西南医科大学学报2025，Vol.48Issue(5)：486-490,5.DOI:10.3969/j.issn.2096-3351.2025.05.008
重症社区获得性肺炎患者死亡风险预测列线图的构建与验证
Development and Validation of a Nomogram for Predicting Mortality Risk in Patients with Severe Community-Acquired Pneumonia
摘要
Abstract
Objective This study aimed to develop and validate a nomogram model based on multivariate analysis for predicting 28-day mortality risk in patients with severe community-acquired pneumonia(CAP),providing a tool for individualized mortality risk assessment.Methods A total of 300 patients diagnosed with severe CAP between January 2023 and August 2024 were included in this study,randomly divided into a training set(210 cases)and a validation set(90 cases)at a 7∶3 ratio.Significant variables associated with mortality risk were identified in the training set through univariate analysis,including age,diabetes,chronic obstructive pulmo-nary disease(COPD),C-reactive protein(CRP)levels,oxygenation index,D-dimer,albumin levels,serum lactate,ICU admission status,and multidrug-resistant bacterial infection.Multivariable logistic regression analysis was performed to determine independent prognostic factors.A nomogram model was constructed based on the results of the multivariable analysis.The model's discrimination ability was evaluated using receiver operating characteristic(ROC)curves and the area under the curve(AUC),while the C-index and calibration curve were used to verify its predictive performance.The validation set was used to assess the model's generalizability.Results Univariate analysis showed that age,diabetes,COPD,CRP levels,oxygenation index,D-dimer,albumin levels,serum lac-tate,ICU admission,and multidrug-resistant bacterial infection were significantly associated with the 28-day mortality risk(P<0.05).Multivariate logistic regression analysis identified diabetes(OR=2.42,95%CI∶1.35～4.45,P=0.003),COPD(OR=2.80,95%CI∶1.58～4.95,P<0.001),age(OR=1.74,95%CI∶1.10～2.76,P=0.021),and oxygenation index(OR=0.48,95%CI∶0.29～0.80,P=0.009)as independent predictors of mortality.The AUC of the nomogram model was 0.84(95%CI∶0.78～0.90)in the training set and 0.81(95%CI∶0.73～0.89)in the validation set.The calibration curve showed high concordance between the pre-dicted and actual 28-day mortality rates.Conclusion The nomogram model developed in this study effectively predicted the 28-day mortality risk in patients with severe CAP,providing clinicians with a practical tool for individualized risk assessment.The model dem-onstrated good discriminative power and calibration in both the training and validation sets.关键词
社区获得性肺炎/28天死亡率/列线图/重症监护病房/死亡风险Key words
Community-acquired pneumonia/28-day mortality/Nomogram/ICU/Mortality risk分类
医药卫生引用本文复制引用
何凤珍,杨小花,高新愿,臧树志..重症社区获得性肺炎患者死亡风险预测列线图的构建与验证[J].西南医科大学学报,2025,48(5):486-490,5.基金项目
河南省医学科技攻关计划项目(LHGJ20220624) （LHGJ20220624）
