Proceedings of the second Artificial Intelligence in Primary Immunodeficiency (AIPI) meeting - 09/10/25

Doi : 10.1016/j.jaci.2025.09.002

Jacques G. Rivière, MD, MSc ^a,^b,^c,^d,^⁎ , Lisa Bastarache, MS ^e, Luiza C. Campos, MD ^f, Gerard Carot-Sans, PhD ^g,^h, Aaron Chin, MD ^an, Rumi Chunara, PhD ⁱ, Charlotte Cunningham-Rundles, MD, PhD ^j, Lorenzo Erra, MS ^k, Jocelyn Farmer, MD, PhD ^l, Nicolas Garcelon, PhD ^m, Elena Hsieh, MD ⁿ, Helen Leavis, MD, PhD ^o, Seungwon Lee, PhD ^p, Liangying Liu, MS ^q,^r, Maaike Kusters, MD, PhD ^s, Brian C. Lloyd, BA ^t, Alexandra K. Martinson, MD ^u, Rachel Mester, PhD ^v, Justin B. Moore, PhD ^w, Despina Moshous, MD, PhD ^x, Jordan S. Orange, MD, PhD ^y, Nefatia Parrish, BS ^z, Sarah Henrickson Parker, PhD ^aa, Bogdan Pasaniuc, PhD ^ab, Xiao P. Peng, MD, PhD ^ac, Martine Pergent, MSc ^ad, Jordi Piera-Jiménez, PhD ^g,^h, Jessica Quinn, MPH ^z, Sidharth Ramesh, MD ^ae, Kirk Roberts, PhD ^af, Peter N. Robinson, MD, PhD ^ag, Guergana Savova, PhD ^ah, Christopher Scalchunes, MPA ^t, Markus G. Seidel, MD ^ai, Rachel Simoneau, MPA ^z, Pere Soler-Palacin, MD, PhD ^a,^b,^c,^d, Kathleen E. Sullivan, MD, PhD ^aj, Marielle Van Gijn, PhD ^ak, Chung-Il Wi, MD ^al, Dawei Zhou, PhD ^am, Vanessa Tenembaum, BA ^z, Manish J. Butte, MD, PhD ^an, Nicholas L. Rider, DO ^ao

^a Universitat Autònoma de Barcelona, Barcelona, Spain

^b Infection and Immunity in Pediatric Patients Research Group, Vall d’Hebron Institut de Recerca, Barcelona, Spain

^c Pediatric Infectious Diseases and Immunodeficiencies Unit, Hospital Infantil i de La Dona Vall d’Hebron, Vall d’Hebron Barcelona Hospital Campus, Barcelona, Spain

^d Jeffrey Modell Diagnostic and Research Center for Primary Immunodeficiencies, Barcelona, Spain

^e Vanderbilt University Medical Center, Nashville, Tenn

^f University College London Institute of Immunity and Transplantation, London, United Kingdom

^g Catalan Health Service, Barcelona, Spain

^h Digitalization for the Sustainability of the Healthcare System (DS3) Research Group, Barcelona, Spain

ⁱ School of Global Public Health and the Tandon School of Engineering, New York University, New York, NY

^j Division of Allergy and Immunology, Icahn School of Medicine at Mount Sinai, New York, NY

^k Departamento de Fisiología, Biología Molecular y Celular, Instituto de Biociencias, Biotecnología y Biología Traslacional (IB3) e Instituto de Química Biológica (IQUIBICEN), FCEN, UBA, CONICET, Buenos Aires, Argentina

^l Program in Clinical Immunodeficiency, Division of Allergy & Immunology, Beth Israel Lahey Health, Burlington, Mass

^m Data Science Platform, Université Paris Cité, Imagine Institute, INSERM UMR 1163, Paris, France

ⁿ Department of Pediatrics, Section of Allergy and Immunology, and the Department of Immunology and Microbiology, University of Colorado School of Medicine, Aurora, Colo

^o Department of Rheumatology and Clinical Immunology, University Medical Center Utrecht and Utrecht University, Utrecht, The Netherlands

^p Computational Health Informatics Program, Boston Children’s Hospital, Boston, Mass

^q Fralin Biomedical Research Institute at VTC, Roanoke, Va

^r Graduate Program in Translational Biology, Medicine, and Health, Virginia Tech, Blacksburg, Va

^s Paediatric Immunology Department, Great Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom

^t Immune Deficiency Foundation, Hanover, Md

^u Department of Pediatrics, Children’s National Hospital, Washington, DC

^v Department of Computational Medicine, University of California, Los Angeles, Calif

^w Department of Implementation Science, Division of Public Health Sciences, Wake Forest University School of Medicine, Winston-Salem, NC

^x Pediatric Immunology, Hematology and Rheumatology, Necker-Enfants Malades University Hospital, Assistance Publique-Hôpitaux de Paris, Institut Imagine and Université Paris Cité, Paris, France

^y Department of Pediatrics, Columbia University Vagelos College of Physicians and Surgeons, Columbia University, New York, NY

^z Jeffrey Modell Foundation, New York, NY

^aa Department of Health Systems and Implementation Science, Virginia Tech Carilion School of Medicine, Roanoke, Va

^ab Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa

^ac Division of Pediatric Genetic Medicine, Department of Pediatrics, Children’s Hospital at Montefiore, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY

^ad The International Patient Organisation for Primary Immunodeficiencies, Brussels, Belgium

^ae Medblocks Inc, Dover, Del

^af McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Tex

^ag Berlin Institute of Health, Charité-Universitätsmedizin Berlin, Berlin, Germany

^ah Computational Health Informatics Program, Boston Children’s Hospital, Harvard Medical School, Boston, Mass

^ai Division of Pediatric Hematology and Oncology, Department of Pediatric and Adolescent Medicine, Styrian Children’s Cancer Research Unit for Cancer and Inborn Errors of the Blood and Immunity in Children, Medical University of Graz, Graz, Austria

^aj Division of Allergy Immunology, The Children’s Hospital of Philadelphia, Philadelphia, Pa

^ak Department of Human Genetics, Amsterdam University Medical Center, Amsterdam, The Netherlands

^al Mayo Clinic Children, Mayo Clinic Health System Research, Mayo Clinic, Rochester, Minn

^am Department of Computer Science, Virginia Tech, Blacksburg, Va

^an Department of Pediatrics, Division of Immunology, Allergy, and Rheumatology, University of California, Los Angeles, Calif

^ao Department of Health Systems and Implementation Science, Virginia Tech Carilion School of Medicine, Section of Allergy-Immunology, The Carilion Clinic, Roanoke, Va

^∗ Corresponding author: Jacques G. Rivière, MD, MSc, Universitat Autònoma de Barcelona, Vall d’Hebron Institut de Recerca, Hospital Infantil Vall d’Hebron, Pg Vall d’Hebron 115-119, Barcelona, Catalonia, Spain. Universitat Autònoma de Barcelona Vall d’Hebron Institut de Recerca Pg Vall d’Hebron Barcelona 115-119 Spain

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Thursday 09 October 2025
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Abstract

The use of artificial intelligence (AI) in inborn errors of immunity offers transformative potential in diagnostics and disease management but faces multiple challenges that were discussed at the second Artificial Intelligence in Primary Immunodeficiency conference, held in New York City (March 19-22, 2025). The conference addressed 7 themes: predictive diagnostic algorithms, health equity, industry collaboration, advanced computational tools like large language models, patient-led AI initiatives, multiomics integration, and implementation science. Discussions highlighted the growing impact of AI on diagnostics, genomics, and health systems, emphasizing the need for high-quality, diverse datasets and ethical safeguards to ensure equitable application. Participants stressed that AI alone cannot resolve systemic inequities or delays in diagnosis. Challenges such as the lack of harmonized datasets, the complexity of integrating multiomics data, ethical concerns, and the difficulty of adapting solutions to low-resource settings were emphasized. Additionally, the use implementation science was pointed out as one of the major challenges to ensure applicability and scalability in real-world settings. This requires overcoming resistance to adoption, addressing infrastructure gaps, and ensuring regulatory compliance. Collaboration across academia, clinicians, patients, regulators, and industry is essential to ensure AI delivers equitable, lasting benefits for individuals with inborn errors of immunity.

Le texte complet de cet article est disponible en PDF.

Key words : Artificial intelligence, inborn errors of immunity, primary immunodeficiency, electronic health records, machine learning, large language models, health equity, -omics, clinical decision support, implementation science, patient-centered AI, AI scalability, AI rare diseases

Abbreviations used : AI, AIPI, CVID, EHR, ESID, ICD, IDDA, IDF, IEI, IPOPI, JMF, LLM, NLP, USIDNET