AUTHOR=Wang Jiachen , Zang Yaning , Wu Qian , She Yingjia , Xu Haoran , Zhang Jian , Cai Shan , Li Yuzhu , Zhang Zhengbo 

TITLE=Predicting Adverse Events During Six-Minute Walk Test Using Continuous Physiological Signals

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.887954

DOI=10.3389/fphys.2022.887954

ISSN=1664-042X

ABSTRACT=Background and objective: The six-minute walk test (6MWT) is a common functional assessment test, but adverse events during the test can be potentially dangerous and can lead to serious consequences, such as death and life-threatening events. This study aimed to predict the occurrence of adverse events during 6MWT, using continuous physiological parameters combined with demographic variables.
Methods: 578 patients who had performed standardized 6MWT with wearable devices from 3 hospitals were included in this retrospective study. Adverse events occurred in 73 patients (12.6%). ECG, respiratory signal, tri-axial acceleration signals, oxygen saturation, demographic variables and scales assessment were obtained. Feature extraction and selection of physiological signals were performed during 2-minute resting and 1-minute movement phases. 5-fold cross-validation was used to assess the machine learning models. The predictive ability of different models and scales was compared.
Results: Of the 16 features selected by the recursive feature elimination method, heart rate related features were the most important. Light Gradient Boosting Machine (LightGBM) had the highest AUC of 0.874±0.063 and the AUC of Logistic Regression was AUC of 0.869±0.067. The National Early Warning Score (NEWS), a scale related to physiological parameters, was more effective than other scales (Borg and Modified Medical Research Council (mMRC) dyspnea score) with an AUC of 0.739.
Conclusion: It’s feasible to predict the occurrence of adverse event during 6MWT using continuous physiological parameters combined with demographic variables. Wearable sensors/systems can be used for continuous physiological monitoring and provide additional tools for patient safety, no matter during 6MWT or in daily life.