical manifestations, diagnosis, classification, and management publication-title: J Investig Allergol Clin Immunol – reference: Dicken J. Rare diseases, although limited, available evidence suggests medical and other costs can be substantial. US Government Accountability Office report to congressional committees. General Accounting Office, GAO-22-104235. – volume: 181 start-page: 1371 year: 2022 end-page: 1383 ident: bib29 article-title: The pediatric common variable immunodeficiency - from genetics to therapy: a review publication-title: Eur J Pediatr – volume: 14 start-page: 5056 year: 2024 ident: bib20 article-title: Cluster analysis and visualisation of electronic health records data to identify undiagnosed patients with rare genetic diseases publication-title: Sci Rep – volume: 177 start-page: 671 year: 2014 end-page: 678 ident: bib16 article-title: Calculated globulin (CG) as a screening test for antibody deficiency publication-title: Clin Exp Immunol – volume: 2020 year: 2020 ident: bib2 article-title: Global distribution of common variable immunodeficiency (CVID) in the light of the UNDP human development index (HDI): a preliminary perspective of a rare disease publication-title: J Immunol Res – volume: 148 start-page: 1332 year: 2021 end-page: 1341.e1335 ident: bib31 article-title: Initial presenting manifestations in 16,486 patients with inborn errors of immunity include infections and noninfectious manifestations publication-title: J Allergy Clin Immunol – volume: 12 start-page: 3401 year: 2023 ident: bib32 article-title: Extended list of warning signs in qualification to diagnosis and treatment of inborn errors of immunity in children and young adults publication-title: J Clin Med – volume: 13 year: 2022 ident: bib30 article-title: Evaluation of the 10 warning signs in primary and secondary immunodeficient patients publication-title: Front Immunol – volume: 43 start-page: 2181 year: 2023 end-page: 2191 ident: bib13 article-title: Evaluating drug prescription patterns in undiagnosed common variable immunodeficiency patients publication-title: J Clin Immunol – volume: 14 start-page: 223 year: 2012 ident: bib27 article-title: Common variable immunodeficiency: an update publication-title: Arthritis Res Ther – volume: 142 start-page: 1358 year: 2018 end-page: 1360 ident: bib28 article-title: Questioning the accuracy of currently available pneumococcal antibody testing publication-title: J Allergy Clin Immunol – volume: 5 start-page: e217 year: 2023 ident: 10.1016/j.jaci.2025.02.032_bib18 article-title: Leveraging electronic medical record-embedded standardised electroencephalogram reporting to develop neonatal seizure prediction models: a retrospective cohort study publication-title: Lancet Digit Health doi: 10.1016/S2589-7500(23)00004-3 – volume: 15 start-page: 145 year: 2020 ident: 10.1016/j.jaci.2025.02.032_bib19 article-title: The use of machine learning in rare diseases: a scoping review publication-title: Orphanet J Rare Dis doi: 10.1186/s13023-020-01424-6 – volume: 2020 year: 2020 ident: 10.1016/j.jaci.2025.02.032_bib2 article-title: Global distribution of common variable immunodeficiency (CVID) in the light of the UNDP human development index (HDI): a preliminary perspective of a rare disease publication-title: J Immunol Res doi: 10.1155/2020/8416124 – volume: 154 start-page: 888 year: 2009 ident: 10.1016/j.jaci.2025.02.032_bib6 article-title: Common variable immunodeficiency disorders in children: delayed diagnosis despite typical clinical presentation publication-title: J. Pediatr doi: 10.1016/j.jpeds.2008.12.020 – volume: 113 start-page: 747 year: 2004 ident: 10.1016/j.jaci.2025.02.032_bib9 article-title: Identifying undiagnosed primary immunodeficiency diseases in minority subjects by using computer sorting of diagnosis codes publication-title: J Allergy Clin Immunol doi: 10.1016/j.jaci.2004.01.761 – volume: 13 year: 2022 ident: 10.1016/j.jaci.2025.02.032_bib30 article-title: Evaluation of the 10 warning signs in primary and secondary immunodeficient patients publication-title: Front Immunol doi: 10.3389/fimmu.2022.900055 – volume: 42 start-page: 394 year: 2022 ident: 10.1016/j.jaci.2025.02.032_bib17 article-title: A novel point-of-care rapid diagnostic test for screening individuals for antibody deficiencies publication-title: J Clin Immunol doi: 10.1007/s10875-021-01179-0 – volume: 181 start-page: 1371 year: 2022 ident: 10.1016/j.jaci.2025.02.032_bib29 article-title: The pediatric common variable immunodeficiency - from genetics to therapy: a review publication-title: Eur J Pediatr doi: 10.1007/s00431-021-04287-6 – year: 2021 ident: 10.1016/j.jaci.2025.02.032_bib26 – volume: 3 year: 2022 ident: 10.1016/j.jaci.2025.02.032_bib34 article-title: Artificial intelligence in medicine: overcoming or recapitulating structural challenges to improving patient care? publication-title: Cell Rep Med – volume: 8 start-page: 1190 year: 2017 ident: 10.1016/j.jaci.2025.02.032_bib1 article-title: Unexpectedly high prevalence of common variable immunodeficiency in Finland publication-title: Front Immunol doi: 10.3389/fimmu.2017.01190 – volume: 30 start-page: 14 year: 2020 ident: 10.1016/j.jaci.2025.02.032_bib24 article-title: Common variable immunodeficiency: epidemiology, pathogenesis, clinical manifestations, diagnosis, classification, and management publication-title: J Investig Allergol Clin Immunol doi: 10.18176/jiaci.0388 – volume: 14 start-page: 223 year: 2012 ident: 10.1016/j.jaci.2025.02.032_bib27 article-title: Common variable immunodeficiency: an update publication-title: Arthritis Res Ther doi: 10.1186/ar4032 – volume: 134 start-page: 116 year: 2014 ident: 10.1016/j.jaci.2025.02.032_bib7 article-title: Clinical picture and treatment of 2212 patients with common variable immunodeficiency publication-title: J Allergy Clin Immunol doi: 10.1016/j.jaci.2013.12.1077 – volume: 11 start-page: 982 year: 2020 ident: 10.1016/j.jaci.2025.02.032_bib3 article-title: Shorter diagnostic delay in Polish adult patients with common variable immunodeficiency and symptom onset after 1999 publication-title: Front Immunol doi: 10.3389/fimmu.2020.00982 – volume: 180 start-page: 1 year: 2017 ident: 10.1016/j.jaci.2025.02.032_bib8 article-title: Delay in diagnosis affects the clinical outcome in a cohort of CVID patients with marked reduction of IgA serum levels publication-title: Clin Immunol doi: 10.1016/j.clim.2017.03.011 – volume: 16 start-page: eade4510 year: 2024 ident: 10.1016/j.jaci.2025.02.032_bib12 article-title: Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease publication-title: Sci Transl Med doi: 10.1126/scitranslmed.ade4510 – volume: 148 start-page: 1332 year: 2021 ident: 10.1016/j.jaci.2025.02.032_bib31 article-title: Initial presenting manifestations in 16,486 patients with inborn errors of immunity include infections and noninfectious manifestations publication-title: J Allergy Clin Immunol doi: 10.1016/j.jaci.2021.04.015 – volume: 13 start-page: 201 year: 2018 ident: 10.1016/j.jaci.2025.02.032_bib5 article-title: The burden of common variable immunodeficiency disorders: a retrospective analysis of the European Society for Immunodeficiency (ESID) registry data publication-title: Orphanet J Rare Dis doi: 10.1186/s13023-018-0941-0 – volume: 43 start-page: 2104 year: 2023 ident: 10.1016/j.jaci.2025.02.032_bib33 article-title: Missed opportunities to diagnose common variable immunodeficiency: a population-based case-control study identifying indicator diseases for common variable immunodeficiency publication-title: J Clin Immunol doi: 10.1007/s10875-023-01590-9 – ident: 10.1016/j.jaci.2025.02.032_bib23 – volume: 19 start-page: 728 year: 2018 ident: 10.1016/j.jaci.2025.02.032_bib14 article-title: Validation of calculated globulin (CG) as a screening test for antibody deficiency in an Italian university hospital publication-title: Curr Pharm Biotechnol doi: 10.2174/1389201019666180808163311 – volume: 177 start-page: 671 year: 2014 ident: 10.1016/j.jaci.2025.02.032_bib16 article-title: Calculated globulin (CG) as a screening test for antibody deficiency publication-title: Clin Exp Immunol doi: 10.1111/cei.12369 – volume: 142 start-page: 1358 year: 2018 ident: 10.1016/j.jaci.2025.02.032_bib28 article-title: Questioning the accuracy of currently available pneumococcal antibody testing publication-title: J Allergy Clin Immunol doi: 10.1016/j.jaci.2018.06.013 – volume: 12 start-page: 3401 year: 2023 ident: 10.1016/j.jaci.2025.02.032_bib32 article-title: Extended list of warning signs in qualification to diagnosis and treatment of inborn errors of immunity in children and young adults publication-title: J Clin Med doi: 10.3390/jcm12103401 – volume: 43 start-page: 2181 year: 2023 ident: 10.1016/j.jaci.2025.02.032_bib13 article-title: Evaluating drug prescription patterns in undiagnosed common variable immunodeficiency patients publication-title: J Clin Immunol doi: 10.1007/s10875-023-01598-1 – volume: 52 start-page: 319 year: 2015 ident: 10.1016/j.jaci.2025.02.032_bib15 article-title: Using calculated globulin fraction to reduce diagnostic delay in primary and secondary hypogammaglobulinaemias: results of a demonstration project publication-title: Ann Clin Biochem doi: 10.1177/0004563214545791 – volume: 41 start-page: 256 year: 2011 ident: 10.1016/j.jaci.2025.02.032_bib21 article-title: Common childhood bacterial infections publication-title: Curr Probl Pediatr Adolesc Health Care – volume: 61 start-page: 1217 year: 2015 ident: 10.1016/j.jaci.2025.02.032_bib22 article-title: Community surveillance of respiratory viruses among families in the Utah Better Identification of Germs-Longitudinal Viral Epidemiology (BIG-LoVE) study publication-title: Clin Infect Dis doi: 10.1093/cid/civ486 – volume: 151 start-page: 272 year: 2023 ident: 10.1016/j.jaci.2025.02.032_bib10 article-title: A validated artificial intelligence-based pipeline for population-wide primary immunodeficiency screening publication-title: J Allergy Clin Immunol doi: 10.1016/j.jaci.2022.10.005 – volume: 14 start-page: 5056 year: 2024 ident: 10.1016/j.jaci.2025.02.032_bib20 article-title: Cluster analysis and visualisation of electronic health records data to identify undiagnosed patients with rare genetic diseases publication-title: Sci Rep doi: 10.1038/s41598-024-55424-8 – volume: 10 start-page: 3002 year: 2022 ident: 10.1016/j.jaci.2025.02.032_bib11 article-title: Early diagnosis of primary immunodeficiency disease using clinical data and machine learning publication-title: J Allergy Clin Immunol Pract doi: 10.1016/j.jaip.2022.08.041 – volume: 9 start-page: 694 year: 2018 ident: 10.1016/j.jaci.2025.02.032_bib4 article-title: Delayed diagnosis and complications of predominantly antibody deficiencies in a cohort of Australian adults publication-title: Front Immunol doi: 10.3389/fimmu.2018.00694
SSID	ssj0009389
Score	2.482733
Snippet	[Display omitted] Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population,... Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	186
SubjectTerms	Adolescent antibody deficiency artificial intelligence Child Child, Preschool Common Variable Immunodeficiency - diagnosis Electronic Health Records Female Humans inborn error of immunity Infant Machine Learning Male predictive algorithm Primary immunodeficiency
Title	A predictive model for identification of pediatric individuals with common variable immunodeficiency through electronic medical records
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0091674925002635 https://dx.doi.org/10.1016/j.jaci.2025.02.032 https://www.ncbi.nlm.nih.gov/pubmed/40058414 https://www.proquest.com/docview/3175680311
Volume	156
WOSCitedRecordID	wos001533794300018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier customDbUrl: eissn: 1097-6825 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009389 issn: 0091-6749 databaseCode: AIEXJ dateStart: 20200301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6lLap6QTxLeFSLxC1ytevY8e7RQkWAIOJQUG4r2-tUjlI7ipOo_4D_xK9j9uk0kAIHLlZkZ9eW5_PM7Ox8Mwi9ASMiFVqCUFIeRHlGAyZLGnBQlnkMNnakQwPfPiXjMZtM-Jde74fjwmzmSV2zmxu--K-ihnMgbEWd_Qdx-0nhBPwGocMRxA7HvxJ8qnj_stJ6zDS60amElbR5Qd5HXLguHYPKs7Jal4uunnewgYW0plZVikUCU6lyE5qr6dr7bHXRubZbPibs0-7xelXrlqUt-uRZmWb67fh-Om-zzGQajJv1tFPgLjtNF0XoArnzvLoy6u6q-d0-l0sascQLG-YIY58SC1bKqGbCk2DEDE3a625TlfwWSI0mpqbC9i8WwgQrZuezrKjO1Y10yVYTY91Cx-JawyNSbRcjQ3PdqcvtLh2gozCJOWjUo_TDxeRjV_IZfEFL0zIZhbu3PEHHbpJ9XtG-VY_2fi4foPtWgDg1cHuIemX9CB1_tokZj9H3FHeowxp1GFCHb6MON1PsUYe3UIcV6rBBHXaow7uowxZ1uEMdtqjDFnVP0Nd3F5dv3we2x0dQRISvgpBSScl0Cp5ykZWMhFnMWTFikuRgW0oC5pfmRIayjCRhOWcsDgtwqsqIFBL8z-FTdFg3dfkMYRgfs6QcDmWURXnEGaysCxZnWSKTHCxXH1H3jkVhC-CrPixz4TIdZ0KJSCgRCRIKEFEfDfyYhSn_cue_h050wn1CYIoFYO_OUbEfZd1e487-cdxrhw4BNkFt9GV12axbodYEIwbmmvbRqYGNf3qHuOd7r7xAJ90H-BIdrpbr8hW6V2xWVbs8QwfJhJ1ZrP8EaRPjoA
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+predictive+model+for+identification+of+pediatric+individuals+with+common+variable+immunodeficiency+through+electronic+medical+records&rft.jtitle=Journal+of+allergy+and+clinical+immunology&rft.au=Alsaati%2C+Nouf&rft.au=Penney%2C+Chris&rft.au=Helbig%2C+Ingo&rft.au=Sullivan%2C+Kathleen+E&rft.date=2025-07-01&rft.eissn=1097-6825&rft.volume=156&rft.issue=1&rft.spage=186&rft_id=info:doi/10.1016%2Fj.jaci.2025.02.032&rft_id=info%3Apmid%2F40058414&rft.externalDocID=40058414
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0091-6749&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0091-6749&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0091-6749&client=summon