Systematic Literature Review: Disease Classification Modeling Using Deep Learning Algorithms

This research focuses on models and algorithms used in studies of diseases such tuberculosis, malaria, diabetes, heart disease, and cancer. It also looks at long-term management, therapy, and prevention of chronic disease complications. The objective is to achieve a thorough understanding of the algorithms employed for various diseases, aiding in the development of more effective treatment strategies. Various algorithms, such as decision trees, SVM, Random Forest, Naive Bayes, and neural networks like RNN, LSTM, and CNN, are analyzed. The study finds that deep learning algorithms, when combined with data reduction techniques such as PCA and LDA, show significant results in disease modeling. These techniques enhance efficiency and accuracy in diagnosis, treatment, and prevention. This study uncovers how these algorithms can identify patterns, trends, and associations in large and complex health datasets. This contributes to new insights in disease research that deep learning algorithms show significant results in disease modeling with data reduction techniques such as PCA and LDA. This research also finds that deep learning algorithms can improve efficiency and accuracy in diagnosis, treatment, and disease prevention. The combination of PCA with deep learning algorithms such as LSTM, CNN, and GNN shows potential in improving predictive performance.s.