Indian Institute of Information Technology, Nagpur
Dept. of Computer Science and Engineering
Title:
DISEASE PREDICTION AND MEDICINE
RECOMMENDATION
BT20CSE016 BT20CSE186 BT20CSE094 BT20CSE037
Supervisor:
Keshav Kumar Samrat Mukherjee Aditya Suman Aryan Bhure Dr. Vrinda Yadav
Content
Sr. No. Topic Page
1. Introduction 3
2. Workflow 4
3. Work Done 6
4. Novelty 9
5. References 10
6. Dataset 11
1. Introduction
The Problem
In modern healthcare, the early detection and treatment of diseases play a crucial role in improving patient outcomes and
reducing healthcare costs. However, diagnosing diseases accurately and selecting the most effective medication can be
challenging due to the complexity of medical data and the vast number of available drugs. Therefore, there is a need for an
intelligent system that can predict diseases based on patient symptoms and recommend appropriate medications tailored to
individual patient profiles.
The goal of this project is to develop a Disease Prediction and Medicine Recommendation System that leverages machine
learning techniques to predict diseases based on patient symptoms and recommend suitable medications for treatment. The
system will take patient input in the form of symptoms, and possibly diagnostic test results, and use this information to pre dict
the most likely disease(s) the patient may be suffering from.
The Solution
Our disease prediction system uses Machine Learning algorithms to predict the occurrence of diseases before the symptoms appe ar.
The Goal
Our goal is to help people stay healthy and take necessary precautions to avoid serious illnesses.
Project Overview
Workflow
Frontend
● We have designed our frontend with React thus
making out pages responsive.
● React is a popular JavaScript library for building
user interfaces, particularly single-page applications
where seamless and responsive interactions are
crucial.
● Developed and maintained by Facebook, React
follows a component-based architecture, allowing
developers to break down the user interface into
reusable and modular components.
Backend
● Designed Backend with Fast Api Python
Framework
● Easy Integration with Existing Python
Ecosystem
● Automatic Dependency Resolution
● Actively Maintained and Growing
Community
● Asynchronous Support
Medicine Recommendation
● Objective: The project aimed to recommend suitable medications by analyzing
patient reviews, leveraging data exploration, and employing advanced modeling
techniques.
● Data Exploration: Utilized visualization and statistical methods to understand data
forms.(UCI ML Drug Review dataset )
.
Methodology
● Data Preprocessing: Ensured data relevance by removing irrelevant
conditions.
● Modeling Approach: Implemented a deep learning model with n-gram
representation for sentiment analysis, complemented by Lightgbm to enhance
accuracy and overcome NLP limitations.
● Outcome: The project successfully calculated final predicted values, enabling
tailored medication recommendations based on patient conditions and
sentiments, improving reliability and accuracy.
Data Exploration
Results
Prec Rec F1 Acc.
Logistic 0.85 0.87 0.86 0.84
Regression
Perceptron 0.83 0.85 0.84 0.82
Light GBM 0.86 0.79 0.87 0.86
Tech Stack
Novelty
● Medicine prediction
● Integration of medicine prediction with disease prediction based
on symptoms
Challenges and Solutions
● Medicine Prediction
● Integration of medicine prediction with disease prediction.
● Complexity of Disease-Drug Relationships
● Model Interpretability and Explainability
Future Enhancements
● Integrating the medicine prediction with disease prediction
● SeamLess UI
References
1. Andrea D’Souza International Journal of Research in Engineering and Science (IJRES) ISSN (Online):
2320-9364, ISSN (Print): 2320-9356 www.ijres.org Volume 3 Issue 3 ǁ March. 2015 ǁ PP.74-77.
2. A. Javeed, S. Zhou, L. Yongjian, I. Qasim, A. Noor, and R. Nour, “An Intelligent Learning System
Based on Random Search Algorithm and Opt imized Random Forest Model for Improved Heart Disease
Det ect ion,” IEEE Access, vol. 7, pp. 180235– 180243, 2019, doi: 10.1109/ACCESS.2019.2952107..
3. L. Ali, A. Rahman, A. Khan, M. Zhou, A. Javeed, and J. A. Khan, ―An Automated Diagnostic System
for Heart Disease Prediction Based on χ2 Statistical Model and Optimally Configured Deep Neural
Network,ǁ IEEE Access, vol. 7, pp. 34938–34945, 2019, doi: 10.1109/ACCESS.2019.2904800..
4. P. Saeedi, I. Petersohn, P. Salpea, B. Malanda, S. Karuranga, N. Unwin, S. Colagiuri, L. Guariguata,
A. A. Motala, K. Ogurtsova, J. E. Shaw, D. Bright, and R. Williams, “Global and regional diabetes
prevalence estimates for 2019 and projections for 2030 and 2045: Results from the international
diabetes federation diabetes atlas, 9th edition,” Diabetes Research and Clinical Practice, vol. 157, p.
107843, 2019..
5. Parkinson's Disease Detection Using Machine Learning
6. Classification of Alzheimer's Disease and Parkinson's Disease by Using Machine Learning and Neural
Network Methods
Dataset
1. https://www.kaggle.com/datasets/fedesoriano/heart-failure-prediction
2. https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database
3. https://www.kaggle.com/datasets/gargmanas/parkinsonsdataset
4. https://www.kaggle.com/datasets/johnsmith88/heart-disease-dataset
5. https://www.kaggle.com/datasets/sachinkumar413/alzheimer-mri-dataset
6. https://archive.ics.uci.edu/dataset/462/drug+review+dataset+drugs+com
THANK YOU
