Department of General Practice, Amsterdam UMC, Location Academic Medical Center, University of Amsterdam, Amsterdam, The Netherlands.
Department of Medical Informatics, Amsterdam UMC, Location Academic Medical Center, University of Amsterdam, Amsterdam, The Netherlands.
Fam Pract. 2023 Feb 9;40(1):188-194. doi: 10.1093/fampra/cmac069.
Timely diagnosis of heart failure (HF) is essential to optimize treatment opportunities that improve symptoms, quality of life, and survival. While most patients consult their general practitioner (GP) prior to HF, the early stages of HF may be difficult to identify. An integrated clinical support tool may aid in identifying patients at high risk of HF. We therefore constructed a prediction model using routine health care data.
Our study involved a dynamic cohort of patients (≥35 years) who consulted their GP with either dyspnoea and/or peripheral oedema within the Amsterdam metropolitan area from 2011 to 2020. The outcome of interest was incident HF, verified by an expert panel. We developed a regularized, cause-specific multivariable proportional hazards model (TARGET-HF). The model was evaluated with bootstrapping on an isolated validation set and compared to an existing model developed with hospital insurance data as well as patient age as a sole predictor.
Data from 31,905 patients were included (40% male, median age 60 years) of whom 1,301 (4.1%) were diagnosed with HF over 124,676 person-years of follow-up. Data were allocated to a development (n = 25,524) and validation (n = 6,381) set. TARGET-HF attained a C-statistic of 0.853 (95% CI, 0.834 to 0.872) on the validation set, which proved to provide a better discrimination than C = 0.822 for age alone (95% CI, 0.801 to 0.842, P < 0.001) and C = 0.824 for the hospital-based model (95% CI, 0.802 to 0.843, P < 0.001).
The TARGET-HF model illustrates that routine consultation codes can be used to build a performant model to identify patients at risk for HF at the time of GP consultation.
及时诊断心力衰竭（HF）对于优化治疗机会至关重要，这些机会可以改善症状、生活质量和生存率。虽然大多数患者在 HF 之前会咨询他们的全科医生（GP），但 HF 的早期阶段可能难以识别。综合临床支持工具可能有助于识别 HF 高危患者。因此，我们使用常规医疗保健数据构建了一个预测模型。
我们的研究涉及 2011 年至 2020 年期间在阿姆斯特丹大都市区内因呼吸困难和/或外周水肿就诊的≥35 岁的动态队列患者。感兴趣的结局是由专家小组验证的 HF 事件。我们开发了一个正则化的、特定原因的多变量比例风险模型（TARGET-HF）。该模型通过在单独的验证集上进行引导进行评估，并与使用医院保险数据和患者年龄作为唯一预测因子开发的现有模型进行比较。
共纳入 31905 例患者（40%为男性，中位年龄 60 岁），其中 1301 例（4.1%）在 124676 人年的随访中被诊断为 HF。数据被分配到开发（n=25524）和验证（n=6381）集。TARGET-HF 在验证集上的 C 统计量为 0.853（95%CI，0.834 至 0.872），这证明其在区分能力上优于仅年龄的 C 统计量 0.822（95%CI，0.801 至 0.842，P<0.001）和基于医院的模型的 C 统计量 0.824（95%CI，0.802 至 0.843，P<0.001）。
TARGET-HF 模型表明，常规就诊代码可用于构建一种有效的模型，以便在 GP 就诊时识别 HF 高危患者。
