Classification of Heart Disease Using Cluster Based DT Learning

Thirumalai, Chandrasegar; Rababah, Abdalah

doi:10.3844/jcssp.2020.50.55

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The National Inpatient Sample (NIS), a retrospective cohort study developed for the HCUP, is the largest publicly available inpatient database that covers more than 97% of the U.S. population stratified by hospital region and type of insurance[ 9 ]. The NIS consists of demographic and hospital characteristics at discharge, which are searchable using the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) and ICD-10-CM codes[ 10 ]. As the NIS is fully de-identified and public, ethics committee approval was not required in this study.…”

Section: Methodsmentioning

confidence: 99%

National trend of heart failure and other cardiovascular diseases in people living with human immunodeficiency virus

Park¹,

An²,

Romero³

et al. 2022

WJC

View full text Add to dashboard Cite

BACKGROUND As people living with human immunodeficiency virus (HIV) (PLWH) enjoy longer life expectancy with highly effective antiretroviral therapy, they are encountering challenging cardiovascular health risks. AIM To retrospectively examine the increasing burden of cardiovascular diseases in PLWH over the past decade. METHODS All hospitalizations for heart failure (HF), ischemic heart disease (IHD), and cerebrovascular disease (CeVD) in PLWH were identified using the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) and ICD-10-CM codes in the National Inpatient Sample from 2008 to 2018. Outcomes included number of hospitalizations, in-hospital mortality, length of stay, and total hospital charge. Trend of the outcomes from 2008 to 2018 were analyzed using Cochran-Armitage trend test and simple linear regression. RESULTS The number of hospitalizations for HF in PLWH increased from 4212 in 2008 to 6700 in 2018 ( P trend < 0.01). Similar increasing trend was seen with those for IHD and CeVD over the decade ( P trend < 0.01). A decreasing trend of in-hospital mortality was observed in all hospitalizations of PLWH ( P trend < 0.01) and CeVD in PLWH ( P trend < 0.01), but not in those for HF ( P trend = 0.67) and IHD ( P trend = 0.13). The trend of length of stay was decreasing in all hospitalizations of PLWH ( P trend < 0.01), but increasing in those for HF in PLWH ( P trend < 0.01). An increasing trend of total hospital charge was observed in hospitalizations for HF, IHD, and CeVD ( P trend < 0.01). CONCLUSION The burden of cardiovascular diseases has significantly increased in hospitalizations of PLWH from 2008 to 2018. Continued efforts are needed to address the additional cardiovascular risks in this vulnerable population.

show abstract

Section: Methodsmentioning

confidence: 99%

National trend of heart failure and other cardiovascular diseases in people living with human immunodeficiency virus

Park¹,

An²,

Romero³

et al. 2022

WJC

View full text Add to dashboard Cite

show abstract

“…Channabasavaraju and Vinayakamurthy (2020) used Random Forest Feature Selection (RFS) strategy to extract features from the UCI dataset to improve the prediction accuracy of heart disease. Santhi and Renuka, 2020 used Cluster-based Disease Diagnosis (CDD) with different ML classifiers and UCI datasets to predict cardiac diseases (Mohan et al, 2020). Many other research works (Rajalakshmi and Madhav, 2019;Elsayad and Fakhr, 2015) used various ML techniques and datasets to detect CVD with limited accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Cardiovascular Disease Prediction through Ensembled Transfer Learning on Cardiac Magnetic Resonance Imaging

Cyriac¹,

Sivakumar²,

Raju³

2022

Journal of Computer Science

View full text Add to dashboard Cite

Cardiovascular Diseases (CVD) cause more deaths worldwide than most of the other diseases. The diagnosis of cardiovascular disease from Magnetic Resonance Imaging plays a major role in the medical field. The technological revolution contributed a lot to increase the effectiveness of CVD diagnosis. Many Artificial Intelligence methods using Deep Learning models are available to assist the cardiologist in the diagnosis of CVD from Magnetic Resonance Imaging (MRI). In this study, we leverage on the merits of deep learning, transfer learning, and ensemble voting to improve the accuracy of Artificial Intelligence-based CVD detection. VGG16, MobileNetV2, and InceptionV3, trained on ImageNet, are the models used and the dataset is the Automatic Cardiac Diagnosis Challenge dataset. We customized the classification layers of all three models to suit the CVD detection problem. The results from these models are ensembled using the soft-voting and hard-voting approaches. Test accuracies obtained are 97.94% and 98.08% from hard-voting and soft-voting respectively. The experimental results demonstrated that the ensemble of outputs from transfer learning-based Deep Learning models produces much improved results for CVD diagnosis from MRI images.

show abstract

Classification of Heart Disease Using Cluster Based DT Learning

Cited by 2 publications

References 4 publications

National trend of heart failure and other cardiovascular diseases in people living with human immunodeficiency virus

National trend of heart failure and other cardiovascular diseases in people living with human immunodeficiency virus

Cardiovascular Disease Prediction through Ensembled Transfer Learning on Cardiac Magnetic Resonance Imaging

Contact Info

Product

Resources

About