Machine learning–assisted diagnosis classification of primary immune dysregulation using IDDA2.1 phenotype profiling


Schwitzkowski M., Veeranki S. P. K., Seidel B. N., Rusch S., Abd Elaziz D., Abdelkader S. L. M., ...Daha Fazla

Journal of Allergy and Clinical Immunology, cilt.157, sa.2, ss.470-485, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 157 Sayı: 2
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1016/j.jaci.2025.10.022
  • Dergi Adı: Journal of Allergy and Clinical Immunology
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, BIOSIS, EMBASE, MEDLINE, Natural Science Collection (ProQuest), Biological Science Database (ProQuest), Health Research Premium Collection (ProQuest), Pharma Collection (ProQuest)
  • Sayfa Sayıları: ss.470-485
  • Anahtar Kelimeler: artificial intelligence (AI), immune deficiency and dysregulation activity (IDDA) score, Inborn error of immunity (IEI), interoperable patient data, phenotype-driven disease classification, primary immune disorder (PID), primary immune regulatory disorder (PIRD), primary immunodeficiency (PID), unsupervised and supervised machine learning (ML)
  • Hacettepe Üniversitesi Adresli: Evet

Özet

Background: Immune dysregulation, including autoimmunity, autoinflammation, allergy, and malignancy predisposition, adds significant disease burden in primary immune disorders (PID) and inborn errors of immunity (IEIs). Objective: We evaluated whether the 5-graded immune deficiency and dysregulation activity (IDDA2.1) score, encompassing 21 organ involvement and disease burden parameters, supports diagnosis across a wide spectrum of IEIs. Methods: From April 2022 to November 2024, collaborators from 84 centers collected 1,043 IDDA score datasets from 825 patients across 89 IEIs (17 disorders with ≥10 patients each; range, 1-196 per IEI), including 177 scores from 141 treated patients. Supervised machine learning models (k-nearest neighbors, support vector machine, logistic regression, random forest) classified patients into disease groups and ranked corresponding predictive features, while unsupervised uniform manifold approximation and projection (UMAP) visualized disease-specific clustering. Results: Feature analysis reflected clinicians’ recognition of IEI patterns and confirmed internal IDDA score consistency. Phenotype profiles in treated patients remained informative, inversely reflecting anticipated treatment-dependent phenotype amelioration. UMAP effectively distinguished IEIs by IDDA2.1 profiles. Genetic disorder prediction achieved 73% overall accuracy, 70% for the correct monogenic IEI, and 93% within the top 3 predictions; classification reached 43% for IEI–International Union of Immunological Society categories and 59% for 12 “cardinal” IEIs (25 genes). Conclusions: Random forest feature importance analysis can inform targeted clinical screening for key disease manifestations. The top 3 prediction approach demonstrates diagnostic potential, but improved accuracy will require larger, globally shared datasets. Small sample sizes for rare diseases highlight the necessity of broader collaboration to enhance AI-assisted clinical decision-making in the future.