首页|Shanghai Jiao Tong University School of Medicine Reports Findings in Blood Trans fusion (Prediction of intraoperative red blood cell transfusion in valve replace ment surgery: machine learning algorithm development based on non-anemic cohort)

Shanghai Jiao Tong University School of Medicine Reports Findings in Blood Trans fusion (Prediction of intraoperative red blood cell transfusion in valve replace ment surgery: machine learning algorithm development based on non-anemic cohort)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Transfusion Medicine - Blood Tran sfusion is the subject of a report. According to news reporting originating from Shanghai, People's Republic of China, by NewsRx correspondents, research stated , "Our study aimed to develop machine learning algorithms capable of predicting red blood cell (RBC) transfusion during valve replacement surgery based on a pre operative dataset of the non-anemic cohort. A total of 423 patients who underwen t valvular replacement surgery from January 2015 to December 2020 were enrolled. " Our news editors obtained a quote from the research from the Shanghai Jiao Tong University School of Medicine, "A comprehensive database that incorporated demog raphic characteristics, clinical conditions, and results of preoperative biochem istry tests was used for establishing the models. A range of machine learning al gorithms were employed, including decision tree, random forest, extreme gradient boosting (XGBoost), categorical boosting (CatBoost), support vector classifier and logistic regression (LR). Subsequently, the area under the receiver operatin g characteristic curve (AUC), accuracy, recall, precision, and F1 score were use d to determine the predictive capability of the algorithms. Furthermore, we util ized SHapley Additive exPlanation (SHAP) values to explain the optimal predictio n model. The enrolled patients were randomly divided into training set and testi ng set according to the 8:2 ratio. There were 16 important features identified b y Sequential Backward Selection for model establishment. The top 5 most influent ial features in the RF importance matrix plot were hematocrit, hemoglobin, ALT, fibrinogen, and ferritin. The optimal prediction model was CatBoost algorithm, e xhibiting the highest AUC (0.752, 95% CI: 0.662-0.780), which also got relatively high F1 score (0.695). The CatBoost algorithm also showed superi or performance over the LR model with the AUC (0.666, 95% CI: 0.53 4-0.697). The SHAP summary plot and the SHAP dependence plot were used to visual ly illustrate the positive or negative effects of the selected features attribut ed to the CatBoost model. This study established a series of prediction models t o enhance risk assessment of intraoperative RBC transfusion during valve replace ment in no-anemic patients."

ShanghaiPeople's Republic of ChinaAs iaAlgorithmsBlood CellsBlood TransfusionCell ResearchCyborgsEmerging TechnologiesHealth and MedicineMachine LearningMedical DevicesSurgeryTransfusion Medicine

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Apr.3)