LNG-IUS versus oral progestogen treatment for endometrial hyperplasia: a long-term comparative cohort study

Abstract

Study question: What are the regression and hysterectomy rates for women treated with the levonorgestrel-releasing intrauterine system (LNG-IUS) compared with oral progestogens for endometrial hyperplasia (EH)?

Summary answer: The LNG-IUS achieves higher regression and lower hysterectomy rates than oral progestogens in the treatment of complex and atypical hyperplasia.

What is known already: The LNG-IUS and oral progestogens are both equally used to treat women with EH. There is uncertainty about whether the LNG-IUS is a better therapy for EH.

Study design, size, duration: This comparative cohort study included 344 women recruited from August 1998 until December 2010.

Participants/materials, setting, methods: Women with complex non-atypical or atypical EH were treated with the LNG-IUS (n = 250) or oral progestogens (n = 94) in a tertiary referral hospital. We evaluated the proportion of women who regressed or underwent hysterectomy after treatment with the LNG-IUS compared with oral progestogens by logistic regression adjusting for confounding. The time from diagnosis to regression was explored through a survival analysis.

Main results and the role of chance: The follow-up rate was 95.3%. The mean length of follow-up in the two groups was 66.9 ± SD 35.1 months for the LNG-IUS and 87.2 ± SD 45.5 months for the oral progestogen group. Regression of hyperplasia was achieved in 94.8% (237/250) of patients with the LNG-IUS compared with 84.0% (79/94) of patients treated with oral progestogens (adjusted odds ratio (OR) = 3.04, 95% CI 1.36-6.79, P = 0.001). Hysterectomy rates were lower in the LNG-IUS group during follow-up (22.1, 55/250 versus 37.2%, 35/94, adjusted OR = 0.48, 95% CI 0.28-0.81, P < 0.004). Endometrial cancer was diagnosed in 8 (33%) women who had hysterectomy because of a failure to regress to normal histology during follow-up (n = 24).

Limitations, reasons for caution: The observational design cannot exclude residual confounding from unmeasured variables.

Wider implications of the findings: In treating EH, LNG-IUS achieves higher regression rates and lower hysterectomy rates than oral progestogens and should be the first-line therapy. Failure to achieve regression carries a high risk of underlying endometrial cancer and hysterectomy is advised.

Keywords: LNG-IUS; endometrial hyperplasia; oral progestogens; prospective cohort study.