CureMate：一种用于乳腺癌治疗的临床决策支持系统

CureMate: A clinical decision support system for breast cancer treatment

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS

影响因子:4.1

分区:医学2区 / 卫生保健与服务2区计算机：信息系统3区医学：信息3区

发表日期:2024 Dec

作者: Rodrigo Martín Gómez Del Moral Herranz, María Jesús López Rodríguez, Alexander P Seiffert, Javier Soto Pérez-Olivares, Miguel Chiva De Agustín, Patricia Sánchez-González

DOI: 10.1016/j.ijmedinf.2024.105647

摘要

乳腺癌（BC）在治疗决策中面临重大挑战。目前有多种首选治疗方案，需考虑多种患者特异性因素。本文介绍CureMate，一种预测乳腺癌患者最有效初始治疗方案的临床决策支持系统。研究了基于人口学、组织病理学和磁共振成像变量的不同人工智能模型。CureMate的网页应用方便用户操作。建立了一个包含232例BC患者的数据库，每例由29个变量描述。在四种机器学习算法中，特别是决策树分类器（DTC）、高斯朴素贝叶斯（GNB）、k最近邻（K-NN）和支持向量机（SVM），筛选出最适合该任务的模型，进行优化并进行独立测试。结果显示，SVM在BC治疗方案预测中表现最佳，测试准确率达0.933。CureMate的网页应用结合SVM模型，用户输入相关患者变量后，可显示建议的首选治疗步骤及后续步骤示意图。结果表明，CureMate具有高准确性和临床应用潜力，有助于临床医生做出科学的治疗决策。

Abstract

Breast Cancer (BC) poses significant challenges in treatment decision-making. Multiple first treatment lines are currently available, determined by several patient-specific factors that need to be considered in the decision-making process.To present CureMate, a Clinical Decision Support System to predict the most effective initial treatment for BC patients. Different artificial intelligence models based on demographic, anatomopathological and magnetic resonance imaging variables are studied. CureMate's web application allows for easy use of the best model.A database of 232 BCE patients, each described by 29 variables, was established. Out of four machine learning algorithms, specifically Decision Tree Classifier (DTC), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (K-NN), and Support Vector Machine (SVM), the most suitable model for the task was identified, optimized and independently tested.SVM was identified as the best model for BC treatment planning, resulting in a test accuracy of 0.933. CureMate's web application, including the SVM model, allows for introducing the relevant patient variables and displays the suggested first treatment step, as well as a diagram of the following steps.The results demonstrate CureMate's high accuracy and effectiveness in clinical settings, indicating its potential to aid practitioners in making informed therapeutic decisions.