Service Mechanism for Diagnosis of Respiratory Disorder

Service Mechanism for Diagnosis of respiratory disorder Severity Using Fuzzy Logic for Clinical Decision support system
Faiyaz Ahamad Dr.Manuj Darbari Dr.Rishi Asthana
 
Abstract: Respiratory disorder is a chronic inflammatory lung disease. Globally Respiratory disorder is based on the functional consequences of airways inflammation, clamitous nature and not proper diagnosis. In this paper our aim to develop Service Discovery Mechanism for Diagnosis of respiratory disorder Severity Using Fuzzy Logic for Clinical Decision support system. An Mechanism system has been Created for fuzzy rule-based system. Five symptoms have been taken for the decision of the respiratory disorder conditions.
Keywords: Respiratory disorder ,Information system, , Fuzzy logic.
I. INTRODUCTION
Respiratory disorder is a major public health issue in the world [1,2]. In the United States alone, it influence 7.2 million teenager and 14.8 million adults. Globally, it affects an estimated 350 million family, and is important for approximately 1 out of every 250 deaths [3, 4]. A survey based study estimated the percentage of Respiratory disorder patients in Western Europe and North America with ―severe‘‘ symptoms to be approximately40% [5]. Especially troubling is that it has increased significantly in the past 2–3 decades in the U.S. and worldwide [6]. Hospital based study on 20,000 children under the age of 18 years in 1979,1984,1989,1994,1999,2004 and 2010 in the city of Bangalore showed a prevalence of Respiratory disorder is 9%, 10.5%, 18.5%, 24.5%, 29.5%, 30.94% and 33.74% respectively. Reasons for this increase are not clear; however it may reflect increased exposure to environmental risk factors [7].The episodes of Respiratory disorder severity cause coughing, wheezing, chest tightness and difficulty in breathing. An Respiratory disorder attack can be life threatening. There are many diseases with almost same symptoms and normally misdiagnosed with Respiratory disorder . Although the occurrence of Respiratory disorder is not known exactly and its diagnosis is unclear but in some populations Respiratory disorder is under-diagnosed. Some sources claim Respiratory disorder is under-diagnosed in teenagers, with event of coughing, wheezing not considered possible cases of and thus not seeking diagnosis and treatment for Respiratory disorder .Diagnosis of Respiratory disorder earlier can show a basic role in medical Diagnosis [10].

Get Help With Your Essay
If you need assistance with writing your essay, our professional essay writing service is here to help!
Essay Writing Service

It is a basic knowledge that if a symptoms of patient different then patient goes to different doctors, therfore different doctors give different opinions regarding the grade of the disease. Also, possible two persons with similar symptoms going to the same doctor may be investigating differently. This show that there is a certain amount of fuzziness in the rational process of a doctor [5,11,12]. Fuzzy logic controller, a outstanding application of Zadeh’s fuzzy set theory [13], is a possible tool for dealing with ambiguity and duplicity. Thus, the expertise of a doctor can be shaped using an fuzzy logic controller. The accomplishment of an fuzzy logic controller builds upon its expertise base on which consists of a database and a rule base. It is attended that the achievement of an Fuzzy logic mainly bank on its rule base, and betterment of the membership function which is gathered in the database is a fine process [8].
II. DESIGNING OF FUZZY INFERENCE SYSTEM FOR DIAGNOSIS OF RESPIRATORY DISORDER
The aim of this work is to develop a service mechanism for diagnosis of respiratory disorder severity, it is the specialized unit of a hospital for patients who require special medical care The system consists of two developmental phases: phase I for implementing the solution to communicative information system and phase II for implementing the solution to the decision support system. So as to bring out the various features and perspectives of both the solutions, the whole system is elaborated with the help of the architectural views and process flow diagram.
Comprehensive Software architecture of Mechanism for Diagnosis of respiratory disorder Severity Information System proposed to combination of the modules- Compliance and Decision Support are well modularized to keep high cohesion and low coupling which are the major design principles of the Software Architecture[9] . The process flow of combined system provides an insight of how the whole system works. The Architectures take care of all the required functionalities by the Diagnosis of respiratory disorder Severity.
Figure.1.1 Comprehensive Software architecture of Fuzzy Inference System for Diagnosis of Respiratory system Information System

2.1 Model Development
Due to this development of the mechanism for Diagnosis of respiratory disorder severity Decision support system play very important role in the development of fuzzy inference system. Different authors provide different definitions and scopes of a decision support system (DSS). Albert and Soumitra defines a DSS as- “Decision support systems (DSS) are interactive, computer-based systems helping decision-makers (individuals and/or groups) to solve various semi-structured and unstructured problems involving multiple attributes, objectives, and goals” [Angehrn-98]. Some say that a DSS provides advices (Active DSS) [Caleb-Solly-03] while others argue that they just provide support to decisions (Passive DSS) [Lee-01]. There are number of event under each classification of fuzzy inference system, where they can work input variable to Output variable find out. We can introduce number of different type of variable to find the accurate severity of respiratory disorder in the patient. due to this Inference system we provide (global)standards for the exchange, management and integration of data that supports clinical patient care and the management, delivery and evaluation of healthcare services. Specifically, to create flexible, cost effective approaches, standards, guidelines, methodologies ,enable healthcare information system interoperability and sharing of electronic health records.

Table 1.1. The number of events under each classification of fuzzy Inference system
Respiratory disorder Symptoms are:
I. Peak Expiratory Flow Rate (PEFR)
II. Daytime Symptom Frequency (DSF)
II. Nighttime Symptom Frequency (NSF)
IV. Peak Expiratory Flow Rate Variability (PEFR
Variability)
V. Oxygen Saturation (SaO2)
2.2 Algorithm for repository Disorder
In the present work all input variables (PEFR, FVC, FEV1 and FEF 25-75%) have been divided into 4 categories such as Low, Medium, High and Very High. Each one is defined by the individual membership functions. Low, Very High is shown by trapezoidal membership function and Medium, High is shown by triangular membership functions. But in case of output variable, it is also divided in to 4 categories as Severe, Moderate, Mild and Normal. Norma and Severe is shown by trapezoidal membership function and Moderate, Mild is shown by triangular membership functions [15,16]

Figure 2.1: Membership Function Input Variable PEFR
Table 2.1: Membership Function Input Variable PEFR

Figure 2.2: Membership Function Plot for Input Variable FEV1
Table 2.2: Membership Function value for Input Variable
FEV1

Membership Function

Type

Parameter

 
 
 

Low

Trapmf

[0 0 0.34 1.14]

 
 
 

Medium

Trimf

[0.8 2.15 3.51]

 
 
 

High

Trimf

[1.24 2.39 3.54]

 
 
 

Very High

Trapmf

[1.33 2.56 5 5]

 
 
 

Figure .23: Membership Function Plot for Input Variable FVC
Table 2.3: Membership Function value for Input Variable FVC

Membership Function

Type

Parameter

 
 
 

Low

Trapmf

[0 0 0.61 1.47]

 
 
 
 

Medium

Trimf

[0.94 1.83

2.72]

 
 
 
 

High

Trimf

[1.19 2.18

3.17]

 
 
 
 

Very High

Trapmf

[1.53 2.6

5 5]

 
 
 
 

 
 
 
 

S. No.

Force Vital

Force Expiratory

Peak

Forced

Respiratory disorder

 

Capacity

Volume in one

Expiratory

Expiratory

Severity

 

(FVC)

second (FEV1)

Flow Rate

Flow 25–75%

 

 
 
 

(PEFR)

(FEF25-75%)

 

1.

Low

Low

Low

Low

Severe

2.

Medium

Medium

Medium

Medium

Moderate

3.

High

High

High

High

Mild

4.

Very High

Very High

Very High

Very High

Normal

5.

None

Very High

High

High

Mild

6.

None

Very High

High

Very High

Mild

7.

None

Very High

High

Medium

Moderate

8.

None

Very High

High

Low

Severe

9.

None

Very high

Medium

Low

Severe

10

None

Very High

Medium

Medium

Severe

11.

None

Very High

Medium

High

Moderate

12.

None

Very High

Medium

Very High

Mild

13.

None

High

Low

High

Mild

14.

None

High

Low

Medium

Moderate

15.

None

Medium

Low

Medium

Moderate

16.

Medium

Medium

Low

Medium

Moderate

17.

Low

Medium

Low

Medium

Moderate

18.

Low

Low

Low

Medium

Severe

19.

Medium

Low

Low

Medium

Moderate

Figure 2.4: Membership Function Plot for Input Variable FEF2575
Table 2.4: Membership Function value for Input Variable FEF2575

Figure 2.5: Membership Function Plot for Output Variable
Respiratory disorder Severity
Table 2.5: Membership Function value for output Variable Respiratory disorder Severit

Membership Function

Type

Parameter

 
 
 

Low

Trapmf

[0 0 1.35 2.77]

 
 
 

Medium

Trimf

[1.24 2.57 3.9]

 
 
 

High

Trimf

[1.44 2.96 4.48]

 
 
 

Very High

Trapmf

[1.86 3.14 5 5]

 
 
 

Table 2.6 shows the rule base for the respiratory disorder inference system.
Figure 2.6: Rule Viewer for Repository Disorder Inference System.
There are various input and Output Variables, on the basis of which we design 19 rules selecting an item in each input and output variable using AND Operation. These Variable are selected as the basis of rule defined in the FIS. THE RULES ARE spreads on the left row. these rules are viewed on the basis of status line selected a rule number. The first four plots in the graph yellow plots. which shows the membership function referred to anterior, and if-part of each defined rules.
The fifth column of plot as shown in graph blue plots shows membership function, or the then- part of each defined rules. the design which are untouched in the if-part of any defined rule corresponds to the characterization of the variable in the defined rules. The end plot in the fifth column represent the
Aggregate weighted decision for the given FIS System. this agreement will depend on the input values defined for the plot. The output is shows as on vertical line of the plot. variables and their current values are displayed on the top of the columns in the plot.

S.NO.

FVC

FEV1

PEFR

FEF25-75%

Field data output

System Output

1

3.78

4.15

7.13

3.32

Normal

81.7(N)

2

4.28

3.34

8.13

3.29

Normal

83.2(N)

3

2.68

2.29

5.74

3.21

Mild

60.5(Mi)

4

3.49

4.14

6.80

3.31

Normal

78.9(Mi)

5

1.99

1.96

3.58

2.49

Moderate

41.2(Mo)

6

2.74

1.42

5.50

1.41

Moderate

58.7(Mo)

7

0.86

0.72

1.79

1.29

Severe

21.5(Se)

8

2.08

1.98

2.57

2.29

Moderate

38.6(Se)

Table.3.2 Results of the Fuzzy inference system output and field data output
III. RESULTS AND ANALYSIS
Based on the rules define in the FIS system computed the on the basis of information severity of Respiratory disorder by implement AND connection and after that we defuzzify the generated output using the centric method [14]. The AND operation has been used to perform logical operation .In fuzzy logic system the truth of any statement is matter of degree so the AND connection performed a min operation.
The truth table has been converted to a plot of these fuzzy sets then fuzzy create single set. Figure 3.1 show the operations work over a continuously changes range of truth values A and B on the defined fuzzy operations [17].

Table 3.1: Logical operation AND table performed Fuzzy Logic

Figure 3.1: AND operation varying range of truth table A and B
The output of this system presents the possibility of Respiratory disorder severity gradation from very high to very low in terms of measured values (0-100). These outputs are classified in four classes presenting the status of patients as a risk of Respiratory disorder. These classes include Severe (0-40), Moderate (40-60), Mild (60-80) and Normal (80-100) Table.3.2.
Defuzzification of the Output
As much as fuzziness in fuzzy system support the rule evaluation during the transitional steps, the final desired output obtained input variable is generally a individual number. However, the accumulated of a fuzzy set cover a range of output values and defuzzified in order to resolve a single output value from the set [18,19].

Dca(c)=
(Figure 3.2). The defuzzified value has been computed based on the following equation;
Figure 3.3: Defuzzification of the aggregate output
Where dCA(C) is the defuzzified value and C is the Membership Function [17]. Based on the AND operation every defined rule has been examined for a given set of defiend Input values and the rule defiend which satisfied the operational logic has been used to generate the output for the FIS. So that each rule has been aggregated and AFTER THE defuzzified using centroid OPERATION to generate a single output which is a single number representing the severity of Respiratory disorder .
IV. CONCLUSION
The purpose of the proposed work is to design a system for the diagnosis of Respiratory disorder severity using Fuzzy Logic, so that familiar people who assume little bit of Respiratory disorder may use the system and obtain the result on the bases of severity of Respiratory disorder, which will be defiend to support appropriate corrective purposes before the harshness increases. Fuzzy logic system used for respiratory system severity that these result are better than other conventional system. These system are well supported in the medical science , doctor’s and practitioners. Who faced a problem due to result of respiratory in conventional system The result obtained by the using of FIS system are accurate and very helpful in the field of medical science. the Table.3.2 Results of the Fuzzy inference system output and field data output
adequacy of the system developed is to be endorsed by the doctors in the ground conclusion.
V. REFERENCES
[1]. Yawn B. P. (2008). ―Factors accounting for asthma variability: achieving optimal symptom control for individual patientsâ€-. Primary Care Respiratory Journal, 17: 138-147.
[2]. Teresa To, Sanja Stanojevic, Ginette Moores, Andrea S Gershon, Eric D Bateman, Alvaro A Cruz, Louis-Philippe Boulet,(2012) Global asthma prevalence in adults: findings from the cross-sectional world health survey, BMC Public Health, 12:204.
[3]. Robert H. Lim, Lester Kobzik, Morten Dahl, (2010), Risk for Asthma in Offspring of Asthmatic Mothers versus Fathers: A Meta-Analysis,
[4] Bousquet,J., Jeffery,P.K., Busse,W.W., Johnson,M. and Vignola,A.M. (2000). ―Asthma: From broncho constriction to airways inflammation and remodelingâ€-. American J. RespirCrit Care Med. 16: 1720-1745.
[5]. Klaus F. Rabe, Mitsuru Adachi, Christopher K.W. Lai, Joan B. Soriano, Paul A. Vermeire, Kevin B. Weiss, and Scott T. Weiss,(2004) Worldwide severity and control of asthma in children and adults: The global Asthma Insights and Reality surveys, Journal of Allergy Clinical Immunol VOLUME 114, NUMBER 1, pp-40-47.
[6]. Lim RH, Kobzik L, Dahl M (2010) Risk for Asthma in Offspring of Asthmatic Mothers versus Fathers: A Meta-Analysis. PLoS ONE 5(4).
[7] .Pradeepa P. Narayana, Mithra P. Prasanna, S. R. Narahari, and Aggithaya M. Guruprasad, (2010), Prevalence of asthma in school children in rural India, Annals of Thoracic Medicine, 5(2): 118–119.
[8] M.R. Partridge, (2007), examines the unmet need in adults with severe asthma, Eur Respir Rev, 16: 104, 67–72.
[9] F. Ahamad “Service mechanism for clinical decision support system for an Intensive care units” 978-1-4799-1205-6/13/$31.00 ©2013 IEEE
[10] Guidelines for Management of Asthma at Primary and Secondary Levels of Health Care in India (2005). http://www.indiachest.org/pdf_files/Asthma guidelines.pdf.
[11]. Behl RK, Kashyap S, Sarkar M, (2010), “Prevalence of bronchial asthma in school children of 6-13 years of age in Shimla city”, Indian J Chest Dis Allied Sci, 52(3):145-8.
[12]. Zadeh,L.A. (1965). “Fuzzy sets”. Inform. Contr. 8:338-353.
[13]. Zadeh,L.A. (1973). “Outline of a new approach to the analysis of complex systems and decision processes”.IEEE Transactionson Systems, Man andCybernetics.3: 28-44.
[14] .Sethi, S, Murphy, TF (2008), Infection in the pathogenesis and course of chronic obstructive pulmonary disease. N Engl J Med; 359:2355.
[15] .Hargreave F. E. and Parameswaran K. (2006). ―Asthma, COPD and bronchitis are just components of airway diseaseâ€-. European Respiratory Journal. 28: 264-267.
[16] Payne T.(2000) Computer decision support system. Chest; 118:47-52.
[17] Novák,V., Perfilieva,I. and Mockor,J. (1999). ―Mathematical principles of fuzzy logicâ€- Dodrecht: Kluwer Academic. 45-50.
[18] Pratihar,D.K., Deb,K. and Ghosh,A. (1999). ―A genetic-fuzzy approach for mobile robot navigation among moving obstaclesâ€-.Int. J. Approx. Reason.20: 145-172.
[19]. Roychowdhury,A., Pratihar,D.K., Bose,N., Sankaranarayanan,K.P. and Sudhahar,N. (2004). ―Diagnosis of the diseases – using GA fuzzy approachâ€-.Information Sciences.162: 105-120.