摘要
一位新闻记者兼机器人与机器学习的新闻编辑每日新闻-在一份新的报告中讨论了人工智能的研究结果。根据NewsRx记者从大学教学医院发回的新闻报道，研究表明，“经静脉拔铅(TLE)仍然是一种需要高水平专业知识的程序，”与高容量中心相比，低容量中心的死亡和临床失败风险增加了一倍。本研究的目的是建立一个基于机器学习（ML）的风险分层系统，用于预测因感染而接受TLE的患者需要机械扩张。新闻记者从大学教学医院的研究中获得了一句话：“我们设计了一个基于ML的风险分层系统，利用我们注册中心的数据训练，以预测感染TLE患者机械扩张的需求。对5种不同的ML模型(K-近邻EST邻居、支持向量机、决策树和决策树集成S)进行了广泛的评估。我们使用随机森林和梯度boosting机器(Random Forest and Gradient Boosting Machine)来识别一个最有潜力正确预测以前未见过的病人的分类器,训练模型的数据取自我们25年的TLE病人登记(1998年6月-2023年3月),491例患者（77.8%男性，69.7±12.8岁），938条导联（ICD 21.2%，起搏78.8%，留置时间61±60个月）拔除成功100%，每例患者21条导联（临床14条，设备相关7条），27.5%患者使用(MT)手牵引。对393例患者进行训练和模型选择,98例患者进行独立测试,结果显示梯度增力机的测试准确率为89%(+/-2%标准偏差),测试灵敏度为95%(+/-3%标准偏差),测试结果显示,梯度增力机的测试效果最好,测试精度为89%(+/-3%标准偏差),测试灵敏度为95%(+/-3%标准偏差)。试验特异性为73%（+/-8%标准偏差），试验AUROC为92%（+/-1%标准偏差）。对性能最好的决策树进行了进一步的互操作性分析，显示模型做出预测的内部决策与TLE的当前临床实践之间可重新标记的依从性。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Research findings on artificial intell igence are discussed in a new report. According to news reporting originating fr om the University Teaching Hospital by NewsRx correspondents, research stated, “ Transvenous lead extraction (TLE) remains a procedure that requires a high level of expertise, with a doubled risk of death and clinical failure when performed in low-volume centers compared to highvolume ones. The aim of this study was to create a machine learning (ML)-based risk stratification system for predicting the need for mechanical dilatation in patients undergoing TLE due to infection.” The news reporters obtained a quote from the research from University Teaching H ospital: “We designed a ML-based risk stratification system trained with data fr om our registry to predict the need for mechanical dilatation in patients underg oing TLE for infection. An extensive evaluation of 5 different ML models (k-near est neighbors, support vector machine, decision tree, and decision tree ensemble s, such as random forest and gradient boosting machine) was conducted to identif y a classifier with the highest potential to correctly predict previously unseen patients. Data to train the model was extracted from our 25-year registry of pa tients undergoing TLE (June 1998 - March 2023), for a total of 491 patients (77. 8% male; age 69.7 ± 12.8 years) and 938 leads (ICD 21.2% ; pacing 78.8%; indwelling time 61 ± 60 months) removed with succes s in 100% of cases. Each patient was represented by a set of 21 at tributes (14 clinical, 7 device-related). Manual traction (MT) was used in 27.5% of cases, and mechanical dilatation (MD) was employed in the remaining 72.5% of cases. 5-fold nested cross validation was used to estimate performances: in t urn, 393 patients were used for training and model selection, and 98 patients we re used for independent testing. According to the evaluation, Gradient Boosting Machine performed best, achieving test accuracy of 89% (+/- 2% std. dev.), test sensitivity of 95% (+/- 3% std. dev .), test specificity of 73% (+/- 8% std. dev.), test AUROC of 92% (+/- 1% std. dev.). A further interpre tability analysis on the best performing decision tree was conducted, showing re markable adherence between the internal decisions taken by the model to make pre dictions and the current clinical practice for TLE.”
NETL
NSTL