no code implementations • 24 Mar 2018 • Kahkashan Afrin, Gurudev Illangovan, Sanjay S. Srivatsa, Satish T. S. Bukkapatnam
Accuracies of survival models for life expectancy prediction as well as critical-care applications are significantly compromised due to the sparsity of samples and extreme imbalance between the survival (usually, the majority) and mortality class sizes.