A validated artificial intelligence-based pipeline for population-wide primary immunodeficiency screening - 04/01/23
, Michael Coffey, BBA b, Ashok Kurian, MBA b, Jessica Quinn, MPH c, Jordan S. Orange, MD, PhD d, Vicki Modell c, Fred Modell cAbstract |
Background |
Identification of patients with underlying inborn errors of immunity and inherent susceptibility to infection remains challenging. The ensuing protracted diagnostic odyssey for such patients often results in greater morbidity and suboptimal outcomes, underscoring a need to develop systematic methods for improving diagnostic rates.
Objective |
The principal aim of this study is to build and validate a generalizable analytical pipeline for population-wide detection of infection susceptibility and risk of primary immunodeficiency.
Methods |
This prospective, longitudinal cohort study coupled weighted rules with a machine learning classifier for risk stratification. Claims data were analyzed from a diverse population (n = 427,110) iteratively over 30 months. Cohort outcomes were enumerated for new diagnoses, hospitalizations, and acute care visits. This study followed TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) standards.
Results |
Cohort members initially identified as high risk were proportionally more likely to receive a diagnosis of primary immunodeficiency compared to those at low-medium risk or those without claims of interest respectively (9% vs 1.5% vs 0.2%; P < .001, chi-square test). Subsequent machine learning stratification enabled an annualized individual snapshot of complexity for triaging referrals. This study’s top-performing machine learning model for visit-level prediction used a single dense layer neural network architecture (area under the receiver-operator characteristic curve = 0.98; F1 score = 0.98).
Conclusions |
A 2-step analytical pipeline can facilitate identification of individuals with primary immunodeficiency and accurately quantify clinical risk.
Le texte complet de cet article est disponible en PDF.Key words : Primary immunodeficiency, inborn error of immunity, augmented/artificial intelligence, machine learning, clinical data science, public health, learning health system
Abbreviations used : CPT, DNN, EHR, ICD-10, IEI, LR, ML, PI
Plan
| Supported by a Jeffrey Modell Foundation Translational Research Award (N.L.R.; 58293-I). |
|
| Disclosure of potential conflict of interest: N.L. Rider received funding from the Jeffrey Modell Foundation (58293-I), the National Institutes of Health (R21AI164100), and Takeda Pharmaceuticals. J.S. Orange received funding from the National Institutes of Health (R01AI20989). F. Modell, V. Modell, and J. Quinn are employed by the Jeffrey Modell Foundation, which makes the SPIRIT Analyzer freely available. The rest of the authors declare that they have no relevant conflicts of interest. |
Vol 151 - N° 1
P. 272-279 - janvier 2023 Retour au numéro
Article précédent
- Aberrant T-cell exhaustion in severe combined immunodeficiency survivors with poor T-cell reconstitution after transplantation
- Roxane Labrosse, Ines Boufaied, Benoîte Bourdin, Saideep Gona, Haley E. Randolph, Brent R. Logan, Sara Bourbonnais, Chloé Berthe, Wendy Chan, Rebecca H. Buckley, Roberta E. Parrott, Geoffrey D.E. Cuvelier, Neena Kapoor, Sharat Chandra, Blachy J. Dávila Saldaña, Hesham Eissa, Fred D. Goldman, Jennifer Heimall, Richard O’Reilly, Sonali Chaudhury, Edward A. Kolb, Shalini Shenoy, Linda M. Griffith, Michael Pulsipher, Donald B. Kohn, Luigi D. Notarangelo, Sung-Yun Pai, Morton J. Cowan, Christopher C. Dvorak, Élie Haddad, Jennifer M. Puck, Luis B. Barreiro, Hélène Decaluwe
- Azathioprine therapy induces selective NK cell depletion and IFN-γ deficiency predisposing to herpesvirus reactivation
- Florian Ingelfinger, Colin Sparano, David Bamert, David Reyes-Leiva, Aakriti Sethi, Lukas Rindlisbacher, Pascale Zwicky, Stefanie Kreutmair, Corinne C. Widmer, Sarah Mundt, Elena Cortés-Vicente, Sonia Tugues, Burkhard Becher, Bettina Schreiner
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?