IEEE J Biomed Health Inform. 2021 Mar;25(3):634-646. doi: 10.1109/JBHI.2020.3009903. Epub 2021 Mar 5.
To estimate instantaneous oxygen uptake VO with a small, low-cost wearable sensor during exercise and daily activities in order to enable monitoring of energy expenditure (EE) in uncontrolled settings. We aim to do so using a combination of seismocardiogram (SCG), electrocardiogram (ECG) and atmospheric pressure (AP) signals obtained from a minimally obtrusive wearable device.
In this study, subjects performed a treadmill protocol in a controlled environment and an outside walking protocol in an uncontrolled environment. During testing, the COSMED K5 metabolic system collected gold standard breath-by-breath (BxB) data and a custom-built wearable patch placed on the mid-sternum collected SCG, ECG and AP signals. We extracted features from these signals to estimate the BxB VO data obtained from the COSMED system.
In estimating instantaneous VO, we achieved our best results on the treadmill protocol using a combination of SCG (frequency) and AP features (RMSE of 3.68 ± 0.98 ml/kg/min and R of 0.77). For the outside protocol, we achieved our best results using a combination of SCG (frequency), ECG and AP features (RMSE of 4.3 ± 1.47 ml/kg/min and R of 0.64). In estimating VO consumed over one minute intervals during the protocols, our median percentage error was 15.8[Formula: see text] for the treadmill protocol and 20.5[Formula: see text] for the outside protocol.
SCG, ECG and AP signals from a small wearable patch can enable accurate estimation of instantaneous VO in both controlled and uncontrolled settings. SCG signals capturing variation in cardio-mechanical processes, AP signals, and state of the art machine learning models contribute significantly to the accurate estimation of instantaneous VO.
Accurate estimation of VO with a low cost, minimally obtrusive wearable patch can enable the monitoring of VO and EE in everyday settings and make the many applications of these measurements more accessible to the general public.
使用小型低成本可穿戴传感器在运动和日常活动中估计即时摄氧量 VO，以便能够在不受控制的环境中监测能量消耗 (EE)。我们的目标是使用从最小干扰的可穿戴设备获得的地震心动图 (SCG)、心电图 (ECG) 和大气压力 (AP) 信号的组合来实现这一目标。
在这项研究中，受试者在受控环境中进行跑步机测试，并在不受控制的环境中进行室外步行测试。在测试过程中，COSMED K5 代谢系统收集了金标准逐口气（BxB）数据，而放置在胸骨中部的定制可穿戴贴片则收集了 SCG、ECG 和 AP 信号。我们从这些信号中提取特征，以估计从 COSMED 系统获得的 BxB VO 数据。
在估计即时 VO 时，我们在跑步机测试中使用 SCG（频率）和 AP 特征的组合获得了最佳结果（RMSE 为 3.68±0.98 ml/kg/min，R 为 0.77）。对于室外协议，我们使用 SCG（频率）、ECG 和 AP 特征的组合获得了最佳结果（RMSE 为 4.3±1.47 ml/kg/min，R 为 0.64）。在估计协议期间一分钟间隔内消耗的 VO 时，我们的中位数百分比误差为跑步机协议的 15.8%[公式：见正文]和室外协议的 20.5%[公式：见正文]。
小型可穿戴贴片的 SCG、ECG 和 AP 信号可在受控和不受控环境中准确估计即时 VO。捕获心血机械过程变化的 SCG 信号、AP 信号和最先进的机器学习模型对即时 VO 的准确估计有很大贡献。
使用低成本、最小干扰的可穿戴贴片准确估计 VO 可以实现 VO 和 EE 在日常环境中的监测，并使这些测量的许多应用更容易为公众所接受。
