Predicting oxygen uptake responses during cycling at varied intensities using an artificial neural network

Open access

Summary

Study aim: Oxygen Uptake (VO2) is avaluable metric for the prescription of exercise intensity and the monitoring of training progress. However, VO2 is difficult to assess in anon-laboratory setting. Recently, an artificial neural network (ANN) was used to predict VO2 responses during aset walking protocol on the treadmill [9]. The purpose of the present study was to test the ability of an ANN to predict VO2 responses during cycling at self-selected intensities using Heart Rate (HR), time derivative of HR, power output, cadence, and body mass data.

Material and methods: 12 moderately-active adult males (age: 21.1 ± 2.5 years) performed a50-minute bout of cycling at a variety of exercise intensities. VO2, HR, power output, and cadence were recorded throughout the test. An ANN was trained, validated and tested using the following inputs: HR, time derivative of HR, power output, cadence, and body mass. A twelve-fold hold-out cross validation was conducted to determine the accuracy of the model.

Results: The ANN accurately predicted the experimental VO2 values throughout the test (R2 = 0.91 ± 0.04, SEE = 3.34 ± 1.07 mL/kg/min).

Discussion: This preliminary study demonstrates the potential for using an ANN to predict VO2 responses during cycling at varied intensities using easily accessible inputs. The predictive accuracy is promising, especially considering the large range of intensities and long duration of exercise. Expansion of these methods could allow ageneral algorithm to be developed for a more diverse population, improving the feasibility of oxygen uptake assessment.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • 1. Abraham A. (2005) Handbook of Measuring System Design: Artificial Neural Networks. Edited by P. H. Sydenham and Richard Thorn. Chichester England: Wiley.

  • 2. Akalan C. Robergs R. Kravitz L. (2008) Prediction of VO2max from an Individualized Submaximal Cycle Ergometer Protocol. J. Exerc. Physiol. Online 11(2): 1–17.

  • 3. Akay F. Abut F. (2015) Machine Learning and Statistical Methods for the Prediction of Maximal Oxygen Uptake: Recent Advances. Medical Devices: Evidence and Research. DOI: 10.2147/MDER.S57281.

  • 4. Akay F. Inan C. Bradshaw I.D. George J.D. (2009) Support Vector Regression and Multilayer Feed Forward Neural Networks for Non-Exercise Prediction of VO2max. Expert Syst. Appl. 36(6): 10112–10119. DOI: 10.1016/j.eswa.2009.01.009.

  • 5. Al-Mallah Mouaz H. Elshawi R. Ahmed A.M. Qureshi W.T. Brawner C.A. Blaha M.J. Ahmed H.M. Ehrman J.K. Keteyian S.J. Sakr S. (2017) Using Machine Learning to Define the Association between Cardiorespiratory Fitness and All-Cause Mortality (from the Henry Ford Exercise Testing Project). Am. J. Card. 120(11): 2078–2084. DOI: 10.1016/j.amjcard.2017.08.029.

  • 6. American College of Sports Medicine and Pescatello L.S. (2014) ACSM’s Guidelines for Exercise Testing and Prescription. Philadelphia: Wolters Kluwer Health/Lippincott Williams & Wilkins.

  • 7. Astrand I. (1967) Aerobic Work Capacity: Its Relation to Age Sex and Other Factors. Circulation Res. 211–217.

  • 8. Basset D. Howley E. (2000) Limiting Factors for Maximum Oxygen Uptake and Determinants of Endurance Performance. Med. Sci. Sports Exerc. 32 (1): 70–84.

  • 9. Beltrame T. Amelard R. Wong A. Hughson R.L. (2017) Prediction of Oxygen Uptake Dynamics by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living. Sci. Rep. 7 (April): 45738. DOI: 10.1038/srep45738.

  • 10. Beltrame T. Amelard R. Villar R. Shafiee M.J. WongA. Hughson R.L. (2016) Estimating Oxygen Uptake and Energy Expenditure during Treadmill Walking by Neural Network Analysis of Easy-to-Obtain Inputs. J. Appl. Physiol. 121(5): 1226–1233. DOI: 10.1152/japplphysiol.00600.2016.

  • 11. Beltrame T. Amelard R. Wong A. Hughson R.L. (2018) Extracting Aerobic System Dynamics during Unsupervised Activities of Daily Living Using Wearable Sensor Machine Learning Models. J. Appl. Physiol. 124(2): 473–481. DOI: 10.1152/japplphysiol.00299.2017.

  • 12. Blair S.N. Kampert J.B. Kohl H.W. Barlow C.E. Macera C.A. Paffenbarger R.S. Gibbons L.W. (1996) Influences of Cardiorespiratory Fitness and Other Precursors on Cardiovascular Disease and All-Cause Mortality in Men and Women. JAMA 276(3): 205–210.

  • 13. Capostagno B. Lambert M.I. Lamberts R.P. (2016) A Systematic Review of Submaximal Cycle Tests to Predict Monitor and Optimize Cycling Performance. Int. J. Sports Physiol. Perf. 11(6): 707–714. DOI: 10.1123/ijspp.2016-0174.

  • 14. Chilibeck P.D. Paterson D.H. Petrella R.J. Cunningham D.A. (1996) The Influence of Age and Cardiorespiratory Fitness on Kinetics of Oxygen Uptake. Can. J. Appl. Physiol. 21(3): 185–196.

  • 15. Crouter S.E. Clowers K.G. Bassett D. (2006) A Novel Method for Using Accelerometer Data to Predict Energy Expenditure. J. Appl. Physiol. 100(4): 1324–1331. DOI: 10.1152/japplphysiol.00818.2005.

  • 16. Ekelund L.G. Haskell W.L. Johnson J.L. Whaley F.S. Criqui M.H. Sheps D.S. (1988) Physical Fitness as a Predictor of Cardiovascular Mortality in Asymptomatic North American Men. N. Engl. J. Med. 319(21): 1379–1384. DOI: 10.1056/NEJM198811243192104.

  • 17. Erikssen G. Liestøl K. Bjørnholt J. Thaulow E. Sandvik L. Erikssen J. (1998) Changes in Physical Fitness and Changes in Mortality. Lancet 352(9130): 759–762.

  • 18. Faul F. Erdfelder E Lang A.G. Buchner A. (2007) G*Power 3: AFlexible Statistical Power Analysis Program for the Social Behavioral and Biomedical Sciences. Behav. Res. Methods 39(2): 175–191.

  • 19. García-Massó X. Serra-Añó P. García-Raffi L. Sánchez-Pérez E. Giner-Pascual M. González L.M. (2014) Neural Network for Estimating Energy Expenditure in Paraplegics from Heart Rate. Int. J. Sports Med. 35(12): 1037–1043. DOI: 10.1055/s-0034-1368722.

  • 20. Gavin H.P. (2017) The Levenberg-Marquardt Method for Nonlinear Least Squares Curve-Fitting Problems. Department of Civil and Environmental Engineering Duke University.

  • 21. Guazzi M. Adams V. Conraads V. Halle M. Mezzani A. Vanhees L. Arena R. Fletcher G.F. Forman D.E. Kitzman D.W. Lavie C.J. Myers J. (2012) Clinical Recommendations for Cardiopulmonary Exercise Testing Data Assessment in Specific Patient Populations. Circulation 126 (18): 2261–2274. DOI: 10.1161/CIR.0b013e31826fb946.

  • 22. Gulati M. Black H.R. Shaw L.J. Arnsdorf M.F. Bairey Merz C.N. Lauer M.S. Marwick T.H. Pandey D.K. Wicklund R.H. Thisted R.A. (2005) The Prognostic Value of aNomogram for Exercise Capacity in Women. N. Engl. J. Med. 353(5): 468–75. DOI: 10.1056/NEJMoa044154.

  • 23. Hills A.P. Byrne N.M. Ramage A.J. (1998) Submaximal Markers of Exercise Intensity. J. Sports Sci. 16(sup1): 71–76. DOI: 10.1080/026404198366696.

  • 24. Howley E. Bassett D. Welch H. (1995) Criteria for Maximal Oxygen Uptake: AReview and Commentary. Med. Sci. Sports Exerc. 27(9): 1292–1301.

  • 25. Jamnick N.A. By S. Pettitt C.D. Pettitt R.W. (2016) Comparison of the YMCA and aCustom Submaximal Exercise Test for Determining VO2max. Med. Sci. Sports Exerc. 48(2): 254–259. DOI: 10.1249/MSS.0000000000000763.

  • 26. Katch V. Weltman A Sady S. Freedson P. (1978) Validity of the Relative Percent Concept for Equating Training Intensity. Eur. J. Appl. Physiol. Occup. Physiol. 39(4): 219–227.

  • 27. Kemps H.M.C. Schep G. Hoogsteen J. Thijssen E.J.M. De Vries W.R. Zonderland M.L. Doevendans P. (2009) Oxygen Uptake Kinetics in Chronic Heart Failure: Clinical and Physiological Aspects. Neth. Heart J. 17(6): 238–244.

  • 28. Lin C.W. Yang Y.T.C. Wang J.S. Yang Y.C. (2012) AWearable Sensor Module with aNeural-Network-Based Activity Classification Algorithm for Daily Energy Expenditure Estimation. IEEE Trans. Inf. Tech. Biomed. 16(5): 991–998. DOI: 10.1109/TITB.2012.2206602.

  • 29. Liu Y. Starzyk J.A. Zhu Z. (2007) Optimizing Number of Hidden Neurons in Neural Networks. Artif. Intell. Appl. 138–143.

  • 30. Mann B.P. Khasawneh F.A. Fales R. (2011) Using Information to Generate Derivative Coordinates from Noisy Time Series. Commun. Nonlinear Sci. Numer. Simul. 16(8): 2999–3004. DOI: 10.1016/j.cnsns.2010.11.011.

  • 31. Mazzoleni M.J. Battaglini C.L. Martin K.J. Coffman E.M. Ekaidat J.A. Wood W.A. Mann B.P. (2017) A Dynamical Systems Approach for the Submaximal Prediction of Maximum Heart Rate and Maximal Oxygen Uptake. Sports Eng. 21(1): 31–41. DOI: 10.1007/s12283-017-0242-1.

  • 32. Mazzoleni M.J. Battaglini C.L. Martin K.J. Coffman E.M. Wood W.A. Mann B.P. (2016) Modeling and Predicting Heart Rate Dynamics across a Broad Range of Transient Exercise Intensities during Cycling. Sports Eng. 19(2): 117–127. DOI: 10.1007/s12283-015-0193-3.

  • 33. Morris M. Lamb K. Cotterrell D. Buckley J. (2009) Predicting Maximal Oxygen Uptake via a Perceptually Regulated Exercise Test (PRET) J. Exerc. Sci. Fit. 7 (2): 122–128.

  • 34. Myers J. Prakash M. Froelicher V. Do D. Partington S. Atwood J.A. (2002) Exercise Capacity and Mortality among Men Referred for Exercise Testing. N. Engl. J. Med. 346 (11): 793–801. DOI: 10.1056/NEJMoa011858.

  • 35. Nevill A.M. Cooke C. B. (2017) The Dangers of Estimating VO2max Using Linear Nonexercise Prediction Models. Med. Sci. Sports Exerc. 49(5): 1036-1042. DOI: 10.1249/MSS.0000000000001178.

  • 36. Plasqui G. Westerterp K.R. (2005) Accelerometry and Heart Rate as aMeasure of Physical Fitness: Proof of Concept: Med. Sci. Sports Exerc. 37(5): 872–76. DOI: 10.1249/01.MSS.0000161805.61893.C0.

  • 37. Poole D.C. Jones A.M. (2012) Oxygen Uptake Kinetics. In Compr. Physiol. edited by Ronald Terjung. Hoboken NJ USA: John Wiley & Sons Inc. DOI: wiley.com/10.1002/cphy.c100072.

  • 38. Robergs R.A. Landwehr R. (2002) The Surprising History of the ‘HRmax= 220-Age’ equation. J. Exerc. Physiol. Online 5(2): 1–10.

  • 39. Ross R. Blair S.N. Arena R. Church R.S. Després J.P. Franklin B.A. Haskell W.L. (2016) Importance of Assessing Cardiorespiratory Fitness in Clinical Practice: ACase for Fitness as aClinical Vital Sign: AScientific Statement from the American Heart Association. Circulation CIR–0000000000000461.

  • 40. Rothney M.P. Neumann M. Béziat A. Chen K.Y. (2007) An Artificial Neural Network Model of Energy Expenditure Using Nonintegrated Acceleration Signals. J. Appl. Physiol. 103(4): 1419–1427. DOI: 10.1152/japplphysiol.00429.2007.

  • 41. Ruch N. Joss F. Jimmy G. Melzer K. Hänggi J. Mäder U. (2013) Neural Network versus Activity-Specific Prediction Equations for Energy Expenditure Estimation in Children. J. Appl. Physiol. 115(9): 1229–1236. DOI: 10.1152/japplphysiol.01443.2012.

  • 42. Sandvik L. Erikssen J. Thaulow E. Erikssen G. Mundal R. Rodahl K. (1993) Physical Fitness as a Predictor of Mortality among Healthy Middle-Aged Norwegian Men. N. Engl. J. Med. 328(8): 533–537. DOI: 10.1056/NEJM199302253280803.

  • 43. Snell P.G. Stray-Gundersen J. Levine B.D. Hawkins M.N. Raven P.B. (2007) Maximal Oxygen Uptake as aParametric Measure of Cardiorespiratory Capacity. Med. Sci. Sports Exerc. 39(1): 103–107. DOI: 10.1249/01.mss.0000241641.75101.64.

  • 44. Soares de Araújo C.G. Duarte C.V. (2015) Maximal Heart Rate in Young Adults: AFixed 188bpm Outperforms Values Predicted by aClassical Age-Based Equation. Int. J. Cardiol. 184: 609–610. DOI: 10.1016/j.ijcard.2015.02.043.

  • 45. Staudenmayer J. Pober D. Crouter S. Bassett D. Freedson P. (2009) An Artificial Neural Network to Estimate Physical Activity Energy Expenditure and Identify Physical Activity Type from an Accelerometer. J. Appl. Physiol. 107(4): 1300–1307. DOI: 10.1152/japplphysiol.00465.2009.

  • 46. Stirling J. Zakynthinaki M. Saltin B. (2005) A Model of Oxygen Uptake Kinetics in Response to Exercise: Including aMeans of Calculating Oxygen Demand/Deficit/Debt. Bull. Math. Biol. 67(5): 989–1015. DOI: 10.1016/j.bulm.2004.12.005.

  • 47. Stirling J.R. Zakynthinaki M.S. Billat V. (2008) Modeling and Analysis of the Effect of Training on VO2 Kinetics and Anaerobic Capacity. Bull. Math. Bio. 70(5): 1348–1370. DOI: 10.1007/s11538-008-9302-9.

  • 48. Stringer W. Hansen J. Wasserman K. (1997) Cardiac Output Estimated Noninvasively from Oxygen Uptake during Exercise. J. Appl. Physiol. 82(3): 908-912. DOI: 10.1152/jappl.1997.82.3.908.

  • 49. Swain D.P. Abernathy K.S. Smith C.S. Lee S.J. Bunn S.A. (1994) Target Heart Rates for the Development of Cardiorespiratory Fitness. Med. Sci. Sports. Exerc. 26(1): 112–116.

  • 50. Wright S.P. Hall Brown T.S. Collier S.R. Sandberg K. (2017) How Consumer Physical Activity Monitors Could Transform Human Physiology Research. Am. J. Physiol. Regul. Integr. Comp. Physiol. 312(3): R358–367. DOI: 10.1152/ajpregu.00349.2016.

  • 51. Yamaji K. Miyashita M. Shepharo R.J. (1978) Relationship between Heart Rate and Relative Oxygen Intake in Male Subjects Aged 10 to 27 Years. J. Hum. Ergol. 7 (1): 29–39.

  • 52. Yardley M. Havik O.E. Grov I. Relbo A. Gullestad L. Nytrøen K. (2016) Peak Oxygen Uptake and Self-Reported Physical Health Are Strong Predictors of Long-Term Survival after Heart Transplantation. Clin. Transplant. 30(2): 161–169. DOI: 10.1111/ctr.12672.

  • 53. Żołądź J.A. Duda K. Majerczak J. (1998) Oxygen Uptake Does Not Increase Linearly at High Power Outputs during Incremental Exercise Test in Humans. Eur. J. Appl. Physiol. Occup. Physiol. 77(5): 445–451.

Search
Journal information
Impact Factor


CiteScore 2018: 0.38

SCImago Journal Rank (SJR) 2018: 0.144
Source Normalized Impact per Paper (SNIP) 2018: 0.432

Cited By
Metrics
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 302 302 82
PDF Downloads 194 194 26