EFFECTIVE APPLICATION OF MACHINE LEARNING ALGORITHMS FOR THE EARLY DIAGNOSIS OF LEARNING DISABILITIES IN PRESCHOOL CHILDREN

Abstract

Introduction. Learning disabilities are a common developmental disorder that affects a significant number of preschool children. Early diagnosis and intervention are critical to improving the academic performance and quality of life of children with learning disabilities. However, modern diagnostic methods can be subjective, time-consuming, and costly. Machine learning algorithms can remove these limitations and provide a more accurate and efficient method for early diagnosis of learning disabilities in preschool children. Method and methodology of the work. The research is based on methods of analysis, synthesis and generalization, and pedagogical experiment. Application of numerical methods for model training. The preschool children data set consisted of children with and without learning disabilities. The data sets were used in four machine-learning algorithms. The following metrics Accuracy, Precision, Recall, and F1 score were used to evaluate the effectiveness of each algorithm. Results. These results show that machine learning algorithms can be a powerful tool for early diagnosis of learning disabilities in preschool children. The logistic regression algorithm showed the highest results. Conclusion. In conclusion, the use of machine learning algorithms for early diagnosis of learning disabilities in preschool children has high potential benefits, including early achievement, increased accuracy, cost-effectiveness, time savings, objective analysis, and accessibility to diagnosis. The authors plan to conduct additional studies to test their safety and use these algorithms.

Keywords

• pedagogy
• psychology
• learning disabilities
• early diagnosis
• preschoolers
• upbringing
• machine learning
• logistic regression
• smv
• decision trees