A Five-Parameter Logistic Model to Predict the Possibility of Misdiagnosis for Improving the Specificity of Lugol Chromoendoscopy in the Diagnosis of Esophageal Neoplastic Lesions

Abstract

BackgroundLugol chromoendoscopy (LCE) is a technique that is inexpensive and convenient for screening esophageal neoplastic lesions. However, the specificity of LCE is limited. The purpose of this study was to determine the risk characteristics of lesions related to false-positive results for LCE.MethodsIn this retrospective study, 871 lesions in 773 patients scheduled for LCE in Wuhan Union Hospital and First Affiliated Hospital of Shihezi University between April 2013 and October 2018 were enrolled. The 871 lesions were used to determine the diagnostic performance of LCE for detecting esophageal neoplastic lesions and were divided into an LCE-positive group (627 lesions) and an LCE-negative group (244 lesions). Six hundred and twenty-seven unstained/understained lesions from 563 patients were used to determine the significant risk factors for misdiagnosis of neoplasms by LCE. Among them, 358 lesions and 269 lesions were classified into the misdiagnosed group and correctly diagnosed group, respectively. A multivariate logistic regression analysis was conducted for suspected esophageal neoplastic lesions during the LCE examination.ResultsThe sensitivity, specificity, and overall accuracy for LCE were 100%, 40.5%, and 58.9%, respectively. Among 13 characteristics of lesions, lesions with branching vascular network (OR 4.53, 95% CI 2.23–9.21, p < 0.001), smooth lesions (OR 2.40, 95% CI 1.38–4.18, p = 0.002) under white light endoscopy (WLE), lesions with a size < 5 mm (OR 3.06, 95% CI 1.38–6.78, p = 0.006), ill-demarcated lesions (OR 7.83, 95% CI 4.59–13.37, p < 0.001), and pink color sign (PCS)-negative (OR 4.04, 95% CI 2.38–6.84, p < 0.001) lesions after reaction with iodine solution were independent risk factors for misdiagnosis as neoplastic lesions by LCE.ConclusionLCE has a high sensitivity but limited specificity for screening esophageal neoplastic lesions. For unstained or understained lesions, branching vascular network or smooth appearance under WLE, a size < 5 mm in diameter, ill-demarcated, or PCS-negative lesions after staining are related to the misdiagnosis of esophageal neoplastic lesions by LCE based on logistic regression. The multivariate logistic model may be used to predict the possibility of misdiagnosis and help improve the specificity of LCE in diagnosing esophageal neoplastic lesions.