Scholarlink

<p>Postoperative thrombocytopenia (TP) is a serious complication of cardiopulmonary bypass (CPB). An accurate prediction model is crucial for the early identification of high-risk patients. This study aimed to develop and validate a prediction model for TP following CPB using machine learning (ML) algorithms combined with least absolute shrinkage and selection operator (LASSO) regression for variable selection. Using a large public database, patients admitted to the intensive care unit (ICU) following initial CPB were included. Clinical demographics, outcomes, and biochemical marker data were collected to identify key variables affecting TP. Prediction models were constructed with four different ML approaches, and model performance was externally validated. Both ICU stay and total hospitalization were longer, and the mortality rate was higher in the TP group than in the non-TP group. LASSO regression identified 10 key predictive variables. The Extreme Gradient Boosting model performed the best, demonstrating strong performance in both internal validation (area under the curve [AUC] = 0.841) and external validation (AUC = 0.795). Platelet count at ICU admission and lactate levels were among the key factors influencing TP risk.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and validation of a machine learning-based prediction model for thrombocytopenia following cardiopulmonary bypass

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月3日

查看全文
  • Shan Guo,
  • Xuping Cheng,
  • Xuandong Jiang,
  • Xufeng Cai

摘要

Postoperative thrombocytopenia (TP) is a serious complication of cardiopulmonary bypass (CPB). An accurate prediction model is crucial for the early identification of high-risk patients. This study aimed to develop and validate a prediction model for TP following CPB using machine learning (ML) algorithms combined with least absolute shrinkage and selection operator (LASSO) regression for variable selection. Using a large public database, patients admitted to the intensive care unit (ICU) following initial CPB were included. Clinical demographics, outcomes, and biochemical marker data were collected to identify key variables affecting TP. Prediction models were constructed with four different ML approaches, and model performance was externally validated. Both ICU stay and total hospitalization were longer, and the mortality rate was higher in the TP group than in the non-TP group. LASSO regression identified 10 key predictive variables. The Extreme Gradient Boosting model performed the best, demonstrating strong performance in both internal validation (area under the curve [AUC] = 0.841) and external validation (AUC = 0.795). Platelet count at ICU admission and lactate levels were among the key factors influencing TP risk.