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

Abstract

Background and Objective: The 6-min 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 and low quality of life. This study aimed to predict the occurrence of adverse events during 6MWT, using continuous physiological parameters combined with demographic variables. Methods: 578 patients with respiratory disease who had performed standardized 6MWT with wearable devices from three hospitals were included in this 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-min resting and 1-min 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, those related to blood oxygen were the most important and those related to heart rate were the most numerous. 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 mMRC (Modified Medical Research Council) scale and Borg scale had the lowest performance, with an AUC of 0.733 and 0.656 respectively. Conclusion: It is 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 during 6MWT.

Keywords: 6-min walk test; adverse events; machine learning; physiological signals; wearable devices.

FIGURE 1

Picture of multi-functional 6MWT system, including wearable devices and an intelligence terminal device (a hand-held PAD). Wearable devices include a flexible vest, an oximeter and a blood pressure monitor. The system is able to monitor ECG, respiratory waves, triaxial acceleration, oxygen saturation and blood pressure. The physiological signal can be transmitted to the PAD via Wi-Fi and displayed in real time.

FIGURE 2

Distribution of the time between the occurrence of the first adverse event and the beginning of the 6MWT. Adverse events of over 95% of patients occurred after 1 min.

FIGURE 3

An example of changes in physiological parameters of a patient before, during and after the 6MWT process. This patient had a rapid increase in heart rate and respiratory rate while a rapid drop in oxygen saturation following the beginning of 6MWT. About 90 s after the beginning of 6MWT, the patient had a dyspnea and had a rest. During the rest period, the patient’s heart rate, respiratory rate and oxygen saturation recovered. About 280 s after the beginning of 6MWT, the patient developed a more severe intolerable dyspnea and was treated with oxygen. The 6MWT was terminated about 80 s early.

FIGURE 4

ROC curves for different machine learning models and scoring scales. The ROC curves for machine learning models were the average score of the results of a five-fold cross-validation. AUC results of all machine learning models outperformed the scales. SVC, support vector classification; LightGBM, light gradient boosting machine; XGBoost, extreme gradient boosting; mMRC, modified medical research council dyspnea scale.

FIGURE 5

Feature importance ranking in lightGBM model. SpO2_decrease1, Spo2 decrease value in 1 min; SVM, signal vector magnitude; SpO2 mean 1, mean value of SpO2 in first 1 min; HR intercept, heart rate intercept; HR peak, peak heart rate; SpO2 DA, SpO2 desaturation area; RR rest, breath rate during rest segment; HR rest, heart rate during rest segment; HF, high frequency power, one of HRV parameters; HR min, minimum heart rate; HR rest std, standard deviation of beat-to-beat heart rate during rest segment; HR increase 1, heart rate increase value in 1 min; Total power, one of HRV parameters; CVI, cardiac vagal index, one of HRV parameters; NNI mean, mean value of normal-to-normal intervals.