A validated artificial intelligence-based pipeline for population-wide primary immunodeficiency screening.

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.

Use of a screening tool to determine nonadherent behavior in inflammatory bowel disease.

OBJECTIVES: Nonadherence is an issue in the management of inflammatory bowel disease (IBD), and no validated screening tool is available. We aimed to determine whether scores from a self-reported adherence survey correlated with pharmacy refill data as a reliable measure of medication adherence. METHODS: We used the eight item, self-reported Morisky Medication Adherence Scale. Each question is worth a point, with a maximum score of 8. Pharmacies were contacted for refill information for the previous 3 months, then 3 and 6 months from enrollment. Refill data were recorded for each time interval as the medication possession ratio (MPR); adherence was defined as >80%. Analysis of variance was used to determine the relationship between survey scores and MPR by drug class. RESULTS: One hundred fifty outpatients were enrolled, of whom 94 had Crohn's disease and 56 had ulcerative colitis; 89 were female. At baseline, 47% of patients were on 5-aminosalicylic acid (5-ASA), 54% an immunomodulator, 15% infliximab, 8% an injectable biologic, and 6% budesonide. The median adherence score was 7. Fifty-two percent stated they "rarely" missed a dose of medication. The median adherence score, as defined by refill data, ranged from 0% (injectable biologic) to 75% (infliximab) by drug class. Only those on an immunomodulator had a survey score that positively correlated with adherence. CONCLUSIONS: Only those on a thiopurine were likely to have a score predicting adherence behavior. Adherence to therapy for IBD is complex and cannot be predicted reliably by a self-reported survey tool validated for other chronic conditions.

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

BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: PI Prob was accurate in classifying immunodeficiency patients from controls (AUROC = 0.945; p<0.0001) at a risk threshold of ≥6%. Additionally, the model was 89% accurate for categorizing validation cohort members into appropriate International Union of Immunological Societies diagnostic categories. Our network outperformed 3 other machine learning models and provides superior transparency with a prescriptive output element. CONCLUSION: Artificial intelligence methods can classify risk for primary immunodeficiency and guide management. PI Prob enables accurate, objective decision making about risk and guides the user towards the appropriate diagnostic evaluation for patients with recurrent infections. Probabilistic models can be trained with small datasets underscoring their utility for rare disease detection given appropriate domain expertise for feature selection and network construction.

Time to endoscopy for acute upper gastrointestinal bleeding: Results from a prospective multicentre trainee-led audit.

Background: Endoscopy within 24 h of admission (early endoscopy) is a quality standard in acute upper gastrointestinal bleeding (AUGIB). We aimed to audit time to endoscopy outcomes and identify factors affecting delayed endoscopy (>24 h of admission). Methods: This prospective multicentre audit enrolled patients admitted with AUGIB who underwent inpatient endoscopy between November and December 2017. Analyses were performed to identify factors associated with delayed endoscopy, and to compare patient outcomes, including length of stay and mortality rates, between early and delayed endoscopy groups. Results: Across 348 patients from 20 centres, the median time to endoscopy was 21.2 h (IQR 12.0-35.7), comprising median admission to referral and referral to endoscopy times of 8.1 h (IQR 3.7-18.1) and 6.7 h (IQR 3.0-23.1), respectively. Early endoscopy was achieved in 58.9%, although this varied by centre (range: 31.0-87.5%, p = 0.002). On multivariable analysis, lower Glasgow-Blatchford score, delayed referral, admissions between 7:00 and 19:00 hours or via the emergency department were independent predictors of delayed endoscopy. Early endoscopy was associated with reduced length of stay (median difference 1 d; p = 0.004), but not 30-d mortality (p = 0.344). Conclusions: The majority of centres did not meet national standards for time to endoscopy. Strategic initiatives involving acute care services may be necessary to improve this outcome.