Heart failure is one of the most life-threatening diseases of the modern era, with high global mortality and morbidity rates, motivating the need for long-term outcome prediction. One established tool is the MAGGIC Risk Calculator for Heart Failure, which predicts 3-5 year mortality risk from parameters like blood pressure, age, sodium concentration, heart rate and COPD presence. This study develops regression models — polynomial regression, support vector regression and random forest regression — to estimate the MAGGIC score from physical examination, blood biomarker, ECG and ultrasound data without relying on the calculator's standard input parameters. Random forest regression achieved the lowest error (RMSE of 6.37 on a 0-91 point scale), enabling a precise, alternative assessment of death risk over the following 3-5 years. This work was presented at the 4th Serbian International Conference on Applied Artificial Intelligence (SICAAI 2025), Zlatibor, Serbia, and was carried out within the STRATIFYHF project.