Skip to main content

Table 3 Statistical quantitative description of the numeric features

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

 Full sampleDead patientsSurvived patients
Numeric featureMedianMeanσMedianMeanσMedianMeanσ
Age60.0060.8311.8965.0065.2213.2160.0058.7610.64
Creatinine phosphokinase250.00581.80970.29259.00670.201316.58245.00540.10753.80
Ejection fraction38.0038.0811.8330.0033.4712.5338.0040.2710.86
Platelets262.00263.3697.80258.50256.3898.53263.00266.6697.53
Serum creatinine1.101.391.031.301.841.471.001.190.65
Serum sodium137.00136.604.41135.50135.405.00137.00137.203.98
Time115.00130.3077.6144.5070.8962.38172.00158.3067.74
  1. Full sample: 299 individuals. Dead patients: 96 individuals. Survived patients: 203 individuals. σ: standard deviation