Рақамли технологияларнинг назарий ва амалий масалалари Volume 8 Issue 2 (2025) · pp. 87-94
Development of Diabetes Diagnosis Algorithms Based on Machine Learning Ensembles
Сариев, Ш.Н.
Abstract
In this study, algorithms were developed for applying ensemble models of machine learning algorithms - LightGBM, AdaBoost, and HGB - in the diagnosis of diabetes mellitus. In the study, attributes with high correlation were selected from the dataset, and the models were tested by dividing them into training and test sets. For each model, accuracy, precision, recall, F1-scores, and AUC-ROC indicators were calculated. The results of the experiment revealed that HGB and LightGBM demonstrated higher efficiency among the three models. These models demonstrate a high advantage in the analysis of complex clinical data. This research demonstrates that machine learning algorithms are an effective tool for the early diagnosis of diabetes mellitus. It will serve as an important scientific foundation for the development of automated diagnostic systems in the healthcare sector.
AdaBoostLightGBMHGBдиабетAdaBoostLightGBMHGBdiabetes
Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.