Predicting noncontact injuries of professional football players using machine learning.
Noncontact injuries are prevalent among professional football players. Yet, most research on this topic is retrospective, focusing solely on statistical correlations between Global Positioning System (GPS) metrics and injury occurrence, overlooking the multifactorial nature of injuries. This study i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0315481 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555633259675648 |
|---|---|
| author | Diogo Nuno Freitas Sheikh Shanawaz Mostafa Romualdo Caldeira Francisco Santos Eduardo Fermé Élvio R Gouveia Fernando Morgado-Dias |
| author_facet | Diogo Nuno Freitas Sheikh Shanawaz Mostafa Romualdo Caldeira Francisco Santos Eduardo Fermé Élvio R Gouveia Fernando Morgado-Dias |
| author_sort | Diogo Nuno Freitas |
| collection | DOAJ |
| description | Noncontact injuries are prevalent among professional football players. Yet, most research on this topic is retrospective, focusing solely on statistical correlations between Global Positioning System (GPS) metrics and injury occurrence, overlooking the multifactorial nature of injuries. This study introduces an automated injury identification and prediction approach using machine learning, leveraging GPS data and player-specific parameters. A sample of 34 male professional players from a Portuguese first-division team was analyzed, combining GPS data from Catapult receivers with descriptive variables for machine learning models-Support Vector Machines (SVMs), Feedforward Neural Networks (FNNs), and Adaptive Boosting (AdaBoost)-to predict injuries. These models, particularly the SVMs with cost-sensitive learning, showed high accuracy in detecting injury events, achieving a sensitivity of 71.43%, specificity of 74.19%, and overall accuracy of 74.22%. Key predictive factors included the player's position, session type, player load, velocity and acceleration. The developed models are notable for their balanced sensitivity and specificity, efficiency without extensive manual data collection, and capability to predict injuries for short time frames. These advancements will aid coaching staff in identifying high-risk players, optimizing team performance, and reducing rehabilitation costs. |
| format | Article |
| id | doaj-art-d222880b0bba4fe68129a5b36b97ab78 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-d222880b0bba4fe68129a5b36b97ab782025-01-08T05:31:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031548110.1371/journal.pone.0315481Predicting noncontact injuries of professional football players using machine learning.Diogo Nuno FreitasSheikh Shanawaz MostafaRomualdo CaldeiraFrancisco SantosEduardo FerméÉlvio R GouveiaFernando Morgado-DiasNoncontact injuries are prevalent among professional football players. Yet, most research on this topic is retrospective, focusing solely on statistical correlations between Global Positioning System (GPS) metrics and injury occurrence, overlooking the multifactorial nature of injuries. This study introduces an automated injury identification and prediction approach using machine learning, leveraging GPS data and player-specific parameters. A sample of 34 male professional players from a Portuguese first-division team was analyzed, combining GPS data from Catapult receivers with descriptive variables for machine learning models-Support Vector Machines (SVMs), Feedforward Neural Networks (FNNs), and Adaptive Boosting (AdaBoost)-to predict injuries. These models, particularly the SVMs with cost-sensitive learning, showed high accuracy in detecting injury events, achieving a sensitivity of 71.43%, specificity of 74.19%, and overall accuracy of 74.22%. Key predictive factors included the player's position, session type, player load, velocity and acceleration. The developed models are notable for their balanced sensitivity and specificity, efficiency without extensive manual data collection, and capability to predict injuries for short time frames. These advancements will aid coaching staff in identifying high-risk players, optimizing team performance, and reducing rehabilitation costs.https://doi.org/10.1371/journal.pone.0315481 |
| spellingShingle | Diogo Nuno Freitas Sheikh Shanawaz Mostafa Romualdo Caldeira Francisco Santos Eduardo Fermé Élvio R Gouveia Fernando Morgado-Dias Predicting noncontact injuries of professional football players using machine learning. PLoS ONE |
| title | Predicting noncontact injuries of professional football players using machine learning. |
| title_full | Predicting noncontact injuries of professional football players using machine learning. |
| title_fullStr | Predicting noncontact injuries of professional football players using machine learning. |
| title_full_unstemmed | Predicting noncontact injuries of professional football players using machine learning. |
| title_short | Predicting noncontact injuries of professional football players using machine learning. |
| title_sort | predicting noncontact injuries of professional football players using machine learning |
| url | https://doi.org/10.1371/journal.pone.0315481 |
| work_keys_str_mv | AT diogonunofreitas predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT sheikhshanawazmostafa predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT romualdocaldeira predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT franciscosantos predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT eduardoferme predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT elviorgouveia predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning AT fernandomorgadodias predictingnoncontactinjuriesofprofessionalfootballplayersusingmachinelearning |