Photo by National Cancer Institute on Unsplash
- According to a recent study carried out by BMJ quality and safety, 12 million adults who seek medical care are misdiagnosed each year in the United States.
- The accumulation of large case loads and incomplete medical histories lead to rise in human-errors.
- An Artificial Intelligent system can predict and diagnose a disease at a faster and more efficient way as compared to medical professionals.
- In the following project we will be predicting diseases from symptoms using machine learning algorithms like decision tree and random forests.
- Moreover, we will try to plot the diseases and symptoms and create a network graph to analyse the common symptoms between diseases, most common symtoms, most common diseases etc.
Source: Disease-Symptom Knowledge Database
- The data set consists of 148 diseases with their corresponding symptoms.
- The data set also included the count of disease occurences.
-
Model Accuracy - 90.54%
-
Decision Tree
Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/amazing-feature) - Commit your Changes (
git commit -m 'feat: some amazing feature') - Push to the Branch (
git push origin feature/amazing-feature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
Maharsh Suryawala - Portfolio
Project Link: https://github.com/MaharshSuryawala/Predict-Disease-From-Symptoms
