Overview / Usage

Healthcare is a niche area of concern. With the increased demand for treatments over alarming disease rates, affordability comes at stake. Often healthcare organizations mislead people for the sake of money. Unfortunately, in most scenarios, underserved communities become targets of such traps of organ trade and other criminal offences or spend their entire savings after travelling from one organization to another. Negligence towards health and no proper mechanism to monitor makes things worse. Financial aspects and lack of knowledge in due fields lead to losing lives at many early stages.

Methodology / Approach

Our application aims to leverage the power of Intel OneAPI AI Analytics Toolkit and Libraries to develop an intelligent medical diagnosis system that enhances the capabilities of healthcare professionals to deal with complex medical problems and stay up to date with the latest technology and help patients with the tools they need to extract valuable insights and real-time patient monitoring.

Technologies Used

We’ve implemented a client-server architecture via a Python web app using the flask app and react UI. Once a user uploads relevant text/image data. After data cleaning and pre-processing, it is then sent to the backend server through RESTAPIs where our deployed ML models trained on Intel OneAPI reside. We seamlessly get result predictions and then sent them back over to the user screen. Parallelly we also perform live training over the data received to keep our models updated with unforeseen data and benchmarking with domain experts before adding relevant data back to the database.

Other links

• Medium Link
• Tabular Data Model Training using oneAPI
• Hitaya OneAPI: Chronic Kidney Disease Machine Learning Model Training Using Intel oneAPI
• Hitaya OneAPI: Skin Cancer Detection using Intel® Optimization for Tensorflow