Inspiration
Sepsis affects more than 30 million people worldwide each year and takes 8 million lives including more than 3 million children each year.
What it does
Sepsis is a life-threatening condition also known as ‘blood poisoning’ that seriously endangers millions of people over the world.
How I built it
the machine learning model has been trained and tested using the Naive Bayes approach. The resultant report will predict whether he/she is dealing with sepsis or not and classifying them according to the risk rate.
Challenges I ran into
collecting data for training our model(but have gathered around 700,000 data).
Accomplishments that I'm proud of
our model has achieved an accuracy of 97-98%.
What I learned
Sepsis is a very dreadful disease yet many people are not aware of it. Awareness of such diseases is as important as treatment for it.
What's next for sepsis predictor
Converting our Naive Bayes approach into CNN(conventional neural networks).
Log in or sign up for Devpost to join the conversation.