Inspiration
ERNI is a software consulting company which is growing in the data field. We are focusing efforts in medicine projects. We see this hackathon as an opportunity to play with real medical data.
What it does
We did an exploratory data analysis and feature engineering to prepare the data. Next, we proposed some ML models.
How we built it
For the feature engineering site, we used needleman-wunsch algorithm over the phenotype variable. Finally, we did some cleaning and transforming data to put it in a more proper way.
Challenges we ran into
First, the data format. Furthermore, as we didn't understand the meaning of some variables, it was difficult for us to interpretate and correlate some variables. Finally, we suposed that some phenotypes could be indirectly related but, we didn't have time correlate them. Although, the algorithm is ready to do that.
Accomplishments that we're proud of
We have been able to figure out how to approach the problem, even without prior experience.
What we learned
We understood how to deal with needleman-wunsch algorithm.
What's next for ERNI Healthcare
We would like to further develop our idea, trainning some ML models to get the probability of the most relevant diseases.
Log in or sign up for Devpost to join the conversation.