A Novel Clinical Decision Support System Using Improved Adaptive Genetic Algorithm for the Assessment of Fetal Well-Being

Table 7

Comparison with previous works of all the datasets.

S. number	[Reference Number]	Features and methods	Selected features	Classifier	Accuracy
Multiclass classification
CTG dataset
1	[7]	ANFIS	—	—	97.15
2	[6]	GA	13	SVM	99.23
3	[8]	LS-SVM-PSO-BDT	—	SVM	91.62
4	Proposed study	IAGA-M1	6	ELM	93.61 ± 0.42
ES dataset
1	[20]	IFSFS	21	SVM	98.61
2	[21]	Two-stage GFSBFS	20, 16, 19	SVM	100, 100, 97.06
3	[22]	GA based FS algorithm	16	BN	99.20
4	Proposed study	IAGA-M2	14	BN	98.83 ± 0.12
BT dataset
1	[23]	Normalization	—	SVM	71.69
2	[24]	Electrical impedance spectroscopy	8		92
3	[25]	ACO and fuzzy system	—	SVM	71.69
4	Proposed study	IAGA-M2	3	ELM	93.58 ± 0.42
Binary Classification
MEEI dataset
1	[26]	30 acoustic features and PCA	17	SVM	98.1
2	[27]	LDA based filter bank energies	Not reported	LDA	85
3	[28]	22 acoustic features and IFS	16	SVM	91.55
4	Proposed study	22 acoustic features and IAGA	8	SVM	100
PD dataset
1	[29]	GA	10	SVM	99
2	[30]	GA	9	k-NN	98.20
3	Proposed study	IAGA-M1	8	k-NN	99.38 ± 0.22
CAD dataset
1	[31]	GA	9	SVM	83
2	[32]	WEKA filtering method	7	MLP	86
3	Proposed study	IAGA-M2	3	SVM	83.23 ± 0.84