首页|Chengdu University of Information Technology Reports Findings in Machine Learnin g (Utilising intraoperative respiratory dynamic features for developing and vali dating an explainable machine learning model for postoperative pulmonary ...)
Chengdu University of Information Technology Reports Findings in Machine Learnin g (Utilising intraoperative respiratory dynamic features for developing and vali dating an explainable machine learning model for postoperative pulmonary ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news originating from Sichuan, People’s Repu blic of China, by NewsRx correspondents, research stated, “Timely detection of m odifiable risk factors for postoperative pulmonary complications (PPCs) could in form ventilation strategies that attenuate lung injury. We sought to develop, va lidate, and internally test machine learning models that use intraoperative resp iratory features to predict PPCs.” Our news journalists obtained a quote from the research from the Chengdu Univers ity of Information Technology, “We analysed perioperative data from a cohort com prising patients aged 65 yr and older at an academic medical centre from 2019 to 2023. Two linear and four nonlinear learning models were developed and compared with the current gold-standard risk assessment tool ARISCAT (Assess Respiratory Risk in Surgical Patients in Catalonia Tool). The Shapley additive explanation of artificial intelligence was utilised to interpret feature importance and inte ractions. Perioperative data were obtained from 10 284 patients who underwent 10 484 operations (mean age [range] 71 [65-98] yr; 42% female). An optimised XGBoost mo del that used preoperative variables and intraoperative respiratory variables ha d area under the receiver operating characteristic curves (AUROCs) of 0.878 (0.8 66-0.891) and 0.881 (0.879-0.883) in the validation and prospective cohorts, res pectively. These models outperformed ARISCAT (AUROC: 0.496-0.533). The intraoper ative dynamic features of respiratory dynamic system compliance, mechanical powe r, and driving pressure were identified as key modifiable contributors to PPCs. A simplified model based on XGBoost including 20 variables generated an AUROC of 0.864 (0.852-0.875) in an internal testing cohort.
SichuanPeople’s Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningRisk and Prevention
NETL
NSTL
