BioProg

Inspiration

Motivated by one of our group member’s family members fighting breast cancer, we were eager to find a way to use tools in Computer Science to further our understanding, find new patterns and make strides in medical prognosis. The large majority of way this disease is found in patients is largely outdated and inefficiently done, especially in developing societies, which we see as the core problem we are trying to solve. Therefore, we wanted to create a free and simple tool which allows people to make an accurate cancer tumor prognosis based on common parameters that can be measured in hospitals.

What it does Our program uses a machine learning algorithm that has been trained by a dataset obtained from the University of Wisconsin. The user then inputs the values of the 9 parameters that are commonly measured and the system is able to determine whether there is a high likelihood of a malignant or benign tumor. This is especially useful as there has not been any research which definitively proves correlation between any of our parameters and malignant/benign tumors, so we are able to give users new information. We display this on a user-friendly website which allows accessibility for a wide range of people

How we built it We used the atom text editor to code our HTML, Javascript, and CSS files. TensorFlow was used to create the machine learning model for diagnosing breast cancer. Django connected the front end to the backend, done using the Python programming language.

Challenges we ran into Collecting the data. We needed a windows pc to run the software where data was stored

Accomplishments that we’re proud of We are most proud of using machine learning algorithms that we used to find new patterns and create new ideas in the prognosis of tumors. We are proud that we managed to integrate these Machine Learning tools into our website in a manner that it can be used by anyone.

What we learned As a group, we learned and taught each other how to use frameworks such as HTML, CSS, Tensorflow, Django and developed a website from scratch. This was an especially great learning experience as we came in to the project with no experience in HTML,CSS and Javascript.

What's next for BioProg Get more data and get more parameters

Built With

• css
• django
• html
• javascript
• pytho
• tensorflow