Research Article
Machine Learning-Based Model to Predict Heart Disease in Early Stage Employing Different Feature Selection Techniques
Table 1
Heart disease dataset description.
| Serial no. | Feature name | Code | Description |
| 1 | Age | AGE | The patient’s age in years. | 2 | Sex | SEX | The patient’s sex: , | 3 | cp | CPT | Chest pain type: angina,1 = atypical angina, pain, | 4 | trestbps | RBP | Resting blood pressure (in mm) | 5 | chol | CM | The patient’s cholesterol measurement in mg/dl | 6 | fbs | FBS | The patient’s fasting blood mg/dl. , | 7 | restecg | REC | Resting electrocardiographic results: to note, ST-T wave abnormality, or definite left ventricular hypertrophy | 8 | Thalach | MHR | Maximum heart rate achieved | 9 | exang | EIA | Exercise-induced angina: , | 10 | Oldpeak | OP | ST depression induced by exercise relative to rest checks the stress of the heart during exercise. The weak heart will stress more. | 11 | Slope | PES | The slope of the peak exercise ST segment sloping, 1, | 12 | ca | NMV | Number of primary vessels (0-3) colored by fluoroscopy. | 13 | thal | TS | Thallium stress result: 1, , defect, defect |
|
|