Table of Contents
Korie Westbrook: [email protected]
Mansoor Haidari: [email protected]
Kelvin Luk: [email protected]
This project is a Medical AI tool that is designed to assist healthcare professionals in diagnosing diseases based on symptoms and test results. The tool uses advanced machine learning algorithms to analyze patient data and provide a diagnosis with a high degree of accuracyMedical AI is a critical tool for disease diagnosis because it can help healthcare professionals make more accurate and faster diagnoses. By using machine learning algorithms, medical AI can analyze vast amounts of medical data, including patient histories, test results, and imaging studies, to identify patterns and make predictions about the presence of specific diseases. This helps to improve the speed and accuracy of diagnoses, which can lead to earlier treatment and better health outcomes for patients. Additionally, medical AI can assist healthcare professionals in making complex diagnoses that would otherwise be challenging to identify. Overall, medical AI has the potential to significantly improve patient outcomes and reduce healthcare costs.
- Automated diagnostic tool that provides a fast and accurate diagnosis
- Integration with Microsoft Azure, Python, Kaggle, and APIs to access and analyze patient data
- Supports data formats like JSON and XML
- Robust error handling and recovery mechanisms
- Advanced security features to protect patient data and information
- Python
- TensorFlow
- Tkinter
- PHP for the frame work of the website.
- CSS for styling the GUI and Display.
- Javascripting, Json, and XML to fetch , used data to store and transmit data, and to represent data
- BootStrap framework for developing responsive forms, buttons, navigation, and other interface components.
- API Socket to collection of socket calls that enables to perform the following primary communication functions between application programs:
- Website Prototype Demo Update and Complete Version coming soon.
-
A Tkinter application has been developed to implement a machine learning model for predicting heart disease using TensorFlow and Keras libraries. The model consists of two layers, including a dense layer and a sigmoid layer. The dense layer helps the machine to identify the significant variables for predicting heart disease. The sigmoid layer uses the sigmoid activation function to generate the probability of heart disease, ranging from zero to one.
-
Before feeding the data into the neural network, the application sanitizes it by filling any null or unknown values with the dataset's median and scaling all the data between zero and one. This approach ensures that the data fed to the model is accurate and relevant, and the predictions generated are reliable.
-
The Tkinter application provides an interactive interface for the users to input their data and obtain the probability of having heart disease. The application is user-friendly, making it easy to navigate and operate even for those without prior experience in using machine learning models. The predictions generated by the application can aid in early detection and prevention of heart disease, potentially saving lives
- Microsoft Azure account
- Python 3+
- TensorFlow
- Tkinter
- Kaggle API key
- API documentation (if available)
- Clone the repository to your local machine
- Set up a Microsoft Azure account and obtain an API key
- Obtain a Kaggle API key
- Install required dependencies using pip or conda
- Run the tool using the command line interface or a Python IDE
We welcome contributions to this project! If you are interested in contributing, please fork the repository, make your changes, and submit a pull request.
This project is licensed under the University of the Pacific School of Engineering and Computer Science.
For any questions or feedback, please email us at [ -Korie Westbrook: [email protected] -Mansoor Haidari: [email protected] -Kelvin Luk: [email protected] -------------------------------------------- Contact of our Overseeing Project Advisor -Prof. Canniff: [email protected] ].
- Every Thursday Starts: 6:00 PM (Meeting will via discord)
- Every Sunday Starts: 1:00 PM (zoom Link: https://pacific.zoom.us/j/93113615764)
University of the Pacific Stockton, CA Studenst