Skip to main content

Table 10 Stratified logistic regression feature ranking

From: Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone

RankClinical featureImportance
1Ejection fraction4.13938106
2Serum creatinine3.69917184
3Age2.61938095
4Creatinine phosphokinase1.88929235
5Sex1.32038950
6Platelets1.06270364
7High blood pressure0.79478093
8Anaemia0.77547306
9Smoking0.65828165
10Diabetes0.60355319
11Serum sodium0.54241360
  1. Results of the feature ranking obtained by the stratified logisitc regression. Importance: coefficient of the trained logistic regression model, average of 100 execution