WiseCare

Overview (What inspired our)

As people age, their healthcare needs become more complex and varied. In many American families, elder individuals are serious financial liabilities because of their sub-optimal healthcare insurance choices. That is the problem we identified (and was personally important to us) and is why we created WiseCare. WiseCare aims to strategically minize cost and to simplify the process of choosing the right insurance plan by leveraging advanced algorithms and comprehensive data analysis. Our system takes into account individual medical histories, past insurance claims, and current health status to recommend the most suitable and cost-effective insurance options for seniors.

Features (How we created it)

Personalized Recommendations: Tailored insurance suggestions based on individual health profiles Historical Data Analysis: Utilizes past medical and insurance records for accurate predictions User-Friendly Interface: Designed with seniors in mind, ensuring ease of use Cost-Benefit Analysis: Compares different plans to find the best value for each user Regular Updates: Stays current with the latest insurance offerings and policy changes

Usage

Download the website UI folder and run the HTML file. Your answers will automatically be recorded locally.

How its Built

Random forest machine learning algorithm for regression to predict total hospital costs for a patient within the next year Researched top Texas health insurance companies to find insurance costs Cost benefit analysis to choose the best healthcare insurance based off total hospital costs for patient Integrated all into a user-friendly website where a patient inputs their information to find the optimal insurance plans

Future Plans

Training model on larger more recent datasets to improve prediction accuracy Extend model to younger populations Improve insurance provider options and include location as a variable when considering optimal health insurance

Challenges Faced

It was hard to find publicly available datasets since patient information is protected by HIPA. As such, we had to spend lots of time searching for datasets and ended up settling on an older dataset with senior citizens. Also, it was hard to find information about all healthcare insurance providers. With more support, we could acquire these datasets and therefore make our project better.

What We Learned

We learned how to create a machine learning model as well as how to utilize HTML/CSS to create a website that allows the user to input their demographics and receive a result. We also learned how to work around problems when they came up and how to adapt our ideas so that we could create an end product even with limited information, data, time, and resources.

Built With

• html/css
• python
• tensorflow