Identifying the Presence, Activity, and Status of Extraintestinal Manifestations of Inflammatory Bowel Disease Using Natural Language Processing of Clinical Notes.

BACKGROUND: Extraintestinal manifestations (EIMs) occur commonly in inflammatory bowel disease (IBD), but population-level understanding of EIM behavior is difficult. We present a natural language processing (NLP) system designed to identify both the presence and status of EIMs using clinical notes from patients with IBD. METHODS: In a single-center retrospective study, clinical outpatient electronic documents were collected in patients with IBD. An NLP EIM detection pipeline was designed to determine general and specific symptomatic EIM activity status descriptions using Python 3.6. Accuracy, sensitivity, and specificity, and agreement using Cohen's kappa coefficient were used to compare NLP-inferred EIM status to human documentation labels. RESULTS: The 1240 individuals identified as having at least 1 EIM consisted of 54.4% arthritis, 17.2% ocular, and 17.0% psoriasiform EIMs. Agreement between reviewers on EIM status was very good across all EIMs (κ = 0.74; 95% confidence interval [CI], 0.70-0.78). The automated NLP pipeline determining general EIM activity status had an accuracy, sensitivity, specificity, and agreement of 94.1%, 0.92, 0.95, and κ = 0.76 (95% CI, 0.74-0.79), respectively. Comparatively, prediction of EIM status using administrative codes had a poor sensitivity, specificity, and agreement with human reviewers of 0.32, 0.83, and κ = 0.26 (95% CI, 0.20-0.32), respectively. CONCLUSIONS: NLP methods can both detect and infer the activity status of EIMs using the medical document an information source. Though source document variation and ambiguity present challenges, NLP offers exciting possibilities for population-based research and decision support in IBD.

Extraintestinal manifestations of inflammatory bowel disease impact on patient experience, but are poorly captured by electronic health records. Natural language processing systems are capable of not only detecting extraintestinal manifestations, but also inferring activity information by automated analysis of clinical notes.

CD4+ Tissue-resident Memory T Cells Expand and Are a Major Source of Mucosal Tumour Necrosis Factor α in Active Crohn's Disease.

BACKGROUND AND AIMS: Tumour necrosis factor [TNF]α- and IL-17A-producing T cells are implicated in Crohn's disease [CD]. Tissue-resident memory T [TRM] cells are tissue-restricted T cells that are regulated by PR zinc finger domain 1 [PRDM1], which has been implicated in pathogenic Th17 cell responses. TRM cells provide host defence but their role in CD is unknown. We thus examined CD4+ TRM cells in CD. METHODS: Colon samples were prospectively collected at endoscopy or surgery in CD and control subjects. Flow cytometry and ex vivo assays were performed to characterise CD4+ TRM cells. RESULTS: CD4+ TRM cells are the most abundant memory T cell population and are the major T cell source of mucosal TNFα in CD. CD4+ TRM cells are expanded in CD and more avidly produce IL-17A and TNFα relative to control cells. There was a unique population of TNFα+IL-17A+ CD4+ TRM cells in CD which are largely absent in controls. PRDM1 was highly expressed by CD4+ TRM cells but not by other effector T cells. Suppression of PRDM1 was associated with impaired induction of IL17A and TNFA by CD4+ TRM cells. CONCLUSIONS: CD4+ TRM cells are expanded in CD and are a major source of TNFα, suggesting that they are important in CD. PRDM1 is expressed by TRM cells and may regulate their function. Collectively, this argues for prospective studies tracking CD4+ TRM cells over the disease course.