METHOD FOR DETECTING DIABETES IN INDIVIDUALS

Abstract

ABSTRACT A method (100) for detecting diabetes in individuals. Further, the method comprising collecting a dataset that includes relevant health-related features selected from the group consisting of age, body mass index (BMI), blood pressure, and glucose levels from individuals with and without diabetes. Further, the method (100) comprising the steps of pre-processing the dataset to remove missing values, outliers, and errors, and normalizing the data for compatibility with machine learning algorithms. Further, the method (100) comprising the steps of selecting relevant features from the dataset that are informative for diabetes detection to reduce dimensionality and improve model interpretability. Further, the method (100) comprising the steps of training ML algorithms, including Decision Trees (DT), Random Forests (RF), and Gradient Boosting (GB), using the pre-processed dataset. Further, the method (100) comprising the steps of generating predictions regarding

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to the field of diabetes detection and management, and in particular relates to a method for utilizing machine learning algorithms to accurately and efficiently detect diabetes in individuals based on relevant health-related features and risk factors extracted from their medical data.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Diabetes is a chronic metabolic disorder characterized by high blood sugar levels due to inadequate insulin productio , Claims:1. A method (100) for detecting diabetes in individuals, the method (100) comprising the steps of:
collecting a dataset that includes relevant health-related features selected from the group consisting of age, body mass index (BMI), blood pressure, and glucose levels from individuals with and without diabetes;
pre-processing the dataset to remove missing values, outliers, and errors, and normalizing the data for compatibility with machine learning algorithms;
selecting relevant features from the dataset that are informative for diabetes detection to reduce dimensionality and improve model interpretability;
training multiple machine learning algorithms, including Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), and Gradient Boosting (GB), using the pre-processed dataset; and
generating predictions regarding the likelihood of an individual having diabetes based on input health-related features using the best-performing model.

2. The method (100) as claimed in claim 1, wherein the model

Documents