Flatten the curve. From Instagram to news articles to talk radio, everyone is talking about what we can do to help flatten the curve of coronavirus infections and slow down the spread. It's why we are all self-isolating at home, far away from work and school and other people. But what if we could flatten the curve while also raising the line? There are two main parts to the stereotypical "flatten the curve" diagram. The curve itself describes the rate of infection and the flattening of the curve describes spreading out the cases over time. The second part, however, is the line representing the maximum health care system capacity. This line does not have to be a constant, we can raise this line by more effectively using our ventilators and hospital beds, bringing in more doctors, and also by distributing coronavirus and non-coronavirus patients evenly among hospitals. This last point birthed HospiFind, which will help everyone both flatten the curve and raise the line.

What it does

When a patient needs medical attention, they usually go to the nearest hospital to get care. However, during the COVID-19 pandemic, many more patients than usual need care, and simply going to the nearest hospital may lead to certain hospitals overloading with patients. Hospifind solves this problem by directing patients to nearby hospitals that are best equipped to treat them. A patient can quickly enter their address, age, available modes of transportation, potential coronavirus symptoms, and previous medical conditions, and the application will display a map of nearby hospitals ranked by their ability to treat that specific patient. Hospitals are evaluated by factors including available hospital beds, ICU beds, ventilators, and coronavirus tests. The application collects this data through a hospital interface, through which hospitals can enter information about their capacity and resources. By alleviating stress on the healthcare system and ensuring patients get the care they need, Hospifind has the power to save lives of patients and healthcare workers across the country.

How we built it

We built Hospifind using Google Maps APIs, AWS, and online hospital data. We used Google Maps APIs to obtain a list of the 10 nearest hospitals to a patient whenever he/she fills out the form on the website. We then sent this list to an AWS Lambda function, which queries additional hospital data from a DynamoDB database and passes the patient's information into a decision model, which assigns each hospital a rating based on its capacity and the patient's symptoms. We obtained some hospital data online using web-scraping techniques and used mathematical models and simulations to estimate the rest.

Challenges we ran into

We found finding useful hospital data online difficult, especially retrieving it from websites using web-scrapers. Creating the hospital evaluation system was also was difficult due to a lack of widely available day-to-day hospital operational data. We had to use several mathematical models and simulations to use the limited data available to make reliable recommendations for patients.

Accomplishments that we're proud of, what we learned, and what's next for Hospifind

We are proud of the fact that our decision model produces accurate results based on simulated data. We learned ways to get around a lack of data and how to apply our knowledge of mathematical modeling to real-world scenarios. However, if Hospifind is to be implemented on a large scale, we will eventually have to start using concrete, hospital-reported data. Our next steps for Hospifind are moving it to a mobile-web platform that supports grassroots data collection from patients and hospital staff. We hope that widespread data reporting in the US will allow Hospifind to achieve its goal of saving the lives of patients and healthcare workers across the country.

Important Note

To prevent unauthorized usage of our Google Maps API key we removed it from our website. The website below will work for the hospital portal, and in our video we showed how the website would function for a patient with a working API key.

+ 2 more
Share this project: