整合多模态数据的ERCP术后胰腺炎预测系统的多步骤验证:一项多中心研究
本研究回顾性收集多中心1916例ERCP病例,构建并验证整合多模态数据的预测模型。逐步加入技术操作和预防策略特征后,模型4的敏感性和特异性较模型2显著提高。最终模型8采用随机森林算法表现最佳,图像和技术特征对PEP预测至关重要。
要点
- 多模态预测模型整合基线、诊断、技术、预防策略及图像特征。
- 加入技术和预防策略特征后模型4敏感性63.89% vs 模型2的83.33%,特异性75.00% vs 85.92%。
- 模型8采用随机森林算法表现最佳,图像特征权重最高。
核心结论
- 首次开发了用于识别PEP的多模态预测模型,具有临床可接受的性能。
- 图像和技术特征对PEP预测至关重要。
研究设计与样本
- 回顾性收集多中心1916例ERCP病例用于模型构建。
- 通过文献研究确定49个电子健康记录特征和1个图像特征。
- 特征分为基线、诊断、技术、预防策略四类,覆盖ERCP术前、术中及围手术期。
- 逐步构建模型1至4(加入四类特征),再将图像特征加入模型1至4形成模型5至8。
- 使用内部和外部测试集对所有模型进行测试和比较,选择最优模型后比较多种机器学习算法。
主要发现
- 模型4(加入技术和预防策略)较模型2(仅基线和诊断)敏感性提高(63.89% vs 83.33%,P < .05),特异性提高(75.00% vs 85.92%,P < .001)。
- 内部和外部测试中观察到相似趋势。
- 模型4中权重排名前3的特征为既往胰腺炎、非甾体抗炎药使用和插管困难。
- 图像特征在模型5至8中权重最高。
- 模型8采用随机森林算法表现最佳。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND AND AIMS: The impact of various categories of information on the prediction of post-ERCP pancreatitis (PEP) remains uncertain. We comprehensively investigated the risk factors associated with PEP by constructing and validating a model incorporating multimodal data through multiple steps. METHODS: Cases (n = 1916) of ERCP were retrospectively collected from multiple centers for model construction. Through literature research, 49 electronic health record (EHR) features and 1 image feature related to PEP were identified. The EHR features were categorized into baseline, diagnosis, technique, and prevention strategies, covering pre-ERCP, intra-ERCP, and peri-ERCP phases. We first incrementally constructed models 1 to 4 incorporating these 4 feature categories and then added the image feature into models 1 to 4 and developed models 5 to 8. All models underwent testing and comparison using both internal and external test sets. Once the optimal model was selected, we conducted comparisons among multiple machine learning algorithms. RESULTS: Compared with model 2 that incorporated baseline and diagnosis features, adding technique and prevention strategies (model 4) greatly improved the sensitivity (63.89% vs 83.33%, P < .05) and specificity (75.00% vs 85.92%, P < .001). A similar tendency was observed in the internal and external tests. In model 4, the top 3 features ranked by weight were previous pancreatitis, nonsteroidal anti-inflammatory drug use, and difficult cannulation. The image-based feature has the highest weight in models 5 to 8. Finally, model 8 used a random forest algorithm and showed the best performance. CONCLUSIONS: We first developed a multimodal prediction model for identifying PEP with a clinical-acceptable performance. The image and technique features are crucial for PEP prediction.
引用
- Xu Y, Dong Z, Huang L, et al. Multistep validation of a post-ERCP pancreatitis prediction system integrating multimodal data: a multicenter study. Gastrointest Endosc. 2024. PMID: 38583541. doi:10.1016/j.gie.2024.03.033
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。