Machine learning predicts peak oxygen uptake and peak power output for customizing cardiopulmonary exercise testing using non-exercise features.
Cardiopulmonary exercise testing
Machine learning
Peak oxygen uptake
Peak power output
Prediction
Journal
European journal of applied physiology
ISSN: 1439-6327
Titre abrégé: Eur J Appl Physiol
Pays: Germany
ID NLM: 100954790
Informations de publication
Date de publication:
03 Jul 2024
03 Jul 2024
Historique:
received:
28
03
2024
accepted:
22
06
2024
medline:
3
7
2024
pubmed:
3
7
2024
entrez:
3
7
2024
Statut:
aheadofprint
Résumé
Cardiopulmonary exercise testing (CPET) is considered the gold standard for assessing cardiorespiratory fitness. To ensure consistent performance of each test, it is necessary to adapt the power increase of the test protocol to the physical characteristics of each individual. This study aimed to use machine learning models to determine individualized ramp protocols based on non-exercise features. We hypothesized that machine learning models will predict peak oxygen uptake ( The cross-sectional study was conducted with 274 (♀168, ♂106) participants who performed CPET on a cycle ergometer. Machine learning models and multiple linear regression were used to predict The most accurate machine learning model was the random forest (RMSE: 6.52 ml/kg/min [95% CI 5.21-8.17]) for Machine learning models predict DRKS00031401 (6 March 2023, retrospectively registered).
Identifiants
pubmed: 38958720
doi: 10.1007/s00421-024-05543-x
pii: 10.1007/s00421-024-05543-x
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Abut F, Akay MF, George J (2019) A robust ensemble feature selector based on rank aggregation for developing new VO
doi: 10.3906/elk-1808-138
Akay F, Abut F (2015) Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances. MDER. https://doi.org/10.2147/MDER.S57281
doi: 10.2147/MDER.S57281
Antunes BM, Campos EZ, Parmezzani SS et al (2017) Sleep quality and duration are associated with performance in maximal incremental test. Physiol Behav 177:252–256. https://doi.org/10.1016/j.physbeh.2017.05.014
doi: 10.1016/j.physbeh.2017.05.014
pubmed: 28502838
Appelman B, Charlton BT, Goulding RP et al (2024) Muscle abnormalities worsen after post-exertional malaise in long COVID. Nat Commun 15:17. https://doi.org/10.1038/s41467-023-44432-3
doi: 10.1038/s41467-023-44432-3
pubmed: 38177128
pmcid: 10766651
Armstrong T, Bull F (2006) Development of the world health organization Global Physical Activity Questionnaire (GPAQ). J Public Health 14:66–70. https://doi.org/10.1007/s10389-006-0024-x
doi: 10.1007/s10389-006-0024-x
Ashfaq A, Cronin N, Müller P (2022) Recent advances in machine learning for maximal oxygen uptake (VO
doi: 10.1016/j.imu.2022.100863
Bassett DR, Howley ET (2000) Limiting factors for maximum oxygen uptake and determinants of endurance performance. Med Sci Sports Exerc 32:70–84. https://doi.org/10.1097/00005768-200001000-00012
doi: 10.1097/00005768-200001000-00012
pubmed: 10647532
Booth FW, Roberts CK, Laye MJ (2012) Lack of exercise is a major cause of chronic diseases. Compr Physiol 2:1143–1211. https://doi.org/10.1002/cphy.c110025
doi: 10.1002/cphy.c110025
pubmed: 23798298
pmcid: 4241367
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
doi: 10.1023/A:1010933404324
Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. Taylor & Francis. https://doi.org/10.1201/9781315139470
doi: 10.1201/9781315139470
Buchfuhrer MJ, Hansen JE, Robinson TE et al (1983) Optimizing the exercise protocol for cardiopulmonary assessment. J Appl Physiol 55:1558–1564. https://doi.org/10.1152/jappl.1983.55.5.1558
doi: 10.1152/jappl.1983.55.5.1558
pubmed: 6643191
Burnley M, Vanhatalo A, Jones AM (2012) Distinct profiles of neuromuscular fatigue during muscle contractions below and above the critical torque in humans. J Appl Physiol 113:215–223. https://doi.org/10.1152/japplphysiol.00022.2012
doi: 10.1152/japplphysiol.00022.2012
pubmed: 22556396
Buysee DJ, Reynolds CF, Monk TH et al (1989) Pittsburgh Sleep Quality Index. J Clin Psychol Med Settings. https://doi.org/10.1037/t05178-000
doi: 10.1037/t05178-000
Caen K, Boone J, Bourgois JG et al (2020) Translating ramp VO
doi: 10.1249/MSS.0000000000002328
pubmed: 32118695
American College of Sports Medicine (ed) (2021) ACSMs guidelines for exercise testing and prescription, 11th edn. Wolters Kluwer, Philadelphia
Cunha F, Midgley A, Montenegro R et al (2015) Utility of a non-exercise VO
doi: 10.1055/s-0034-1395590
pubmed: 26038880
da Silva SC, Monteiro WD, Cunha FA et al (2012) Determination of best criteria to determine final and initial speeds within ramp exercise testing protocols. Pulm Med 2012:1–10. https://doi.org/10.1155/2012/542402
doi: 10.1155/2012/542402
Evans HJL, Ferrar KE, Smith AE et al (2015) A systematic review of methods to predict maximal oxygen uptake from submaximal, open circuit spirometry in healthy adults. J Sci Med Sport 18:183–188. https://doi.org/10.1016/j.jsams.2014.03.006
doi: 10.1016/j.jsams.2014.03.006
pubmed: 24721146
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
doi: 10.1214/aos/1013203451
Glaab T, Taube C (2022) Practical guide to cardiopulmonary exercise testing in adults. Respir Res 23:9. https://doi.org/10.1186/s12931-021-01895-6
doi: 10.1186/s12931-021-01895-6
pubmed: 35022059
pmcid: 8754079
Glas CAW (2010) Missing data. In: Peterson P, Baker E, McGaw B (eds) International encyclopedia of education, 3rd edn. Elsevier, Oxford, pp 283–288
doi: 10.1016/B978-0-08-044894-7.01346-4
Godin G, Shepard R (1985) A simple method to assess exercise behavior in the community. Can J Appl Sport Sci 10(3):141–146. https://doi.org/10.1097/00005768-199706001-00009
doi: 10.1097/00005768-199706001-00009
Hill DW, Poole DC, Smith JC (2002) The relationship between power and the time to achieve [Formula: see text]O2max. Med Sci Sports Exerc 34:709
Iannetta D, De Almeida AR, Ingram CP et al (2020) Evaluating the suitability of supra-PO
doi: 10.1152/ajpregu.00126.2020
pubmed: 32697652
pmcid: 7509256
Jobson JD (1991) Multiple linear regression. In: Jobson JD (ed) Applied multivariate data analysis: regression and experimental design. Springer, New York, pp 219–398
doi: 10.1007/978-1-4612-0955-3_4
Kokkinos P, Kaminsky LA, Arena R et al (2018) A new generalized cycle ergometry equation for predicting maximal oxygen uptake: the Fitness Registry and the Importance of Exercise National Database (FRIEND). Eur J Prev Cardiolog 25:1077–1082. https://doi.org/10.1177/2047487318772667
doi: 10.1177/2047487318772667
Langer RD, da Costa KG, Bortolotti H et al (2020) Phase angle is associated with cardiorespiratory fitness and body composition in children aged between 9 and 11 years. Physiol Behav 215:112772. https://doi.org/10.1016/j.physbeh.2019.112772
doi: 10.1016/j.physbeh.2019.112772
pubmed: 31837386
Li K, Yao S, Zhang Z et al (2022) Efficient gradient boosting for prognostic biomarker discovery. Bioinformatics 38:1631–1638. https://doi.org/10.1093/bioinformatics/btab869
doi: 10.1093/bioinformatics/btab869
pubmed: 34978570
pmcid: 10060728
Lindauer M, Feurer M, Eggensperger K, et al (2019) Towards assessing the impact of bayesian optimization’s own hyperparameters. arXiv. https://doi.org/10.48550/arXiv.1908.06674
Liu Y, Herrin J, Huang C et al (2022) Non-exercise machine learning models for maximal oxygen uptake prediction in national population surveys. medRxiv. https://doi.org/10.1101/2022.09.30.22280471
Myers J (2005) Applications of cardiopulmonary exercise testing in the management of cardiovascular and pulmonary disease. Int J Sports Med 26:S49–S55. https://doi.org/10.1055/s-2004-830515
doi: 10.1055/s-2004-830515
pubmed: 15702456
Myers J, Do D, Herbert W et al (1994) A nomogram to predict exercise capacity from a specific activity questionnaire and clinical data. Am J Cardiol 73:591–596. https://doi.org/10.1016/0002-9149(94)90340-9
doi: 10.1016/0002-9149(94)90340-9
pubmed: 8147307
Myers J, Bader D, Madhavan R, Froelicher V (2001) Validation of a specific activity questionnaire to estimate exercise tolerance in patients referred for exercise testing. Am Heart J 142:1041–1046. https://doi.org/10.1067/mhj.2001.118740
doi: 10.1067/mhj.2001.118740
pubmed: 11717610
Nohara Y, Matsumoto K, Soejima H, Nakashima N (2022) Explanation of machine learning models using Shapley additive explanation and application for real data in hospital. Comput Methods Programs Biomed 214:106584. https://doi.org/10.1016/j.cmpb.2021.106584
doi: 10.1016/j.cmpb.2021.106584
pubmed: 34942412
Poole DC, Jones AM (2017) Measurement of the maximum oxygen uptake [Formula: see text]O
Przednowek K, Barabasz Z, Zadarko-Domaradzka M et al (2018) Predictive modeling of VO
doi: 10.3390/app8112213
Ray S (2019) A quick review of machine learning algorithms. In: 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon), pp 35–39
Refaeilzadeh P, Tang L, Liu H (2016) Cross-validation. In: Liu L, Özsu MT (eds) Encyclopedia of database systems. Springer, New York, pp 1–7
Ross R, Blair SN, Arena R et al (2016) Importance of assessing cardiorespiratory fitness in clinical practice: a case for fitness as a clinical vital sign: a scientific statement from the American Heart Association. Circulation. https://doi.org/10.1161/CIR.0000000000000461
doi: 10.1161/CIR.0000000000000461
pubmed: 27881567
Saengsuwan J, Nef T, Hunt KJ (2017) A method for predicting peak work rate for cycle ergometer and treadmill ramp tests. Clin Physiol Funct Imaging 37:610–614. https://doi.org/10.1111/cpf.12344
doi: 10.1111/cpf.12344
pubmed: 29068162
Sarker IH (2021) Machine learning: algorithms, real-world applications and research directions. SN Comput Sci 2:160. https://doi.org/10.1007/s42979-021-00592-x
doi: 10.1007/s42979-021-00592-x
pubmed: 33778771
pmcid: 7983091
Schembre SM, Riebe DA (2011) Non-exercise estimation of VO
doi: 10.1080/1091367X.2011.568369
pubmed: 21927551
pmcid: 3173948
Shen T, Liu D, Lin Z et al (2022) A machine learning model to predict cardiovascular events during exercise evaluation in patients with coronary heart disease. JCM 11:6061. https://doi.org/10.3390/jcm11206061
doi: 10.3390/jcm11206061
pubmed: 36294382
pmcid: 9605581
Singh A, Thakur N, Sharma A (2016) A review of supervised machine learning algorithms. In: 2016 3rd international conference on computing for sustainable global development (INDIACom), pp 1310–1315
Song Y, Lu Y (2015) Decision tree methods: applications for classification and prediction. Shanghai Arch Psychiatry 27:130–135. https://doi.org/10.11919/j.issn.1002-0829.215044
doi: 10.11919/j.issn.1002-0829.215044
pubmed: 26120265
pmcid: 4466856
Sreevalsan-Nair J (2020) K-nearest neighbors. In: Daya Sagar BS, Cheng Q, McKinley J, Agterberg F (eds) Encyclopedia of mathematical geosciences. Springer International Publishing, Cham, pp 1–3
Tanaka H, Monahan KD, Seals DR (2001) Age-predicted maximal heart rate revisited. J Am Coll Cardiol 37:153–156. https://doi.org/10.1016/S0735-1097(00)01054-8
doi: 10.1016/S0735-1097(00)01054-8
pubmed: 11153730
Van Rossum G, Drake FL (2009) Python 3 reference manual. CreateSpace, Scotts Valley
Vanhatalo A, Fulford J, DiMenna FJ, Jones AM (2010) Influence of hyperoxia on muscle metabolic responses and the power–duration relationship during severe-intensity exercise in humans: a 31P magnetic resonance spectroscopy study. Exp Physiol 95:528–540. https://doi.org/10.1113/expphysiol.2009.050500
doi: 10.1113/expphysiol.2009.050500
pubmed: 20028850
Wier LT, Jackson AS, Ayers GW, Arenare B (2006) Nonexercise models for estimating [Formula: see text]O2max with waist girth, percent fat, or BMI. Med Sci Sports Exerc 38:555. https://doi.org/10.1249/01.mss.0000193561.64152