Rao, Krishna

PURPOSE Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet their use is associated with immune-related adverse events (irAEs). Estimating the prevalence and patient impact of these irAEs in the real-world data setting is critical for characterizing the benefit/risk profile of ICI therapies beyond the clinical trial population. Diagnosis codes, such as International Classification of Diseases codes, do not comprehensively illustrate a patient's care journey and offer no insight into drug-irAE causality. This study aims to capture the relationship between ICIs and irAEs more accurately by using augmented curation (AC), a natural language processing–based innovation, on unstructured data in electronic health records. METHODS In a cohort of 9,290 patients treated with ICIs at Mayo Clinic from 2005 to 2021, we compared the prevalence of irAEs using diagnosis codes and AC models, which classify drug-irAE pairs in clinical notes with implied textual causality. Four illustrative irAEs with high patient impact—myocarditis, encephalitis, pneumonitis, and severe cutaneous adverse reactions, abbreviated as MEPS—were analyzed using corticosteroid administration and ICI discontinuation as proxies of severity. RESULTS For MEPS, only 70% (n = 118) of patients found by AC were also identified by diagnosis codes. Using AC models, patients with MEPS received corticosteroids for their respective irAE 82% of the time and permanently discontinued the ICI because of the irAE 35.9% (n = 115) of the time. CONCLUSION Overall, AC models enabled more accurate identification and assessment of patient impact of ICI-induced irAEs not found using diagnosis codes, demonstrating a novel and more efficient strategy to assess real-world clinical outcomes in patients treated with ICIs.

AbstractBackgroundMany patients with quiescent inflammatory bowel disease (IBD) suffer from irritable bowel syndrome (IBS)‐like symptoms. Although these symptoms cause significant reductions in quality of life, evidence‐based treatments are lacking as risk factors and pathophysiology of these symptoms are not clearly defined. We aimed to identify risk factors for development of IBS‐like symptoms in IBD patients with quiescent disease.MethodsWe performed a single‐center retrospective cohort study of adults with IBD from 2015 to 2021. Quiescent IBD was defined by a fecal calprotectin level <250 μg/g of stool or endoscopic evidence of quiescent disease. Cox regression was performed to identify variables that were independently associated with the incident development of IBS‐like symptoms in IBD patients.Key ResultsA total of 368 IBD patients were included for analysis, including 278 patients with UC and 88 with Crohn's disease. 15.5% of quiescent IBD patients developed IBS symptoms, with an incidence rate of (95% CI 48.0–82.0) 63.3 per 1000 person‐years. In the multivariate model, mood disorders (including anxiety and depression) and Crohn's disease were associated with increased risk for developing IBS symptoms. Male sex and higher iron levels conferred lower risk for developing IBS symptoms. Results from the multivariable model were similar in sensitivity analysis with quiescent IBD defined by fecal calprotectin level <150 mcg/g.Conclusions & InferencesMood disorder and Crohn's disease were positively associated with IBS‐like symptoms in quiescent IBD, whereas male sex and iron levels were protective. Our results were robust to different fecal calprotectin levels, arguing against inflammation as a mechanism for IBS‐like symptoms. This data suggests noninflammatory mechanisms may be important in the pathogenesis of IBS‐like symptoms in quiescent IBD. Future work may address whether modifying these risk factors may alter disease course.