This study aimed to determine whether the fatigue induced by a mountain ultramarathon (MUM) led to changes in energy cost and kinematic during level and graded running. Pre- and post-race, 14 ultratrail runners ran on a level, uphill (5%) and downhill (5%) treadmill at 10 km · h(-1). Kinematic data were acquired using a photocell system. Post-race, the downhill energy cost increased by 13.1% (P < 0.001). No change was noted in level and uphill running. Duty factor and stride frequency were increased, whereas swing time, cycle time and stride length were decreased in all conditions (P < 0.05). Contact time was increased and the rate of force generation was decreased only in the uphill and downhill conditions (P < 0.05). Positive correlations were observed between performance time and the pre- to post-changes in the energy cost of level (r = 0.52, P = 0.04) and uphill running (r = 0.50, P = 0.04). MUM-induced fatigue resulted in physiological and spatiotemporal changes, though the response to fatigue varied considerably between running conditions. These changes resulted in a significant increment only in the downhill energy cost. Incorporating downhill locomotion in the training programmes of ultratrailers may help to improve performance-related physiological and biomechanical parameters.

Measurement of oxygen uptake during exercise ( ) is currently non-accessible to most individuals without expensive and invasive equipment. The goal of this pilot study was to estimate cycling from easy-to-obtain inputs, such as heart rate, mechanical power output, cadence and respiratory frequency. To this end, a recurrent neural network was trained from laboratory cycling data to predict values. Data were collected on 7 amateur cyclists during a graded exercise test, two arbitrary protocols (Prot-1 and -2) and an “all-out” Wingate test. In Trial-1, a neural network was trained with data from a graded exercise test, Prot-1 and Wingate, before being tested against Prot-2. In Trial-2, a neural network was trained using data from the graded exercise test, Prot-1 and 2, before being tested against the Wingate test. Two analytical models (Models 1 and 2) were used to compare the predictive performance of the neural network. Predictive performance of the neural network was high during both Trial-1 (MAE = 229(35) mlO₂min^-1, r = 0.94) and Trial-2 (MAE = 304(150) mlO₂min^-1, r = 0.89). As expected, the predictive ability of Models 1 and 2 deteriorated from Trial-1 to Trial-2. Results suggest that recurrent neural networks have the potential to predict the individual response from easy-to-obtain inputs across a wide range of cycling intensities.

Purpose: To examine the effects of the world’s most challenging mountain ultramarathon (MUM, 330 km, cumulative elevation gain of +24000 m) on the energy cost and kinematics of different uphill gaits. Methods: Before (PRE) and immediately after (POST) the competition, 19 male athletes performed three submaximal 5-min treadmill exercise trials in a randomized order: walking at 5 km·h-1, +20%; running at 6 km·h-1, +15%; and running at 8 km·h-1, +10%. During the three trials, energy cost was assessed using an indirect calorimetry system and spatiotemporal gait parameters were acquired with a floor-level high-density photoelectric cells system. Results: The average time of the study participants to complete the MUM was 129 h 43 min 48 s (range: 107 h 29 min 24 s to 144 h 21 min 0 s). Energy costs in walking (-11.5 ± 5.5%, P < 0.001), as well as in the first (-7.2 ± 3.1%, P = 0.01) and second (-7.0 ± 3.9%, P = 0.02) running condition decreased between PRE and POST, with a reduction both in the heart rate (-11.3%, -10.0%, and -9.3%, respectively) and oxygen uptake only for the walking condition (-6.5%). No consistent and significant changes in the kinematics variables were detected (P values from 0.10 to 0.96). Conclusion: Though fatigued after completing the MUM, the subjects were still able to maintain their uphill locomotion patterns noted at PRE. The decrease (improvement) in the energy costs was likely due to the prolonged and repetitive walking/running, reflecting a generic improvement in the mechanical efficiency of locomotion after ~130 h of uphill locomotion rather than constraints imposed by the activity on the musculoskeletal structure and function.

First and second ventilatory thresholds (VT₁ and VT₂) represent the boundaries of the moderate‐heavy and heavy‐severe exercise intensity. Currently, VTs are primarily detected visually from cardiopulmonary exercise test (CPET) data, beginning with an initial data screening followed by data processing and statistical analysis. Automated VT detection is a challenging task owing to the high signal to noise ratio typical of CPET data. Recurrent neural networks describe a machine learning form of Artificial Intelligence that can be used to uncover complex non‐linear relationships between input and output variables. Here we proposed detection of VTs using a single neural network classifier, trained with a database of 228 laboratory CPET data. We tested the neural network performance against the judgement of 7 couples of board‐certified exercise‐physiologists on 25 CPET tests. The neural network achieved expert‐level performances across the tasks (mean absolute error was 9.5% (r = 0.79) and 4.2% (r = 0.94) for VT₁ and VT₂, respectively). Estimation errors are compatible with the typical error of the current gold standard visual methodology. The neural network demonstrated VT detecting and exercise intensity level classifying at a high competence level. Neural networks could potentially be embedded in CPET hardware/software to extend the reach of exercise physiologists beyond their laboratories.

The problem of the automatic determination of the first and second ventilatory thresholds (VT1 and VT2) from cardiopulmonary exercise test (CPET) still leads to controversy. The reliability of the gold standard methodology (i.e. expert visual inspection) feeds into the debate and several authors call for more objective automatic methods to be used in the clinical practice. In this study, we present a framework based on a collaborative approach, where a web‐application was used to crowd‐source a large number (1245) of CPET data of individuals with different aerobic fitness. The resulting database was used to train and test an artificial intelligence (i.e. a convolutional neural network) algorithm. This automatic classifier is currently implemented in another web‐application and was used to detect the ventilatory thresholds in the available CPET. A total of 206 CPET were used to evaluate the accuracy of the estimations against the expert opinions. The neural network was able to detect the ventilatory thresholds with an average mean absolute error of 178 (198) mlO₂/min (11.1%, r = 0.97) and 144 (149) mlO₂/min (6.1%, r = 0.99), for VT1 and VT2 respectively. The performance of the neural network in detecting VT1 deteriorated in case of individuals with poor aerobic fitness. Our results suggest the potential for a collective intelligence system to outperform isolated experts in ventilatory thresholds detection. However, the inclusion of a larger number of VT1 examples certified by a community of experts will be likely needed before the abilities of this collective intelligence can be translated into the clinical use of CPET.