Learning curves for endobronchial ultrasound using cusum analysis

Abstract

Background: The assessment of medical trainees is becoming an increasingly prominent issue, with current methods having varying degrees of inherent subjectivity and bias. Cusum analysis is a technique used in quality control systems, and is starting to be employed in medical training. Endobronchial ultrasound (EBUS) is an established tool in the diagnosis and staging of lung cancer, although its use in the UK is currently restricted. As it becomes more widespread, there will be a need to assess trainees' competence accurately to ensure that those performing EBUS at new centres are appropriately skilled.

Methods: A retrospective review of clinical practice in tertiary referral centres in England, Scotland and Spain was carried out. The study group comprised 500 patients undergoing EBUS for the diagnosis and staging of lung cancer as part of a clinical service. Using cusum analysis, the first 100 cases from each of the five centres are presented. Each centre has one consultant physician as the primary EBUS operator, and all operators began using EBUS at their current centre (ie, no learning from prior experience). The data are presented as learning curves.

Results: It is evident that there is a wide range of time over which EBUS-guided transbronchial needle aspiration (TBNA) competence is attained. The pooled sensitivity was 67.4% (individual sensitivities 66.7, 70.7, 61.2, 80.3 and 59.7%).

Conclusion: Cusum analysis is well suited to the assessment of procedures with a binary outcome, but accurate and appropriate standards of practice must be determined prior to assessment to ensure correct identification of underperformance. This report suggests that the learning curve for EBUS is greater than previously reported using different methods, and that even experienced bronchoscopists vary in their speed of learning.