J D COLLEGE OF ENGINEERING & MANAGEMENT

An Autonomous College, Affiliated to DBATU, Lonere

At: Khandala, Post- Valni, Kalmeshwar Road, Near Fetri, Nagpur

DRUG Disease Prediction using

Machine Learning
Guide:
Prof:- Pankaj Wankhede

Name of Projectees
Lavanya Godbole
Sagar Rahate
 Contents

Abstract
Introduction
Objectives
Problem Statement
Literature Survey
Block Diagram
Expected Result
Work plan
References
 Abstract

The integration of machine learning techniques into the field of healthcare has
opened up new avenues for early disease diagnosis and drug discovery. This
thesis explores the application of machine learning algorithms in predicting
disease outcomes and identifying potential drug candidates. The primary
objective is to leverage data-driven approaches to enhance the accuracy and
efficiency of disease prognosis and drug discovery processes.

People today deal with a variety of diseases as a due to their lifestyle choices
and the surroundings Disease prediction is an essential component of
treatment. So, it becomes crucial to make disease predictions early on. The
hardest task is making an accurate diagnosis of a disease. So, Machine learning
is crucial in predicting the disease in order to solve this issue. The system
proposed in this project uses the patient's symptoms as input to predict the
disease and then recommends the right medication. This system takes the
symptoms of the user from which he or she suffers as an Input. We use
Classification Algorithms for disease prediction and drug recommendation, such
as Naive Bayes (NB) and Random Forest, with a variety of accuracy levels. Once
thedisease has been predicted by the system, then it is followed by
recommending the appropriate medicine.
 Introduction

It is estimated that more than 70% of people in India are inclined to
general body maladies like viral, flu, cough, cold etc., in every 2
months. Since numerous individuals don't understand that the
general body illnesses could be side effects to something
increasingly hurtful, 25% of the populace surrenders to death
because of ignoring the early general body symptoms. This could be
a risky circumstance for the population and can be alarming.
Hence recognizing or predicting the disease at the earliest is
essential to maintain strategic distance from any undesirable losses.
The intent is to deduce a satisfactory Machine Learning algorithm
which is efficient and accurate for the prediction of disease. In this
project, the supervised Machine Learning concept is used for
predicting the diseases. The main feature will be Machine Learning
in which we will be using algorithms such as Decision Tree, Random
Forest, Naïve Bayes which will help in early prediction of diseases
accurately and better patient care.
 Objectives

 There is a require to ground work and evolve a system that will

enable end users to predict diseases without having to visit a
physician or doctor for diagnosis. To identify the patient sickness
by analyzing symptoms and suggest the drug by using various
machine learning algorithms. Machine learning can improve the
accuracy of prediction
A framework for multiple disease predication system based on the symptoms
using Decision Tree, Random Forest, Naïve bayes supervised machine learning
algorithms
to study and make a system which will make it easy for an end users to predict
the chronic diseases without visiting physician or doctor for diagnosis. To detect
the Various Diseases through the examining Symptoms of patient's using
different techniques of Machine Learning Models.
 Problem Statement

Most people in our digital age are prone to ailments as a result

of a lack of good food, adequate sleep, and daily exercise. It is
critical to know if we are afflicted with sickness at an early stage
rather than discovering it later. As a result, illness prediction
systems play a significant role since they predict diseases based
on symptoms. This disease prediction system employs the
Machine Learning algorithms. This approach also recommends
drug that are widely used to treat the illness.
 Literature Survey
Paper Title Author Finding
A Review of Approaches Ke Han , Peigang Cao The occurrence of DDI
for Predicting Drug–Drug (2023) affects the treatment of
Interactions Based on patients and has become
Machine Learning a serious problem for
patient safety and drug
management. The harm
caused by DDI will be
greatly reduced if
machine learning can be
used to efficiently predict
DDI. To this end, it is
urgent to develop better-
performing machine
learning approaches. This
article describes existing
machine learning- based
approaches for predicting
DDI. In the past 10 years,
machine learning has
been widely applied in
bioinformatics
 Literature Survey
Paper Title Author Finding
Machine Learning and Omar Enzo Santangelo , Vito Taim of the study is to show
Prediction of Infectious Gentile (2023) whether it is possible to
Diseases: A Systematic predict infectious disease
Review out- breaks early, by using
machine learning. This study
was carried out following the
guidelines of the Cochrane
Collaboration and the meta-
analysis of observational
studies in epidemiology and
the preferred reporting items
for systematic reviews and
meta-analyses. The suitable
bibliography At the end of
the search, this systematic
review contained 75 records.
The studies analyzed in this
systematic review
demonstrate that it is
possible to predict the
incidence and trends of some
 Literature Survey
Paper Title Author Finding
A Machine Learning Mohapatra, Mahima; r, drug
based Drug Nayak, Mamata; and recommendation
Recommendation Mahapatra, Saswati systems are developed
System for Health Care (2022) to help endusers in
distinctive correct
medications for a
particular wellness
based on the reviews
of other end-users
provided on totally
different medications
for various specific
diseases. The goal of
this recommendation
system
is to examine the
dataset using data
mining concepts,
visualization,
sentiment analysis and
recommend drugs
Flowchart
 Flowchart Details
 Loading the Dataset:
We first load the given dataset
After that we import the required library packages. Data Pre-
processing
We do reshape and data augmentations. Defining the Model
We define the model as sequential or Functional.
Now we decide the number of layers to be used, Number of nodes to
be used in the model and also the evaluation metrics. Compiling the
Model
It defines the loss function, optimizer, and weights. Model Fit
Training Data, Testing Data.
 Mertis
 Increased accuracy for effective heart disease diagnosis.
Handles roughest (enormous) amount of data using random forest
algorithm andfeature selection.
 Reduce the time complexity of doctors.
Cost effective for patients.
Demerit.
 SYSTEM SPECIFICATIONS
.
HARDWARE REQUIREMENTS:
 System : Pentium IV 2.4 GHz.
 Hard Disk : 40 GB.
 Floppy Drive : 1.44 Mb.
 Monitor : 14‟ Colour Monitor.
 Mouse : Optical Mouse.
 Ram : 512 Mb
SOFTWARE REQUIREMENTS:
 Operating system : Windows 7 Ultimate.
 Coding Language : Python.
 Front-End : Python.
 Designing : Tkinter
 Conclusion
.
We have created a fully hybrid application that makes use of
machine learning algorithms in order to predict various diseases
based on the symptoms provided by the user. Based on the
suggested disease we will suggest prescriptions. Finally with help of
confusion matrix we will also be able to suggest which algorithm
gives us the most accurate predictions
 Future Scope
.
The future scope of drug-disease prediction using machine learning is expansive and
promising, as technology continues to advance and healthcare demands innovative
solutions. Here are several future directions and areas of growth in this field:

Personalized Medicine: As machine learning models become more sophisticated, they

can be tailored to individual patient profiles. This allows for personalized treatment
recommendations based on a person's genetic makeup, lifestyle, and medical history,
improving treatment efficacy and minimizing side effects.

Multi-Modal Data Integration: Combining diverse data sources such as genomics,

proteomics, clinical records, and imaging data can provide a more comprehensive
view of a patient's health. Future research will focus on developing methods to
effectively integrate and analyze these multi-modal datasets for better disease
prediction.

Drug Repurposing: Machine learning can identify existing drugs that may be
repurposed for treating different diseases. This approach can significantly accelerate
drug discovery and reduce costs.
 References

Han K, Cao P, Wang Y, Xie F, Ma J, Yu M, Wang J, Xu Y, Zhang Y and Wan J (2022) A

Review of Approaches for Predicting Drug–Drug Interactions Based on Machine
Learning. Front. Pharmacol. 12:814858. doi: 10.3389/fphar.2021.814858
 Santangelo, O.E.; Gentile, V.; Pizzo, S.; Giordano, D.; Cedrone, F. Machine Learning
and Prediction of Infectious Diseases: A Systematic Review. Mach. Learn. Knowl.
Extr.2023, 5, 175–198. https://doi.org/ 10.3390/make5010013
 Mohapatra, Mahima; Nayak, Mamata; and Mahapatra, Saswati (2022) "A Machine
Learning based Drug Recommendation System for Health Care," Graduate Research
in Engineering and Technology (GRET): Vol. 1: Iss. 6, Article 2. DOI:
10.47893/GRET.2022.1109
Available at: https://www.interscience.in/gret/vol1/iss6/2
[Shirsath, Shraddha. Subhash., & Patil, Prof. Shubhangi. (2018).Disease Prediction
Using Machine Learning over Big Data .International Journal Of Innovative Research
in Science and Technology , 7(6), 6752-6757
 Khurana, Sarthak., Jain, Atishay., Kataria, Shikhar., Bhasin, Kunal., Arora, Sunny., &
Gupta, Dr. Akhilesh. Das. (2019). Disease Prediction System. International Research
Journal of Engineering and Technology, 6(5), 5178
Thank
you !