Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness
Background/Objective: Considerable attention has been paid to interindividual differences in the cardiorespiratory fitness (CRF) response to exercise. However, the complex multifactorial nature of CRF response variability poses a significant challenge to our understanding of this issue. We aimed to...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Journal of Exercise Science & Fitness |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1728869X22000855 |
| _version_ | 1797936379295956992 |
|---|---|
| author | Lin Xie Bo Gou Shuwen Bai Dong Yang Zhe Zhang Xiaohui Di Chunwang Su Xiaoni Wang Kun Wang Jianbao Zhang |
| author_facet | Lin Xie Bo Gou Shuwen Bai Dong Yang Zhe Zhang Xiaohui Di Chunwang Su Xiaoni Wang Kun Wang Jianbao Zhang |
| author_sort | Lin Xie |
| collection | DOAJ |
| description | Background/Objective: Considerable attention has been paid to interindividual differences in the cardiorespiratory fitness (CRF) response to exercise. However, the complex multifactorial nature of CRF response variability poses a significant challenge to our understanding of this issue. We aimed to explore whether unsupervised clustering can take advantage of large amounts of clinical data and identify latent subgroups with different CRF exercise responses within a healthy population. Methods: 252 healthy participants (99 men, 153 women; 36.8 ± 13.4 yr) completed moderate endurance training on 3 days/week for 4 months, with exercise intensity prescribed based on anaerobic threshold (AT). Detailed clinical measures, including resting vital signs, ECG, cardiorespiratory parameters, echocardiography, heart rate variability, spirometry and laboratory data, were obtained before and after the exercise intervention. Baseline phenotypic variables that were significantly correlated with CRF exercise response were identified and subjected to selection steps, leaving 10 minimally redundant variables, including age, BMI, maximal oxygen uptake (VO2max), maximal heart rate, VO2 at AT as a percentage of VO2max, minute ventilation at AT, interventricular septal thickness of end-systole, E velocity, root mean square of heart rate variability, and hematocrit. Agglomerative hierarchical clustering was performed on these variables to detect latent subgroups that may be associated with different CRF exercise responses. Results: Unsupervised clustering revealed two mutually exclusive groups with distinct baseline phenotypes and CRF exercise responses. The two groups differed markedly in baseline characteristics, initial fitness, echocardiographic measurements, laboratory values, and heart rate variability parameters. A significant improvement in CRF following the 16-week endurance training, expressed by the absolute change in VO2max, was observed only in one of the two groups (3.42 ± 0.4 vs 0.58 ± 0.65 ml⋅kg−1⋅min−1, P = 0.002). Assuming a minimal clinically important difference of 3.5 ml⋅kg−1⋅min−1 in VO2max, the proportion of population response was 56.1% and 13.9% for group 1 and group 2, respectively (P<0.001). Although group 1 exhibited no significant improvement in CRF at group level, a significant decrease in diastolic blood pressure (70.4 ± 7.8 vs 68.7 ± 7.2 mm Hg, P = 0.027) was observed. Conclusions: Unsupervised learning based on dense phenotypic characteristics identified meaningful subgroups within a healthy population with different CRF responses following standardized aerobic training. Our model could serve as a useful tool for clinicians to develop personalized exercise prescriptions and optimize training effects. |
| first_indexed | 2024-04-10T18:29:56Z |
| format | Article |
| id | doaj.art-7666fdb0803f46299cdadcc59fcbedcc |
| institution | Directory Open Access Journal |
| issn | 1728-869X |
| language | English |
| last_indexed | 2024-04-10T18:29:56Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Exercise Science & Fitness |
| spelling | doaj.art-7666fdb0803f46299cdadcc59fcbedcc2023-02-02T04:48:01ZengElsevierJournal of Exercise Science & Fitness1728-869X2023-01-01211147156Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitnessLin Xie0Bo Gou1Shuwen Bai2Dong Yang3Zhe Zhang4Xiaohui Di5Chunwang Su6Xiaoni Wang7Kun Wang8Jianbao Zhang9Key Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaDepartment of Physical Activity and Public Health, Xi'an Physical Education University, Xi'an, 710068, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaKey Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, ChinaDepartment of Physical Activity and Public Health, Xi'an Physical Education University, Xi'an, 710068, China; Corresponding author.Key Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, China; Corresponding author. Key Laboratory of Biomedical Information Engineering of Education Ministry, Department of Life Science and Technology, Xi'an Jiaotong University, No.28, Xianning West Road, Xi'an, China.Background/Objective: Considerable attention has been paid to interindividual differences in the cardiorespiratory fitness (CRF) response to exercise. However, the complex multifactorial nature of CRF response variability poses a significant challenge to our understanding of this issue. We aimed to explore whether unsupervised clustering can take advantage of large amounts of clinical data and identify latent subgroups with different CRF exercise responses within a healthy population. Methods: 252 healthy participants (99 men, 153 women; 36.8 ± 13.4 yr) completed moderate endurance training on 3 days/week for 4 months, with exercise intensity prescribed based on anaerobic threshold (AT). Detailed clinical measures, including resting vital signs, ECG, cardiorespiratory parameters, echocardiography, heart rate variability, spirometry and laboratory data, were obtained before and after the exercise intervention. Baseline phenotypic variables that were significantly correlated with CRF exercise response were identified and subjected to selection steps, leaving 10 minimally redundant variables, including age, BMI, maximal oxygen uptake (VO2max), maximal heart rate, VO2 at AT as a percentage of VO2max, minute ventilation at AT, interventricular septal thickness of end-systole, E velocity, root mean square of heart rate variability, and hematocrit. Agglomerative hierarchical clustering was performed on these variables to detect latent subgroups that may be associated with different CRF exercise responses. Results: Unsupervised clustering revealed two mutually exclusive groups with distinct baseline phenotypes and CRF exercise responses. The two groups differed markedly in baseline characteristics, initial fitness, echocardiographic measurements, laboratory values, and heart rate variability parameters. A significant improvement in CRF following the 16-week endurance training, expressed by the absolute change in VO2max, was observed only in one of the two groups (3.42 ± 0.4 vs 0.58 ± 0.65 ml⋅kg−1⋅min−1, P = 0.002). Assuming a minimal clinically important difference of 3.5 ml⋅kg−1⋅min−1 in VO2max, the proportion of population response was 56.1% and 13.9% for group 1 and group 2, respectively (P<0.001). Although group 1 exhibited no significant improvement in CRF at group level, a significant decrease in diastolic blood pressure (70.4 ± 7.8 vs 68.7 ± 7.2 mm Hg, P = 0.027) was observed. Conclusions: Unsupervised learning based on dense phenotypic characteristics identified meaningful subgroups within a healthy population with different CRF responses following standardized aerobic training. Our model could serve as a useful tool for clinicians to develop personalized exercise prescriptions and optimize training effects.http://www.sciencedirect.com/science/article/pii/S1728869X22000855Interindividual variabilityOxygen uptakeTraining responsivenessUnsupervised learning |
| spellingShingle | Lin Xie Bo Gou Shuwen Bai Dong Yang Zhe Zhang Xiaohui Di Chunwang Su Xiaoni Wang Kun Wang Jianbao Zhang Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness Journal of Exercise Science & Fitness Interindividual variability Oxygen uptake Training responsiveness Unsupervised learning |
| title | Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| title_full | Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| title_fullStr | Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| title_full_unstemmed | Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| title_short | Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| title_sort | unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness |
| topic | Interindividual variability Oxygen uptake Training responsiveness Unsupervised learning |
| url | http://www.sciencedirect.com/science/article/pii/S1728869X22000855 |
| work_keys_str_mv | AT linxie unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT bogou unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT shuwenbai unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT dongyang unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT zhezhang unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT xiaohuidi unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT chunwangsu unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT xiaoniwang unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT kunwang unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness AT jianbaozhang unsupervisedclusteranalysisrevealsdistinctsubgroupsinhealthypopulationwithdifferentexerciseresponsesofcardiorespiratoryfitness |