Improving predictor selection for injury modelling methods in male footballers

Authors: Philp, F., Al-Shallawi, A., Kyriacou, T., Blana, D. and Pandyan, A.

Journal: BMJ Open Sport and Exercise Medicine

Volume: 6

Issue: 1

ISSN: 2055-7647

DOI: 10.1136/bmjsem-2019-000634

Abstract:

Objectives This objective of this study was to evaluate whether combining existing methods of elastic net for zero-inflated Poisson and zero-inflated Poisson regression methods could improve real-life applicability of injury prediction models in football. Methods Predictor selection and model development was conducted on a pre-existing dataset of 24 male participants from a single English football team's 2015/2016 season. Results The elastic net for zero-inflated Poisson penalty method was successful in shrinking the total number of predictors in the presence of high levels of multicollinearity. It was additionally identified that easily measurable data, that is, mass and body fat content, training type, duration and surface, fitness levels, normalised period of a € no-play' and time in competition could contribute to the probability of acquiring a time-loss injury. Furthermore, prolonged series of match-play and increased in-season injury reduced the probability of not sustaining an injury. Conclusion For predictor selection, the elastic net for zero-inflated Poisson penalised method in combination with the use of ZIP regression modelling for predicting time-loss injuries have been identified appropriate methods for improving real-life applicability of injury prediction models. These methods are more appropriate for datasets subject to multicollinearity, smaller sample sizes and zero-inflation known to affect the performance of traditional statistical methods. Further validation work is now required.

https://eprints.bournemouth.ac.uk/36623/

Source: Scopus

Improving predictor selection for injury modelling methods in male footballers.

Authors: Philp, F., Al-Shallawi, A., Kyriacou, T., Blana, D. and Pandyan, A.

Journal: BMJ Open Sport Exerc Med

Volume: 6

Issue: 1

Pages: e000634

ISSN: 2055-7647

DOI: 10.1136/bmjsem-2019-000634

Abstract:

OBJECTIVES: This objective of this study was to evaluate whether combining existing methods of elastic net for zero-inflated Poisson and zero-inflated Poisson regression methods could improve real-life applicability of injury prediction models in football. METHODS: Predictor selection and model development was conducted on a pre-existing dataset of 24 male participants from a single English football team's 2015/2016 season. RESULTS: The elastic net for zero-inflated Poisson penalty method was successful in shrinking the total number of predictors in the presence of high levels of multicollinearity. It was additionally identified that easily measurable data, that is, mass and body fat content, training type, duration and surface, fitness levels, normalised period of 'no-play' and time in competition could contribute to the probability of acquiring a time-loss injury. Furthermore, prolonged series of match-play and increased in-season injury reduced the probability of not sustaining an injury. CONCLUSION: For predictor selection, the elastic net for zero-inflated Poisson penalised method in combination with the use of ZIP regression modelling for predicting time-loss injuries have been identified appropriate methods for improving real-life applicability of injury prediction models. These methods are more appropriate for datasets subject to multicollinearity, smaller sample sizes and zero-inflation known to affect the performance of traditional statistical methods. Further validation work is now required.

https://eprints.bournemouth.ac.uk/36623/

Source: PubMed

Improving predictor selection for injury modelling methods in male footballers

Authors: Philp, F., Al-shallawi, A., Kyriacou, T., Blana, D. and Pandyan, A.

Journal: BMJ OPEN SPORT & EXERCISE MEDICINE

Volume: 6

Issue: 1

eISSN: 2055-7647

ISSN: 2398-9459

DOI: 10.1136/bmjsem-2019-000634

https://eprints.bournemouth.ac.uk/36623/

Source: Web of Science (Lite)

Improving predictor selection for injury modelling methods in male footballers.

Authors: Philp, F., Al-Shallawi, A., Kyriacou, T., Blana, D. and Pandyan, A.

Journal: BMJ open sport & exercise medicine

Volume: 6

Issue: 1

Pages: e000634

eISSN: 2055-7647

ISSN: 2055-7647

DOI: 10.1136/bmjsem-2019-000634

Abstract:

Objectives

This objective of this study was to evaluate whether combining existing methods of elastic net for zero-inflated Poisson and zero-inflated Poisson regression methods could improve real-life applicability of injury prediction models in football.

Methods

Predictor selection and model development was conducted on a pre-existing dataset of 24 male participants from a single English football team's 2015/2016 season.

Results

The elastic net for zero-inflated Poisson penalty method was successful in shrinking the total number of predictors in the presence of high levels of multicollinearity. It was additionally identified that easily measurable data, that is, mass and body fat content, training type, duration and surface, fitness levels, normalised period of 'no-play' and time in competition could contribute to the probability of acquiring a time-loss injury. Furthermore, prolonged series of match-play and increased in-season injury reduced the probability of not sustaining an injury.

Conclusion

For predictor selection, the elastic net for zero-inflated Poisson penalised method in combination with the use of ZIP regression modelling for predicting time-loss injuries have been identified appropriate methods for improving real-life applicability of injury prediction models. These methods are more appropriate for datasets subject to multicollinearity, smaller sample sizes and zero-inflation known to affect the performance of traditional statistical methods. Further validation work is now required.

https://eprints.bournemouth.ac.uk/36623/

Source: Europe PubMed Central

Improving predictor selection for injury modelling methods in male footballers.

Authors: Philp, F., Al-shallawi, A., Kyriacou, T., Blana, D. and Pandyan, A.

Journal: BMJ Open Sport and Exercise Medicine

Volume: 6

Issue: 1

ISSN: 2055-7647

Abstract:

Objectives: This objective of this study was to evaluate whether combining existing methods of elastic net for zero-inflated Poisson and zero-inflated Poisson regression methods could improve real-life applicability of injury prediction models in football. Methods: Predictor selection and model development was conducted on a pre-existing dataset of 24 male participants from a single English football team's 2015/2016 season. Results: The elastic net for zero-inflated Poisson penalty method was successful in shrinking the total number of predictors in the presence of high levels of multicollinearity. It was additionally identified that easily measurable data, that is, mass and body fat content, training type, duration and surface, fitness levels, normalised period of 'no-play' and time in competition could contribute to the probability of acquiring a time-loss injury. Furthermore, prolonged series of match-play and increased in-season injury reduced the probability of not sustaining an injury. Conclusion: For predictor selection, the elastic net for zero-inflated Poisson penalised method in combination with the use of ZIP regression modelling for predicting time-loss injuries have been identified appropriate methods for improving real-life applicability of injury prediction models. These methods are more appropriate for datasets subject to multicollinearity, smaller sample sizes and zero-inflation known to affect the performance of traditional statistical methods. Further validation work is now required.

https://eprints.bournemouth.ac.uk/36623/

Source: BURO EPrints