Wang Jesse, Nouraie Seyed M, Kelly Neil J, Chan Stephen Y
Department of Medicine, University of Pittsburgh School of Medicine and University of Pittsburgh Medical Center, Pittsburgh, PA.
Center for Pulmonary Vascular Biology and Medicine, Pittsburgh Heart, Lung, and Blood Vascular Medicine Institute, University of Pittsburgh School of Medicine and University of Pittsburgh Medical Center, Pittsburgh, PA.
medRxiv. 2025 Jul 14:2025.07.11.25331386. doi: 10.1101/2025.07.11.25331386.
Determination of cardiac output (CO) is essential to the clinical management of cardiovascular compromise. However, the invasiveness, procedural risks, and reliance on specialized infrastructure limit accessibility and scalability of standard-of-care right heart catheterization (RHC). Seismocardiography (SCG), a non-invasive technique which records subtle chest wall vibrations generated by cardiac mechanical activity, may offer a promising alternative for CO determination.
To develop and evaluate a deep learning model for estimating CO directly from SCG, electrocardiogram (ECG), and body mass index (BMI) in heart failure patients undergoing RHC.
We trained a deep convolutional neural network for CO estimation using an open-access dataset comprising 73 heart failure patients with simultaneous RHC, SCG, and ECG recordings. Model performance was evaluated using a rotating leave-pair-out cross-validation strategy.
When estimating CO, the deep learning model achieved a mean bias of -0.35 L/min with limits of agreement (LoA) from -2.21 to 1.51 L/min. When predicting cardiac index in patients with a reference index < 2.2 L/min/m, the model yielded a mean bias of 0.07 L/min/m with LoA from -0.35 to 0.48 L/min/m.
This study demonstrates the feasibility of using deep learning in combination with wearable SCG sensors to non-invasively estimate CO. Model performance was particularly strong in low-output states. These findings highlight the potential of SCG-based monitoring to augment clinical decision-making in settings where invasive measurements are impractical or unavailable. Prospective multicenter validation is needed to confirm generalizability and assess clinical impact.
心输出量（CO）的测定对于心血管功能不全的临床管理至关重要。然而，侵入性、操作风险以及对专业基础设施的依赖限制了标准治疗方法右心导管检查（RHC）的可及性和可扩展性。心震图描记法（SCG）是一种非侵入性技术，可记录心脏机械活动产生的细微胸壁振动，可能为CO测定提供一种有前景的替代方法。
开发并评估一种深度学习模型，用于直接从接受RHC的心力衰竭患者的SCG、心电图（ECG）和体重指数（BMI）估计CO。
我们使用一个开放获取数据集训练了一个用于CO估计的深度卷积神经网络，该数据集包含73例同时进行RHC、SCG和ECG记录的心力衰竭患者。使用旋转留对交叉验证策略评估模型性能。
在估计CO时，深度学习模型的平均偏差为-0.35 L/min，一致性界限（LoA）为-2.21至1.51 L/min。在预测参考指数<2.2 L/min/m²的患者的心脏指数时，该模型的平均偏差为0.07 L/min/m²，LoA为-0.35至0.48 L/min/m²。
本研究证明了结合可穿戴SCG传感器使用深度学习无创估计CO的可行性。在低输出状态下，模型性能尤其强大。这些发现突出了基于SCG的监测在侵入性测量不切实际或无法进行的情况下增强临床决策的潜力。需要进行前瞻性多中心验证以确认其普遍性并评估临床影响。
