Application of decision tree-based ensemble learning in the classification of breast cancer

Computers in Biology and Medicine, Journal Year: 2020, Volume and Issue: 128, P. 104089 - 104089

Published: Oct. 31, 2020

Language: Английский

---

A classification and regression tree algorithm for heart disease modeling and prediction

Healthcare Analytics, Journal Year: 2022, Volume and Issue: 3, P. 100130 - 100130

Published: Dec. 16, 2022

Heart disease remains the leading cause of death, such that nearly one-third all deaths worldwide are estimated to be caused by heart-related conditions. Advancing applications classification-based machine learning medicine facilitates earlier detection. In this study, Classification and Regression Tree (CART) algorithm, a supervised method, has been employed predict heart extract decision rules in clarifying relationships between input output variables. addition, study's findings rank features influencing based on importance. When considering performance parameters, 87% accuracy prediction validates model's reliability. On other hand, extracted reported study can simplify use clinical purposes without needing additional knowledge. Overall, proposed algorithm support not only healthcare professionals but patients who subjected cost time constraints diagnosis treatment processes disease.

Language: Английский

---

Applying Artificial Intelligence to Wearable Sensor Data to Diagnose and Predict Cardiovascular Disease: A Review

Sensors, Journal Year: 2022, Volume and Issue: 22(20), P. 8002 - 8002

Published: Oct. 20, 2022

Cardiovascular disease (CVD) is the world’s leading cause of mortality. There significant interest in using Artificial Intelligence (AI) to analyse data from novel sensors such as wearables provide an earlier and more accurate prediction diagnosis heart disease. Digital health technologies that fuse AI sensing devices may help prevention reduce substantial morbidity mortality caused by CVD worldwide. In this review, we identify describe recent developments application digital for CVD, focusing on approaches detection, diagnosis, through models driven collected wearables. We summarise literature use cardiovascular followed a detailed description dominant applied modelling acquired discuss algorithms clinical applications find machine-learning-based are superior traditional or conventional statistical methods predicting events. However, further studies evaluating applicability real world needed. addition, improvements wearable device accuracy better management their required. Lastly, challenges introduction into routine healthcare face.

Language: Английский

---

Effective Class-Imbalance Learning Based on SMOTE and Convolutional Neural Networks

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(6), P. 4006 - 4006

Published: March 21, 2023

Imbalanced Data (ID) is a problem that deters Machine Learning (ML) models from achieving satisfactory results. ID the occurrence of situation where quantity samples belonging to one class outnumbers other by wide margin, making such models’ learning process biased towards majority class. In recent years, address this issue, several solutions have been put forward, which opt for either synthetically generating new data minority or reducing number classes balance data. Hence, in paper, we investigate effectiveness methods based on Deep Neural Networks (DNNs) and Convolutional (CNNs) mixed with variety well-known imbalanced meaning oversampling undersampling. Then, propose CNN-based model combination SMOTE effectively handle To evaluate our methods, used KEEL, breast cancer, Z-Alizadeh Sani datasets. order achieve reliable results, conducted experiments 100 times randomly shuffled distributions. The classification results demonstrate Synthetic Minority Oversampling Technique (SMOTE)-Normalization-CNN outperforms different methodologies 99.08% accuracy 24 Therefore, proposed can be applied binary problems real

Language: Английский

---

Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data

Diagnostics, Journal Year: 2023, Volume and Issue: 13(3), P. 481 - 481

Published: Jan. 28, 2023

The biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal brain patients. As result, non-invasive computer-aided diagnosis (CAD) tool required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been proposed MRI several sequences, which can express structure in different ways. suitable sequence classification not yet known. most common 'glioma', the form. Therefore, study, maximize ability between low-grade versus high-grade glioma, three datasets were designed comprising sequences: T1-Weighted (T1W), T2-weighted (T2W), and fluid-attenuated inversion recovery (FLAIR). Further, five well-established convolutional neural networks, AlexNet, VGG16, ResNet18, GoogleNet, ResNet50 adopted classification. An ensemble algorithm was using majority vote of above deep learning (DL) models produce more consistent improved results than any individual model. Five-fold cross validation (K5-CV) protocol training testing. For ensembled classifier with K5-CV, highest test accuracies 98.88 ± 0.63%, 97.98 0.86%, 94.75 0.61% achieved FLAIR, T2W, T1W-MRI data, respectively. FLAIR-MRI data found be significant classification, where showed 4.17% 0.91% improvement accuracy against T2W-MRI (MajVot) improvements average 3.60%, 2.84%, 1.64%, 4.27%, 1.14%, respectively, ResNet50.

Language: Английский

---

Towards Diagnostic Aided Systems in Coronary Artery Disease Detection: A Comprehensive Multiview Survey of the State of the Art

International Journal of Intelligent Systems, Journal Year: 2023, Volume and Issue: 2023, P. 1 - 19

Published: Aug. 9, 2023

Introduction. Coronary artery disease (CAD) is one of the main causes death all over world. One way to reduce mortality rate from CAD predict its risk and take effective interventions. The use machine learning- (ML-) based methods an method for predicting CAD-induced death, which why many studies in this field have been conducted recent years. Thus, study aimed review published on artificial intelligence classification algorithms detection diagnosis. Methods. This systematically reviewed most cutting-edge techniques analyzing clinical paraclinical data quickly diagnose CAD. We searched PubMed, Scopus, Web Science databases using a combination related keywords. A extraction form was used collect after selecting articles inclusion exclusion criteria. content analysis analyze data, study’s objectives, results are presented tables figures. Results. Our search three prevalent resulted 15689 studies, 54 were included be analysis. Most laboratory demographic shown desirable results. In general, ML (traditional ML, DL/NN, ensemble) used. Among used, random forest (RF), linear regression (LR), neural networks (NNs), support vector (SVM), K-nearest (KNNs) applications code recognition. Conclusion. findings show that these models different successful despite lack benchmark comparing features, methods, Many performed better their analyses features as result closer look. near future, specialists can ML-based powerful tool diagnosing more precisely by looking at design’s technical facets. incredible outcomes decreased diagnostic errors, time, needless invasive tests, typically decreases expenses healthcare systems.

Language: Английский

---

A Review of Machine Learning Algorithms for Biomedical Applications

Annals of Biomedical Engineering, Journal Year: 2024, Volume and Issue: 52(5), P. 1159 - 1183

Published: Feb. 21, 2024

Language: Английский

---

Supervised Learning - A Systematic Literature Review

Published: June 13, 2024

Machine Learning (ML) is a rapidly emerging field that enables plethora of innovative approaches to solving real-worldproblems. It machines learn without human intervention from data and used in variety applications,from fraud detection recommendation systems medical imaging. Supervised learning, unsupervised andreinforcement learning are the 3 main categories ML. involves pre-training model on labeleddataset entails two distinct types learning: classification regression. Regression when output iscontinuous. By contrast, categorical.Supervised aims optimize class label models using predictor features. Following that, second classifieris assign labels test cases where values characteristics known butthe value unknown. In classification, identifies which training set belongs.However, regression, real-value response corresponds example.

Language: Английский

---

Ensemble of heterogeneous classifiers for diagnosis and prediction of coronary artery disease with reduced feature subset

Computer Methods and Programs in Biomedicine, Journal Year: 2020, Volume and Issue: 198, P. 105770 - 105770

Published: Sept. 30, 2020

Language: Английский

---

A Comprehensive Analysis on Detecting Chronic Kidney Disease by Employing Machine Learning Algorithms

EAI Endorsed Transactions on Pervasive Health and Technology, Journal Year: 2021, Volume and Issue: 7(29), P. e1 - e1

Published: Aug. 13, 2021

INTRODUCTION: Chronic Kidney Disease refers to the slow, progressive deterioration of kidney functions. However, impairment is irreversible and imperceptible up until disease reaches one later stages, demanding early detection initiation treatment in order ensure a good prognosis prolonged life. In this aspect, machine learning algorithms have proven be promising, points towards future diagnosis.OBJECTIVES: We aim apply different for purpose assessing comparing their accuracies other performance parameters chronic disease.METHODS: The ‘chronic dataset’ from repository University California, Irvine, has been harnessed, eight supervised models developed by utilizing python programming language disease.RESULTS: A comparative analysis portrayed among evaluating like accuracy, precision, sensitivity, F1 score ROC-AUC. Among models, Random Forest displayed highest accuracy 99.75%.CONCLUSION: observed that can contribute significantly domain predictive disease, assist developing robust computer-aided diagnosis system aid healthcare professionals treating patients properly efficiently.

Language: Английский

---