| Title | Machine Learning Techniques for Early Detection of Diabetes Using Clinical and Lifestyle Data |
| Research Area | Machine Learning |
| Abstract | Diabetes mellitus is one of the fastest-growing chronic diseases worldwide, leading to severe complications such as cardiovascular disorders, kidney failure, and vision loss if not detected early. Traditional diagnostic approaches rely on periodic clinical tests, which often fail to identify the disease at an early stage. Machine learning (ML) techniques provide an effective solution by analyzing large volumes of clinical and lifestyle data to predict diabetes risk before critical symptoms appear. This paper presents a comprehensive study of machine learning models for early diabetes detection, including Support Vector Machines (SVM), Random Forest (RF), Logistic Regression, and Artificial Neural Networks (ANN). Experimental evaluation demonstrates that ML-based predictive models achieve high accuracy and assist healthcare professionals in proactive decision-making. The results show that early prediction using ML can reduce disease progression and improve preventive healthcare outcomes. |
| Keywords | Machine Learning, Diabetes Prediction, Healthcare Analytics, Early Diagnosis, Classification Algorithms |
| Paper Status | Published |
| Volume | 1 |
| Issue | 6 |
| Published On | 16/12/2025 |
| Published File |
IJSRTD_4862.pdf
|