Table 12 Comparison between a single C4.5 tree and descriptive forest for CVD-dataset accuracy, precision, and recall
Comparison | the single C4.5 tree | the {Oldpeak > 85}-tree | the {ChestPainType = ASY}-tree | the {ExerciseAngina = Y}-tree | the {ST_Slope = Flat}-tree | the {Sex = M}-tree | the {Sex = M, ChestPainType = ASY}-tree | the {Sex = M, ExerciseAngina = Y}-tree | the {Sex = M, ST_Slope = Flat}-tree | the Descriptive Forest |
|---|---|---|---|---|---|---|---|---|---|---|
-True positive | 459 | 316 | 367 | 311 | 377 | 4 | 330 | 285 | 339 | 470 |
-True negative | 328 | 47 | 60 | 14 | 28 | 154 | 47 | 10 | 15 | 333 |
-False positive | 82 | 44 | 44 | 41 | 51 | 2 | 26 | 29 | 28 | 77 |
-False negative | 49 | 16 | 25 | 5 | 4 | 14 | 23 | 4 | 3 | 38 |
-Number of instances of the training dataset | 918 | 423 | 496 | 371 | 460 | 174 | 426 | 328 | 385 | 918 |
-Correctness I (accuracy) | 0.8573 | 0.8582 | 0.8609 | 0.8760 | 0.8804 | 0.9080 | 0.8850 | 0.8994 | 0.9195 | 0.8747 |
-Correctness II (precision) | 0.8484 | 0.8778 | 0.8929 | 0.8835 | 0.8808 | 0.6667 | 0.9270 | 0.9076 | 0.9237 | 0.8592 |
-Coverage (recall) | 0.9035 | 0.9518 | 0.9362 | 0.9842 | 0.9895 | 0.2222 | 0.9348 | 0.9862 | 0.9912 | 0.9252 |
-Overall quality (F-measure) | 0.8751 | 0.9133 | 0.9141 | 0.9311 | 0.9320 | 0.3333 | 0.9309 | 0.9453 | 0.9563 | 0.8910 |
-Not predict | 0 | 495 | 422 | 547 | 458 | 744 | 492 | 590 | 533 | 0 |