Related works

Below is a table summarizing related works from the provided files, focusing on disease prediction using machine learning. The
table includes the focus area, key findings, technology used, and challenges addressed.

Author/Paper
Focus Area Key Findings Technology Used Challenges Addressed
Name
Random Forest achieved the highest Random Forest, Handling imbalanced
Coronary Heart accuracy (96.8%) in predicting CHD. Decision Tree, K- datasets, preprocessing of
Divya Krishnani
Disease (CHD) Preprocessing steps like resampling and Nearest Neighbours, medical data, and
et al. (2019)
Prediction normalization improved model K-Fold Cross- improving prediction
performance. Validation accuracy.
Naïve Bayes, Decision Tree, and
Naïve Bayes, Decision Predicting diseases from
Random Forest were used to predict
C K Gomathy et Disease Prediction Tree, Random Forest, symptoms, handling
diseases like Diabetes, Malaria, and
al. (2021) using Symptoms KNN, Logistic structured data, and
Tuberculosis. Random Forest achieved
Regression improving model accuracy.
the highest accuracy (98.95%).
Handling imbalanced
Tilakachuri Random Forest outperformed other
Chronic Kidney Random Forest, Naïve datasets, improving
Balakrishna et algorithms in predicting chronic kidney
Disease Prediction Bayes, J48 accuracy in disease
al. (2017) disease.
prediction.
Heart sounds were used to detect Filtering audio signals,
Machine Learning,
Martin Gjoreski Chronic Heart chronic heart failure. Stacking of ML feature extraction, and
Stacking of ML
et al. (2017) Failure Detectionalgorithms improved detection improving detection
algorithms
accuracy. accuracy.
Supervised and unsupervised ML Handling large datasets,
Nitten S.
Chronic Disease algorithms were used for chronic Random Forest, SVM, cohort segmentation, and
Rajliwali et al.
Risk Monitoring disease risk prediction. Random Forest KNN improving prediction
(2017)
and SVM showed high accuracy. accuracy.
Chronic Kidney Multilayer Perceptron (MLP) was used to
Handling class imbalance
Pinar Yildirim Disease Prediction predict chronic kidney disease. Multilayer Perceptron,
in datasets and improving
(2017) on Imbalanced Resampling methods improved Resampling methods
model performance.
Data accuracy.
Maryam Feature selection and normalization Feature selection,
Decision Tree, Neural
Soltanpour Chronic Kidney improved the performance of classifiers normalization, and
Network, SVM, Naïve
Gharihoudusi et Disease Prediction like Decision Tree, Neural Network, and improving classifier
Bayes
al. (2017) SVM. performance.
Handling large-scale
Machine learning models were used to
Min Chen et al. Disease Prediction Machine Learning, Big healthcare data and
predict diseases using big data from
(2017) using Big Data Data Analytics improving disease
healthcare communities.
prediction accuracy.
M. A. Jabbar et Heart Disease Hidden Naïve Bayes classifier was used Improving accuracy in
Hidden Naïve Bayes
al. (2016) Prediction to predict heart disease. heart disease prediction.
Gunarathne Chronic Kidney Machine learning classification Machine Learning, Improving accuracy in
W.H.S.D et al. Disease techniques were evaluated for disease Classification disease classification and
(2017) Classification classification and forecasting. Techniques forecasting.
Liver Fibrosis
Machine learning approaches were
Somaya Hashem Prediction in Improving accuracy in liver
compared for predicting advanced liver Machine Learning
et al. (2018) Chronic Hepatitis fibrosis prediction.
fibrosis.
C Patients
Early Prediction of Machine learning supported by Early detection of chronic
Ahmed J. Aljaaf Machine Learning,
Chronic Kidney predictive analytics was used for early diseases and improving
et al. (2018) Predictive Analytics
Disease prediction of chronic kidney disease. prediction accuracy.
A new method using ECG signals and
Coronary Artery ECG Signal Improving accuracy in
M. Sharma et al. time-frequency concentrated anti-
Disease Processing, Wavelet coronary artery disease
(2019) symmetric biorthogonal wavelet filter
Identification Transform identification.
bank was proposed.

References: