Table 10 Comparative analysis of the proposed models with the existing state of arts.

From: A hybrid framework for heart disease prediction using classical and quantum-inspired machine learning techniques

Authors

Feature Selection Methods

Hyperparameter Tuning

Classification Methods

Accuracy (%)

Time (s)

Sensitivity (%)

Precision (%)

F1-Score (%)

Vijayshree et al.28

Chi-squared

PSO

SVM

88.22

148

---

---

---

Shafiey et al.29

GA

PSO

RF

95.6

2525.59

94.1

96.2

95.1

Huang et al.23

GA

---

SVM

85.6

---

---

---

---

Tao et al.30

GA

PSO

SVM

89.88

---

---

---

---

Khammassi et al.31

GA-LR

---

DT

81.42

---

79.3

82.0

80.6

Temitayo et al.32

GA

---

SVM

93.5

119.56

92.8

94.1

93.4

Chen et al.33

GA

---

SVM

95.56

---

---

---

---

Nandipati et al.34

Pearson Correlation

---

SVM / RF

82.27 / 85

117.57 / 187

80.2 / 84.1

83.4 / 85.9

81.7 / 85

Sreejith et al.17

Wrapper Method

Ant Colony

SVM / RF

84.5 / 89.81

---

83.2 / 88.9

85.0 / 90.5

84.1 / 89.7

Abdulsalam et al.35

---

---

QSVM / QNN

88 / 86

317 / 455.51

87.5 / 85.1

88.2 / 86.3

87.8 / 85.7

Proposed Classical Model

CGA

CPSO

CSVM

94.02

362.92

93.1

94.4

93.7

Proposed Quantum Model

QGA

QPSO

QSVM

97.83

413.57

97.2

98.1

97.6