Improved heart disease detection from ECG signal using deep learning based ensemble model

Rath, Adyasha; Mishra, Debahuti; Panda, Ganapati; Satapathy, Suresh Chandra; Xia, Kaijian

doi:10.1016/j.suscom.2022.100732

Cited by 16 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the features that we depend on greatly affect the final efficiency of the model, so more than one method must be applied to choose the essential features and then choose among them the best algorithm that gives the best efficiency. 5) Self Organizing Maps (SOMs): Adisha Rath et al [31] developed a new method for predicting HF based on the electrocardiogram (ECG) using the PTB and MIT datasets. More than one DL model was tested, and based on the results, it turned out that SOM with an autoencoder gave the best results on the two datasets.…”

Section: ) Generative Adversarial Network (Gans)mentioning

confidence: 99%

A Comparative Study Of Artificial Intelligence Techniques For Categorization And Prediction Of Heart Diseases

رضا رشوان,

الفنجري,

عزام

2024

النشرة المعلوماتية في الحاسبات والمعلومات

View full text Add to dashboard Cite

Heart failure (HF) is one of the most common diseases in recent years, and a large number of people die annually around the world from it. The heart is considered one of the most important organs in the human body, so it requires high accuracy when predicting the presence of heart disease or not, as an error in prediction may cause human death, so it requires a high-accuracy method in predicting HF. Artificial intelligence (AI) plays a large and important role in many fields today, especially in the medical field, as AI helps doctors obtain a quick and accurate diagnosis of the patient's condition, which contributes to saving time during the diagnosis. It is important to predict HF using AI to help with rapid and accurate diagnosis and thus reduce the number of deaths from this disease. AI techniques increase the accuracy of predicting whether or not HF is present compared to traditional methods. Also, in rural areas where there are fewer physicians, it is very important to provide such technologies to aid in diagnosis. Many studies point to new AI-based HF prediction techniques. These technologies relied on different algorithms and datasets of different sizes and types. Each of these technologies has advantages and limitations. Therefore, this paper presents an illustrative study of the most advanced AI methods for HF prediction. This study also included a comparison between the different methods based on the most famous standards.

show abstract

Section: ) Generative Adversarial Network (Gans)mentioning

confidence: 99%

A Comparative Study Of Artificial Intelligence Techniques For Categorization And Prediction Of Heart Diseases

رضا رشوان,

الفنجري,

عزام

2024

النشرة المعلوماتية في الحاسبات والمعلومات

View full text Add to dashboard Cite

show abstract

“…An ensemble of random forest and support vector machine is implemented in [28], to classify five types of cardiac arrhythmia's and obtained an accuracy of 98.21%. Recent advances in technology proposed deep learning-based ensemble classification technique for improved cardiac diagnosis [29]. Experimentation is carried out on PTBDB and MITBIH database and found an accuracy, F1 score and area under curve (AUC) of 0.98, 0.93 and 0.92 for MITBIH datasets and 0.99, 0.986 and 0.995 for PTB dataset.…”

Section: Motivation Towards Ensemble Learningmentioning

confidence: 99%

An Outlier Detection and Feature Ranking based Ensemble Learning for ECG Analysis

Ardeti¹,

Kolluru²,

Varghese³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Automated classification of each heartbeat class from the ECG signal is important to diagnose cardiovascular diseases (CVDs) more quickly. ECG data acquired from the realtime or clinical databases contains exceptional values or extreme values called outliers. The separation and removal of outliers is very much useful for improving the data quality. The presence of outliers will influence the results of machine learning (ML) methods such as classification and regression. Outlier identification and removal plays a significant role in this area of research and is a part of signal denoising. Also, most of the traditional ECG-signal processing methods are facing the difficulty in finding the essential key features of recorded signal. In this work, an extreme outlier detection technique known as improved inter quartile range (IIQR) filtering method is used to find the outliers of the signal for the feature ranking process. In addition, an optimized random forest (ORF) based heterogenous ensemble classification model is proposed to improve the true positive and runtime on the ECG data. The classification of each heartbeat type is classified with majority voting technique. Ensemble learning and majority voting rule is used to enhance the accuracy of heart disease prediction. The proposed feature ranking based ORF ensemble classification model (LR + SVM + ORF + XGBoost + KNN) is evaluated on the MITBIH arrhythmia database and produces an overall accuracy of 99.45% which significantly outperforms the state-of-the-art methods such as, (LR + SVM + RF + XGBoost + KNN) with 96.17% accuracy, ensemble deep learning accuracy of 95.81% and ensemble SVM accuracy of 94.47%.

show abstract

“…Recent technological advances have helped identify medical conditions [1,2] and treat them. Rapid advances have been made in detecting cardiovascular diseases [3], Parkinson's disease from gait [4], sensing and treating myocardial infarction [5] and more applications like identifying the fall of old adults by a variety of methods [6,7].…”

Section: Introductionmentioning

confidence: 99%

A Novel Computationally Efficient Approach to Identify Visually Interpretable Medical Conditions from 2D Skeletal Data

Jesudhas¹,

Raghuveera²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Timely identification and treatment of medical conditions could facilitate faster recovery and better health. Existing systems address this issue using custom-built sensors, which are invasive and difficult to generalize. A low-complexity scalable process is proposed to detect and identify medical conditions from 2D skeletal movements on video feed data. Minimal set of features relevant to distinguish medical conditions: AMF, PVF and GDF are derived from skeletal data on sampled frames across the entire action. The AMF (angular motion features) are derived to capture the angular motion of limbs during a specific action. The relative position of joints is represented by PVF (positional variation features). GDF (global displacement features) identifies the direction of overall skeletal movement. The discriminative capability of these features is illustrated by their variance across time for different actions. The classification of medical conditions is approached in two stages. In the first stage, a low-complexity binary LSTM classifier is trained to distinguish visual medical conditions from general human actions. As part of stage 2, a multi-class LSTM classifier is trained to identify the exact medical condition from a given set of visually interpretable medical conditions. The proposed features are extracted from the 2D skeletal data of NTU RGB + D and then used to train the binary and multi-class LSTM classifiers. The binary and multi-class classifiers observed average F1 scores of 77% and 73%, respectively, while the overall system produced an average F1 score of 69% and a weighted average F1 score of 80%. The multi-class classifier is found to utilize 10 to 100 times fewer parameters than existing 2D CNN-based models while producing similar levels of accuracy.

show abstract

Improved heart disease detection from ECG signal using deep learning based ensemble model

Cited by 16 publications

References 37 publications

A Comparative Study Of Artificial Intelligence Techniques For Categorization And Prediction Of Heart Diseases

A Comparative Study Of Artificial Intelligence Techniques For Categorization And Prediction Of Heart Diseases

An Outlier Detection and Feature Ranking based Ensemble Learning for ECG Analysis

A Novel Computationally Efficient Approach to Identify Visually Interpretable Medical Conditions from 2D Skeletal Data

Contact Info

Product

Resources

About