基于患者报告结局的慢性心力衰竭患者出院后机器学习预后模型。
Machine learning prognosis model based on patient-reported outcomes for chronic heart failure patients after discharge.
机构信息
Department of Cardiology, the 1st Hospital of Shanxi Medical University, 85 South Jiefang Road, Taiyuan, Shanxi Province, 030001, China.
Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, 56 South XinJian Road, Taiyuan, Shanxi Province, 030001, China.
出版信息
Health Qual Life Outcomes. 2023 Mar 29;21(1):31. doi: 10.1186/s12955-023-02109-x.
BACKGROUND
Patient-reported outcomes (PROs) can be obtained outside hospitals and are of great significance for evaluation of patients with chronic heart failure (CHF). The aim of this study was to establish a prediction model using PROs for out-of-hospital patients.
METHODS
CHF-PRO were collected in 941 patients with CHF from a prospective cohort. Primary endpoints were all-cause mortality, HF hospitalization, and major adverse cardiovascular events (MACEs). To establish prognosis models during the two years follow-up, six machine learning methods were used, including logistic regression, random forest classifier, extreme gradient boosting (XGBoost), light gradient boosting machine, naive bayes, and multilayer perceptron. Models were established in four steps, namely, using general information as predictors, using four domains of CHF-PRO, using both of them and adjusting the parameters. The discrimination and calibration were then estimated. Further analyze were performed for the best model. The top prediction variables were further assessed. The Shapley additive explanations (SHAP) method was used to explain black boxes of the models. Moreover, a self-made web-based risk calculator was established to facilitate the clinical application.
RESULTS
CHF-PRO showed strong prediction value and improved the performance of the models. Among the approaches, XGBoost of the parameter adjustment model had the highest prediction performance with an area under the curve of 0.754 (95% CI: 0.737 to 0.761) for death, 0.718 (95% CI: 0.717 to 0.721) for HF rehospitalization and 0.670 (95% CI: 0.595 to 0.710) for MACEs. The four domains of CHF-PRO, especially the physical domain, showed the most significant impact on the prediction of outcomes.
CONCLUSION
CHF-PRO showed strong prediction value in the models. The XGBoost models using variables based on CHF-PRO and the patient's general information provide prognostic assessment for patients with CHF. The self-made web-based risk calculator can be conveniently used to predict the prognosis for patients after discharge.
CLINICAL TRIAL REGISTRATION
URL: http://www.chictr.org.cn/index.aspx ; Unique identifier: ChiCTR2100043337.
背景
患者报告的结局（PROs）可在医院外获得，对于评估慢性心力衰竭（CHF）患者具有重要意义。本研究旨在建立一个使用 PROs 对院外患者进行预测的模型。
方法
从前瞻性队列中收集了 941 例 CHF 患者的 CHF-PRO。主要终点是全因死亡率、HF 住院和主要不良心血管事件（MACEs）。为了在两年的随访期间建立预后模型，使用了六种机器学习方法，包括逻辑回归、随机森林分类器、极端梯度提升（XGBoost）、轻梯度提升机、朴素贝叶斯和多层感知机。模型的建立分为四个步骤，即使用一般信息作为预测因子、使用 CHF-PRO 的四个领域、同时使用两者并调整参数。然后评估了区分度和校准度。进一步对最佳模型进行了分析。进一步评估了顶级预测变量。使用 Shapley 可加性解释（SHAP）方法来解释模型的黑盒。此外，还建立了一个自制的基于网络的风险计算器，以方便临床应用。
结果
CHF-PRO 具有很强的预测价值，并提高了模型的性能。在这些方法中，参数调整模型的 XGBoost 具有最高的预测性能，死亡的曲线下面积为 0.754（95%CI：0.737 至 0.761），HF 再住院的曲线下面积为 0.718（95%CI：0.717 至 0.721），MACE 的曲线下面积为 0.670（95%CI：0.595 至 0.710）。CHF-PRO 的四个领域，特别是身体领域，对结局预测的影响最大。
结论
CHF-PRO 在模型中具有很强的预测价值。使用基于 CHF-PRO 和患者一般信息的变量的 XGBoost 模型为 CHF 患者提供预后评估。自制的基于网络的风险计算器可以方便地用于预测出院后患者的预后。
临床试验注册
网址：http://www.chictr.org.cn/index.aspx；唯一标识符：ChiCTR2100043337。
Zotero 插件