Nonlinear Modeling of Cardiovascular Response to Exercise

This study experimentally investigates the relationships between central cardiovascular variables and oxygen uptake based on nonlinear analysis and modeling. Ten healthy subjects were studied using cycleergometry exercise tests with constant workloads ranging from 25 Watt to 125 Watt. Breath by breath gas exchange, heart rate, cardiac output, stroke volume and blood pressure were measured at each stage. The modeling results proved that the nonlinear modeling method (Support Vector Regression) outperforms traditional regression method (reducing Estimation Error between 59% and 80%, reducing Testing Error between 53% and 72%) and is the ideal approach in the modeling of physiological data, especially with small training data set.

[1]  T. Fujinami,et al.  Impedance cardiography for estimating cardiac output during submaximal and maximal work. , 1978, Journal of applied physiology: respiratory, environmental and exercise physiology.

[2]  Andrey V. Savkin,et al.  Estimation of Oxygen Consumption for Moderate Exercises by Using a Hammerstein Model , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  J. Reeves,et al.  Circulatory changes in man during mild supine exercise. , 1961, Journal of applied physiology.

[4]  L N KATZ,et al.  Effect of training on response of cardiac output to muscular exercise in athletes. , 1955, Journal of applied physiology.

[5]  Artur Lichtenberg,et al.  Non-invasive cardiac output determination by two-dimensional independent Doppler during and after cardiac surgery. , 2005, The Annals of thoracic surgery.

[6]  Bruce D. Johnson,et al.  Relationship between cardiac output and oxygen consumption during upright cycle exercise in healthy humans. , 2006, Journal of applied physiology.

[7]  P. G. Iatridis,et al.  Human Circulation: Regulation During Physical Stress , 1987 .

[8]  J. Pivarnik,et al.  Treadmill economy in girls and women matched for height and weight. , 2000, Journal of applied physiology.

[9]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[10]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[11]  B. Saltin,et al.  CARDIAC OUTPUT DURING SUBMAXIMAL AND MAXIMAL WORK. , 1964, Journal of applied physiology.

[12]  Federico Girosi,et al.  An Equivalence Between Sparse Approximation and Support Vector Machines , 1998, Neural Computation.

[13]  P. Paré,et al.  Prediction of heart rate and oxygen uptake during incremental and maximal exercise in healthy adults. , 1994, Chest.

[14]  Lu Wang,et al.  Identification and Control for Heart Rate Regulation During Treadmill Exercise , 2007, IEEE Transactions on Biomedical Engineering.

[15]  A.V. Savkin,et al.  Estimation of Walking Energy Expenditure by Using Support Vector Regression , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[16]  Kenneth R. Turley,et al.  Cardiovascular responses to treadmill and cycle ergometer exercise in children and adults , 1997 .

[17]  Valeriy V. Gavrishchaka,et al.  Volatility forecasting from multiscale and high-dimensional market data , 2003, Neurocomputing.

[18]  J. Reeves,et al.  Cardiac output response to standing and treadmill walking. , 1961, Journal of applied physiology.

[19]  Stéphane Dufour,et al.  Cardiac output and oxygen release during very high-intensity exercise performed until exhaustion , 2004, European Journal of Applied Physiology.

[20]  T. Rowland,et al.  Cardiac responses to maximal upright cycle exercise in healthy boys and men. , 1997, Medicine and science in sports and exercise.