anterior cruciate ligament; artificial intelligence; football; large language models; sports medicine; Humans; Male; Adult; Sensitivity and Specificity; Young Adult; Return to Sport; Search Engine; Anterior Cruciate Ligament Injuries/diagnosis; Soccer/injuries; Databases, Factual; Artificial Intelligence; Anterior Cruciate Ligament Injuries; Soccer; Surgery; Orthopedics and Sports Medicine
Abstract :
[en] [en] PURPOSE: While public databases like Transfermarkt provide valuable data for assessing the impact of anterior cruciate ligament (ACL) injuries in professional footballers, they require robust verification methods due to accuracy concerns. We hypothesised that an artificial intelligence (AI)-powered framework could cross-check ACL tear-related information from large publicly available data sets with high specificity.
METHODS: The AI-powered framework uses Google Programmable Search Engine to search a curated, multilingual list of websites and OpenAI's GPT to translate search queries, appraise search results and analyse injury-related information in search result items (SRIs). Specificity was the chosen performance metric-the AI-powered framework's ability to accurately identify texts that do not mention an athlete suffering an ACL tear-with SRI as the evaluation unit. A database of ACL tears in male professional footballers from first- and second-tier leagues worldwide (1999-2024) was collected from Transfermarkt.com, and players were randomly selected for appraisal until enough SRIs were obtained to validate the framework's specificity. Player age at injury and time until return-to-play (RTP) were recorded and compared with Union of European Football Associations (UEFA) Elite Club Injury Study data.
RESULTS: Verification of 231 athletes yielded 1546 SRIs. Human analysis of the SRIs showed that 335 mentioned an ACL tear, corresponding to 83 athletes with ACL tears. Specificity and sensitivity of GPT in identifying mentions of ACL tears in a player were 99.3% and 88.4%, respectively. Mean age at rupture was 26.6 years (standard deviation: 4.6, 95% confidence interval [CI]: 25.6-27.6). Median RTP time was 225 days (interquartile range: 96, 95% CI: 209-251), which is comparable to reports using data from the UEFA Elite Club Injury Study.
CONCLUSION: This study shows that an AI-powered framework can achieve high specificity in cross-checking ACL tear reports in male professional football from public databases, markedly reducing manual workload and enhancing the reliability of media-based sports medicine research.
LEVEL OF EVIDENCE: Level III.
Disciplines :
Physical, chemical, mathematical & earth Sciences: Multidisciplinary, general & others
Author, co-author :
Diniz, Pedro ; Department of Orthopaedic Surgery, Centre Hospitalier de Luxembourg - Clinique d'Eich, Luxembourg, Luxembourg ; Luxembourg Institute of Research in Orthopaedics, Sports Medicine and Science (LIROMS), Luxembourg, Luxembourg ; Luxembourg Institute of Health (LIH), Luxembourg, Luxembourg ; Department of Bioengineering, iBB - Institute for Bioengineering and Biosciences, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
GRIMM, Bernd ; University of Luxembourg ; Luxembourg Institute of Health (LIH), Luxembourg, Luxembourg
Mouton, Caroline; Department of Orthopaedic Surgery, Centre Hospitalier de Luxembourg - Clinique d'Eich, Luxembourg, Luxembourg ; Luxembourg Institute of Research in Orthopaedics, Sports Medicine and Science (LIROMS), Luxembourg, Luxembourg
LEY, Christophe ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Mathematics (DMATH)
Andersen, Thor Einar; Oslo Sports Trauma Research Center, Department of Sports Medicine, Norwegian School of Sport Sciences, Oslo, Norway
Seil, Romain; Department of Orthopaedic Surgery, Centre Hospitalier de Luxembourg - Clinique d'Eich, Luxembourg, Luxembourg ; Luxembourg Institute of Research in Orthopaedics, Sports Medicine and Science (LIROMS), Luxembourg, Luxembourg ; Luxembourg Institute of Health (LIH), Luxembourg, Luxembourg
External co-authors :
yes
Language :
English
Title :
High specificity of an AI-powered framework in cross-checking male professional football anterior cruciate ligament tear reports in public databases.
Carey, J.L. (2023) The critical reader: data sources. The American Journal of Sports Medicine, 51(12), 3103–3105. Available from: https://doi.org/10.1177/03635465231200790
Choi, R.Y., Coyner, A.S., Kalpathy-Cramer, J., Chiang, M.F. & Campbell, J.P. (2020) Introduction to machine learning, neural networks, and deep learning. Translational Vision Science and Technology, 9(2), 14. Available from: https://doi.org/10.1167/tvst.9.2.14
Dave, T., Athaluri, S.A. & Singh, S. (2023) ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Frontiers Artificial Intelligence, 6, 1169595. Available from: https://doi.org/10.3389/frai.2023.1169595
Diaz, C.C., Forlenza, E.M., Lavoie-Gagne, O.Z., Knapik, D.M., Korrapati, A., Chahla, J. et al. (2021) Acromioclavicular joint separation in UEFA soccer players: a matched-cohort analysis of return to play and player performance from 1999 to 2018. Orthopaedic Journal of Sports Medicine, 9(10), 23259671211026262. Available from: https://doi.org/10.1177/23259671211026262
Diniz, P., Abreu, M., Lacerda, D., Martins, A., Pereira, H., Ferreira, F.C. et al. (2022) Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier. Knee Surgery, Sports Traumatology, Arthroscopy, 30(12), 4225–4237. Available from: https://doi.org/10.1007/s00167-022-07082-4
Diniz, P., Lacerda, D., Mendes, B., Pereira, H., Ferreira, F.C. & Kerkhoffs, G.M.M.J. (2023) Return-to-performance in elite soccer players after Achilles tendon ruptures: a study using a weighted plus/minus metric and matched-control analysis. Knee Surgery, Sports Traumatology, Arthroscopy, 31(12), 6059–6068. Available from: https://doi.org/10.1007/s00167-023-07607-5
Ekstrand, J., Krutsch, W., Spreco, A., van Zoest, W., Roberts, C., Meyer, T. et al. (2020) Time before return to play for the most common injuries in professional football: a 16-year follow-up of the UEFA Elite Club Injury Study. British Journal of Sports Medicine, 54(7), 421–426. Available from: https://doi.org/10.1136/bjsports-2019-100666
Fayed, A.M., Mansur, N.S.B., de Carvalho, K.A., Behrens, A., D'Hooghe, P. & de Cesar Netto, C. (2023) Artificial intelligence and ChatGPT in orthopaedics and sports medicine. Journal of Experimental Orthopaedics, 10(1), 74. Available from: https://doi.org/10.1186/s40634-023-00642-8
FIFPRO (n.d.) Men's Player Workload Monitoring Platform: an analytical tool from FIFPRO and Football Benchmark—FIFPRO world players' union. FIFPRO. Available from: https://fifpro.org/en/men-s-player-workload-monitoring-platform [Accessed 9th Oct 2024].
Florez, F. (2024) REST countries. Available from: https://restcountries.com/ [Accessed 19th Aug 2024].
Forlenza, E.M., Lavoie-Gagne, O.Z., Lu, Y., Diaz, C.C., Chahla, J. & Forsythe, B. (2021) Return to play and player performance after achilles tendon rupture in UEFA professional soccer players: a matched-cohort analysis of players from 1999 to 2018. Orthopaedic Journal of Sports Medicine, 9(9), 23259671211024199. Available from: https://doi.org/10.1177/23259671211024199
Forsythe, B., Lavoie-Gagne, O.Z., Forlenza, E.M., Diaz, C.C. & Mascarenhas, R. (2021) Return-to-play times and player performance after ACL reconstruction in elite UEFA professional soccer players: a matched-cohort analysis from 1999 to 2019. Orthopaedic Journal of Sports Medicine, 9(5), 23259671211008892. Available from: https://doi.org/10.1177/23259671211008892
Grassi, A., Rossi, G., D'Hooghe, P., Aujla, R., Mosca, M., Samuelsson, K. et al. (2020) Eighty-two per cent of male professional football (soccer) players return to play at the previous level two seasons after Achilles tendon rupture treated with surgical repair. British Journal of Sports Medicine, 54(8), 480–486. Available from: https://doi.org/10.1136/bjsports-2019-100556
Grassi, A., Macchiarola, L., Filippini, M., Lucidi, G.A., Della Villa, F. & Zaffagnini, S. (2020) Epidemiology of anterior cruciate ligament injury in Italian first division soccer players. Sports Health: A Multidisciplinary Approach, 12(3), 279–288. Available from: https://doi.org/10.1177/1941738119885642
Grauer, J.N. & Leopold, S.S. (2015) Editorial: large database studies—what they can do, what they cannot do, and which ones we will publish. Clinical Orthopaedics & Related Research, 473(5), 1537–1539. Available from: https://doi.org/10.1007/s11999-015-4223-z
Hoenig, T., Edouard, P., Krause, M., Malhan, D., Relógio, A., Junge, A. et al. (2022) Analysis of more than 20,000 injuries in European professional football by using a citizen science-based approach: an opportunity for epidemiological research? Journal of Science and Medicine in Sport, 25(4), 300–305. Available from: https://doi.org/10.1016/j.jsams.2021.11.038
Den Hollander, S., Kerkhoffs, G. & Gouttebarge, V. (2024) The impact of match workload and international travel on injuries in professional men's football. Sports, 12(8), 212. Available from: https://doi.org/10.3390/sports12080212
Inclan, P.M., Chang, P.S., Mack, C.D., Solomon, G.S., Brophy, R.H., Hinton, R.Y. et al. (2022) Validity of research based on public data in sports medicine: a quantitative assessment of anterior cruciate ligament injuries in the National Football League. The American Journal of Sports Medicine, 50(6), 1717–1726. Available from: https://doi.org/10.1177/03635465211015435
Krutsch, V., Grechenig, S., Loose, O., Achenbach, L., Zellner, J., Striegel, H. et al. (2020) Injury analysis in professional soccer by means of media reports—only severe injury types show high validity. Open Access Journal of Sports Medicine, 11, 123–131.
Kumar, P. (2024) Large language models (LLMs): survey, technical frameworks, and future challenges. Artificial Intelligence Review, 57(10), 260. Available from: https://doi.org/10.1007/s10462-024-10888-y
Kvist, J. & Pettersson, M. (2024) Knee-related quality of life compared between 20 and 35 years after an anterior cruciate ligament injury treated surgically with primary repair or reconstruction, or nonsurgically. The American Journal of Sports Medicine, 52(2), 311–319. Available from: https://doi.org/10.1177/03635465231218237
Lavoie-Gagne, O., Mehta, N., Patel, S., Cohn, M.R., Forlenza, E., Nwachukwu, B.U. et al. (2021) Adductor muscle injuries in UEFA soccer athletes: a matched-cohort analysis of injury rate, return to play, and player performance from 2000 to 2015. Orthopaedic Journal of Sports Medicine, 9(9), 23259671211023098. Available from: https://doi.org/10.1177/23259671211023098
Leventer, L., Eek, F., Hofstetter, S. & Lames, M. (2016) Injury patterns among elite football players: a media-based analysis over 6 seasons with emphasis on playing position. International Journal of Sports Medicine, 37(11), 898–908. Available from: https://doi.org/10.1055/s-0042-108201
Lewis, N. (2021) Sports as (digital) media entertainment. In: Vorderer, P. & Klimmt, C. (Eds.) The Oxford handbook of entertainment theory. New York, NY: Oxford University Press. https://doi.org/10.1093/oxfordhb/9780190072216.013.27
Monti, C.B., Ambrogi, F. & Sardanelli, F. (2024) Sample size calculation for data reliability and diagnostic performance: a go-to review. European Radiology Experimental, 8, 79. Available from: https://doi.org/10.1186/s41747-024-00474-w
Niederer, D., Engeroff, T., Wilke, J., Vogt, L. & Banzer, W. (2018) Return to play, performance, and career duration after anterior cruciate ligament rupture: a case-control study in the five biggest football nations in Europe. Scandinavian Journal of Medicine & Science in Sports, 28(10), 2226–2233. Available from: https://doi.org/10.1111/sms.13245
Oettl, F.C., Pareek, A., Winkler, P.W., Zsidai, B., Pruneski, J.A., Senorski, E.H. et al. (2024) A practical guide to the implementation of AI in orthopaedic research, part 6: how to evaluate the performance of AI research? Journal of Experimental Orthopaedics, 11(3), e12039. Available from: https://doi.org/10.1002/jeo2.12039
Pinheiro, V.H., Borque, K.A., Laughlin, M.S., Jones, M., Balendra, G., Kent, M.R. et al. (2023) Determinants of performance in professional soccer players at 2 and 5 years after ACL reconstruction. The American Journal of Sports Medicine, 51(14), 3649–3657. Available from: https://doi.org/10.1177/03635465231207832
Prentice, H.A., Lind, M., Mouton, C., Persson, A., Magnusson, H., Gabr, A. et al. (2018) Patient demographic and surgical characteristics in anterior cruciate ligament reconstruction: a description of registries from six countries. British Journal of Sports Medicine, 52(11), 716–722. Available from: https://doi.org/10.1136/bjsports-2017-098674
Requejo-Herrero, P., Pineda-Galan, C. & Medina-Porqueres, I. (2023) Anterior cruciate ligament ruptures in Spanish soccer first division: an epidemiological retrospective study. The Knee, 41, 48–57. Available from: https://doi.org/10.1016/j.knee.2022.11.014
Sanders, T.L., Pareek, A., Desai, V.S., Hewett, T.E., Levy, B.A., Stuart, M.J. et al. (2018) Low accuracy of diagnostic codes to identify anterior cruciate ligament tear in Orthopaedic Database Research. The American Journal of Sports Medicine, 46(12), 2894–2898. Available from: https://doi.org/10.1177/0363546518790507
Schiffner, E., Latz, D., Grassmann, J.P., Schek, A., Scholz, A., Windolf, J. et al. (2019) Fractures in German elite male soccer players. The Journal of Sports Medicine and Physical Fitness, 59(1), 110–115. Available from: https://doi.org/10.23736/S0022-4707.17.07901-4
Seil, R., Pioger, C., Siboni, R., Amendola, A. & Mouton, C. (2023) The Anterior Cruciate Ligament Injury Severity Scale (ACLISS) is an effective tool to document and categorize the magnitude of associated tissue damage in knees after primary ACL injury and reconstruction. Knee Surgery, Sports Traumatology, Arthroscopy, 31(7), 2983–2997. Available from: https://doi.org/10.1007/s00167-023-07311-4
Sochacki, K.R., Jack II, R.A., Hirase, T., McCulloch, P.C., Lintner, D.M., Varner, K.E. et al. (2019) There is a high return to sport rate but with reduced career lengths after Achilles tendon repair in Major League Soccer players. Journal of ISAKOS, 4(1), 15–20. Available from: https://doi.org/10.1136/jisakos-2018-000246
Transfermarkt.com (2024) Transfermarkt.com: football transfers, rumours, market values, news and statistics. Available from: http://www.transfermarkt.com [Accessed 19th Aug 2024].
Della Villa, F., Hägglund, M., Della Villa, S., Ekstrand, J. & Waldén, M. (2021) High rate of second ACL injury following ACL reconstruction in male professional footballers: an updated longitudinal analysis from 118 players in the UEFA elite club injury study. British Journal of Sports Medicine, 55(23), 1350–1357. Available from: https://doi.org/10.1136/bjsports-2020-103555
Wilke, J., Tenberg, S. & Groneberg, D. (2022) Prognostic factors of muscle injury in elite football players: a media-based, retrospective 5-year analysis. Physical Therapy in Sport, 55, 305–308. Available from: https://doi.org/10.1016/j.ptsp.2022.05.009
Zsidai, B., Kaarre, J., Narup, E., Hamrin Senorski, E., Pareek, A., Grassi, A. et al. (2024) A practical guide to the implementation of artificial intelligence in orthopaedic research—part 2: a technical introduction. Journal of Experimental Orthopaedics, 11(3), e12025. Available from: https://doi.org/10.1002/jeo2.12025
