Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies
Abstract Combined immunodeficiencies (CID) and common variable immunodeficiencies (CVID), prevalent yet substantially underdiagnosed primary immunodeficiencies, necessitate improved early detection. Leveraging large-scale electronic health records (EHR) from four nationwide US cohorts, we developed...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-06-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01761-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849691407343681536 |
|---|---|
| author | Giorgos Papanastasiou Marco Scutari Raffi Tachdjian Vivian Hernandez-Trujillo Jason Raasch Kaylyn Billmeyer Nikolay V. Vasilyev Vladimir Ivanov |
| author_facet | Giorgos Papanastasiou Marco Scutari Raffi Tachdjian Vivian Hernandez-Trujillo Jason Raasch Kaylyn Billmeyer Nikolay V. Vasilyev Vladimir Ivanov |
| author_sort | Giorgos Papanastasiou |
| collection | DOAJ |
| description | Abstract Combined immunodeficiencies (CID) and common variable immunodeficiencies (CVID), prevalent yet substantially underdiagnosed primary immunodeficiencies, necessitate improved early detection. Leveraging large-scale electronic health records (EHR) from four nationwide US cohorts, we developed a novel causal Bayesian Network (BN) model to identify antecedent clinical phenotypes associated with CID/CVID. Consensus directed acyclic graphs (DAGs) demonstrated robust predictive performance within each cohort (ROC AUC: 0.61–0.77) and generalizability across unseen cohorts (ROC AUC: 0.56–0.72) in identifying CID/CVID, despite varying inclusion criteria across cohorts. The consensus DAGs reveal causal relationships between comorbidities preceding CID/CVID diagnosis, including autoimmune and blood disorders, lymphomas, organ damage or inflammation, respiratory conditions, genetic anomalies, recurrent infections, and allergies. Further evaluation through causal inference and by expert clinical immunologists substantiates the clinical relevance of the identified phenotypic trajectories. These findings hold promise for translation into improved clinical practice, potentially leading to earlier identification and intervention of adults at risk for CID/CVID. |
| format | Article |
| id | doaj-art-b2cfbccc3f954cfd830d136afb27c938 |
| institution | DOAJ |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-b2cfbccc3f954cfd830d136afb27c9382025-08-20T03:21:02ZengNature Portfolionpj Digital Medicine2398-63522025-06-018111310.1038/s41746-025-01761-5Large scale causal modeling to identify adults at risk for combined and common variable immunodeficienciesGiorgos Papanastasiou0Marco Scutari1Raffi Tachdjian2Vivian Hernandez-Trujillo3Jason Raasch4Kaylyn Billmeyer5Nikolay V. Vasilyev6Vladimir Ivanov7Pfizer Inc.Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)Division of Allergy & Clinical Immunology, David Geffen School of Medicine at University of California Los AngelesAllergy & Immunology Care Center of South FloridaMidwest Immunology ClinicPfizer Inc.Pfizer Inc.Pfizer Inc.Abstract Combined immunodeficiencies (CID) and common variable immunodeficiencies (CVID), prevalent yet substantially underdiagnosed primary immunodeficiencies, necessitate improved early detection. Leveraging large-scale electronic health records (EHR) from four nationwide US cohorts, we developed a novel causal Bayesian Network (BN) model to identify antecedent clinical phenotypes associated with CID/CVID. Consensus directed acyclic graphs (DAGs) demonstrated robust predictive performance within each cohort (ROC AUC: 0.61–0.77) and generalizability across unseen cohorts (ROC AUC: 0.56–0.72) in identifying CID/CVID, despite varying inclusion criteria across cohorts. The consensus DAGs reveal causal relationships between comorbidities preceding CID/CVID diagnosis, including autoimmune and blood disorders, lymphomas, organ damage or inflammation, respiratory conditions, genetic anomalies, recurrent infections, and allergies. Further evaluation through causal inference and by expert clinical immunologists substantiates the clinical relevance of the identified phenotypic trajectories. These findings hold promise for translation into improved clinical practice, potentially leading to earlier identification and intervention of adults at risk for CID/CVID.https://doi.org/10.1038/s41746-025-01761-5 |
| spellingShingle | Giorgos Papanastasiou Marco Scutari Raffi Tachdjian Vivian Hernandez-Trujillo Jason Raasch Kaylyn Billmeyer Nikolay V. Vasilyev Vladimir Ivanov Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies npj Digital Medicine |
| title | Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| title_full | Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| title_fullStr | Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| title_full_unstemmed | Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| title_short | Large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| title_sort | large scale causal modeling to identify adults at risk for combined and common variable immunodeficiencies |
| url | https://doi.org/10.1038/s41746-025-01761-5 |
| work_keys_str_mv | AT giorgospapanastasiou largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT marcoscutari largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT raffitachdjian largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT vivianhernandeztrujillo largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT jasonraasch largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT kaylynbillmeyer largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT nikolayvvasilyev largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies AT vladimirivanov largescalecausalmodelingtoidentifyadultsatriskforcombinedandcommonvariableimmunodeficiencies |