e15128 Background: Data from immune checkpoint inhibitor (ICI) clinical trials show a higher incidence of ICI-related myositis with single agent ICI compared to combination therapy, but the true frequency in clinical practice is unknown. We sought to determine the incidence and clinical course of patients with ICI-related myositis at our institution. Methods: We performed a retrospective cohort study of patients treated with ICIs at MD Anderson Cancer Center between 2016 and 2019. Suspected cases of ICI-related myositis were identified using International Classification of Disease version 10 codes and confirmed by reviewing medical records, muscle enzymes and pathology. Patients treated with single agent anti-programmed death-1/ligand-1 (monotherapy) were compared to patients treated with nivolumab and ipilimumab (combination therapy) with Fischer’s exact tests, t tests, and Kaplan Meier analysis. Results: A total of 8,705 patients received ICI (7,428 monotherapy and 1,277 combination therapy), of which 31 (0.36%) were diagnosed with myositis. Estimated incidence of myositis was 0.28% and 0.78% (p=0.004), in the monotherapy and combination therapy groups, respectively. One patient was treated with ipilimumab alone (excluded from pooled data). Overall median age was 69 years (range: 40-95) with median follow up of 4 months after presentation for myositis. Thirteen (43%) patients had myositis alone and 17 (57%) had overlap with myasthenia gravis or myocarditis or both. After myositis resolution, 5 (17%) patients were rechallenged on ICI, of which 1 (20%) patient experienced a myositis flare. Differences between combination and monotherapy are summarized in the table. Patients treated with combination had shorter time to symptoms, but similar symptom grade at presentation, median length of hospitalization, and initial tumor response, compared to patients given monotherapy. Median overall survival (OS) was longer in combination vs monotherapy. Conclusions: Patients receiving combination ICI therapy had higher incidence of myositis with earlier onset than monotherapy; however, no differences in cancer outcomes or hospitalizations were observed between groups. Creation of multi-center databases are needed to develop treatment guidelines for ICI-related adverse events that will improve outcomes. [Table: see text]