Diabetic Prediction using Flask with Login History Patient in Python Projects

Diabetic Prediction using Flask with Login History Patient in Python Projects
Abstract
Diabetes is a chronic disease that requires early detection and continuous monitoring to prevent life-threatening complications. The project “Diabetic Prediction using Flask with Login History Patient in Python” focuses on developing a web-based system that predicts whether a patient is at risk of diabetes using machine learning algorithms. The system takes patient health data such as glucose level, BMI, insulin, blood pressure, and age as input and generates predictions. A Flask web application is developed as the front-end, providing secure user login, registration, and personalized dashboards. Additionally, the system maintains a login and prediction history for each patient, allowing individuals and healthcare providers to track progress and monitor trends over time. Python libraries such as Scikit-learn, Pandas, NumPy, and Matplotlib are used for machine learning, while Flask and SQLite/MySQL handle deployment and data storage.

Existing System
Traditional diabetes prediction is largely dependent on laboratory tests and medical consultations, which are often time-consuming and not readily available in all regions. Existing computational models use simple machine learning classifiers, but many lack scalability, data security, or patient management features. Most existing web-based solutions do not integrate personalized login systems or prediction history tracking, which are crucial for real-time monitoring and medical record maintenance. Patients typically have to undergo repeated tests without access to centralized digital history, leading to inefficiency in long-term monitoring.

Proposed System

The proposed system provides a Flask-powered web application that integrates diabetes prediction with patient management features. Users can register, log in securely, and access personalized dashboards. A machine learning model (trained using algorithms such as Logistic Regression, Random Forest, or SVM) processes patient medical attributes and outputs a prediction of diabetic or non-diabetic status along with confidence levels. Each prediction result is stored in the patient’s history, enabling them and healthcare professionals to review past records and monitor health progression. The login history also supports audit trails and accountability for medical usage. The Flask framework ensures a lightweight yet scalable deployment, while the database maintains patient details, prediction logs, and security through authentication mechanisms. This system thus combines healthcare prediction with digital record management, making it practical for real-world clinical and personal use.

Customer Reviews (0)

Share Your Experience

Rating

Your Comment

Submit Review Cancel

No reviews yet. Be the first!