Wei Shuxing, Dong Hongmeng, Yao Weidong, Chen Ying, Wang Xiya, Ji Wenqing, Zhang Yongsheng, Guo Shubin
Emergency Medicine Clinical Research Center, Beijing Key Laboratory of Cardiopulmonary Cerebral Resuscitation, Beijing Chaoyang Hospital, Affiliated to Capital Medical University, Beijing, 100020, China.
Department of Anesthesiology, Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine, Jinan, China.
BMC Med Inform Decis Mak. 2025 May 27;25(1):198. doi: 10.1186/s12911-025-03033-4.
Acute pancreatitis (AP) represents a critical medical condition where timely and precise prediction of in-hospital mortality is crucial for guiding optimal clinical management. This study focuses on the development of advanced machine learning (ML) models to accurately predict in-hospital mortality among AP patients admitted to intensive care unit (ICU).
Our study utilized data from three distinct sources: the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV databases, and Beijing Chaoyang Hospital. We systematically developed and evaluated 11 distinct machine learning (ML) models, employing a comprehensive set of evaluation metrics to assess model performance, including the area under the curve (AUC). To enhance interpretability and identify key predictive features, we implemented Shapley Additive Explanations (SHAP) analysis for the top-performing model. Furthermore, we developed a streamlined version of the model through strategic feature reduction, followed by rigorous hyperparameter optimization (HPO) to maximize predictive performance. To facilitate clinical implementation, we designed and deployed an intuitive web-based calculator, enabling convenient access and practical application of our optimized predictive model.
The study analyzed 1802 AP patients, with 266 (14.8%) experiencing in-hospital mortality. A set of 27 features was utilized to construct various models, and among them, CatBoost demonstrated the highest performance in both the validation and test sets. To create a more concise model, we selected the top 13 features. After HPO, the AUC in the test set reached 0.835 (95% CI: 0.793-0.872), the AUC in the external validation from Beijing Chaoyang hospital was 0.782 (95% CI: 0.699-0.860).
ML models have shown promising reliability in predicting in-hospital mortality among patients with AP in the ICU. Among these models, the CatBoost model exhibits superior predictive performance, providing valuable assistance to clinical practitioners in identifying high-risk patients and facilitating early interventions to enhance prognosis. The development of a compact model and a web-based calculator further enhances the convenience of using these models in clinical practice.
急性胰腺炎（AP）是一种危急病症，及时、准确地预测院内死亡率对于指导最佳临床管理至关重要。本研究聚焦于开发先进的机器学习（ML）模型，以准确预测入住重症监护病房（ICU）的AP患者的院内死亡率。
我们的研究使用了来自三个不同来源的数据：重症监护医学信息集市III（MIMIC-III）、MIMIC-IV数据库和北京朝阳医院。我们系统地开发并评估了11种不同的机器学习（ML）模型，采用一套综合评估指标来评估模型性能，包括曲线下面积（AUC）。为提高可解释性并识别关键预测特征，我们对表现最佳的模型实施了Shapley值加法解释（SHAP）分析。此外，我们通过策略性特征约简开发了模型的简化版本，随后进行严格的超参数优化（HPO）以最大化预测性能。为便于临床应用，我们设计并部署了一个直观的基于网络的计算器，使我们优化后的预测模型能够便捷访问和实际应用。
该研究分析了1802例AP患者，其中266例（14.8%）发生院内死亡。利用一组27个特征构建各种模型，其中CatBoost在验证集和测试集中均表现出最高性能。为创建更简洁的模型，我们选择了前13个特征。经过HPO后，测试集中的AUC达到0.835（95%CI：0.793 - 0.872），北京朝阳医院外部验证中的AUC为0.782（95%CI：0.699 - 0.860）。
ML模型在预测ICU中AP患者的院内死亡率方面显示出有前景的可靠性。在这些模型中，CatBoost模型表现出卓越的预测性能，为临床医生识别高危患者并促进早期干预以改善预后提供了有价值的帮助。紧凑模型和基于网络的计算器的开发进一步提高了这些模型在临床实践中的使用便利性。
