Thymectomy for non-thymomatous myasthenia gravis: a propensity score matched study

Background: The efficacy of thymectomy in patients with non-thymomatous Myasthenia Gravis (MG) is still unclear. Main limitations have been variable outcome definitions, lack of a control group and adjustment for confounding. Objective: To study the efficacy of thymectomy in achieving remission or minimal manifestation (R/MM) status in patients with non-thymomatous MG. Methods: Patients with generalized MG and minimum follow-up of 6 months were included. Demographic data and treatments were recorded, as well as the MGFA post-intervention status at the last visit. Propensity scores were used to create a matched cohort of treated and untreated patients. Standard and Bayesian Cox models were used to study treatment effects. Results: Of 395 patients included, 183(46%) had a thymectomy. Thymectomy patients were younger (p < 0.001), with more females (p < 0.001) and more patients in MGFA classes 4-5 at diagnosis (p = 0.01). A matched cohort of thymectomized patients and controls (n = 98) was created. The hazard ratio (HR) for the matched cohort was 1.9 (CI:1.6-2.3), favoring thymectomy. The predicted R/MM rate was 21% in treated and 6% in controls at 5 years (Absolute difference:15%). A Bayesian Cox model for the matched cohort had an estimated probability of thymectomy efficacy (HR > 1) of 96% using a non-informative prior, and 79% using a skeptical prior. Discussion: When controlling for potential confounders, thymectomized patients had a higher probability of achieving R/MM status through time compared to controls. This study provides class III evidence of the efficacy of thymectomy in non-thymomatous myasthenia gravis.