ABSTRACT
Background: There are now approximately 450 discrete inborn errors of immunity (IEI) described; however, diagnostic rates remain suboptimal. Use of structured health record data has proven useful for patient detection but may be augmented by natural language processing (NLP). Here we present a machine learning model that can distinguish patients from controls significantly in advance of ultimate diagnosis date. Objective: We sought to create an NLP machine learning algorithm that could identify IEI patients early during the disease course and shorten the diagnostic odyssey. Methods: Our approach involved extracting a large corpus of IEI patient clinical-note text from a major referral center's electronic health record (EHR) system and a matched control corpus for comparison. We built text classifiers with simple machine learning methods and trained them on progressively longer time epochs before date of diagnosis. Results: The top performing NLP algorithm effectively distinguished cases from controls robustly 36 months before ultimate clinical diagnosis (area under precision recall curve > 0.95). Corpus analysis demonstrated that statistically enriched, IEI-relevant terms were evident 24+ months before diagnosis, validating that clinical notes can provide a signal for early prediction of IEI. Conclusion: Mining EHR notes with NLP holds promise for improving early IEI patient detection.
ABSTRACT
BACKGROUND: The 10 Warning Signs of Primary Immunodeficiency were created 30 years ago to advance recognition of inborn errors of immunity (IEI). However, no population-level assessment of their utility applied to electronic health record (EHR) data has been conducted. OBJECTIVE: We sought to quantify the value of having ≥2 warning signs (WS) toward diagnosing IEI using a highly representative real-world US cohort. A secondary goal was estimating the US prevalence of IEI. METHODS: In this cohort study, we accessed normalized and de-identified EHR data on 152 million US patients. An IEI cohort (n = 41,080), in which patients were defined by having at least 1 verifiable IEI diagnosis placed ≥2 times in their record, was compared with a matched set of controls (n = 250,262). WS were encoded along with relevant diagnoses, relative weights were calculated, and the proportion of IEI cases versus controls with ≥2 WS was compared. RESULTS: The proportion of IEI cases with ≥2 WS significantly differed from controls (0.33 vs 0.031; P < .0005, χ2 test). We also estimated a US IEI prevalence of 6 per 10,000 individuals (41,080/73,165,655; 0.056%). WS 9 (≥2 deep-seated infections), 7 (fungal infections), 5 (failure to thrive) and 4 (≥2 pneumonias in 1 year) were the most heavily weighted among the IEI cohort. CONCLUSIONS: This nationally representative US-based cohort study demonstrates that presence of WS and associated clinical diagnoses can facilitate identification of patients with IEI from EHR data. In addition, we estimate that 6 in 10,000, or approximately 150,000 to 200,000 individuals are affected by IEI across the United States.
