Using Decision Trees to Support Classifiers’ Decision-Making about Activity Limitation of Cerebral Palsy Footballers

Abstract

This study aimed (1) to determine the appropriateness of using decision trees as a classification tool for determining the allocation of sport classes of para-footballers with “moderate vs. mild” cerebral palsy (CP) profiles of spastic diplegia/hemiplegia and ataxia/athetosis based on observational outcomes by international classifiers, and (2) to identify what key observational features were relevant to discriminating among different impairment levels. A sample of 16 experienced international classifiers from five world regions participated in this study, observing activity limitation of a final sample of 21 international CP footballers when performing 16 gross-motor and sports-specific tests for balance (n = 3), coordination (n = 5), running, accelerations and decelerations (n = 3), jumping (n = 4), and change of direction ability (n = 1). For the overall sample (336 observations), the model included eight decision nodes and 24 branches with 17 leaves, including side-step, side-stepping, and triple hop as the tests with the best sensitivity (precision = 67.0%). For those with spastic diplegia (64 observations: Two nodes, six branches with five leaves), the range of motion in the side-step test and the balance in the tandem walk tests correctly classified 89.1% of the observations. In those with athetosis and ataxia (96 observations), the model included five nodes, 15 branches, and 11 leaves (176 observations, precision = 86.5%). For those with spastic hemiplegia, a model containing two nodes, six branches, and five leaves had 90.9% accuracy, including observational features of balance in the side-step test and symmetry in the side-stepping test. The observational tool used in this study, based on the impact of specific impairment measurements of hypertonia, athetosis, and ataxia, can be used to determine which assessments are more appropriate for discriminating between functional profiles in para-footballers with CP.

Relationships between take-off speed and performance in F-44 and F-46 paralympic discus throwers

“…Notably, the F-44 class is designed especially for athletes with lower limb disabilities, usually amputees and individuals with cerebral palsy (www.cpb.org.br). Balance is among the variables with the greatest impact on motor control in sports activities in the standing position (Reina et al, 2022;Sarabia et al, 2021). Although this is a speculative aspect, athletes in such classes are likely to have less capacity to maintain dynamic balance, especially in activities with greater muscle power.…”

To What Degree Does Limb Spasticity Affect Motor Performance in Para-Footballers With Cerebral Palsy?

“…The test was performed twice with each leg (RHT D and RHT ND ), starting first with the dominant side and heel contact with 1 min rest between attempts. When the participant makes an erroneous contact, the attempt is not considered, and the time (in s) to complete the fastest two trials were registered ( Reina et al, 2021b ; Sarabia et al, 2021 ).…”

Futebol para pessoas com paralisia cerebral: revisão de escopo

“…Dos artigos selecionados para esta revisão, 11 nos trazem achados importantes em relação à classificação esportiva do futebol PC. De modo geral, quando aplicados testes físico/motores os atletas de classe baixa (FT1) obtiveram resultados inferiores quando comparados com atletas de classe alta (FT3) (Daniel et al, 2020;Henriquez et al, 2020;Reina et al, 2016Reina et al, , 2017Reina et al, , 2018Reina et al, , 2019Reina et al, , 2020Rosch de Faria et al, 2018;Sarabia et al, 2021;Yanci et al, 2018). Esses resultados demonstram que pode existir uma relação clara entre o desempenho esportivo e a classe funcional.…”

“…Assim, através dos resultados demonstrados aqui é possível identificar testes que podem ser utilizados para avaliar fatores que podem ser determinantes para diferenciar as diferentes classes esportivas e a gravidade da deficiência. Os principais testes utilizados nos artigos reunidos nesta revisão de escopo foram testes que avaliaram saltos (n = 5) (Reina et al, 2018(Reina et al, , 2019(Reina et al, , 2020Rosch de Faria et al, 2018;Sarabia et al, 2021), testes de agilidade (n = 4) (Reina et al, 2016(Reina et al, , 2017Rosch de Faria et al, 2018;Sarabia et al, 2021), testes de sprint (n = 4) (Henriquez et al, 2020;Reina et al, 2017Reina et al, , 2020Sarabia et al, 2021), testes de habilidades com a bola (n = 1) (Daniel et al, 2020) e testes que avaliaram o equilíbrio (n = 2) (Reina et al, 2020;Sarabia et al, 2021). Alguns dos testes apresentados já estão presentes nas regras e regulamentos da classificação do IFCPF de 2018 (IFCPF Classification Rules, 2018).…”

“…A tecnologia também tem se mostrado uma ferramenta que pode auxiliar os classificadores na tomada de decisão. A utilização de sensores inerciais pode enriquecer avaliações de equilíbrio e coordenação por conseguirem coletar sinais de variação de aceleração em três eixos diferentes (Di Paolo et al, 2021) além disso, Sarabia et al (2021) demonstram como a utilização de arvores de decisões (modelos preditivos) podem ser aplicados na prática, tornando o processo de classificação ainda mais objetivo.…”