November 12, 2019Open Access
View Full PaperImproving Risk Prediction in Heart Failure Using Machine Learning
Structured PICO
Does a machine learning-based mortality risk score improve prediction accuracy compared to other risk scores in patients with heart failure?
P
Population
Patients with heart failure (HF)
I
Intervention
Mortality risk score generated using machine learning and readily available variables
C
Comparator
Other risk scores
O
Outcome
Accuracy of mortality risk prediction
A machine learning approach using readily available variables can generate a mortality risk score for heart failure patients that is more accurate than existing risk scores.
Abstract
Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.