Effect of Hyperlipidemia on Aneurysm: Fuzzy inference analysis

BOUHARATI IMENE1,2, BOUHARATI KHAOULA3, LAOUAMRI SLIMANE4

1Faculty of Medicine, Paris Sorbonne-University, FRANCE

2Laboratory of intelligent systems, UFAS Ferhat Abbas Setif University, ALGERIA,

3Faculty of Medicine, Constantine University, ALGERIA

4Faculty of Medicine, UFAS Ferhat Abbas Setif University, ALGERIA,

Abstract: - Introduction: The abdominal aortic aneurysm is a silent disease. This disease is often detected

by accident when diagnosing another disease. There are many factors that promote this disease. These factors

are mainly related to age. Doppler ultrasound can detect this disease. But often and for more details, we resort

to the scanner. Since the factors that characterize this disease are multiple and complex, this study proposes to

analyze them using artificial intelligence techniques. Method: During a period of two years between 2019

and 2020, around 100 patients are diagnosed at the Sétif hospital in Algeria as well as in other private clinics

in the city. At each diagnosis, the diameter of the aorta is measured and related to hyperlipidemia. A system

of analysis using the principles of fuzzy inference is proposed in the data processing. Result: With the

development of this application, it becomes possible to introduce the variables of hyperlipidemia randomly at

the input of the system to automatically read the diameter of the abdominal aorta possibly planned.

Conclusion: By considering hyperlipidemia as a fuzzy variable, because it is a function of other complex

physiological parameters, this fuzzy analysis makes it possible to compensate for these uncertainties. The

diameter of the abdominal aorta predicted for the hyperlipidemia will be as precise as possible. This tool can

be considered as a preventive aid for the aneurysm.

Key words: Aneurysm, hyperlipidemia, intelligent modeling, fuzzy logic

Received: April 16, 2021. Revised: January 25, 2022. Accepted: February 26, 2022. Published: April 2, 2022.

1 Introduction

A localized deformity of the arterial diameter often

characterized by loss of parallelism is referred to as

an "aneurysm"[1]. We speak of aneurysm as a

disease when the arterial diameter exceeds 30 mm

or 1.5 times the normal value of the diameter[2];[3].

This patient is mainly related to age. It concerns

men much more than women. With age, several

complex physiological factors are involved in the

onset of this disease. At its critical threshold, the

aneurysm can lead to rupture of the abdominal aorta

and even death in proportions of up to a threshold

above 80% [4];[5]. Abdominal aortic aneurysms are

usually located below the renal arteries and end

before the aortic bifurcation.

There are many risk factors. All of these factors are

related to age, including smoking, high blood

pressure, atherosclerosis, hyperlipidemia as well as

the genetic factor. It should be noted that the risk

factors are not the same as the disruptive factors.

Taking into account that these factors are complex

and imprecise, this study is limited just to the

analysis of hyperlipidemia and which itself is

dependent on other factors. Also, we see that the

classical mathematical tools of analysis are very

difficult if not impossible. This study proposes a

tool based on artificial intelligence techniques. The

principles of fuzzy logic are applied to this data

processing. Since fuzzy inference treats the

variables as uncertain variables, these uncertainties

are compensated using this mode of analysis and the

result will be as precise as possible.

2. Risk factors

This study is limited to the hyperlipidemia factor.

This factor can be the cause of other abnormalities

such as cholesterol, high density lipoproteins or

triglycerides. This can lead to cardiovascular

disease. From there, appears the importance of

analyzing hyperlipidemia, because, alongside these

abnormalities, it is a cause of the appearance of

abdominal aneurysm (AAA).

Findings were made in people with high

triglyceride levels where the aneurysm is reported

compared to the rest of the population [6]. Also, the

direct link between cholesterol levels and the

aneurysm is found [7]. Cholesterol can cause crystal

damage to the vascular system and lipids are

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2022.19.8

Bouharati Imene, Bouharati Khaoula, Laouamri Slimane

E-ISSN: 2224-2902

Volume 19, 2022

sometimes the cause of inflammatory factors and

endothelial damage associated with the abdominal

aneurysm [8-12]. Add to that, lipoproteins are

directly linked to the abdominal aneurysm. This is

reported in other studies [13];[14]. The lipoproteins

can be taken as an indicator of the aneurysm [15].

In summary, different factors are linked. These

factors are very complex to analyze by classical

mathematical techniques. The hyperlipidemia-

aneurysm relationship is analyzed in this study.

What characterizes these patients is that they are of

advanced age and mainly male.

Given its complexity and uncertainty, an intelligent

analysis is proposed. The principles of fuzzy logic

are applied.

3. Role of imagery

Doppler ultrasound is considered the first

preparatory vascular diagnostic technique [16];[17].

This technique has the advantage of being invasive

and allows the detection of certain vascular

anomalies. From there, it is necessary to orient the

patient towards the surgical act [18-20].

For the purpose of confirmation, this diagnostic step

can be followed by a CT scan which reveals more

details. For more affinity, CT computed tomography

presents more detail especially when it comes to

anatomical structures [21-[23].

4. Materials and methods

A sample of 100 patients is diagnosed in the

radiology department of the Setif hospital in Algeria

and in nearby private service clinics over a period

from 2019 to 2020. Patients likely to have an

aneurysm are subjected to the preliminary analyzes

the rate of various factors. Among these factors is

hyperlipidemia. Doppler ultrasound imaging is used

in these patients. Confirmation is made by CT

tomography. Abdominal aortic diameter

measurements are linked with hyperlipidemia. In

addition to this factor, the age and gender of the

patients are taken into account.

To analyze these factors, a fuzzy inference system is

proposed. The system is constructed with three input

variables (Age, Gender, Hyperlipidemia) and the

diameter of the abdominal aorta as an output

variable (Figure 1). All of these variables are

considered uncertain and therefore fuzzy variables.

Each variable is fuzzyfied. It is an operation, the

numeric variables are converted into linguistic

variables in human language. This helps to

compensate for these uncertainties. A rule base is

built that supports all possible combinations

between input and output variables. The general

form of the rule base is: [IF… THEN] [24].

Figure 1: Block diagram of the system

4.1. Fuzzyfication of variables

4.1.1. Input variables:

 The input variable ‘Age’ is fuzzyfied into

three triangular shaped membership

functions:

Young: [0 - 30 years old]; Adult: [25 - 60

years old]; Old: [55 - 100 years].

We see the creation of an overlap interval

between two neighboring functions to

compensate for the imprecision associated

with the allocation of ages (Figure 2].

Figure 2. Fuzzyfication of the variable ‘Age’

 The input variable ‘Gender’ is not

fuzzyfied. Numerical values are assigned to

each genre.

Male: [1] ; Female: [2] (Figure 3].

Figure 3. Representation of the variable ‘Gender’

 The input variable ‘Hyperlipidemia’is

fuzzyfied into three triangular shaped

membership functions. Hyperlipidemia is

assigned numeric ranges based on their

severity.

Low: [0 - 2] ; Medium: [1 - 3] ; High: [2 -

4].

We note the creation of an overlap interval

between two neighboring functions to

compensate for the imprecision related to

the assignment of the degrees of severity

(Figure 4].

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2022.19.8

Bouharati Imene, Bouharati Khaoula, Laouamri Slimane

E-ISSN: 2224-2902

Volume 19, 2022

Figure 4. Fuzzyfication of the variable

‘Hyperlipidemia’

4.1.2. Output variable

 The output variable represents the diameter

of the abdominal aorta. This variable is

fuzzyfied into three triangular shaped

membership functions:

Normal: [15 - 25mm] ; Risky: [20 - 40 mm];

Serious : [35 - 60 mm] (Figure 5].

Figure 5. Fuzzyfication of the variable ‘Diameter’

4.2. Basis of the rules

This is to establish the correspondence between

the input variables and the output variable. This

link is made from the actual values measured

during the analysis carried out and the aorta

measurements obtained by imaging. The rule base

must contain all possible combinations.

The mathematical formulation can be written in

the form: d = f (a, g, h)

Where: d (diameter of the aorta)

a: (age)

h: (hyperlpidemia)

The general form of a rule:

IF d is x1 AND a is x2 AND h is x3 THAN d is Y

5. Conclusion

Studies prove the direct link between aneurysm

and various factors that promote it. What

characterizes these factors is complexity,

uncertainty and imprecision. The weight of the

effect on certain factors is known. The precise

effect of other factors is poorly understood. While

in other factors this effect is totally ignored. The

fuzzy analysis proposed in this study supports this

incompleteness and imprecision. By considering

these variables as fuzzy variables, this uncertainty

is compensated for. Once the basis of the rules is

established from the actual measured values and

all possible combinations are introduced, the

output variable expressing the diameter of the

aorta will be possible with maximum precision.

The result expressing the diameter of the aorta is

calculated by aggregating all the rules introduced.

When the system is established, the result is that

the system provides the ability to introduce

random variables at the input to automatically read

the likely value of the diameter of the aorta at the

output (Figure 6).

In the absence of a systematic screening program

for the aneurysm, this tool is intended to provide

preventive support for this disease.

Figure 6

Example of application

Financial support and sponsorship:

Nil.

Conflicts of interest

There are no conflicts of interest.

References

[1]. Collège des enseignants de médecine

vasculaire et Angioweb. Anévrisme de l’aorte

abdominale. In: Traité de médecine vasculaire,

Principes de base, maladies artérielles, Tome 1.

ElsevierMasson. 2010. p. 729.

[2]. 2014 ESC Guidelines on the diagnosis and

treatment of aortic diseases: Document

covering acute and chronic aortic diseases of

the thoracic and abdominal aorta of the adult,

The Task Force for the Diagnosis and

Treatment of Aortic Diseases of the European

Society of Cardiology (ESC). Eur Heart J.

2014;35(41):2873-926.

[3]. Starck J, Aaltonen HL, Björses K,

Lundgren F, Gottsäter A, Sonesson B, et al. A

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2022.19.8

Bouharati Imene, Bouharati Khaoula, Laouamri Slimane

E-ISSN: 2224-2902

Volume 19, 2022

significant correlation between body surface

area and infrarenal aortic diameter is detected in

a large screening population with possibly

clinical implication. Int Angiol J Int Union

Angiol. 2019.

[4]. Fleming C, Whitlock EP, Beil T, et al.

Screening for abdominal aortic aneurysm : a

best-evidence systematic review for the US

preventive services task force. Ann Inter Med

2005 ; 142 : 203–11.

[5]. Ashton HA, Buxton MJ, Day ME, et al.

The Multicentre Aneurysm Screening Study

Group. The Multicentre Aneurysm Screening

Study (MASS) into the effect of abdominal

aortic aneurysm screening on mortality in men :

a randomised controlled trial. Lancet 2002 ;

360 : 1531–9

[6]. Wanhainen A, Bergqvist D, Boman K, et

al. Risk factors associated with abdominal

aortic aneurysm: a population-based study with

historical and current data. J Vasc Surg.

2005;41:390–396.

[7]. Forsdahl SH, Singh K, Solberg S, et al.

Risk factors for abdominal aortic aneurysms a

7-year prospective study: the troms study 1994-

2001. Circulation. 2009;119: 2202–2208. 286–

293.

[8]. Sofi F, Marcucci R, Abbate R, et al.

Lipoprotein(a) and venous thromboembolism in

adults: a meta-analysis. Am J Med.

2007;120:728–733.

[9]. Johnsen SH, Forsdahl SH, Singh K, et al.

Atherosclerosis in abdominal aortic aneurysms:

a causal event or a process running in parallel?

The Troms study. Arterioscler Thromb Vasc

Biol. 2010;30:1263–1268.

[10]. Hellenthal FA, Geenen IL, Teijink JA, et

al. Histological features of human abdominal

aortic aneurysm are not related to clinical

characteristics. Cardiovasc Pathol. 2009;18:

[11]. Mourmoura E, Vasilaki A, Giannoukas A,

et al. Evidence of deregulated cholesterol efflux

in abdominal aortic aneurysm. Acta Histochem.

2016;118:97–108.

[12]. Williams KJ, Tabas I. The response-to-

retention hypothesis of early atherogenesis.

Arterioscler Thromb Vasc Biol. 1995;15:551–

561

[13]. Thompson GR, Seed M. Lipoprotein(a):

the underestimated cardiovascular risk factor.

Heart. 2014;100:534–535.

[14]. Kotani K, Sahebkar A, Serban MC, et al.

Lipoprotein(a) levels in patients with abdominal

aortic aneurysm A systematic review and meta-

analysis. Angiology. 2017;68:99–108.

[15]. Takagi H, Manabe H, Kawai N, et al.

Circulating lipoprotein(a) concentrations and

abdominal aortic aneurysm presence. Interact

Cardiovasc Thorac Surg. 2009;9: 467–470.

[16]. Nwafor IA, Eze JC, Ezemba N, Chinawa

JM, Idoko LF and Ngene CN. Management of

Varicose Veins of the Lower Extremities: A 10-

year Institutional Experience. J Vasc Med Surg

5: 309. doi: 10.4172/2329-6925.1000309

[17]. Rulon L. Hardman ; Paul J. Rochon. Role

of Interventional Radiologists in the

Management of Lower Extremity Venous

Insufficiency. RadioGraphics 2009; 29:525–

536.

[18]. Jutley RS, Cadle I, Cross KS. Preoperative

assessment of primary varicose veins: a duplex

study of venous incompetence. Eur J Vasc

Endovasc Surg 2001; 21:370–373

[19]. Van der Heijden FH, Bruyninckx CM.

Preoperative colour-coded duplex scanning in

varicose veins of the lower extremity. Eur J

Surg 1993; 159:329–333

[20]. Dixon PM. Duplex ultrasound in the pre-

operative assessment of varicose veins.

Australas Radiol 1996; 40:416–421

[21]. Pleass HC, Holdsworth JD. Audit of

introduction of hand-held Doppler and duplex

ultrasound in the management of varicose

veins. Ann R Coll Surg Engl 1996; 78:494–496.

[22]. Whal Lee, Jin Wook Chung, Yong Hu

Yin, Hwan Jun Jae, Sang Joon Kim, Jongwon

Ha, Jae Hyung Park. Three-Dimensional CT

Venography of Varicose Veins of the Lower

Extremity: Image Quality and Comparison with

Doppler Sonography Vascular and

Interventional Radiology. AJR 2008;

191:1186–1191

[23]. Rihyeon Kim, Whal Lee, Eun-Ah Park, Jin

Young Yooand Jin Wook Chung. Anatomic

variations of lower extremity venous system in

varicose vein patients: demonstration by three-

dimensional CT venography. Acta Radiol

OnlineFirst, published on August 26, 2016 as

doi:10.1177/0284185116665420.

[24]. Khaoula B., Imene B., Nassim B.,

Abdelhak L., Soumaya A., Slimane L., &

Boussouf N. Cancer Incidence in Algeria:

Fuzzy Inference System Modeling. Current

Research in Public Health, ((2021). 1(1), 1–7.

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 BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2022.19.8

Bouharati Imene, Bouharati Khaoula, Laouamri Slimane

E-ISSN: 2224-2902

Volume 19, 2022