Predição de Lesões no Futebol Profissional com ACWR e Aprendizado de Máquina
Resumo
A intensificação do calendário no futebol profissional tem aumentado a incidência de lesões, com impactos no desempenho esportivo e prejuízos econômicos, especialmente para clubes de elite. Diante disso, este trabalho visa explorar modelos de aprendizado de máquina capazes de prever tais lesões, utilizando dados de dispositivos GPS e o indicador de proporção de carga de trabalho aguda e crônica. O modelo de aprendizado de máquina com o melhor resultado desse estudo conseguiu prever lesões com um F1 score de 93,3%.
Palavras-chave:
Predição de Lesões, Futebol Profissional, Dados de GPS, Razão entre Carga Aguda e Crônica (ACWR), Aprendizado de Máquina
Referências
Andrade, R. et al. [2020]. “Is the Acute: Chronic Workload Ratio (ACWR) Associated with Risk of Time-Loss Injury in Professional Team Sports? A Systematic Review of Methodology, Variables and Injury Risk in Practical Situations”. Em: Sports Medicine 50.9, pp. 1613–1635.
Bengtsson, H. et al. [2013]. “Muscle injury rates in professional football increase with fixture congestion: An 11-year follow-up of the UEFA Champions League injury study”. Em: British Journal of Sports Medicine 47.12, pp. 743–747.
Bowen, L. et al. [2020]. “Spikes in acute:chronic workload ratio (ACWR) associated with a 5–7 times greater injury rate in English Premier League football players: a comprehensive 3-year study”. Em: British Journal of Sports Medicine, pp. 731–738.
Carey, D. et al. [2016]. “Training loads and injury risk in Australian football-differing acute: Chronic workload ratios influence match injury risk”. Em: British Journal of Sports Medicine.
Delecroix, B. et al. [2018]. “Workload and non-contact injury incidence in elite football players competing in European leagues”. Em: European Journal of Sport Science 18.9, pp. 1280–1287.
Di Credico, A. et al. [2021]. “The prediction of running velocity during the 30–15 intermittent fitness test using accelerometry-derived metrics and physiological parameters: A machine learning approach”. Em: Intern. J. of Environmental Research and Public Health.
Dwyer, D. B. e Gabbett, Tim J. [2012]. “Global positioning system data analysis: velocity ranges and a new definition of sprinting for field sport athletes”. Em: Journal of Strength and Conditioning Research 26.3, pp. 818–824.
Eetvelde, H. V. et al. [2021]. “Machine learning methods in sport injury prediction and prevention: a systematic review”. Em: Journal of Experimental Orthopaedics 8.1.
Gabbett, T. J. [2016]. “The training-injury prevention paradox: should athletes be training smarter and harder?” Em: British Journal of Sports Medicine 50, pp. 273–280.
Jiang, Z. et al. [2022]. “A Systematic Review of the Relationship between Workload and Injury Risk of Professional Male Soccer Players”. Em: Inter. J. of Environmental Research and Public Health, p. 13237.
Malone, J. J. et al. [2015]. “Seasonal training-load quantification in elite English Premier League soccer players”. Em: Inter. J. of Sports Physiology and Performance, pp. 489–497.
Melo, M. et al. [2024]. “Data-Centric AI for predicting non-contact injuries in professional soccer players”. Em: XXXIX Simpósio Brasileiro de Bancos de Dados, pp. 167–180.
Piłka, T. et al. [2023]. “Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors”. Em: Sensors 23.3.
Rossi, A. et al. [2018]. “Effective injury forecasting in soccer with GPS training data and machine learning”. Em: PLoS ONE 13.7.
Salces, J.N. et al. [2014]. “An examination of injuries in Spanish Professional Soccer League”. Em: The Journal of sports medicine and physical fitness 6, pp. 765–771.
Vallance, E. et al. [2020]. “Combining internal- and external-training-loads to predict non-contact injuries in soccer”. Em: Applied Sciences 10.15.
Bengtsson, H. et al. [2013]. “Muscle injury rates in professional football increase with fixture congestion: An 11-year follow-up of the UEFA Champions League injury study”. Em: British Journal of Sports Medicine 47.12, pp. 743–747.
Bowen, L. et al. [2020]. “Spikes in acute:chronic workload ratio (ACWR) associated with a 5–7 times greater injury rate in English Premier League football players: a comprehensive 3-year study”. Em: British Journal of Sports Medicine, pp. 731–738.
Carey, D. et al. [2016]. “Training loads and injury risk in Australian football-differing acute: Chronic workload ratios influence match injury risk”. Em: British Journal of Sports Medicine.
Delecroix, B. et al. [2018]. “Workload and non-contact injury incidence in elite football players competing in European leagues”. Em: European Journal of Sport Science 18.9, pp. 1280–1287.
Di Credico, A. et al. [2021]. “The prediction of running velocity during the 30–15 intermittent fitness test using accelerometry-derived metrics and physiological parameters: A machine learning approach”. Em: Intern. J. of Environmental Research and Public Health.
Dwyer, D. B. e Gabbett, Tim J. [2012]. “Global positioning system data analysis: velocity ranges and a new definition of sprinting for field sport athletes”. Em: Journal of Strength and Conditioning Research 26.3, pp. 818–824.
Eetvelde, H. V. et al. [2021]. “Machine learning methods in sport injury prediction and prevention: a systematic review”. Em: Journal of Experimental Orthopaedics 8.1.
Gabbett, T. J. [2016]. “The training-injury prevention paradox: should athletes be training smarter and harder?” Em: British Journal of Sports Medicine 50, pp. 273–280.
Jiang, Z. et al. [2022]. “A Systematic Review of the Relationship between Workload and Injury Risk of Professional Male Soccer Players”. Em: Inter. J. of Environmental Research and Public Health, p. 13237.
Malone, J. J. et al. [2015]. “Seasonal training-load quantification in elite English Premier League soccer players”. Em: Inter. J. of Sports Physiology and Performance, pp. 489–497.
Melo, M. et al. [2024]. “Data-Centric AI for predicting non-contact injuries in professional soccer players”. Em: XXXIX Simpósio Brasileiro de Bancos de Dados, pp. 167–180.
Piłka, T. et al. [2023]. “Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors”. Em: Sensors 23.3.
Rossi, A. et al. [2018]. “Effective injury forecasting in soccer with GPS training data and machine learning”. Em: PLoS ONE 13.7.
Salces, J.N. et al. [2014]. “An examination of injuries in Spanish Professional Soccer League”. Em: The Journal of sports medicine and physical fitness 6, pp. 765–771.
Vallance, E. et al. [2020]. “Combining internal- and external-training-loads to predict non-contact injuries in soccer”. Em: Applied Sciences 10.15.
Publicado
08/09/2026
Como Citar
PADRÃO, Gabriel; MELO, Matheus; ARAÚJO, Ana G.; SPINETI, Juliano; GIUSTI, Lucas; BRANDÃO, Diego; SOARES, Jorge.
Predição de Lesões no Futebol Profissional com ACWR e Aprendizado de Máquina. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 819-825.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2026.249418.
