A Machine Learning Model to Predict a Diagnosis of Brain Stroke
IEEE Base Paper Title:
A Machine Learning Model to Predict a Diagnosis of Brain Stroke
(or)
Our Proposed Project Title:
Enhanced Stroke Diagnosis Prediction System Using Random Forest Classifier compared with Bagging Classifier.
IEEE BASE PAPER ABSTRACT:
A stroke is caused by a disturbance in blood flow to a specific location of the brain. This might occur due to an issue with the arteries. The objective of this research to develop the optimal model to predict brain stroke using Machine Learning Algorithms (MLA’s), namely Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Support Vector Machine (SVC), Naive Bayes Classifier (NBC), KNN Classifier (KNN), and XGBoost Classifier (XGB). Apply the above algorithms with hyperparameter along with GridSearchCV (CV= 5) on the given dataset. The given dataset is imbalanced, while training the models, a few difficulties were met, including underfitting, a dataset with null values, and a model without balancing the data to boost performance of the models, need to balance the data by using a data sampling method such as SMOTE. Among the Seven models, XGB is the optimal model based on the accuracy of 96.34%.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
Random Forest Classifier & Bagging Classifier.
OUR PROPOSED PROJECT ABSTRACT:
Stroke is a severe medical condition that demands prompt diagnosis and treatment to prevent long-term disabilities or even fatalities. This project presents the development and evaluation of a robust machine learning model for predicting the diagnosis of strokes using Python. Two classification algorithms, Random Forest Classifier and Bagging Classifier, were implemented and assessed for their performance.
The Random Forest Classifier exhibited remarkable results, achieving a train score accuracy of 100% and a test score accuracy of 99%. On the other hand, the Bagging Classifier demonstrated high accuracy as well, with a train score of 99% and a test score of 98%. These exceptional accuracy scores underline the potential of machine learning in stroke diagnosis prediction.
The dataset used for this project encompasses several patient attributes, including gender, age, hypertension status, heart disease history, marital status, work type, residence type, average glucose level, BMI (body mass index), smoking status, and the presence of a stroke. These attributes collectively provide valuable insights into the patient’s health and lifestyle, making them essential for accurate stroke prediction.
The results of this project suggest that machine learning models, specifically the Random Forest and Bagging Classifiers, can play a pivotal role in aiding medical professionals in diagnosing strokes efficiently. This tool can assist in early intervention and personalized patient care, potentially reducing the long-term consequences of strokes. Furthermore, it highlights the significance of data-driven approaches in healthcare and the potential for machine learning to transform the field of medical diagnosis.
In summary, the project demonstrates the effectiveness of Python-based machine learning models in stroke diagnosis prediction. The combination of high accuracy scores and comprehensive patient attribute information makes this model a valuable tool for healthcare providers in their efforts to improve stroke diagnosis and patient outcomes.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 / 11.
- Coding Language : Python 3.10.9.
- Web Framework : Flask.
- Frontend : HTML, CSS, JavaScript.
REFERENCE:
Sairam Vasa; PremKumar Borugadda; Archana Koyyada, “A Machine Learning Model to Predict a Diagnosis of Brain Stroke”, 2023 International Conference on Inventive Computation Technologies (ICICT), IEEE Conference, 2023.