Dataset Information

Prediction and Quantification of Individual Athletic Performance of Runners.

ABSTRACT: We present a novel, quantitative view on the human athletic performance of individual runners. We obtain a predictor for running performance, a parsimonious model and a training state summary consisting of three numbers by application of modern validation techniques and recent advances in machine learning to the thepowerof10 database of British runners' performances (164,746 individuals, 1,417,432 performances). Our predictor achieves an average prediction error (out-of-sample) of e.g. 3.6 min on elite Marathon performances and 0.3 seconds on 100 metres performances, and a lower error than the state-of-the-art in performance prediction (30% improvement, RMSE) over a range of distances. We are also the first to report on a systematic comparison of predictors for running performance. Our model has three parameters per runner, and three components which are the same for all runners. The first component of the model corresponds to a power law with exponent dependent on the runner which achieves a better goodness-of-fit than known power laws in the study of running. Many documented phenomena in quantitative sports science, such as the form of scoring tables, the success of existing prediction methods including Riegel's formula, the Purdy points scheme, the power law for world records performances and the broken power law for world record speeds may be explained on the basis of our findings in a unified way. We provide strong evidence that the three parameters per runner are related to physiological and behavioural parameters, such as training state, event specialization and age, which allows us to derive novel physiological hypotheses relating to athletic performance. We conjecture on this basis that our findings will be vital in exercise physiology, race planning, the study of aging and training regime design.

SUBMITTER: Blythe DA

PROVIDER: S-EPMC4919094 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction and Quantification of Individual Athletic Performance of Runners.

Blythe Duncan A J DA Király Franz J FJ

PloS one 20160623 6

We present a novel, quantitative view on the human athletic performance of individual runners. We obtain a predictor for running performance, a parsimonious model and a training state summary consisting of three numbers by application of modern validation techniques and recent advances in machine learning to the thepowerof10 database of British runners' performances (164,746 individuals, 1,417,432 performances). Our predictor achieves an average prediction error (out-of-sample) of e.g. 3.6 min o ...[more]

PMID: 27336162

Similar Datasets

Project description:UnlabelledThe purpose of this study determined if oral supplementation of Protandim® (a nutraceutical) for 90 days improved 5-km running performance and reduced serum thiobarbituric acid-reacting substances (TBARS) at rest, an indicator of oxidative stress. Secondary objectives were to measure whole blood superoxide dismutase (SOD), glutathione (GSH), and glutathione peroxidase (GPX), at rest and 10 minutes after completion of the race before and after supplementation as well as quality of life. In a double-blind, randomized, placebo controlled trial, 38 runners [mean (SD) = 34 (7) yrs; BMI = 22 (2) kg/m2] received either 90 days of Protandim® [1 pill a day, n = 19)] or placebo (n = 19). Randomization was done in blocks of two controlling for sex and 5-km baseline performance. A 5-km race was performed at baseline and after 90 days of supplementation, with blood samples taken before and 10-min after each race. Fasting blood samples were acquired at baseline, after 30, 60, and 90 days of supplementation. TBARS, SOD, GPX, and GSH were assayed in an out-of-state accredited lab. Running performance was not altered by Protandim® or placebo [20.3 (2.1) minutes, with an -8 (33) seconds change in 5-km time regardless of group]. There was no change in TBARS, SOD, or GPX (at rest) after three months of Protandim® supplementation compared to placebo. However, in a subgroup ≥ 35 years of age, there was a 2-fold higher increase in SOD in those taking Protandim® for three months compared to those on placebo (p = 0.038). The mean post-race change in TBARS (compared to pre-race) increased by about 20% in half of the subjects, but was not altered between groups, even after three months of supplementation. Quality of life was also not different between the two conditions. In conclusion, Protandim® did not (1) alter 5-km running time, (2) lower TBARS at rest (3) raise antioxidant enzyme concentrations compared to placebo (with exception of SOD in those ≥ 35 years old) or, (4) affect quality of life compared to placebo.Trial registrationClinicalTrials.gov NCT02172625.

Project description:PURPOSE:The use of oxygen cost ([Formula: see text]aero) parameters to predict endurance performance has recently been criticized. Instead, it is suggested that aerobic energy cost ([Formula: see text]) provides greater validity; however, a comparison of these quantification methods has not previously been made. METHODS:Fifty-six male (n?=?34) and female (n?=?22) competitive adolescent (17?±?1 years) middle-distance runners participated in a sub-maximal and maximal incremental treadmill test. Running economy (RE) was measured at the speed corresponding to lactate turnpoint, and the three speeds prior. Maximal oxygen uptake ([Formula: see text]O2max), speed at [Formula: see text]O2max and fraction of [Formula: see text]O2max utilized across a range of intensities, and speeds from 0.8, 1.5 and 3 km races were also quantified. RE and fractional utilization were calculated in units of [Formula: see text]aero and [Formula: see text]aero. RESULTS:Multiple linear regression models demonstrated no discernible difference in the predictive capability of RE, fractional utilization and [Formula: see text]O2max when expressed as [Formula: see text]aero or [Formula: see text]aero in both sexes. When plotted as a function of running speed, [Formula: see text]aero displayed a stepwise decrease (F?=?11.59, p?<?0.001) whereas [Formula: see text]aero exhibited a curvilinear response (F?=?4.74, p?=?0.015). Differences were also evident in the slopes plotted for %[Formula: see text]O2max and %[Formula: see text]aeromax against running speed (F?=?5.38, p?=?0.021). CONCLUSIONS:Quantifying aerobic determinants of performance in units of [Formula: see text]aero provides no greater validity compared to [Formula: see text]aero-based measurement. Although both [Formula: see text]aero and [Formula: see text]aero are sensitive to changes in speed, [Formula: see text]aero provides the more valid reflection of the underlying metabolic cost of running. Physiologists should also be aware of the potential differences between expression of aerobic running intensity based upon %[Formula: see text]O2max compared to %[Formula: see text]aeromax.

Project description:PurposeThis study aimed to apply open-source analysis code to raw habitual physical activity data from wrist-worn monitors to: 1) objectively, unobtrusively, and accurately discriminate between "running" and "nonrunning" days; and 2) develop and compare simple accelerometer-derived metrics of external training load with existing self-report measures.MethodsSeven-day wrist-worn accelerometer (GENEActiv; Activinsights Ltd, Kimbolton, UK) data obtained from 35 experienced runners (age, 41.9 ± 11.4 yr; height, 1.72 ± 0.08 m; mass, 68.5 ± 9.7 kg; body mass index, 23.2 ± 2.2 kg·m; 19 [54%] women) every other week over 9 to 18 wk were date-matched with self-reported training log data. Receiver operating characteristic analyses were applied to accelerometer metrics ("Average Acceleration," "Most Active-30mins," "Mins≥400 mg") to discriminate between "running" and "nonrunning" days and cross-validated (leave one out cross-validation). Variance explained in training log criterion metrics (miles, duration, training load) by accelerometer metrics (Mins≥400 mg, "workload (WL) 400-4000 mg") was examined using linear regression with leave one out cross-validation.ResultsMost Active-30mins and Mins≥400 mg had >94% accuracy for correctly classifying "running" and "nonrunning" days, with validation indicating robustness. Variance explained in miles, duration, and training load by Mins≥400 mg (67%-76%) and WL400-4000 mg (55%-69%) was high, with validation indicating robustness.ConclusionsWrist-worn accelerometer metrics can be used to objectively, unobtrusively, and accurately identify running training days in runners, reducing the need for training logs or user input in future prospective research or commercial activity tracking. The high percentage of variance explained in existing self-reported measures of training load by simple, accelerometer-derived metrics of external training load supports the future use of accelerometry for prospective, preventative, and prescriptive monitoring purposes in runners.

Project description:BACKGROUND: The World Anti-Doping Agency (WADA) publishes the Prohibited List, a manually compiled international standard of substances and methods prohibited in-competition, out-of-competition and in particular sports. It would be ideal to be able to identify all substances that have one or more performance-enhancing pharmacological actions in an automated, fast and cost effective way. Here, we use experimental data derived from the ChEMBL database (~7,000,000 activity records for 1,300,000 compounds) to build a database model that takes into account both structure and experimental information, and use this database to predict both on-target and off-target interactions between these molecules and targets relevant to doping in sport. RESULTS: The ChEMBL database was screened and eight well populated categories of activities (Ki, Kd, EC50, ED50, activity, potency, inhibition and IC50) were used for a rule-based filtering process to define the labels "active" or "inactive". The "active" compounds for each of the ChEMBL families were thereby defined and these populated our bioactivity-based filtered families. A structure-based clustering step was subsequently performed in order to split families with more than one distinct chemical scaffold. This produced refined families, whose members share both a common chemical scaffold and bioactivity against a common target in ChEMBL. CONCLUSIONS: We have used the Parzen-Rosenblatt machine learning approach to test whether compounds in ChEMBL can be correctly predicted to belong to their appropriate refined families. Validation tests using the refined families gave a significant increase in predictivity compared with the filtered or with the original families. Out of 61,660 queries in our Monte Carlo cross-validation, belonging to 19,639 refined families, 41,300 (66.98%) had the parent family as the top prediction and 53,797 (87.25%) had the parent family in the top four hits. Having thus validated our approach, we used it to identify the protein targets associated with the WADA prohibited classes. For compounds where we do not have experimental data, we use their computed patterns of interaction with protein targets to make predictions of bioactivity. We hope that other groups will test these predictions experimentally in the future.

Dataset Information

Prediction and Quantification of Individual Athletic Performance of Runners.

Publications

Prediction and Quantification of Individual Athletic Performance of Runners.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets