Introduction
Most of the heart diseases show their symptoms in the Electrocardiogram (ECG) test, but the diagnosis of heart failure with the help of ECG requires the knowledge and experience of specialists. Since these specialists may not always be available, it is necessary to design tools to provide the possibility of diagnosing heart failure by the staff of different departments. Considering the importance of early diagnosis of heart failure, intelligentization of the diagnosis process based on ECG data can increase accuracy, speed, ease of use, and economic efficiency in diagnosis. This study aims to design an approach for diagnosing heart disease based on ECG data.
Materials and Methods
In this study, a smart model using artificial neural network (ANN) was designed to diagnose heart disease based on the ECG data (Figure 1). First, the ECG data of patients were collected from medical centers in Arak, Iran. The data were examined based on the opinions of specialists. Then, 154 ECG data as the inputs of the proposed model were defined (Table 1).


Two ANNs were used to detect the ECG status (usable and unusable) and the presence of heart disease (yes, no). Finally, the performance of this two-stage approach was evaluated and its accuracy and precision in determining the ECG status and disease diagnosis were determined.
Results
The ANN used for determining of the ECG status had an accuracy of 97.1%, a precision of 97.3%, a specificity of 100%, a sensitivity of 64.8% and a negative predictive value (NPV) of 100%. The ANN used for heart disease diagnosis had 95.8% accuracy, 95.4% precision, 99.4% specificity, 48.1% sensitivity and 86.7% NPV (Table 2).


These values showed efficiency and high performance of the proposed approach in automatic determination of ECG quality and diagnosis of heart disease.
Discussion
The two-stage approach based on ANN and ECG data has high efficiency in determining the ECG quality and diagnosing heart diseases. 

Ethical Considerations
Compliance with ethical guidelines
This study was approved by the ethics committee of Arak University of Medical Sciences (Code: IR.ARAKMU.REC.1400.138). 

Funding
This research did not receive any grant from funding agencies in the public, commercial, or non-profit sectors. 

Authors' contributions
 Methodology and sampling: Majid Mehrad, Majid Nojavan and Sadigh Raisi; Data analysis: Majid Mehrad and Sadigh Raisi; Conceptualization editing & review: All authors.

Conflicts of interest
The authors declare no conflicts of interest.

Acknowledgements
The authors would like to thank the Head of the Research Unit of Arak University of Medical Sciences, Dr. Kalantari (the Head of Cardiology Department of Arak University of Medical Sciences), and Dr. Mashayekhi as well as the medical staff of Amir Kabir Hospital, Imam Reza Clinic and Vali-E-Asr Hospital in Arak for providing data and their cooperation.


References

1. Kendir C, van den Akker M, Vos R, Metsemakers J. Cardiovascular disease patients have increased risk for comorbidity: A cross-sectional study in the Netherlands. Eur J Gen Pract. 2018; 24(1):45-50. [DOI:10.1080/13814788.2017.1398318] [PMID] [PMCID]
2. Carlson B, Austel Nadeau C, Glaser D, Fields W. Evaluation of the effectiveness of the healthy heart tracker on heart failure self-care. Patient Educ Couns. 2019; 102(7):1324-30. [DOI:10.1016/j.pec.2019.02.010] [PMID]
3. Bayés de Luna A, Brugada J, Baranchuk A, Borggrefe M, Breithardt G, Goldwasser D, et al. Current electrocardiographic criteria for diagnosis of Brugada pattern: A consensus report. J Electrocardiol. 2012; 45(5):433-42. [DOI:10.1016/j.jelectrocard.2012.06.004] [PMID]
4. Van Pham H. A proposal of expert system using deep learning neural networks and fuzzy rules for diagnosing heart disease. In: Satapathy S, Bhateja V, Nguyen B, Nguyen N, Le DN, editors. Frontiers in intelligent computing: Theory and applications. Singapore: Springer; 2019. [DOI:10.1007/978-981-32-9186-7_21]
5. Bayés de Luna A, Brugada J, Baranchuk A, Borggrefe M, Breithardt G, Goldwasser D, et al. Current electrocardiographic criteria for diagnosis of Brugada pattern: A consensus report. J Electrocardiol. 2012; 45(5):433-42. [DOI:10.1016/j.jelectrocard.2012.06.004] [PMID]
6. Rani KU. Analysis of heart diseases dataset using neural network approach. Int J Data Min Knowl Manag Process. 2011; 1(5):1-8. [DOI:10.5121/ijdkp.2011.1501]
7. Muthukaruppan S, Er MJ. A hybrid particle swarm optimization based fuzzy expert system for the diagnosis of coronary artery disease. Expert Syst Appl. 2012; 39(14):11657-65. [DOI:10.1016/j.eswa.2012.04.036]
8. Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. J Appl Biomed. 2013; 11:47-58. [DOI:10.2478/v10136-012-0031-x]
9. Hu YH, Tompkins WJ, Urrusti JL, Afonso VX. Applications of artificial neural networks for ECG signal detection and classification. J Electrocardiol. 1993; 26 Suppl:66-73. [PMID]
10. Rai HM, Trivedi A, Shukla S. ECG signal processing for abnormalities detection using multi-resolution wavelet transform and artificial neural network classifier. Measurement. 2013; 46(9):3238-46. [DOI:10.1016/j.measurement.2013.05.021]
11. Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M, et al. Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals. Appl Intell. 2019; 49(1):16-27. [DOI:10.1007/s10489-018-1179-1]
12. Acharya UR, Fujita H, Lih OS, Adam M, Tan JH, Chua CK. Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network. Knowl Based Syst. 2017; 132:62-71. [DOI:10.1016/j.knosys.2017.06.003]
13. Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci. 2017; 415:190-8. [DOI:10.1016/j.ins.2017.06.027]
14. Shamsollahi M, Badiee A, Ghazanfari M. Using combined descriptive and predictive methods of data mining for coronary artery disease prediction: A case study approach. J AI Data Min. 2019; 7(1):47-58. [DOI:10.22044/jadm.2017.4992.1599]
15. Naruei I, Zamani B. Diagnosis of cardiac arrhythmia using deep learning (Persian)]. Paper presented at: The First Electronic Conference on New Ideas in Cumputer Engineering. 3 September 2015; Sahrekord: Iran. [Link]
16. Naruei I, Zamani B. [Diagnosis of cardiac arrhythmia using Fisher and Ls-Svm (Persian)]. Paper presented at: The Second Electronic Conference on New Research in Science and Technology (EMA). 21 July 2015; Kerman, Iran. [Link]
17. Naruei I, Zamani B. Diagnosis of cardiac arrhythmia using Pca and MLP neural network (Persian)]. Paper presented at: The Second Electronic Conference on New Research in Science and Technology (EMA). 21 July 2015; Kerman, Iran. [Link]
18. Saqlain SM, Sher M, Shah FA, Khan I, Ashraf MU, Awais M, et al. Fisher score and Matthews correlation coefficient-based feature subset selection for heart disease diagnosis using support vector machines. Knowl Inf Syst. 2019; 58(1):139-67. [DOI:10.1007/s10115-018-1185-y]
19. Najafi Zereh Bashi HR, Hosseini R, Mazinani M. Diagnosis of obstructive apnea disease AHI in chemical warfare veterans based on HRV signals analysis using the ANFIS neural network. Spec J Electron Comput Sci. 2021; 7(1):1-12. [Link]
20. Wang J, Qiao X, Liu C, Wang X, Liu Y, Yao L, et al. Automated ECG classification using a non-local convolutional block attention module. Comput Methods Programs Biomed. 2021; 203:106006. [DOI:10.1016/j.cmpb.2021.106006] [PMID]
21. Kobat MA, Karaca O, Barua PD, Dogan S. Prismatoid pat net 54: An accurate ECG signal classification model using prismatoid pattern-based learning architecture. Symmetry. 2021; 13(10):1914. [DOI:10.3390/sym13101914]
22. Glass GF, Sudhir A, Pandit AA. The ECG and metabolic abnormalities. Electrocardiogram Clin Med. 2020, 5:307-13. [DOI:10.1002/9781118754511.ch30]
23. Abiodun OI, Jantan A, Omolara AE, Dada KV, Umar AM, Linus OU, et al. Comprehensive review of artificial neural network applications to pattern recognition. IEEEAccess. 2019; 7:158820-46. [DOI:10.1109/ACCESS.2019.2945545]