BRAIN STROKE PREDICTION

BY USING CLASSIFICATION
TECHNIQUE
Abstract:

 Stroke is a medical disorder in which the blood arteries in the brain are ruptured, causing
damage to the brain. When the supply of blood and other nutrients to the brain is interrupted,
symptoms might develop. According to the World Health Organization (WHO), stroke is the
greatest cause of death and disability globally. Early recognition of the various warning signs of
a stroke can help to reduce the severity of the stroke. Different machine learning (ML) models
have been developed to predict the likelihood of a stroke occurring in the brain. The dataset used
in the development of the method was the open-access Stroke Prediction dataset. The analysis of
the dataset by supervised machine learning technique (SMLT) to capture several information
like, variable identification, univariate analysis, bi-variate and multi-variate analysis, missing
value treatments and analyze the data validation, data cleaning/preparation, and data
visualization will be done on the entire given dataset. Additionally, to compare and discuss the
performance of various machine learning algorithms from the given hospital dataset with an
evaluation classification report, identify the confusion matrix and to categorizing data from
priority and the result shows that the effectiveness of the proposed machine learning algorithm
technique can be compared with the best accuracy with precision, Recall and F1 Score.
Existing System:

 Stroke has become a leading cause of death and long-term disability in the world with no effective
treatment. Deep learning-based approaches have the potential to outperform existing stroke risk
prediction models, but they rely on large well-labeled data. Due to the strict privacy protection policy
in health-care systems, stroke data is usually distributed among different hospitals in small pieces. In
addition, the positive and negative instances of such data are extremely imbalanced. Transfer learning
can solve small data issue by exploiting the knowledge of a correlated domain, especially when
multiple source of data are available. This work has addressed the issues of SRP with small and
imbalanced stroke data. We have proposed a novel Hybrid Deep Transfer Learning-based Stroke Risk
Prediction (HDTL-SRP) framework which consists of three key components: Generative Instance
Transfer (GIT) for making use of the external stroke data distribution among multiple hospitals while
preserving the privacy, Network Weight Transfer (NWT) for making use of data from highly
correlated diseases (i.e., hypertension or diabetes), Active Instance Transfer (AIT) for balancing the
stroke data with the most informative generated instances. It is found that the proposed HDTL-SRP
framework outperforms the state-of-the-art SRP models in both synthetic and real-world scenarios.
 .
Disadvantages:

 1. Accuracy is low.

 2. They are not using any machine learning algorithms.

 3. They are not implementing the performance metrics.

Proposed System:

 The proposed method is to build a machine learning model for the classification of
brain stroke. The process carries from data collection where past data related to brain
stroke are collected. Data mining is a commonly used technique for processing
enormous data in the healthcare domain. A brain stroke if found before proper
treatment can save lives. Machine learning is now applied and mostly used in health
care where it reduces the manual effort and a better model makes error less which leads
to saving the life. The data analysis is done on the dataset proper variable identification
is done that is both the dependent variables and independent variables are found. The
proper machine learning algorithms are applied to the dataset where the pattern of data
is learned. After applying different algorithms a better algorithm is used for the
prediction of the outcome.
Advantages:

 1. Accuracy will be increased.

 2. Machine Learning Algorithms are compared and the best model is evaluated for
better prediction.

 3. Performance metrics of different algorithms are compared and a better prediction is

done.
LITERATURE REVIEW:

 Title : Brain Stroke Prediction Using Machine Learning Approach

Author: DR. AMOL K. KADAM1 , PRIYANKA AGARWAL2

Year : 2022

A Stroke is an ailment that causes harm by tearing the veins in the mind. Stroke may likewise happen when
there is a stop in the blood stream and different supplements to the mind. As per the WHO, the World Health
Organization, stroke is one of the world's driving reasons for death and incapacity. The majority of the work
has been completed on heart stroke forecast however not many works show the gamble of a cerebrum stroke.
Subsequently, the AI models are worked to foresee the chance of cerebrum stroke. The project is pointed
towards distinguishing the familiarity with being in danger of stroke and its determinant factors amongst
victims. The research has taken numerous factors and utilized ML calculations like Logistic Regression,
Decision Tree Classification, Random Forest Classification, KNN, and SVM for accurate prediction.
LITERATURE REVIEW:

Title : Brain Stroke Prediction using Machine Learning

Author: Mrs. Neha Saxena, Mr. Deep Singh Bhamra, Mr. Arvind Choudhary

Year : 2014

A stroke, also known as a cerebrovascular accident or CVA is when part of the brain loses its blood supply and the part of the body that the
blood-deprived brain cells control stops working. This loss of blood supply can be ischemic because of lack of blood flow, or haemorrhagic
because of bleeding into brain tissue. A stroke is a medical emergency because strokes can lead to death or permanent disability. There are
opportunities to treat ischemic strokes but that treatment needs to be started in the first few hours after the signs of a stroke begin. The
patient, family, or bystanders should activate emergency medical services immediately should a stroke be suspected. A transient ischemic
attack (TIA or mini-stroke) describes an ischemic stroke that is short-lived where the symptoms resolve spontaneously. This situation also
requires emergency assessment to try to minimize the risk of a future stroke. By definition, a stroke would be classified as a TIA if all
symptoms resolved within 24 hours. According to the World Health Organization (WHO) stroke is the 2nd leading cause of death globally,
responsible to approximately 11% of total deaths . For survival prediction, our ML model uses dataset to predict whether a patient is likely to
get stroke based on the input parameters like gender, age, various diseases, and smoking status. Unlike most of the datasets, our dataset
focuses on attributes that would have a major risk factors of a Brain Stroke.
AIM AND OBJECTIVE:
Objectives:

The goal of this study is to develop a novel decision-making tool for predicting
strokes. This study compares the accuracy, precision, and execution time of
convolution neural networks, densenet, and VGG 16 for stroke prediction. The
performance of the CNN classifier is superior than Densent and VGG 16, according to
the findings of the experiments.
AIM:

 Stroke prediction is essential and must be treated promptly to avoid irreversible damage
or death. With the development of technology in the medical sector, it is now possible
to anticipate the onset of a stroke by utilizing ML techniques So this project can easily
find out the Attack.
LIST OF MODULES:

 Data Pre-processing
 Data Analysis of Visualization
 Implementing Algorithm 1
 Implementing Algorithm 2
 Implementing Algorithm 3
 Implementing Algorithm 4
 Implementing Algorithm 5
 Deployment
Environmental Requirements:

 1. Software Requirements:
 Operating System : Windows
 Tool : Anaconda with Jupyter Notebook
 2. Hardware requirements:
 Processor : Pentium IV/III
 Hard disk : minimum 100 GB
 RAM : minimum 4 GB
System Architecture:
Use Case Diagram:
MODULE DESCRIPTION:

Data Pre-processing:
 Validation techniques in machine learning are used to get the error rate of
the Machine Learning (ML) model, which can be considered as close to the
true error rate of the dataset. If the data volume is large enough to be
representative of the population, you may not need the validation
techniques. However, in real-world scenarios, to work with samples of data
that may not be a true representative of the population of given dataset. To
finding the missing value, duplicate value and description of data type
whether it is float variable or integer. The sample of data used to provide an
unbiased evaluation of a model fit on the training dataset while tuning model
hyper parameters.
Data visualization:

 Data visualization is an important skill in applied statistics and machine

learning. Statistics does indeed focus on quantitative descriptions and
estimations of data. Data visualization provides an important suite of tools for
gaining a qualitative understanding. This can be helpful when exploring and
getting to know a dataset and can help with identifying patterns, corrupt
data, outliers, and much more. With a little domain knowledge, data
visualizations can be used to express and demonstrate key relationships in
plots and charts that are more visceral and stakeholders than measures of
association or significance. Data visualization and exploratory data analysis
are whole fields themselves and it will recommend a deeper dive into some
the books mentioned at the end.
OUTPUT SCREENSHOT:
OUTPUT SCREENSHOT
Conclusion:

After the literature survey, we came to know various pros and cons of different
research papers and thus, proposed a system that helps to predict brain strokes in a cost
effective and efficient way by taking few inputs from the user side and predicting accurate
results with the help of trained Machine Learning algorithms. Thus, the Brain Stroke
Prediction system has been implemented using the Machine Learning algorithm given a
Best accuracy . The system is therefore designed providing simple yet efficient User
Interface design with an empathetic approach towards their users and patients. The system
has a potential for future scope which
Future Work:

 The added background knowledge from other datasets can also possibly
improve the accuracy of stroke prediction models as well.
 We intend to collect our institutional dataset for further benchmarking of these
machine learning methods for stroke prediction.
 We also plan to perform external validation of our proposed method, as a part
of our upcoming planned work.