Back

Examining the Efficacies of Different Machine Learning Algorithms on Predicting Future Potential Death from Heart Failure

Radi, O. O.

2023-11-11 cardiovascular medicine
10.1101/2023.11.11.23298416 medRxiv
Show abstract

1 in every 5 deaths is from heart failure. If this heart failure was able to be predicted, medical practitioners would be able to issue the proper preventative measures in order to prevent the fatal heart attack. As machine learning is gaining its place in medicine, one of the most commonly asked questions is which machine learning algorithms can be used where. This paper aims to find which machine learning algorithm is most efficacious in predicting future fatal heart disease. Two machine learning algorithms were evaluated in this study; namely linear regression models and k-nearest-neighbors models. The K-Nearest-Neighbors model was found to be most efficacious with an accuracy between 96.67% and 100% in predicting future heart failure. The reliability of this algorithm in predicting death from heart failure will surely prove useful in the future of treating at-risk patients.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.