Heart Disorder Detection Using R to R Interval Signal Classifier

Subairi Subairi, Delila Cahya Permatasari, Yandhika Surya Akbar Gumilang, Wahyu Dirgantara

Abstract


The heart is the most important part of our body. So, the condition of the heart is affected by all of our bodies. If our heart has trouble, our body feels it too. So, a routine heart health check is important. One of the heart disorders is arrhythmia. Arrhythmia is a disorder of the heart rate or heart rhythm which is characterized by an irregular heartbeat, which can be too fast or too slow from the normal heartbeat. One method to detect arrhythmia is to determine the value of the R to R interval signal on the heart rhythm signal (ECG Signal). ECG signal has a peak wave value, which is called an R signal. From the R signal, the researcher can detect the condition of the heart. Purposed research is an interval R to R signal classifier using the Decision Tree Algorithm. The decision tree can find solutions to problems by making criteria as nodes that are interconnected to form a tree-like structure. The process of the purposed method first is the detection of R to R using filters signal is called preprocessing, second is the extraction feature, from ECG signal extracted to 7 features, and the last process is the decision tree using Gini index. The result of the purposed method shows that the accuracy of heart disorder detection using a decision tree is 98,27% accuracy. From 3140 epochs, it detects 2105 normal (N), 972 arrhythmia (A), and 63 misclassifications. It is the purposed method that has a 98% success rate. From these results, the purposed method is valid for heart disorders. Keywords: Heart Disorder, ECG signal, Interval R to R, Decision Tree. 

The heart is the most important part of our body. So, the condition of the heart is affected by all of our bodies. If our heart has trouble, our body feels it too. So, a routine heart health check is important. One of the heart disorders is arrhythmia. Arrhythmia is a disorder of the heart rate or heart rhythm which is characterized by an irregular heartbeat, which can be too fast or too slow from the normal heartbeat. One method to detect arrhythmia is to determine the value of the R to R interval signal on the heart rhythm signal (ECG Signal). ECG signal has a peak wave value, which is called an R signal. From the R signal, the researcher can detect the condition of the heart. Purposed research is an interval R to R signal classifier using the Decision Tree Algorithm. The decision tree can find solutions to problems by making criteria as nodes that are interconnected to form a tree-like structure. The process of the purposed method first is the detection of R to R using filters signal is called preprocessing, second is the extraction feature, from ECG signal extracted to 7 features, and the last process is the decision tree using Gini index. The result of the purposed method shows that the accuracy of heart disorder detection using a decision tree is 98,27% accuracy. From 3140 epochs, it detects 2105 normal (N), 972 arrhythmia (A), and 63 misclassifications. It is the purposed method that has a 98% success rate. From these results, the purposed method is valid for heart disorders.

 

Keywords: Heart Disorder, ECG signal, Interval R to R, Decision Tree.

Full Text:

166-173

References


Afroni, M. J., & Basuki, B. M. (2020). Algoritma Pendeteksi Titik Ekstrim Pada Sinyal ECG Untuk Analisis Awal Gejala Aritmia. JE-Unisla, 5(2), 400–404.

Akhter, N., Gite, H., Tharewal, S., & Kale, K. v. (2015). Computer-based RR-interval detection system with ectopy correction in HRV data. 2015 International Conference on Advances in Computing, Communications, and Informatics (ICACCI), 1613–1618.

Brunner, E., Bathke, A. C., & Konietschke, F. (2002). Nichtparametrische datenanalyse. Springer.

Gupta, V., Mittal, M., & Mittal, V. (2020). R-peak detection based chaos analysis of ECG signal. Analog Integrated Circuits and Signal Processing, 102(3), 479–490.

Guyton, A. C., & Hall, J. E. (2000). Textbook of medical physiology, 2006. WB Saunder’s Co, Philadelphia.

Hardani, D. N. K. (2015). Ekstraksi Fitur Sinyal Elektrokardiogram Berbasis Independent Component Analysis. Techno (Jurnal Fakultas Teknik, Universitas Muhammadiyah Purwokerto), 16(1), 10–15.

Moody, G. B., & Mark, R. G. (2001). The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 20(3), 45–50.

Pramadhani, A. E., & Setiadi, T. (2014). Penerapan Data Mining Untuk Klasifikasi Prediksi Penyakit ISPA (Infeksi Saluran Pernapasan Akut) Dengan Algoritma Decision Tree (ID3). Jurnal Sarjana Teknik Informatika, 2(1), 831–839.

Rohan, R., & Kumari, L. V. R. (2021). Classification of sleep apneas using decision tree classifier. 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), 1310–1316.

Stefanie, A., & Bangsa, I. A. (2018). Perancangan Sistem Pendeteksi Iregularitas Interval RR Pada Sinyal Elektrokardiogram (Ekg) Sebagai Indikator Penyakit Kardiovaskular. EEICT (Electric, Electronic, Instrumentation, Control, Telecommunication), 1(2).

Wasimuddin, M., Elleithy, K., Abuzneid, A.-S., Faezipour, M., & Abuzaghleh, O. (2020). Stages-based ECG signal analysis from traditional signal processing to machine learning approaches A survey. IEEE Access, 8, 177782–177803.




DOI: https://doi.org/10.26905/icgss.v7i1.9265

Refbacks

  • There are currently no refbacks.