Page 90 - The-5th-MCAIT2021-eProceeding

intricate patterns, which presented in a wide range of applications in various fields, including healthcare (Adadi
& Berrada, 2018). The rest of this survey as structured as followed. In Section 2 we introduce the ECG structure
and components, and the diseases that can aid to diagnose. Section 3 describes the related state-of-art works
used to detect CVDs using ECG signals. The widely used MACHINE LEARNING algorithms, feature
selections, and datasets are discussed in this section.

2. Electrocardiogram Signal (ECGs)

Electrocardiogram Signal or ECGs is a non-invasive, easy to acquire, and uncostly diagnose tool used for
recording the heart’s physiological activities of the heart (Hong et al., 2020; Sahoo, Dash, Behera, & Sabut,
2020). ECGs can aid in diagnosing many cardiovascular abnormalities such as Premature contractions of the
atria (PAC) or ventricles (PVC), Atrial fibrillation (AF), Myocardial infarction (MI), and Congestive heart
failure (CHF) (Holst et al., 1999). The standard ECG has 12 leads; six of them are placed on the arms and legs
of the patient that are labelled as ”Limb Leads”, and the other six leads are placed on the torso (precordium),
and they labelled as ”Precordial Leads”. The limb leads are called lead I, II, III, aVL, aVR and aVF and the
precordial leads are called leads V1, V2, V3, V4, V5 and V6. A normal ECG contains waves, intervals,
segments and QRS complex, (Fig. 1) (Sahoo et al., 2020).
Waves represent a positive or negative
deflection from the baseline that indicates a
specific electrical event. The waves on an
ECG include the P wave, Q wave, R wave, S
wave, T wave and U wave. Intervals represent
the time between two specific ECG events.
The intervals commonly measured on an ECG
include the PR interval, QRS interval (also
called QRS duration), QT interval and RR
interval. Segment is the length between two
specific points on an ECG supposed to be at
the baseline amplitude (not negative or
positive). The segments on an ECG include
the PR segment, ST-segment and TP segment.
Complex represents the combination of
multiple waves grouped together. The only Fig. 1 Electrocardiogram Sample (ECG)
main complex on an ECG is the QRS complex.
The main part of an ECG contains a P wave, QRS complex and T wave. The P wave indicates atrial
depolarization. The QRS complex consists of a Q wave, R wave and S wave and represents ventricular
depolarization. Finally, the T wave comes after the QRS complex and indicates ventricular repolarization.
3. Related Works

In (Kiranyaz, Ince, & Gabbouj, 2015), the author proposed a real-time ECG classification and monitoring
system. A 1D-CNN algorithm trained on MIT-BIH dataset to diagnose CVDs. The model achieved 98.9%
accuracy, 95.9% sensitivity, and 99.4% specificity. The MIT-BIH dataset was used in (Zubair, Kim, & Yoon,
2016 ) to train a CNN algorithm to diagnose CVDs and automatically classified ECG beats into five different
normal beat classes Supraventricular ectopic beat, Ventricular ectopic beat, Fusion beat, Unknown beat. The
proposed model achieved 92.7% overall accuracy.
Two- and five-seconds durations of ECGS signal segments from Fantasia and St.Petersburg datasets are used
to train a CNN algorithm to predict CAD in (Acharya et al., 2017). The CNN model structures comprising of
four convolutional layers, four max-pooling layers and three fully connected layers. The proposed model is
capable of differentiating between normal and abnormal ECG with 94.95% precision, 93.72% sensitivity and
95.18% specificity for Net 1 (two seconds) and 95.11% accuracy, 91.13% sensitivity and 95.88% specificity for
Net 2 (5 s). Different kernels of Least Squares-Support Vector Machine (LS-SVM) are used in (Kumar, Pachori,

E- Proceedings of The 5th International Multi-Conference on Artificial Intelligence Technology (MCAIT 2021) [77]
Artificial Intelligence in the 4th Industrial Revolution