Forecasting Heart Disease Risk Using Revised Machine Learning Models DOI

Afrina Sultana,

Afroza Akter,

Ayesha Aziz Prova

et al.

2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 6

Published: Nov. 16, 2023

Heart-disease, often synonymous with cardiac arrest or heart attack, stands as one of the predominant contributors to global mortality in our contemporary world. Globally, disease claims lives approximately 20 million people each year, making up roughly 32% all fatalities. Among these, attacks account for 60% casualties. Heart are gradually increasing among younger generation which is most alarming. The surge particularly pronounced low- and middle-income countries. Due inadequate preventive care risk factor screening, individuals these regions experience early-onset suboptimal outcomes. This paper has proposed a Revised Logistic Regression (RLR), Random Forest (RRF), Gaussian Naïve Bayes (RGNB) algorithms enhance accuracy, precision, recall, f1-score model that offers time-efficient low-risk method predicting disease. These revised provide better results compared Regression, Forest, naïve Bayes. accuracy RLR reached 94.23% 6% higher than previous algorithm. RGNB become 90.38% 5% And, highest increased algorithm RRF 96.15% 9% Furthermore, precision 97%, recall 96%, 96%.

Language: Английский

Enhancing Cardiovascular Health Prediction: A Machine Learning Perspective DOI
Ratnam Dodda,

Abhishek Reddy Bonam,

Srinidhi Sakinala

et al.

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 87 - 96

Published: Jan. 1, 2025

Language: Английский

Citations

0
A Disentangled VAE-BiLSTM Model for Heart Rate Anomaly Detection DOI Creative Commons
Alessio Staffini, Thomas Svensson, Ung‐il Chung

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(6), P. 683 - 683

Published: June 3, 2023

Cardiovascular diseases (CVDs) remain a leading cause of death globally. According to the American Heart Association, approximately 19.1 million deaths were attributed CVDs in 2020, particular, ischemic heart disease and stroke. Several known risk factors for include smoking, alcohol consumption, lack regular physical activity, diabetes. The last decade has been characterized by widespread diffusion use wristband-style wearable devices which can monitor collect rate data, among other information. Wearable allow analysis interpretation physiological activity data obtained from wearer therefore be used prevent potential CVDs. However, these are often provided manner that does not general user immediately comprehend possible health risks, require further analytics draw meaningful conclusions. In this paper, we propose disentangled variational autoencoder (

Language: Английский

Citations

10
Enhancing Heart Disease Detection Using Convolutional Neural Networks and Classic Machine Learning Methods DOI Creative Commons
Sri Mulyani, Nurhadi Wijaya,

Fike Trinidya

et al.

Journal of Computer Electronic and Telecommunication, Journal Year: 2024, Volume and Issue: 4(2)

Published: Jan. 26, 2024

This study addresses the problem of heart disease detection, a critical concern in public health. The research aims to compare performance Convolutional Neural Networks (CNN) with conventional machine learning algorithms diagnosing using dataset comprising 14 features. primary objective is determine whether CNNs can provide more accurate and reliable results than traditional techniques. employs rigorous preprocessing, normalizing relevant features, splits into an 80-20 training-testing split. model trained for 300 epochs batch size 64, evaluation conducted confusion matrices classification reports. reveal that CNN achieved remarkable accuracy 100%, demonstrating its potential outperform algorithms. These findings emphasize significance deep techniques improving diagnostics, although further needed optimize models address interpretability concerns practical implementation healthcare settings.

Language: Английский

Citations

1
Comparative analysis and prediction of coronary heart disease DOI Open Access
Sashikanta Prusty, Srikanta Patnaik, Sujit Kumar Dash

et al.

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2022, Volume and Issue: 27(2), P. 944 - 944

Published: July 22, 2022

Cardiovascular disease (CVD) <span>is now one of the leading causes death worldwide and was also thought to be a serious illness in mid old ages. Artificial intelligence machine learning have huge impact on healthcare areas. As result, getting familiar individual with data processing techniques suitable for numerical health data. Although, most often used algorithms classification tasks will incredibly advantageous terms time management. In particular here, common procedure has been proposed predicting cardiovascular disease. Accordingly, we herein consider nine typical classifiers both deep technology comparative analysis prediction coronary heart failure. These models are computationally inexpensive easy build. Moreover, these tested compared using confusion matrix Jupyter notebook, yielding measures such as accuracy, f1-score, recall, precision. logistic regression classifier gives maximum possible precision, f1-score 90.78%, 90.24%, 91.35% respectively.</span>

Language: Английский

Citations

6
Development of heart attack prediction model based on ensemble learning DOI Open Access
Omar Shakir Hasan,

Ibrahim Ahmed Saleh

Eastern-European Journal of Enterprise Technologies, Journal Year: 2021, Volume and Issue: 4(2(112)), P. 26 - 34

Published: Aug. 31, 2021

With the advent of data age, continuous improvement and widespread application medical information systems have led to an exponential growth biomedical data, such as imaging, electronic records, biometric tags, clinical records that potential essential research value. However, based on statistical methods is limited by class size community, so it cannot effectively perform mining for large-scale information. At same time, supervised machine learning techniques can solve this problem. Heart attack one most common diseases leading causes death, finding a system accurately reliably predict early diagnosis influential step in treating diseases. Researchers used various analyze helping professionals heart disease. This paper presents features related disease, model ensemble learning. The proposed involves preprocessing selecting attributes, then using logistic regression algorithms meta-classifiers build model. Furthermore, (Support Vector Machines, Decision Tree, Random Forest, Extreme Gradient Boosting) prediction Framingham Study dataset compared with methodology. results show feasibility effectiveness method group provide accuracy recommendations better than single traditional algorithm.

Language: Английский

Citations

7
A Model Statistik untuk Deteksi Status Ketahanan Pangan Rumah Tangga di Daerah Istimewa Yogyakarta DOI Creative Commons

Suparna Parwodiwiyono

JURNAL KESEHATAN SAMODRA ILMU, Journal Year: 2023, Volume and Issue: 14(01), P. 13 - 17

Published: May 25, 2023

Deteksi status ketahanan pangan telah menjadi aspek bahasan yang menarik di negara berkembang termasuk Indonesia, karena disadari kurangnya pendekatan atau model tepat. Makalah ini berupaya mendapatkan berbasis regresi logistik untuk analisis dan deteksi pada tingkat rumah tangga. Analisis berdasarkan data sekunder bersumber dari Badan Pusat Statistik Daerah Istimewa Yogyakarta. Probabilitas tangga rawan pangan, kurang maupun rentan terkait erat dengan kondisi kemiskinan memiliki pengaruh paling besar. Bila kita perhatikan menurut tempat tinggal, ditemukan bahwa tinggal daerah perdesaan, dapat digunakan sebagai ketidaktahanan Demikian pula tidak tanah/lahan, kawin kepala tangga, dikepalai oleh perempuan, pendidikan rendah/hanya dasar akan punya probabilitas lebih besar masuk kategori ataupun pangan. Dengan demikian peningkatan akses terhadap sangat diperlukan, terutama melalui pendapatan kualitas penduduk.

Citations

2
A Comparative Analysis of Heart Disease Prediction Using Machine Learning Approaches DOI

Khushi Khushi,

Sonia Deshmukh, Rohit Vashisht

et al.

Advances in healthcare information systems and administration book series, Journal Year: 2024, Volume and Issue: unknown, P. 31 - 45

Published: April 19, 2024

Escalating unhealthy lifestyles has led to a surge in common health diseases, notably cardiovascular ailments, leading cause of human mortality with over 17 million annual fatalities. This study focuses on conducting data analytics within the domain heart disease, which become progressively popular predictive field. The expanding availability this area further emphasizes significance in-depth analysis for comprehensive insights and informed decision-making. Diverse strategies methods have been explored by other researchers. Employing algorithms encompassing KNN, decision tree, random forest, authors prognosticate patient illnesses. support vector machine (SVM) demonstrated superior accuracy among all algorithms. research enhances disease prediction through varied algorithms, underscoring SVM's efficacy data-driven approaches addressing escalating concerns.

Language: Английский

Citations

0
Early Detection of Cardiovascular Disorders Using Enhanced ANN Model DOI

Valarmathi Krishnamoorthi,

Revanth Srinivasa Reddy B

Published: April 18, 2024

This research paper presents a study that focuses on predicting heart disease using an Artificial Neural Network (ANN), with Logistic Regression serving as the reference model. The utilizes dataset containing indicators of disease. An ANN model is then trained training data to predict in testing data. To evaluate model's performance several metrics are employed, including confusion matrix and classification report. proposed by previous literature has achieved accuracy rate 85.71% for Regression-a used method However, our surpasses this baseline achieving 94.15%. provides analysis methodology encompassing preprocessing, cross-validation, construction, procedures well evaluation techniques. results underscore capabilities signifying important avenue future research, field.

Language: Английский

Citations

0
Logistic Regression Model based on heart disease and Its Potential Influencing Factors DOI Creative Commons
Yu Qiu

Highlights in Science Engineering and Technology, Journal Year: 2023, Volume and Issue: 61, P. 88 - 97

Published: July 30, 2023

Heart disease is without doubt getting more and popular in human society. According to the statistics of World Federation, one person dies heart diseases for every 3 deaths world, number due stroke as high 17.5 million world year. In this paper, 5 potential influencing factors their data are selected construct a logistic regression model predict possibility catching so that early prevention may be achieved time. During construction model, some transformations applied predictors optimize model. end, cross-validation method used test final results show accuracy over 73%. conclusion, can briefly disease, also reveal chosen do have significant impacts on prediction.

Language: Английский

Citations

1
Classification Prediction of Heart Disease Using Machine Learning Techniques DOI

Kevis Setiawan,

Jonathan Jonathan,

Putu Satria Beratha

et al.

Published: Sept. 6, 2023

Heart disease is also called a common one of global health concerns. A lot research has been done before to predict someone whether heart or not by machine learning. In this study, we use five learning techniques as comparison which technique most accuracy recognize in someone's condition. case, are using UCI Cleveland Dataset sample and the result shows that Support Vector Machine K-Nearest Neighbor gives 85% along with many aspects respectively.

Language: Английский

Citations

1