通讯作者: 胡欣, 375389606@qq.com

DOI：10.12201/bmr.202501.00053

Construction and application evaluation of risk prediction model and nomogram for shivering during cesarean sectio

• 摘要：目的 构建剖宫产手术患者术中寒战风险预测模型并验证模型的预测效果。方法 选取温州医科大学附属第二医院2023年1月—2023年4月期间住院行剖宫产手术的患者为研究对象,将发生术中寒战患者(101例)和未发生术中寒战患者(124例)的相关影响因素进行对比,纳入有差异指标进行模型构建,使用AUC、十折交叉验证等指标或手段,对模型进行评价和验证,并绘制预测模型的受试者操作特征曲线及列线图。结果 纳入既往糖尿病史、术前S-AI评分、麻醉方式3个因素构建预测模型。该模型ROC曲线下面积为0.799,P值小于0.001,十折内部交叉验证得出的最大AUC值为0.925,提示模型具有较好的拟合效果及鉴别效度。结论 该模型能较好地预测剖宫产术期间产妇寒战的发生风险,为医护人员及时对高危产妇采取预防性管理措施提供参考。

  关键词： 剖宫产; 寒战; 预测模型; S-AI评分

   

  Abstract: Abstract: Objective To develop and validate a predictive model for the risk of shivering during cesarean section surgery. Methods This study selected women who underwent cesarean sections at our hospital from January 2023 to April 2023 as research subjects. The study compared the relevant influencing factors between patients who experienced intraoperative shivering (n=101) and those who did not (n=124). Various indicators were incorporated into the model construction, and the model was evaluated using metrics such as the Area Under the Curve (AUC) and ten-fold cross-validation. The receiver operating characteristic (ROC) curve and nomogram of the prediction model were also generated. Results Five factors were included in the final prediction model: history of diabetes mellitus, preoperative Simplified Acute Physiology Score (SAPS), anesthesia method, post-anesthesia hypothermia, and intraoperative warming measures. The area under the ROC curve for this model was 0.831 (P < 0.001), with an internal ten-fold cross-validation AUC of up to 0.934, indicating that the model exhibits excellent fitting and discrimination performance. Conclusion The developed model can effectively predict the risk of shivering during cesarean sections, providing valuable guidance for healthcare professionals to implement timely preventive measures for high-risk patients.

  Key words: Cesarean section; shivering; Prediction model; S-AI score

  提交时间：2025-01-19

  版权声明：作者本人独立拥有该论文的版权，预印本系统仅拥有论文的永久保存权利。任何人未经允许不得重复使用。
• html

• 图表

• 陈冰融, 舒文秀, 罗柳飞, 童嘉琦, 乐静. 骨髓瘤患者发生3-4级骨髓瘤骨病的风险预测模型构建. 2024. doi: 10.12201/bmr.202410.00057

  施明杰, 叶洪舟, 袁琛. 大环内酯类耐药肺炎支原体肺炎患儿发展为重症肺炎的危险因素分析及预测模型构建. 2024. doi: 10.12201/bmr.202409.00021

  韦云师, 莫伟, 向娅, 廖秋姣, 何柳, 凌朝灵, 陆启祥, 刘芳印. 老年髋部骨折患者术后谵妄风险预测模型的研究进展. 2024. doi: 10.12201/bmr.202409.00029

  阮旭凌, 刘琦, 郭志恒, 晏峻峰. 基于LDA和XGBoost算法的乳腺癌预测模型构建研究. 2022. doi: 10.12201/bmr.202106.00007

  王一凡, 石超君, 马安宁. Ⅱ型糖尿病并发动脉粥样硬化风险预测模型比较. 2024. doi: 10.12201/bmr.202404.00007

  张二利, 何兰兰, 李丹阳, 沈立, 吴钟华, 张军, 叶永强. 基于脑小血管病影像学总负荷的急性脑梗死患者住院时间延长列线图模型构建与验证. 2025. doi: 10.12201/bmr.202501.00008

  杜雪杰, 葛辉. 基于BP神经网络方法构建手足口病预测预警模型设计研究. 2021. doi: 10.12201/bmr.202102.00002

  唐诗诗, 李宇轩, 唐圣晟, 刘庆华, 周毅. 基于SARIMA-LSTM模型的肾综合征出血热发病率预测研究. 2024. doi: 10.12201/bmr.202407.00046

  黄山, 王延照. 基于集聚度和GM（1,1）的安徽省卫生管理人员资源配置公平性及需求预测研究. 2024. doi: 10.12201/bmr.202410.00075

  许峻川, 费琦. BFH-OST和OSTA对于绝经后妇女骨质疏松风险预测的对比性研究. 2024. doi: 10.12201/bmr.202407.00019

• 序号	提交日期	编号	操作
  1	2024-11-25	bmr.202501.00053V1	下载

• 公开评论  匿名评论  仅发给作者 提交评论