PI Prob: A risk prediction and clinical guidance system for evaluating patients with recurrent infections

• Published in: PloS one 2021-02, Vol.16 (2), p.e0237285-e0237285
• Main Authors: Rider, Nicholas L, Cahill, Gina, Motazedi, Tina, Wei, Lei, Kurian, Ashok, Noroski, Lenora M, Seeborg, Filiz O, Chinn, Ivan K, Roberts, Kirk
• Format: Article
• Language: English
• Subjects: Application programming interface; Bioinformatics; Biology and Life Sciences; Children; Clinical decision making; Colon; Colon cancer; Computer and Information Sciences; Congestive heart failure; Data analysis; Decision making; Disease; Diseases; Drafting software; Editing; Evaluation; Health risks; Hospitals; Hypersensitivity; Immunology; Infectious diseases; Information services; Liver cancer; Liver diseases; Medical schools; Medicine; Medicine and Health Sciences; Patients; Pediatrics; Probability; Relapse; Streptococcus infections
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0237285

Primary immunodeficiency diseases represent an expanding set of heterogeneous conditions which are difficult to recognize clinically. Diagnostic rates outside of the newborn period have not changed appreciably. This concern underscores a need for novel methods of disease detection. We built a Bayesian network to provide real-time risk assessment about primary immunodeficiency and to facilitate prescriptive analytics for initiating the most appropriate diagnostic work up. Our goal is to improve diagnostic rates for primary immunodeficiency and shorten time to diagnosis. We aimed to use readily available health record data and a small training dataset to prove utility in diagnosing patients with relatively rare features. We extracted data from the Texas Children's Hospital electronic health record on a large population of primary immunodeficiency patients (n = 1762) and appropriately-matched set of controls (n = 1698). From the cohorts, clinically relevant prior probabilities were calculated enabling construction of a Bayesian network probabilistic model(PI Prob). Our model was constructed with clinical-immunology domain expertise, trained on a balanced cohort of 100 cases-controls and validated on an unseen balanced cohort of 150 cases-controls. Performance was measured by area under the receiver operator characteristic curve (AUROC). We also compared our network performance to classic machine learning model performance on the same dataset. PI Prob was accurate in classifying immunodeficiency patients from controls (AUROC = 0.945; p