一个预测模型的二次性桃体切除术后出血在儿科患者:一个8年的回顾性研究
Yuting Ge1, Wenchuan Chang1, Lixiao Xie1
1Department of Otolaryngology Children's Hospital of Soochow University Suzhou Jiangsu China.
Laryngoscope investigative otolaryngology
|January 16, 2025
概括
这项研究开发了一种机器学习模型,用于预测儿童桃体切除术后的二次出血 (PTH). XGBoost模型准确评估了这种常见并发症的风险,有助于临床决策.
科学领域:
- 儿科耳鼻喉科 儿科耳鼻喉科
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
背景情况:
- 桃体切除术后出血 (PTH) 是小儿桃体切除术后的一个重大并发症.
- 准确预测二次PTH对于患者管理至关重要.
- 评估PTH风险的现有工具有限.
研究的目的:
- 开发和验证儿科患者中二次PTH的预测模型.
- 使用机器学习算法识别二级PTH的关键预测因素.
主要方法:
- 对492名接受桃体切除术的儿科患者进行了回顾性分析.
- 使用后勤回归和七个机器学习算法的预测模型的开发.
- 使用歧视,校准和临床效用指标进行验证; SHAP用于模型解释.
主要成果:
- XGBoost模型在预测二级PTH方面表现最好.
- SHAP方法为XGBoost模型的预测提供了特征重要性和解释.
结论:
- 一个基于机器学习的模型,特别是XGBoost,可以准确地预测儿童的二级PTH.
- 该模型为临床医生提供了一种有价值的工具,以评估和管理PTH风险.
相关概念视频
01:26Tonsillitis II: Management
103
This lesson will focus on the different treatment options for managing tonsillitis, which typically depend on the cause and severity.
103
01:23Chronic Pharyngitis
1.1K
Chronic pharyngitis refers to persistent inflammation of the pharyngial mucosa.
Etiology
It often arises from persistent viral or bacterial infections affecting sinuses and tonsils.
Additional contributing factors include inadequate dental hygiene, mouth breathing, recurring tonsillitis, allergic rhinitis, laryngopharyngeal reflux, and exposure to smoke, chemicals, and other environmental pollutants. Allergic reactions to pollen, mold, and pet dander, chronic cough, excessive voice usage,...
Etiology
It often arises from persistent viral or bacterial infections affecting sinuses and tonsils.
Additional contributing factors include inadequate dental hygiene, mouth breathing, recurring tonsillitis, allergic rhinitis, laryngopharyngeal reflux, and exposure to smoke, chemicals, and other environmental pollutants. Allergic reactions to pollen, mold, and pet dander, chronic cough, excessive voice usage,...
1.1K