通过集成机器学习提高合并恶性肿瘤的脓毒症ICU患者死亡率预测：一项回顾性队列研究
Enhancing mortality prediction in septic ICU patients with malignancies through ensemble machine learning: a retrospective cohort study.
摘要(中文译文)
脓毒症仍是重症监护病房（ICU）死亡的主要原因，而合并基础恶性肿瘤的患者受影响尤为严重。传统严重程度评分在该脆弱亚组中常难以提供充分的预后区分能力。本研究旨在利用全面的ICU数据，构建集成机器学习模型，以预测合并恶性肿瘤的脓毒症患者28天ICU死亡率和院内死亡率。在这项回顾性研究中，从MIMIC-IV数据库中提取了4312例合并恶性肿瘤的成人脓毒症患者。分析ICU第一天的临床数据。基于不同特征选择方法（LASSO、mRMR、Relief、Boruta）衍生的五个特征集，评估了九种机器学习算法。通过以高斯朴素贝叶斯为元学习器的混合集成方法组合最佳模型。应用Platt缩放进行概率校准。采用区分度（AUC）、校准度（Brier评分、校准曲线）、临床效用（决策曲线分析）和可解释性（SHAP分析）评估模型性能。详细的校准、DCA和SHAP图见补充材料。LASSO特征选择表现最佳。最终混合集成模型对28天ICU死亡率（0.753）和院内死亡率（0.777）取得了最高的预测AUC，优于单个模型和传统评分（SOFA、OASIS、APSIII、SAPSII）。Platt缩放改善了校准度，将Brier评分从0.218降至0.184（ICU 28天），从0.194降至0.163（院内）。决策曲线分析证实，在临床相关阈值概率范围内具有正向净获益。SHAP分析确定APSIII、BUN、PO2和OASIS为最重要的预测因子。生存分析显示，模型分层风险组之间差异显著（log-rank p < 0.0001）。在合并恶性肿瘤的脓毒症ICU患者中，混合集成模型在死亡率预测方面较传统严重程度评分取得了适度但具有统计学意义的改善。该模型为早期风险分层提供了一种有前景的工具，有必要开展前瞻性验证并将其整合到临床工作流程中。
Abstract
Sepsis remains a leading cause of mortality in the intensive care unit (ICU), and patients with underlying malignancies are disproportionately affected. Conventional severity scores frequently provide inadequate prognostic discrimination in this vulnerable subgroup. We aimed to develop an ensemble machine learning model to predict 28-day ICU and in-hospital mortality in septic patients with malignancies using comprehensive ICU data. In this retrospective study, 4312 adult septic patients with malignancy were extracted from the MIMIC-IV database. Clinical data from the first ICU day were analyzed. Nine machine learning algorithms were assessed across five feature sets derived from different selection methods (LASSO, mRMR, Relief, Boruta). Top models were combined via a blending ensemble with Gaussian Naive Bayes as the meta-learner. Platt scaling was applied for probability calibration. Model performance was evaluated using discrimination (AUC), calibration (Brier score, calibration curves), clinical utility (decision curve analysis), and interpretability (SHAP analysis). Detailed calibration, DCA, and SHAP figures are provided in the Supplementary Materials. LASSO feature selection performed best. The final blending ensemble model achieved the highest predictive AUCs for 28-day ICU mortality (0.753) and in-hospital mortality (0.777), outperforming individual models and traditional scores (SOFA, OASIS, APSIII, SAPSII). Platt scaling improved calibration, reducing Brier scores from 0.218 to 0.184 (ICU 28-day) and from 0.194 to 0.163 (in-hospital). Decision curve analysis confirmed positive net benefit across clinically relevant threshold probabilities. SHAP analysis identified APSIII, BUN, PO2, and OASIS as top predictors. Survival analysis showed significant differences between model-stratified risk groups (log-rank p < 0.0001). In septic ICU patients with malignancies, the blending ensemble model achieved modest but statistically significant improvements in mortality prediction over conventional severity scores. The model offers a promising tool for early risk stratification, and prospective validation together with integration into clinical workflows is warranted.
如何引用
AMA
Yongshi Shen, Wei Zhang, Chunxia Zhang, Yundan You, Kangni Lin, Peng Zheng, et al. Enhancing mortality prediction in septic ICU patients with malignancies through ensemble machine learning: a retrospective cohort study.. Scientific reports. 2026; doi:10.1038/s41598-026-62320-w.
APA
Yongshi Shen, Wei Zhang, Chunxia Zhang, Yundan You, Kangni Lin, Peng Zheng, et al (2026). Enhancing mortality prediction in septic ICU patients with malignancies through ensemble machine learning: a retrospective cohort study.. Scientific reports. https://doi.org/10.1038/s41598-026-62320-w
GB/T 7714
Yongshi Shen, Wei Zhang, Chunxia Zhang, Yundan You, Kangni Lin, Peng Zheng, et al. Enhancing mortality prediction in septic ICU patients with malignancies through ensemble machine learning: a retrospective cohort study.[J]. Scientific reports, 2026 doi:10.1038/s41598-026-62320-w.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出