Predictive Analysis of Dominant Hand Grip Strength Among Young Children Aged 6-15 Years Using Machine Learning Techniques-Decision tree and Regression analysis

Mastour Saeed Alshahrani ¹ Resmi Ann Thomas ² Paul Silvian ^1* Venkata Nagaraj Kakaraparthi ¹ RAVI SHANKAR YERRAGONDA REDDY ¹ Snehil Dixit ¹

• ¹ King Khalid University, Abha, Saudi Arabia
• ² Centennial College, Toronto, Ontario, Canada

Background: To investigate and understand predictor variables and isolate the exact roles of anthropometric and demographic variables in hand grip strength of young children.Material and Methods: 315 male and female children participated in the study and 11 participants were excluded, therefore 304 participants completed the assessments. Anthropometric measurements were collected at the time of study, along with age, height, weight, circumference of the hand, hand span, hand-length, palm-length, hand grip strength (HGS) was measured. Both decision and regression machine learning analysis were used to isolate the relative contribution of independent features in predicting the targeted grip strength of children. Results: Two predictive models were developed to understand the role of predictor variables in dominant hand target features Hand Grip Strength (HGS) for both males and females. For males Decision tree was found to be the best model with lowest error to predict HGS. Respondent age, handspan along with weight was the most significant contributors to male handgrip strength. For males, based on the decision tree analysis, boys under 9.5 years of age, weight (split at 27.5 kg) was found to be the most significant predictor. Whereas, for males under 14.5 years of age, weight (split at 46.7 kg) remained the most important predictor. For males 14.5, years and older, handspan was important in predicting handgrip strength. Backward regression was found to be the best model for predicting female handgrip strength. R2 value for the model was 0.6646 and the significant variables were BMI, hand length, handspan and palm length showing significance at p value <=0.05. This model predicted 66.46% of variance in handgrip strength among females. Conclusion: Anthropometric factors played a significant role in hand grip strength. Age, weight, larger hand span was found to be significant in impacting male HGS, while BMI, along with hand length and palm contributed to higher grip strength, among females.