Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates
A cardiopulmonary exercise test (CPET) is essential for lung resection. However, performing a CPET can be challenging. This study aimed to develop a machine learning model to estimate maximal oxygen consumption (VO<sub>2max</sub>) using data collected through a patch-type single-lead ele...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/11/21/2863 |
| _version_ | 1797631835352596480 |
|---|---|
| author | Hyun Ah Lee Woosik Yu Jong Doo Choi Young-sin Lee Ji Won Park Yun Jung Jung Seung Soo Sheen Junho Jung Seokjin Haam Sang Hun Kim Ji Eun Park |
| author_facet | Hyun Ah Lee Woosik Yu Jong Doo Choi Young-sin Lee Ji Won Park Yun Jung Jung Seung Soo Sheen Junho Jung Seokjin Haam Sang Hun Kim Ji Eun Park |
| author_sort | Hyun Ah Lee |
| collection | DOAJ |
| description | A cardiopulmonary exercise test (CPET) is essential for lung resection. However, performing a CPET can be challenging. This study aimed to develop a machine learning model to estimate maximal oxygen consumption (VO<sub>2max</sub>) using data collected through a patch-type single-lead electrocardiogram (ECG) monitoring device in candidates for lung resection. This prospective, single-center study included 42 patients who underwent a CPET at a tertiary teaching hospital from October 2021 to July 2022. During the CPET, a single-lead ECG monitoring device was applied to all patients, and the results obtained from the machine-learning algorithm using the information extracted from the ECG patch were compared with the CPET results. According to the Bland–Altman plot of measured and estimated VO<sub>2max</sub>, the VO<sub>2max</sub> values obtained from the machine learning model and the FRIEND equation showed lower differences from the reference value (bias: −0.33 mL·kg<sup>−1</sup>·min<sup>−1</sup>, bias: 0.30 mL·kg<sup>−1</sup>·min<sup>−1</sup>, respectively). In subgroup analysis, the developed model demonstrated greater consistency when applied to different maximal stage levels and sexes. In conclusion, our model provides a closer estimation of VO<sub>2max</sub> values measured using a CPET than existing equations. This model may be a promising tool for estimating VO<sub>2max</sub> and assessing cardiopulmonary reserve in lung resection candidates when a CPET is not feasible. |
| first_indexed | 2024-03-11T11:29:19Z |
| format | Article |
| id | doaj.art-02ee12233a6443e29f133a23b9d5545a |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-11T11:29:19Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-02ee12233a6443e29f133a23b9d5545a2023-11-10T15:03:49ZengMDPI AGHealthcare2227-90322023-10-011121286310.3390/healthcare11212863Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection CandidatesHyun Ah Lee0Woosik Yu1Jong Doo Choi2Young-sin Lee3Ji Won Park4Yun Jung Jung5Seung Soo Sheen6Junho Jung7Seokjin Haam8Sang Hun Kim9Ji Eun Park10Department of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Thoracic and Cardiovascular Surgery, Ajou University School of Medicine, Suwon 16499, Republic of KoreaSeers Technology Co., Seongnam-si 13558, Republic of KoreaSeers Technology Co., Seongnam-si 13558, Republic of KoreaDepartment of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Thoracic and Cardiovascular Surgery, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Thoracic and Cardiovascular Surgery, Ajou University School of Medicine, Suwon 16499, Republic of KoreaDepartment of Rehabilitation Medicine, Biomedical Research Institute, Pusan National University Hospital, Busan 49241, Republic of KoreaDepartment of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of KoreaA cardiopulmonary exercise test (CPET) is essential for lung resection. However, performing a CPET can be challenging. This study aimed to develop a machine learning model to estimate maximal oxygen consumption (VO<sub>2max</sub>) using data collected through a patch-type single-lead electrocardiogram (ECG) monitoring device in candidates for lung resection. This prospective, single-center study included 42 patients who underwent a CPET at a tertiary teaching hospital from October 2021 to July 2022. During the CPET, a single-lead ECG monitoring device was applied to all patients, and the results obtained from the machine-learning algorithm using the information extracted from the ECG patch were compared with the CPET results. According to the Bland–Altman plot of measured and estimated VO<sub>2max</sub>, the VO<sub>2max</sub> values obtained from the machine learning model and the FRIEND equation showed lower differences from the reference value (bias: −0.33 mL·kg<sup>−1</sup>·min<sup>−1</sup>, bias: 0.30 mL·kg<sup>−1</sup>·min<sup>−1</sup>, respectively). In subgroup analysis, the developed model demonstrated greater consistency when applied to different maximal stage levels and sexes. In conclusion, our model provides a closer estimation of VO<sub>2max</sub> values measured using a CPET than existing equations. This model may be a promising tool for estimating VO<sub>2max</sub> and assessing cardiopulmonary reserve in lung resection candidates when a CPET is not feasible.https://www.mdpi.com/2227-9032/11/21/2863maximal oxygen consumption (VO<sub>2max</sub>)cardiopulmonary exercise test (CPET)machine learning modelestimationlung resection candidates |
| spellingShingle | Hyun Ah Lee Woosik Yu Jong Doo Choi Young-sin Lee Ji Won Park Yun Jung Jung Seung Soo Sheen Junho Jung Seokjin Haam Sang Hun Kim Ji Eun Park Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates Healthcare maximal oxygen consumption (VO<sub>2max</sub>) cardiopulmonary exercise test (CPET) machine learning model estimation lung resection candidates |
| title | Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates |
| title_full | Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates |
| title_fullStr | Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates |
| title_full_unstemmed | Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates |
| title_short | Development of Machine Learning Model for VO<sub>2max</sub> Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in Lung Resection Candidates |
| title_sort | development of machine learning model for vo sub 2max sub estimation using a patch type single lead ecg monitoring device in lung resection candidates |
| topic | maximal oxygen consumption (VO<sub>2max</sub>) cardiopulmonary exercise test (CPET) machine learning model estimation lung resection candidates |
| url | https://www.mdpi.com/2227-9032/11/21/2863 |
| work_keys_str_mv | AT hyunahlee developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT woosikyu developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT jongdoochoi developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT youngsinlee developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT jiwonpark developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT yunjungjung developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT seungsoosheen developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT junhojung developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT seokjinhaam developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT sanghunkim developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates AT jieunpark developmentofmachinelearningmodelforvosub2maxsubestimationusingapatchtypesingleleadecgmonitoringdeviceinlungresectioncandidates |