Two Statistical Methods to Analyze the Role of CHA2DS2VASc Score
in Patients with STEMI
ETLEVA BELIU, ENDRI RAÇO, KLEIDA HAXHI, ORIANA ZAÇAJ, KOSTAQ HILA
Department of Statistic, Faculty of Mathematical Engineering and Physics Engineering
Tirana Polytechnic University,
Tirana, 1069,
ALBANIA
Abstract: - The CHA2DS2VASc score includes risk factors for coronary artery disease. The aim of this study is
to show that the CHA2DS2VASc score calculated at the time of hospital admission may predict mortality and
major adverse cardiovascular and cerebrovascular events (MACCE) in-hospital and at 30-day follow-up for
patients with STEMI, who were subjected to primary percutaneous coronary intervention (p-PCI). A
retrospective cohort study was performed at University Hospital Center ‘Mother Teresa’, in the Cardiology
Department between June 2021 and September 2021. The CHA2DS2VASc score was calculated at the time of
hospital admission for all of them. The study population was divided into 3 groups according to the
CHA2DS2VASc score at the time of admission. A statistical control of result of hospital MACCE was done.
As the result of multivariable analysis, smoking and CHA2DS2VASc groups were found to be independent
MACCE predictors. The chances of developing MACCE were approximately 5 times higher in a patient of the
third CHA2DS2VASc group, compared to that of the first group. CHA2DS2VASc groups are important to
define the likelihood that MACCE will occur in patients with ascending STEMI who had undergone PCI. The
ROC plot provided a visual representation of the accuracy of CHA2DS2VASc in predicting reinfarction and
stroke. AUC 0.852 (95% C.I: 0.776-0.928) showed when CHA2DS2VASc has this predictive ability for
morbidity and mortality. CHA2DS2VASc ≥ 4 can be used to determine risk of reinfarction and stroke.
Key-Words: - AUC, CHA2DS2VASc, MACCE, Multiple logistics model, ROC, STEMI
Received: August 24, 2021. Revised: May 16, 2022. Accepted: June 5, 2022. Published: July 1, 2022.
1 Introduction
The CHA2DS2VASc score is a well know method
capable of predicting the risk of stroke in patients
with atrial fibrillation (AF) [1]. Recent research has
extended the use of CHA2DS2VASc score to non-
AF populations [1]. Previous studies have
demonstrated that the CHA2DS2VASc score can
predict in-hospital and long-term adverse clinical
outcomes, including mortality in stable coronary
artery disease (CAD), as well as an acute coronary
syndrome. A CHA2DS2VASc >2 [3] was an
independent predictor for the incidence of acute
stent thrombosis. The score includes variables such
as heart failure, hypertension (HT), older age,
diabetes mellitus (DM), female gender [4], vascular
disease, and stroke. The components have similar
risk factors, and as such are valued at 1 point, with
the exception of age (65<Age <75 = 1 point, Age >
75 = 2 points) [5] and previous stroke/transient
ischemic attack (2 points) [6]. Since these
components are also risk factors for atherosclerosis
and ischemic heart disease, it may be reasonable to
use them for risk stratification in patients with
STEMI [7], too. The CHA2DS2VASc scoring
system is easy to calculate, so it may be useful
compared to other scores such as GRACE [8][8],
and TIMI 0 that cannot be calculated manually.
Since acute myocardial infarction (AMI) is
considered to be a vascular disease, all patients with
AMI received at least 1 point.
2 Statistical Analysis
The data were processed in SPSS version 26.0 for
Windows (IBM, USA). During the study, the
continuous numerical variables were descriptively
analysed. The mean, standard deviation, and even
the confidence interval (CI) of mean with a
confidence level of 95% of all these data were
represented. CI generates the upper bound "Upper
Confidence Level", UCL, and the lower "Lower
Confidence Level", LCL. The ANOVA method was
used to compare the means of continuous random
variables, or binary random variables. The p-value
of ANOVA simply indicates whether these averages
are equal or not. The comparison of the values of
more than two groups was also done with the
Benjamin-Hochberg method. This method is
suitable for testing the hypothesis of equal mean
values in these cases because it controls which one
differs. It works with two values of Type I error, α =
0.05 and 0.01. When the letters shown below the
averages are capitalized then the p-value was less
than 0.01, the difference between the groups is very
significant. When the group letters below the
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
461
Volume 21, 2022
averages are in lower case, then 0.01 < p-value <
0.05, meaning that the difference between the
groups is significant. Receiver operating
characteristic (ROC) curve analysis was used to
determine the optimal cut-off value of
CHA2DS2VASc score or the value of
CHA2DS2VASc scores needed to predict the
development of MACCE.
3 Materials and Methods
212 consecutive patients, included in this study, are
admitted to undergoing Primary PCI for ST-elevated
myocardial infarction (STEMI) in the Cardiology
Center of the “Mother Teresa” University Medical
Center, (177 men and 35 women with a mean age of
63.82, range: 30-85 y.). STEMI was diagnosed
based on ST-segment elevation ≥1 mm in at least 2
contiguous electrocardiographic (ECG) leads or new
left bundle branch block with chest pain lasting over
30 minutes. Blood samples were taken at the time of
admission to the hospital and daily during the
hospital stay. A 12-lead ECG was recorded in each
patient immediately upon admission to the hospital,
and myocardial infarction (MI) type is observed
with the help of ECG. Left ventricular ejection
fraction (LVEF) was measured using the modified
Simpson method.
Follow-up procedures took place 1 month after
discharge, using a standardized protocol that
included telephone contacts, and recordings of
cardiac events. The primary endpoint was all-cause
mortality in hospital. Cardiovascular deaths, re-
infarctions, and repeated target vessel
revascularizations (TVRs) were defined as MACCE.
During short-term follow-up, any events of stroke,
heart failure-related re-hospitalizations, or MACCE
were noted. The potential occurrence of MACCE
was calculated based on data gathered from phone
call conversations with each patient 1 month after
discharge. If we could not reach the patient, the
patient's general practitioner was contacted In cases
of patients with a possible MACCE or unknown
status, the electronic hospital records were
investigated. All information possibly indicating
MACCE was further investigated by examining
medical records from the hospital and/or the general
practitioner. All potential events were then reviewed
by two independent cardiologists, who decided
whether MACCE occurred or not. Both
cardiologists were blinded for the GRACE, TIMI,
and CHA2DS2-VAS scores.
Patients were divided into three groups according to
their CHA2DS2VAS scores. Patients with scores of
1-2 were categorized in the low-level
CHA2DS2VASc group (1), those of 3-4 points in
the medium-level group (2), while the high-level of
CHA2DS2VASc group (3) included patients with
the highest scores of CHA2DS2VASc, ranging from
5 to 9 [11].
Demographic and clinical data of the patients are
registered in a dedicated database. Then these
characteristics of the studied population were
analyzed. 64 patients were in the low-level
CHA2DS2VASc group (No. 64 males/0 female),
112 in the medium-level group (No. 94 males/18
females), and 36 patients in the high-level group
(No. 19 males/17 females). The average age of
patients of the low-level group of CHA2DS2VASc
was 55 years; that of the medium-level group was
66 years for males and 61 for females; that of the
high-level group was 77 years for males and 75 for
females as detailed in
Table 1. In the different CHA2DS2VASc groups,
age increased significantly (F-value = 73,489 and p-
value = 6.7849E-45). The first group is younger,
averaging 55.45, the second at 64.8, and the third at
75.61. As expected, HTN, DM, Stroke, and CHF
occurred more often in patients with the high-level
CHA2DS2VASc. We noted the difference between
Killip Class and CHA2DS2-VAS groups, as there
are cases of patients of different groups of
CHA2DS2VASc in every classification of Killip
Class.
Table 1. The main characteristic of patients
low-level group
CHA2DS2VASc
medium-level group
CHA2DS2VASc
(A)
(B)
Count
Column
N %
Count
Column N %
Count
Column N %
Sex
male
64
100.0%
94
C
83.9%
19
52.8%
female
0
0.0%
18
16.1%
17
B
47.2%
Dyslipidemia
32
50.0%
63
56.3%
17
47.2%
HTN
45
70.3%
108
A
96.4%
35
A
97.2%
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
462
Volume 21, 2022
DM
3
4.7%
66
A
58.9%
27
A
75.0%
Stroke
0
0.0%
1
0.9%
10
B
27.8%
CHF
0
B C
0.0%
3
2.7%
2
5.6%
PAD
0
0.0%
0
0.0%
0
0.0%
Post-IM
1
1.6%
5
4.5%
4
11.1%
Post CABG
0
0.0%
0
0.0%
0
0.0%
Post PCI
3
4.7%
6
5.4%
3
8.3%
Killip Class
I
52
B C
81.3%
74
C
66.1%
13
36.1%
II
11
17.2%
30
26.8%
19
A B
52.8%
III
1
1.6%
6
5.4%
3
8.3%
All laboratory assessments were stored in the
institutional, in this dedicated laboratory database,
too. Procedural and angiographic data were
prospectively collected and entered by
interventional cardiologists and specialized nurses.
The results of angiographic and procedural data are
represented in Table 2.
By using the Benjamin-Hochberg method,
significant changes were shown only in terms of the
number of afflicted vessels. The number of patients
in the second and third groups of CHA2DS2VASc
with 3-vessel CAD was significantly higher than in
the first CHA2DS2VASc group. The other
procedural and angiographic data have no
statistically significant difference.
Table 2. Angiography and procedural characteristics of patients
low-level group
CHA2DS2VASc
medium-level group
CHA2DS2VASc
high-level group
vesselCHA2DS2VASc
(A)
(B)
(C)
N
%
N
%
N
%
Stent DES
1
26
40.6%
53
47.3%
16
44.4%
Stent BMS
1
40
62.5%
65
58.0%
23
63.9%
STEMI Anterior
1
28
43.8%
51
45.5%
18
50.0%
Inferior
1
26
40.6%
47
42.0%
17
47.2%
Inferior-lateral
1
7
10.9%
12
10.7%
1
2.8%
Posterior
1
2
3.1%
1
0.9%
0
0.0%
Lateral
1
1
1.6%
1
0.9%
0
0.0%
TIMI Flow
0
0
0.0%
1
0.9%
0
0.0%
1
1
1.6%
3
2.7%
1
2.8%
2
6
9.4%
13
11.6%
6
16.7%
3
57
89.1%
95
84.8%
29
80.6%
CAD 1-Vesssel
1
27
42.2%
28
25.0%
9
25.0%
2- Vesssel
1
25
39.1%
45
41.1%
11
30.6%
3- Vesssel
1
12
18.8%
38
a
33.9%
16
a
44.4%
Culprit vessel
64
112
36
LAD
1
28
43.8%
51
45.5%
18
50.0%
RCA
1
25
39.1%
46
41.1%
17
47.2%
LCX
1
9
14.1%
14
12.5%
1
2.8%
D1
1
0
0.0%
1
0.9%
0
0.0%
MI
1
2
3.1%
0
0.0%
0
0.0%
VSG
0
64
100.0%
112
100.0%
36
100.0%
When analyzing laboratory baseline data, significant
changes were observed in variables: creatinine, Hb,
and glucose in different CHA2DS2VASc groups.
Table 3 presents the averages of creatinine, Hb, and
glucose in each of the CHA2DS2VASc groups but
also the 95% confidence intervals where these
averages are located (respectively LCL and ULC).
Creatinine increased only in the third group of
CHA2DS2VASc, Hb decreased significantly
throughout the three levels of CHA2DS2VASc,
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
463
Volume 21, 2022
while glucose displayed an increase in the two higher levels.
Table 3. Laboratory data
low-level group
CHA2DS2VASc
medium-level group
CHA2DS2VASc
high-level group
CHA2DS2VASc
(A)
(B)
(C)
Mean
LCL
UCL
Mean
LCL
UCL
Mean
LCL
UCL
Creatinine (mg/dl)
.98
.93
1.02
1.03
.99
1.08
1.12
A B
1.04
1.20
Hb (g/dl)
13.63
BC
13.32
13.94
12.94
C
12.69
13.20
11.91
11.33
12.48
Glucose(mg/dl)
126.33
116.95
135.70
178.89
A
166.14
191.65
181.50
A
157.57
205.43
The hospitalization time varied from 1 to 20 days.
The average length of stay (ALOS) in a hospital was
5.444, [5.444 ± 0.36]. In 50% of cases, the stay time
was 4-7 days. There was no statistical difference in
the hospitalization time between the
CHA2DS2VASc groups.
Table 4 shows the therapy of patients during
hospitalization. During the in-hospital treatment, a
greater use of diuretics, nitrates, and positive
inotropes (Dobutamine, Dopamine, and
Noradrenaline) was noticed in the third group of
CHA2DS2VASc.
Table 4. In-hospital therapy
low-level group CHA2DS2VASc
medium-level group
CHA2DS2VASc
high-level group
CHA2DS2VASc
(A)
(B)
(C)
N
%
N
%
N
%
DAPT
641
100.0%
1121
100.0%
361
100.0%
Statin
641
100.0%
1121
100.0%
361
100.0%
B- blockers
61
95.3%
106
94.6%
32
88.9%
ACE-I/ARB
Diuretics
Antiarrhythmics
Nitrates
Inotrop+
62
96.9%
107
95.5%
34
94.4%
20
31.7%
50
44.6%
21
a
58.3%
2
3.1%
6
5.4%
4
11.1%
13
20.3%
34
30.4%
19
A b
52.8%
01
0.0%
3
2.7%
6
B
16.7%
As a result of dividing the patients into three groups,
the likelihood of morbidity was recorded at 3.1% in
the low-level group of CHA2DS2VASc, 12.5% in
the medium-level group, and 52.8% in the high-
level one. When analyzing survival data of MACCE
30 days after discharge, it was concluded that the
survival probability for patients had increased from
one CHA2DS2VASc group to another (p-value
<0.01). The survival curves 0, 0 were plotted using
the Kaplan Meier method (Figure1). The Survival
Function Graph of Cardiovascular
Problems for the three levels of CHA2DS2VASc
serves to define the point estimation of the
probability that patients do not show problems in a
certain period of time after surgery. The result of
Long-Rank, (Chi-Square =44.177, p-value=
2.5538E-10), and two other methods: Breslow
(Generalized Wilcoxon), (Chi-Square =44.699, p-
value= 2E-10) and Tarone-Ware (Chi-Square
=44.449, p-value= 2E-10), indicate that likelihood
of MACCE differ among CHA2DS2VASc groups at
many points during the study.
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
464
Volume 21, 2022
Fig. 1: Kaplan- Meier survival curves for cases classified into groups
To study the relationship of MACCE and
independent variables age, gender, HTN, DM, and
CHA2DS2VASc groups, we have used logistic
regression. The multiple logistics model of
MACCE, represented in Table 5, shows the
significant impact CHA2DS2VASc -groups (p-
value 0.02) and smoking (p-value 0.034) have in the
forecast of MACCE. The multiple logistics model 0
is fitting as long as the Hosmer and Lemeshow test
result is Chi-square 5.191 and sig. 0.737. This
model justifies 54% of the variation of MACCE.
Furthermore, a patient from high-level
CHA2DS2VASc -group has higher odds for
MACCE compared to a patient from
CHA2DS2VASc group 1, (4.939 times higher, p-
value = 0.026).
Table 5. The multiple logistics model of MACCE Total
Variables in the Equation
B
ODD RATIO
P-Value
Step 1a
Age
.031
1.060
.303
Sex
.466
.486
.486
Smoking
1.362
4.503
.034
HTN
-.392
.182
.669
DM
.677
1.561
.212
CHA2DS2VASc group (1)
7.829
.020
CHA2DS2VASc group (2)
1.083
1.168
.280
CHA2DS2VASc group (3)
2.926
4.939
.026
Constant
-6.207
8.543
.003
a. Variable(s) entered on step 1: Age, Sex, Smoking, HTN, DM, score group.
A new variable, MACCE Total was created. This is
a Bernoulli variable for patients that had problems
such as stroke, re-infraction, thrombosis, anterior
infarction, or death within 30 days after STEMI
[15]. ROC curves were plotted (false positive rate
versus sensitivity) and areas under the curve (AUC
ROC) were calculated, aiming to determine optimal
test cut-offs for the patients with STEMI [16]. In
receiver operating characteristic curve analysis, the
area under the curve, ROC, for predicting MACCE
Total was 0.852 (p =3.155 E-6, 95% CI 0.776–
0.928). The cut-off value for CHA2DS2VASc score
was 4.5 (sensitivity 93.9%, specificity 76.2%),
(Figure 2).
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
465
Volume 21, 2022
Fig. 2: ROC Curve of MACCE Total
4 Results
CHA2DS2VASc score is a basic, useful, and easily
recalled bedside score for predicting in-hospital and
short-term adverse clinical outcomes in STEMI. It is
a good classification of morbidity and mortality in-
hospital and in a short time follow-up, in those
patients. In this study was shown that
CHA2DS2VASc ≥ 4 can be used to determine the
risk of reinfarction and stroke. Additionally,
previous studies have suggested dividing the
patients into two groups according to their
CHA2DS2VASc score. The findings of the present
study appear to agree with the idea of three
CHA2DS2VASc groups as a strong and
independent predictor of MACCE. These
CHA2DS2VASc groups have the important
advantage of identifying extremely low-risk patients
with major adverse cardiovascular and
cerebrovascular events, MACCE, as well as
classifying a portion of patients as high risk. Using a
different therapy for different CHA2DS2VASc
groups (i.e. different antithrombotic therapy for each
group, with greater use of reperfusion therapy for
the high-level group), it is possible to decline in
acute after STEMI. Detection of high creatinine or
glucose in the high-level group may considerably
influence the further treatment of the patients of this
group.
The probabilities of MACCE differ among
CHA2DS2VASc groups at many points throughout
the first 30 days after discharge. They are
approximately shown in Kaplan Meier survival
curves of the three studied groups.
References:
[1] Ly Chen, L Norby, A Chamberlain, R.
MacLehose, L. Bengtson L, P. Lutsey,
and Alonso A, CHA2DS2VASc Score and
Stroke Prediction in Atrial Fibrillation in
Whites, Blacks, and Hispanics. 2019;
https://doi.org/10.1161/strokeaha.118.021453
[2] GP Perna. High CHA2DS2VASc score without
atrial fibrillation: ‘NAO yes, NAO no’.
European Heart Journal Supplements, Volume
21, Issue Supplement_B, March 2019, Pages
B67–B68. 2019;
https://doi.org/10.1093/eurheartj/suz011.
[3] KH Kim, W Kim, SH Hwang, Wy Kang, et al,
The CHA2DS2VASc score can be used to
stratify the prognosis of acute myocardial
infarction patients irrespective of the presence
of atrial fibrillation. Journal of cardiology,
65(2), 121–127. 2015;
https://www.journal-of-
cardiology.com/article/S0914-5087(14)00141-
5/fulltext
[4] J Wei, T Henry, Women Have a Worse
Prognosis Than Men Following STEMI: CON,
American College of Cardiology. 2017;
https://www.acc.org/latest-in-
cardiology/articles/2017/12/20/07/04/women-
have-a-worse-prognosis-than-men-following-
stemi-con
[5] Mr O’Reilly, Ld McCullough, Age and Sex Are
Critical Factors in Ischemic Stroke Pathology,
Endocrinology, Volume 159, Issue 8, August
2018, Pages 3120 – 8131.
2018; https://doi.org/10.1210/en.2018-00465
[6] J Xu, S Jia, Zhu P Pei, L Jiang, P Jiang, Y
Song, et al. Does Prior Stroke Predict Long-
Term Recurrent Stroke After Percutaneous
Coronary Intervention? Five-Year Results from
a Large Cohort Study Front. Neurol., 2021;
https://doi.org/10.3389/fneur. 2021.740136
[7] RA Weir, JJ McMurray, EJ Velazquez,
Epidemiology of Heart Failure and Left
Ventricular Systolic Dysfunction After Acute
Myocardial Infarction, The American Journal
of Cardiology, 97(10), 13–25. 2006;
https://www.ajconline.org/article/S0002-
9149(06)00460-7/fulltext
[8] KA Fox, OH Dabbous, RJ Goldberg, KS Pieper,
KA Eagle, et al, Prediction of risk of death and
myocardial infarction in the six months after
presentation with acute coronary syndrome:
prospective multinational observational study
(GRACE), BMJ (Clinical research ed.),
333(7578), 1091. 2006;
https://www.bmj.com/content/333/7578/1091
[9] G Sofidis, N Otountzidis, N Stalikas, et al.,
Association of GRACE Risk Score with
Coronary Artery Disease Complexity in
Patients with Acute Coronary Syndrome.2021,
https://www.mdpi.com/2077-0383/10/10/2210
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
466
Volume 21, 2022
[10] D Morrow, E Antman, A Charlesworth, et al.,
TIMI Risk Score for ST-Elevation Myocardial
Infarction: A Convenient, Bedside, Clinical
Score for Risk assess.2000; circulation,
102(37), 2031–2037.
https://www.ahajournals.org/doi/10.1161/01.CI
R.102.17.2031
[11] B Hudzik, J Szkodziński, M Hawranek, A
Lekston, et al., CHA2DS2VASc score is useful
in predicting poor 12-month outcomes
following myocardial infarction in diabetic
patients without atrial fibrillation, Acta
Diabetologica, 53(5), 807–815.2016; 2016,
https://link.springer.com/article/10.1007/s00592
-016-0877-6
[12] PG Karadeniz, I Ercan, Examining tests for
comparing survival curves with right-censored
data, Statistics in Transition. New Series, 18(2),
311–328. 2017
https://www.exeley.com/statistics_in_transition
/doi/10.21307/stattrans-2016-072
[13] SJ Pocock, TC Clayton, DG Altman, Survival
plots of time-to-event outcomes in clinical
trials: good practice and pitfalls, The Lancet,
359(9318), 1686–1689.2002;
https://www.thelancet.com/journals/lancet/artic
le/PIIS0140-6736(02)08594-X/fulltext
[14] A Halkin, M Singh, E Nikolsky, et al.,
Prediction of Mortality After Primary
Percutaneous Coronary Intervention for Acute
Myocardial Infarction, Journal of the American
College of Cardiology, 45(9), 1397–1405.
2005;
https://www.sciencedirect.com/science/article/p
ii/S0735109705004171?via%3Dihub
[15] DA Morrow, EM Antman, RP Giugliano, et al.
A simple risk index for rapid initial triage of
patients with ST-elevation myocardial
infarction: an InTIME II substudy.;2006;
https://www.thelancet.com/journals/lancet/artic
le/PIIS0140-6736(01)06649-1/fulltextA
[16] Kurtul, "Usefulness of the CHA2DS2- VASc
Score in Predicting In-Stent Restenosis Among
Patients Undergoing Revascularization With
Bare-Metal Stents", Clinical and Applied
Thrombosis/Hemostasis,
https://journals.sagepub.com/doi/pdf/10.1177/1
076029617716769
Contribution of Individual Authors to the
Creation of a Scientific Article (Ghostwriting
Policy)
--Etleva Beliu, and Endri Raço applied a range of
statistical techniques, analyzed and interpreted
statistical data, as well as formatted, and generated
the reports of this scientific research.
-Kleida Haxhi, and Oriana Zaçaj planned and
managed the complex databases.
Research Ethics and Consent
Participants were informed about the study and their
consent was obtained. The study has complied with
the rules and ethical codes specified in the
Declaration of Helsinki.
Creative Commons Attribution License 4.0
(Attribution 4.0 International, CC BY 4.0)
This article is published under the terms of the
Creative Commons Attribution License 4.0
https://creativecommons.org/licenses/by/4.0/deed.en
_US
WSEAS TRANSACTIONS on MATHEMATICS
DOI: 10.37394/23206.2022.21.53
Etleva Beliu, Endri Raço,
Kleida Haxhi, Oriana Zaçaj, Kostaq Hila
E-ISSN: 2224-2880
467
Volume 21, 2022