Abstract: Diabetes is a long-term health condition that affects many people worldwide. It results in high levels of sugar in the blood, leading to symptoms like frequent urination, increased thirst, and hunger. If not managed properly, diabetes can cause serious complications like blindness, kidney failure, amputations, heart problems, and stroke.
Our body normally uses a hormone called insulin to regulate blood sugar levels. However, in diabetes, this system malfunctions. There are mainly two types of diabetes: type 1 and type 2. Type 1 diabetes occurs when the body does not produce enough insulin, while type 2 diabetes happens when the body does not use insulin effectively. Additionally, there is gestational diabetes, which develops during pregnancy. To tackle the growing concern of diabetes, researchers are exploring ways to use machine learning, to predict diabetes at an early stage with high accuracy. Machine learning helps machines learn from past data and experiences, and it can be useful in analyzing complex patterns in large datasets.
The goal of this project is to create a system that can predict diabetes in patients with better accuracy by combining the results of various machine-learning techniques. These techniques include K nearest neighbor, Logistic Regression, Random Forest, Support Vector Machine, and Decision Tree algorithms. Each algorithm is applied to the data, and its accuracy in predicting diabetes is calculated. The algorithm that shows good accuracy in its predictions will be chosen as the model for predicting diabetes in patients.
By using machine learning to predict diabetes early on, doctors and healthcare professionals can intervene timely and provide appropriate treatment to manage the condition effectively. This can help prevent or reduce the severity of complications associated with diabetes, thus improving the overall health and quality of life for affected individuals.
In summary, the project aims to utilize machine learning to develop an accurate and reliable system for early diabetes prediction, ultimately contributing to better healthcare outcomes for individuals at risk of diabetes.
Keywords: Diabetes, Blood sugar, Insulin, Type 1 diabetes, Type 2 diabetes, Gestational diabetes, Machine learning, Predictive modeling, K nearest neighbor, Logistic Regression, Random Forest, Support Vector Machine, Decision Tree, Early prediction, Healthcare intervention, Complications, Quality of life, Healthcare outcomes, Timely treatment, Patient risk assessment.
|
DOI:
10.17148/IJARCCE.2023.12725
