Chang Ying-Feng, Yen Kun-Chi, Wang Chun-Li, Chen Sin-You, Chen Jenhui, Chu Pao-Hsien, Lai Chao-Sung
Artificial Intelligence Research Center, Chang Gung University, Taoyuan, Taiwan; Department of Gastroenterology and Hepatology, New Taipei Municipal Tu Cheng Hospital (Built and Operated by Chang Gung Medical Foundation), New Taipei, Taiwan.
Division of Cardiology, Department of Internal Medicine, Linkou Medical Center, Chang Gung Memorial Hospital, Taoyuan, Taiwan; Graduate Institute of Clinical Medical Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan.
Biomed J. 2024 Oct 28;48(4):100803. doi: 10.1016/j.bj.2024.100803.
Recently, as a relatively novel technology, artificial intelligence (especially in the deep learning fields) has received more and more attention from researchers and has successfully been applied to many biomedical domains. Nonetheless, just a few research works use deep learning skills to predict the cardiac resynchronization therapy (CRT)-response of heart failure patients.
We try to use the deep learning-based technique to construct a model which is used to predict the CRT response of patients with high prediction accuracy, precision, and sensitivity.
Using two-dimensional echocardiographic strain traces from 131 patients, we pre-processed the data and synthesized 2000 model inputs through the synthetic minority oversampling technique (SMOTE). These inputs trained and optimized deep neural networks (DNN) and one-dimensional convolution neural networks (1D-CNN). Visualization of prediction results was performed using t-distributed stochastic neighbor embedding (t-SNE), and model performance was evaluated using accuracy, precision, sensitivity, F1 score, and specificity. Variable importance was assessed using Shapley additive explanations (SHAP) analysis.
Both the optimal DNN and 1D-CNN models demonstrated exceptional predictive performance, with prediction accuracy, precision, and sensitivity all around 90%. Furthermore, the area under the receiver operating characteristic curve (AUROC) of the optimal 1D-CNN and DNN models achieved 0.8734 and 0.9217, respectively. Crucially, the most significant input variables for both models align well with clinical experience, further corroborating their robustness and applicability in real-world settings.
We believe that both the DL models could be an auxiliary to help in treatment response prediction for doctors because of the excellent prediction performance and the convenience of obtaining input data to predict the CRT response of patients clinically.
近年来，作为一项相对新颖的技术，人工智能（尤其是深度学习领域）受到了研究人员越来越多的关注，并已成功应用于许多生物医学领域。尽管如此，仅有少数研究工作使用深度学习技术来预测心力衰竭患者的心脏再同步治疗（CRT）反应。
我们试图使用基于深度学习的技术构建一个模型，用于以高预测准确性、精确性和敏感性预测患者的CRT反应。
我们使用131例患者的二维超声心动图应变轨迹，对数据进行预处理，并通过合成少数过采样技术（SMOTE）合成2000个模型输入。这些输入用于训练和优化深度神经网络（DNN）和一维卷积神经网络（1D-CNN）。使用t分布随机邻域嵌入（t-SNE）对预测结果进行可视化，并使用准确性、精确性、敏感性、F1分数和特异性评估模型性能。使用Shapley加性解释（SHAP）分析评估变量重要性。
最优的DNN和1D-CNN模型均表现出卓越的预测性能，预测准确性、精确性和敏感性均在90%左右。此外，最优的1D-CNN和DNN模型的受试者工作特征曲线下面积（AUROC）分别达到0.8734和0.9217。至关重要的是，两个模型最重要的输入变量与临床经验高度吻合，进一步证实了它们在实际应用中的稳健性和适用性。
我们认为，由于这两种深度学习模型具有出色的预测性能以及获取输入数据以临床预测患者CRT反应的便利性，它们可以作为辅助工具帮助医生进行治疗反应预测。
