Shi Tao, Yang Jianping, Zhang Ningli, Rong Wei, Gao Lusha, Xia Ping, Zou Jie, Zhu Na, Yang Fazhi, Chen Lixing
Department of Cardiology, The First Affiliated Hospital of Kunming Medical University, Kunming, China.
College of Big Data, Yunnan Agricultural University, Kunming, China.
Digit Health. 2024 Aug 25;10:20552076241277027. doi: 10.1177/20552076241277027. eCollection 2024 Jan-Dec.
Explainable machine learning (XAI) was introduced in this study to improve the interpretability, explainability and transparency of the modelling results. The survex package in R was used to interpret and compare two survival models - the Cox proportional hazards regression (coxph) model and the random survival forest (rfsrc) model - and to estimate overall survival (OS) and its determinants in heart failure (HF) patients using these models.
We selected 1159 HF patients hospitalised at the First Affiliated Hospital of Kunming Medical University. First, the performance of the two models was investigated using the C-index, the integrated C/D AUC, and the integrated Brier score. Second, a global explanation of the whole cohort was carried out using the time-dependent variable importance and the partial dependence survival profile. Finally, the SurvSHAP(t) and SurvLIME plots and the ceteris paribus survival profile were used to obtain a local explanation for each patient.
By comparing the C-index, the C/D AUC, and the Brier score, this study showed that the model performance of rfsrc was better than coxph. The global explanation of the whole cohort suggests that the C-reactive protein, lg BNP (brain natriuretic peptide), estimated glomerular filtration rate, albumin, age and blood chloride were significant unfavourable predictors of OS in HF patients in both the cxoph and the rfsrc models. By including individual patients in the model, we can provide a local explanation for each patient, which guides the clinician in individualising the patient's treatment.
By comparison, we conclude that the model performance of rfsrc is better than that of coxph. These two predictive models, which address not only the whole population but also selected patients, can help clinicians personalise the treatment of each HF patient according to his or her specific situation.
本研究引入可解释机器学习（XAI）以提高建模结果的可解释性、阐释性和透明度。使用R语言中的survex包来解释和比较两种生存模型——Cox比例风险回归（coxph）模型和随机生存森林（rfsrc）模型，并使用这些模型估计心力衰竭（HF）患者的总生存期（OS）及其决定因素。
我们选取了在昆明医科大学第一附属医院住院的1159例HF患者。首先，使用C指数、综合C/D曲线下面积（AUC）和综合Brier评分来研究这两种模型的性能。其次，使用随时间变化的变量重要性和部分依赖生存曲线对整个队列进行全局解释。最后，使用SurvSHAP(t)和SurvLIME图以及不变条件生存曲线对每位患者进行局部解释。
通过比较C指数、C/D AUC和Brier评分，本研究表明rfsrc的模型性能优于coxph。对整个队列的全局解释表明，在coxph和rfsrc模型中，C反应蛋白、lg BNP（脑钠肽）、估计肾小球滤过率、白蛋白、年龄和血氯是HF患者OS的显著不利预测因素。通过将个体患者纳入模型，我们可以为每位患者提供局部解释，这有助于临床医生对患者进行个体化治疗。
通过比较，我们得出rfsrc的模型性能优于coxph的结论。这两种预测模型不仅适用于总体人群，也适用于特定患者，可帮助临床医生根据每位HF患者的具体情况进行个体化治疗。
