Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals
Oxygen uptake (VO2) is an important parameter in sports medicine, health assessment and clinical treatment. At present, more and more wearable devices are used in daily life, clinical treatment and health care. The parameters obtained by wearables have great research potential and application prospe...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2022.897412/full |
| _version_ | 1811183082716266496 |
|---|---|
| author | Zhao Wang Qiang Zhang Ke Lan Zhicheng Yang Xiaolin Gao Anshuo Wu Yi Xin Zhengbo Zhang |
| author_facet | Zhao Wang Qiang Zhang Ke Lan Zhicheng Yang Xiaolin Gao Anshuo Wu Yi Xin Zhengbo Zhang |
| author_sort | Zhao Wang |
| collection | DOAJ |
| description | Oxygen uptake (VO2) is an important parameter in sports medicine, health assessment and clinical treatment. At present, more and more wearable devices are used in daily life, clinical treatment and health care. The parameters obtained by wearables have great research potential and application prospect. In this paper, an instantaneous VO2 estimation model based on XGBoost was proposed and verified by using data obtained from a medical-grade wearable device (Beijing SensEcho) at different posture and activity levels. Furthermore, physiological characteristics extracted from single-lead electrocardiogram, thoracic and abdominal respiration signal and tri-axial acceleration signal were studied to optimize the model. There were 29 healthy volunteers recruited for the study to collect data while stationary (lying, sitting, standing), walking, Bruce treadmill test and recuperating with SensEcho and the gas analyzer (Metalyzer 3B). The results show that the VO2 values estimated by the proposed model are in good agreement with the true values measured by the gas analyzer (R2 = 0.94 ± 0.03, n = 72,235), and the mean absolute error (MAE) is 1.83 ± 0.59 ml/kg/min. Compared with the estimation method using a separate heart rate as input, our method reduced MAE by 54.70%. At the same time, other factors affecting the performance of the model were studied, including the influence of different input signals, gender and movement intensity, which provided more enlightenment for the estimation of VO2. The results show that the proposed model based on cardio-pulmonary physiological signals as inputs can effectively improve the accuracy of instantaneous VO2 estimation in various scenarios of activities and was robust between different motion modes and state. The VO2 estimation method proposed in this paper has the potential to be used in daily life covering the scenario of stationary, walking and maximal exercise. |
| first_indexed | 2024-04-11T09:42:02Z |
| format | Article |
| id | doaj.art-60b7ca37398645e584f83134e11ca9d2 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-11T09:42:02Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-60b7ca37398645e584f83134e11ca9d22022-12-22T04:31:11ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-08-011310.3389/fphys.2022.897412897412Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signalsZhao Wang0Qiang Zhang1Ke Lan2Zhicheng Yang3Xiaolin Gao4Anshuo Wu5Yi Xin6Zhengbo Zhang7Medical School of Chinese PLA, Beijing, ChinaSchool of Life Science, Beijing Institute of Technology, Beijing, ChinaBeijing SensEcho Science and Technology Co Ltd, Beijing, ChinaPAII Inc., Palo Alto, Santa Clara, CA, United StatesInstitute of Sports Science, General Administration of Sport of China, Beijing, ChinaThe Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, United StatesSchool of Life Science, Beijing Institute of Technology, Beijing, ChinaCenter for Artificial Intelligence in Medicine, Chinese PLA General Hospital, Beijing, ChinaOxygen uptake (VO2) is an important parameter in sports medicine, health assessment and clinical treatment. At present, more and more wearable devices are used in daily life, clinical treatment and health care. The parameters obtained by wearables have great research potential and application prospect. In this paper, an instantaneous VO2 estimation model based on XGBoost was proposed and verified by using data obtained from a medical-grade wearable device (Beijing SensEcho) at different posture and activity levels. Furthermore, physiological characteristics extracted from single-lead electrocardiogram, thoracic and abdominal respiration signal and tri-axial acceleration signal were studied to optimize the model. There were 29 healthy volunteers recruited for the study to collect data while stationary (lying, sitting, standing), walking, Bruce treadmill test and recuperating with SensEcho and the gas analyzer (Metalyzer 3B). The results show that the VO2 values estimated by the proposed model are in good agreement with the true values measured by the gas analyzer (R2 = 0.94 ± 0.03, n = 72,235), and the mean absolute error (MAE) is 1.83 ± 0.59 ml/kg/min. Compared with the estimation method using a separate heart rate as input, our method reduced MAE by 54.70%. At the same time, other factors affecting the performance of the model were studied, including the influence of different input signals, gender and movement intensity, which provided more enlightenment for the estimation of VO2. The results show that the proposed model based on cardio-pulmonary physiological signals as inputs can effectively improve the accuracy of instantaneous VO2 estimation in various scenarios of activities and was robust between different motion modes and state. The VO2 estimation method proposed in this paper has the potential to be used in daily life covering the scenario of stationary, walking and maximal exercise.https://www.frontiersin.org/articles/10.3389/fphys.2022.897412/fulloxygen uptakemachine learningwearable sensorXGBoostheart raterespiration |
| spellingShingle | Zhao Wang Qiang Zhang Ke Lan Zhicheng Yang Xiaolin Gao Anshuo Wu Yi Xin Zhengbo Zhang Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals Frontiers in Physiology oxygen uptake machine learning wearable sensor XGBoost heart rate respiration |
| title | Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals |
| title_full | Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals |
| title_fullStr | Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals |
| title_full_unstemmed | Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals |
| title_short | Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals |
| title_sort | enhancing instantaneous oxygen uptake estimation by non linear model using cardio pulmonary physiological and motion signals |
| topic | oxygen uptake machine learning wearable sensor XGBoost heart rate respiration |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2022.897412/full |
| work_keys_str_mv | AT zhaowang enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT qiangzhang enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT kelan enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT zhichengyang enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT xiaolingao enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT anshuowu enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT yixin enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals AT zhengbozhang enhancinginstantaneousoxygenuptakeestimationbynonlinearmodelusingcardiopulmonaryphysiologicalandmotionsignals |