Porth Ymchwil

A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis

Allbwn ymchwil: Cyfraniad at gyfnodolyn › Erthygl › adolygiad gan gymheiriaid

StandardStandard

A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis. / Silveira Bianchim, Mayara; McNarry, Melitta A.; Barker, Alan et al.
Yn: Measurement in Physical Education and Exercise Science, 24.10.2023.

Allbwn ymchwil: Cyfraniad at gyfnodolyn › Erthygl › adolygiad gan gymheiriaid

HarvardHarvard

Silveira Bianchim, M, McNarry, MA, Barker, A, Williams, C, Denford, S, Thia, L, Evans, R & Mackintosh, K 2023, 'A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis', Measurement in Physical Education and Exercise Science. https://doi.org/10.1080/1091367X.2023.2271444

APA

Silveira Bianchim, M., McNarry, M. A., Barker, A., Williams, C., Denford, S., Thia, L., Evans, R., & Mackintosh, K. (2023). A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis. Measurement in Physical Education and Exercise Science. Cyhoeddiad ar-lein ymlaen llaw. https://doi.org/10.1080/1091367X.2023.2271444

CBE

Silveira Bianchim M, McNarry MA, Barker A, Williams C, Denford S, Thia L, Evans R, Mackintosh K. 2023. A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis. Measurement in Physical Education and Exercise Science. https://doi.org/10.1080/1091367X.2023.2271444

MLA

Silveira Bianchim, Mayara et al. "A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis". Measurement in Physical Education and Exercise Science. 2023. https://doi.org/10.1080/1091367X.2023.2271444

VancouverVancouver

Silveira Bianchim M, McNarry MA, Barker A, Williams C, Denford S, Thia L et al. A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis. Measurement in Physical Education and Exercise Science. 2023 Hyd 24. Epub 2023 Hyd 24. doi: https://doi.org/10.1080/1091367X.2023.2271444

Author

Silveira Bianchim, Mayara ; McNarry, Melitta A. ; Barker, Alan et al. / A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis. Yn: Measurement in Physical Education and Exercise Science. 2023.

RIS

TY - JOUR

T1 - A Machine Learning Approach for Physical Activity Recognition in Cystic Fibrosis

AU - Silveira Bianchim, Mayara

AU - McNarry, Melitta A.

AU - Barker, Alan

AU - Williams, Craig

AU - Denford, Sarah

AU - Thia, Lena

AU - Evans, Rachel

AU - Mackintosh, Kelly

PY - 2023/10/24

Y1 - 2023/10/24

N2 - This study aimed to develop and validate machine learning models to predict intensities in children and adolescents with cystic fibrosis (CF) across different accelerometry brands and placements. Thirty-five children and adolescents with CF (11.6 ± 2.8 yrs; 15 girls) and 28 healthy youth (12.2 ± 2.7 yrs; 16 girls) performed six activities whilst wearing GENEActivs (both wrists) and ActiGraphs GT9X (both wrists and waist). Three supervised learning classifiers (K-Nearest Neighbour, Random Forest and eXtreme Gradient Boosted Decision Tree) were used to identify the input signal pattern for each PA type and intensity, with a 10-fold cross-validation utilized to assess the performance of the classifiers. ActiGraph GT9X on the dominant wrist and waist and GENEActiv on the dominant wrist failed to predict vigorous intensity PA activities. All other models, for activity type and intensities, exceeded 97% accuracy, with a sensitivity and specificity of greater than 95%, irrespective of accelerometer brand, placement or health condition.

AB - This study aimed to develop and validate machine learning models to predict intensities in children and adolescents with cystic fibrosis (CF) across different accelerometry brands and placements. Thirty-five children and adolescents with CF (11.6 ± 2.8 yrs; 15 girls) and 28 healthy youth (12.2 ± 2.7 yrs; 16 girls) performed six activities whilst wearing GENEActivs (both wrists) and ActiGraphs GT9X (both wrists and waist). Three supervised learning classifiers (K-Nearest Neighbour, Random Forest and eXtreme Gradient Boosted Decision Tree) were used to identify the input signal pattern for each PA type and intensity, with a 10-fold cross-validation utilized to assess the performance of the classifiers. ActiGraph GT9X on the dominant wrist and waist and GENEActiv on the dominant wrist failed to predict vigorous intensity PA activities. All other models, for activity type and intensities, exceeded 97% accuracy, with a sensitivity and specificity of greater than 95%, irrespective of accelerometer brand, placement or health condition.

KW - Threshold

KW - Physical Activity

KW - ENMO

KW - MAD

KW - Youth

U2 - https://doi.org/10.1080/1091367X.2023.2271444

DO - https://doi.org/10.1080/1091367X.2023.2271444

M3 - Article

JO - Measurement in Physical Education and Exercise Science

JF - Measurement in Physical Education and Exercise Science

SN - 1091-367X

ER -