Decision Support System for Mitigating Athletic Injuries

Open access


The purpose of the present study was to demonstrate an inductive approach for dynamically modelling sport-related injuries with a probabilistic graphical model. Dynamic Bayesian Network (DBN), a well-known machine learning method, was employed to illustrate how sport practitioners could utilize a simulatory environment to augment the training management process. 23 University of Iowa female student-athletes (from 3 undisclosed teams) were regularly monitored with common athlete monitoring technologies, throughout the 2016 competitive season, as a part of their routine health and well-being surveillance. The presented work investigated the ability of these technologies to model injury occurrences in a dynamic, temporal dimension. To verify validity, DBN model accuracy was compared with the performance of its static counterpart. After 3 rounds of 5-fold cross-validation, resultant DBN mean accuracy surpassed naïve baseline threshold whereas static Bayesian network did not achieve baseline accuracy. Conclusive DBN suggested subjectively-reported stress two days prior, subjective internal perceived exertions one day prior, direct current potential and sympathetic tone the day of, as the most impactful towards injury manifestation.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Barrett S. Midgley A. & Lovell R. (2014). PlayerLoad™: Reliability convergent validity and influence of unit position during treadmill running. International Journal of Sports Physiology and Performance 9 945-952.

  • Boyd L. Ball K. & Aughey R. (2011). The reliability of MinimaxX accelerometers for measuring physical activity in Australian football. International Journal of Sports Physiology and Performance 6 311-321.

  • Blanch P. & Gabbett T. (2015). Has the athlete trained enough to return to play safely? The acute:chronic workload ratio permits clinicians to quantify a player’s risk of subsequent injury. British Journal of Sports Medicine 50 471-475.

  • Biermann A. (1987). Fundamental mechanisms in machine learning and inductive inference: Part 2. Advanced Topics in Artificial Intelligence 345 125-145.

  • Bittencourt N. Meeuwise W. Mendonca L. Nettel-Aguirre A. Ocarino L. & Fonseca S. (2016). Complex systems approach for sports injuries: Moving from risk factor identification to injury pattern recognition – narrative review and new concept. British Journal of Sports Medicine 50 1309-1314.

  • Buchheit M. (2014). Monitoring training status with HR measures: Do all roads lead to Rome? Frontiers in Physiology 5 1-19.

  • Buchheit M. Chivot A. Parouty J. Mercier D. Haddad A.H. Laursen P.B. & Ahmaid i S. (2009). Monitoring endurance running performance using cardiac parasympathetic function. European Journal of Applied Physiology 108(6) 1153–1167.

  • Coffey D. 1998. Self-organization complexity and chaos: The new biology for medicine.” Nature Medicine 4 882-885.

  • Conrady L. & Jouffe L. (2015). Bayesian networks and BayesiaLab – A practical introduction for researchers. Franklin TN: Bayesia USA.

  • Cook C. (2016). Predicting future physical injury in sports: It’s a complicated dynamic system. British Journal of Sports Medicine 50 1356-1357.

  • Drew M. & Finch C. (2016). The relationship between training load and injury illness andsoreness: A systematic review. Sports Medicine 46 861-883.

  • Dye S.F. (2001). Therapeutic implications of a tissue homeostasis approach to patellofemoral pain. Sports Medicine and Arthroscopy Review 9(4) 306–311.

  • Dye S.F. (2005). The pathophysiology of patellofemoral pain. Clinical Orthopaedics and Related Research 436 100–110.

  • Foster C. (1998). Monitoring training in athletes with reference to overtraining syndrome. Medicine & Science in Sports & Exercise 30 1164-1168.

  • Friedman N. (2004). Inferring cellular networks using probabilistic graphical models. Science 303 799-805.

  • Friedman N. Murphy K. & Russell S. (1998). Learning the structure of dynamic probabilistic networks. In G. Cooper & S. Moral (Eds.) Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (139-147). San Francisco CA: Morgan Kaufmann Publishers Inc.

  • Fuster-Parra P. Garcia-Mas A. Ponseti F. Palou P. & Cruz J. (2014). A bayesian network to discover relationships between negative features in sport: A case study of teen players. Quality & Quantity 48 1473-1491.

  • Gabbett T. (2010). The development and application of an injury prediction model for noncontact soft-tissue injuries in elite collision sport athletes. Journal of Strength and Conditioning Research 24 2593-2603.

  • Gabbett T. (2016). The training-injury prevention paradox: Should athletes be training smarter and harder?” British Journal of Sport Medicine 50 273-280.

  • Galea S. Riddle M. & Kaplan G. (2010). Causal thinking and complex system approaches in epidemiology. International Journal of Epidemiology 39 97-106.

  • Gemela J. (2001). Financial analysis using bayesian networks. Applied Stochastic Models in Business and Industry 17 57-67.

  • Gisselman A.S. Baxter G.D. Wright A. Hegedus E. & Tumilty E. (2016). Musculoskeletal overuse injuries and heart rate variability: Is there a link? Medical Hypotheses 87(C) 1–7.

  • Glover F. (1986). Future paths for integer programming and links to artificial intelligence. Computers and Operations Research 13 533-549.

  • Halson S. (2014). Monitoring training load to understand fatigue in athletes. Sports Medicine 44 139-147.

  • Hautala A. Tulppo M.P. Mäkikallio T.H. Laukkanen R. Nissilä S. & Huikuri H.V. (2001). Changes in cardiac autonomic regulation after prolonged maximal exercise. Clinical Physiology 21(2) 238–245.

  • Holme B.R. (2015). Wearable microsensor technology to measure physical activity demands in handball: A reliability study of Inertial Movement Analysis and PlayerLoad (master’s thesis). Norwegian School of Sport Sciences Oslo Norway.

  • Hooper K. Mackinnon L. Howard A. Gordon R. & Bachman A. (1995). Markers for monitoring overtraining and recovery. Medicine & Science in Sports & Exercise 27 106-112.

  • Hulin B. Gabbett T. Lawson D. Captui P. & Sampson J. (2015). The acute:chronic workload ratio predicts injury: High chronic workload may decrease injury risk in elite rugby league players. British Journal of Sports Medicine 50 231-236.

  • Ilyukhina V. A. (2011). Continuity and prospects of research in systemic integrative psychophysiology of functional states and cognitive activity. Human Physiology 37(4) 484–499.

  • Ilyukhina V. A. (2013). Ultraslow information control systems in the integration of life activity processes in the brain and body. Human Physiology 39(3) 323–333.

  • Ivarsson A. & Johnson U. (2010). Psychological factors as predictors of injuries among senior soccer players. A prospective study. Journal of Sport Science and Medicine 9 347-352.

  • Ivarsson A. Johnson U. & Poglog L. (2013). Psychological predictors of injury occurrence: A prospective investigation of professional Swedish soccer players.” Journal of Sport Rehabilitation 22 19-26.

  • Jouffe L. & Munteanu P. (2001). New search strategies for learning bayesian networks. Proceedings of the Tenth International Symposium on Applied Stochastic Models and Data Analysis 2 591-596.

  • Koller D. & Friedman N. (2009). Probabilistic Graphical Models: Principles and Techniques. Cambridge MA: MIT Press.

  • Korb K. & Nicholson A. (2011). Bayesian artificial intelligence. In D. Blei D. Madigan M. Meila & F. Murtagh (Eds.). Boca Raton FL: Taylor & Francis Group LLC.

  • Lam W. & Bacchus F. (1994). Learning bayesian belief networks: An approach based on MDL principle. Computational Intelligence 10(4) 271-293.

  • Larranaga P. & Moral S. (2011). Probabilistic graphical models in artificial intelligence. Applied Soft Computing 11 1511-1528.

  • Laux P. Krumm B Diers D.M. & Flor H. (2015). Recovery-stress balance and injury risk in professional football players: A prospective study. Journal of Sports Sciences 33 2140-2148.

  • Lucas P. van der Gaag L. & Abu-Hanna A. (2004). Bayesian networks in biomedicine and healthcare. Artificial Intelligence in Medicine 30 201-214.

  • Neapolitan R. (2004). Learning bayesian networks. Englewood Cliffs NJ: Prentice Hall.

  • Nicholson J. Holmes E. Lindon J. & Wilson I. (2004). The challenge of modelling mammalian biocomplexity. Nature Biotechnology 22 1268-1274.

  • Mah C.D. Mah K.E. Kezirian E.J. & Dement W. (2011). The effects of sleep extension on the athletic performance of collegiate basketball players. Sleep 34(7) 943–950.

  • Meeuwisse W. (1994). Causation in sports injury: A multifactorial model. Clinical Journal of Sport Medicine 4 166-170.

  • Pearl J. (1988). Probabilistic reasoning in intelligent systems: Networks of plausible inference. San Mateo CA: Morgan Kaufmann Publishers Inc.

  • Philippe P. & Mansi O. (1998). Nonlinearity in the epidemiology of complex health and disease process. Theoretical Medicine and Bioethics 19 591-607.

  • Quatman C. Quatman C. & Hewett T. (2009). Prediction and prevention of musculoskeletal injury: A paradigm shift in methodology. British Journal of Sports Medicine 43 1100-1107.

  • Reyner L.A. & Horne J.A. (2013). Sleep restriction and serving accuracy in performance tennis players and effects of caffeine. Physiology and Behavior 120 93–96.

  • Rodgers T. & Landers D. (2005). Mediating effects of peripheral vision in the life event stress/athletic injury relationship. Sport Psychology 27 271-288.

  • Russell S. & Norvig P. (2003). Artificial intelligence: A modern approach. Upper Saddle River NJ: Pearson Inc.

  • Soligard T. Schwellnus M. Alonso J. Bahr R. Clarsen B. Dijkstra H. Gabbett T. Gleeson M. Hagglund M. Hutchinson M. Janse van Rensburg C. Khan K. Meeusen R. Orchard J. Pluim B. Raftery M. Budgett R. & Engebretsen L. (2016). How much is too Much? (Part 1) International Olympic Committee consensus statement on load in sport and risk of injury. British Journal of Sports Medicine 50 1030-1041.

  • Timpka T. Jacobsson J. Dahlström Ö. Kowalski J. Bargoria V. Ekberg J. Nilsson S. & Renström P. (2015). The psychological factor ‘self-blame’ predicts overuse injury among top-level Swedish track and field athletes: A 12-month cohort study. British Journal of Sports Medicine 49 1472-1477.

  • Tufféry S. (2011). Data mining and statistics for decision making. West Sussex UK: John Wiley & Sons Ltd.

  • Vilamitjana J.J. Lentini N.A. Perez M.F.J & Verde P.E. (2014). Heart rate variability as biomarker of training load in professional soccer players. Medicine and Science in Sports and Exercise 46(5) 842–843.

  • Williams J. Tonymon P. & Anderson M. (1991). Effects of stressors and coping resources on anxiety and peripheral narrowing. Journal of Applied Sport Psychology 16 174-181.

  • Williams S. West S. Cross M. & Stokes K. (2017). Better way to determine the acute:chronic workload ratio?. British Journal of Sports Medicine 51 209-210.

  • Williamson L. (2005). Bayesian nets and causality: Philosophical and computational foundations. Oxford England: Oxford University Press.

  • Zebis M. K. Bencke L. Andersen L.L. Alkjaer T. Suetta C. Mortensen P. Kjaer M. & Aagaard P. (2010). Acute fatigue impairs neuromuscular activity of anterior cruciate ligament-agonist muscles in female team handball players. Scandinavian Journal of Medicine and Science in Sports 21(6) 833–840.

  • Zou M. & Conzen S. (2005). A new dynamic bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data. Bioinformatics 21 71-79.

Journal information
Impact Factor

CiteScore 2018: 0.71

SCImago Journal Rank (SJR) 2018: 0.355
Source Normalized Impact per Paper (SNIP) 2018: 0.462

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 2525 2525 235
PDF Downloads 1659 1659 165