Related Experiment Video
Updated: May 23, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
A predictive model for identification of pediatric individuals with common variable immunodeficiency through
Nouf Alsaati1, Chris Penney2, Ingo Helbig3
1Division of Allergy and Immunology, Children's Hospital of Philadelphia, Philadelphia, Pa.
Insights
Machine learning identified key indicators for early Common Variable Immunodeficiency (CVID) diagnosis in children. This approach can significantly reduce diagnostic delays for this rare immune disorder.
Area of Science:
- Pediatric immunology
- Computational diagnostics
- Machine learning in healthcare
Background:
- Common Variable Immunodeficiency (CVID) presents with recurrent sinopulmonary infections, often leading to diagnostic delays in children due to overlapping symptoms.
- A significant diagnostic lag, averaging 10 years, highlights the urgent need for improved early identification strategies for pediatric CVID.
Purpose of the Study:
- To develop and validate machine learning models for identifying a distinct clinical signature of CVID in pediatric patients.
- To enable earlier and more accurate diagnosis of Common Variable Immunodeficiency in children.
Main Methods:
- Utilized a cohort of 112 individuals with CVID and 627 controls, excluding those with other infection-associated conditions.
- Trained and validated three supervised machine learning classifiers, including an Extreme Gradient Boosting (XGBoost) model, on patient-level clinical metrics.
- Validated findings with a high-complexity control cohort and a logistic regression approach.
Main Results:
- The Extreme Gradient Boosting (XGBoost) model demonstrated strong predictive performance (F1 score 0.77) for CVID diagnosis up to 10 years prior.
- Key predictive features included chest radiograph counts, antibiotic prescription frequency, and the incidence of common infections.
- The model correctly classified 21 of 29 CVID cases and 179 of 183 non-CVID patients, indicating high accuracy.
Conclusions:
- A distinct clinical signature for pediatric CVID was identified, enabling earlier detection even with frequent infections in the control group.
- Machine learning techniques offer a promising avenue for reducing diagnostic delays and improving outcomes for children with CVID.
Introduction:
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.
Objective:
Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population.
Methods:
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.
Results:
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.
Conclusion:
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.
