Prediction of Type- 2 Diabetes using the LGBM Classifier Methods and Techniques
Main Article Content
Abstract
In our day to day life we come across a lot of diseases and one of the most commonly heard Auto-immune disease is Diabetes Mellitus. Diabetes is a non-communicable disease, that has affected the lives of many people due to its effects and medications available as of today. There are a number of medical facilities available in the healthcare industry, however a specific computational technique to predict and detect diabetes is not available. Inorder to overcome the problem, a prediction based model needs to be developed. To develop a model, a dataset containing patient details is required along with the necessary attributes needed for testing the presence of Diabetes on the patient. The process is divided into training, validation and testing. There are many Machine learning algorithms available for the study. Some of them include XGB Classifier, Logistic Regression, Gradient Boosting Classifier, Decision Tree, Extra Trees Classifier and Random Forest and LGBM Classifier Algorithm. Out of all the above algorithms, the LGBM Classifier Algorithm is considered to give the most accurate results. The LGBM is a Light gradient Boosting Algorithm which can be implemented using classifiers. The PIMA Indian Dataset is used in this study for the comparison of the different algorithms mentioned above and an accuracy of 95.20% is obtained using the LGBM Classifier Algorithm. Therefore the LGBM classifiers can be used to develop a data model for detecting and predicting diabetes.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.