Heart Failure Occurrence: Mining Significant Patterns and 10 Days Early Prediction

Abstract

Electronic health records containing patient’s medical history, drug prescription, vital signs measurements, and many more parameters, are being frequently extracted and stored as unused raw data. On the other hand, machine learning and data mining techniques are becoming popular in the medical field, providing the ability to extract knowledge and valuable information from electronic health records along with accurately predicting future disease occurrence. This chapter presents a study on medical data containing vital signs recorded over the course of some years, for real patients suffering from heart failure. The first significant patterns that come along with heart failure occurrence are extracted and examined using data mining techniques that have already proven to be effective. In this study, FP-GROWTH and RULEGROWTH algorithms are employed to discover the most influencing patterns and series of vital signs recordings leading to a possible heart failure risk. Finally, as a first contribution, Long short-term memory (LSTM) recurrent neural network is used to predict a possible heart failure risk within a window of 10-days in the future, with 76% of correct predictions.