Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/subratamondal1/heart-attack-prediction

Heart Attack Prediction of patients based on the required data. Data Ingestion - Data Preparation - Exploratory Data Analysis (EDA) - Modelling - Evaluation.
https://github.com/subratamondal1/heart-attack-prediction

data-analysis data-science data-visualization kaggle-dataset machine-learning matplotlib-pyplot numpy pandas python3 scikit-learn seaborn

Last synced: 17 days ago
JSON representation

Heart Attack Prediction of patients based on the required data. Data Ingestion - Data Preparation - Exploratory Data Analysis (EDA) - Modelling - Evaluation.

Awesome Lists containing this project

README 

        
# `Heart Attack Prediction`

[Click here for the Web App](https://subratamondal1-heart-attack-prediction-app-p4oz89.streamlit.app/)

Heart Attack is a type of disease that affects the heart or blood vessels. The risk of certain heart diseases may be increased by smoking, high blood pressure, high cholesterol, unhealthy diet, lack of exercise, and obesity. `The main objective is to create an end-to-end Machine Learning Solution, on which if we give input data the ML Solution will provide us a result of:` **Whether the person has the Risk of Heart Attack or Not and with how much Certainity.** ` Based on that result it can provide useful information to the doctors and help them to diagnose the disease.

> **Note** This readme.md is just the mere representation of the actual project, to get detailed view [Click This](https://github.com/subratamondal1/heart-attack-prediction/blob/main/heart_attack_prediction.ipynb) in Google Colab or Jupyter Notebook or Lab.

## `🎓Tech Stack`

  * Python

  * Streamlit for web app and cloud hosting

  * Pandas

  * Numpy

  * Matplotlib

  * Seaborn

  * Scikit-Learn

  * Jupyter Notebook

  * Kaggle

  

## `Data Science, CRISP-DM Framework`








## 1 `Business Understanding`

An estimated 17.9 million people died from Cardiovascular Diseases, CVDs in 2019, representing 32% of all global deaths. Of these deaths, 85% were due to heart attack and stroke. (According to WHO : World Health Organization). 



Create a predictive model so that critical information can be extracted from the data and provide insightful information to the doctors so, they can diagnose the disease effictively.



## 2 `Data Understanding`

The data we got is from the Kaggle Website [Kaggle](https://www.kaggle.com/datasets/rashikrahmanpritom/heart-attack-analysis-prediction-dataset). 

* This dataset contains 303 Unique Patients & 14 Unique Features out of which one is Target Feature with the value of 0 & 1. 

* below is the Features with description :

* **Age** : Age of the patient

* **Sex** : Sex of the patient

    - Value 0: Fele

    - Value 1: Male

* **cp** : Chest Pain type

    - Value 0: typical angina

    - Value 1: atypical angina

    - Value 2: non-anginal pain

    - Value 3: asymptomatic



* **trtbps** : resting blood pressure (in mm Hg)



* **chol** : cholesterol in mg/dl fetched via BMI sensor



* **fbs** : (fasting blood sugar > 120 mg/dl)

    -  Value 1 = true

    -  Value 0 = false



* **rest_ecg** : resting electrocardiographic results

    - Value 0: normal

    - Value 1: having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV)

    - Value 2: showing probable or definite left ventricular hypertrophy by Estes' criteria



* **thalach** : maximum heart rate achieved



* **exang** : exercise induced angina

    -  Value 1 = yes

    -  Value 0 = no



* **old peak** : ST depression induced by exercise relative to rest



* **slp** : the slope of the peak exercise ST segment

    -  Value 0 = unsloping

    -  Value 1 = flat

    -  Value 2 = downsloping



* **caa** : number of major vessels (0-3) colored by flourosopy.



* **thal** : thalassemia

    -  Value 0 = null

    -  Value 1 = fixed defect

    -  Value 2 = normal

    -  Value 3 = reversable defect



* **output/target** : diagnosis of heart disease (angiographic disease status)

    -  Value 0:  less chance of heart disease

    -  Value 1:  more chance of heart disease

 

## 3 `Data Preparation`

* **Data Cleaning**

* **Data Wrangling**

* **Data Imputing**

* **Exploratory Data Analysis**

* **Uni-Variate Analysis**

* **Bi-Variate Analysis**

* **Feature Scaling with RobustScaler**

  

## 4 `Modelling`

## 5 `Evaluation`

## 6 `Deployment`

  

**...will update the remaining part soon. Download and Open the [Ntebook](https://github.com/subratamondal1/heart-attack-prediction/blob/main/heart_attack_prediction.ipynb) for complete project.**