Baker Heart & Diabetes Institute, Melbourne, Australia.
Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne, Melbourne, Australia.
BMC Med Res Methodol. 2024 Sep 30;24(1):222. doi: 10.1186/s12874-024-02311-5.
Wrist-worn data from commercially available devices has potential to characterize sedentary time for research and for clinical and public health applications. We propose a model that utilizes heart rate in addition to step count data to estimate the proportion of time spent being sedentary and the usual length of sedentary bouts.
We developed and trained two Hidden semi-Markov models, STEPHEN (STEP and Heart ENcoder) and STEPCODE (STEP enCODEr; a steps-only based model) using consumer-grade Fitbit device data from participants under free living conditions, and validated model performance using two external datasets. We used the median absolute percentage error (MDAPE) to measure the accuracy of the proposed models against research-grade activPAL device data as the referent. Bland-Altman plots summarized the individual-level agreement with activPAL.
In OPTIMISE cohort, STEPHEN's estimates of the proportion of time spent sedentary had significantly (p < 0.001) better accuracy (MDAPE [IQR] = 0.15 [0.06-0.25] vs. 0.23 [0.13-0.53)]) and agreement (Bias Mean [SD]=-0.03[0.11] vs. 0.14 [0.11]) than the proprietary software, estimated the usual sedentary bout duration more accurately (MDAPE[IQR] = 0.11[0.06-0.26] vs. 0.42[0.32-0.48]), and had better agreement (Bias Mean [SD] = 3.91[5.67] minutes vs. -11.93[5.07] minutes). With the ALLO-Active dataset, STEPHEN and STEPCODE did not improve the estimation of proportion of time spent sedentary, but STEPHEN estimated usual sedentary bout duration more accurately than the proprietary software (MDAPE[IQR] = 0.19[0.03-0.25] vs. 0.36[0.15-0.48]) and had smaller bias (Bias Mean[SD] = 0.70[8.89] minutes vs. -11.35[9.17] minutes).
STEPHEN can characterize the proportion of time spent being sedentary and usual sedentary bout length. The methodology is available as an open access R package available from https://github.com/limfuxing/stephen/ . The package includes trained models, but users have the flexibility to train their own models.
可穿戴设备腕部数据具有对研究以及临床和公共卫生应用中久坐时间进行特征描述的潜力。我们提出了一种利用心率和计步数据估算久坐时间比例和典型久坐时间长度的模型。
我们使用消费者级别的 Fitbit 设备数据，在自由生活条件下开发和训练了两个隐半马尔可夫模型，分别为 STEPHEN（步频和心率编码器）和 STEPCODE（基于步频的编码器），并使用两个外部数据集验证了模型性能。我们使用中值绝对百分比误差（MDAPE）来衡量与研究级 activPAL 设备数据（作为参考）相比，提出模型的准确性。Bland-Altman 图总结了与 activPAL 的个体水平一致性。
在 OPTIMISE 队列中，STEPHEN 估算的久坐时间比例具有更高的准确性（MDAPE[IQR] = 0.15[0.06-0.25] 与 0.23[0.13-0.53]）和更好的一致性（Bias Mean [SD]=-0.03[0.11] 与 0.14 [0.11]），与专有软件相比，该模型能够更准确地估算典型的久坐时间长度（MDAPE[IQR] = 0.11[0.06-0.26] 与 0.42[0.32-0.48]），并且具有更好的一致性（Bias Mean [SD] = 3.91[5.67] 分钟与-11.93[5.07] 分钟）。使用 ALLO-Active 数据集，STEPHEN 和 STEPCODE 并没有改善久坐时间比例的估计，但 STEPHEN 比专有软件更准确地估算典型的久坐时间长度（MDAPE[IQR] = 0.19[0.03-0.25] 与 0.36[0.15-0.48]），且偏差更小（Bias Mean[SD] = 0.70[8.89] 分钟与-11.35[9.17] 分钟）。
STEPHEN 可以描述久坐时间比例和典型的久坐时间长度。该方法可以从 https://github.com/limfuxing/stephen/ 以开放访问的 R 包形式获得。该包包括训练好的模型，但用户可以灵活地训练自己的模型。
