基于随机森林模型预测儿童扁桃体术后出血率的临床结果
Prediction of hemorrhage rate after tonsil surgery in children based on random forest model
徐宏鸣 1仇书要 2王金霞 3韩富根 4夏忠芳 5倪丽艳 6马静 7陈春光 8高兴强 9张军梅 10刘海霞 11刘海兵 12姚红兵 13庄强尔 14宋伟 15赵斯君 16张明君 1刘大波 2李晓艳1
作者信息
- 1. 上海市儿童医院,上海交通大学医学院附属儿童医院耳鼻咽喉头颈外科(上海,200062)
- 2. 南方医科大学深圳医院儿童耳鼻咽喉科
- 3. 上海市儿童医院,上海交通大学医学院附属儿童医院临床研究中心
- 4. 郑州大学附属儿童医院/河南省儿童医院/郑州儿童医院耳鼻咽喉头颈外科
- 5. 华中科技大学同济医学院附属武汉儿童医院(武汉市妇幼保健院)耳鼻咽喉头颈外科
- 6. 温州医科大学附属第二医院耳鼻咽喉头颈外科
- 7. 昆明市儿童医院,昆明医科大学附属儿童医院耳鼻咽喉头颈外科
- 8. 安阳市妇幼保健院耳鼻咽喉头颈外科
- 9. 厦门市儿童医院耳鼻咽喉头颈外科
- 10. 天津市儿童医院/天津大学儿童医院耳鼻咽喉科
- 11. 山西省儿童医院耳鼻咽喉科,山西省妇幼保健院
- 12. 四川省妇幼保健院耳鼻咽喉头颈外科
- 13. 重庆医科大学附属儿童医院耳鼻咽喉头颈外科,国家儿童健康与疾病临床研究中心,儿童发育与疾病教育部重点实验室,重庆市结构性出生缺陷与重建重点实验室
- 14. 江南大学附属儿童医院(无锡市儿童医院)耳鼻咽喉头颈外科
- 15. 大连市妇女儿童医疗中心(集团)耳鼻咽喉头颈外科
- 16. 湖南省儿童医院耳鼻咽喉头颈外科
- 折叠
摘要
目的:儿童扁桃体术后出血是一种严重且可能危及生命的并发症,本研究旨在通过一项全国多中心回顾性研究来构建儿童扁桃体术后出血的风险预警模型,为儿童扁桃体术后分层管理提供依据.方法:通过对2022年1月15日-2023年5月15日从不同省份的15个研究中心接受全身麻醉下行扁桃体切除术的8 854例患儿进行分层抽样后得到,本研究样本量2 724例,其中男1 096例,女1 628例.根据术后患儿有无出血分为出血组与未出血组,采用随机森林算法构建风险预警模型,通过不断探寻最优化模型,提高预测儿童扁桃体术后出血率的准确性,并通过十折交叉验证模型的预测效能.结果:2 724例患儿中有117例扁桃体术后出血,出血率为4.30％.采用随机森林算法针对训练集构建的模型在测试集中予以验证,得出的预测准确率为98.72％,召回率为78.95％,ROC曲线下面积(AUC)为0.96.结论:随机森林模型虽然召回率有待提高,但整体准确性相当出色,能有效地避免将阳性病例误判为阴性病例,是一种可以被用来预测扁桃体术后出血率和临床医疗决策的有用工具,为后续优化提升奠定了良好基础.
Abstract
Objective:Hemorrhage after tonsil surgery in children is a serious and potentially life-threatening complication.The purpose of this study was to establish a risk warning model for hemorrhage after tonsil surgery in children through a national multi-center retrospective study,providing a basis for hierarchical management after tonsil surgery in children.Methods:Stratified sampling was performed on 8 854 children who underwent tonsillec-tomy under general anesthesia from 15 research centers in different provinces from January 15,2022 to May 15,2023.The sample size of this study was 2 724 cases,including 1 096 males and 1 628 females.Children were di-vided into bleeding and non-bleeding groups according to whether or not they had bleeding after surgery.The ran-dom forest algorithm was used to build a risk warning model.By continuously exploring the optimized model,the accuracy of predicting the postoperative bleeding rate of tonsils in children was improved,and the prediction effec-tiveness of the model was verified by ten-fold cross-validation.Results:Among 2 724 children,117 had postopera-tive bleeding after tonsillectomy,with a bleeding rate of 4.30％.The model constructed by the random forest al-gorithm for the training set was verified in the test set,and the obtained prediction accuracy was 98.72％,the re-call rate was 78.95％,and the area under the ROC curve AUC was 0.96.Conclusion:Although the recall rate of the random forest model needs to be improved,the overall accuracy is quite excellent.It can effectively avoid mis-judging positive cases as negative cases.It is a useful tool that can be used to predict the postoperative bleeding rate of tonsils and clinical medical decision-making,laying a good foundation for subsequent optimization and im-provement.
关键词
儿童/扁桃体切除术/术后出血/多中心/随机森林/预测Key words
children/tonsillectomy/postoperative bleeding/multi center/random forest/forecast引用本文复制引用
出版年
2024
NETL
NSTL
万方数据