Intelligent analysis of some factors accompanying hepatitis B
BOUHARATI KHAOULA
1,2*
,
BOUHARATI IMENE
3,4
, GUENIFI WAHIBA
5
,
GASMI ABDELKADER
5
, LAOUAMRI SLIMANE
5
1.Department of Epidemiology, Faculty of Medicine, Constantine University, ALGERIA
2.Laboratory of Health and Environment, UFAS Setif1 University, Setif, ALGERİA
3.Faculty of Medicine, Paris Sorbonne University, FRANCE
4.Laboratory of Intelligent Systems, UFAS Setif1 University, Setif, ALGERIA
5.Faculty of Medicine, Setif University Hospital, UFAS Setif1 University, Setif, ALGERİA
Abstract. Background. It is evident that the B hepatitis disease is favored by several risk
factors. Among the factors analyzed in this study, gender, diabetes, arterial hypertension, and
body mass index. The age of the first infection is related to these variables. As the system is
very complex, because other factors can have an effect and which are ignored, this study
processes data using artificial intelligence techniques. Method. The study concerns 30 patients
diagnosed at our service of the university hospital of Setif in Algeria. The study period runs
from 2011 to 2020. The risk factors are considered imprecise and therefore fuzzy. A fuzzy
inference system is applied in this study. The data is fuzzyfied and a rule base is established.
Results. As the principles of fuzzy logic deal with the uncertain, this allowed us to take care of
this imprecision and complexity. The established rule base maps the inputs, which are the risk
factors, to hepatitis as the output variable. Conclusion. Several factors promote hepatitis B.
The physiological system differs from one individual to another. Also, the weight of each factor
is ignored. Given this complexity, the principles of fuzzy logic proposed are adequate. Once the
system has been completed, it allows the random introduction of values at the input to
automatically read the result at the output. This tool can be considered as a prevention system
in the appearance and and establish a typical profile of people likely to be affected by hepatitis
Keywords: Hepatitis B, Risk factors, İntelligne techniques, Fuzzy logic
Received: May 22, 2021. Revised: March 16, 2022. Accepted: April 17, 2022. Published: May 9, 2022.
1. Introduction
Hepatitis B is a viral inflammatory disease
affecting the liver. Its mode of transmission
is essentially contact with contaminated
blood. While this infection is often mild, in
about 10% of cases it progresses to a
chronic infection. This hepatocyte infection
can cause acute hepatitis and sometimes
cirrhosis or liver cancer [1]. Hepatocellular
carcinomas rank second in the world among
fatal cancers, despite the availability of a
vaccine [2]. Hepatitis B is characterized by
a negative HBeAg status and a positive
HBe phase associated with viral replication.
Adding to that, this profile is very complex
regarding the viral base. This can be the
cause of hepatocellular carcinomas [3]. The
WHO reports that approximately 257
million are classified as chronic carriers [4].
Over a period of nine years, patients
diagnosed at the level of our hospital
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
61
Volume 2, 2022
department for hepatitis, different
parameters are taken. A database is built
summarizing these entire characteristics
specific to each patient. This study attempts
to establish a typical profile of these
patients. Hepatitis B and C are mapped to
accompanying factors. As these factors are
multiple and complex, this study is limited
to five main ones which are sex, diabetes,
blood pressure, age at first infection and
body mass index. Despite this limitation,
the effect and interaction of these factors
remains complex. The individual
physiological response is far from being
homogeneous and mathematically
analyzable. The study proposes an artificial
intelligence technique in data analysis. The
application of the principles of fuzzy
inference is perfectly suited. The principles
of this logic ensure that the uncertainty and
imprecision inherent in the nature of the
data are compensated for. The proposed
system makes it possible to establish a
typical profile of people likely to have
hepatitis with maximum precision.
2. Material and method
During a period from 2011 to 2020, patients
were diagnosed with hepatitis B in our
department at the University Hospital of Setif in
Algeria. For each patient, physiological
parameters are sampled in the database. The
factors considered in this study are: gender,
diabetes, blood pressure, and body mass index
related to the age at first infection.
2.1.Risk factors
The direct relationship of these factors with
hepatitis is reviewed below.
Gender and hepatitis
Studies report that the hepatocarcinogenesis
factor resulting from HBV is much more
pronounced in men than in women [5].
Even in the case of subjects vaccinated at
birth with a booster at 18 years of age, the
prevalence of chronic carriers is higher in
males than in females [6]. In general,
hepatocellular carcinomas resulting from
hepatitis B virus infection occur much more
in men than in women [7]. This only
reveals liver disease between the two sexes
appeared long ago. This, can be explained
in a certain way by the hormonal
androgenic and estrogenic effects [8].
Moreover, this does not only concern
hepatitis but also other diseases [9–13],
either in terms of risk factors or in terms of
disease progression [14].
Diabetes and hepatitis
Type 2 diabetic patients are often tested
during their blood sugar monitoring. This
will expose them to a high risk of
contamination by the hepatitis B or C virus
[15]. These procedures, especially when it
comes to poor blood sampling, put this
population at the highest risk of hepatitis
[16][17]. When blood sampling for diabetes
monitoring is combined with hemodialysis,
this risk is much greater [18–20]. Other
studies report that the risk is much higher
when there is an association between
diabetes and HBV infection [21–26].
Blood pressure and hepatitis
The effect of blood pressure and cirrhosis
has been the subject of several studies. It
has been found that treatment with enzymes
inhibitors, used in the treatment of high
blood pressure, has contributed to the
reduction of chronic viral liver fibrosis
[27].The relationship between HCV
infection and cardiovascular disease
demonstrates an increased cardiovascular
risk due to HCV infection.
Effect of age at the first infection on
hepatitis
he age of HBsAg serodeclaration is
associated with the viral infection of
hepatitis as well as its evolution into
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
62
Volume 2, 2022
cirrhosis. This can be considered as a non-
negligible risk factor [28-30]. The clinical
threshold for this is when the age is greater
than 50 years at the time of HbsAg
serodeclaration [31,32]. The age of
menopause is a determining factor in
chronic hepatitis. This is of lower risk
before this age and higher after. This
median age in women is around 48 years,
varying between 40 and 60 years [33]. This
may explain the effect of age in women
aged between 50 and 60 years after
menopause on chronic hepatitis te without
HBsAg [34].
BMI and hepatitis
Studies report that there is a possible
relationship between BMI and chronic liver
carcinoma and even liver cancer and that
BMI may be a risk factor [35-37]. From a
simple hepatic stenosis, a high BMI in
HBsAg carriers can cause it to switch to a
benign stage and even to cirrhosis [38].
Also, it should be noted that the metabolic
risk associated with hepatic steatosis, which
is considered to be cofactors in the
development of fibrosis, is directly linked
to obesity. This is all the more significant
when the cases are prone to chronic
hepatitis B or C [39-41].
2.2. Fuzzy inference analysis
In an attempt to solve imprecise situations
in the real world, a theory of fuzzy sets was
developed by Lotfi Zadeh in 1965 [42].
Nowadays, fuzzy logic has found its
applications in various fields, including the
medical field [43]. The advantage of fuzzy
inference is that it is able to translate a
human expert's uncertainty and knowledge
to extract a sharp decision. Add to this, the
rules used can be adapted to all situations
[44]. Fuzzy inference consists of matching
a set of input variables to an output variable
based on fuzzy rules [45]. This study uses a
‘Mamdani Fuzzy’ fuzzy inference system.
The result after defuzzification is obtained
from the rules requiring prior fuzzification
[46].
The principle of operation operates on the
mini-max of the functions. The basis of the
rules is of the form:
If X1 is A1 and ….and Xn is An then Y is B.
The numerical variables must be converted
into linguistic variables by the process of
'fuzzyfication' represented here by (A and
B) defined in the universe of discourse (X
and Y).
As the output of the system must be sharp,
it is necessary to extract a sharp value from
the fuzzy set. Defuzzification then operates
inversely to fuzzification. This study uses
the surface center of gravity method after
aggregating all the established rules.
Schematic of the structure of the fuzzy
analysis model. (Figure 1a,b).
Figure 1a. Fuzzy Inference System
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
63
Volume 2, 2022
Figure 1b. Fuzzy system and its integral components in MATLAB 2016a software
Fuzzy Modeling Details
The application of fuzzy logic is developed
in this study to establish a typical profile of
a patient likely to be affected by hepatitis B.
Based on the significant cases diagnosed
(Table 1). The system built has four input
variables and one output. (Figure 2a,b).
Table 1. Parameters of diagnosed cases
N°
Gender
Diabetes
BMI
Age at first
infection
1
M
No
29,74
48
2
M
Yes
28,73
72
3
M
Y/ From 22 Years
24,69
66
4
M
Yes
29,32
36
5
M
Y/ From 9 Years
22,22
41
6
F
No
19,36
64
7
F
No
37,18
72
8
M
Y/ From 4 Years
32,65
36
9
M
Y/ From 4
Months
30,42
78
10
F
No
23,44
31
11
F
No
25,78
69
12
F
Y/4 Years
36,73
37
13
F
No
22,68
48
14
M
No
20,83
32
15
M
No
25,95
13
16
M
Y/ From 1 Years
21,61
29
17
M
No
20,76
32
18
M
Y/ From 16 Years
27,55
61
19
M
No
26,83
26
20
F
No
29,38
49
21
F
Y/ From 20 Years
34,63
69
22
F
No
27,16
31
23
M
No
26,03
51
24
M
No
22,04
65
25
F
Y/ From 5 Years
31,16
62
26
M
Y/ From 3 Years
31,79
63
27
F
No
14,48
83
28
F
No
31,11
30
29
M
No
27,17
24
30
M
Y/ From 3 Years
29,07
60
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
64
Volume 2, 2022
Figure 2a. Schematic of the structure of the fuzzy analysis model
Figure 2b. General structure and membership functions of the model
Inputs fuzzification
a. Gender variable: Variable 'Gender'
is not fuzzified. The 'male' sex is
expressed by [1] and [2] for the
'female' sex (Figure 3).
Figure 3. Gender variable representation
b. Diabetes variable: Variable ‘Diabetes’
is fuzzified into three triangular
membership functions. Ranges are assigned
to each degree of diabetes severity. As the
limits between the intervals are imprecise,
each two neighboring functions overlap in
order to compensate for these inaccuracies.
Mild diabetes [0-2], moderate diabetes [1-
3], severe diabetes [2-4]. (Figure 4).
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
65
Volume 2, 2022
Figure 4. Diabetes variable fuzzification
c. High blood pressure variable: Variable
‘High blood pressure’ is fuzzified into three
triangular membership functions. Ranges
are assigned to each degree of blood
pressure severity. In the same way, three
triangular membership functions are
assigned and intervals are created according
to the degree of blood pressure severity.
Low [0-2], moderate[1-3], High [2-4].
(Figure 5).
Figure 5. Arterial pressure variable fuzzification
d. BMI variable: Variable ‘BMI’ is
fuzzified into five triangular membership
functions. Ranges are assigned to each body
mass index value. (Figure 6).
Numerical representation
Fuzzy representation
Nutritional
status
BMI
BMI
Underweight
Below 18.5
[< 20]
Normal weight
18.5–24.9
[18-27]
Obesity class I
30.0–34.9
[23-37]
Obesity class II
35.0–39.9
[33-42]
Obesity class III
Above 40
[> 38]
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
66
Volume 2, 2022
Figure 6. BMI variable fuzzification
Output fuzzification
Age at the first infection: Variable ‘Age’ is
fuzzified into three triangular membership
functions. Ranges are assigned to each age
at the first infection value. In the same way,
three triangular membership functions are
assigned and intervals are created according
to the age. Also, these values are assigned
according to the ages of the diagnosed
patients shown in the table above.
Young [20-40 years old], Adult [30-50
years old], Old [> 40 years old]. (Figure 7).
Figure 7. Age of the first infection variable fuzzification
Base rules
The general form of a rule is: If..Then. In
this application, the rules are created based
on the numerical values shown in Table 1.
Example:
IF gender is male AND diabetes is average
AND blood pressure is high AND body
mass index is low THEN age susceptible to
hepatitis infection is adult
Each rule refers to the actual values
recorded. The rule base must contain all
possible combinations.
Defuzzification
After the fazzification process where the
numeric variables are translated into
linguistic variables, the fuzzy result at the
numeric output has to be converted back
into a numeric term. This is the process of
defuzzification. The result is obtained by
aggregating the set of inference rules. The
method used is that of the COG (center of
gravity).
In this method, the AND operator is used in
each rule. The aggregation of several rules
uses the OR operator. The result is a surface
at which its center of gravity must be
calculated according to the formula:
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
67
Volume 2, 2022
𝑈 = ∫𝑢. 𝜇(𝜇)𝑑𝑢
𝑀𝑎𝑥
𝑀𝑖𝑛
∫𝜇(𝜇)𝑑𝑢
𝑀𝑎𝑥
𝑀𝑖𝑛
Where: U is the result of the
defuzzification; u is the output variable; µ is
the transfer function; Min and Max are the
limits of the defuzzification
3. Result and discussion
The risk factors that promote hepatitis B are
multiple. Some are known, others totally
ignored, while the weight of some others is
poorly understood. Also, the interaction
between these factors and the physiological
specificity of each individual is impossible
to know. Faced with this situation, it is very
difficult to model them using classical
mathematical techniques.
The proposed tool makes it possible to deal
with this complexity. This study is limited
to only four factors. Like human reasoning,
each factor is considered uncertain and
therefore fuzzy.
The 'fuzzification' makes it possible to
convert the numerical data recorded from
each patient to the linguistic variables of
human language. Input or output variables
are fuzzified. The basis of the rules is
established from the actual recorded data.
Each rule uses the ‘AND’ operator.
Mathematically, the result of this operator
is a function that represents the minimum of
each function expressing each variable.
When several rules are established, it is
then a question of aggregating them with
the ‘OR’ operator. This operator takes the
maximum of the results of each rule. The
resulting surface represents the participation
of the set of all rules.
As the final result must be expressed in net
terms, defuzzification operates inversely to
fuzzification. The calculation of the center
of gravity of this final surface represents the
final output variable. By this technique, all
uncertainties are compensated (Figure 8).
Figure 8. Application example
4. Conclusion
Given the complexity of the risk factors
involved in hepatitis B, it becomes
impossible to model them mathematically.
Some studies attempt to analyze them
statistically. However, the statistical
analysis remains in the realm of the
probable. The significant and the non-
significant remain imprecise terms. This
study offers an intelligent analysis like
human reasoning where complexity is taken
care of and uncertainties are compensated.
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
68
Volume 2, 2022
The established application makes it
possible to randomly introduce variables at
the input to automatically and instantly read
the result at the output. It suffices to set the
patient's sex, his level of diabetes, arterial
hypertension and his body mass index to
predict at what age the degree likely to be
affected by hepatitis B. This application
remains extensible to other factors that do
not are not taken here. This can be a tool to
help prevent this disease.
Financial support and sponsorship:
Nil.
Conflicts of interest:
There are no conflicts of interest.
Appendix
Membership code of Fuzzy analysis module
[System]
Name='HEPATITIS B'
Type='mamdani'
Version=2.0
NumInputs=4
NumOutputs=1
NumRules=40
AndMethod='min'
OrMethod='max'
ImpMethod='min'
AggMethod='max'
DefuzzMethod='centroid'
[Input1]
Name='Gender'
Range=[0 3]
NumMFs=2
MF1='Male':'trimf',[1 1 1]
MF2='Female':'trimf',[2 2 2]
[Input2]
Name='Diabetes'
Range=[0 4]
NumMFs=3
MF1='Mild.Daiabetes':'trimf',[0 1 2]
MF2='Moderate.Daiabetes':'trimf',[1 2 3]
MF3='Severe.Diabetes':'trimf',[2 3 4]
[Input3]
Name='Arterial.Pressure'
Range=[0 4]
NumMFs=3
MF1='Low':'trimf',[0 1 2]
MF2='Moderate':'trimf',[1 2 3]
MF3='High':'trimf',[2 3 4]
[Input4]
Name='BMI'
Range=[0 50]
NumMFs=5
MF1='Underweight':'trimf',[-50000 10 20]
MF2='Normal.Weight':'trimf',[18 22.5 27]
MF3='Obesity.Cl.I':'trimf',[23 30 37]
MF4='Obesity.Cl.II':'trimf',[33 37.5 42]
MF5='Obesity.Cl.III':'trimf',[38 44 50]
[Output1]
Name='Age'
Range=[20 100]
NumMFs=3
MF1='Young':'trimf',[20 30 40]
MF2='Adult':'trimf',[30 40 50]
MF3='Old':'trimf',[40 70 100]
References
[1] European Association for the Study of the
Liver. EASL clinical practice guidelines:
management of chronic hepatitis B virus
infection. J Hepatol. 2012;57:167-85.
[2] Ferlay J, Soerjomataram I, Dikshit R, et al.
Cancer incidence and mortality worldwide:
Sources, methods and major patterns in
GLOBOCAN 2012: Globocan 2012. Int J
Cancer. 2015;136:E359-86.
[3] Sadhna D., Stephen C W., AND Swan N T.
Liver pathology of hepatitis C, beyond
grading and staging of the disease. World J
Gastroenterol. 2016;22(4):1357–1366.
DOI: 10.3748/wjg.v22.i4.1357
[4] World health organization. Global hepatitis
report, 2017. Geneva : WHO; 2017.
[5] Chu CM, Liaw YF, Sheen IS, Lin DY,
Huang MJ. Sex difference in chronic
hepatitis B virus infection: an appraisal
based on the status of hepatitis B e antigen
and antibody. Hepatology 1983;3: 947–50.
[6] Su F, Chen JD, Cheng SH, Lin CH, Liu
YH, Chu FY. Seroprevalence of Hepatitis-
B infection amongst Taiwanese university
students 18 years following the
commencement of a national Hepatitis-B
vaccination program. J. Med. Virol.
2007;79: 138–43.
[7] Chen CJ, Yang HI, Iloeje UH. Hepatitis B
virus DNA levels and outcomes in chronic
hepatitis B. Hepatology 2009; 49: S72–84.
[8] Sheng-Han Wang, Pei-Jer Chen, and Shiou-
Hwei Y. Gender disparity in chronic
hepatitis B: Mechanisms of sex hormones.
Journal of Gastroenterology and
Hepatology 2015;30;1237–1245.
doi:10.1111/jgh.12934
[9] Liu W-C., Liu Q-Y. Molecular mechanisms
of gender disparity in hepatitis B virus-
associated hepatocellular carcinoma. World
J Gastroenterol. 2014;20, 6252.
[10] Wu E.M., Wong L.L., Hernandez B.Y.,
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
69
Volume 2, 2022
Ji, J-F., Jia W., Kwee S.A., Kalathil S.
Gender differences in hepatocellular
cancer: Disparities in nonalcoholic fatty
liver disease/steatohepatitis and liver
transplantation. Hepatoma Res. 2018;4, 66.
[11] Yang D., Hanna D.L., Usher J., Lococo
J. Chaudhari P.; Lenz H-J., Setiawan V., El-
Khoueiry A. Impact of sex on the survival
of patients with hepatocellular carcinoma:
A Surveillance, Epidemiology, and End
Results analysis. Cancer 2014;120, 3707–
3716.
[12] Altekruse S.F., Henley S.J., Cucinelli,
J.A Mcglynn, K. Changing Hepatocellular
Carcinoma Incidence and Liver Cancer
Mortality Rates in the United States. Am. J.
Gastroenterol. 2014;109, 542–553.
[13] White, D.L., Tavakoli-Tabasi S.,
Kuzniarek J., Pascua, R., Ramsey D.J., EL-
Serag, H.B. Higher serum testosterone is
associated with increased risk of advanced
hepatitis C-related liver disease in males.
Hepatology 2011,55, 759–768.
[14] Ba-Essa EM, Mobarak EI, AL-Daghri
NM. Hepatitis C virus infection among
patients with diabetes mellitus in Dammam,
Saudi Arabia. BMC Health Serv Res.
2016,16:313.
https://doi.org/10.1186/s12913-016-1578-0
PMID: 27464785
[15] Thompson ND and Perz Joseph F.
Eliminating the Blood: Ongoing Outbreaks
of Hepatitis B Virus Infection and the Need
for Innovative Glucose Monitoring
Technologies. J of Diabetes Sci and
Technol. 2009,3:283–288.
[16] Cadranel JF, DI Martino V, Lambrey
G, Mourlhon C, Nalet B, Anciaux ML, ET
AL. Prevalence of hepatitis C infection and
risk factors in hospitalized diabetic patients:
results of a cross-sectional study. Eur J
Gastroenterol Hepatol. 2008,20:829–836.
https://doi.org/10.1097/MEG.0b013e3282fc
73a1 PMID: 18794595
[17] Sotiropoulos A, Peppas TA, Skliros E,
Apostolou O, Kotsini V, Pappas SI. Low
prevalence of hepatitis C virus infection in
Greek diabetic patients. Diabet Med.
1999,16:250–252. PMID: 10227572
[18] Ocak S, Duran N, Kaya H, Emir I.
Seroprevalence of hepatitis C in patients
with type 2 diabetes mellitus and non-
diabetic on haemodialysis. Int J Clin Pract.
2006,60:670–674.
https://doi.org/10.1111/j.1368-
5031.2006.00738.x PMID: 16805751
[19] Chehadeh W, Kurien SS, Abdella N,
Ben-Nakhi A, AL-Arouj M, Almuaili T, et
al. Hepatitis C virus infection in a
population with high incidence of type 2
diabetes: impact on diabetes complications.
J Infect Public Health. 2011,4:200–206.
ttps://doi.org/10.1016/j.jiph.2011.05.004
PMID: 22000848
[20] Naing C, Mak JW, Ahmed SI, Maung
M. Relationship between hepatitis C virus
infection and type 2 diabetes mellitus:
meta-analysis. World J Gastroenterol.
2012,18:1642–1651.
https://doi.org/10.3748/ wjg.v18.i14.1642
PMID: 22529694
[21] Schillie SF, Xing J, Murphy TV and Hu
DJ: Prevalence of hepatitis B virus
infection among persons with diagnosed
diabetes mellitus in the United States,
1999-2010. J Viral Hepat 2012,19:
674-676.
[22] Li-Ng M, Tropp S, Danoff A and Bini
EJ: Association between chronic hepatitis B
virus infection and diabetes among Asian
Americans and Pacific Islanders. Dig Liver
Dis 2007,39: 549-556.
[23] Yang SQ, CheN HS, Jiang D, et al:
Relationship between chronic hepatitis C
and type II diabetes mellitus. Zhonghua Shi
Yan He Lin Chuang Bing Du Xue Za Zhi
2003,17: 46-49, (In Chinese).
[24] Qureshi H, Ahsan T, Mujeeb SA, et al:
Diabetes mellitus is equally frequent in
chronic HCV and HBV infection. J Pak
Med Assoc 2002,52: 280-283.
[25] Yang JH, Sun CM, Xu XB and Bao
CX: Susceptibility of diabetes in patients
with positive hepatitis B surface antigen.
Zhongguo Wuzhen Xue Zazhi 2002,2: 564,
(In Chinese).
[26] Parrillia G., Mangusoa F., Orsinia L.,
Coccolia P., Vecchioneb R., Terraccianob
L., DE Lucac N., et al. Essential
hypertension and chronic viral hepatitis.
Digestive and Liver Disease. Volume 39,
Issue 5, May 2007, Pages 466-472.
[27] Badawi A, Di Giuseppe G,
Arora P. Cardiovascular disease risk in
patients with hepatitis C infection: Results
from two general population health surveys
in Canada and the United States (2007-
2017). PLOS ONE 2018. 13(12):
e0208839. https://doi.org/10.1371/journal.p
one.0208839
[28] Liu J, Yang HI, Lee Mh, Lu SN, Jen
CL, Batrla-Utermann R, et al. Spontaneous
seroclearance of hepatitis B seromarkers
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
70
Volume 2, 2022
and subsequent risk of hepatocellular
carcinoma. Gut. 2014,63:1648-57.
[29] Chen YC, Sheen IS, Chu CM, Liaw
YF. Prognosis following spontaneous
HbsAg seroclearance in chronic hepatitis B
patients with or without concurrent
infection. Gastroenterology.
2002,123:1084-9.
[30] Kim GA, Lim YS, An J, Lee D, Shim
JH, Kim KM, et al. HBsAg seroclearance
after nucleoside analogue therapy in
patients with chronic hepatitis B: clinical
outcomes and durability. Gut.
2014,63:1325-32.
[31] Kim GA, Lee HC, Kim MJ, Ha Y, Park
EJ, An J, et al. Incidence of hepatocellular
carcinoma after HBsAg seroclearance in
chronic hepatitis B patients: a need for
surveillance. J Hepatol. 2015,62:1092-9.
[32] Liu F, Wang XW, Chen L, Hu P, Ren
H, HU HD. Systematic review with meta-
analysis: development of hepatocellular
carcinoma in chronic hepatitis B patients
with hepatitis B surface antigen
seroclearance. Aliment Pharmacol Ther.
2016,43:1253-61.
[33] Mcglynn KA, Sahasrabuddhe VV,
Campbell PT, Graubard BI, Chen J,
Schwartz LM, et al. Reproductive factors,
exogenous hormone use and risk of
hepatocellular carcinoma among US
women: results from the Liver Cancer
Pooling Project. Br J Cancer.
2015,112:1266-72.
[34] Yip T.C-F., Chan H.L-Y., Wong V.W-
S., Tse Y-K., Lam K.L-Y., Wong G.L-H.,
Impact of age and gender on risk of
hepatocellular carcinoma after hepatitis B
surface antigen seroclearance, Journal of
Hepatology 2017, doi:
http://dx.doi.org/10.1016/j.jhep.2017.06.01
9
[35] Calle EE, Rodriguez C, Walker-
Thurmond K, et al: Overweight, obesity,
and mortality from cancer in a
prospectively studied cohort of US adults.
N Engl J Med 348: 2003,1625-1638,
[36] Samanic C, Chow WH, Gridley G, et
al: Relation of body mass index to cancer
risk in 362,552 Swedish men. Cancer
Causes Control 2006,17:901-909
[37] Samanic C, Gridley G, Chow WH, et
al. Obesity and cancer risk among white
and black United States veterans. Cancer
Causes Control 15:35-43, 2004
[38] Ming-Whei YU, Wei-Liang SHIH,
Chih-Lin L, Chun-Jen L, Jhih-Wei J, Keh-
Sung T, and Chien-Jen C. Body-Mass
Index and Progression of Hepatitis B: J
Clin Oncol 2008, 26:5576-5582.
[39] Hourigan LF, Macdonald GA, Purdie
D, Whitehall VH, Shorthouse C, et al.
Fibrosis in chronic hepatitis C correlates
significantly with body mass index and
steatosis. Hepatology 1999,29(4): 1215-
1219.
[40] Mena Á, Pedreira JD, Castro Á, López
S, Vázquez P, et al. Metabolic syndrome
association with fibrosis development in
chronic hepatitis B virus inactive carriers. J
Gastroenterol Hepatol 2014,29(1): 173-
178.
[41] Wong GL, Chan HL, Yu Z, Chan AW,
Choi PC, et al. Coincidental metabolic
syndrome increases the risk of liver fibrosis
progression in patients with chronic
hepatitis B–a prospective cohort study with
paired transient elastography examinations.
Aliment Pharmacol Ther 2014,39(8): 883-
893.
[42] Zadeh, L.A. Fuzzy sets, Inf. Control
1965,8,338-353.
[43] Işik H., & Arslan S. The design of
ultrasonic therapy device via fuzzy logic.
Expert Systems with Applications, 2011,38,
7342–7348.
[44] Bouharati K., Bouharati I., GUENIFI
W., Gasmi A., Boucenna N. and Laouamri
S. Liver fibrosis: Intelligent Analysis of
Risk Factors. Asian Journal of Research in
Medicine and Medical Science.2022,4(1):
51-58,.
[45] Kuşan H., Aytekin, O., & Özdemir I.
The use of fuzzy logic in predicting house
selling price. Expert Systems with
Applications 2010,37,1808–1813.
[46] Omid M. Design of an expert system
for sorting pistachio nuts through decision
tree and fuzzy logic classifier. Expert
Systems with Applications, 2011,38, 4339–
4347
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
MOLECULAR SCIENCES AND APPLICATIONS
DOI: 10.37394/232023.2022.2.7
Bouharati Khaoula, Bouharati Imene,
Guenifi Wahiba, Gasmi Abdelkader, Laouamri Slimane
E-ISSN: 2732-9992
71
Volume 2, 2022