Sign in Subscribe
Data mining

Artificial Intelligence in Predicting Musculoskeletal Disorders in Elementary School Students

Strategic Insights

— 1 min read

Researchers at Hamadan University of Medical Sciences conducted a study to evaluate the effectiveness of Synthetic Minority Over-sampling Technique (SMOTE)-based machine learning algorithms in predicting musculoskeletal disorders (MSDs) in elementary school students. The study aimed to improve the accuracy of MSD prediction in children using SMOTE-based techniques, which address class imbalance in unbalanced datasets. The research involved 438 primary school students (grades 1 to 6) in Hamedan, Iran, and used six machine learning algorithms, including Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM).

Key Takeaways:

  • The study found that SMOTE-based techniques significantly improved the accuracy of MSD prediction in elementary school students, with sensitivity increasing from 18% to 85% for Decision Tree (DT) and from 65 to 99% for RF and XGBoost.
  • The Borderline-SMOTE technique achieved the highest accuracy for XGBoost and RF, with 96% and 93.65%, respectively.
  • Key predictors of MSD included regional facilities, body mass index (BMI), and gender, highlighting the significance of environmental and physiological factors in the development of this disorder.
  • The study demonstrated the effectiveness of SMOTE in addressing class imbalance and improving the accuracy of MSD prediction among students.
  • Random Forest (RF) and XGBoost outperformed other algorithms in the study.

Statistics:

  • 28 (6.39%) of the 438 students had musculoskeletal disorders (MSD).
  • The study analyzed data from 12 public and private schools in Hamedan, Iran.
  • SMOTE-NC achieved the highest accuracy for XGBoost (93.65%) and RF (93.41%).
  • Borderline-SMOTE yielded the highest accuracy (96%) for XGBoost and RF.
  • RF and XGBoost performed best overall, with an Area Under the Curve (AUC) of 99% and 99%, respectively.
  • Regional facilities, BMI, and gender were identified as key factors influencing MSD.

Sources:

  • Evaluating the performance of different machine learning algorithms based on SMOTE in predicting musculoskeletal disorders in elementary school students. BMC Medical Research Methodology, 2025,25(1):1-11. (BMC Medical Research Methodology - http://bmcmedresmethodol.biomedcentral.com)
  • NewsRx. Hamadan University of Medical Sciences Researchers Detail Findings in Machine Learning (Evaluating the performance of different machine learning algorithms based on SMOTE in predicting musculoskeletal disorders in elementary school students). Journal of Engineering. October 20, 2025; p 1087.

Read more