Search

We present a personalized approach for frequent fitness monitoring in road cycling solely relying on sensor data collected during bike rides and without the need for maximal effort tests. We use competition and training data of three world-class cyclists of Team Jumbo-Visma to construct personalised heart rate models that relate the heart rate during exercise to the pedal power signal. Our model captures the non-trivial dependency between exertion and corresponding response of the heart rate, which we show can be effectively estimated by an exponential kernel. To construct the daily heart rate models that are required for day-to-day fitness estimation, we aggregate all sessions in the previous week and apply sampling. On average, the explained variance of our models is 0.86, which we demonstrate is more than twice as large as for models that ignore the temporal integration involved in the heart's response to exercise. We show that the fitness of a cyclist can be monitored by tracking developments of parameters of our heart rate models. In particular, we monitor the decay constant of the kernel involved, and also analytically determine virtual aerobic and anaerobic thresholds. We demonstrate that our findings for the virtual anaerobic threshold on average agree with the results of exercise tests. We believe this work is an important step forward in performance optimization by opening up avenues for switching to adaptive training programs that take into account the current physiological state of an athlete.

Accumulating evidence suggests that most elite cyclists have lower bone mineral density (BMD) values when compared with their nonelite counterparts (1) or sedentary young males (2, 3). This raises the question whether these ostensibly healthy athletes have a higher acute bone fracture risk and a higher risk of osteoporosis and associated comorbidities later in life. Although treatment of low BMD seems warranted in elite cyclists, the benefits of treatment for health and performance in this population remain to be established. In this viewpoint, we describe the etiology and consequences of impaired bone health in elite cyclists and discuss the need for interventions to optimize bone health in this unique population.

This study aims to describe the intensity and load demands of different stage types within a cycling Grand Tour. Nine professional cyclists, whom are all part of the same World-Tour professional cycling team, participated in this investigation. Competition data were collected during the 2016 Giro d'Italia. Stages within the Grand Tour were classified into four categories: flat stages (FLAT), semi-mountainous stages (SMT), mountain stages (MT) and individual time trials (TT). Exercise intensity, measured with different heart rate and power output based variables, was highest in the TT compared to other stage types. During TT's the main proportion of time was spent at the high-intensity zone, whilst the main proportion of time was spent at low intensity for the mass start stage types (FLAT, SMT, MT). Exercise load, quantified using Training Stress Score and Training Impulse, was highest in the mass start stage types with exercise load being highest in MT (329, 359 AU) followed by SMT (280, 311 AU) and FLAT (217, 298 AU). Substantial between-stage type differences were observed in maximal mean power outputs over different durations. FLAT and SMT were characterised by higher short-duration maximal power outputs (5-30 s for FLAT, 30 s-2 min for SMT) whilst TT and MT are characterised by high longer duration maximal power outputs (10 min). The results of this study contribute to the growing body of evidence on the physical demands of stage types within a cycling Grand Tour.

This study examined if short-duration record power outputs can be predicted with the Anaerobic Power Reserve (APR) model in professional cyclists using a field-based approach. Additionally, we evaluated if modified model parameters could improve predictive ability of the model. Twelve professional cyclists (V̇O

This study evaluated the changes in ratios of different intensity (rating of perceived exertion; RPE, heart rate; HR, power output; PO) and load measures (session-RPE; sRPE, individualized TRIMP; iTRIMP, Training Stress Score; TSS) in professional cyclists. RPE, PO and HR data was collected from twelve professional cyclists (VO2max 75 +/- 6ml.min.kg(-1)) during a two-week baseline training period and during two cycling Grand Tours. Subjective:objective intensity (RPE:HR, RPE:PO) and load (sRPE:iTRIMP, sRPE:TSS) ratios and external:internal intensity (PO:HR) and load (TSS:iTRIMP) ratios were calculated for every session. Moderate to large increases in the RPE:HR, RPE:PO and sRPE:TSS ratios (d=0.79-1.79) and small increases in the PO:HR and sRPE:iTRIMP ratio (d=0.21-0.41) were observed during Grand Tours compared to baseline training data. Differences in the TSS:iTRIMP ratio were trivial to small (d=0.03-0.27). Small to moderate week-to-week changes (d=0.21-0.63) in the PO:HR, RPE:PO, RPE:HR, TSS:iTRIMP, sRPE:iTRIMP and sRPE:TSS were observed during the Grand Tour. Concluding, this study shows the value of using ratios of intensity and load measures in monitoring cyclists. Increases in ratios could reflect progressive fatigue that is not readily detected by changes in solitary intensity/load measures.

Purpose:To assess if short-duration (5 to ~300 s) high-power performance can accurately be predicted using the anaerobic power reserve (APR) model in professional cyclists.Methods:Data from 4 professional cyclists from a World Tour cycling team were used. Using the maximal aerobic power, sprint peak power output, and an exponential constant describing the decrement in power over time, a power-duration relationship was established for each participant. To test the predictive accuracy of the model, several all-out field trials of different durations were performed by each cyclist. The power output achieved during the all-out trials was compared with the predicted power output by the APR model.Results:The power output predicted by the model showed very large to nearly perfect correlations to the actual power output obtained during the all-out trials for each cyclist (r = .88 ± .21, .92 ± .17, .95 ± .13, and .97 ± .09). Power output during the all-out trials remained within an average of 6.6% (53 W) of the predicted power output by the model.Conclusions:This preliminary pilot study presents 4 case studies on the applicability of the APR model in professional cyclists using a field-based approach. The decrement in all-out performance during high-intensity exercise seems to conform to a general relationship with a single exponential-decay model describing the decrement in power vs increasing duration. These results are in line with previous studies using the APR model to predict performance during brief all-out trials. Future research should evaluate the APR model with a larger sample size of elite cyclists.