development of an expert system for diagnosis ...manzaramesh.in/prephdbooks/ppt/03 nmu_2 by...

60
Presented by Shaikh Abdul Hannan Under the guidance of Dr. R.J. Ramteke North Maharashtra University, Jalgaon. Development of an Expert System for Diagnosis and Appropriate Medical Prescription of Heart Disease using Neural Network Techniques

Upload: others

Post on 23-Mar-2020

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Presented by

Shaikh Abdul Hannan

Under the guidance of

Dr. R.J. Ramteke

North Maharashtra University, Jalgaon.

Development of an Expert System for Diagnosis

and Appropriate Medical Prescription of Heart

Disease using Neural Network Techniques

Page 2: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

The term heart disease ◦ to a number of illness

circulatory system,

heart and blood vessels.

Heart attack ◦ sudden pain in chest with sweating,

breathing difficulty, giddiness, palpitations etc.

Heart disease◦ one or more valves

in the heart are

through heart properly .

16

Page 3: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

• This can put

– on the heart

• breathlessness and sweating .

• The patients

– under proper treatment

• many useful years.

• Heart disease factor

• in human beings

– medical research area.

17

Page 4: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Symptoms of heart disease

◦ depend on the duration, severity, and type of disease.

Weakness or dizziness

Nausea

Sweating

Vomiting

Pain in the chest or arm

Discomfort to the back, jaw, or throat

Choking feeling (may feel like heartburn)

Shortness of breath

Rapid or irregular heartbeats

18

Page 5: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

A complete Medical evaluation ◦ Medical history

◦ Systems enquiry

◦ Physical examination

◦ Appropriate laboratory or imaging studies

◦ Analysis of data

◦ Medical decision making to obtain

diagnoses

treatment plan.

19

Page 6: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

The data is collected◦ from Sahara Hospital Jinsi, Roshan Gate, Aurangabad

under supervision of

Dr. Abdul Jabbar (MD Medicine).

All the data is prepared◦ from the patients case papers.

20

Page 7: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Patient Case

paper

This is one of the

patient report from

which the data is

recorded.

21

Page 8: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

22

Page 9: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

23

Page 10: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

24

Page 11: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

25

Page 12: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

The data is collected as symptoms and◦ information about patients details

Such as Previous History (P1)

Present symptoms or disease (P2)

Personal History (P3)

Physical Examination (P4)

Cardio Vascular System (CVS)

Respiratory System (RS)

Per Abdomen (PA)

Central Nervous system (CNS)

Electro-Cardio-Gram (ECG)

and Blood Investigation (BI)

are recorded.

26

Page 13: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

The 300 data collected ◦ regarding heart patients and

are prepared in different Excel Sheets which contains codes of

each symptoms of the patient.

In one excel sheet ◦ 13 sub-sheets has taken

for each field of information

such as for Previous History one sub-sheet has taken and given the name is given (P1),

for Present disease the second sub-sheet and the name is given (P2),

for Personal History the third sheet is taken and the name is given (P3),

like this 13 different sheet has taken for different fields .

27

Page 14: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Code Name of Disease Code Present Disease

1 Hypertension 1 Chest Pain / Discomfort

2 Diabetes Mellitus 2 Retrosternal Pain

3 TB 3 Palpitations

4 Bronchial Asthama 4 Breathlessness

5 Hyperthyroidism 5 Sweating

6 Hypothyrodism 6 Perspiration

7 Old Ischaemic heart disease 7 Giddiness

8 Nil 8 Nausea / Vomiting

9 Interstitial Lung disease (ILD) 9 Epigastric Pain

10 Cerebrovascular Accident(CVA) 10 Left Arm pain

11 Rheumatoid arthritis 11 Syncope

12 Haemorrhoids(Bleeding piles) 12 Unconciousness

13 Rheumatic heart disease 13 Uneasiness/restlessness

14 Atrial fibrillation 14 Back pain

15 Chronic Obstructive Pulmonary Disease 15 Heavyness in Chest

16 Supra Ventricular Tachycardia (S.V.T.) 16 Difficulty in breathing

17 Fibroid with Menorrhagia 17 Cough

18 Dilated Cardiomyopathy 18 Swelling over feet

19 convulsion (fits)

20 Headache

21 Heartburn

22 Jaw / Throat Pain

23 Decrease Apetite

24 Epistaxis (Bleeding from Nose)

Code Personal History 25 Haemoptysis

1 Smoking 26 Both Shoulder Pain

2 Tobacco 27 Bleeding per rectum (PR)

3 Alcohol 28 Haemetemesis (Blood Wrmtlne)

4 Nil 29 Loose motion

Previous History (P1) Present Disease (P2)

Personnel History (P3)

28

Patient Disease Information

Page 15: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Code Physical Examination Code Symptoms

1 altered Conciousness 1 Heart Sounds

2 Orientation 2 Normal heart rate

3 Dyspnoea 3 Tachycardia

4 Fever 4 Bradycardia

5 Low Pulse rate 5 Regular Heart Rhythm

6 Normal Pulse rate 6 Irregular Heart Rhythm

7 High Pulse rate 7 Gallop sound

8 Low systolic Blood Pressure 8 No Abnormality Detected (NAD)

9 Normal Blood Pressure

10 High Blood Pressure

11 Low Respiratory rate Code Findings

12 Normal Respiratory rate 1 Breath Sounds preserved

13 High Respiratory rate 2 Breath Sounds reduced

14 Pallor 3 Basal crepts

15 Jaundice 4 No Abnormality Detected (NAD)

16 Oedema Feet 5 Ronchi

17 Perspiration

18 Saturation Less than 90%

19 NAD Code Finding

20 restlessness 1 Liver (hepatomegaly)

21 cyanosis 2 Spleen (Splenomegaly)

22 Irregular pulse 3 Free Fluid Present

23 General Condition - Not satisfactory 4 Abdominal Distension

24 Facial Puffiness 5 No Abnormality Detected (NAD)

25 cold extremeties 6 Obesity

Respiratory System (RS)

Per Abdomen (PA)

Physical Examination (P4) Cardio-Vascular-System

Patient Disease Information

29

Page 16: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Patient Disease Information

Code Finding Code Findings

1 Conciousness 1 Cardiac Enzymes (High)

2 Orientation 2 Blood Sugar Test Normal

3 Focal Deficit 3 Blood Sugar Test Low

4 No Abnormality Detected (NAD) 4 Blood Sugar Test High

5 Restlessness 5 Kidney Function Test deranged

6 Lipid Profile normal

7 Lipid Profile Abnormal

Code Finding 8 Complete Blood Count Normal

1 ST Elevation 9 Leucocytosis

2 Anterior Wall 10 Anaemia

3 Anteroseptal 11 Thrombocytopenia

4 Inferior 12 Urine Routine

5 Inferoposterior 13 Troponin T/I ( positive )

6 Lateral 14 No Abnormality Detected (NAD)

7 Septal 15 Chest X ray (Cardiomegaly)

8 High Lateral 16 2D-Echo RWMA

9 T Wave inversion 17 2D-Echo LV CLOT

10 ST Depression 18 2d-echo LVH

11 QS complex 19 Hypokalemia

12 LBBB 20 Hyponatremia

13 inferior & lateral(4&6) 21 Thyroid Profile (Abnormal)

14 atrial fibrillation 22 20-Echo - Poor LVEF

15 RBBB 23 Hypercalemia

16 VPB's 24 Chest X-ray (COPD)

17 Sinus Tachycardia

18 Sinus Rhythm

19 Supraventricular tachycardia S.V.T.

20 Left Ventricular hypertrophy (LVH)

21 Ventricular tachycardia / Fibrillation

Electro-Cardio-Gram (ECG)

Blood Investigation (BI)Central Nervous System (CNS)

30

Page 17: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Patient Medicines prescribed by the doctor

MID Medicine name MID Medicine name

1 Alprazolam 27 Fortwin Inj

2 Amlodepine 28 Diazepam Inj

3 Aspirin 29 Nitroglycerin Inj

4 Atenolol 30 Ciprofloxacin Inj

5 atorvastatin 31 Cardarone

6 Clopidogrel 32 Dobutamine Inj

7 DIGOXIN 33 Levolin (Nebolize)

8 Diltiazem 34 Methyl prednisolone

9 Diphenylhydantoin Sodium 35 Oral Hypoglycaemics

10 Enalapril 36 Lactulose syrup

11 Furosemide 37 Eltroxin

12 Ethamsylate 38 Dextrose 25% Inj

13 Insulin Inj 39 Dopamine

14 Iso sorbide dinitrate 40 Warfarin sodium

15 Losartan 41 Iron Capsule

16 Metoprolol 42 Neomercazole

17 Nikorandil 43 Betahistine HCL

18 Ondansetron 44 Kesol Syrup / Inj

19 Paracetamol 45 Vit - B12

20 Perindopril 46 Ethamysylate

21 Ramipril 47 Fenofibrate

22 Trimetazidine 48 Inj Calcium Gluconate

23 Streptokinase Inj 49 (Glucose + Insulin ) Drip

24 Taxim Inj 50 K-bind powder

25 Enoxaparin Inj 51 Syp. Gellusil / Mucaine gel

26 Rabeprazole Inj 52 Sucralfate Syp

ALL MEDICINES

31

Page 18: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Individual Patients Information regarding diseases and symptoms

Sr. No.

Patient

NameAge P1 P2 P3 P4 CVS RS PA CNS ECG BT

1 A 55M 2 1,2,13,5 4 7,10 8 4 5 4 1,3 14

2 B 58M 2 1,2,8 2 7,8,13,14 8 4 5 4 2 7,

3 C 60 M 8 13,7,5 4 1,6,12 8 4 5 4 9 14

4 D 60F 1,2 4,5 4 1,2,7,13,14,16 3,5 3 5 4 12 4

5 E 56F 1 15,16 4 6,9,12 8 4 6 4 10 2

6 F 33M 8 1,4 1 6,10 8 4 5 4 3 2

7 G 60 M 1 15,3,4 4 6,10,12 8 4 5 4 9 14

8 H 60M 1,7 1,17 4 6,9 6 4 5 4 9 9

9 I 50M 7 18 4 3,7,9,16 3 3 1 4 11,3 14

10 J 60F 9,2,3 4 4 7,9,13,18 3 3,5 5 4 11.3 9,10,4

11 K 47M 8 1,5 1 6,10 8 4 5 4 3 9,1,2

12 L 45F 8 1 4 19 8 4 5 4 1,9 14,2

13 M 60F 1,2,6 1,5,8 4 6,10,12,14 8 4 5 4 1,2 1,4,9,10

14 N 50M 1,7 4,3,5,6,15 2 3,7,10,13,17,18 3 3,5 5 4 4,11 15

15 O 75M 7,10 19 4 6,9,14 8 4 5 3 11,4 14

16 P 60F 1 1 4 6,9,12 8 4 5 4 10,9 14

17 Q 60F 1,2,7 3,5,6,7 4 6,9,12 8 4 5 4 9 3

18 R 42M 7 1 4 6,9,12 8 4 5 4 11,4 14

19 S 42M 4 2,5,6,13 4 6,10,12,17,20 8 4 5 5 1,4 4,9,16,17

20 T 55M 7 1,5,6,13 4 20,17,6,10,13 8 4 5 5 1,3,11,4 2,9,10,16,17

Symptoms and Findings

32

Page 19: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Sr. No. Patient

NameMID1 MID2 MID3 MID4 MID5 MID6 MID7 MID8 MID9 MID10 MID11 MID12 MID13 MID14 MID15 MID16 MID17

1 A 1 3 5 6 14 17 19 21 23 25 26 27 29 36

2 B 1 3 5 6 13 14 17 19 21 23 25 26 27 29 36

3 C 14 6 5 1 25

4 D 11 13 14 17 3 5 7 10 29 19 30

5 E 3 14 19 15

6 F 25 6 3 29 5 17 1 21 16

7 G 14 3 5 6 1 26

8 H 29 1 3 5 25 17 16 27 24

9 I 32 11 20 33 14

10 J 14 11 34 3 5 33 35 24

11 K 23 1 5 6 29 25 17 31 16 21 36

12 L 25 1 3 5 29 17 16

13 M 23 25 26 27 28 29 13 1 3 5 16 17 18 21 37 6 36

14 N 11 21 29 1 3 5 17 7 28 19 15

15 O 9 30 33 3 19

16 P 14 1 3 5 2

17 Q 38 3 14 5 1

18 R 25 2 3 5 6 29 17 16

19 S 2 3 5 6 13 14 17 19 21 23 25 26 27 28 29 36

20 T 2 3 5 6 14 16 17 19 21 25 26 27 28 29 36

Individual Patient Medicines prescribed by doctor

33

Page 20: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

After the collection of ◦ 300 Patients information

the data is verified by doctor.

For further training of neural network process ◦ the proposed information is coded into

binary form (0 or 1).

If the symptom is present, ◦ it is represented by one (1) and

if the symptoms or disease is not present at that position it is represented by Zero (0).

34

Page 21: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Suppose for example in the field ◦ P2 (Present Disease)

there are total 29 symptoms

and the patient A is having the symptoms

1, 2, 5 and 13 so these locations are

defined by 1 (one) and

all other locations are defined by 0 (zero).

In such a way all the fields are defined.

◦ All the parameter

are converted in binary numbers

where this is used in neural network

to train the neurons for achieving better result.

35

Page 22: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Age 0110111 {7}P1 010000000000000000 {18}P2 11001000000010000000000000000 {29} P3 0001 {4}P4 0000001001000000000000000 {25} CVS 00000001 {8} RS 00010 {5}PA 000010 {6}CNS 00010 {5}ECG 101000000000000000000 {21} BI 000000000000010000000000 {24}

-------152 Inputs

0110111 010000000000000000 11001000000010000000000000000 0001 0000001001000000000000000 00000001 00010 000010 00010 101000000000000000000 000000000000010000000000

Fig. 3.1 Symptoms and Information Coding of patient A

And medicine given by the doctor for patient A is converted into binary form as shown in fig. 3.2

1010110000000100101010101110100000010000000000000000 (52 Outputs)

Fig. 3.2 Medicines coding of patient A

36

Page 23: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Proper diagnosis◦ is critical,

appropriate treatment the underlying cause.

So in order to present ◦ mathematical form,

a neural network with 152 inputs and 52 outputs

has been created.

37

Page 24: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Total number of neurons ◦ is equal to the number of

input parameters (152) and number of output parameters (52).

This network ◦ MATLAB 7.4

neural network toolbox version 5.0.2.

Out of 300 patient’s data, ◦ 250 were trained and

50 patient’s data were tested using all the following techniques.

38

Page 25: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Diagnosis of Heart Disease, ◦ proper interpretation of the

heart data besides

clinical examination and

complementary investigations

are considered in our work.

In this research work ◦ five ANN architectures were used such as,

Feedforward Back-Propagation Neural Network (BPN),

Generalized Regression Neural Network (GRNN),

Quasi Newton’s Algorithm,

Support Vector Machine (SVM) and

Radial Basis Function (RBF) Networks are used.

39

Page 26: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

40

Page 27: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Step 1: Initialize weight to small random values

Step 2: While stopping condition is false, do

Steps 3-10

Step 3: For each training pair do Steps 4-9

Feed Forward

Step 4: Each input unit receives the input signal xi

and transmits this signals to all units in the above

layer i.e. hidden units.

41

Page 28: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Comparison of Results with Original Medicine

Sr

.

Results obtained by using

FFBP

Medicines prescribed by the

doctor

Extra

Medicine

Medicine not

prescribed

A 1,3,5,6,14,16,17,21,23,25,26,2

7,28

1,3,5,6,14,17,19,21,23,25,26,27,

29,36

16, 19,28

B 1,3,5,6,14,25 1,3,5,6,13,14,17,19,21,23,25,26,

27,29,36

Nil 13,17,19,21,23,25,26,

27,29,36

C 1,3,5,6,14,25 1,5,6,14,25 3 Nil

D 1,3,5,6,14,25 3,5,7,10,11,13,14,17,19,29,30 1,6 7,10,11,13,14,17,19,

30

E 1,3,5,6,14,25 3,14,15,19 1,5,6,25 15,19

F 1,3,5,6,14,25 1,3,5,6,16,17,21,25,29 Nil 16,17,21,29

G 1,3,5,6,14,25 1,3,5,6,14,26 25 26

H 1,3,5,6,14,25 1, 3, 5, 16, 17, 24, 25, 27, 29 14 16,17,24,27,29

I 1,3,5,6,14,25 11,14,20,32,33 1,3,5,6,25 11,20,32,33

J 1,3,5,6,14,25 3,5,11,14,24,33,34,35 1,6,25 11,24,33,34,35

47

Comparison of Results obtained by FFBP with Medicines prescribed by doctor

Page 29: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

25/05/2016

Second International Conference on

Computer Technology, Kerla. 48

•Quasi-Newton search directions provide an attractive alternative

to Newton’s direction requiring only to satisfy the secant equation

•It is an iterative procedure

•They update an approximate Hessian matrix at each iteration of

the algorithm. The update is computed as a function of the

gradient

kkk ysB 1

Page 30: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Sr.. Results obtained by using Quasi

Newtons Algorithm

Medicines prescribed by

the doctor

Extra Medicine Medicine not prescribed

A3,4,8,11,12,14,16,20,24,26,27,28,29,32,

33,38,39,40,41,42,43,45,47,49,50

1,3,5,6,14,17,19,21,23,25,2

6,27,29,36

4,8,11,12,16,20,24,

28,32,33,38,39,40,4

1,43,45,47,

49,50

1,5,6,17,19,21,23,25,36

B

3,4,5,8,13,14, 19,22,26, 27,29,31,

36,37,38,41,42,43,44,45,46,48,50,

52

1,3,5,6,13,14,17,19,21,23,2

5,26,27,29,36

4,8,22,31,37,38,41,

42,43,44,45,4

6,48,50,52

1,6,17,21,23,25

C3,4,8,13,14,19,22,25,29,31,34,35,36,37,

41,44,45,46,48,50,521,5,6,14,25

3,4,8,13,19,22,29,

31,34,35,36,3

7,

41,44,45,46,4

8, 50,52

1,5,6

D3,4,8,13,14,19,22,25,29,31,34,35,36,37,

41,44,45,46,48,50,52

3,5,7,10,11,13,14,17,19,29,

30

4,8,22,25,31,34,35,

36,37,41,44,4

5,46,48,50,52

5,7,10,11,17,30

E3,4,8,14,19,25,29,31,34,35,36,37,41,44,

45,46,48,50,523,14,15,19

4,8,25,29,31,34,35,

36,37,41,44,4

5,46,48,50,52

15

F2,4,5,7,8,11,18,22,24,25,28,31,33,34,36,

37,38,39,40,43,44,45,47,49,501,3,5,6,16,17,21,25,29

2,4,5,7,8,11,18,22,2

4,28,31,33,34,

36,37,38,39,4

0,43,44,45,47,

49,50

1,3,5,6,16,17,21,29

49

Comparison of Results obtained by Quasi Newton’s Algorithm with Medicines prescribed by doctor

Page 31: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

25/05/2016

Second International Conference on

Computer Technology, Kerla. 50

A GRNN is a variation of the radial basis neural networks, which isbased on kernel regression networks.

A GRNN does not require an iterative training procedure as backpropagation networks.

A GRNN consists of four layers: input layer, pattern layer,summation layer and output layer as shown in Fig. 4.5. Thenumber of input units in input layer depends on the totalnumber of the observation parameters. The first layer isconnected to the pattern layer and in this layer each neuronpresents a training pattern and its output. The pattern layer isconnected to the summation layer. The summation layer hastwo different types of summation, which are a single divisionunit and summation units. The summation and output layertogether perform a normalization of output set. In training ofnetwork, radial basis and linear activation functions are usedin hidden and output layers

Page 32: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Sr. Results obtained by using

GRNN

Medicines prescribed by the

doctor

Extra Medicine Medicine not

prescribed

A 1,3,5,6,14,16,17,21,23,25,26,27 1,3,5,6,14,17,19,21,23,25,26,27,2

9,36

19 29,36

B 1,3,5,6,11,14,16,17,21,23,24,25,

26,27,36

1,3,5,6,13,14,17,19,21,23,25,26,2

7,29,36

11,16 13,19,29

C 1,3,5,6,11,17,21,25 1,5,6,14,25 3,11,17,21 14

D 1,3,5,6,11,13,14,17,21,25 3,5,7,10,11,13,14,17,19,29,30 1,6,21,25 7,10,19,29,30

E 3,5,6,14 3,14,15,19 5,6 15,19

F 1,5,6,16,17,21,23,25,29,31,36 1,3,5,6,16,17,21,25,29 31,36 3

G 1,3,5,6,14,17,25 1,3,5,6,14,26 17,25 26

H 1,3,5,6,14,17,25 1, 3, 5, 16, 17, 24, 25, 27, 29 6 24,27,29

I 1,3,5,6,12,15,17,21,25,26 11,14,20,32,33 1,3,5,6,1215,17,

25,26

11,14,20,32,33

J 1,3,5,6,11,14,17,21,25,32 3,5,11,14,24,33,34,35 16,17,21,25,32 24,33,34,35

51

Comparison of Results obtained by GRNN with Medicines prescribed by doctor

Page 33: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

linearly separable case, the decision rules defined by an optimal hyperplane separating the binary decision classes is given as the following equation in terms of

52

N

i

iii bxxysignY1

)(

Page 34: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

25/05/2016

Second International Conference on

Computer Technology, Kerla. 53

Linearly separable statistical technique

The decision function for an SVM is fully specifiedby a subset of the data which defines the positionof the separator, These points are referred to asthe support vectors

The classification function is

N

i

iii bxxysignY1

)(

Page 35: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Sr

.

.

Results obtained by using

SVM

Medicines prescribed by the

doctor

Extra

Medici

ne

Medicine not

prescribed

A 1,3,5,6,16,17,18,21,23,25,26

,27,28,29

1,3,5,6,14,17,19,21,23,25,26,27

,29,36 16,18,28 14,1936

B 1,3,5,6,16,17,18,21,23,25,26

,27,28,29

1,3,5,6,13,14,17,19,21,23,25,26

,27,29,36 16,18, 13,14,36

C 1,3,5,6,11,14,21,22,23,24,25

,26,27

1,5,6,14,25 3,21,22,2324

,26,27Nil

D 1,3,5,6,13,14,17,21,22,23,25

,26,27,28

3,5,7,10,11,13,14,17,19,29,30 1,6,21,22,23,

25,26,2

7,28

7,10,11,19,29,30

E 1,2,3,5,14 3,14,15,19 1,2,5,14 15,19

F 1,2,3,6,13,14,16,17,21,25 1,3,5,6,16,17,21,25,29 2,13,14 29

G 1,2,3,8,11,14,25,26 1,3,5,6,14,26 2,8,11,25,26 5,6

H 1,3,5,6,10,11,14,17,22,25,27 1, 3, 5, 16, 17, 24, 25, 27, 29 6,10,11,14,22 16,29

I 1,3,5,6,10,11,14,20,24 11,14,20,32,33 1,3,5,6,10,24 32,33

J 1,3,5,6,11,14,24,33 3,5,11,14,24,33,34,35 1,6 34,35

54

Comparison of Results obtained by SVM with Medicines prescribed by doctor

Page 36: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

25/05/2016

Second International Conference on

Computer Technology, Kerla. 55

It is a feed forward network with a single layer of hidden units called RBFs.

Its output shows the maximum value at its center points and decrease its output value as its input leaves the center

Page 37: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Calculate the output of the neural network

Where, H – number of hidden layer nodes (RBF function)ynet – output value of mth node in output layer for the nth incoming patternwim – Weight between ith RBF unit mth output nodewo – Biasing term of output node

56

1

( )H

net im i i o

i

y w v x w

Page 38: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Sr. Results obtained by using RBF Medicines prescribed by doctor Extra

Medicine

Medicine not

prescribed

A 1,3,5,6,14,16,17,21,23,25,26,27 1,3,5,6,14,17,19,21,23,25,26,27,29

,3616 19, 29,36

B 1,3,5,6,14,17,21,23,25,26,27,36 1,3,5,6,13,14,17,19,21,23,25,26,27

,29,36 Nil 13,19,29

C 1,5,6,14,25 1,5,6,14,25 Nil Nil

D 3,5,7,10,11,13,14,17,19,29,30 3,5,7,10,11,13,14,17,19,29,30 Nil Nil

E 1,3,5,6,14 3,14,15,191,5,6 15,19

F 1,5,6,16,17,21,23,29,31,36 1,3,5,6,16,17,21,25,2923,31,36 3,25

G 1,3,5,6,14,17,25 1,3,5,6,14,2617,25 26

H 1,3,5,6,14,17 1, 3, 5, 16, 17, 24, 25, 27, 296,14 16,25,27,29

I 1,5,11,14,20,24,25,32,33 11,14,20,32,33 1,3,24 Nil

J 1,3,5,6,11,14,17,21,32,33,34,35 3,5,11,14,24,33,34,351,6,17,21,32 24

57

Comparison of Results obtained by RBF with Medicines prescribed by doctor

Page 39: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Result

prescribed by

FFBP

Result

prescribed by

GRNN

Result

prescribed by

SVM

Result

prescribed by

Quasi

Result

prescribed by

RBF

Result

prescribed by

Doctor

1,3,5,6,14,16,17,2

1,23,25,26,27,28

1,3,5,6,14,16,17,2

1,23,25,26,27

1,3,5,6,16,17,18,2

1,23,25,26,27,28,

29

3,4,8,11,12,14,16,

20,24,26,27,28,29

,32,33,38,39,40,4

1,42,43,45,47,49,

50

1,3,5,6,14,16,17,2

1,23,25,26,27

1,3,5,6,14,17,19,2

1,23,25,26,27,29,

36

0110111 010000000000000000 11001000000010000000000000000 0001

7 24 29 4

0000001001000000000000000 00000001 00010 000010 00010

25 8 5 6 5

101000000000000000000 000000000000010000000000

21 25

Inputs given for patient A

1010110000000100101010101110100000010000000000000000

52

Medicines prescribed by the doctor to patient A

58

Comparison of Results obtained by each technique with Medicines prescribed by doctor

Page 40: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Discussion of First Eight Patients prescribed by RBF with doctor:

Patient A:◦ Medicine no. 16 is beneficial as it reduces the heart rate and thereby reduces

workload and improves outcome. ◦ Medicine no. 19 is a antipyretic drug (to reduce fever) or an analgesic if given,

will not affect the cardiac outcome. ◦ Medicine No. 29 is injectable form of medicine no. 14 which the system has

already prescribed. ◦ Medicine no. 36 is a laxative (Stool Softener) is given to patients who complain

passing hard stools which cannot be judged by the system.

Patient B :◦ Medicine no. 13 is insulin injection which is given to patients having high blood

sugar levels which must be prescribed by the expert system as per sugar levels. ◦ Medicine no. 19 is a antipyretic drug (to reduce fever) or an analgesic if given

will not affect the cardiac outcome. ◦ Medicine No. 29 is injectable form of medicine no. 14 which the system has

already prescribed.

59

Page 41: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Patient C: ◦ The system has prescribed as per the symptoms and physical examination which is justified.

Patient D: ◦ The system has prescribed as per the symptoms and physical examination which is justified.

Patient E: ◦ Medicine no 1 is alprazolam which is anxiolytic and is given to almost all patients and won’t affect the

heart patient.

◦ Medicine no. 5 is Atorvastatin which is a lipid lowering agent and helpful in decreasing cholesterol levels.

◦ Medicine no. 6 and Medicine no. 3 has the same effect.

◦ Medicine no. 19 is an antipyretic drug (to reduce fever) or as an analgesic if given will not affect the cardiac outcome.

Patient F: ◦ Medicine no. 6 has the same action as medicine no. 3 and is already prescribed.

◦ Medicine no. 23 is given only after interpretation of ECG and clinical judgment of patient by the treating physician and that too within first 24 hours of ECG changes which the system can’t identify.

◦ Medicine no. 31 is prescribed only in presence of Arrhythmias and has to be used cautiously.

◦ Medicine no. 36 is given, wont harm the patient’s outcome as it is a stool softener.

60

Page 42: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

In this research work,◦ neural network

diagnosing proper disease and

medical prescription.

The network was ◦ trained with 250 patient’s data

and 50 patients were tested by using all the techniques.

It was found that Radial basis function

satisfactory medical prescriptions.

This research work◦ developing countries

where immediate expert and medical help is not possible.

61

Page 43: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Employing the technology, ◦ specially neural network techniques

in medical application could minimize the cost, time,

human expertise and

medical errors.

This expert system ◦ could prove useful for

paramedical staff and trainee doctors especially at remote places

where medical experts could not give services instantly.

Under those circumstances ◦ the paramedical staff or trainee doctors

can use this system as primary source to save patient life till medical expert arrives.

62

Page 44: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

This research work developed by ◦ using Artificial Neural Network techniques

could be used to assist the doctors in making decision without consulting the specialists directly.

However medicine being a clinical branch, ◦ few drugs has to be

clinical parameters on the basis of judgment and clinical experience

of the treating physician which

cannot recognize

because of lack of vision.

It does not mean ◦ that this research work will

experienced and specialized doctors but the research work will help a

medical practitioner/paramedical staff

in facilitating to prescribe

proper medicines for heart disease.

63

Page 45: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

In future this experiment

◦ will be extended to diagnose

the heart disease using ECG waveform

which will be taken directly by

computer system along with patient’s information.

Hope that such unique

◦ combination may increase more accuracy

64

Page 46: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

69

Page 47: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

70

Page 48: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

Thank You..!

Welcome

71

Page 49: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

1. Ulla Uusitalo, Pirjo Pietinen, Pekka Puska, Globalization, Diets and Noncommunicable Diseases, World Health Organization, Geneva, November 2002.

2. Abdul Hamid M Ragab, Khalid Abdullah Fakeeh and Mohamed Ismail Roushdy, A medical multimedia expert system for heart diseases diagnosis and training, IInd Saudi Sci conference, Fac. Sci., Kau, pp 31-45, Mar 2004.

3. Fraser, H.S.F., et.al, Differential diagnosis of the heart disease program have better sensitivity than resident physicians, Tufts-New England Medical Center, Boston, 2001.

4. Long W., et al., Developing a program for tracking heart failure, MIT Lab for Computer Science, Cambridge, 2001.

5. Fraser, H.S.F., et al., Comparing complex diagnoses a formative evaluation of the heart disease program, MIT lab for Computer Science, Cambridge, 2001.

6. Salem, A.M. Aoushdy, M and HodHod, R.A., A rule based expert system for diagnosis of heart diseases, 8th International conference on soft computing MENDEL, Brno, Czech Republic, pp 258-263, June 2002.

7. R.K. Lindsay, B.G. Buchanan, E.A. Feigenbaum, and J. Lederberg, Applications of Artificial Intelligence for Chemical Inference: The DENDRAL Project. New York, NY: McGraw-Hill, 1980.

8. E.H. Shortliffe, Computer-Based Medical Consultations: MYCIN, New York, NY: Elsevier, 1976.

9. Huyc, Chris. Configuration with R1/XCon, Middlesex University, 1978. http://www.cwa.mdx.ac.uk/bis2040/lect6ES2/xCon.html

10. http://media.wiley.com/product_data/excerpt/18/04712933/0471293318.pdf.

11. Turban, E., Expert System and Applied Artificial Intelligence. New York: Macmillan Publishing Company, pp 74, 1992.

12. Cao Q, Leggio KB, Schniederjans MJ., A comparison between Fama and French’s model and artificial neural networks in predicting the Chinese stock market, Computers & Operations Research 32, pp 2499–2512, 2005.

13. Pai PF, Hong WC., Support vector machines with simulated annealing algorithms in electricity load forecasting, Energy Conversion and Management, 46, pp 2669–2688, 2005.

14. Torres M, Hervás C, Amador F., Approximating the sheep milk production curve through the use of artificial neural networks and genetic algorithms, Computers & Operations Research, 32, pp 2653–2670, 2005.

15. Gagné F, Blaise C., Predicting the toxicity of complex mixtures using artificial neural networks, Chemosphere 35, pp 1343– 1363, 1997.

72

Page 50: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

16. Dohnal V, Li H, Farková M, Havel J., Quantitative analysis of chiral compounds from unresolved peaks in capillary electrophoresis using multivariate calibration with experimental design and artificial neural networks, Chirality 14, pp 509–518, 2002.

17. Vlastimil Dohnal, Kamil Kuca, Daniel Jun, What are neural networks and what they can do?, Biomed pap Med Fac Univ, Palacky Olomouc Czech Repub., 2005.

18. Noakes P., Introduction to Biological Neural Systems, Technical Report, Dept. of Electronic Systems Eng., University of Essex, Colchester, Essex, CO4 3SQ.

19. McCulloch, W.W. and Pitts, W., A Logical Calculus of Ideas Imminent In Nervous Activity, Bull. Math. Biophys. 5, pp 115−133, 1943.

20. Pitts, W. and McCulloch, W.W., How we Know Universals, Bull. Math. pp 127−147, 1947.

21. McClelland, J.L. and Rumelhart, D.E., Parallel Distributed Processing Explorations in the Microstructure of Cognition, Psychological and Biological Models, MIT Press, Cambridge, Vol. 2, 1986.

22. Rosenblatt, F., Principles of Neurodynamics, Spartan Press, Washington, DC, 1961.

23. Minsky, M. and Papert, S., Perceptron: An Introduction to Computational Geometry, MIT Press, Cambridge, 1969.

24. Widrow, B. and Hoff, M.E, Adaptive Switching Circuits, IRE WESCON Convention Record, Part 4, NY, IRE, pp 96−104, 1960.

25. Fausett, L., Fundamentals of Neural Networks, Prentice-Hall, Englewood Cliffs, NJ, 1994.

26. Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper Saddle River, NJ, 1999.

27. Kosko, B., Neural Network for Signal Processing, Prentice Hall, Englewood Cliffs, NJ, 1992.

28. Heden B. Edenbrandt L. Haisty W.K. jr., Pahlm O., Artificial neural networks for the electrocardiographic diagnosis of healed myocardial infarction, Am. J. Cardiol, 74(1), pp 5-8, 1994.

29. Snow P.B., Smith D.S., Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study, J. Urology, 152(5 Pt 2), pp 1923-1926, 1994.

73

Page 51: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

29. Baxt W., Use of an artificial neural network for data analysis in clinical decision making: the diagnosis of acute coronary occlusion, Neural Computation, 2, pp 480-489, 1990.

30. Bounds D., Lloyd P.J., A multi-layer perceptron network for the diagnosis of low back pain, IEEE Int. Conf. on Neural Networks, Vol.II, pp 481-489, 1988.

31. McGonigal M., A New Technique for Survival Prediction in Trauma Care Using a Neural Network, Proc. World Conference on Neural Networks, pp.3495-3498, 1994.

32. Forsstrom J.J., Dalton K.J., Artificial neural networks for decision support in clinical medicine. Ann Med., 27(5), pp 509-17, Oct. 1995.

33. Penny W., Frost D., Neural networks in clinical medicine, Med. Decis. Making, 16(4): pp 386-398, Oct-Dec 1996.

34. Sharpe P.K., Caleb P., Artificial neural networks within medical decision support systems, Scand J Clin Lab Invest Suppl, pp 3-11, 1994.

35. McCulloch, W. and W. Pitts., A Logical Calculus of the Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics, Vol. 5, pp. 115-133, 1943.

36. Chuan Zhang Tang and Hon Keung Kwan, Parameter effects on convergence speed and generalization capability of Backpropagation algorithm, International Journal of Electronics, Vol. 74, No. 1, pp 35-46, 1993.

37. S.N.Sivanandam, S.Sumathi and S.N.Deepa, Introduction to Neural Networks using MATLAB 6.0, Tata McGraw-Hill Publishing company Limited, New Delhi, pp. 21- 223, 2008.

38. Barto, A.G., Reinforcement Learning and Adaptive Critic Methods, in Handbook of Intelligent Control, eds., Van Nostrand-Reinhold, New York, pp 469-491, 1992.

39. Sutton, R.S., Special Issue on Reinforcement Learning, Machine Learning, vol. 8, pp 1-395, 1992.

40. Hebb, D.O., The Organization of Behavior: a Neuropsychological Theory, Wiley and Sons, New York, 1949.

41. Wilshaw, D.J. and von der Malsburg, C., How Patterned Neural Connections can be Set up by Self-Organization, Proceedings of the Royal Society of London B, Vol. 194, pp 431-445, 1976.

42. Grossberg, S., Adaptive Pattern Classification and Universal Recoding: I. Parallel Development and Coding of Neural Feature Detectors, Biological Cybernetics, vol. 23, pp 121-134, 1976.

43. Kohonen, T., Self-Organized Formation of Topologically Correct Feature Maps, Biological Cybernetics, vol. 43, pp 59-69, 1982.

44. Kohonen, T., Self-Organization and Associative Memory (3rd ed.), Springer-Verlag, Berlin, 1989.

45. Minsky, M. and Papert, S., Perceptron: An Introduction to Computational Geometry, MIT Press, Cambridge, MA, 1969.

74

Page 52: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

46. Abdulkadir Sengur, An expert system for diagnosis of the heart valve diseases, Expert Systems with applications, 23, pp-229–236, 2002.

47. Ghumbre Shashikant Uttreshwar, A.A. Ghatol, Hepatitis B Diagnosis Using Logical Inference And Generalized Regression Neural Networks, IEEE International Advance Computing Conference, IACC, Patiala, India, March, pp-1587-1595, 2009.

48. Murat Karabatak, M. Cevdet Ince, “An expert system for detection of breast cancer based on association rules and neural network, Expert Systems with Applications, 36, pp 3465–3469, 2009.

49. Gerard Wolff, J., "Medical diagnosis as pattern recognition in a framework of information compression by multiple alignment, unification and search", Decision Support Systems, Vol.42, Issue 2, pp. 608 – 625, 2006.

50. Pople, H. E.: Heuristic Methods for Imposing Structure on Ill-Structured Problems: The Structuring of Medical Diagnostics. Chapter 5 in Szolovits, P (Ed.): Artificial Intelligence in Medicine, Westview Press, Boulder, Colorado, 1982.

51. Shortliffe, E. H.: Computer-Based Medical Consultations: MYCIN. Elsevier, New York, 1976.

52. Buchanan, R. G., Shortliffe, E. H.: Rule-Based Expert Systems. Addison Wesley, 1984.

53. Bert A. Mobley , Eliot Schechter, William E. Moore, Patrick A. McKee, June E. Eichner, “Predictions of coronary artery stenosis by artificial neural network”, Artificial Intelligence in Medicine, 18, pp 187–203, 2000.

54. Vazirani, H. Kala, R. Shukla, A. Tiwari, R. , “Diagnosis of breast cancer by modular neural network”, IEEE International Conference on Computer Science and Information Technology (ICCSIT), ISBN: 978-1-4244-5537-9, Vol7, pp 115 – 119, July 2010.

55. Vahid Aeinfar, Hoorieh Mazdarani, Fatemeh Deregeh, Mohsen Hayati, Mehrdad Payandelr, “Multilayer PerceptronNeural Network with supervised training method for diagnosis and prediction blood disorder and cancer” IEEE International Symposium on Industrial Electronics (ISlE), pp 2075-2080, 2009.

56. J. Jiang,P.Trundle, J.Ren “ Medical image analysis with artificial neural networks”, Computerized Medical Imaging and Graphics, Elsevier Publication, Volume 34, Issue 8, Pages 617-631, December 2010 .

57. Inan Culer and Elif Derya Ubeyli, “Multiclass support vector machines for EEG – signal classification, IEEE transactions on Information Technology in Biomedicine, Vol 11, No. 2, pp 117-126, March 2007.

58. Harsh Vazirani, Rahul Kala, Anupam Shukla, Ritu Tiwari, “Use of Modular Neural Network for Heart Disease”, Special Issue of IJCCT, International Conference Vol.1 Issue 2, 3, 4, pp 88-93, August 2010.

59. Er . O , Temurtas F, Tanrikulu AC, “Tuberculosis disease diagnosis using artificial neural networks” J Med Syst., 34(3): pp 299-302, 2010.

60. Hasan Temurtas et. Al. A comparative study on diabetes disease diagnosis using neural networks’, Expert Systems with Applications, Volume 36 Issue 4, pp 8610-8615, May 2009.

75

Page 53: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

61. Qeethara Kadhim Al-Shayea and Itedal S. H. Bahia, “Urinary System Diseases Diagnosis Using Artificial Neural Networks”, IJCSNS International Journal of Computer Science and Network Security, VOL.10 No.7, pp 118-122, July 2010.

62. Orhan Er, Nejat Yumusak and Feyzullah Temurtas, Chest diseases diagnosis using artificial neural networks, Expert Systems with Applications, Volume 37, Issue 12, pp 7648-7655, December 2010.

63. I. M. Ibrahim, A. A. Yassen, A. F. Qurany, G. E. Essam, M. A. Hefnawy, M. A. Yacoub, Y. M. Kadah, “Computer-Aided Diagnostic System for Mass Detection in Digitized Mammograms”, Proceedings Cairo International Biomedical Engineering Conference, pp 1-4, 2006.

64. Stefano Ciatto, Marco Rosselli Del Turco, Gabriella Risso, Sandra Catarzi, Rita Bonardi, Valeria Viterbo, Pierangela Gnutti, Barbara Guglielmoni, Lelio Pinelli, Anna Pandiscia, Francesco Navarra, Adele Lauria, Rosa Palmiero and Pietro Luigi Indovina, "Comparison of standard reading and computer aided detection (CAD) on a national proficiency test of screening mammography," European Journal of Radiology 45, pp135–138, 2003.

65. Danna Voth, “Using AI to detect breast cancer” IEEE Intelligent Systems, pp 88-94, Jan 2005.

66. Kabari, L.G. Bakpo, F.S. , “Diagnosing skin diseases using an artificial neural network”, 2nd IEEE International Conference on Adaptive Science & Technology, ICAST, pp 187 – 191, 2009.

67. D. L. Bounds, P. J. Lioyd, B. Mathew & G. G. Wadell.’ A multilayer perceptron network for the diagnosis of low back pain.’ Proceeding of the IEEE International conference on neural networks, San Diego, Vol. II, New York, pp. 481-489, 1988.

68. Eberhart, R.C.; Dobbins, R.W.; Hutton, L.V., “Neural network paradigm comparisons for appendicitis diagnoses”, Fourth Annual IEEE Symposium Computer-Based Medical Systems,.pp 298 – 304, 1991.

69. Gajanan P. Dhok, S. A. Ladhake, “Arrhythmia Analysis using Artificial Neural Network”, International Journal of Computer Application (IJCA), Number 5 - Article 8, pp 46-52, 2011.

70. Y. O. Yoon, R. W. Brobst, P. R. Bergstresser & L. L. Peterson. ‘ A desktop neural network for dermatology diagnosis.’ Journal of neural network computing, summer, pp. 43-52, 1989.

71. Guodong Zhang, Peiyu Yan, Hong Zhao, Xin Zhang, “A Computer Aided Diagnosis System in Mammography Using Artificial Neural Networks”, IEEE conference on Biomedical Engineering and Informatics, , pp 823 – 826, 2008.

72. B. Sumathi,Dr. A. Santhakumaran, “Pre-Diagnosis of Hypertension Using Artificial Neural Network”, Global Journal of Computer Science and Technology, Vol 11(2), pp 43-48, 2011.

73. St. Karagiannis, A. I. Dounis, T. Chalastras, P. Tiropanis, and D. Papachristos, “Design of Expert System for Search Allergy and Selection of the Skin Tests using CLIPS”, World Academy of Science, Engineering and Technology 31, pp 487-490, 2007.

74. BDCN Prasadl1, P. E. S. N Krishna Prasad2 and Y Sagar, “An approach to develop expert system in medical diagnosis using Machine Learning Algorithms (Asthma) and a performance study”, International Journal on Soft Computing (IJSC), Vol.2, No.1, pp 26-33, 2011.

75. Cao Q, Leggio KB, Schniederjans MJ., “A comparison between Fama and French’s model and artificial neural networks in predicting the Chinese stock market”, Computers & Operations Research 32, pp 2499–2512, 2005.

76

Page 54: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

76. Pai PF, Hong WC., “Support vector machines with simulated annealing algorithms in electricity load forecasting”, Energy Conversion and Management Volume 46, Issue 17, Pages 2669-2688, October 2005.

77. Marico G. Passos, Paulo H. da F. Silva and Humberto C.C. Fernandis, “A RBF/MLP Modular Neural Network for Microwave Design Modeling”, International Journal of Computer Science and Network Security, Vol. 6, pp. 5A, pp 695-700, 2006.

78. James D. Kozlowski, Carl S. Byington, Amulya K. Garga, Matthew J. Watson, Todd A. Hay, “Model-based Predictive Diagnostics for Electrochemical Energy Sources, Aerospace Conference of IEEE Proceeding, pp 3149 to 3193, 2001,.

79. Mason DG, Packer JS, Cade JF, and McDonald RD, Closed-loop management of blood pressure in critically ill patients, Australasian physical and engineering sciences in medicine, 8(4): pp. 164-167, 1985.

80. Kordylewski H, Graupe D, and Kai L, A novel large-memory neural network as an aid in medical diagnosis applications. IEEE Transactions on Information Technology in Biomedicine, 5(3), pp. 202-209, 2001.

81. J.P. Lee, D.J. Lee, P.S. Ji, J.Y. Lim, “Diagnosis of Power Transformer using Fuzzy Clustering and Radial Basis Function Neural Network”, International Joint Conference on Neural Networks, Canada, pp 1398-1404, July 2006.

82. Saeed Salehi, Geir Hareland, Keivan Khademi Dehkordi, Mehdi Ganji, Mahmoud Abdollahi, “Casing collapse risk assessment and depth prediction with Neural Network system approach”, Journal of Petroleum Science and Engineering, Elsevier B.V., pp 156-162, , 2009.

83. Ramesha K1, K B Raja2, Venugopal K R2 and L M Patnaik3, “Feature Extraction based Face Recognition, Gender and Age Classification”, (IJCSE) International Journal on Computer Science and Engineering, Vol. 02, No.01S, pp 14-23, 2010.

84. S. Ouchtati, B. Mouldi, A. Lachouri”, Segmentation and Recognition of Handwritten Numeric Chains”, Journal of Computer Science 3 (4), pp 242—248, , 1997.

85. Younes Chtioui, Suranjan Panigrahi, Leonard Franel, “A generalized regression neural network and its application for leaf wetness prediction to forecast plant disease, Chemometrics and Intelligent laboratory systems, Elsevier Science, pp 47-58, 1999.

86. Marcantonio Catelani, Ada Fort, “Fault diagnosis of electronic analog using a radial basis function network classifier”, Measurement, Elsevier Science Publication, pp 147-158, 2000.

87. Svetlana Ibric, Milica Jovanovic, Zorica Djuric, Jelena Parojcic, Ljiljana Solomun, Branka Lucic, “Generalized regression neural Networks in Prediction of Drug stability”, Journal of Pharmacy and Pharmacology, pp-745-750, , 2007.

88. Luiza H.S. Nunes, Matheus R. C. Teixeira, Lucia Codognoto, Rogerio Marinke, “ Artificial Neural Netowks applied in Quantitative Chemical Analysis”, IIIS, pp 1-3, 2010.

89. Miao M. Chong, Ajith Abraham, Marcin Paprzycki, “Traffic Accident Analysis using decision trees and Neural Networks”, IADIS International Conference Applied Computing, pp 39-42, 2004.

90. Samy S. Abu Naser, Abu Zaiter A. Ola , “An expert system for diagnosing Eye diseases using CLIPS”, Journal of Theoretical and Applied Information Technology, pp 923-930, 2008.

77

Page 55: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

91. Mohamad Adnan Al-Alaoui, Lina Al-Kanj, Jimmy Azar, and Elias Yaacoub, “Speech Recognition using Artificial Neural Networks and Hidden Markov Models”, IEEE Multidisciplinary Engineering Education Magazine, Vol 3, No.3, pp 77-86, Sept. 2008.

92. K.V.Ramana, Raghu.B.Korrapati, “ Neural Network Based Classification and Diagnosis of Brain Hemorrhages, International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (1): Issue (2), pp 7-25, 2011.

93. I. Hatzilygeroudis (1) (2), P. J. Vassilakos(3), A. Tsakalidis, ”An Intelligent Medical System for Diagnosis of Bone Diseases”, 1st International Conference on Medical Physics and Biomedical Engineering (MPBE’94), Nicosia, Cyprus, Vol. I, pp 148-152, , May 1994.

94. Rinki Jajoo, Dinesh Mital, Syed Haque, Shankar Srinivasan, “Prediction of Hepatitis C using Artificial Neural Networks”, 7th International conference on Control, Automation Robotics and Vision (ICARCV), Singapore, pp 1545-1550, Dec. 2002.

95. Nandi, A.K., Advanced digital vibration signal processing for condition monitoring. Proceedings of COMADEM, Houston, TX, USA, 2000, pp. 129–143, 2000.

96. McCormick, A.C., Nandi, A.K.,. Classification of the rotating machine condition using artificial neural networks. Proceedings of IMechE, Part C: Journal of Mechanical Engineering Science, 211, 439–450, 1997.

97. A.Martin1, Na.Ba.Anutthamaa2, M.Sathyavathy3, Marie Manjari Saint Francois4, Dr. Prasanna Venkatesan5, A Framework for Predicting Phishing Websites Using Neural Networks, IJCSI International Journal of Computer Science, Issues, Vol. 8, Issue 2, pp 330-336, March 2011.

98. Maher Aburrous, M.A. Hossain, Keshav Dahal, Fadi Thabtah “Intelligent phishing detection system for e-banking using fuzzy data mining”, Expert Systems with Applications: An International Journal Volume 37 Issue 12, pp 7913-7921, December 2010.

99. K.Ghorbanian, M. Gholamrezaei, “An artificial neural network approach to compressor performance prediction”, Applied Energy, Elsevier, pp1210-1221, 2009.

100. B. Samanta, K.R. Al-Balushi, S.A. Al-Araimi, “Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection”, Engineering Applications of Artificial Intelligence 16 , pp657–665, 2003.

101. N. Ganesan, K. Venkatesh, M.A. Rama, “Application of Neural Networks in Diagnosing Cancer Disease using Demographic data”, International Journal of Computer Application, Vol 1 No. 26, pp 76-85, , 2010.

102. http://yourtotalhealth.ivillage.com/heart-disease-fast-facts.html, 2010.

103. http://www.americanheart.org, 2010.

104. http://yourtotalhealth.ivillage.com/heart-disease-fast-facts.html, 2010.

105. Rohaida Ahmad Azra’ai, Mohd Nasir bin Taib and Nooritawati Md Tahir, “Artificial Neural Network for Identification Of Heart Problem”, IEEE International Conference on Signal Processing and Communication Systems, pp 1-6, , 2008.

78

Page 56: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

106. Yourdiagnosis, an online diagnosis tool," Available: http://www.yourdiagnosis.com/ (Last Accessed Date:15-03-11).

107. Easydiagnosis, an online diagnosis tool," Available: http://easydiagnosis.com/ (Last Accessed Date:15-03-11).

108. Effects of principle component analysis on assessment of coronary artery diseases using support vector machine, Expert system with applications, Elsevier, pp 2182-2185, 2010.

109. Hongmei Yana, Yingtao Jiangb, Jun Zhenge, Chenglin Pengc, Qinghui Lid,” A multilayer perceptron-based medical decision support system for heart disease diagnosis”, Expert Systems with Applications, 30, pp 272–281, 2006.

110. Emre Comak, Ahmet Arslan, Ibrahim Turkoglu, “A decision support system based on support vector machines for diagnosis of the heart valve disease” Computers in Biology and Medicine, Elsevier, 37, pp 21-27, 2007.

111. B.C.D. Chan, F.H.Y. Chan, F.K. Lam, P.W. Lui, P.W.F. Poon, “Fast detection of venous air embolism is Doppler Heart sound using the wavelet transform”, IEEE transactions, Biomed. Eng. 44(4), pp 237-245, 1997.

112. I. Guler, M.K. Kiymik, S. Kara, M.E. Yuksel, “Application of autoregressive analysis to 20 MHz pulsed Doppler data in real time, International Journal Biomed, Computation, 3(3-4), 247-256, 1992.

113. E. Avci , “ A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier”, Expert Systems with Applications, Volume 36, Issue 7, pp 10618-10626, Sept. 2009.

114. Ilias Maglogiannis, Euripides Loukis, Elias Zafiropoulos, Antonis Stasis, “Support Vector Machine based identification of heart valve diseases using heart sounds”, Computer Methods And Programs in Biomedicine, Elsevier, 47-61, 2009.

115. I. Turkoglu, A. Arslan, E. Ilkay, An intelligent system for diagnosis of heart valve diseases with wavelet packet neural networks, Comput. Biol. Med. 33 (4), 319–331, 2003.

116. Long, W. J., Naimi, S., & Criscitello, M. G., Development of a knowledge base for diagnostic reasoning in cardiology. Computers in Biomedical Research, 25, 292–311, , 1992.

117. Azuaje, F., Dubitzky, W., Lopes, P., Black, N., & Adamsom, K., Predicting coronary disease risk based on short-term RR interval measurements: A neural network approach. Artificial Intelligence in Medicine, 15, 275–297, , 1999.

118. Tkacz, E. J., & Kostka, P., An application of wavelet neural network for classification patients with coronary artery disease based on HRV analysis. Proceedings of the Annual International Conference on IEEE Engineering in Medicine and Biology, 1391–1393, 2000.

119. Reategui, E. B., Campbell, J. A., & Leao, B. F., Combining a neural network with case-based reasoning in a diagnostic system. Artificial Intelligence in Medicine, 9, 5–27, 1997.

120. Tsai, D. Y., & Watanabe, S., “Method optimization of fuzzy reasoning by genetic algorithms and its application to discrimination of myocardial heart disease”. Proceedings of IEEE Nuclear Science Symposium and Medical Imaging Conference, pp 1756–1761, 1998.

79

Page 57: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

121. Goldman L, Weinberg M, Weisberg M, A computer-derived protocol to aid in the diagnosis of emergency room patients with acute chest pain. N Engl J Med; 307 (10), pp- 588-96, 1982.

122. Ismail Babaoglu, Oguz Fındık, Mehmet Bayrak, “Effects of principle component analysis on assessment of coronary artery diseases using support vector machine”, Expert Systems with Applications 37, pp- 2182–2185, 2010.

123. Sut, N., S_enocak, M., Assessment of the performances of multilayer perceptron neural networks in comparison with recurrent neural networks and two statistical methods for diagnosing coronary artery disease. Expert Systems, 24(3), pp 131–142, 2007.

124. Noor Akhmad Setiawan1, P.A. Venkatachalam2 and Ahmad Fadzil M.Hani3, “Diagnosis of Coronary Artery Disease Using Artificial Intelligence Based Decision Support System”, Proceedings of the International Conference on Man-Machine Systems (ICoMMS), Batu Ferringhi, Penang, MALAYSIA, pp 1c3-1-1c3-5, October 2009.

125. Anchana Khemphila, Veera Boonjing, “Comparing performances of logistic regression, decision trees, and neural networks for classifying heart disease patients”, IEEE International Conference on Computer Information Systems and Industrial Management Applications (CISIM), pp-193-198, 2010.

126. Orhan Er, nejat Yumusak, Feyzullah Temurtas, “Chest Diseases diagnosis using Artificial Neural Networks”, Expert System with Applications, Elsevier, pp 7648-7655, 2010.

127. U. Rajendra Acharya, E. Y. K. Ng, Jen-Hong Tan, S. Vinitha Sree, Thermography Based Breast Cancer Detection Using Texture Features and Support Vector Machine”, Journal of Medical Systems, pp 1048-1059, 2010.

128. Carlos Andres Pena-Reyes, Moshe Sipper, A fuzzy-genetic approach to breast cancer diagnosis, Artificial Intelligence in Medicine, 131–155, 1999.

129. K. Mumtaz, S.A. Sheriff, K. Duraiswamy, “Evaluation of Three Neural Network models using Wisconsin Breast Cancer Database”, Academic Radiology Volume 16, Issue 7, pp 842-851, July 2009.

130. Tuba Kiyani, Tulay Yildrim, Breast Cancer diagnosis using Statistical Neural Networks”, Journal of Electrical and Electronics Engineering, Vol 4, No. 2, pp, 1149-1153, 2004.

131. Elif Derya Ubeyli, “Implementing automated diagnostic systems for breast cancer detection”, Expert systems with Applications, Vol 33, Issue 4, pp 1054-1062, November 2007.

132. U. Rajendra Acharya, E. Y. K. Ng, Jen-Hong Tan, S. Vinitha Sree, Thermography Based Breast Cancer Detection Using Texture Features and Support Vector Machine”, Journal of Medical Systems, 2010, pp 348-256.

133. P.B. Snow, D.S. Smith, W.J. Catalona, Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study, J. Urol. 152, British Journal of Cancer, 78(2), pp 246-250, 1998.

134. R.N.G. Naguib!,*, F.C. Hamdy, “A general regression neural network analysis of prognostic markers in prostate cancer”, Neurocomputing 19, pp 145 -150, 1998.

135. Zhi-Hua Zhou, Yuan Jiang, Yu-Bin Yang, Shi-Fu Chen, “Lung cancer cell identification based on artificial neural network ensembles, Artificial Intelligence in Medicine, Elsevier, 24, pp 25-36, 2002.

80

Page 58: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

136. Chiou YSP, Lure YMF, Ligomenides PA., Neural Network image analysis and classification in hybrid lung nodule detection (HLND) system, proceedings of the IEEE-SP workshop on neural networks for signal processing, PP 517-526, 1993.

137. Lin JS, Lo SCB, Hasegawa A, Freedman MT, Mun SK., Reduction of false positives in lung nodule detection using a two level neural classification, IEEE Transactions Med Image, 15(2), pp 206-217, 1995.

188. Frank Dieterlea,*, Silvia Muller-Hagedornb, Hartmut M. Liebichb, Gunter Gauglitza, “ Urinary nucleosides as potential tumor markers evaluated by learning vector quantization”, Artificial Intelligence in Medicine 28, 265–279, 2003.

189. SUDHIR D. SAWARKAR, ASHOK A. GHATOL, AMOL P. PANDE, “Neural Network Aided Breast Cancer Detection and Diagnosis Using Support Vector Machine”, Proceedings of the 7th WSEAS International Conference on Neural Networks, Cavtat, Croatia, pp 158-163, June 2006.

190. Özyılmaz, L., & Yıldırım, T., Diagnosis of thyroid disease using artificial neural network methods. In Proceedings of ICONIP, Nineth International conference on neural information processing, Orchid Country Club, Singapore, pp. 2033–2036, 2002.

191. http://www.entnet.org/healthinfo/thyroid/thyroid_gland.cfm (Accessed 10.03.2011).192. Esin Dogantekin a, Akif Dogantekin b, Derya Avci, “An expert system based on Generalized

Discriminant Analysis and Wavelet Support Vector Machine for diagnosis of thyroid diseases”, Expert Systems with Applications, Vol. 38, Issue 1, pp 146-150, January 2011.

193. P.K. Sharpe, H.E. Solberg, K. Rootwelt and M. Yearworth, Artificial neural networks in diagnosis of thyroid function from vitro laboratory tests, Clinical Chemistry 39, pp 2248–2253, 1993.

194. Sharpe PK, Solberg HE, Rootwelt K, Yearworth M., “Artificial neural networks in diagnosis of thyroid function from in vitro laboratory tests”, Clin Chem.: 39(11 Pt 1): pp 2248-2253, Nov 1993.

195. Guoqiang (Peter) Zhang and Victor L. Berardi, “An investigation of neural networks in thyroid function diagnosis”, Health Care Management Science 1 pp 29–37, 1998.

196. Feyzullah Temurtas, “A comparative study on thyroid disease diagnosis using neural networks”, Expert Systems with Applications 36, pp 944–949, 2009.

197. Ozyılmaz, L., Yıldırım, T., Diagnosis of thyroid disease using artificial neural network methods. In Proceedings of ICONIP’02 9th international conference on neural information processing, Singapore pp. 2033– 2036, 2002.

198. Polat, K., Sahan, S., & Gunes, S., A novel hybrid method based on artificial immune recognition system (AIRS) with fuzzy weighted preprocessing for thyroid disease diagnosis. Expert Systems with Applications, 32, 1141–1147, 2007.

199. Anupam Shukla Prabhdeep Kaur, Ritu Tiwari R.R.Janghel, “Diagnosis of Thyroid Disorders using Artificial Neural Networks”, 2009 IEEE International Advance Computing Conference (IACC 2009), Patiala, India, 6-7 March 2009, pp 1016 – 1020.

200. Michal Antkowiak, “Recognition of skin diseases using artificial neural networks” Proceeding of USCCS’05, pages 313–325, 2005.

81

Page 59: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

201. Haralambos Sarimveis, Philip Doganis, Alex Alexandridis, “A classification technique based on Radial Basis Function Neural Networks”, Advances in Engineering Software, 37, pp 218-221, 2006.

202. Branko Celler, Phillip de chazal and Nigel Lovell, “A comparison of expert system for the Automated Interpretation of the ECG, Regulatory Implications of the use of Neural Networks, APAMI, pp. 1 -7, August 1997.

203. Jang-Jae Lee, Byuong-Ho-Song, Tai-Yeun Kim, Dae-Woong Seo, Sang-Hyun Bae, “A Design and Implementation of U-health Diagnosis System using Expert System and Neural Networks”, International Journal of Future Generation Communication and Networking, pp 83-90, 2008.

204. Tripty Singh, Sarita Singh Bhadauoria, AK Wadwani, “Expert system and analysis for Breast Cancer Diagnosis”, International Journal of Engineering Sciences and Technology, Vol 2(12), pp 7491-7400, 2010.

205. Carlos J. Garcia-Orellana, Ramon Gallardo-Caballero, Miguel Macias-Macias and Horacio GanzalezVelasco, “SVM and Neural Networks Comparison in Mammographic CAD”, IEEE proceedings of the 29th Annual International conference of the EMBS, pp 3204-3207, August 23-26, 2007.

206. Murat Karabatak, M.Cevdet Ince, “An expert system for detection of breast cancer based on association rules and neural networks”, Expert Systems with Application, 36, pp 3465-3469, 2009.

207. Mahsa Moein, Mohammad Davarpanah, M. Ali Montazeri and Mehrnaz Ataei, “Classifying Ear Disorders using Support Vector Machine”, IEEE International Conference on Computational Intelligence and Natural computing, pp 321-324, , 2010.

208. Umi Kalthum Ngah, Shalihatun Azlin Aziz, Mohd. Ezane Aziz and Mazeda Murad, “A BI-RADS Based Expert System for the Diagnosis of Breast Diseases”, American Journal of Applied Sciences, 4(11), 865-873, 2007.

209. Abdel-Badeeh M. Salem, and Bassant M. EI Bagoury, “A Case-Based Adaptation for Thyroid Cancer Diagnosis using Neural Networks”, American Association for Artificial Intelligence, pp 155-159, , 2003.

210. I. Turkoglu, A. Arslan, E. Ilkay, “An expert system for diagnosis of heart valve diseases”, Expert System with Applications, 23, pp 229-236, 2002.

211. Samy S. Abu Naser, Alaa N Akkila, “A proposed expert system for skin diseases diagnosis”, Journal of Applied Sciences Research, 4(12), pp 1682-1693, 2008.

212. Eugene ROVENTA, George ROSU, “The Diagnosis of some Kidney Diseases in a Small Prolog Expert System”, IEEE Engineering in Medicine and Biology, pp 219-224, , 2009.

213. Harsh Vazirani, Rahul Kala, Anupam Shukla and Ritu Tiwari, “Diagnosis of breast cancer by modular neural network”, IEEE International Advance Computing Conference, pp 115-119, 2010.

82

Page 60: Development of an expert system for Diagnosis ...manzaramesh.in/prephdbooks/PPT/03 NMU_2 by Hannan... · Patient Medicines prescribed by the doctor MID Medicine name MID Medicine

The perceptron itself consists of the weights, the summation processor and the threshold processor.

Learning is the process of modifying the values of the weights and the threshold.

A perceptron computes a binary function of its input.

Linearly separable means we can draw a line that separates one class from another.

83