查看更多>>摘要：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 Caxias do Sul, Brazil, by NewsRx correspondents, research stated, "Liver transplant (LT) patients have become older and sicker. The rate of post-LT major adverse cardiovascular event s (MACE) has increased, and this in turn raises 30-d post-LT mortality." Our news journalists obtained a quote from the research from Universidade de Cax ias do Sul, "Noninvasive cardiac stress testing loses accuracy when applied to p re-LT cirrhotic patients. To assess the feasibility and accuracy of a machine le arning model used to predict post-LT MACE in a regional cohort. This retrospecti ve cohort study involved 575 LT patients from a Southern Brazilian academic cent er. We developed a predictive model for post-LT MACE (defined as a composite out come of stroke, newonset heart failure, severe arrhythmia, and myocardial infar ction) using the extreme gradient boosting (XGBoost) machine learning model. We addressed missing data (below 20%) for relevant variables using the k-nearest neighbor imputation method, calculating the mean from the ten nearest neighbors for each case. The modeling dataset included 83 features, encompassin g patient and laboratory data, cirrhosis complications, and pre-LT cardiac asses sments. Model performance was assessed using the area under the receiver operati ng characteristic curve (AUROC). We also employed Shapley additive explanations (SHAP) to interpret feature impacts. The dataset was split into training (75% ) and testing (25%) sets. Calibration was evaluated using the Brier score. We followed Transparent Reporting of a Multivariable Prediction Model fo r Individual Prognosis or Diagnosis guidelines for reporting. Scikit-learn and S HAP in Python 3 were used for all analyses. The supplementary material includes code for model development and a user-friendly online MACE prediction calculator . Of the 537 included patients, 23 (4.46%) developed inhospital MA CE, with a mean age at transplantation of 52.9 years. The majority, 66.1% , were male. The XGBoost model achieved an impressive AUROC of 0.89 during the t raining stage. This model exhibited accuracy, precision, recall, and F1-score va lues of 0.84, 0.85, 0.80, and 0.79, respectively. Calibration, as assessed by th e Brier score, indicated excellent model calibration with a score of 0.07. Furth ermore, SHAP values highlighted the significance of certain variables in predict ing postoperative MACE, with negative noninvasive cardiac stress testing, use of nonselective beta-blockers, direct bilirubin levels, blood type O, and dynamic alterations on myocardial perfusion scintigraphy being the most influential fact ors at the cohort-wide level. These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE, making it a valuable tool for clinical practice. Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE, usin g both cardiovascular and hepatic variables. The model demonstrated impressive p erformance, aligning with literature findings, and exhibited excellent calibrati on."
NETL
NSTL