疑似心衰患者NT-proBNP与临床特征的个体化评估:PRECISE-HF研究
PRECISE-HF研究基于英国CPRD初级保健数据,纳入535 583例因临床怀疑心衰而检测NT-proBNP的患者,开发并验证了整合NT-proBNP与年龄、肾功能、BMI、房颤史等临床特征的XGBoost机器学习模型。模型在内部验证中AUROC为0.896,排除阈值灵敏度90.1%、阴性预测值98.5%,可排除64.8%的患者;纳入阈值特异度90.0%、阳性预测值44.1%。与ESC通用阈值相比,该个体化方法每1000人可多排除144例,代价为漏诊3例,纳入时减少73例假阳性。
要点
- PRECISE-HF整合NT-proBNP与年龄、eGFR、BMI、房颤史等变量,个体化判定心衰概率。
- 排除阈值灵敏度90.1%、阴性预测值98.5%,可安全排除64.8%的疑似患者。
- 与ESC阈值相比每1000人多排除144例,仅增加3例漏诊,减少73例假阳性。
核心结论
- PRECISE-HF模型整合多种临床特征与NT-proBNP,在社区疑似心衰患者中诊断性能优于通用排除阈值和年龄校正纳入阈值。
- 该个体化方法可能使最可能患心衰的患者更早接受确诊检查和改善预后的药物治疗。
研究设计与样本
- 队列研究,2018年1月1日至2025年3月31日,使用英国CPRD初级保健数据,共纳入535 583例因临床怀疑心衰检测NT-proBNP且无心衰史的患者。
- 患者随机分为推导队列(n=374 909)和内部验证队列(n=160 674),采用XGBoost机器学习建模,并在瑞典REVOLUTION-HF队列进行外部验证。
- 心衰诊断定义为NT-proBNP检测后12个月内的初级保健诊断或心衰住院。
主要发现
- 验证队列中10%的患者记录有心衰诊断。
- 内部验证中模型AUROC为0.896,Brier评分为0.061。
- 外部验证中模型AUROC为0.757,Brier评分为0.163。
- 与ESC阈值相比,PRECISE-HF每1000人可多排除144例患者,代价为漏诊3例,纳入时减少73例假阳性。
关键数值与推荐
- 排除阈值灵敏度90.1%,阴性预测值98.5%,可排除64.8%的患者。
- 纳入阈值特异度90.0%,阳性预测值44.1%,可纳入16.1%的患者。
- 模型纳入变量包括NT-proBNP、年龄、性别、种族、eGFR、BMI、收缩压、贫血、袢利尿剂处方及房颤、糖尿病、心肌梗死、COPD病史。
- 排除和纳入阈值分别基于≥90%的灵敏度和特异度确定。
临床怎么用
- 对于心衰可能性低的疑似患者,可使用PRECISE-HF排除阈值安全避免不必要的超声心动图转诊。
- 对于模型判定心衰概率高的患者,可优先安排确诊检查和启动疾病修正治疗。
- 临床应用时需注意外部验证中模型校准有所下降(Brier评分0.163),可能需要本地化调整。
局限性
- 外部验证中AUROC由0.896降至0.757,Brier评分由0.061升至0.163,提示跨人群泛化能力有限。
- 心衰诊断基于初级保健记录或住院数据,可能存在漏诊或误分类。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND AND AIMS: N-terminal pro-B-type natriuretic peptide (NT-proBNP) is recommended to guide echocardiography referral in community-based patients with suspected heart failure (HF), but diagnostic performance is influenced by individual characteristics including age, ethnicity, kidney function, cardiac rhythm, and body mass index (BMI). An individualised probabilistic approach may have superior diagnostic performance to guideline-recommended universal thresholds. This study aimed to develop and validate the PRECISE-HF model to provide probabilistic rule-out and rule-in thresholds based on NT-proBNP and relevant clinical characteristics. METHODS: Cohort study performed from January 1, 2018 to March 31, 2025, using primary care data from the Clinical Practice Research Datalink (CPRD), broadly representative of the UK population. Patients were included if they had an NT-proBNP measured due to clinical suspicion of HF with no known history of HF. HF diagnosis was recorded as a primary care diagnosis or HF hospitalisation within 12 months of NT-proBNP measurement. Using XGBoost machine learning, the probability of HF was modelled incorporating NT-proBNP alongside age, sex, ethnicity, estimated glomerular filtration rate, BMI, systolic blood pressure, anaemia, loop diuretic prescription and history of atrial fibrillation, diabetes, myocardial infarction and chronic obstructive pulmonary disease. Rule-out and rule-in thresholds were identified based on ≥90% sensitivity and specificity, respectively, and compared to current European Society of Cardiology (ESC) recommendations. External validation was performed in the REVOLUTION-HF Swedish cohort. RESULTS: Overall, 535 583 patients were included, randomly split into derivation (n=374 909) and internal validation (n=160 674) cohorts. A HF diagnosis was recorded in 10% of the validation cohort. The PRECISE-HF model demonstrated excellent discrimination (area under the receiver operating characteristic curve [AUROC] 0.896) and calibration (Brier score 0.061). The rule-out threshold had a sensitivity of 90.1% and a negative predictive value of 98.5%, ruling out 64.8% of patients. The rule-in threshold ruled in 16.1% with a specificity of 90.0% and a positive predictive value of 44.1%. Compared to the ESC thresholds, PRECISE-HF13 ruled out 144 additional patients per 1000 at the expense of three missed diagnoses, with 73 fewer false positives per 1000 at rule-in. In external validation, the model retained good discrimination (AUROC 0.757) and calibration (Brier score 0.163). CONCLUSIONS: The PRECISE-HF model, integrating multiple clinical characteristics with NT-proBNP, demonstrated superior diagnostic performance compared with universal rule-out and age-adjusted rule-in thresholds in community-based patients with suspected HF. This individualised approach may enable earlier confirmatory testing and initiation of disease-modifying treatment in those most likely to have HF.
引用
- Docherty, Heywood, Anderson, et al. Personalized evaluation of NT-proBNP and clinical characteristics in suspected heart failure: the PRECISE-HF study. Eur Heart J. 2026. PMID: 42663089. doi:10.1093/eurheartj/ehag686
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。