重症监护病房中合并恶性肿瘤的高龄脓毒症患者短期病死率研究

Short-term mortality in elderly sepsis patients with malignant tumors in the intensive care unit

目的:分析恶性肿瘤是否为重症监护病房(ICU)中高龄脓毒症患者短期病死率的独立危险因素,探索该类患者序贯器官衰竭评估(SOFA)评分与短期病死率的剂量反应关系。方法:回顾性分析2008—2019年重症监护医疗信息市场(MIMIC-Ⅳ)数据库中80岁及以上高龄脓毒症患者资料,根据患者是否合并恶性肿瘤分为肿瘤组与非肿瘤组,比较两组患者基线数据及预后。根据患者入ICU后28 d生存情况分为存活组和死亡组,比较两组患者基线数据,采用Logistic回归分析短期病死率的危险因素。采用概率单位回归拟合SOFA评分与短期病死率的剂量反应关系。结果:共筛选53150份医疗记录,纳入5126例80岁及以上高龄脓毒症患者,其中754例合并恶性肿瘤,264例为转移性肿瘤。肿瘤组患者28 d病死率显著高于非肿瘤组[26.79%(202/754)比18.85%(824/4372),χ^(2)=24.85,P<0.001]。短期病死率的Logistic回归分析结果显示,年龄(OR=1.073、95%CI:1.040~1.108,P<0.001)、除肿瘤外的查尔森合并症指数(CCI)(OR=1.134、95%CI:1.067~1.205,P<0.001)、入ICU血乳酸(OR=1.111、95%CI:1.048~1.179,P<0.001)、机械通气(OR=1.603、95%CI:1.176~2.187,P=0.003)、SOFA评分(OR=1.227、95%CI:1.182~1.273,P<0.001)是短期病死率的危险因素,CCI(OR=0.957、95%CI:0.867~1.057,P=0.380)、使用血管活性药物(OR=1.370、95%CI:0.902~2.081,P=0.140)、合并恶性肿瘤(OR=1.131、95%CI:0.449~2.848、P=0.794)及恶性肿瘤转移(OR=1.799、95%CI:0.930~3.477,P=0.081)则与短期病死率无相关性。剂量反应曲线结果显示,随着SOFA评分的增加,患者的28 d病死率增加,且SOFA评分达到11分时预期病死率达到50%,SOFA评分达到20分时预期病死率超过80%。结论:恶性肿瘤和肿瘤转移均不是ICU中高龄脓毒症患者短期病死率的独立危险因素,该类患者短期病死率与SOFA评分呈剂量反应关系。

Objective To investigate whether malignant tumors are an independent risk factor for short-term mortality in elderly patients with sepsis in the intensive care unit(ICU),and to examine the dose-response relationship between the sequential organ failure assessment(SOFA)score and short-term mortality in this patient population.Methods A retrospective analysis was conducted on elderly sepsis patients aged 80 and above from the Medical Information Mart for Intensive Care(MIMIC-Ⅳ)database spanning from 2008 to 2019.The patients were categorized into a tumor group and a non-tumor group based on the presence of malignant tumors,and a comparison was made between the baseline data and prognosis of these two groups.Furthermore,patients were classified into survival and mortality groups based on their ICU survival status within 28 days,and a comparison of baseline data was performed.Logistic regression analysis was employed to identify the risk factors associated with short-term mortality.Additionally,probability unit regression was utilized to model the dose-response relationship between the SOFA score and short-term mortality.Results A total of 53150 medical records were screened,identifying 5126 elderly sepsis patients aged 80 and above.Among them,754 had malignant tumors and 264 had metastatic tumors.The 28-day mortality rate in the tumor group was significantly higher than in the non-tumor group[26.79%(202/754)vs.18.85%(824/4372),χ^(2)=24.85,P<0.001].Logistic regression analysis revealed age(OR=1.073,95%CI:1.040-1.108,P<0.001),Charlson comorbidity index(CCI)excluding tumors(OR=1.134,95%CI:1.067-1.205,P<0.001),blood lactate concentration at ICU admission(OR=1.111,95%CI:1.048-1.179,P<0.001),mechanical ventilation(OR=1.603,95%CI:1.176-2.187,P=0.003),and SOFA score(OR=1.227,95%CI:1.182-1.273,P<0.001)as risk factors for short-term mortality.Conversely,CCI(OR=0.957,95%CI:0.867-1.057,P=0.380),use of vasoactive drugs(OR=1.370,95%CI:0.902-2.081,P=0.140),malignant tumors(OR=1.131,95%CI:0.449-2.848,P=0.794),and metastasis of malignant tumors(OR=1.799,95%CI:0.930-3.477,P=0.081)were not associated with short-term mortality.The dose-response curve illustrated that as the SOFA score increased,patients'28-day mortality rate also rose,reaching 50%at a SOFA score of 11 and exceeding 80%at a score of 20.Conclusions Malignant tumors and tumor metastasis do not appear to be independent risk factors for short-term mortality in elderly sepsis patients in the ICU.Instead,the short-term mortality rate of these patients seems to be correlated with the SOFA score in a dose-response manner.