Research Article
Heart Risk Failure Prediction Using a Novel Feature Selection Method for Feature Refinement and Neural Network for Classification
Table 1
Types of features of the dataset.
| Feature no. | Feature description | Feature code | (Mean std)Healthy | (Mean std)Patients |
| 1 | Age (AGE) | | 52.64 9.52 | 56.84 7.42 | 2 | Sex (SEX) | | 0.55 0.49 | 0.81 0.385 | 3 | Chest pain type (CPT) | | 2.79 0.92 | 3.60 0.79 | 4 | Resting blood pressure (RBP) | | 129.17 16.32 | 134.85 18.69 | 5 | Serum cholesterol (SCH) | | 243.49 53.58 | 250.73 49.83 | 6 | Fasting blood sugar (FBS) | | 0.14 0.35 | 0.15 0.35 | 7 | Resting electrocardiographic results (RES) | | 0.84 0.98 | 1.14 0.97 | 8 | Maximum heart rate achieved (MHR) | | 158.59 18.98 | 138.89 22.74 | 9 | Exercise induced angina (EIA) | | 0.14 0.35 | 0.54 0.49 | 10 | Old peak (OPK) | | 0.59 0.78 | 1.64 1.29 | 11 | Peak exercise slope (PES) | | 1.41 0.59 | 1.83 0.56 | 12 | Number of major vessels colored by fluoroscopy (VCA) | | 0.27 0.63 | 1.13 1.01 | 13 | Thallium scan (THA) | | 3.78 1.55 | 5.90 1.70 |
|
|