A computational predictor of the anaerobic mechanical power outputs from a clinical exercise stress test

We previously were able to predict the anaerobic mechanical power outputs using features taken from a maximal incremental cardiopulmonary exercise stress test (CPET). Since a standard aerobic exercise stress test (with electrocardiogram and blood pressure measurements) has no gas exchange measurement and is more popular than CPET, our goal, in the current paper, was to investigate whether features taken from a clinical exercise stress test (GXT), either submaximal or maximal, can predict the anaerobic mechanical power outputs to the same level as we found with CPET variables. We have used data taken from young healthy subjects undergoing CPET aerobic test and the Wingate anaerobic test, and developed a computational predictive algorithm, based on greedy heuristic multiple linear regression, which enabled the prediction of the anaerobic mechanical power outputs from a corresponding GXT measures (exercise test time, treadmill speed and slope). We found that for submaximal GXT of 85% age predicted HRmax, a combination of 3 and 4 variables produced a correlation of r = 0.93 and r = 0.92 with % error equal to 15 ± 3 and 16 ± 3 on the validation set between real and predicted values of the peak and mean anaerobic mechanical power outputs (p < 0.001), respectively. For maximal GXT (100% of age predicted HRmax), a combination of 4 and 2 variables produced a correlation of r = 0.92 and r = 0.94 with % error equal to 12 ± 2 and 14 ± 3 on the validation set between real and predicted values of the peak and mean anaerobic mechanical power outputs (p < 0.001), respectively. The newly developed model allows to accurately predict the anaerobic mechanical power outputs from a standard, submaximal and maximal GXT. Nevertheless, in the current study the subjects were healthy, normal individuals and therefore the assessment of additional subjects is desirable for the development of a test applicable to other populations.

Validity of the Training-Load Concept

Training load (TL) is a widely used concept in training prescription and monitoring and is also recognized as as an important tool for avoiding athlete injury, illness, and overtraining. With the widespread adoption of wearable devices, TL metrics are used increasingly by researchers and practitioners worldwide. Conceptually, TL was proposed as a means to quantify a dose of training and used to predict its resulting training effect. However, TL has never been validated as a measure of training dose, and there is a risk that fundamental problems related to its calculation are preventing advances in training prescription and monitoring. Specifically, we highlight recent studies from our research groups where we compare the acute performance decrement measured following a session with its TL metrics. These studies suggest that most TL metrics are not consistent with their notional training dose and that the exercise duration confounds their calculation. These studies also show that total work done is not an appropriate way to compare training interventions that differ in duration and intensity. We encourage scientists and practitioners to critically evaluate the validity of current TL metrics and suggest that new TL metrics need to be developed.

Effect of protocol on peak power output in continuous incremental cycle exercise tests

PURPOSE

Peak power output ([Formula: see text]peak) in an incremental exercise test (EXT) is considered an important predictor of performance for cyclists. However, [Formula: see text]peak is protocol dependent. The purpose of this study was to model the effect of EXT design on [Formula: see text]peak.

METHODS

An adapted version of a previously developed mathematical model was used. For the purpose of validity testing, we compared predicted [Formula: see text]peak differences (predicted Δ[Formula: see text]peak) with actual Δ[Formula: see text]peak found in sports science literature.

RESULTS

The model quantified Δ[Formula: see text]peak between 36 EXT designs with stage durations in the range 1-5 min and increments in the range 10-50 W. Predicted Δ[Formula: see text]peak and actual Δ[Formula: see text]peak across a wide range of performance levels of cyclists were in good agreement. Depending on the specific combination of increment and stage duration, [Formula: see text]peak may be widely different or equivalent. A minimum difference in increment (5 W) or in stage duration (1 min) already results in significantly different [Formula: see text]peak. In EXTs having the same ratio between increment and stage duration, [Formula: see text]peak in the EXT with the shortest stage duration or the greatest increment is significantly higher. Tests combining 15 W, 25 W or 40 W increments with 2, 3 and 4 min stage durations, respectively, are 'special' in that their [Formula: see text]peak approximates the power output associated with maximal oxygen uptake ([Formula: see text]).

CONCLUSIONS

The modeling results allow comparison of [Formula: see text]peak between widely different EXT designs. Absolute performance level does not affect Δ[Formula: see text]peak. [Formula: see text]peak15/2, [Formula: see text]peak25/3 and [Formula: see text]peak40/4 constitute a practical physiologic reference for performance diagnostics and exercise intensity prescription.

Prediction of the Wingate anaerobic mechanical power outputs from a maximal incremental cardiopulmonary exercise stress test using machine-learning approach

The Wingate Anaerobic Test (WAnT) is a short-term maximal intensity cycle ergometer test, which provides anaerobic mechanical power output variables. Despite the physiological significance of the variables extracted from the WAnT, the test is very intense, and generally applies for athletes. Our goal, in this paper, was to develop a new approach to predict the anaerobic mechanical power outputs using maximal incremental cardiopulmonary exercise stress test (CPET). We hypothesized that maximal incremental exercise stress test hold hidden information about the anaerobic components, which can be directly translated into mechanical power outputs. We therefore designed a computational model that included aerobic variables (features), and used a new computational \ predictive algorithm, which enabled the prediction of the anaerobic mechanical power outputs. We analyzed the chosen predicted features using clustering on a network. For peak power (PP) and mean power (MP) outputs, the equations included six features and four features, respectively. The combination of these features produced a prediction model of r = 0.94 and r = 0.9, respectively, on the validation set between the real and predicted PP/MP values (P< 0.001). The newly predictive model allows the accurate prediction of the anaerobic mechanical power outputs at high accuracy. The assessment of additional tests is desired for the development of a robust application for athletes, older individuals, and/or non-healthy populations.

Reliability of Physiological Attributes and Their Association With Stochastic Cycling Performance

Purpose:

To assess the reliability of a 5-min-stage graded exercise test (GXT) and determine the association between physiological attributes and performance over stochastic cycling trials of varying distance.

Methods:

Twenty-eight well-trained male cyclists performed 2 GXTs and either a 30-km (n = 17) or a 100-km stochastic cycling time trial (n = 9). Stochastic cycling trials included periods of high-intensity efforts for durations of 250 m, 1 km, or 4 km depending on the test being performing.

Results:

Maximal physiological attributes were found to be extremely reliable (maximal oxygen uptake [VO2max]: coefficient of variation [CV] 3.0%, intraclass correlation coefficient [ICC] .911; peak power output [PPO]: CV 3.0%, ICC .913), but a greater variability was found in ventilatory thresholds and economy. All physiological variables measured during the GXT, except economy at 200 W, were correlated with 30-km cycling performance. Power output during the 250-m and 1-km efforts of the 30-km trial were correlated with VO2max, PPO, and the power output at the second ventilatory threshold (r = .58–.82). PPO was the only physiological attributed measured during the GXT to be correlated with performance during the 100-km cycling trial (r = .64).

Conclusions:

Many physiological variables from a reliable GXT were associated with performance over shorter (30-km) but not longer (100-km) stochastic cycling trials.

Early prediction of the highest workload in incremental cardiopulmonary tests

Incremental tests are widely used in cardiopulmonary exercise testing, both in the clinical domain and in sport sciences. The highest workload (denoted W peak ) reached in the test is key information for assessing the individual body response to the test and for analyzing possible cardiac failures and planning rehabilitation, and training sessions. Being physically very demanding, incremental tests can significantly increase the body stress on monitored individuals and may cause cardiopulmonary overload. This article presents a new approach to cardiopulmonary testing that addresses these drawbacks. During the test, our approach analyzes the individual body response to the exercise and predicts the W peak value that will be reached in the test and an evaluation of its accuracy. When the accuracy of the prediction becomes satisfactory, the test can be prematurely stopped, thus avoiding its entire execution. To predict W peak , we introduce a new index, the CardioPulmonary Efficiency Index (CPE), summarizing the cardiopulmonary response of the individual to the test. Our approach analyzes the CPE trend during the test, together with the characteristics of the individual, and predicts W peak . A K-nearest-neighbor-based classifier and an ANN-based classier are exploited for the prediction. The experimental evaluation showed that the W peak value can be predicted with a limited error from the first steps of the test.