Distribution of ECG samples in the dataset.
<div><p>Cardiovascular diseases (CVDs) have surpassed cancer and become the major cause of death worldwide. An electrocardiogram (ECG) is a non-invasive and quicker method for diagnosing abnormal heart conditions. While research has extensively focused on ECG analysis for disease classif...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852019445913878528 |
|---|---|
| author | Rida Nayyab (21519512) |
| author2 | Asim Waris (16892236) Iqra Zaheer (9377851) Muhammad Jawad Khan (6909224) Fawwaz Hazzazi (11902912) Muhammad Adeel Ijaz (21273116) Hassan Ashraf (13505653) Syed Omer Gilani (21273113) |
| author2_role | author author author author author author author |
| author_facet | Rida Nayyab (21519512) Asim Waris (16892236) Iqra Zaheer (9377851) Muhammad Jawad Khan (6909224) Fawwaz Hazzazi (11902912) Muhammad Adeel Ijaz (21273116) Hassan Ashraf (13505653) Syed Omer Gilani (21273113) |
| author_role | author |
| dc.creator.none.fl_str_mv | Rida Nayyab (21519512) Asim Waris (16892236) Iqra Zaheer (9377851) Muhammad Jawad Khan (6909224) Fawwaz Hazzazi (11902912) Muhammad Adeel Ijaz (21273116) Hassan Ashraf (13505653) Syed Omer Gilani (21273113) |
| dc.date.none.fl_str_mv | 2025-06-10T17:42:37Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0325358.g002 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Distribution_of_ECG_samples_in_the_dataset_/29283950 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Physiology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified four abnormal classes discrete wavelet transform deep neural network deep learning techniques convolutional neural network butterworth bandpass filter deep learning models one key finding subsequent morphological features e ., p detailed classification models mi ), hypertrophy dnn model achieved cnn model achieved models classified one normal unique labels surpassed cancer study utilises study demonstrates sttc ). robust method quicker method precise multi performance metrics major cause hyp ), future real fold cross feature set f1 score extensively focused extensive ptb disease classification dire need death worldwide consistently classified conduction disturbance clean signal balanced using |
| dc.title.none.fl_str_mv | Distribution of ECG samples in the dataset. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Cardiovascular diseases (CVDs) have surpassed cancer and become the major cause of death worldwide. An electrocardiogram (ECG) is a non-invasive and quicker method for diagnosing abnormal heart conditions. While research has extensively focused on ECG analysis for disease classification, it has been primarily directed toward binary classification or classification of Arrhythmias, highlighting the dire need for detailed classification models. This study utilises the extensive PTB-XL database ECG records to develop a robust method for classifying various heart abnormalities. The data with unique labels is filtered through the Butterworth bandpass filter and Discrete Wavelet Transform (DWT) db-8. The R-peaks of the clean signal were used to detect the subsequent morphological features, i.e., P-QRS-T intervals and amplitudes. The feature set was balanced using the Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC) and fed into Convolutional Neural Network (CNN) and Deep Neural Network (DNN) with 5-fold cross-validation. The models classified the ECG records into one normal and four abnormal classes: Conduction Disturbance (CD), Myocardial Infarction (MI), Hypertrophy (HYP), and ST-T Changes (STTC). Performance metrics such as F1 score, recall, precision, and accuracy were evaluated for each model. The CNN model achieved a mean accuracy of 81% ± 0.03, while the DNN model achieved a mean accuracy of 84% ± 0.01. One key finding is that Hypertrophy (HYP) was consistently classified with up to 98% accuracy. Thus, the study demonstrates the effectiveness of combining advanced signal processing and deep learning techniques for precise multi-class heart disease classification using P-QRS-T features, paving the way for future real-time clinical applications.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_7aec4e6ea8bfd143bef8611ae602d844 |
| identifier_str_mv | 10.1371/journal.pone.0325358.g002 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/29283950 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Distribution of ECG samples in the dataset.Rida Nayyab (21519512)Asim Waris (16892236)Iqra Zaheer (9377851)Muhammad Jawad Khan (6909224)Fawwaz Hazzazi (11902912)Muhammad Adeel Ijaz (21273116)Hassan Ashraf (13505653)Syed Omer Gilani (21273113)MedicinePhysiologyCancerSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedfour abnormal classesdiscrete wavelet transformdeep neural networkdeep learning techniquesconvolutional neural networkbutterworth bandpass filterdeep learning modelsone key findingsubsequent morphological featurese ., pdetailed classification modelsmi ), hypertrophydnn model achievedcnn model achievedmodels classifiedone normalunique labelssurpassed cancerstudy utilisesstudy demonstratessttc ).robust methodquicker methodprecise multiperformance metricsmajor causehyp ),future realfold crossfeature setf1 scoreextensively focusedextensive ptbdisease classificationdire needdeath worldwideconsistently classifiedconduction disturbanceclean signalbalanced using<div><p>Cardiovascular diseases (CVDs) have surpassed cancer and become the major cause of death worldwide. An electrocardiogram (ECG) is a non-invasive and quicker method for diagnosing abnormal heart conditions. While research has extensively focused on ECG analysis for disease classification, it has been primarily directed toward binary classification or classification of Arrhythmias, highlighting the dire need for detailed classification models. This study utilises the extensive PTB-XL database ECG records to develop a robust method for classifying various heart abnormalities. The data with unique labels is filtered through the Butterworth bandpass filter and Discrete Wavelet Transform (DWT) db-8. The R-peaks of the clean signal were used to detect the subsequent morphological features, i.e., P-QRS-T intervals and amplitudes. The feature set was balanced using the Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC) and fed into Convolutional Neural Network (CNN) and Deep Neural Network (DNN) with 5-fold cross-validation. The models classified the ECG records into one normal and four abnormal classes: Conduction Disturbance (CD), Myocardial Infarction (MI), Hypertrophy (HYP), and ST-T Changes (STTC). Performance metrics such as F1 score, recall, precision, and accuracy were evaluated for each model. The CNN model achieved a mean accuracy of 81% ± 0.03, while the DNN model achieved a mean accuracy of 84% ± 0.01. One key finding is that Hypertrophy (HYP) was consistently classified with up to 98% accuracy. Thus, the study demonstrates the effectiveness of combining advanced signal processing and deep learning techniques for precise multi-class heart disease classification using P-QRS-T features, paving the way for future real-time clinical applications.</p></div>2025-06-10T17:42:37ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0325358.g002https://figshare.com/articles/figure/Distribution_of_ECG_samples_in_the_dataset_/29283950CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/292839502025-06-10T17:42:37Z |
| spellingShingle | Distribution of ECG samples in the dataset. Rida Nayyab (21519512) Medicine Physiology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified four abnormal classes discrete wavelet transform deep neural network deep learning techniques convolutional neural network butterworth bandpass filter deep learning models one key finding subsequent morphological features e ., p detailed classification models mi ), hypertrophy dnn model achieved cnn model achieved models classified one normal unique labels surpassed cancer study utilises study demonstrates sttc ). robust method quicker method precise multi performance metrics major cause hyp ), future real fold cross feature set f1 score extensively focused extensive ptb disease classification dire need death worldwide consistently classified conduction disturbance clean signal balanced using |
| status_str | publishedVersion |
| title | Distribution of ECG samples in the dataset. |
| title_full | Distribution of ECG samples in the dataset. |
| title_fullStr | Distribution of ECG samples in the dataset. |
| title_full_unstemmed | Distribution of ECG samples in the dataset. |
| title_short | Distribution of ECG samples in the dataset. |
| title_sort | Distribution of ECG samples in the dataset. |
| topic | Medicine Physiology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified four abnormal classes discrete wavelet transform deep neural network deep learning techniques convolutional neural network butterworth bandpass filter deep learning models one key finding subsequent morphological features e ., p detailed classification models mi ), hypertrophy dnn model achieved cnn model achieved models classified one normal unique labels surpassed cancer study utilises study demonstrates sttc ). robust method quicker method precise multi performance metrics major cause hyp ), future real fold cross feature set f1 score extensively focused extensive ptb disease classification dire need death worldwide consistently classified conduction disturbance clean signal balanced using |