Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, Italy.
Department of Breast Radiology, Giovanni Paolo II I.R.C.C.S. Cancer Institute, via Orazio Flacco 65, 70124, Bari, Italy.
Arch Gynecol Obstet. 2022 Dec;306(6):2143-2154. doi: 10.1007/s00404-022-06578-1. Epub 2022 May 9.
In a growing number of social and clinical scenarios, machine learning (ML) is emerging as a promising tool for implementing complex multi-parametric decision-making algorithms. Regarding ovarian cancer (OC), despite the standardization of features that can support the discrimination of ovarian masses into benign and malignant, there is a lack of accurate predictive modeling based on ultrasound (US) examination for progression-free survival (PFS). This retrospective observational study analyzed patients with epithelial ovarian cancer (EOC) who were followed in a tertiary center from 2018 to 2019. Demographic features, clinical characteristics, information about the surgery and post-surgery histopathology were collected. Additionally, we recorded data about US examinations according to the International Ovarian Tumor Analysis (IOTA) classification. Our study aimed to realize a tool to predict 12 month PFS in patients with OC based on a ML algorithm applied to gynecological ultrasound assessment. Proper feature selection was used to determine an attribute core set. Three different machine learning algorithms, namely Logistic Regression (LR), Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and validated with five-fold cross-validation to predict 12 month PFS. Our analysis included n. 64 patients and 12 month PFS was achieved by 46/64 patients (71.9%). The attribute core set used to train machine learning algorithms included age, menopause, CA-125 value, histotype, FIGO stage and US characteristics, such as major lesion diameter, side, echogenicity, color score, major solid component diameter, presence of carcinosis. RFF showed the best performance (accuracy 93.7%, precision 90%, recall 90%, area under receiver operating characteristic curve (AUROC) 0.92). We developed an accurate ML model to predict 12 month PFS.
在越来越多的社会和临床场景中，机器学习 (ML) 正在成为实施复杂多参数决策算法的有前途的工具。关于卵巢癌 (OC)，尽管已经确定了可以支持将卵巢肿块分为良性和恶性的特征，但缺乏基于超声 (US) 检查的无进展生存期 (PFS) 的准确预测建模。这项回顾性观察研究分析了 2018 年至 2019 年在一家三级中心随访的上皮性卵巢癌 (EOC) 患者。收集了人口统计学特征、临床特征、手术和术后组织病理学信息。此外，我们还根据国际卵巢肿瘤分析 (IOTA) 分类记录了 US 检查数据。我们的研究旨在实现一种基于 ML 算法的工具，该工具可根据妇科超声评估预测 OC 患者的 12 个月 PFS。适当的特征选择用于确定属性核心集。然后使用三种不同的机器学习算法，即逻辑回归 (LR)、随机森林 (RFF) 和 K-最近邻 (KNN)，通过五折交叉验证进行训练和验证，以预测 12 个月 PFS。我们的分析包括 n=64 名患者，46/64 名患者 (71.9%) 实现了 12 个月 PFS。用于训练机器学习算法的属性核心集包括年龄、绝经、CA-125 值、组织学类型、FIGO 分期和 US 特征，如主要病变直径、侧位、回声性、彩色评分、主要实性成分直径、癌性存在。RFF 表现出最佳性能 (准确性 93.7%，精度 90%，召回率 90%，接受者操作特征曲线 (AUROC) 下面积 0.92)。我们开发了一种准确的 ML 模型来预测 12 个月 PFS。
