Journal of Clinical and Diagnostic Research, ISSN - 0973 - 709X

Users Online : 108513

AbstractMaterial and MethodsResultsDiscussionConclusionReferencesDOI and Others
Article in PDF How to Cite Citation Manager Readers' Comments (0) Audio Visual Article Statistics Link to PUBMED Print this Article Send to a Friend
Advertisers Access Statistics Resources

Dr Mohan Z Mani

"Thank you very much for having published my article in record time.I would like to compliment you and your entire staff for your promptness, courtesy, and willingness to be customer friendly, which is quite unusual.I was given your reference by a colleague in pathology,and was able to directly phone your editorial office for clarifications.I would particularly like to thank the publication managers and the Assistant Editor who were following up my article. I would also like to thank you for adjusting the money I paid initially into payment for my modified article,and refunding the balance.
I wish all success to your journal and look forward to sending you any suitable similar article in future"



Dr Mohan Z Mani,
Professor & Head,
Department of Dermatolgy,
Believers Church Medical College,
Thiruvalla, Kerala
On Sep 2018




Prof. Somashekhar Nimbalkar

"Over the last few years, we have published our research regularly in Journal of Clinical and Diagnostic Research. Having published in more than 20 high impact journals over the last five years including several high impact ones and reviewing articles for even more journals across my fields of interest, we value our published work in JCDR for their high standards in publishing scientific articles. The ease of submission, the rapid reviews in under a month, the high quality of their reviewers and keen attention to the final process of proofs and publication, ensure that there are no mistakes in the final article. We have been asked clarifications on several occasions and have been happy to provide them and it exemplifies the commitment to quality of the team at JCDR."



Prof. Somashekhar Nimbalkar
Head, Department of Pediatrics, Pramukhswami Medical College, Karamsad
Chairman, Research Group, Charutar Arogya Mandal, Karamsad
National Joint Coordinator - Advanced IAP NNF NRP Program
Ex-Member, Governing Body, National Neonatology Forum, New Delhi
Ex-President - National Neonatology Forum Gujarat State Chapter
Department of Pediatrics, Pramukhswami Medical College, Karamsad, Anand, Gujarat.
On Sep 2018




Dr. Kalyani R

"Journal of Clinical and Diagnostic Research is at present a well-known Indian originated scientific journal which started with a humble beginning. I have been associated with this journal since many years. I appreciate the Editor, Dr. Hemant Jain, for his constant effort in bringing up this journal to the present status right from the scratch. The journal is multidisciplinary. It encourages in publishing the scientific articles from postgraduates and also the beginners who start their career. At the same time the journal also caters for the high quality articles from specialty and super-specialty researchers. Hence it provides a platform for the scientist and researchers to publish. The other aspect of it is, the readers get the information regarding the most recent developments in science which can be used for teaching, research, treating patients and to some extent take preventive measures against certain diseases. The journal is contributing immensely to the society at national and international level."



Dr Kalyani R
Professor and Head
Department of Pathology
Sri Devaraj Urs Medical College
Sri Devaraj Urs Academy of Higher Education and Research , Kolar, Karnataka
On Sep 2018




Dr. Saumya Navit

"As a peer-reviewed journal, the Journal of Clinical and Diagnostic Research provides an opportunity to researchers, scientists and budding professionals to explore the developments in the field of medicine and dentistry and their varied specialities, thus extending our view on biological diversities of living species in relation to medicine.
‘Knowledge is treasure of a wise man.’ The free access of this journal provides an immense scope of learning for the both the old and the young in field of medicine and dentistry as well. The multidisciplinary nature of the journal makes it a better platform to absorb all that is being researched and developed. The publication process is systematic and professional. Online submission, publication and peer reviewing makes it a user-friendly journal.
As an experienced dentist and an academician, I proudly recommend this journal to the dental fraternity as a good quality open access platform for rapid communication of their cutting-edge research progress and discovery.
I wish JCDR a great success and I hope that journal will soar higher with the passing time."



Dr Saumya Navit
Professor and Head
Department of Pediatric Dentistry
Saraswati Dental College
Lucknow
On Sep 2018




Dr. Arunava Biswas

"My sincere attachment with JCDR as an author as well as reviewer is a learning experience . Their systematic approach in publication of article in various categories is really praiseworthy.
Their prompt and timely response to review's query and the manner in which they have set the reviewing process helps in extracting the best possible scientific writings for publication.
It's a honour and pride to be a part of the JCDR team. My very best wishes to JCDR and hope it will sparkle up above the sky as a high indexed journal in near future."



Dr. Arunava Biswas
MD, DM (Clinical Pharmacology)
Assistant Professor
Department of Pharmacology
Calcutta National Medical College & Hospital , Kolkata




Dr. C.S. Ramesh Babu
" Journal of Clinical and Diagnostic Research (JCDR) is a multi-specialty medical and dental journal publishing high quality research articles in almost all branches of medicine. The quality of printing of figures and tables is excellent and comparable to any International journal. An added advantage is nominal publication charges and monthly issue of the journal and more chances of an article being accepted for publication. Moreover being a multi-specialty journal an article concerning a particular specialty has a wider reach of readers of other related specialties also. As an author and reviewer for several years I find this Journal most suitable and highly recommend this Journal."
Best regards,
C.S. Ramesh Babu,
Associate Professor of Anatomy,
Muzaffarnagar Medical College,
Muzaffarnagar.
On Aug 2018




Dr. Arundhathi. S
"Journal of Clinical and Diagnostic Research (JCDR) is a reputed peer reviewed journal and is constantly involved in publishing high quality research articles related to medicine. Its been a great pleasure to be associated with this esteemed journal as a reviewer and as an author for a couple of years. The editorial board consists of many dedicated and reputed experts as its members and they are doing an appreciable work in guiding budding researchers. JCDR is doing a commendable job in scientific research by promoting excellent quality research & review articles and case reports & series. The reviewers provide appropriate suggestions that improve the quality of articles. I strongly recommend my fraternity to encourage JCDR by contributing their valuable research work in this widely accepted, user friendly journal. I hope my collaboration with JCDR will continue for a long time".



Dr. Arundhathi. S
MBBS, MD (Pathology),
Sanjay Gandhi institute of trauma and orthopedics,
Bengaluru.
On Aug 2018




Dr. Mamta Gupta,
"It gives me great pleasure to be associated with JCDR, since last 2-3 years. Since then I have authored, co-authored and reviewed about 25 articles in JCDR. I thank JCDR for giving me an opportunity to improve my own skills as an author and a reviewer.
It 's a multispecialty journal, publishing high quality articles. It gives a platform to the authors to publish their research work which can be available for everyone across the globe to read. The best thing about JCDR is that the full articles of all medical specialties are available as pdf/html for reading free of cost or without institutional subscription, which is not there for other journals. For those who have problem in writing manuscript or do statistical work, JCDR comes for their rescue.
The journal has a monthly publication and the articles are published quite fast. In time compared to other journals. The on-line first publication is also a great advantage and facility to review one's own articles before going to print. The response to any query and permission if required, is quite fast; this is quite commendable. I have a very good experience about seeking quick permission for quoting a photograph (Fig.) from a JCDR article for my chapter authored in an E book. I never thought it would be so easy. No hassles.
Reviewing articles is no less a pain staking process and requires in depth perception, knowledge about the topic for review. It requires time and concentration, yet I enjoy doing it. The JCDR website especially for the reviewers is quite user friendly. My suggestions for improving the journal is, more strict review process, so that only high quality articles are published. I find a a good number of articles in Obst. Gynae, hence, a new journal for this specialty titled JCDR-OG can be started. May be a bimonthly or quarterly publication to begin with. Only selected articles should find a place in it.
An yearly reward for the best article authored can also incentivize the authors. Though the process of finding the best article will be not be very easy. I do not know how reviewing process can be improved. If an article is being reviewed by two reviewers, then opinion of one can be communicated to the other or the final opinion of the editor can be communicated to the reviewer if requested for. This will help one’s reviewing skills.
My best wishes to Dr. Hemant Jain and all the editorial staff of JCDR for their untiring efforts to bring out this journal. I strongly recommend medical fraternity to publish their valuable research work in this esteemed journal, JCDR".



Dr. Mamta Gupta
Consultant
(Ex HOD Obs &Gynae, Hindu Rao Hospital and associated NDMC Medical College, Delhi)
Aug 2018




Dr. Rajendra Kumar Ghritlaharey

"I wish to thank Dr. Hemant Jain, Editor-in-Chief Journal of Clinical and Diagnostic Research (JCDR), for asking me to write up few words.
Writing is the representation of language in a textual medium i e; into the words and sentences on paper. Quality medical manuscript writing in particular, demands not only a high-quality research, but also requires accurate and concise communication of findings and conclusions, with adherence to particular journal guidelines. In medical field whether working in teaching, private, or in corporate institution, everyone wants to excel in his / her own field and get recognised by making manuscripts publication.


Authors are the souls of any journal, and deserve much respect. To publish a journal manuscripts are needed from authors. Authors have a great responsibility for producing facts of their work in terms of number and results truthfully and an individual honesty is expected from authors in this regards. Both ways its true "No authors-No manuscripts-No journals" and "No journals–No manuscripts–No authors". Reviewing a manuscript is also a very responsible and important task of any peer-reviewed journal and to be taken seriously. It needs knowledge on the subject, sincerity, honesty and determination. Although the process of reviewing a manuscript is a time consuming task butit is expected to give one's best remarks within the time frame of the journal.
Salient features of the JCDR: It is a biomedical, multidisciplinary (including all medical and dental specialities), e-journal, with wide scope and extensive author support. At the same time, a free text of manuscript is available in HTML and PDF format. There is fast growing authorship and readership with JCDR as this can be judged by the number of articles published in it i e; in Feb 2007 of its first issue, it contained 5 articles only, and now in its recent volume published in April 2011, it contained 67 manuscripts. This e-journal is fulfilling the commitments and objectives sincerely, (as stated by Editor-in-chief in his preface to first edition) i e; to encourage physicians through the internet, especially from the developing countries who witness a spectrum of disease and acquire a wealth of knowledge to publish their experiences to benefit the medical community in patients care. I also feel that many of us have work of substance, newer ideas, adequate clinical materials but poor in medical writing and hesitation to submit the work and need help. JCDR provides authors help in this regards.
Timely publication of journal: Publication of manuscripts and bringing out the issue in time is one of the positive aspects of JCDR and is possible with strong support team in terms of peer reviewers, proof reading, language check, computer operators, etc. This is one of the great reasons for authors to submit their work with JCDR. Another best part of JCDR is "Online first Publications" facilities available for the authors. This facility not only provides the prompt publications of the manuscripts but at the same time also early availability of the manuscripts for the readers.
Indexation and online availability: Indexation transforms the journal in some sense from its local ownership to the worldwide professional community and to the public.JCDR is indexed with Embase & EMbiology, Google Scholar, Index Copernicus, Chemical Abstracts Service, Journal seek Database, Indian Science Abstracts, to name few of them. Manuscriptspublished in JCDR are available on major search engines ie; google, yahoo, msn.
In the era of fast growing newer technologies, and in computer and internet friendly environment the manuscripts preparation, submission, review, revision, etc and all can be done and checked with a click from all corer of the world, at any time. Of course there is always a scope for improvement in every field and none is perfect. To progress, one needs to identify the areas of one's weakness and to strengthen them.
It is well said that "happy beginning is half done" and it fits perfectly with JCDR. It has grown considerably and I feel it has already grown up from its infancy to adolescence, achieving the status of standard online e-journal form Indian continent since its inception in Feb 2007. This had been made possible due to the efforts and the hard work put in it. The way the JCDR is improving with every new volume, with good quality original manuscripts, makes it a quality journal for readers. I must thank and congratulate Dr Hemant Jain, Editor-in-Chief JCDR and his team for their sincere efforts, dedication, and determination for making JCDR a fast growing journal.
Every one of us: authors, reviewers, editors, and publisher are responsible for enhancing the stature of the journal. I wish for a great success for JCDR."



Thanking you
With sincere regards
Dr. Rajendra Kumar Ghritlaharey, M.S., M. Ch., FAIS
Associate Professor,
Department of Paediatric Surgery, Gandhi Medical College & Associated
Kamla Nehru & Hamidia Hospitals Bhopal, Madhya Pradesh 462 001 (India)
E-mail: drrajendrak1@rediffmail.com
On May 11,2011




Dr. Shankar P.R.

"On looking back through my Gmail archives after being requested by the journal to write a short editorial about my experiences of publishing with the Journal of Clinical and Diagnostic Research (JCDR), I came across an e-mail from Dr. Hemant Jain, Editor, in March 2007, which introduced the new electronic journal. The main features of the journal which were outlined in the e-mail were extensive author support, cash rewards, the peer review process, and other salient features of the journal.
Over a span of over four years, we (I and my colleagues) have published around 25 articles in the journal. In this editorial, I plan to briefly discuss my experiences of publishing with JCDR and the strengths of the journal and to finally address the areas for improvement.
My experiences of publishing with JCDR: Overall, my experiences of publishing withJCDR have been positive. The best point about the journal is that it responds to queries from the author. This may seem to be simple and not too much to ask for, but unfortunately, many journals in the subcontinent and from many developing countries do not respond or they respond with a long delay to the queries from the authors 1. The reasons could be many, including lack of optimal secretarial and other support. Another problem with many journals is the slowness of the review process. Editorial processing and peer review can take anywhere between a year to two years with some journals. Also, some journals do not keep the contributors informed about the progress of the review process. Due to the long review process, the articles can lose their relevance and topicality. A major benefit with JCDR is the timeliness and promptness of its response. In Dr Jain's e-mail which was sent to me in 2007, before the introduction of the Pre-publishing system, he had stated that he had received my submission and that he would get back to me within seven days and he did!
Most of the manuscripts are published within 3 to 4 months of their submission if they are found to be suitable after the review process. JCDR is published bimonthly and the accepted articles were usually published in the next issue. Recently, due to the increased volume of the submissions, the review process has become slower and it ?? Section can take from 4 to 6 months for the articles to be reviewed. The journal has an extensive author support system and it has recently introduced a paid expedited review process. The journal also mentions the average time for processing the manuscript under different submission systems - regular submission and expedited review.
Strengths of the journal: The journal has an online first facility in which the accepted manuscripts may be published on the website before being included in a regular issue of the journal. This cuts down the time between their acceptance and the publication. The journal is indexed in many databases, though not in PubMed. The editorial board should now take steps to index the journal in PubMed. The journal has a system of notifying readers through e-mail when a new issue is released. Also, the articles are available in both the HTML and the PDF formats. I especially like the new and colorful page format of the journal. Also, the access statistics of the articles are available. The prepublication and the manuscript tracking system are also helpful for the authors.
Areas for improvement: In certain cases, I felt that the peer review process of the manuscripts was not up to international standards and that it should be strengthened. Also, the number of manuscripts in an issue is high and it may be difficult for readers to go through all of them. The journal can consider tightening of the peer review process and increasing the quality standards for the acceptance of the manuscripts. I faced occasional problems with the online manuscript submission (Pre-publishing) system, which have to be addressed.
Overall, the publishing process with JCDR has been smooth, quick and relatively hassle free and I can recommend other authors to consider the journal as an outlet for their work."



Dr. P. Ravi Shankar
KIST Medical College, P.O. Box 14142, Kathmandu, Nepal.
E-mail: ravi.dr.shankar@gmail.com
On April 2011
Anuradha

Dear team JCDR, I would like to thank you for the very professional and polite service provided by everyone at JCDR. While i have been in the field of writing and editing for sometime, this has been my first attempt in publishing a scientific paper.Thank you for hand-holding me through the process.


Dr. Anuradha
E-mail: anuradha2nittur@gmail.com
On Jan 2020

Important Notice

Original article / research
Year : 2022 | Month : November | Volume : 16 | Issue : 11 | Page : KC12 - KC16 Full Version

Bidirectional Recurrent Neural Network based Early Prediction of Cardiovascular Diseases using Electrocardiogram Signals for Type 2 Diabetic Patients


Published: November 1, 2022 | DOI: https://doi.org/10.7860/JCDR/2022/55951.17154
T Tamilselvan, Om Prakash Sharma

1. Research Scholor, School of Information Technology, Shri Ramasamy Memorial University, Gangtok, Sikkim, India. 2. Assistant Professor, School of Information Technology, Shri Ramasamy Memorial University, Gangtok, Sikkim, India.

Correspondence Address :
T Tamilselvan,
5th Mile, Tadong East, Gangtok, Sikkim, India.
E-mail: tamilselvan.t@srmus.edu.in

Abstract

Introduction: The electrocardiogram (ECG) signal is important for early diagnosis of heart abnormalities. Type 2 diabetic individuals’ ECG signals provide pertinent data about their heart and are one of the most important diagnostic techniques used by doctors to identify Cardiovascular Disease (CVD). Bidirectional Recurrent Neural Network (RNN) classifies the features linked to normal and abnormal stage ECG signal.

Aim: To analyse ECG signals of type 2 diabetic patients for early prediction of CVDs using feature extraction and bidirectional RNN based classification.

Materials and Methods: This was a secondary data-based modelling study at Shri Ramasamy Memorial University Sikkim, India from December 2020 to January 2022. Different noises were removed by hybrid preprocessing filter made up of a Median and Savitzky-Golay filter. Undecimated Dual Tree Complex Wavelet Transform (UDTCWT) along with Detrended fluctuation (DA) analysis and Empirical Orthogonal Function (EOF) analysis were then used to extract features. These features were classified with Bidirectional RNN.

Results: The proposed method was tested on the MIT-BIH, Physionet and DICARDIA databases, and the findings showed that it achieves an average accuracy of 97.6% when compared to the conventional techniques.

Conclusion: The proposed method proves to be the most effective way for detecting anomalies in ECG signals in both the early and pathological stages. This method is also effective to diagnose the early intervention of cardiovascular symptoms.

Keywords

Median and savitzky-golay filter, Undecimated dual tree complex wavelet transform

Heart monitoring has become an essential diagnosis for human health as the heart is amongst the most fundamental systems of the human body. The most significant information about the heart’s health comes from an ECG analysis (1). An irregular ECG can cause atrial fibrillation, tachycardia, low blood pressure, and fast atrial fibrillation, all of which can lead to cardiac illness, such as prolonged ventricular tachycardia and Cardiovascular Diseases (CVDs). Stroke and heart failure are also more likely in people with type 2 diabetes. These illnesses are life-threatening and require immediate medical help (2).

The electrical activity of the heart is indicated by the ECG signal. To diagnose a cardiac problem, variations in the amplitude and duration of the ECG signal from a preset pattern have been widely used. The ECG signal is separated into several distinct waveforms, including P, QRS, and T waves in that order, as well as portions called PR, QT, and ST (3). Each component has a unique role and provides predictive data for different heart conditions. ECGs are typically recorded with twelve leads, however other numbers of leads are utilised to evaluate cardiovascular disorders. Due to the difficulties of manually interpreting these fluctuations, a computer-aided diagnosis system can assist in cardiac health monitoring. Non linear extraction methods are attractive candidates for obtaining information from the ECG signal because of its non linear and non stationary character (4).

Several approaches based on transform domain-based feature extraction in ECG signal have been proposed (5),(6),(7). The effectiveness of monitoring for CVDs in non pathological diabetic people has recently been addressed (8),(9). For the categorisation of ECG signals, neural network-based models have been developed (10).

Principal component analysis approaches have been used to detect heart rate variability for the analysis of CVDs (11). K-Means clustering using squared Euclidean distance-based methods have been employed for ECG signal processing (12). By detecting features like P, QRS complex from ECG data, analysis and characterisation of normal and abnormal ECG patterns gets higher performance (13). Time domain and frequency domain based features are extracted from the ECG signal for CVD analysis (14). It has been proposed to use a pulse oximeter signal to check for the beginning of type-2 diabetes (15). Machine learning based approaches have been utilised for categorising features from ECG signal (16).

Existing methods have the issue of classifying the ECG signal into normal and abnormal. To overcome this issue the proposed method implements the hybrid preprocessing filter with fused features been classified with bidirectional RNN to detect the early stage and abnormal stage of ECG signal prediction. By analysing the ECG signal features several times, the bidirectional RNN classifies the features linked to early stage and abnormal stage ECG signal in an ideal manner, ensuring correct signal analysis. The proposed work analyses type 2 diabetics ECG data using feature extraction and Bi-RNN based classification. The main objective was to evaluate the predictive significance of ECG abnormalities in Type 2 diabetes mellitus patients without a history of cardiovascular illness.

Material and Methods

This was a secondary data-based modelling study. The secondary data as depicted in (Table/Fig 1) shows the ethically approved observational study been taken from different sources, Diabetic Cardiac Neuropathy Diagnostic and Modelling Database Signals (DICARDIA) (17),(18), Physionet PTB Diagnostic ECG database (19). The study was done at Shri Ramasamy Memorial University Sikkim, India for a period of 1.2 years from December 10, 2020 to January 2022. Since there was no human or animals being used and the modelling done purely based on secondary public domain, no ethical clearance was needed for the same. The study was duly approved by Institutional Research Cell vide Ref. SRMUS/PhD/EC/IT/2022/1.

Data Description

The collected dataset was the combination of three popular widely available dataset like Diabetic Cardiac Neuropathy Diagnostic and Modelling Database Signals (DICARDIA), physionet PTB Diagnostic ECG database and MIT-BIH Arrhythmia Database. (Table/Fig 1) shows the collected database details for diabetics with and without cardiac complications, resolution, frequency and the ECG signal recording characteristics (18),(19),(20).

Inclusion criteria:

• ECG database that were free available as secondary ECG datasets.
• ECG of diabetic patients with and without cardiac complications.
• Only Type 2 diabetic patients ECG signals datasets.

Exclusion criteria:

• Database that was not authenticated.
• Datasets which were not in complete form.

Methodology

The process flow of proposed Bidirectional RNN model to early prediction of CVDs from ECG signal is depicted in (Table/Fig 2). Different noises are removed by hybrid preprocessing filter that is composed of Savitzky-Golay and Median Filter. The features viz., QRS complex and RR interval from the ECG signal were analysed by Undecimated Dual Tree Complex Wavelet Transform (UDTCWT) along with Detrended fluctuation (DA) analysis and Empirical Orthogonal Function (EOF). From the features the signals were classified by Bidirectional RNN model.

Preprocessing

Hybrid preprocessing filter: The initial process of preprocessing in the diagnosis of heart disease is to retrieve the original signal and eliminate the noise signal. Due to noise and abnormalities in the ECG data, clinical evidence is improperly evaluated, and CVD disorders are incorrectly diagnosed. ECG recordings contain a variety of disturbances such as baseline wander, Electromyographical (EMG) noise, and electrode motion artefact noise, as well as powerline interference, channel noise, composite, and random noises. The median filter (21) and the Savitzky-Golay filter (22) work together to remove all types of interference from the ECG signal. The process of noise removal has been shown in (Table/Fig 3).

Initially, the ECG signal E(t) was processed by the Savitzky-Golay filter (22) (E?SUB?SG#SUB#(t)) to remove the baseline wander noise shown in equation (1).

ESG (t)=E(t) (1)

Then the signal was again filtered using the median filter M(t) to remove the remaining noises that existed in the ECG signal. The median filter’s fundamental principle is to go over the signal entry by entry, replacing each one with the median of the entries next to it. The “window” is a pattern of neighbours that slides over the entire frequency range, entry by entry.

E?SUB?SG_M#SUB#(t)=M(E?SUB?SG#SUB# (t)) (2)

Feature Extraction

After preprocessing, the features were extracted with the combination of three different feature extraction techniques such as UDTCWT (23) with DA (15) analysis and EOF (24) analysis. UDTCWT produces two different type of features namely peak value detected by thresholding and amplitude. Detrended fluctuation analysis detects two different features to analysis the heart rate variations. Empirical orthogonal function gives single feature to represent the maximum spots.

B#BUDTCWT:B?B As tiny changes in ECG signals are difficult to identify with visual inspection, detecting aberrant stages of heart disease in diabetes individuals, such as cardiac arrhythmias, is challenging. The UDTCWT coefficients aid in detecting peak values in the QRS complex signal, as slight fluctuations in these signals accurately reflect diabetic heart illness. The preprocessed ECG signal ESG_M(t) is splitted by UDTCWT into detailed coefficients ESG_M(t)D and approximate coefficients ESG_M(t)A. The detailed coefficients provide the peak information in the ECG signal and the approximate coefficients provide lower value information in the ECG signal. By increasing and decreasing the signal values, the coefficients are retrieved from the QRS complex of each cardiac cycle and combined with the characteristics extracted from the third decomposition levels of UDTCWT.

UDTCWT (E?SUB?SG_M#SUB#(t))=ESG_M(t)?SUB?D#SUB# + E?SUB?SG_M#SUB#(t)?SUB?A#SUB# (3)

The detailed and approximate coefficients in each subsequent level are shown in equation 4 and 5.
(4)
(5)

In level 3, the detailed coefficients and approximate coefficients were reconstructed by inverse transform IUDTCWT (ESG_M(t)) and given to selective thresholding algorithm which selects the suitable threshold to the detailed and approximate feature information in the third decomposition levels (Table/Fig 4).

(6)

E?SUB?SG_M#SUB#(t)= IUDTCWT(E?SUB?SG_M#SUB#(t)) (7)

The selective thresholding algorithm uses precise filters on the UDTCWT signals to extract the peak signal from the other signals. The peak value in the decomposed ECG signal represented in equation was picked out by these filters (8)

Threshold=E?SUB?SG-M #SUB#(t) Selecctive (8)

Further, the amplitude between the magnitude of the QRS peak signal (I#IQRSI?I?SUB?P#SUB#) and the magnitude of the valley at the first half wave is (I#IQRSI?I?SUB?VP1#SUB#) calculated using equation (9)

Amplitude=|E?SUB?SG-M#SUB#(QRS?SUB?P#SUB#)_E?SUB?SG-M#SUB#(QRS?SUB?VP1#SUB#)| (9)

Detrended Fluctuation Analysis (DFA): Detrended fluctuation analysis (15) is a method for determining the statistical identity of an ECG signal. This approach, in particular, gave information on heartbeat interval time series correlations. Let be the piecewise series of linear fashion fits that results. The fluctuation is determined using the root mean square divergence from the average, as shown in equation (10)

(10)

Finally, the detrending and fluctuation detection process was repeated for a variety of window sizes n, in an ECG signal, and a log-log graph of DFA(n) against n is created. The stationary situations are represented by a straight line on this log-log graph, which exhibits statistical self-affinity expressed as I#IDFAI?I(n)?α(2). This analysis provides the QRS complex signal relationship of a heartbeat signal.

Empirical Orthogonal Function (EOF): EOF (24) is a signal processing method that experimentally identifies the signal’s periodical frequencies and is fully reliant on the data. The EOF approach objectively determines the data’s intrinsic time spans, which are conceived as the distances between sequential corresponding levels. The inherent mode function is a well-behaved function that uses two requirements to provide an explicit specification of the instantaneous amplitude and frequency: (1) There must be a unit difference between the number of local corresponding levels and zerocrossings. (2) In every location, the average envelope defined by local maximums and minimums must be zero. It interacts with fractal-like signals and extracts the global structure. It also facilitates in the investigation of non linear and non stationary signals’ adaptive time-frequency-amplitude space. It disintegrates the preprocessed signal into a residue and a few Intrinsic Mode Functions (IMF) to detect P,T,R peaks.

(11)

Bidirectional RNN- BiLSTM

The suggested model identifies the ECG signal as normal or abnormal by learning parameters in both the forward and backward directions to boost the Bidirectional Long Short-term Memory (BiLSTM) classifier model’s learning capacity. By memorising information for a long time, bidirectional RNN decreases the likelihood of gradient diminishing problems. The features extracted using feature extraction techniques was fed into a Bidirectional LSTM unit, which learns long-term correlations between normal and abnormal ECG signal. BiLSTM [25, 26] encoder, fully linked layer, and prediction layer make up the proposed bidirectional LSTM for ECG signal, three BiLSTM layers and a maxdropout layer make up the encoder unit. (Table/Fig 5) shows the proposed BiLSTM unit.

The target location I#IT(ES,AB)I?I of the predicted signal for the receive input features are depicted in equation (12).

I#IT(ES,AB)=WI?I?SUB?T#SUB#F(t)+b (12)

Where F(t) is the combination of Threshold and Amplitude taken from UDTCWT, DFA(n) taken from detrended fluctuation analysis and EOF(n) taken from EOF analysis. This predicts the early stage and abnormal stage of heart diseases.

Statistical Analysis

The DICARDIA, Physionet ECG, and MIT-BIH databases are used in the research design for early prediction analysis of type-2 diabetic patients’ ECG signals. The datasets were typically named in number order, starting with the database name and ending with the database name. The algorithm is tested on the MATLAB 2021a platform and trained on a PC with an Intel i4 processor and 16GB of RAM.

Results

The proposed work analyses the normal and abnormal patient details using ECG signal. The ECG signal of the Type-2 diabetic patient has been given to the proposed model. The model removes the noise information from the ECG signal by retaining the important signal information. Then the important features are taken out and the classifier model classifies the abnormal and normal signal.

[Table/Fig-6,7] illustrate samples of images from the DICARDIA and MIT-BIH datasets. (Table/Fig 6) displays the ECG waveform of a 51-year-old female diabetes mellitus type 2 patient with the DICARDIA study number 14800 and the record number 662. The train dataset photos of M24,M34, and M36 are downloaded from the MIT-BIH dataset images on the kaggle website.

The input ECG signals from various datasets are preprocessed with a hybrid preprocessing filter that combines the golay and median filters. These filters eliminated several sorts of noise from the ECG data. The features are recovered from the UDTCWT decomposition filter after the noise has been removed. Using thresholding and amplitude values obtained during the third step of decomposition, this determines the peak and valley points of the MIT-BIH dataset image (Table/Fig 8).

The peak and valley points are taken as the first feature set for the classifier. The heart fluctuations points are analysed by detrended fluctuation analysis shown in (Table/Fig 9). The maximum spots are detected in DICARDIA database images through EOF analysis shown in (Table/Fig 10).

The fused feature combinations are given to the BiLSTM classifier model to classify the early stage and abnormal stage patients through ECG signal. (Table/Fig 11) shows the network architecture of BiLSTM classifier model.

Through the bidirectional RNN approach, this model learns from weak learners and classifies them more accurately. The suggested model was trained using 80% of the data and evaluated using 20% of the data. The pareto concept is used to categorise the features. The BiLSTM model employs three distinct blocks with varying hidden layer sizes and dropouts of 0.1 and 0.2. The model learns in 0.24 seconds with the minimum set of features and achieves a higher average accuracy of 97.6%. (Table/Fig 12) shows the comparison results of the proposed BiLSTM classifier model with the state of art techniques. The proposed method achieves the better performance in precision, recall, F1score and accuracy. It attains a gain of 0.40 in accuracy, 2.44 in F1score, 0.433 in recall and 0.64 in precision (27),(28),(29).

Discussion

The experimental evaluation of the proposed technique (Table/Fig 12) reveals that the automatic BiRNN based early detection and prediction of CVD in Type-2 diabetic patient’s results in better forecast planning for physicians. The noise removal with feature extraction provides a better prediction of CVD in Type-2 patients. It is a direct image processing-based analysis; therefore user intervention is not necessary for training or testing. However, if the images are acquired with an excessive amount of noisy signal, this method might not provide accurate analysis.

Limitation(s)

This proposed model has also been given the false analysis of 2.4% and this is comparatively less than other prediction models. This would be recovered by training more models in future.

Conclusion

Bidirectional RNN classifier model based on hybrid preprocessing with fused features is proposed for early prediction of CVDs from ECG signals taken from type-2 diabetic patients. To reduce noise from the ECG signal received from various datasets, a hybrid unique preprocessing filter is used. The features are then extracted using UDTCWT, DF, and EOF analysis to detect the ECG signals’ maximum, peak, valley points, and variations. Signal-based bidirectional RNN model is used to classify the features. The proposed method is the most effective way for detecting anomalies in ECG signals in both the early and pathological stages.

References

1.
Serhani MA, El Kassabi HT, Ismail H, Nujum Navaz A. ECG monitoring systems: Review, architecture, processes, and key challenges. Sensors (Basel). 2020;20(6):1796. Doi: 10.3390/s20061796. PMID: 32213969; PMCID: PMC7147367. [crossref] [PubMed]
2.
Nesheiwat Z, Goyal A, Jagtap M. Atrial Fibrillation. In: StatPearls. Treasure Island (FL): StatPearls Publishing; 2022. Available from: https://www.ncbi.nlm.nih.gov/books/NBK526072/.
3.
Yakut O, Bolat ED. An improved QRS complex detectionmethod having low computational load. Biomedical Signal Processing and Control. 2018;42:230-41. [crossref]
4.
Martis RJ, Acharya UR, Ray AK, Chakraborty C. Application of higher order cumulants to ECG signals for the cardiac health diagnosis. In Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicineand Biology Society (EMBS ’11). 2011;2011:1697-1700. [crossref] [PubMed]
5.
Camargo-Olivares JL, Clemente R, Hornillo-Mellado S, Elena MM, Román I. The maternal abdominal ECG as input to MICA in the fetal ECG extraction problem. IEEE Signal Processing Letters. 2011;18(3):161-64. [crossref]
6.
Khoshnoud S, Teshnehlab M, Shoorehdeli MA. Probabilistic neural network oriented classification methodology for Ischemic Beat detection using multi resolution Waveletanalysis. In Proceedings of the 17th Iranian Conference of Biomedical Engineering (ICBME ’10). 2010;1-4. [crossref]
7.
Saxena SC, Kumar V, Hamde ST. Feature extraction from ECG signals using wavelet transforms for disease diagnostics. Int J Syst Sci. 2002;33:1073-85. [crossref]
8.
Wackers FJ, Young LH, Inzucchi SE, Chyun DA, Davey JA, Barrett EJ, et al. Detectionof ischemia in asymptomatic diabetics (DIAD) investigators: Detection of silent myocardial ischemia in asymptomatic diabetic subjects. Diabetes Care. 2004;27(8):1954-61. [crossref] [PubMed]
9.
Young LH, Wackers FJ, Chyun DA, Davey JA, Barrett EJ, Taillefer R, et al. Cardiac outcomes after screening for asymptomatic coronary artery disease in patients with type 2 diabetes: The DIAD study: A randomised controlled trial. Journal of the American Medical Association. 2009;301(15)1547-55. [crossref] [PubMed]
10.
Maglaveras N, Stamkopoulos T, Pappas C, Gerassimos Strintzis M. An adaptive backpropagation neural network for real-time ischemia episodes detection: Development and performance analysis using the European ST-T database. IEEE Transactions on Biomedical Engineering. 1998;45(7):805-13. [crossref] [PubMed]
11.
Langley P, Bowers EJ, Murray A. Principal component analysis as a tool for analyzing beat-to-beat changes in ECG features: Application to ECG-derived respiration. IEEE Transactions on Biomedical Engineering. 2010;57(4):821-29. [crossref] [PubMed]
12.
Kaur M, Arora AS. Unsupervised Analysis of Arrhythmias using K-means Clustering. (IJCSIT) International Journal of Computer Science and Information Technologies. 2010;1(5):417-19.
13.
Manimegalai P, Bharathi P, Thanushkodi K. Real time implementation of analysis of ECG characteristic points using discrete wavelets. Global Journal of Researches in Engineering Electrical and Electronics Engineering. 2012;12(1):78-87.
14.
Tribhuvanam S, Nagaraj HC, Naidu VPS. ECG abnormality classification with single beat analysis. In: International conference on vision towards emerging trends in communication and networking. 2019:01-06. [crossref]
15.
Sassi R, Cerutti S, Lombardi F, Malik M, Huikuri HV, Peng CK, et al. Advances in heart rate variability signal analysis: joint position statement by thee-cardiology ESC working group and the European heart rhythm association co-endorsed by the asia pacific heart rhythm society. Europace. 2015;17(9):1341-53. [crossref] [PubMed]
16.
Moreno EM, Luján MJA, Rusinol MT, Fernández PJ, Manrique, PN, Trivino CA, et al. Type 2 diabetes screening test by means of a pulse oximeter. IEEE Trans. Biomed. Eng. 2016;64(2):341-51. [crossref] [PubMed]
17.
Qomariah DUN, Tjandrasa H, Fatichah C. Classification of Diabetic Retinopathy and Normal Retinal Images using CNN and SVM. In: 2019 12th International Conference on Information & Communication Technology and System (ICTS).2019;152-57. [crossref]
18.
Ledezma C, Severeyn E, Perpinan G, Altuve M, Wong S. A new on-line electrocardiographic records database and computer routines for data analysis. In Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE. 2014;2014:2738-41. [crossref] [PubMed]
19.
Bousseljot R, Kreiseler D, Schnabel A. Nutzung der EKG-Signal daten bank CARDIODAT der PTB über das Internet. Biomedizinische Technik, Band 40, Ergänzungsband 1 .1995; S317. [crossref]
20.
Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine. 2001;20(3):45-50. Doi: 10.1109/51.932724. [crossref] [PubMed]
21.
Subbiah S, Patro R, Rajendran K. Reduction of noises in ECG signal by various filters. International Journal of Engineering Research & Technology. 2014;3(1):656-60. 10.13140/RG.2.2.35951.89763.
22.
Kaur H, Rajni R. Signal Denoising with Savitzky-Golay Filter and Discrete Wavelet Transform (DWT). International Journal of Emerging Trends & Technology in Computer Science. 2016;36:161-65. 10.14445/22315381/IJETT-V36P249. [crossref]
23.
Hill P, Achim A, Bull D. The undecimated dual tree complex wavelet transform and its application to bivariate image denoising using a Cauchy model. 2012 19th IEEE International Conference on Image Processing. 2012;1205-08. Doi: 10.1109/ICIP.2012.6467082. [crossref]
24.
Ghobadi Azbari P, Mohaqeqi S, Ghanbarzadeh Gashti N, Mikaili M. Introducing a combined approach of empirical mode decomposition and PCA methods for maternal and fetal ECG signal processing. The Journal of Maternal-Fetal & Neonatal Medicine. 201629(19):3104-09. 10.3109/14767058.2015.1114089. [crossref] [PubMed]
25.
Schuster M, Paliwal KK. Bidirectional recurrent neural networks. In IEEE Transactions on Signal Processing. 1997;45(11):2673-81. Doi: 10.1109/78.650093. [crossref]
26.
Yu W, Yu H, Wang D, Du J, Zhang M. SL-BiLSTM: A signal-based bidirectional LSTM network for over-the-horizon target localization. Mathematical Problems in Engineering, Hindawi. 2021. [crossref]
27.
Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med. 2017;89:389-96. Doi: 10.1016/j.compbiomed.2017.08.022. [crossref] [PubMed]
28.
Kachuee M, Fazeli S, Sarrafzadeh M. ECG heartbeat classification: A deep transferable representation. Proc. - 2018 IEEE Informatics, ICHI. 2018;2018:443-44. Doi:10.1109/ICHI.2018.00092. [crossref]
29.
Abdullah LA, Al-Ani MS. CNN-LSTM based model for ECG arrhythmias and myocardial infarction classification. ASTES Journal. 2020;5(5):601-06. [crossref]

DOI and Others

DOI: 10.7860/JCDR/2022/55951.17154

Date of Submission: Mar 01, 2022
Date of Peer Review: Apr 25, 2022
Date of Acceptance: Sep 17, 2022
Date of Publishing: Nov 01, 2022

AUTHOR DECLARATION:
• Financial or Other Competing Interests: None
• Was Ethics Committee Approval obtained for this study? No
• Was informed consent obtained from the subjects involved in the study? NA
• For any images presented appropriate consent has been obtained from the subjects. NA

PLAGIARISM CHECKING METHODS:
• Plagiarism X-checker: Mar 07, 2022
• Manual Googling: Sep 08, 2022
• iThenticate Software: Sep 15, 2022 (5%)

ETYMOLOGY: Author Origin

JCDR is now Monthly and more widely Indexed .
  • Emerging Sources Citation Index (Web of Science, thomsonreuters)
  • Index Copernicus ICV 2017: 134.54
  • Academic Search Complete Database
  • Directory of Open Access Journals (DOAJ)
  • Embase
  • EBSCOhost
  • Google Scholar
  • HINARI Access to Research in Health Programme
  • Indian Science Abstracts (ISA)
  • Journal seek Database
  • Google
  • Popline (reproductive health literature)
  • www.omnimedicalsearch.com