Farzaneh Farah, Jafari Ashtiani Azadeh, Hashemi Mohammad, Hosseini Maryam Sadat, Arab Maliheh, Ashrafganjoei Tahereh, Hooshmand Chayjan Shaghayegh
Preventative Gynecology Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran.
Caspian J Intern Med. 2023 Summer;14(3):526-533. doi: 10.22088/cjim.14.3.526.
Over the last decade, artificial intelligence in medicine has been growing. Since endometrial cancer can be treated with early diagnosis, finding a non-invasive method for screening patients, especially high-risk ones, could have a particular value. Regarding the importance of this issue, we aimed to investigate the risk factors related to endometrial cancer and find a tool to predict it using machine learning.
In this cross-sectional study, 972 patients with abnormal uterine bleeding from January 2016 to January 2021 were studied, and the essential characteristics of each patient, along with the findings of curettage pathology, were analyzed using statistical methods and machine learning algorithms, including artificial neural networks, classification and regression trees, support vector machine, and logistic regression.
Out of 972 patients with a mean age of 45.77 ± 10.70 years, 920 patients had benign pathology, and 52 patients had endometrial cancer. In terms of endometrial cancer prediction, the logistic regression model had the best performance (sensitivity of 100% and 98%, specificity of 98.83% and 98.7%, for trained and test data sets respectively,) followed by the classification and regression trees model.
Based on the results, artificial intelligence-based algorithms can be applied as a non-invasive screening method for predicting endometrial cancer.
在过去十年中，医学人工智能一直在发展。由于子宫内膜癌可通过早期诊断进行治疗，因此找到一种非侵入性的患者筛查方法，尤其是针对高危患者的筛查方法，可能具有特殊价值。鉴于此问题的重要性，我们旨在研究与子宫内膜癌相关的危险因素，并找到一种使用机器学习来预测它的工具。
在这项横断面研究中，对2016年1月至2021年1月期间972例子宫异常出血患者进行了研究，并使用统计方法和机器学习算法，包括人工神经网络、分类与回归树、支持向量机和逻辑回归，分析了每位患者的基本特征以及刮宫病理结果。
在972例平均年龄为45.77±10.70岁的患者中，920例患者病理结果为良性，52例患者患有子宫内膜癌。在子宫内膜癌预测方面，逻辑回归模型表现最佳（训练数据集和测试数据集的敏感性分别为100%和98%，特异性分别为98.83%和98.7%），其次是分类与回归树模型。
基于这些结果，基于人工智能的算法可作为预测子宫内膜癌的非侵入性筛查方法应用。
