Cumulative Sum Analysis for the Learning Curve of Optical Coherence Tomography Assisted Diagnosis of Basal Cell Carcinoma

Abstract

The amount of training needed to correctly interpret optical coherence tomography scans of the skin is undefined. The aim of this study was to illustrate how cumulative sum charts can be used to determine how many optical coherence tomography scans novice assessors should evaluate in order to obtain competence in diagnosing basal cell carcinoma. Four hundred lesions suspected for non-melanoma skin cancer were evaluated by optical coherence tomography in combination with clinical photographs, using a 5-point confidence scale. The diagnostic error rate (sum of false-negative and false-positive optical coherence tomography results/total number of cases) was used to evaluate performance, with histopathological diagnosis as the reference standard. Acceptable and unacceptable error rates were set at 16% and 25%, respectively. Adequate performance was reached after assessing 183–311 scans, dependent on the cut-off for a positive test result. In conclusion, cumulative sum analysis is useful to monitor the progress of optical coherence tomography trainees. The caseload necessary for training is substantial.

Keywords

• optical coherence tomography
• basal cell carcinoma
• diagnostic
• non-invasive
• cumulative sum analysis
• learning curve