Beacon+

Inspiration

Beacon Plus aims to make the United States a country with a 100% insurance rate. While this may seem ambitious, solving such bold challenges leads to revolutionary outcomes.

What it does

Our solution addresses the needs of both doctors and patients:

For doctors, we streamline their workflow by reducing time spent on repetitive questions, while providing a primary report on the patient's condition for quicker and more informed decision-making.

For patients, we are making it fast by utilizing a large language model to analyze their medical reports. This model provides summaries and suggestions on suitable insurance options and areas for improvement to the doctor which helps him to make quick and efficient decisions.

Our solution is both cost-effective and time-efficient, empowering individuals to secure affordable and appropriate health insurance.

How we built it

We have built a Machine Learning model using unsupervised learning to group the insurance companies based on their features and assign the company to the patient who suits better to take that insurance.

Challenges we ran into

It took us a lot of time to come up with the effective and realistic solution, after the solution we couldn't find the proper model to exactly fit the purpose then we have created out own mathematics model and fulfilled the requirements

Our mentors have explicitly explained that manually replicated patient data from surveys into Qualtrics and EMRs.
Medical students have no way to contact patients for follow-ups on whether they have applied for health insurance.
Our doctor at the clinic's workload is too much, increasing downtime and 1-on-1 consultations with patients who need insurance.

Solutions for LFMC

We created an autofill system that would replicated patient profile data from surveys into Qualtrics and their EMRs.
We have designed a system that would recommend health insurance companies to the doctor based on patient data.
We have provided medical students with a follow-up system that allows them to help reach out to patients who haven't applied for health insurance.

What we learned

The most important thing we have learnt is the time management, how to effectively divide time to build a working model in small period of time, how 1 and half day can be divided into 36 hours and 2160 minutes. We have learnt different ways of research, a lot of useful insurance websites, with all this knowledge we have become a beginner level in insurance suggestions.