Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, Jiangsu, China.
Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, Jiangsu, China.
Int J Cardiovasc Imaging. 2024 Sep;40(9):1891-1901. doi: 10.1007/s10554-024-03177-w. Epub 2024 Jul 5.
Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.
心力衰竭（HF）与高发病率和死亡率相关。目前尚不清楚使用胸部 X 射线（CXR）的深度学习生存预测模型在心力衰竭患者中的价值。我们的研究旨在开发和验证一种使用心力衰竭患者的胸部 X 射线（DLSPCXR）的深度学习生存预测模型。该研究回顾性纳入了 2012 年 3 月至 2017 年 3 月在我院接受胸部 X 射线（CXR）检查的 353 例心力衰竭患者的队列。数据集被随机分为训练（n=247）和验证（n=106）数据集。对训练数据集进行单变量和多变量 Cox 分析，以开发临床和影像学生存预测模型。对 DLSPCXR 进行训练，并将选定的临床参数纳入 DLSPCXR 中以建立一个新模型，称为 DLSPinteg。使用时间依赖性接收器工作特征曲线下面积（TD AUC）评估区分性能，以预测 1、3 和 5 年的生存率。采用 Delong 检验比较不同模型之间的两个 AUC 的差异。通过 Kaplan-Meier 曲线评估最佳模型的风险区分能力。在多变量 Cox 分析中，年龄较大、较高的 N 末端前 B 型利钠肽（NT-ProBNP）、收缩期肺动脉压（sPAP）>50mmHg、纽约心脏协会（NYHA）功能分类 III-IV 和心胸比（CTR）≥0.62 在 CXR 中是心力衰竭患者预后不良的独立预测因子。基于接收者操作特征（ROC）曲线分析，在验证队列中，DLSPCXR 在预测 5 年生存率方面优于影像学 Cox 模型（AUC：0.757 与 0.561，P=0.01）。作为最优模型的 DLSPinteg 优于临床 Cox 模型（AUC：0.826 与 0.633，P=0.03）、影像学 Cox 模型（AUC：0.826 与 0.555，P<0.001）和 DLSPCXR（AUC：0.826 与 0.767，P=0.06）。使用胸部 X 射线的深度学习模型可以以可接受的准确性预测心力衰竭患者的生存率。
