Many popular sporting codes feature some derivative of ‘sprinting’ as a central tenant of performance. This ranges from sports where sprinting ability is the sole measure of success, such as the 100-m dash, to sports requiring athletes to sprint while moving an external mass, such as the bobsled. The relationship between sprinting acceleration and practical on-field success is not synonymous across all sporting disciplines. For example, a rugby player has little need for the same ability to generate high levels of velocity that are commonly witnessed in 200-m sprinters. In contrast, a 200-m sprinter is typically much lighter than the average rugby player, and never needs to partake in recurrent low-velocity collisions and driving forward with external mass. As such, there are distinct bands of force and velocity capacities specific to individuals, and perhaps sporting codes, that would benefit from understanding if we are to maximize the transfer between training and practical performance [1–3].

During sprint acceleration, as with many other maximal movements, the mechanical ability to generate force under a range of velocities can be measured and expressed in the force-velocity (Fv) relationship. The integral of these two variables explains the ability of the athlete to express and maximize power, and has been of interest in enhancing performance in a range of movements and disciplines [4–6]. During multi-joint accelerative movements, the relationship between external force production and velocity is typically fitted with linear regressions, with power-velocity being parabolic and fitted using 2^nd or 3^rd order polynomial relationships [7]. The intercepts of this relationship represent the maximum capacity of the neuromuscular system; the force production theoretically possible in the absence of velocity (F₀), and the maximum theoretical velocity until which horizontal force can be produced (v₀). Maximal power (P_max) is determined as the optimal combination of Fv capacities, existing in the centre of the Fv relationship as the peak of the power-velocity (P_v) curve (for illustration, see Fig 1C). In the case of sprinting, these relationships represent the diverse abilities of force production at a range of velocities in a horizontal direction. The comparison of these variables, and the slope of the linear regression between them (S_Fv), can provide insight into a number of factors underlying performance [8]. For example, Fv profiles have been shown to differ between rugby players [9] and may differentiate athletes who have suffered hamstring injury [10, 11]. In jumping, an ‘optimal profile’ can be calculated that, if attained, will maximize jump height for a maintained level of P_max ceteris paribus [1, 2, 12].

Due to a lack of information on the best method of applying resisted sprint overload, the training protocol was the same as presented in a recent pilot study in soccer players [22].

After two sessions of familiarization to heavy and very heavy loads over the span of two weeks, athletes were subject to a 12-session block of testing and training (Table 1). During sessions 1 and 12, the optimal load (L_opt) and the load inducing a 10% decrease in maximal speed (L₁₀) were determined for each player as described in Figs 1 and 2. Sessions 2 to 10 consisted of training (10 repetitions of 20 m resisted sprints, separated by approximately 5 min passive rest). At sessions 1, 6 (mid-program) and 12, the sprint force-velocity-power profiles were determined using the field method of [13] over 2 unresisted 30-m sprints.

Descriptive statistics are presented as means ± standard deviation. Changes in athlete scores were evaluated using effect sizes (ES) and 90% confidence limits. Magnitude-based inferences were calculated using modified statistical Excel spreadsheets from sportsci.org (xPostOnlyCrossover.xls; xParallelGroupsTrial.xls). Two separate statistical methods were used to assess the effectiveness of each method of training. Pre- post-analysis was performed on each group’s data, to provide a clear effect of whether there were substantial and clear changes as a result of the training intervention. A second parallel group trials assessment compared the interventions. The thresholds used to interpret the magnitude of effects measured were based on the work of Hopkins and colleagues (sportsci.org) [27]. Probabilities that differences were higher, lower or similar to the smallest worthwhile difference (preset at a value of 0.20) were evaluated qualitatively as: possibly, 25–74.9%; likely, 75–94.9%, very likely, 95–99.5%; most (extremely) likely, >99.5%. The true difference was assessed as unclear if the chance of both higher and lower values was >5%.

All Fv relationships, pre- and post-training were well fitted by linear regressions (all r²>0.98, typical example in Fig 1C). Similar results were obtained for all linear load-velocity relationships for both the radar and the 1080 Sprint protocols (all r²>0.924).

The main result from the group comparison (L_opt versus L₁₀ between-group differences) showed a likely trivial between-group difference in 20-m performance and P_max increase post-training. All results are presented in Table 2, with between-groups differences presented in Table 3.

Overall, both optimally loaded (L_opt) and ‘10% decrease in v_max’ loaded interventions (L₁₀) provided beneficial effects in a range of performance variables (Table 2). The magnitude of changes experienced were often marginal (small and trivial), and there was a lack of clear distinction in the group effects between the training cohorts (Table 3). Our initial hypothesis was that conditions of high horizontal force exhibited during training would transfer into a linked increase in the corresponding mechanical capacity (i.e. increased F₀), with training in conditions of lower force resulting in emphasised improvements in the opposite capacity (v₀). Instead, what we observed were clear trends for small changes in both force and velocity capabilities as a result of both modalities of training. Among the possible explanations of this unexpected result is a possible interaction effect between pre-test values of Fv profiles, and the timing of post-training measurements, that was common to all subjects; this and other points will be discussed towards the end of this article.

A detailed commentary of the methods, including suggestions of how they may be best applied in a practical context, is available as supplementary material (S1 Table and S1 Text). While this section includes discussion of the results as they pertain to the outcome of the training implementation, we believe this additional content is important for practitioners wishing to implement the methods in the field, without an ability to access the types of equipment widely available to researchers.

L₁₀ produced small measureable increases in practical performance measures, with a reduction in sprint times between -2.28 to -1.96%. However, L_opt produced negligible group changes overall -1.40 to -1.81%. The changes observed were within the range (-0.5 to -9.12%) reported in a recent systematic review [18] from a range of resisted sprint training interventions. The comparison between the effects of the training interventions were largely inconclusive, with the majority of comparative analyses requiring more data to provide clear statistical inferences (changes are unclear; Table 3). These results appear to stand in opposition to the theory that training in conditions that represent a particular mechanical condition will transfer to changes in said condition [8, 15]. Indeed, a recent example in jumping [12] clearly showed that training in the conditions of high force resulted in developments of this capacity. Moreover, previous literature on resisted sprinting (albeit limited in nature) remains unclear, and more research is required to test whether heavier training may specifically benefit the development of acceleration based stimuli [18]. As such, these somewhat counterintuitive results will be discussed further in the paragraphs following.

The result of lighter loading providing a platform for the development of maximum force, and conversely heavier loading developing velocity, appears to refute our initial hypothesis of specific mechanical adaptations in sprint training. There are some factors that we believe may help clarify these unexpected results. Firstly, the change scores and associated inferences were relatively similar (although clear) between training protocols (Table 2). While the statistical interpretation for some effects was different (i.e. trivial vs. small), it could be questioned whether these results were separated by enough of a margin to be practically worthwhile. Regardless, this simply would appear to support a conclusion that loading may not substantially affect the outcomes of this manner of resistive sprint training. One possible explanation for this unexpected outcome may be found in the spread of results observed in the team sport players studied. For example, while the effects of the training interventions were different in respect to their effects on RF_%max (small inference, likely negative), the range of change scores observed from the groups were wide (12.15 ± 15.50% and 7.96 ± 12.52%, for L₁₀ and L_opt changes, respectively). These results may suggest that while there were no statistically measureable differences in the groups at baseline with regards to practical performance measures, the adaptations experienced by the athletes studied were highly individualised.

We theorise a scenario where athletes adapted to the stimuli provided to them based on the level and balance of Fv capacities exhibited pre-test (i.e. their initial Fv profile). For example, athletes with a more velocity-oriented profile (i.e. less negative S_Fv or flatter linear Fv relationship) may have improved their force capacity, regardless of the magnitude of resistive stimulus applied; it is important to note that resisted sprint training using loading constituting L₁₀ training (or indeed lighter) may represent force-dominant training for some athlete presenting a low F₀/RF_%max profile. The unfortunate factor about this theory, is that due to the limited information on sprint Fv profile it is difficult to qualify a priori individual strengths and weaknesses in mechanical capacities. One possible avenue of such an approach is comparing individual scores to a group average/median value, however due to a current lack of normative data these types of analyses are not possible. In jumping the existence of an individualized optimal balance between mechanical capacities has been proven [2], and it is possible that a model of individual optimal Fv capacities applies to that developed during a sprint running acceleration phase. If such an approach is validated in sprinting, an athlete’s particular orientation with regards to this theoretical optimal profile may influence their results from a given training program. This may, partially explain why some athletes in this study improved and not others, even when presented with a greater ‘force-oriented’ stimulus (L_opt sled). To further explore this theory, we tested the correlation between individual pre-score S_Fv and training-induced changes in F₀ and observed a significant interaction effect (r = 0.39; P<0.02). Similarly, changes in RF_%max appeared to be related to the pre-intervention levels expressed in each individual (r = -0.66; P<0.0001). Simply, changes in RF_%max were greater for participants who presented lower values pre-intervention, whatever training method they followed. Consequently, it seems logical that an athlete expressing a low RF_%max value would improve his RF_%max following training using a lighter stimuli (L₁₀) than an athlete with high RF_%max value following heavier training (L_opt). However, no statistically observable differences were found between groups in these variables at baseline. Taken present and previous findings together, the quest for effective training load stimuli to improve sprint mechanical output and performance requires a more individualized approach as to the specific needs (and thus margins of improvement) of athletes. These theories require further investigation, and we recommend that in the future, athletes should be assigned to intervention group(s) based on their initial Fv characteristics [12], rather than randomly as in the current pilot study.

Another possible consideration is the different nature of what happened within sprints during the resisted sprint stimulus before the athletes reached maximal resisted speed (note: maximum resisted velocity is methodologically the point around which loading was profiled, allocated and trained). It is possible that while the conditions at maximum resisted velocity targeted specific adaptations in the way that we hypothesized [15], the time spent before that peak was attained (i.e. 2 to 4 seconds depending on the participants, Fig 2A) while accelerating confounded the results. That is, during each sprint of the training program, the L_opt group probably spent ~4 seconds below v_opt (thus training at v_opt only a very short amount of time in the sprint), and as a consequence potentially not enough time at P_max. (~2–3 seconds). Perhaps if the athletes had performed less sprints, but more time at v_opt (~6 seconds) we may have seen different adaptations. There seems to be a trade-off between accelerating from zero to v_opt and maintaining v_opt at the targeted P_max velocity. Although it might be technically challenging to use such a setting in sprint running, future research could investigate the effect of a resistance onset applied only once the athletes have reached v_opt after an unresisted acceleration, as in sprint cycling [28, 29]. This type of investigation could clarify the role played by the acceleration phase work against L_opt compared to the work performed in the F_opt / v_opt conditions as a stimulus to improve P_max.

Finally, all athletes were tested post-training at the same time after the last session of the protocol. It cannot be ruled out that the systematic 2-week time window used between the end-of-training and post-testing was not optimal for some athletes. It is possible that the adaptation necessary to transfer heavy-sled resistance training over several sessions to improve sprint acceleration performance and mechanical outputs may have taken longer in some athletes. As seen in elite rugby players following a development and tapering protocol [30], and confirmed by our experience with elite players using heavy-resistance sprint training (unpublished data), sprint performance and physical qualities show variable kinetics of ‘peak adaptation’. Such variability is included in a ‘single post-training measurement session’ design. However, since this is the case in most sprint training studies, further research should determine the training-induced adaptation kinetics after heavy-sled resisted training in order to verify if, and to what extent, athletes show peak adaptation windows and between-participants variability in the occurrence of these peaks. Overall, the efficacy of a range of periodization protocols on adaptations, including total sprinting load (per session, and macro-cycle length), and tapering lengths (i.e. time course of adaptations in following weeks), should be studied in more detail, to allow for peak performance following a resisted sprint training program.

Seemingly in contrast to our hypothesis, the group effects of sprint training at optimal power did not appear to be substantially different than training using traditional lighter loading protocols. However, individual adaptations to the type of training imposed were varied, leading us to conclude that pre-training Fv profile (among other confounding factors) may have contributed to the results observed in the athletes. Despite seeming lack of clarity in these results, it should be noted that both resisted-sprint training protocols were likely to improve performance after a short training intervention in already sprint trained athletes. We hope the results of this study will add to the developing narrative of resisted sprint literature, and will serve to guide future, well-designed research in the area of individualised programming for resisted sprinting.