Building alliances for early detection of immunodeficiencies: from primary care to hematology

Inborn errors of immunity (IEI), also known as primary immunodeficiencies, are a heterogeneous group of rare disorders characterized by increased susceptibility to infections, immune dysregulation, and malignancy. Early detection remains a major challenge due to the complexity of clinical presentations, limited awareness among non-specialists, and delayed diagnostic pathways. This review explores current strategies to enhance early detection of IEI, highlighting both technological innovations and clinical insights. Tools such as newborn screening, the Jeffrey Modell Foundation (JMF) warning signs, software like SPIRIT, and the PIDCAP project—a structured model designed for primary care implementation using ICD-coded clinical data— have shown promise in identifying at-risk patients. Artificial intelligence (AI) offers additional potential by detecting diagnostic patterns in electronic health records, although challenges related to data quality, heterogeneity, and system interoperability persist. Importantly, hematologic manifestations such as autoimmune cytopenias, lymphoproliferative disorders, and myelodysplastic syndromes often precede or accompany IEI and should prompt immunological evaluation. These conditions, frequently encountered in hematology, may serve as early clinical clues and justify genetic and immunophenotypic assessment. A multidisciplinary approach combining primary care, immunology, hematology, and AI technologies is essential to advance the early detection of IEI. Projects like PIDCAP, and their potential extension to secondary immunodeficiencies, exemplify scalable, patient-centered strategies that may significantly improve diagnostic timeliness and clinical outcomes.