Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 4;31(4):448-457.
doi: 10.1093/eurjpc/zwad375.

Development of deep-learning models for real-time anaerobic threshold and peak VO2 prediction during cardiopulmonary exercise testing

Tatsuya Watanabe  1   2 , Takeshi Tohyama  3 , Masataka Ikeda  1   2 , Takeo Fujino  1   2 , Toru Hashimoto  1   2 , Shouji Matsushima  1   2 , Junji Kishimoto  4 , Koji Todaka  3   4 , Shintaro Kinugawa  1   2 , Hiroyuki Tsutsui  1   2   5 , Tomomi Ide  1   2
Affiliations

Development of deep-learning models for real-time anaerobic threshold and peak VO2 prediction during cardiopulmonary exercise testing

Tatsuya Watanabe et al. Eur J Prev Cardiol. .

Abstract

Aims: Exercise intolerance is a clinical feature of patients with heart failure (HF). Cardiopulmonary exercise testing (CPET) is the first-line examination for assessing exercise capacity in patients with HF. However, the need for extensive experience in assessing anaerobic threshold (AT) and the potential risk associated with the excessive exercise load when measuring peak oxygen uptake (peak VO2) limit the utility of CPET. This study aimed to use deep-learning approaches to identify AT in real time during testing (defined as real-time AT) and to predict peak VO2 at real-time AT.

Methods and results: This study included the time-series data of CPET recorded at the Department of Cardiovascular Medicine, Kyushu University Hospital. Two deep neural network models were developed to: (i) estimate the AT probability using breath-by-breath data and (ii) predict peak VO2 using the data at the real-time AT. The eligible CPET contained 1472 records of 1053 participants aged 18-90 years and 20% were used for model evaluation. The developed model identified real-time AT with 0.82 for correlation coefficient (Corr) and 1.20 mL/kg/min for mean absolute error (MAE), and the corresponding AT time with 0.86 for Corr and 0.66 min for MAE. The peak VO2 prediction model achieved 0.87 for Corr and 2.25 mL/kg/min for MAE.

Conclusion: Deep-learning models for real-time CPET analysis can accurately identify AT and predict peak VO2. The developed models can be a competent assistant system to assess a patient's condition in real time, expanding CPET utility.

Keywords: Anaerobic threshold; Cardiopulmonary exercise testing; Deep learning; Peak oxygen uptake; Respiratory gas analysis.

Plain language summary

Cardiopulmonary exercise testing can be used to evaluate the condition of patients with heart failure during exercise. Developed deep-learning models can accurately predict a patient’s anaerobic threshold in real time and peak oxygen uptake. The models can be used by clinicians for more objective and accurate assessments in real time, expanding the utility of cardiopulmonary exercise testing.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: T.W. is an employee of Nihon Kohden Inc., Tokyo, Japan. T.I. received research funding from SBI Pharmaceuticals and Pfizer Japan Co., Ltd. H.T. received remunerations from Daiichi Sankyo, Viatris, Ono Pharmaceutical, Bayer Yakuhin, Otsuka Pharmaceutical, AstraZeneca, Novartis Pharma, and Nippon Boehringer Ingelheim. Research funding was received from MEDINET, Kowa, Nippon Boehringer Ingelheim, Daiichi Sankyo, IQVIA Services Japan, Johnson & Johnson, NEC Corporation, and Medical Innovation Kyushu. Scholarship funds or donations were received from Otsuka Pharmaceutical, Boston Scientific Japan, Ono Pharmaceutical, Teijin Pharma, Zeon Medical, Bayer Yakuhin, Nippon Boehringer Ingelheim, St. Mary’s Hospital, Teijin Home Healthcare, Daiichi Sankyo, Mitsubishi Tanabe Pharma, Abbott Medical Japan, and Japan Lifeline. T.T., M.I., T.F., T.H., S.M., J.K., K.T., S.K., and T.I. declare no conflict of interest.

Comment in

Grants and funding