Scholarlink

<p>To evaluate the prediction model of acute postoperative pain in patients with gastrointestinal cancer surgery and provide better guidance and support for the prognosis and nursing of patients with GIT surgery. The features of GIT surgery patients were extracted and empowered, and a synchronous optimization machine learning model (SOMLM) was constructed according to the characteristics of GIT surgery patients. The improved spider wasp optimizer (ISWO) was applied to improve the performance of the algorithm. Among them, 80% (168 cases) were selected as the training set, and the remaining 20% (42 cases) were selected as the test set. In order to avoid overfitting, five-fold cross-validation was performed on the training set. Among the many algorithms, ISWO was superior to the control methods in terms of convergence speed and the ability to obtain the global optimal solution. SOMLM screening has obvious advantages over XGBoost training results, which is consistent with the ReliefF results. SOMLM is an effective postoperative prediction model for acute postoperative pain after gastrointestinal cancer surgery. Combined with the improved ISWO, SOMLM is a better prediction model for pain in patients undergoing GIT surgery, which improves the methodological and theoretical research of GIT, provides a basis for individualized pain treatment, and has good clinical nursing application value.</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

Establishment and Clinical Transformation of a Prediction Model for Acute Postoperative Pain in Patients Undergoing Gastrointestinal Cancer Surgery Based on Synchronous Optimization Machine Learning Models

  • 期刊论文

  • 发表日期：

    2025年3月17日

查看全文
  • Xiangnan Li,
  • Xiuquan Shi

摘要

To evaluate the prediction model of acute postoperative pain in patients with gastrointestinal cancer surgery and provide better guidance and support for the prognosis and nursing of patients with GIT surgery. The features of GIT surgery patients were extracted and empowered, and a synchronous optimization machine learning model (SOMLM) was constructed according to the characteristics of GIT surgery patients. The improved spider wasp optimizer (ISWO) was applied to improve the performance of the algorithm. Among them, 80% (168 cases) were selected as the training set, and the remaining 20% (42 cases) were selected as the test set. In order to avoid overfitting, five-fold cross-validation was performed on the training set. Among the many algorithms, ISWO was superior to the control methods in terms of convergence speed and the ability to obtain the global optimal solution. SOMLM screening has obvious advantages over XGBoost training results, which is consistent with the ReliefF results. SOMLM is an effective postoperative prediction model for acute postoperative pain after gastrointestinal cancer surgery. Combined with the improved ISWO, SOMLM is a better prediction model for pain in patients undergoing GIT surgery, which improves the methodological and theoretical research of GIT, provides a basis for individualized pain treatment, and has good clinical nursing application value.