Can Injuries Be Predicted by Functional Movement Screen in Adolescents? The Application of Machine Learning

Abstract

Karuc, J, Mišigoj-Duraković, M, Šarlija, M, Marković, G, Hadžić, V, Trošt-Bobić, T, and Sorić, M. Can injuries be predicted by functional movement screen in adolescents? The application of machine learning. J Strength Cond Res 35(4): 910–919, 2021—This study used machine learning (ML) to predict injuries among adolescents by functional movement testing. This research is a part of the CRO-PALS study conducted in a representative sample of adolescents and analyses for this study are based on nonathletic (n = 364) and athletic (n = 192) subgroups of the cohort (16–17 years). Sex, age, body mass index (BMI), body fatness, moderate-to-vigorous physical activity (MVPA), training hours per week, Functional Movement Screen (FMS), and socioeconomic status were assessed at baseline. A year later, data on injury occurrence were collected. The optimal cut-point of the total FMS score for predicting injury was calculated using receiver operating characteristic curve. These predictors were included in ML analyses with calculated metrics: area under the curve (AUC), sensitivity, specificity, and odds ratio (95% confidence interval [CI]). Receiver operating characteristic curve analyses with associated criterium of total FMS score >12 showed AUC of 0.54 (95% CI: 0.48–0.59) and 0.56 (95% CI: 0.47–0.63), for the nonathletic and athletic youth, respectively. However, in the nonathletic subgroup, ML showed that the Naïve Bayes exhibited highest AUC (0.58), whereas in the athletic group, logistic regression was demonstrated as the model with the best predictive accuracy (AUC: 0.62). In both subgroups, with given predictors: sex, age, BMI, body fat percentage, MVPA, training hours per week, socioeconomic status, and total FMS score, ML can give a more accurate prediction then FMS alone. Results indicate that nonathletic boys who have lower-body fat could be more prone to suffer from injury incidence, whereas among athletic subjects, boys who spend more time training are at a higher risk of being injured. Conclusively, total FMS cut-off scores for each subgroup did not successfully discriminate those who suffered from those who did not suffer from injury, and, therefore, our research does not support FMS as an injury prediction tool.

A Narrative Review for a Machine Learning Application in Sports: An Example Based on Injury Forecasting in Soccer

“…Jump, sprint on 10 and 20 m, Change Of Direction (COD), and YoYo tests are only a few examples of all the tests performed on sport fields [ 43 , 44 ]. Moreover, neuromuscular assessment (e.g., core stability, joints range of motion, isokinetic joints flexion and extension strength, and Functional Movement Screen) are other evaluation tests that allow for the assessment the stability and mobility of the joints that are found to be linked to the injury risk [ 20 , 23 , 45 , 46 ].…”

Assessment of Dysfunctional Movements and Asymmetries in Children and Adolescents Using the Functional Movement Screen—A Narrative Review

“…Although there is a plethora of research on the use of the FMS in adults, there is growing scientific evidence indicating the use of the FMS in youth. Studies to date have been performed in the United States, Canada [ 42 , 43 ], Hungary and Germany [ 44 , 45 ], Italy [ 46 ], Moldova [ 38 ], countries of the UK [ 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 ], Ireland [ 58 , 59 ], Poland [ 60 , 61 , 62 , 63 , 64 ], Slovakia [ 65 ], Iran [ 66 , 67 , 68 ], Turkey [ 69 , 70 , 71 , 72 , 73 , 74 ], Japan [ 75 ], China [ 76 , 77 ], Thailand [ 32 ], Taiwan [ 78 , 79 , 80 ], Korea [ 81 ], Indonesia [ 82 ], Croatia [ 40 , 41 , 83 , 84 ], Brazil [ 85 ], Portugal [ 86 ], Spain [ 87 , 88 , 89 , 90 …”

“…Performance on the FMS can include comparisons between boys and girls on the total FMS score, scores on individual test items, and prevalence of asymmetries and dysfunctional scores. Of the available studies, some include both boys and girls [ 32 , 40 , 41 , 44 , 54 , 55 , 57 , 58 , 59 , 62 , 63 , 76 , 77 , 78 , 81 , 82 , 83 , 84 , 86 , 87 , 88 , 89 , 91 , 92 , 93 , 103 , 108 ], some include only boys [ 43 , 46 , 47 , 50 , 51 , 53 , 56 , 61 , 64 , 66 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 80 , 85 , 90 , 94 , 97 , 100 , 101 , 102 …”

“…Using the FMS to assess asymmetries is important because having asymmetrical movement patterns in two or more individual tests items increases the risk of injury [ 109 ]. Nevertheless, many studies that use the FMS to assess motor competency in youth do not report the prevalence of asymmetries in bilateral tests or dysfunctional scores [ 32 , 40 , 41 , 47 , 53 , 58 , 59 , 61 , 62 , 63 , 69 , 73 , 74 , 76 , 78 , 79 , 81 , 82 , 83 , 84 , 87 , 89 , 90 , 91 , 93 , 106 , 108 ].…”

“…,54,55,[57][58][59]62,63,[76][77][78][81][82][83][84][86][87][88][89][91][92][93]103,108], some include only boys[43,46,47,50,51,53,56,61,64,66,[68][69][70][71][72][73][74][75]80,85,90,94,97,[100][101][102]105,106,109] and some studies do not report the sex of the participants at all[14,52,…”