Table 2.

Machine-Learning algorithms application on human diseases

Human diseases	ML Algorithms	Features	Reference
Covid-19	ES, LR, LASSO, SVM	The goal was to demonstrate how ML approaches may be utilized to estimate the number of future individuals impacted by COVID-19, commonly recognized as a potential threat to humanity	[178]
Brain Stroke	SVM	The hematoma growth is due to the prediction that ICH will naturally arise from a comparable resource when SVM is used	[179]
Brain Tumor	KNN, SVM, RF, LDA	The goal of the best machine-learning and classification algorithms was to learn from training automatically and make a wise judgment with high accuracy	[180]
Liver Disease	J48, SVM& NB	Compare algorithm strategies with a greater accuracy rate for identifying liver disease to anticipate the same conclusive conclusion	[181]
Alzheimer	CNN	The project's goal was to improve accuracy to levels comparable to the highest development, address the issue of overfitting, and look at validated brain technologies with visible AD diagnostic markers	[182]
Alzheimer	SVM	This study aimed to look at several aspects of Alzheimer's disease diagnosis to see whether it can be used as a biomarker to differentiate between AD and other subjects	[183]
Parkinson’s Disease	SVM	The study discovered the most effective and comprehensive technique to suggest for improving Parkinson's disease identification accuracy	[184]
Thyroid Disease	SVM	The study's objective was to select the prime approach to classify thyroid disease, which is one of the most challenging classification tasks	[185]
Diabetes	SVM	Determine the most effective methods for detecting breast cancer early	[186]