Shin Ikgyu, Bhatt Nilay, Alashi Alaa, Kandala Keervani, Murugiah Karthik
Yale School of Public Health, New Haven, CT, USA.
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
medRxiv. 2024 Oct 16:2024.10.15.24315524. doi: 10.1101/2024.10.15.24315524.
To develop and compare prediction models for 30-day and 1-year mortality in Heart failure with preserved ejection fraction (HFpEF) using EHR data, utilizing both traditional and machine learning (ML) techniques.
HFpEF represents 1 in 2 heart failure patients. Predictive models in HFpEF, specifically those derived from electronic health record (EHR) data, are less established.
Using MIMIC-IV EHR data from 2008-2019, patients aged ≥ 18 years admitted with a primary diagnosis of HFpEF were identified using ICD-9 and 10 codes. Demographics, vital signs, prior diagnoses, and lab data were extracted. Data was partitioned into 80% training, 20% test sets. Prediction models from seven model classes (Support Vector Classifier (SVC), Logistic Regression, Lasso Regression, Elastic Net, Random Forest, Histogram-based Gradient Boosting Classifier (HGBC), and XGBoost) were developed using various imputation and oversampling techniques with 5-fold cross-validation. Model performance was compared using several metrics, and individual feature importance assessed using SHapley Additive exPlanations (SHAP) analysis.
Among 3910 hospitalizations for HFpEF, 30-day mortality was 6.3%, and 1-year mortality was 29.2%. Logistic regression performed well for 30-day mortality (Area Under the Receiver operating characteristic curve (AUC) 0.83), whereas Random Forest (AUC 0.79) and HGBC (AUC 0.78) for 1-year mortality. Age and NT-proBNP were the strongest predictors in SHAP analyses for both outcomes.
Models derived from EHR data can predict mortality after HFpEF hospitalization with comparable performance to models derived from registry or trial data, highlighting the potential for clinical implementation.
利用电子健康记录（EHR）数据，运用传统和机器学习（ML）技术，开发并比较射血分数保留的心力衰竭（HFpEF）患者30天和1年死亡率的预测模型。
HFpEF占心力衰竭患者的二分之一。HFpEF的预测模型，尤其是那些从电子健康记录（EHR）数据得出的模型，尚不完善。
使用2008 - 2019年的MIMIC-IV EHR数据，通过ICD - 9和10编码识别年龄≥18岁且以HFpEF为主要诊断入院的患者。提取人口统计学、生命体征、既往诊断和实验室数据。数据被划分为80%的训练集和20%的测试集。使用各种插补和过采样技术以及5折交叉验证，开发了来自七个模型类别的预测模型（支持向量分类器（SVC）、逻辑回归、套索回归、弹性网络、随机森林、基于直方图的梯度提升分类器（HGBC）和XGBoost）。使用多种指标比较模型性能，并使用夏普利值附加解释（SHAP）分析评估个体特征重要性。
在3910例HFpEF住院病例中，30天死亡率为6.3%，1年死亡率为29.2%。逻辑回归对30天死亡率表现良好（受试者操作特征曲线下面积（AUC）为0.83），而随机森林（AUC为0.79）和HGBC（AUC为0.78）对1年死亡率表现较好。在两种结局的SHAP分析中，年龄和N末端脑钠肽前体（NT-proBNP）是最强的预测因素。
从EHR数据得出的模型可以预测HFpEF住院后的死亡率，其性能与从注册登记或试验数据得出的模型相当，突出了临床应用的潜力。
