Group ID:- 10
Group Member:- 1. Rohan Sul
2. Naman Lalwani
3. Prem Pote
Title:
Health Disease Prediction System Using Python and Tkinter
Abstract:
The Health Disease Prediction System is a desktop-based application designed to
predict the likelihood of certain diseases based on a user’s health parameters and
medical history. The system integrates Machine Learning (ML) algorithms for
accurate disease prediction and a Tkinter-based GUI for an interactive and user-
friendly interface. The application collects user input such as age, gender,
symptoms, lifestyle factors, and key medical parameters (e.g., blood pressure,
glucose level, heart rate, BMI). This data is processed and analyzed using pre-
trained ML models built with libraries such as scikit-learn, pandas, and NumPy.
The system applies classification algorithms (e.g., Logistic Regression, Random
Forest, or Support Vector Machines) to generate predictions for potential health
conditions such as diabetes, heart disease, or other chronic illnesses. The Tkinter
GUI provides an intuitive platform for real-time data entry and instant prediction
results. The application also includes visualization features to present health
metrics and risk levels in a clear, interpretable manner. The goal is to offer a quick,
accessible, and cost-effective tool to assist in early detection and awareness, thereby
enabling timely medical consultation and preventive measures. This project aims to
demonstrate effective integration of data science techniques, machine learning
models, and GUI-based interaction to create a practical healthcare application.
Future enhancements may include real-time sensor integration, cloud-based
storage, and predictive analytics for multiple disease categories.
Introduction:
The Health Disease Prediction System is an intelligent application designed to
assist individuals and healthcare professionals in predicting the likelihood of
potential diseases based on user-provided health parameters. With the increasing
prevalence of lifestyle-related and chronic illnesses, early detection and timely
intervention have become crucial in improving health outcomes. This project
leverages the power of Machine Learning (ML) to analyze patient data, recognize
patterns, and predict possible health conditions. It uses Python for backend logic,
popular ML libraries such as scikit-learn, pandas, and NumPy for model building
and prediction, and Tkinter for creating an interactive and user-friendly graphical
interface. The system allows users to enter relevant health metrics (e.g., age, blood
pressure, glucose level, heart rate, BMI, etc.) into GUI. The data is then processed
and passed through trained ML models, which provide real-time prediction results
along with possible risk factors. This enables users to take preventive measures,
consult doctors early, and monitor their health effectively. By integrating data-
driven analytics with a simple and accessible interface, the Health Disease
Prediction System aims to bridge the gap between medical knowledge and everyday
health awareness. It can be extended to predict multiple diseases such as heart
disease, diabetes, and kidney disorders, making it a versatile and impactful
healthcare solution.
Literature Survey:
Author and
Sr. Title of the
publication Methodology Used Findings/Gap
No paper
Details
1 Disease S. Marpu, R. Implemented Decision Tree, Achieved ~90%
Prediction Shaik, A. Random Forest, and Naïve accuracy on the dataset
Using Peeka, Bayes algorithms on a but lacks scalability for
Machine International symptom-based dataset. multiple datasets and
Learning Journal of GUI built Python Tkinter for does not integrate real-
Novel user interaction; results time patient data.
Research and displayed with predicted
Development disease and model accuracy.
(IJNRD), vol.
9, no. 9, Sept.
2024
2 Symptom- V. Vinod, Collected symptoms from Demonstrated good
Based International users via Tkinter interface, accuracy for selected
Disease Journal of processed data using label symptoms but limited to
Prediction Engineering encoding, and applied a fixed symptom list and
Using Research & multiple ML classifiers. does not support multi-
Machine Technology Compared model accuracies disease prediction.
Learning (IRJMETS), to select the best performer.
2024
3 Multiple V. Patil, Developed Python-based GUI Effective for specific
Disease Project using Tkinter for predicting diseases but lacks
Prediction Report, 2021 heart disease, diabetes, and unified model
System Parkinson’s disease. Utilized architecture and
separate pre-trained ML interoperability with
models for each disease; electronic health
displayed results with records for wider
performance metrics and deployment.
graphs.
Problem Statement:
Many people are unaware of early signs of potential diseases, leading to delayed
diagnosis and treatment. A health disease prediction system using Python, Tkinter,
and machine learning can analyze user health data, predict possible future diseases,
and provide timely alerts. This can help individuals take preventive actions,
reducing risks and improving overall health outcomes.
Objectives:
1. Develop a user-friendly GUI using Python and Tkinter framework.
2. Integrate machine learning models for accurate disease risk prediction.
3. Enable real-time health data monitoring from connected hardware devices.
4. Provide personalized health recommendations based on prediction results.
5. Store and manage patient health data securely for future analysis.
6. Visualize health trends using interactive charts and graphical reports.
7. Support multitasking for simultaneous monitoring and prediction processes
Methodology:
1) Problem Identification: Identify the healthcare problem of predicting
potential disease using patient symptoms and data.
2) Data Collection: Gather relevant health datasets from reliable sources
including patient records, symptoms and diagnostic results.
3) Data Preprocessing: Clean and handle missing values to improve accuracy.
4) Feature Selection: Select significant features for prediction.
5) Model Selection: Choose appropriate machine learning algorithms.
6) Model Training: Train the selected model using processed datasets to
identify patterns and correlations among health parameters.
7) Model Evaluation: Evaluate model accuracy, precision, recall and F1-
score using appropriate metrics and test datasets.
8) GUI Development: Design an interactive Tkinter-based interface.
9) Deployment and Testing: Deploy the application , perform rigorous
testing and fine-tune the system improved disease prediction
accuracy.
Expected Conclusion:
The project successfully predicts potential health risks using Python, Tkinter for the
interface, and machine learning libraries for analysis. It processes user data and
provides accurate, real-time predictions with an easy-to-use design. This system can
help users take preventive health measures, promoting early diagnosis and better
healthcare decisions, thus improving overall well-being and awareness.
References:
[1] Disease Prediction Using Machine Learning Dataset, Kaggle, 2025. [Online]. Available:
[Link]
[2] M. Harikrishnan, V. Vinod, V. Sarala Devi, “Symptom-Based Disease Prediction Using
Machine Learning and Tkinter,” International Research Journal of Modernization in
Engineering, Technology and Science, vol. 06, no. 03, Mar. 2024. [Online]. Available: IRJMETS
paper
[3] S. Marpu, R. Shaik, A. Peeka, “Disease Outcome Prediction Using Multiple ML Models
with Tkinter GUI and Tracking Database,” International Journal of Novel Research and
Development, vol. 9, no. 9, Sept. 2024. [Online]. Available: IJNRD paper
Prof. Aishwarya Pathak Dr. L. B. Chaudhari
Project Guide & Project Coordinator HOD