Table 1.

A relative study of different literature reviews.

Ref	Objective	Techniques	Accuracy %	Precision %	Recall %	F1 Score %
[26]	The early detection of cardiovascular disease in patients.	NB, DT, DF, and K-NN classifiers	KNN:90.7, DT: 80.2, RF: 84.2, NB: 88.15	N/A	N/A	N/A
[34]	A comparative study of intelligent computational techniques	SVM, NB LR, DNN, DT, RF, and K-NN.	SVM:97.41, NB: 91.38, LR: 96.29, DNN: 98.15, DT: 96.42, RF: 90.46, KNN: 96.42	N/A	N/A	N/A
[37]	Medical image classification	AOC-CapsNet	93.1	92	90.3	91.9
[38]	Handling imbalanced medical images	CNN framework	N/A	N/A	N/A	N/A
[39]	Ultrasonography thyroid nodule image synthesis	KACGAN-based model	91.46	N/A	N/A	N/A
[40]	Classification of arrhythmia	2-D CNN	99.11%	98.58	N/A	98
[42]	Classification of noisy images	Five hybrid CNN models	DVAE- CNN: 62.8, DVAE-CDAE-CNN: 53.91	N/A	N/A	N/A
[43]	Heart-disease prediction	AHHO and deep genetic algorithm	97.3	95.6	N/A	N/A
[44]	Heart-disease prediction	CNN	97	N/A	N/A	N/A
[45]	Heart-disease prediction	ANN, SVM, and KNN	SVM: 85.18, KNN: 80.74, ANN: 73.33	N/A	N/A	N/A
[46]	AI and image-classification-based heart-disease prediction	HLDA-MALO and hybrid R-CNN with SE-ResNet-101 model	99.15	98.06	99.15	99.02
[47]	Detection of abnormalities in ECG images.	FM-ECG framework	CECG: N/A, DECG: N/A	79.23, 90.42	69.10, 83.59	73.88, 86.87