https://github.com/param302/heart-disease-predictor

https://github.com/param302/heart-disease-predictor

gui machine-learning neural-network neural-networks python tkinter tkinter-gui

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/param302/heart-disease-predictor
• Owner: Param302
• Created: 2022-07-31T10:54:16.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2022-12-22T17:31:33.000Z (about 2 years ago)
• Last Synced: 2023-03-10T10:36:44.676Z (almost 2 years ago)
• Topics: gui, machine-learning, neural-network, neural-networks, python, tkinter, tkinter-gui
• Language: Jupyter Notebook
• Homepage:
• Size: 1.67 MB
• Stars: 10
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
# Heart Disease Predictor

A Heart Disease predictor GUI made in Python using **Neural Network** ML model to predict the probability of Heart Disease.

## Project details

### Working

It takes $8$ parameters and do prediction based on them

- Age

- Sex (M / F)

- Chest Pain (4 types)

- Chest Pain during exercise (yes / no)

- trestbps - Resting blood pressure

- Maximum Heart Rate

- Blood sugar above 120mg/dl (yes / no)

- Cholesterol

![preview](./preview_2.0.jpg)

### Model details

Model made using Neural Networks with accuracy of $98.26\%$ consists of total 3 layers

- $1^{st}$ hidden layer $18$ neurons (relu)

- $2^{nd}$ hidden layer $9$ neurons (relu)

- $3^{rd}$ output layer $1$ neuron (linear)

Used `BinaryCrossentropy()` loss function with `from_logits=True`, and convert predictions into sigmoid using `tf.nn.sigmoid(preds)` and `Adam` optimizer

### Clone

```

git clone https://github.com/Param302/Heart-Disease-predictor.git

```

### Software used

Python 3.10.2

### Setup before run

- Make sure to install all required libraries and module before using it:

```

pip install -r requirements.txt

```

- Run `main.py` file:

```

python main.py

```