Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning.

Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult OptimEye S5 wearable device was collected from both national and international level fast bowlers (n = 35) in both training and matches, at various intensities. A machine-learning based approach was used to develop the algorithm. Outputs were compared with over 20,000 manually recorded events. A high Matthews correlation coefficient (r = 0.945) showed very good agreement between the automatically detected bowling deliveries and manually recorded ones. The algorithm was found to be both sensitive and specific in training (96.3%, 98.3%) and matches (99.6%, 96.9%), respectively. Rare falsely classified events were typically warm-up deliveries or throws preceded by a run. Inertial sensors data processed by a machine-learning based algorithm provide a valid tool to automatically detect bowling events, whilst also providing the opportunity to look at performance metrics associated with fast bowling. This offers the possibility to better monitor bowling workloads across a range of intensities to mitigate injury risk potential and maximise performance.

The Performance Effects of Microdose Recombinant Human Erythropoietin Administration and Carbon Monoxide Rebreathing.

Frequent, low doses of recombinant human erythropoietin (rHuEpo) have been shown to increase the oxygen carrying capacity of an athlete and enhance endurance performance, although its effect on repeated sprint ability (RSA) remains unknown. If the mechanisms behind improved RSA performance reside within the augmented O2 carrying capacity, then carbon monoxide (CO) inhalation should inhibit RSA. Purpose: The aim of this study was to assess the effects on maximal oxygen uptake (V˙O2max) and RSA of two interventions known to differentially influence blood oxygen carrying capacity. Methods: Fourteen endurance-trained individuals were administered microdoses of rHuEpo (20-40 IUkg) or placebo twice per week for 7 wk using a randomized, crossover design. V˙O2max and RSA were measured at baseline and after rHuEpo administration. Total hemoglobin mass (tHb-mass) was measured twice at baseline (14 and 7 d before the first injection), three times during rHuEpo administration (10, 24, and 38 d after the first rHuEpo injection) and twice after the cessation of rHuEpo administration (7 and 21 d after the final injection) using the optimized CO rebreathing method. V˙O2max and RSA also were assessed in a separate cohort of 11.

Validation of whole-blood transcriptome signature during microdose recombinant human erythropoietin (rHuEpo) administration.

BACKGROUND: Recombinant human erythropoietin (rHuEpo) can improve human performance and is therefore frequently abused by athletes. As a result, the World Anti-Doping Agency (WADA) introduced the Athlete Biological Passport (ABP) as an indirect method to detect blood doping. Despite this progress, challenges remain to detect blood manipulations such as the use of microdoses of rHuEpo. METHODS: Forty-five whole-blood transcriptional markers of rHuEpo previously derived from a high-dose rHuEpo administration trial were used to assess whether microdoses of rHuEpo could be detected in 14 trained subjects and whether these markers may be confounded by exercise (n = 14 trained subjects) and altitude training (n = 21 elite runners and n = 4 elite rowers, respectively). Differential gene expression analysis was carried out following normalisation and significance declared following application of a 5% false discovery rate (FDR) and a 1.5 fold-change. Adaptive model analysis was also applied to incorporate these markers for the detection of rHuEpo. RESULTS: ALAS2, BCL2L1, DCAF12, EPB42, GMPR, SELENBP1, SLC4A1, TMOD1 and TRIM58 were differentially expressed during and throughout the post phase of microdose rHuEpo administration. The CD247 and TRIM58 genes were significantly up- and down-regulated, respectively, immediately following exercise when compared with the baseline both before and after rHuEpo/placebo. No significant gene expression changes were found 30 min after exercise in either rHuEpo or placebo groups. ALAS2, BCL2L1, DCAF12, SLC4A1, TMOD1 and TRIM58 tended to be significantly expressed in the elite runners ten days after arriving at altitude and one week after returning from altitude (FDR > 0.059, fold-change varying from 1.39 to 1.63). Following application of the adaptive model, 15 genes showed a high sensitivity (≥ 93%) and specificity (≥ 71%), with BCL2L1 and CSDA having the highest sensitivity (93%) and specificity (93%). CONCLUSIONS: Current results provide further evidence that transcriptional biomarkers can strengthen the ABP approach by significantly prolonging the detection window and improving the sensitivity and specificity of blood doping detection. Further studies are required to confirm, and if necessary, integrate the confounding effects of altitude training on blood doping.

Blood transcriptional signature of recombinant human erythropoietin administration and implications for antidoping strategies.

Recombinant human erythropoietin (rHuEPO) is frequently abused by athletes as a performance-enhancing drug, despite being prohibited by the World Anti-Doping Agency. Although the methods to detect blood doping, including rHuEPO injections, have improved in recent years, they remain imperfect. In a proof-of-principle study, we identified, replicated, and validated the whole blood transcriptional signature of rHuEPO in endurance-trained Caucasian males at sea level (n = 18) and Kenyan endurance runners at moderate altitude (n = 20), all of whom received rHuEPO injections for 4 wk. Transcriptional profiling shows that hundreds of transcripts were altered by rHuEPO in both cohorts. The main regulated expression pattern, observed in all participants, was characterized by a "rebound" effect with a profound upregulation during rHuEPO and a subsequent downregulation up to 4 wk postadministration. The functions of the identified genes were mainly related to the functional and structural properties of the red blood cell. Of the genes identified to be differentially expressed during and post-rHuEPO, we further confirmed a whole blood 34-transcript signature that can distinguish between samples collected pre-, during, and post-rHuEPO administration. By providing biomarkers that can reveal rHuEPO use, our findings represent an advance in the development of new methods for the detection of blood doping.

Letter to the editor.

Santos-Concejero and Tucker argued in their letter to the editor that in our study the running economy in achieving superior performance was overlooked due to some methodological aspects. Having given the remarks of Santos-Concejero and Tucker appropriate consideration, in this letter to the editor, we argue that our paper does not downplay the influence of running economy on the determinants of the East African running phenomenon, but rather adds novel insights into the interaction between running economy, maximal oxygen uptake and performance.

Dissociation between running economy and running performance in elite Kenyan distance runners.

The purpose of this study was to investigate the relationship between running economy (RE) and performance in a homogenous group of competitive Kenyan distance runners. Maximal aerobic capacity (VO2max) (68.8 ± 3.8 ml∙kg(-1)∙min(-1)) was determined on a motorised treadmill in 32 Kenyan (25.3 ± 5.0 years; IAAF performance score: 993 ± 77 p) distance runners. Leg anthropometry was assessed and moment arm of the Achilles tendon determined. While Achilles moment arm was associated with better RE (r(2) = 0.30, P = 0.003) and upper leg length, total leg length and total leg length to body height ratio were correlated with running performance (r = 0.42, P = 0.025; r = 0.40, P = 0.030 and r = 0.38, P = 0.043, respectively), RE and maximal time on treadmill (t(max)) were not associated with running performance (r = -0.01, P = 0.965; r = 0.27; P = 0.189, respectively) in competitive Kenyan distance runners. The dissociation between RE and running performance in this homogenous group of runners would suggest that RE can be compensated by other factors to maintain high performance levels and is in line with the idea that RE is only one of many factors explaining elite running performance.

An integrative 'omics' solution to the detection of recombinant human erythropoietin and blood doping.

Administration of recombinant human erythropoietin (rHumanEPO) improves sporting performance and hence is frequently subject to abuse by athletes, although rHumanEPO is prohibited by the WADA. Approaches to detect rHumanEPO doping have improved significantly in recent years but remain imperfect. A new transcriptomic-based longitudinal screening approach is being developed that has the potential to improve the analytical performance of current detection methods. In particular, studies are being funded by WADA to identify a 'molecular signature' of rHumanEPO doping and preliminary results are promising. In the first systematic study to be conducted, the expression of hundreds of genes were found to be altered by rHumanEPO with numerous gene transcripts being differentially expressed after the first injection and further transcripts profoundly upregulated during and subsequently downregulated up to 4 weeks postadministration of the drug; with the same transcriptomic pattern observed in all participants. The identification of a blood 'molecular signature' of rHumanEPO administration is the strongest evidence to date that gene biomarkers have the potential to substantially improve the analytical performance of current antidoping methods such as the Athlete Biological Passport for rHumanEPO detection. Given the early promise of transcriptomics, research using an 'omics'-based approach involving genomics, transcriptomics, proteomics and metabolomics should be intensified in order to achieve improved detection of rHumanEPO and other doping substances and methods difficult to detect such a recombinant human growth hormone and blood transfusions.

Effects of EPO on Blood Parameters and Running Performance in Kenyan Athletes.

INTRODUCTION: Recombinant human erythropoietin (rHuEpo) administration enhances oxygen carrying capacity and performance at sea level. It remains unknown whether similar effects would be observed in chronic altitude-adapted endurance runners. The aim of this study was to assess the effects of rHuEpo on hematological and performance parameters in chronic altitude-adapted endurance runners as compared to sea level athletes. METHODS: Twenty well-trained Kenyan endurance runners (KEN) living and training at approximately 2150 m received rHuEpo injections of 50 IU·kg body mass every 2 d for 4 wk and responses compared with another cohort (SCO) that underwent an identical protocol at sea level. Blood samples were obtained at baseline, during rHuEpo administration and 4 wk after the final injection. A maximal oxygen uptake (V˙O2max) test and 3000-m time trial was performed before, immediately after and 4 wk after the final rHuEpo injection. RESULTS: Hematocrit (HCT) and hemoglobin concentration (HGB) were higher in KEN compared to SCO before rHuEpo but similar at the end of administration. Before rHuEpo administration, KEN had higher V˙O2max and faster time trial performance compared to SCO. After rHuEpo administration, there was a similar increase in V˙O2max and time trial performance in both cohorts; most effects of rHuEpo were maintained 4 wk after the final rHuEpo injection in both cohorts. CONCLUSIONS: Four weeks of rHuEpo increased the HGB and HCT of Kenyan endurance runners to a lesser extent than in SCO (~17% vs ~10%, respectively) and these alterations were associated with similar improvements in running performance immediately after the rHuEpo administration (~5%) and 4 wk after rHuEpo (~3%).

Haemoglobin mass and running time trial performance after recombinant human erythropoietin administration in trained men.

UNLABELLED: Recombinant human erythropoietin (rHuEpo) increases haemoglobin mass (Hb(mass)) and maximal oxygen uptake (v O(2 max)). PURPOSE: This study defined the time course of changes in Hb(mass), v O(2 max) as well as running time trial performance following 4 weeks of rHuEpo administration to determine whether the laboratory observations would translate into actual improvements in running performance in the field. METHODS: 19 trained men received rHuEpo injections of 50 IU•kg(-1) body mass every two days for 4 weeks. Hb(mass) was determined weekly using the optimized carbon monoxide rebreathing method until 4 weeks after administration. v O(2 max) and 3,000 m time trial performance were measured pre, post administration and at the end of the study. RESULTS: Relative to baseline, running performance significantly improved by ∼6% after administration (10:30±1:07 min:sec vs. 11:08±1:15 min:sec, p<0.001) and remained significantly enhanced by ∼3% 4 weeks after administration (10:46±1:13 min:sec, p<0.001), while v O(2 max) was also significantly increased post administration (60.7±5.8 mL•min(-1)•kg(-1) vs. 56.0±6.2 mL•min(-1)•kg(-1), p<0.001) and remained significantly increased 4 weeks after rHuEpo (58.0±5.6 mL•min(-1)•kg(-1), p = 0.021). Hb(mass) was significantly increased at the end of administration compared to baseline (15.2±1.5 g•kg(-1) vs. 12.7±1.2 g•kg(-1), p<0.001). The rate of decrease in Hb(mass) toward baseline values post rHuEpo was similar to that of the increase during administration (-0.53 g•kg(-1)•wk(-1), 95% confidence interval (CI) (-0.68, -0.38) vs. 0.54 g•kg(-1•)wk(-1), CI (0.46, 0.63)) but Hb(mass) was still significantly elevated 4 weeks after administration compared to baseline (13.7±1.1 g•kg(-1), p<0.001). CONCLUSION: Running performance was improved following 4 weeks of rHuEpo and remained elevated 4 weeks after administration compared to baseline. These field performance effects coincided with rHuEpo-induced elevated v O(2 max) and Hb(mass).