摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-肿瘤学的新研究-肺癌是一篇报道的主题。根据《中华人民共和国杭州消息》，NewsRx记者报道，“本研究旨在利用机器学习技术，建立预测肺癌电视胸腔镜手术（VAT S）患者术后延长住院时间（PPOL OS）的模型，为临床决策提供有价值的见解。”我们的新闻记者引用了工业设计部的研究，“这项回顾性队列研究分析了接受VATS手术的肺癌患者的数据集，识别了25个数字特征和45个文本特征。建立了三种分类机器学习模型：XGBoos T、随机森林、随机森林、在6767例肺癌患者中,1481例(21.9%)术后住院天数>4d,男性(4111例,60.8%),已婚(6246例,92.3%)。随机森林分类器具有较好的预测性能,其曲线下面积(AUC)为0.792,ACC为0.804.。CA平动图显示三种分类器均与理想校准线高度一致,具有较高的校准可靠性,其5个主要特征分别为手术时间(0.116)、GE(0.066)、肌酐(0.062)、血红蛋白(0.058)。本研究建立并评价了三种机器学习模型用于预测VATS肺癌患者的POLO，结果表明Ra NDOM森林模型预测POLO最准确。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Oncology - Lung Cancer is the subject of a report. According to news originating from Hangzhou, People ’s Republic of China, by NewsRx correspondents, research stated, “This study aim ed to develop models for predicting prolonged postoperative length of stay (PPOL OS) in lung cancer patients undergoing video-assisted thoracoscopic surgery (VAT S) by utilizing machine-learning techniques. These models aim to offer valuable insights for clinical decision-making.” Our news journalists obtained a quote from the research from the Department of I ndustrial Design, “This retrospective cohort study analyzed a dataset of lung ca ncer patients who underwent VATS, identifying 25 numerical features and 45 textu al features. Three classification machine-learning models were developed: XGBoos t, random forest, and neural network. The performance of these models was evalua ted based on accuracy (ACC) and area under the receiver operating characteristic curve, whereas the importance of variables was assessed using the feature impor tance parameter from the random forest model. Of the 6767 lung cancer patients, 1481 patients (21.9%) experienced a postoperative length of stay of > 4 days. The majority were male (4111, 60.8% ), married (6246, 92.3%), and diagnosed with adenocarcinoma (4145, 61.3%). The Random Forest classifier exhibited superior prediction performance with an area under the curve (AUC) of 0.792 and ACC of 0.804. The ca libration plot revealed that all three classifiers were in close alignment with the ideal calibration line, indicating high calibration reliability. The five mo st critical features identified were the following: surgical duration (0.116), a ge (0.066), creatinine (0.062), hemoglobin (0.058), and total protein (0.054). T his study developed and evaluated three machine-learning models for predicting P POLOS in lung cancer patients undergoing VATS. The findings revealed that the Ra ndom Forest model is most accurately predicting the PPOLOS.”
NETL
NSTL