首页|Department of Obstetrics and Gynecology Reports Findings in Acute Kidney Injury (Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in C ritically Ill Elderly Patients During Hospitalization: Internet-Based and ...)
Department of Obstetrics and Gynecology Reports Findings in Acute Kidney Injury (Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in C ritically Ill Elderly Patients During Hospitalization: Internet-Based and ...)
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 Kidney Diseases and Co nditions - Acute Kidney Injury is the subject of a report. According to news rep orting from Dalian, People’s Republic of China, by NewsRx journalists, research stated, “Acute kidney disease (AKD) affects more than half of critically ill eld erly patients with acute kidney injury (AKI), which leads to worse short-term ou tcomes. We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps.” The news correspondents obtained a quote from the research from the Department o f Obstetrics and Gynecology, “Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) dat abase were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South U niversity were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators wit hin 24 hours of the first diagnosis of AKI and the fluctuation range of some ind icators, namely delta (day 3 after AKI minus day 1), as features. Six machine le arning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpret ing; and the Heroku platform for deploying the best-performing models as web-bas ed apps. For the model of predicting the risk of AKD in elderly patients with AK I during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841- 0.865 ), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addi tion, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.86 8, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed u sers to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model’s top 10 influ encing factors conducted based on the SHAP value, partial dependence plots revea led the optimal cutoff of some interventionable indicators. The top 5 factors pr edicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitr ogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 fact ors determining in-hospital mortality were age, BUN on day 1, vasopressor use, B UN on day 3, and partial pressure of carbon dioxide (PaCO). We developed and val idated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively.”
Dalian, People’s Republic of China, Asia , Acute Kidney Injury, Cyborgs, Emerging Technologies, Health and Medicine, Hosp itals, Kidney Diseases and Conditions, Machine Learning
NETL
NSTL
