A comparative review of machine learning methods for big data analysis

Modern medicine is actively implementing machine learning methods to analyze medical data and improve diagnostic accuracy. The use of such methods in the classification of diabetes makes it possible to automate the process of detecting the disease, improving results and reducing the likelihood of missing cases. This article provides a comparative analysis of five popular machine learning algorithms: linear regression, logistic regression, decision tree, random forest and gradient boosting. The study showed that gradient boosting demonstrates the best balance between accuracy and completeness, minimizing the number of classification errors. The use of machine learning in medical diagnostics helps to detect diabetes early and improve the quality of treatment, allowing medical professionals to make more informed decisions.