Rapid identification of inflammatory arthritis and associated adverse events following immune checkpoint therapy: a machine learning approach.

Introduction: Immune checkpoint inhibitor-induced inflammatory arthritis (ICI-IA) poses a major clinical challenge to ICI therapy for cancer, with 13% of cases halting ICI therapy and ICI-IA being difficult to identify for timely referral to a rheumatologist. The objective of this study was to rapidly identify ICI-IA patients in clinical data and assess associated immune-related adverse events (irAEs) and risk factors. Methods: We conducted a retrospective study of the electronic health records (EHRs) of 89 patients who developed ICI-IA out of 2451 cancer patients who received ICI therapy at Northwestern University between March 2011 to January 2021. Logistic regression and random forest machine learning models were trained on all EHR diagnoses, labs, medications, and procedures to identify ICI-IA patients and EHR codes indicating ICI-IA. Multivariate logistic regression was then used to test associations between ICI-IA and cancer type, ICI regimen, and comorbid irAEs. Results: Logistic regression and random forest models identified ICI-IA patients with accuracies of 0.79 and 0.80, respectively. Key EHR features from the random forest model included ICI-IA relevant features (joint pain, steroid prescription, rheumatoid factor tests) and features suggesting comorbid irAEs (thyroid function tests, pruritus, triamcinolone prescription). Compared to 871 adjudicated ICI patients who did not develop arthritis, ICI-IA patients had higher odds of developing cutaneous (odds ratio [OR]=2.66; 95% Confidence Interval [CI] 1.63-4.35), endocrine (OR=2.09; 95% CI 1.15-3.80), or gastrointestinal (OR=2.88; 95% CI 1.76-4.72) irAEs adjusting for demographics, cancer type, and ICI regimen. Melanoma (OR=1.99; 95% CI 1.08-3.65) and renal cell carcinoma (OR=2.03; 95% CI 1.06-3.84) patients were more likely to develop ICI-IA compared to lung cancer patients. Patients on nivolumab+ipilimumab were more likely to develop ICI-IA compared to patients on pembrolizumab (OR=1.86; 95% CI 1.01-3.43). Discussion: Our machine learning models rapidly identified patients with ICI-IA in EHR data and elucidated clinical features indicative of comorbid irAEs. Patients with ICI-IA were significantly more likely to also develop cutaneous, endocrine, and gastrointestinal irAEs during their clinical course compared to ICI therapy patients without ICI-IA.

Lung Cancer Survival in Patients With Autoimmune Disease.

Importance: Patients with autoimmune disease and lung cancer pose a multidisciplinary treatment challenge, particularly with the advent of immunotherapy. However, the association between autoimmune disease and lung cancer survival is largely unknown. Objective: To determine the association between autoimmune disease and lung cancer survival. Design, Setting, and Participants: Retrospective cohort study between 2003 and 2019 at a single academic medical center (Northwestern University). A query of the Northwestern Medicine Enterprise Data Warehouse identified 349 patients with lung cancer and several autoimmune diseases. Types of lung cancers included small cell, adenocarcinoma, squamous cell carcinoma, non-small cell not otherwise specified, and large cell carcinoma. Autoimmune diseases included rheumatoid arthritis, systemic lupus erythematosus, systemic sclerosis, mixed connective tissue disease, myositis, and Sjögren syndrome. Inclusion criteria were biopsy-confirmed lung cancer, autoimmune diagnosis confirmed by a rheumatologist, and death or an encounter listed in the electronic medical record within 2 years of study end. A control group of patients with biopsy-proven lung cancer but without autoimmune disease was identified. Data analysis was conducted from March to July 2020. Exposure: Presence of autoimmune disease. Main Outcomes and Measures: Overall survival and progression-free survival in patients with autoimmune disease. The hypothesis was that patients with autoimmune disease would have worse progression-free survival and overall survival compared with patients in the control group. Results: Of the original 349 patients, 177 met inclusion criteria. Mean (SD) age at lung cancer diagnosis was 67.0 (10.0) years and 136 (76.8%) were women. Most common autoimmune diseases were rheumatoid arthritis (97 [54.8%]), systemic sclerosis (43 [24.3%]), and systemic lupus erythematous (15 [8.5%]). Most common lung cancers were adenocarcinoma (99 [55.9%]), squamous cell carcinoma (29 [16.4%]), and small cell lung cancer (17 [9.6%]). A total of 219 patients (mean [SD] age at diagnosis, 65.9 [4.1] years; 173 [79.0%]) were identified as having lung cancer without autoimmune disease and included in the control cohort. Compared with patients in the control group, patients with autoimmune disease experienced no difference in overall survival (log-rank P = .69). A total of 126 patients (69.5%) with autoimmune disease received standard of care vs 213 patients (97.3%) in the control group (P < .001). No individual autoimmune disease was associated with worse prognosis, even among patients with underlying interstitial lung disease. Conclusions and Relevance: Compared with institutional controls, patients with autoimmune disease experienced no difference in survival despite the fact that fewer patients in this group received standard-of-care treatment. No individual autoimmune disease was associated with worse prognosis. Future multicenter prospective trials are needed to further evaluate autoimmune disease and lung cancer survival.