Research on Diabetes Prediction Model Based on Machine Learning Algorithms
Na Hu, Jiali Gao
Abstract
Diabetes is a common chronic disease, and accurate prediction of its occurrence is crucial for early diagnosis and prevention of disease progression. To address the problem of difficulty and time-consuming traditional detection methods such as blood and urine tests for early diagnosis of diabetes, this paper models and predicts the Pima Indian diabetes dataset using machine learning algorithms such as KNN, decision tree, and random forest. The performance of the models was evaluated using cross-validation and confusion matrix, and the optimal diabetes prediction model was selected. The results showed that the random forest model performed the best, with an accuracy of 0.84 and an F1 value of 0.77. Compared with traditional diabetes detection methods, the accuracy of diabetes prediction based on machine learning algorithms has been significantly improved. The research results have certain reference value for early diagnosis and prevention of diabetes.