中国口腔颌面外科杂志 ›› 2025, Vol. 23 ›› Issue (5): 483-490.doi: 10.19438/j.cjoms.2025.05.009

• 论著 • 上一篇    下一篇

日间头面部手术患儿术后疼痛预测模型的构建及效果评估

沈晓敏#, 杨美#, 李静洁, 郑永超*, 王旭*   

  1. 上海交通大学医学院附属第九人民医院 麻醉科,上海 200011
  • 收稿日期:2025-02-24 修回日期:2025-04-23 发布日期:2025-10-10
  • 通讯作者: 王旭,E-mail: wangx1636@sh9hospital.org.cn;郑永超,E-mail: yongchao0110@163.com。*共同通信作者
  • 作者简介:沈晓敏(1983-),女,硕士,E-mail: jenny26_111@hotmail.com;杨美(1989-),男,硕士,E-mail: ymshsmu1108@163.com。#并列第一作者
  • 基金资助:
    上海交通大学医学院附属第九人民医院临床研究助推计划(JYLJ202405)

Construction and effect evaluation of postoperative pain prediction model for children undergoing head and facial day surgery

Shen Xiaomin, Yang Mei, Li Jingjie, Zheng Yongchao, Wang Xu   

  1. Department of Anesthesiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine. Shanghai 200011, China
  • Received:2025-02-24 Revised:2025-04-23 Published:2025-10-10

摘要: 目的: 基于机器学习算法,构建日间头面部手术患儿术后疼痛的预测模型,并评估其预测效果。方法: 回顾性纳入893例全麻下日间头面部手术患儿,收集人口学特征和围术期资料。根据手术后全麻恢复期FLACC疼痛评估量表评分,将患儿分为疼痛组(FLACC评分≥4)和非疼痛组(FLACC评分<4),采用最小绝对收缩和选择算子(LASSO)回归算法五倍交叉验证筛选变量,使用6种不同机器学习算法(Logistics回归模型、K最近邻模型、支持向量机模型、决策树模型、双向递归模型和神经网络模型)将受试者按照7∶3比例分为训练集和测试集,采用受试者工作特征曲线下面积(AUROC)展示训练集和测试集对术后疼痛的预测效果。结果: 日间头面部手术患儿术后疼痛的总发生率为23.63%,通过LASSO 回归筛选的危险因素包括患儿的改良耶鲁术前焦虑量表(m-YPAS)评分、家长术前的状态焦虑问卷(SAI)评分、手术史、手术类型、患儿年龄、性别、诱导期使用舒芬太尼和氯胺酮8项。6种不同机器学习算法中,4种(Logistics回归模型,支持向量机模型、双向递归模型和神经网络模型)能够在测试集中维持较好的表现(AUROC>0.70)。测试集中,Logistic回归模型的预测结果最好(AUROC=0.78,95%CI:0.72~0.84)。结论: 基于机器学习得到的预测模型,可有效预测日间头面部手术患儿的术后疼痛。

关键词: 头面部日间手术, 全身麻醉, 儿童, 术后疼痛, 风险预测模型

Abstract: PURPOSE: To develop and validate a machine learning-based prediction model for postoperative pain in pediatric patients undergoing head and facial day surgery. METHODS: A total of 893 children who underwent head and facial day surgery under general anesthesia were retrospectively included, the patients were categorized into pain (FLACC score ≥4) or non-pain (FLACC score <4) group based on assessments in the postanesthesia care unit (PACU). Variables were selected via the least absolute shrinkage and selection operator (LASSO) regression with fivefold cross-validation. Six machine learning algorithms—including logistic regression (LR), K-nearest neighbor(KNN), support vector machine (SVM), decision tree (DT), bidirectional recurrent neural network (BRNN), and artificial neural network (ANN)—were trained on a 7∶3 split dataset. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). RESULTS: The incidence of postoperative pain was 23.63%. Key predictors included preoperative m-YPAS scores, parental SAI scores, surgical history, procedure type, age, gender and induction with sufentanil/ketamine. Four out of 6 different machine learning algorithms (LR, SVM, BRNN, and ANN) were able to maintain good performance in the test set (AUROC>0.70). Among the models, logistic regression achieved the highest AUROC (0.78, 95%CI: 0.72-0.84) in the test set. CONCLUSIONS: The prediction model based on machine learning in this study can effectively predict postoperative pain in pediatric patients undergoing head and facial day surgery.

Key words: Head and facial day surgery, General anesthesia, Pediatric patients, Postoperative pain, Risk prediction model

中图分类号: