IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

International Journal of Research in Information Technology (IJRIT) www.ijrit.com

ISSN 2001-5569

Anesthesia Prediction Using Fuzzy Logic Guide Mr. Yogesh Gaidhane [email protected] Professor, Dr. Babasaheb Ambedkar college of engg. And research, ECE department, R.T.M. Nagpur University, Nagpur, Maharashtra, India Tushar Diwase¹, Akshay Hadke², Akash Pandav 3, Kunal Fule 4

[email protected] ¹,[email protected] , [email protected]

Abstract In the hospitals,for any surgery is performed, the patient must be in anesthetize condition. If the operation precedings for a long time, complete dose of aesthesia cannot be given in a single stroke, it may lead to the patient’s death. If lower amount of anesthesia is given then patient may wakeup at the middle of the operation.So the biggest challenge for doctorsis to calculate appropriate dose of anesthesia. Thus a system proposed based on fuzzy controller to administer a proper dose of isoflurane as an anesthetic agent. Dose of isoflurane is calculated on the basis of parameters like systolic pressure, diastolic pressure and heart rate,body temperature of a patient .The method is based on the analysis of these variables by giving membership function, evaluation of rule based system and defuzzification process to control the depth of anesthesia and decide required dose of isoflurane. The potential benefits of the system are it will increase patient’s safety and comfort, direct anaesthesiologist’s attention to other physiological variables which they have to keep under control by abating their tasks and reduction in the costs of an operation. Thus this system will serve as a guide in developing new anesthesia control systems for patients based on physiological parameters of the patient.

Keywords: Heart rate, diastolic pressure and systolic pressure, fuzzy controller, Dose of Anesthesia 1. INTRODUCTION Anesthesia is a tool used by medical professionals to produce a state of unconsciousness among patient’s body. This state of unconsciousness is normally produced so that doctors can perform otherwise excruciatingly painful procedures on patients. In medical profession, it ensures that the patient’s body remain insensitive to pain and any other mental or physical activity during surgical operation. Various methods to induce anesthesia into the patients’ body are through needle or through inhalation. Accurate inducement of dose of anesthesia through needle is much easier as compared to inducement through inhalation. But if the operation continues to remain for a long time span, say for 6 to 7 hours, entire dose of anesthesia cannot be injected into the patient’s body in a single stroke, it may lead to the death of the patient. At the same time if lesser amount of dose of anesthesia is administered, the patient may get up during the operation. The Tushar Diwase, IJRIT

165

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

benefit of inducing anesthesia through inhalation is that no needles or anything e painful is operated onto the patient’s body until the patient is completely anesthetized [1][2][3].

1.1. Problem Definition As enlighten before anesthesia is used by medical professionals to create a state of unconsciousness among patient’s body. This state of unconsciousness is usually created so that surgeons can perform painful operation on patients. Normally it is a closed loop system, in which anesthesiologist continuously examine various parameters such as systolic pressure, diastolic pressure and pulse rate and based on the variation in input, the percentage of dose of anesthesia is varied in accordance to the response of the patient to the current dose of anesthesia given. But it creates a lot of pressure on the anesthesiologist. As it becomes very difficult to monitor all the parameters at the same time, it creates a lot of pressure on the anesthesiologist so that he cannot pay attention to other physiological factor. Thus an expert system for calculating dose of anesthesia based upon different parameters such as systolic pressure, diastolic pressure and pulse rate is always welcome. To Bhatt monitor the dose ofand anesthesia few fuzzy systems havewith been developed. Microcontroller based fuzzy logic used system as for a[5] common sevoflurane inhalation is by A.Yardimci agent. It does [6]. not Isoflurane react is volatile, light, non flammable, no Prof. chemical colorless liquid and usually does V. not react with has metals chosen it designed as rubbers. ananesthetic anesthetic Because ofbased such useful characteristics ofrequires Isofurane H. T.stabilizers Kashipara, Mr. T.

1.2. Objective of System To build up a system based on fuzzy controller that utilizes linguistic fuzzy rules for simulating anesthesia levels and adjusts the infusion rate with respect to input variables is the main objective. For the modeling purpose fuzzy input variables such as systolic pressure, diastolic pressure and heart rate are obtained from the patient during operational process. Depending upon value of these variables, fuzzy controller calculates appropriate dose of anesthesia which is an output controlled variable. From this we represent membership fuction and according to that initial dose of anesthesia can be calculated with respect to classical two valued logic [7][8]. Relationship among different variables is established by rule based fuzzy controller system [9][10][11]. To visualize the performance and the design of fuzzy controller, MATLAB fuzzy logic controller is used.

2.APPROACHE 2.1 Input and Output Variables: This Fuzzy controller system for administering proper dose of anesthesia has one output variables and three input variables[4][5]. For fuzzy implementation, three input variable along with their ranges are required and this ranges are given below

a. Heart rate (PR):Maximum Value: 95 pulse per minute Minimum Value: 60 pulse per minute b. Systolic pressure (SP):Maximum Value: 145 mm Hg Minimum Value: 95 mm Hg c. Diastolic pressure (DP):-

Tushar Diwase, IJRIT

166

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

Maximum Value: 95 mm Hg Minimum Value: 60 mm Hg And the Dose of anesthesia, that is the output variable which is given as the percentage of concentration of Isoflurane in pure oxygen is given as follows

a. Dose of anesthesia (DOI):Maximum Value: 4 % Minimum Value: 0.1 % Thus to check the depth of anesthesia and decide the dose of anesthetic agent, anesthetist use the fuzzy controller for regulating dose of anesthesia input variables such as systolic pressure, diastolic pressure and heart rate.

2.2 System Development plan There are various steps in system development plan which is used to examine the system in terms of input variable system, to convert these inputs into fuzzy values define membership functions for inputs and outputs, to define rules for the change in output with changes in inputs (these are called as fuzzy logic rules) and at last to stipulate dose of isoflurane based on the value of SP, DP,HR and BT. All these steps are explain below

Input Variables Blood Pressure

Body Temperature

Heart Rate

Fuzzification

Membership Function

Inference Module

If-then

De-fuzzification

Output Variables Dose of Anesthesia

1. Examine the system in terms of input variables: The first step for system development plan is analyzing the system in terms of input variables. Analysis of the system is done in terms of which are the input variables, what is the range for each input value of the variable and how output depends on input.

Tushar Diwase, IJRIT

167

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

2. Conversion of inputs into fuzzy values : Input variable’s values are the crisp values. First we have to convert input variable’s values into fuzzy values as they are the crisp values. This process of conversion of crisps values into fuzzy values is known as fuzzification. In such a transformation, for each input and output variable, membership function and degree of truth in each premise is determined. System contains input and output variables with different predicates for the diastolic pressure (DP) , systolic pressure (SP) and heart rate (HR). Fuzzification takes a real time input value of above mentioned physiological parameters and compares it with membership function information to produce fuzzy input value.

3. Define membership functions for outputs and inputs : How each point in the input space is mapped to a membership value between 0 and 1 is defined by membership function (MF) curve. Here to declare membership function for input and output variable, Trapezoid membership function is used . Trapezoid membership function is given as: trapmf(x, [a b c d]) = MAX{MIN {(x – a) / (b – a),1, (d – x) / (d – c)},0} Figure 1, 2 and 3 shows membership function for diastolic pressure, systolic pressure and heart rate. SSM, SM, N, HN, HHN are the predicates for input and output variable.

Fig 1: Membership Function for Diastolic pressure

Fig 2: Membership Function for Systolic Pressure

Fig 3: Membership Function Editor for HR

Tushar Diwase, IJRIT

168

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

The membership function for Dose of anesthesia which is an output variable is shown in figure 4. System contains output variables with different predicates like low, normal and high.

Fig 4: Membership Function Editor for DOI

4. Define fuzzy logic rules for the change in output with changes in inputs: It is a set of IF-THEN rules and membership functions. The fuzzy rule is: If Θ ... Θ then Θ ..Θ Ancestor shows condition, resultant shows conclusion and Θ represents the logical operator. By attaching a set of fuzzy value inputs to the rule that match up to actual values for the ancestor, a set of actual conclusions can be determined by executing the rule. In general, a single rule alone is ineffective. Two or more rules that can oppose one another are required. Fuzzy set is the output of each rule. A single output fuzzy set is aggregated by using the output fuzzy sets for each rule. At last the resulting set is defuzzified or resoluted to a single number [12][13]. Rule base table for calculating dose of isoflurane is specified in Table

TABLE 1 FUZZY RULE BASE FOR CONTROLLING DOSE OF ANESTHESIA DP SSM

SM

S

M

LM

LLM

SMALL

S

SMALL

M

MODERATE

SM MODERATE HIGH

SMALL

LM SM

SMALL S

M

MODERATE

M

MODERATE M

HIGH SMALL

S

LM SM

M

M MODERATE HIGH

B

LM

P R

SM

P Tushar Diwase, IJRIT

L

169

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

N M HIGH L

LM MODERATE

SM

MODERATE L M

M HIGH

LM

5. Finally specify dose of isoflurane As per the value of diastolic BP, systolic BP and heart rate, the rule base is evaluated and based on that fuzzy value for dose of isoflurane is given. This output value is a fuzzy value which is converted into crisp value by the process known as defuzzification[5][6].

3. FUZZY CONTROLLER SIMULATION To show the dependency of the outputs on any one or more of the inputs, surface viewer is used — that is, it creates and plots an output surface map for the system. In simpler way, surface viewer displays the entire span of the output set based on the entire span of the input set. In Figure 5, surface viewer shows the dependence of output on two inputs like diastolic pressure and systolic pressure. Similarly, Figure 6 and 7 shows surface viewer showing dependency of output that is dose of anesthesia on inputs heart rate and diastolic pressure (DP) and the dependency of output that is dose of anesthesia on two inputs heart rate and systolic pressure (SP).

Fig. 5: 3D Surface Viewer for DOI with Respect To diastolic pressure

Tushar Diwase, IJRIT

170

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

Fig 6: 3D Surface Viewer for DOI with Respect To HR &DP

Fig. 7: 3D Surface Viewer for DOI with Respect HR& SP

Figure 8 displays the graph of dose of anesthesia for DP=80, SP=123 and HR ranging from 60-95. From the graph, it can be observed that value of dose of anesthesia remains unchanged for the heart rate value ranging from approximately 62 mm Hg to 68 mm Hg then increases unexpectedly with rise in value of heart rate. Similarly dose of anesthesia can be graph for different values of input variables.

Fig 8: Graph of dose of Anesthesia for DP=80, SP=123 Vs HR

Table II specifies different values of dose of anesthesia as a percentage of isofurane in oxygen for various values of input variables. Dose of isoflurane can be very easily calculated by using the proposed fuzzy controller for different values of input variables.

TABLE II DOSE OF ANESTHESIA FOR DIFFERENT INPUT VARIABLES Tushar Diwase, IJRIT

171

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

Actual Calculated Dose Dose of of Isoflurane Isofulrane (%) (%)

Pressure

Diastolic pressure

Heart rate

101.00000

66.00000

63.00000

0.56158

0.58000

101.00000

66.00000

69.00000

0.52291

0.50000

101.00000

66.00000

72.00000

0.54452

0.55000

107.00000

72.00000

87.00000

1.85630

1.80000

113.00000

90.00000

78.00000

2.18288

2.00000

113.00000

90.00000

81.00000

3.24951

3.30000

125.00000

72.00000

63.00000

0.54122

0.50000

131.00000

78.00000

78.00000

2.08973

2.00000

131.00000

78.00000

60.00000

2.00000

2.00000

132.00000

80.00000

68.00000

1.85240

1.50000

102.00000

84.70000

81.90000

2.30520

2.40000

128.50000

92.30000

85.00000

3.24960

3.30000

97.00000

68.00000

70.00000

0.52290

0.50000

135.00000

85.00000

85.00000

2.48200

2.50000

105.00000

78.34000

92.89000

1.87470

2.00000

97.00000

66.00000

78.00000

1.28801

1.00000

97.00000

66.00000

79.00000

1.56702

1.50000

99.00000

82.00000

62.00000

0.54452

0.50000

Tushar Diwase, IJRIT

172

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

4. CONCLUSION Present general anesthetic method must assure its three necessary parts, i.e. narcosis, analgesia and muscle relaxation, be adequately covered. In easy language, during anesthesia, the patient must sleep deeply enough, must not experience any pain, and should be totally remain unaware of anything happening to him or her. During weakly balanced anesthesia, it may happen that the patient gets totally paralyzed. That is why accurate information about all of the anesthesia parameters is of extreme importance. The proposed system is depends upon fuzzy controller to administer a appropriate dose of isoflurane as an aesthetic agent. Fuzzy logic simplifies the design of a control strategy by providing a simpler way to understand and perceptive approach to resolve control troubles. The fuzzy logic control system can be utilized as tool that controls the depth of anesthesia. As the system works alone without the anesthesiologist, it can simply be used as a monitor who helps maintain track of depth of anesthesia. Dose of isoflurane is calculated on the basis of physiological factors like diastolic pressure, systolic pressure and heart rate of a patient .The process is based on the analysis of these variables by specifying membership function, estimation of rule based system and defuzzification process to control the depth of anesthesia and decide essential dose of anesthesia.

5. REFERENCES [1]COLLINS, V.J., “General Anesthesia Fundamental Considerations”, 3th Edition, Philadelphia, Lea&Febiger, pp:314-359, 1993 [2]VICKERS, M.D., MORGAN, M., SPENCER, P.S.S.,”General Anaesthetics”, 7th edition, Butterwurth-Heineman Ltd., Oxford, pp:118-159, 1991 [3].GILBERT, H.C., VENDER, J.S., “Monitoring the Anesthetized Patient”, Clinical Anesthesia, pp: 742-743, 1992 Proceedings – 23rd Annual Conference – IEEE/EMBS Oct.25-28, 2001, Istanbul, TURKEY [4] M. Logesh Kumar , R.Harikumar, A. Keerthi , “Fuzzy Controller for Automatic Drug Infusion in Cardiac Patients”, Proceedings of the International MultiConference of Engineers [1]VICKERS, M.D., MORGAN, M., SPENCER, P.S.S.,”General Anaesthetics”, 7th edition, ButterwurthHeineman Ltd., Oxford, pp:118-159, 1991 [2].GILBERT, H.C., VENDER, J.S., “Monitoring the Anesthetized Patient”, Clinical Anesthesia, pp: 742-743, 1992 Proceedings – 23rd Annual Conference – IEEE/EMBS Oct.25-28, 2001, Istanbul, TURKEY [3]COLLINS, V.J., “General Anesthesia Fundamental Considerations”, 3th Edition, Philadelphia, Lea&Febiger, pp:314359, 1993 [4] M. Logesh Kumar , R.Harikumar, A. Keerthi , “Fuzzy Controller for Automatic Drug Infusion in Cardiac Patients”, Proceedings of the International MultiConference of Engineers and Computer Scientists 2009 Vol I,IMECS 2009, March 18 - 20, 2009, Hong Kong.

Tushar Diwase, IJRIT

173

IJRIT International Journal of Research in Information Technology, Volume 2, Issue 3, March 2014, Pg: 165-174

[5] Prof. H. T. Kashipara, Mr. T. V. Bhatt, “Fuzzy Modeling and Simulation for Regulating the Dose of Anesthesia” International conference on “control, automation, communication and energy conservation ” -2009, 4th-6th june 2009. [6] A.Yardimci, A.Ferikoglu, “Depth control of sevofluorane anesthesia with microcontroller based fuzzy logic system”, Proceedings – 23rd Annual Conference – IEEE/EMBS Oct.25-28, 2001, Istanbul, TURKEY [7] John Yen and Reza Langari, “Fuzzy Logic: Intelligence, Control and Information,” Pearson Education, pp. 4677, 2005. [8] Riza C. Berkan and Sheldon L. Trubatch, “Fuzzy System Design Principles,” IEEE press, pp. 83-129, 2000. [9] Jan Jantzen, "Foundation of Fuzzy Control," John Wiley and Sons, pp. 51-68, 2007 [10] Senen Barro and Roque Marin, “Fuzzy Logic in Medicine,"Physica – Verlag, pp. 93-97, 2002. [11] S. N. Sivanandam, S. Sumathi and S. N. Deepa, “Introduction to Fuzzy Logic using MATLAB," Springer, pp. 200-204, 2007. [12] D.A. Linkens,. J.S. Shieh, and J.E. Peacock, (1994). Machine Learning Rule-Based Fuzzy Logic Control for Depth of Anaesthesia. IEE Control ’94, 31-36. [13] Benhur Aysin, Elif Aysin. “Effect of Respiration in Heart Rate Variability (HRV) Analysis”, Engineering in Medicine and Biology Society, 2006. EMBS '06. 28th Annual International Conference of the IEEE Aug. 2006, pp. 1776 – 177

Tushar Diwase, IJRIT

174

Anesthesia Prediction Using Fuzzy Logic - IJRIT

Thus a system proposed based on fuzzy controller to administer a proper dose of ... guide in developing new anesthesia control systems for patients based on ..... International conference on “control, automation, communication and energy ...

1MB Sizes 0 Downloads 347 Views

Recommend Documents

Wall Follower Robot Using Fuzzy Logic: A Review - IJRIT
system that enables a mobile robot in moving through a corridor or following a .... The gain scheduling controller will be used before the FLC to control the error signal ... 2) computing the path winding number, 3) learning a combinatorial map,.

Wall Follower Robot Using Fuzzy Logic: A Review - IJRIT
and to enter open areas of the rooms [1,2]. In attempts .... Computer simulations are carried out to compare between a Knowledge Based Fuzzy Logic Controller.

Using Fuzzy Logic to Enhance Stereo Matching in ...
Jan 29, 2010 - Stereo matching is generally defined as the problem of discovering points or regions ..... Scheme of the software architecture. ..... In Proceedings of the 1995 IEEE International Conference on Robotics and Automation,Nagoya,.

Introduction to Fuzzy Logic using MatLab - Sivanandam Sumathi and ...
Introduction to Fuzzy Logic using MatLab - Sivanandam Sumathi and Deepa.pdf. Introduction to Fuzzy Logic using MatLab - Sivanandam Sumathi and Deepa.

Realization of a Ship Autopilot using Fuzzy Logic
control, the Proportional plus Integral plus Derivative (PID) controllers remain common-place. ... changes in speed, water depth, mass loading, the severity of the weather, etc. ... For the course-keeping and the track-keeping problems only the.

TCPS Controller Design Using Fuzzy Logic Controller for Power ...
For economic and ecological reasons, the building of new transmission lines and expansion of existing transmission systems are becoming more and more difficult. In this new situation, it is necessary to utilize the existing power transmission system

Online Electric Vehicle Control Using Fuzzy Logic Controller.pdf ...
There was a problem previewing this document. Retrying... Download. Connect more apps... Try one of the apps below to open or edit this item. Online Electric ...

Fuzzy Logic ilfan.pdf
Interference System (Evaluasi Rule), merupakan sebagai acuan untuk menjelaskan hubungan. antara variable-variabel masukan dan keluaran yang mana ...

Fuzzy Grill m-Space and Induced Fuzzy Topology - IJRIT
IJRIT International Journal of Research in Information Technology, Volume 2, Issue 6, June 2014, Pg: .... Definition 3.13:-Let G be a fuzzy grill on fuzzy m-space.

Fuzzy Grill m-Space and Induced Fuzzy Topology - IJRIT
IJRIT International Journal of Research in Information Technology, Volume 2, Issue 6, June ... Roy and Mukherjee [1] introduced an operator defined by grill on.

Combined Backstepping Adaptive Fuzzy Output Feedback ... - IJRIT
IJRIT International Journal of Research in Information Technology, Volume 2, ... uncertainties, i.e., unstructured uncertainties (unknown nonlinear functions) and ...

Combined Backstepping Adaptive Fuzzy Output Feedback ... - IJRIT
Student BE(IT), Amravati University/ HVPM COET Amravati, Maharashtra, India .... where x Rn and u Rm are the state and the input of system, respectively. w is ...

Application of Fuzzy Logic Pressure lication of Fuzzy ...
JOURNAL OF COMPUTER SCIENCE AND ENGINEER .... Experimental data has been implemen ... The dynamic process data obtained via modelling or test-.

Fuzzy Based QOS in WSN - IJRIT
Keywords: Fuzzy Logic, Quality of Service (QOS), Wireless Sensor Network (Wsn). 1. ... requirement such as the performance measure associated with event ...

Fuzzy Based QOS in WSN - IJRIT
The system results are studied and compared using MATLAB. It gives better and .... yes/no; high/low etc. Fuzzy logic provides an alternative way to represent.

integrating fuzzy logic in ontologies
software consists in a number of different modules providing a .... fit them in the best way to a specific environment or, in ..... In Polkowski, L. and Skowron, A., edi-.

integrating fuzzy logic in ontologies - Semantic Scholar
application of ontologies. KAON allows ... cycle”, etc. In order to face these problems the proposed ap- ...... porting application development in the semantic web.

Ideal Types and Fuzzy Logic
between dimensions, clustering them in two different sets inversely related – AUT, DIV, REG, PRO on one side (bureaucratization) and IMP,. COM on the other ...

Fuzzy Logic (Arabic).pdf
There was a problem previewing this document. Retrying... Download. Connect more apps... Try one of the apps below to open or edit this item. Fuzzy Logic ...