Related Experiment Video
Updated: May 10, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Diagnostic Performance of ADNEX Model and IOTA Simple Rules in Differentiating Malignant from Benign Adnexal Masses
Ammaraporn Chankrachang1, Worashorn Lattiwongsakorn1, Charuwan Tantipalakorn1
1Department of Obstetrics and Gynecology, Faculty of Medicine, Chiang Mai University, Chiang Mai 50200, Thailand.
Abstract:
Objective: The aim of the study was evaluate the diagnostic performance of the ADNEX model performed by non-expert examiners in differentiating between benign and malignant adnexal masses and to compare its performance with the IOTA Simple Rules. Methods: This diagnostic study was a secondary analysis based on a prospectively collected database of gynecological patients scheduled for elective surgery for adnexal masses. Preoperative ultrasound was performed within 24 h before surgery by second- and third-year gynecology residents who had completed a 20 h training course on adnexal mass ultrasound. Ultrasound data, CA-125 levels, and demographic information were reviewed and validated. Malignancy risk assessment using the IOTA Simple Rules was based on M-rules and B-rules, while risk calculations with the ADNEX model were conducted using an online application. Results: The area under the curve (AUC) for the ADNEX model was 0.958 (95% CI: 0.936-0.980), which was significantly higher than that of the IOTA Simple Rules at 0.886 (95% CI: 0.840-0.931; p < 0.001). Using a 10% cutoff, the ADNEX model demonstrated a sensitivity of 93.9% and a specificity of 81.0%, while the IOTA Simple Rules had a sensitivity of 84.0% and a specificity of 93.1%. The AUCs of the ADNEX model did not significantly differ when center status was considered (oncologic vs. non-oncologic centers). Conclusions: The ADNEX model, using a 10% cutoff, exhibited superior efficacy in differentiating benign from malignant adnexal masses compared with the IOTA Simple Rules. Furthermore, the sensitivity and specificity of the ADNEX model did not significantly differ between oncologic and non-oncologic centers. Both methods demonstrated high diagnostic accuracy, even when performed by non-expert examiners, suggesting that their diagnostic performance is reproducible and applicable in general clinical practice by general practitioners and gynecologists.
