基于XGBoost的多组学模型预测胰腺癌ICU患者脓毒症相关急性肾损伤及个体化免疫治疗疗效的单中心研究
本研究为单中心混合回顾-前瞻性队列研究,纳入2020年1月至2024年12月523例胰腺癌ICU患者(回顾性366例,前瞻性157例),整合临床数据、实验室指标、NK细胞活性、TCR测序及NK细胞scRNA-seq数据,构建XGBoost SA-AKI预测模型。模型训练队列AUC为0.959(95%CI 0.938-0.979),内部验证AUC为0.923。关键预测生物标志物包括APACHE II评分、TCR克隆性、NK细胞活性、NK细胞IFN-γ表达和CRP。风险分层显示低/中/高危亚组在治疗反应率、28天ICU转出率和90天死亡率上存在显著差异。个体化免疫治疗显著改善中/高危患者总生存(中位OS:172/98天 vs 对照组115/65天,p<0.001)。
要点
- XGBoost多组学模型在胰腺癌ICU患者中预测SA-AKI的AUC为0.959(95%CI 0.938-0.979),内部验证AUC为0.923。
- 关键预测生物标志物按SHAP值排序:APACHE II评分(0.606)、TCR克隆性(0.504)、NK细胞活性(0.425)、NK细胞IFN-γ表达(0.398)、CRP(0.161)。
- 低/中/高危亚组治疗反应率分别为82.1%、52.4%、34.2%,28天ICU转出率分别为85.9%、69.5%、41.6%,90天死亡率分别为25.9%、47.4%、71.2%(均p<0.001)。
- 中/高危患者接受个体化免疫治疗(NK细胞输注±TCR-T)的中位OS为172/98天,对照组为115/65天(p<0.001)。
- 应答者治疗后NK细胞活性升高39%、TCR克隆性升高25%(p<0.001);应答者功能性NK细胞(IFN-γ+GZMB+)比例高于非应答者(36.0% vs 13.9%,p<0.001)。
适用人群与场景
- 胰腺癌并收入ICU的患者,共523例(回顾性366例,前瞻性157例),研究时间2020年1月至2024年12月。
- 单中心研究人群,作者指出未来需多中心前瞻性研究验证模型并提高其在不同患者群体中临床应用的可推广性。
诊断标准与关键阈值
- 风险分层分为低/中/高危亚组,用于指导个体化免疫治疗(NK细胞输注±TCR-T治疗)。
处置流程与药物剂量
- 根据XGBoost模型风险分层(低/中/高危)指导个体化免疫治疗:NK细胞输注±TCR-T治疗。
- 动态监测NK细胞活性和TCR克隆性可作为治疗疗效的替代指标。
研究设计与关键结果
- 研究类型:单中心混合回顾-前瞻性队列研究,纳入523例胰腺癌ICU患者(回顾性366例,前瞻性157例),时间2020年1月至2024年12月。
- 模型性能:训练队列AUC 0.959(95%CI 0.938-0.979),AUPRC 0.946;内部验证AUC 0.923,AUPRC 0.905。
- 关键预测生物标志物(平均绝对SHAP值):APACHE II评分0.606、TCR克隆性0.504、NK细胞活性0.425、NK细胞IFN-γ表达0.398、CRP 0.161。
- 风险分层结果:低/中/高危亚组治疗反应率82.1% vs 52.4% vs 34.2%,28天ICU转出率85.9% vs 69.5% vs 41.6%,90天死亡率25.9% vs 47.4% vs 71.2%(均p<0.001)。
- 个体化免疫治疗中/高危患者中位OS:172/98天 vs 对照组115/65天(p<0.001)。
- 应答者治疗后NK细胞活性升高39%、TCR克隆性升高25%(p<0.001)。
- NK细胞scRNA-seq识别功能性(IFN-γ+GZMB+)、耗竭性(PD-1+)和初始亚群,应答者功能性NK细胞比例36.0% vs 非应答者13.9%(p<0.001)。
证据类型、等级与局限
- 证据类型:单中心混合回顾-前瞻性队列研究。
- 局限:原文未报告局限性(原文在背景中提及未来需多中心前瞻性研究验证模型并提高可推广性)。
对床旁实践的改变
- 基于XGBoost的多组学模型可用于胰腺癌ICU患者SA-AKI的预测和风险分层。
- 风险分层的个体化免疫治疗(NK细胞输注±TCR-T)可能改善中/高危患者临床结局(作者结论)。
- 动态监测NK细胞活性/TCR克隆性可作为治疗疗效的替代指标(作者结论)。
- 作者认为该研究为这一高危单中心人群的SA-AKI管理提供了新的临床决策路径。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Sepsis-associated acute kidney injury (SA-AKI) is a highly prevalent and lethal complication in pancreatic cancer patients admitted to the intensive care unit (ICU), characterized by complex pathophysiology involving tumor-induced inflammation and immune dysfunction. Traditional prediction models lack specificity for this population, and targeted therapeutic strategies remain limited.Future multi-center prospective studies will further validate the model and improve its generalizability for clinical application in diverse patient populations.
METHODS: We conducted a single-center mixed retrospective-prospective cohort study involving 523 pancreatic cancer ICU patients (366 retrospective, 157 prospective) between January 2020 and December 2024. Clinical data, laboratory indices, natural killer (NK) cell activity, T-cell receptor (TCR) sequencing, and NK cell single-cell RNA sequencing (scRNA-seq) data were integrated. The XGBoost algorithm was used to construct a SA-AKI prediction model,with performance evaluated via area under the receiver operating characteristic curve (AUC),precision-recall curve (AUPRC), calibration curve, decision curve analysis (DCA), and Brierscore. SHAP (SHapley Additive exPlanations) analysis identified key biomarkers. Risk stratification (low/medium/high-risk) guided personalized immune therapy (NK cell infusion ± TCR-T therapy). Primary endpoints included 28-day ICU discharge rate, 90-day mortality, and overall survival (OS); secondary endpoints included biomarker dynamic changes and treatmentresponse.
RESULTS: The XGBoost model achieved an AUC of 0.959 (95% CI: 0.938-0.979) and AUPRC of 0.946 in the training cohort, with consistent performance in internal validation (AUC=0.923, AUPRC=0.905). Key predictive biomarkers included APACHE II score (mean absolute SHAP value=0.606), TCR clonality (0.504), NK cell activity (0.425), IFN-γ expression in NK cells (0.398), and CRP (0.161). Risk stratification revealed significant differences in responserates (82.1% vs. 52.4% vs. 34.2%), 28-day ICU discharge rates (85.9% vs. 69.5% vs. 41.6%),and 90-day mortality (25.9% vs. 47.4% vs. 71.2%) across low/medium/high-risk subgroups (all p<0.001). Personalized immune therapy significantly improved OS in medium/high-risk patients (median OS: 172/98 days vs. 115/65 days in controls, p<0.001). Dynamic monitoringshowed that NK cell activity (increase by 39%) and TCR clonality (increase by 25%) were significantly elevated post-treatment in responders (p<0.001). NK cell scRNA-seq identified functional (IFN-γ+GZMB+), exhausted (PD-1+), and naive subgroups, with higher functional NK cell proportion in responders (36.0% vs. 13.9%, p<0.001).
CONCLUSIONS: The XGBoost-based multi-omics model enables accurate SA-AKI prediction and risk stratification in pancreatic cancer ICU patients. Risk-stratified personalized immune therapy improves clinical outcomes, and dynamic monitoring of NK cell activity/TCR clonalityserves as a surrogate for therapeutic efficacy. This study provides a novel clinical decision-making pathway for SA-AKI management in this high-risk single-center population.
参考来源
- Long Z, Fu Y, Wang S, et al. A Single-Center Study: XGBoost-Based Multi-Omics Prediction Model for Sepsis-Associated Acute Kidney Injury (SA-AKI) and Personalized Immune Therapy Efficacy in Pancreatic Cancer ICU Patients. Shock. 2026. PMID: 42008769. doi:10.1097/SHK.0000000000002859
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。