GIÁ TRỊ CỦA PHÂN LOẠI JNET TRONG DỰ ĐOÁN ĐẶC ĐIỂM MÔ BỆNH HỌC POLYP ĐẠI TRỰC TRÀNG TẠI THÁI NGUYÊN

Abstract

Objective: To evaluate the diagnostic value of JNET classification in predicting the histopathological features of colorectal polyps in Thai Nguyen. Methods: A cross-sectional descriptive study assessing diagnostic performance was conducted on 104 patients who underwent colonoscopy and were found to have colorectal polyps at Thai Nguyen Central General Hospital and Thai Nguyen University of Medicine and Pharmacy Hospital from August 2024 to June 2025. Results: The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy of JNET type I in differentiating non-neoplastic from neoplastic lesions were 88.2%, 97.7%, 88.2%, 97.7%, and 96.2%, respectively; of type IIA lesions for differentiating low-grade dysplasia from others were 92.3%, 88.5%, 92.3%, 88.5%, and 91.3%, respectively; of Type IIB lesions for differentiating high-grade dysplasia and shallow submucosal invasive carcinoma from others were 71.4%, 95.9%, 55.6%, 97.9%, and 94.2%, respectively; and of type III lesions for differentiating deep submucosal invasive carcinoma from others were 100%, 98.8%, 66.7%, 100%, and 98.9%, respectively. Conclusion: JNET classification demonstrates high accuracy in predicting the histopathological characteristics of colorectal polyps. However, the reliability of the JNET IIB group remains limited.