jmarihawkins/Disease_Prediction_App

The Disease Prediction Project uses AI/ML to predict diseases based on selected symptoms, designed for low-resource communities. It delivers fast, accurate predictions using a MLP model, offering tailored, efficient diagnostics for areas with limited healthcare access. # Disease Prediction Project ## Summary The Disease Prediction Project is designed to assist healthcare providers, especially in regions with limited resources, in predicting diseases based on selected symptoms. This project includes two main files: - **disease_prediction.py**: The core app where users input symptoms, and the model predicts possible diseases. - **main.ipynb**: This Jupyter Notebook is responsible for training the machine learning model, performing exploratory data analysis (EDA), and testing different models to find the most effective one for use in the app. Artificial Intelligence (AI) and Machine Learning (ML) are integral to this project. By training an ML model on a dataset of symptoms and diseases, the app can provide quick disease predictions based on user input, allowing healthcare providers to make faster and more informed decisions. ## File Breakdown ### `disease_prediction.py` - **Purpose**: This file is the main driver for the web-based app that allows users to select symptoms and get predictions for potential diseases using a trained machine learning model. - **Role of AI/ML**: The app loads a pre-trained MLP model that processes the symptoms inputted by the user and returns predictions for the most likely diseases. #### Libraries Used: 1. **Streamlit**: - Manages the web interface of the app, allowing users to select symptoms from dropdowns. - Provides a simple, intuitive layout for ease of use by non-technical users. 2. **Pandas**: - Loads and processes symptom data for the model. - Converts input symptoms into a format usable by the prediction model. 3. **TensorFlow/Keras**: - Loads the pre-trained MLP model and uses it to make predictions on the input symptoms. - Provides the framework for deploying the trained model within the app. 4. **Plotly**: - Supports visualizations (if needed) for displaying additional data insights in an interactive manner. 5. **NumPy**: - Assists with efficient handling of arrays and numerical oper …