Scribd
Upload
25 views14 pages

Project PPT Batch (5) )

The document outlines a project by the Department of Computer Science and Engineering at Avanthi Institute of Engineering and Technology, focusing on the design and development of a Disease Prediction System using machine learning. The system aims to enhance early disease detection by analyzing patient symptoms and historical data, reducing reliance on traditional, time-consuming diagnostic methods. It incorporates various machine learning models to improve accuracy and provides a user-friendly interface for symptom input and personalized health recommendations.

Uploaded by

jayasrimucheti
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
25 views14 pages

Project PPT Batch (5) )

The document outlines a project by the Department of Computer Science and Engineering at Avanthi Institute of Engineering and Technology, focusing on the design and development of a Disease Prediction System using machine learning. The system aims to enhance early disease detection by analyzing patient symptoms and historical data, reducing reliance on traditional, time-consuming diagnostic methods. It incorporates various machine learning models to improve accuracy and provides a user-friendly interface for symptom input and personalized health recommendations.

Uploaded by

jayasrimucheti
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

AVANTHI INSTITUTE OF ENGINEERINGAND TECHNOLOGY

(AUTONOMOUS)
Accredited by NAAC with “A+” Grade
Cherukupally (Village), Near Tagarapuvalasa Bridge, Vizianagaram (Dist), AP, 531162

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

Batch -05

PROJECT

TITLE

Design & Development of Disease


Prediction System using Data Analytics
Team Members:
Under the Guidance - Manda Vinutna (21Q71A0593)
of: - Lalam Chandu (22Q75A0507)
Mr. P. - Kalluru Bhagya Sri (21Q71A0573)
Satyanarayana - Padithini Viswa Teja
M .Tech (PhD)
(21Q71A05B9)
Associate Professor
INTRODUCTION
• The early detection of diseases is one of the most
crucial aspects of modern healthcare. Millions of
people suffer from delayed diagnosis, leading to
severe health complications and increased treatment
costs. Traditional diagnosis methods rely on physical
examinations, lab tests, and doctors' expertise, which
can be time-consuming, costly.
• Healthcare industry faces challenges in early
disease diagnosis.

Our system predicts diseases based on


symptoms .
ABSTRACT
 The Disease Prediction System utilizes machine learning to analyze
patient symptoms and historical data.

 Traditional diagnosis methods rely heavily on doctor consultations, lab tests, and
patient history, which can be time-consuming and sometimes prone to human errors.

 It helps in early disease detection, reducing misdiagnosis cases, and


improving patient outcomes.

 Various ML models, including Decision Trees, Naive Bayes, and Random


Forest,
and KNN are implemented to ensure high accuracy and reliability.
EXISTING SYSTEM
 Manual diagnosis can be slow and error-prone.

 Shortage of medical professionals in remote


areas.

 Late detection of diseases can lead


to complications.
Disadvantages:
 Prone to human error.
 Limited scalability.
 Lack of predictive insights –
Traditional methods do not leverage
data-driven predictions.
PROPOSED SYSTEM
 Uses machine learning to predict diseases based
on symptoms.
 Early detection helps in timely medical
intervention.
 Reduces workload on healthcare professionals.
 Can be accessed remotely for preliminary
diagnosis.
 Included data storage method (SQLite database) for
tracking patient history.

Advantages:
 Faster Diagnosis: Reduces dependency on manual
checks.
 Improved Accuracy: Uses trained ML models for
WORKING PRINCIPLE
 Symptom Input: Users select symptoms through dropdown menus on the interface.
 Data Preprocessing: The system converts selected symptoms into a structured
format suitable for machine learning models.
 Model Inference: Multiple ML models (Decision Tree, KNN, Random Forest, Naïve
Bayes) process the input to predict diseases.
 Prediction Output: The system displays the most probable disease along with
its confidence score.
 Storage: Predictions are stored in an SQLite database for future reference.
 History Feature: Users can view their past predictions via a history module.
System Architecture
1. User Interface (Streamlit)
Users select symptoms from dropdown menus.

2. Preprocessing :The selected symptoms are converted


into a format suitable for machine learning models.

3.Machine Learning Models :The system uses


algorithms like Decision Tree, Random Forest, K-Nearest
Neighbors (KNN), and Naive Bayes to process the input.

4. Prediction & Confidence Score


The system predicts the most likely disease and provides
a confidence percentage for each result.

5. Recommendation
Based on the prediction, the system provides
personalized guidance on diet, workout, medications,
and necessary precautions.

6. Storage (SQLite)
User prediction history is stored for future reference.
METHODOLOGY & IMPLEMENTATION
Methodology:
1. Data Collection
2. Preprocessing
3. Model Training & Evaluation
4. Deployment

Implementation Tools:
 Programming: Python (Pandas, Scikit-learn)
 Deployment: Streamlit
 ML Models: Decision Trees, Random
forest, Naive Bayes, KNN.
EXPECTED RESULTS
 Automated disease prediction based on user-entered symptoms.
 Reduced workload for doctors.
 Improved early detection rates.
 Easy access to preliminary diagnoses in remote areas.

Sample Prediction Result


Model Predicted Disease Confidence (%)
Decision Tree Pneumonia 85.6%
Random Forest Pneumonia 90.2%
Naïve Bayes Bronchitis 75.4%
KNN Pneumonia 78.9%
OUTPUT
RESULTS
RESULTS IN DATABASE
CONCLUSION
 The Disease Prediction System effectively leverages data analytics and
machine learning to provide accurate disease predictions.

 It offers a user-friendly interface for symptom input and delivers reliable


results based on trained models.

 The system supports healthcare decision-making by offering relevant


recommendations, including diet, medications, workouts, and
precautions.

 Overall, it contributes to improved health awareness and early detection, aiding


both users and medical professionals.
THANK
YOU

You might also like