Prediction of running injuries from training load: a machine learning approach

Research output: Contribution to conferencePaperOther research output

169 Downloads (Pure)

Abstract

The prediction of the running injuries based on selfreported training data on load is difficult. At present, coaches and researchers have no validated system to predict if a runner has an increased risk of injuries. We aim to develop an algorithm to predict the increase of the risk of a runner to sustain an injury. As a first step Self-reported data on training parameters and injuries from high-level runners (duration=37 weeks, n=23, male=16, female=7) were used to identify the most predictive variables for injuries, and train a machine learning tree algorithm to predict an injury. The model was validated by splitting the data in training and a test set. The 10 most important variables were identified from 85 possible variables using the Random Forest algorithm. To predict at an earliest stage, so the runner or the coach is able to intervene, the variables were classified by time to build tree algorithms up to 7 weeks before the occurrence of an injury. By building machine learning algorithms using existing self-reported training data can enable prospective identification of high-level runners who are likely to develop an injury. Only the established prediction model needs to be verified as correct.
Translated title of the contributionVoorspelling van hardloopblessures op basis van trainingsload: een machine learning benadering
Original languageEnglish
Number of pages3
Publication statusPublished - 19 Mar 2017
Event9th International Conference on eHealth, Telemedicine, and Social Medicine 2017 - Nice, France
Duration: 19 Mar 201723 Mar 2017
Conference number: 9th
https://www.iaria.org/conferences2017/eTELEMED17.html

Conference

Conference9th International Conference on eHealth, Telemedicine, and Social Medicine 2017
Abbreviated titleeTELEMED 2017
CountryFrance
CityNice
Period19/03/1723/03/17
Internet address

Keywords

  • sport injuries
  • monitoring
  • athletes

Cite this

Dijkhuis, T., Otter, R., Velthuijsen, H., & Lemmink, K. (2017). Prediction of running injuries from training load: a machine learning approach. Paper presented at 9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, Nice, France.
Dijkhuis, Talko ; Otter, Ruby ; Velthuijsen, Hugo ; Lemmink, Koen. / Prediction of running injuries from training load: a machine learning approach. Paper presented at 9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, Nice, France.3 p.
@conference{b277c6c939e44f5ea0ccf210b9014743,
title = "Prediction of running injuries from training load: a machine learning approach",
abstract = "The prediction of the running injuries based on selfreported training data on load is difficult. At present, coaches and researchers have no validated system to predict if a runner has an increased risk of injuries. We aim to develop an algorithm to predict the increase of the risk of a runner to sustain an injury. As a first step Self-reported data on training parameters and injuries from high-level runners (duration=37 weeks, n=23, male=16, female=7) were used to identify the most predictive variables for injuries, and train a machine learning tree algorithm to predict an injury. The model was validated by splitting the data in training and a test set. The 10 most important variables were identified from 85 possible variables using the Random Forest algorithm. To predict at an earliest stage, so the runner or the coach is able to intervene, the variables were classified by time to build tree algorithms up to 7 weeks before the occurrence of an injury. By building machine learning algorithms using existing self-reported training data can enable prospective identification of high-level runners who are likely to develop an injury. Only the established prediction model needs to be verified as correct.",
keywords = "sportblessures, trainingsanalyse, sport injuries, monitoring, athletes",
author = "Talko Dijkhuis and Ruby Otter and Hugo Velthuijsen and Koen Lemmink",
year = "2017",
month = "3",
day = "19",
language = "English",
note = "9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, eTELEMED 2017 ; Conference date: 19-03-2017 Through 23-03-2017",
url = "https://www.iaria.org/conferences2017/eTELEMED17.html",

}

Dijkhuis, T, Otter, R, Velthuijsen, H & Lemmink, K 2017, 'Prediction of running injuries from training load: a machine learning approach' Paper presented at 9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, Nice, France, 19/03/17 - 23/03/17, .

Prediction of running injuries from training load: a machine learning approach. / Dijkhuis, Talko; Otter, Ruby; Velthuijsen, Hugo; Lemmink, Koen.

2017. Paper presented at 9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, Nice, France.

Research output: Contribution to conferencePaperOther research output

TY - CONF

T1 - Prediction of running injuries from training load: a machine learning approach

AU - Dijkhuis, Talko

AU - Otter, Ruby

AU - Velthuijsen, Hugo

AU - Lemmink, Koen

PY - 2017/3/19

Y1 - 2017/3/19

N2 - The prediction of the running injuries based on selfreported training data on load is difficult. At present, coaches and researchers have no validated system to predict if a runner has an increased risk of injuries. We aim to develop an algorithm to predict the increase of the risk of a runner to sustain an injury. As a first step Self-reported data on training parameters and injuries from high-level runners (duration=37 weeks, n=23, male=16, female=7) were used to identify the most predictive variables for injuries, and train a machine learning tree algorithm to predict an injury. The model was validated by splitting the data in training and a test set. The 10 most important variables were identified from 85 possible variables using the Random Forest algorithm. To predict at an earliest stage, so the runner or the coach is able to intervene, the variables were classified by time to build tree algorithms up to 7 weeks before the occurrence of an injury. By building machine learning algorithms using existing self-reported training data can enable prospective identification of high-level runners who are likely to develop an injury. Only the established prediction model needs to be verified as correct.

AB - The prediction of the running injuries based on selfreported training data on load is difficult. At present, coaches and researchers have no validated system to predict if a runner has an increased risk of injuries. We aim to develop an algorithm to predict the increase of the risk of a runner to sustain an injury. As a first step Self-reported data on training parameters and injuries from high-level runners (duration=37 weeks, n=23, male=16, female=7) were used to identify the most predictive variables for injuries, and train a machine learning tree algorithm to predict an injury. The model was validated by splitting the data in training and a test set. The 10 most important variables were identified from 85 possible variables using the Random Forest algorithm. To predict at an earliest stage, so the runner or the coach is able to intervene, the variables were classified by time to build tree algorithms up to 7 weeks before the occurrence of an injury. By building machine learning algorithms using existing self-reported training data can enable prospective identification of high-level runners who are likely to develop an injury. Only the established prediction model needs to be verified as correct.

KW - sportblessures

KW - trainingsanalyse

KW - sport injuries

KW - monitoring

KW - athletes

M3 - Paper

ER -

Dijkhuis T, Otter R, Velthuijsen H, Lemmink K. Prediction of running injuries from training load: a machine learning approach. 2017. Paper presented at 9th International Conference on eHealth, Telemedicine, and Social Medicine 2017, Nice, France.