Ogasawara Takayuki, Mukaino Masahiko, Matsuura Hirotaka, Aoshima Yasushi, Suzuki Takuya, Togo Hiroyoshi, Nakashima Hiroshi, Saitoh Eiichi, Yamaguchi Masumi, Otaka Yohei, Tsukada Shingo
NTT Basic Research Laboratories and Bio-Medical Informatics Research Center, NTT Corporation, Atsugi, Japan.
Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan.
Front Physiol. 2023 Jan 26;14:1094946. doi: 10.3389/fphys.2023.1094946. eCollection 2023.
Acceleration sensors are widely used in consumer wearable devices and smartphones. Postures estimated from recorded accelerations are commonly used as features indicating the activities of patients in medical studies. However, recording for over 24 h is more likely to result in data losses than recording for a few hours, especially when consumer-grade wearable devices are used. Here, to impute postures over a period of 24 h, we propose an imputation method that uses ensemble averaging. This method outputs a time series of postures over 24 h with less lost data by calculating the ratios of postures taken at the same time of day during several measurement-session days. Whereas conventional imputation methods are based on approaches with groups of subjects having multiple variables, the proposed method imputes the lost data variables individually and does not require other variables except posture. We validated the method on 306 measurement data from 99 stroke inpatients in a hospital rehabilitation ward. First, to classify postures from acceleration data measured by a wearable sensor placed on the patient's trunk, we preliminary estimated possible thresholds for classifying postures as 'reclining' and 'sitting or standing' by investigating the valleys in the histogram of occurrences of trunk angles during a long-term recording. Next, the imputations of the proposed method were validated. The proposed method significantly reduced the missing data rate from 5.76% to 0.21%, outperforming a conventional method.
加速度传感器广泛应用于消费级可穿戴设备和智能手机中。从记录的加速度中估计出的姿势通常被用作医学研究中指示患者活动的特征。然而，与记录几个小时相比，记录超过24小时更有可能导致数据丢失，尤其是在使用消费级可穿戴设备时。在此，为了推算24小时内的姿势，我们提出了一种使用总体平均的推算方法。该方法通过计算几个测量时间段内同一天同一时间所采取姿势的比率，输出24小时内姿势的时间序列，且丢失的数据更少。传统的推算方法基于具有多个变量的受试者组的方法，而本文提出的方法单独推算丢失的数据变量，并且除了姿势之外不需要其他变量。我们在一家医院康复病房中对99名中风住院患者的306份测量数据上验证了该方法。首先，为了从放置在患者躯干上的可穿戴传感器测量的加速度数据中分类姿势，我们通过研究长期记录期间躯干角度出现次数的直方图中的谷值，初步估计了将姿势分类为“躺卧”和“坐或站”的可能阈值。接下来，对所提出方法的推算进行了验证。所提出的方法显著降低了缺失数据率，从5.76%降至0.21%，优于传统方法。
