首页|Sun Yat-Sen University Reports Findings in Hemodialysis (Interpretable machine l earning models for the prediction of all-cause mortality and time to death in he modialysis patients)
Sun Yat-Sen University Reports Findings in Hemodialysis (Interpretable machine l earning models for the prediction of all-cause mortality and time to death in he modialysis patients)
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 Dialysis-Hemodialysi s is the subject of a report. According to news reporting originating in Shenzhe n, People's Republic of China, by NewsRx journalists, research stated, "The elev ated mortality and hospitalization rates among hemodialysis (HD) patients unders core the necessity for the development of accurate predictive tools. This study developed two models for predicting all-cause mortality and time to death-one us ing a comprehensive database and another simpler model based on demographic and clinical data without laboratory tests." The news reporters obtained a quote from the research from Sun Yat-Sen University, "A retrospective cohort study was conducted from January 2017 to June 2023. T wo models were created: Model A with 85 variables and Model B with 22 variables. We assessed the models using random forest (RF), support vector machine, and lo gistic regression, comparing their performance via the AU-ROC. The RF regression model was used to predict time to death. To identify the most relevant factors for prediction, the Shapley value method was used. Among 359 HD patients, the RF model provided the most reliable prediction. The optimized Model A showed an AU -ROC of 0.86 ± 0.07, a sensitivity of 0.86, and a specificity of 0.75 for predic ting all-cause mortality. It also had an R of 0.59 for predicting time to death. The optimized Model B had an AU-ROC of 0.80 ± 0.06, a sensitivity of 0.81, and a specificity of 0.70 for predicting all-cause mortality. In addition, it had an R of 0.81 for predicting time to death. Two new interpretable clinical tools ha ve been proposed to predict all-cause mortality and time to death in HD patients using machine learning models."
ShenzhenPeople's Republic of ChinaAs iaCyborgsDialysisEmerging TechnologiesHealth and MedicineHemodialysisMachine Learning
NETL
NSTL
