Evaluating Partial Middle Ear Filling for the Diagnosis of Cholesteatoma Using Machine Learning: A Radiological Approach

利用机器学习评估部分中耳充盈对胆脂瘤诊断的价值:一种放射学方法

阅读:1

Abstract

OBJECTIVES:  To evaluate the diagnostic accuracy of middle ear partial filling on temporal bone computed tomography (CT) scan for middle ear cholesteatoma identification using supervised machine learning models. METHODS:  We conducted an observational case-control study that retrospectively analyzed temporal bone CT scans from 212 patients from a single tertiary healthcare institution using supervised machine learning models, including k-Nearest Neighbors (kNN), Neural Networks, Logistic Regression, Support Vector Machine (SVM), and Random Forest. The study assessed the diagnostic value of partial middle ear filling for cholesteatoma. Limitations such as dataset imbalance and data complexity were addressed.  Results. In internal validation, kNN and Neural Networks achieved the highest performance (area under the receiver operating characteristic curve [AUC]: 1.000, classification accuracy [CA]: 99.6-99.7%, F1: 0.996-0.997), followed by Logistic Regression (AUC: 0.998, CA: 98.3%, F1: 0.983) and SVM (AUC: 0.997, CA: 97.5%, F1: 0.975). Random Forest performed the weakest (AUC: 0.980, CA: 92.0%, F1: 0.919). External validation (125 cases) revealed Neural Networks' superior generalizability (four errors), outperforming Logistic Regression (five), SVM (seven), Random Forest (28), and kNN (45). kNN demonstrated notably lower generalizability, suggesting limited robustness for unseen data. Discussion. The study highlights the effectiveness of machine learning in diagnosing cholesteatoma. Addressing data imbalance and variability in CT scans was crucial for model performance. Further research is needed to refine these models and explore their integration into clinical practice.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。