Conventional and neuro-fuzzy framework for diagnosis and therapy of cardiovascular disease

Okure U. Obot; Faith-Michael Uzoka; Oluwole C. Akinyokun; Joseph J. Andy

doi:10.1515/bams-2013-0018

Artikel

Conventional and neuro-fuzzy framework for diagnosis and therapy of cardiovascular disease

Okure U. Obot , Faith-Michael Uzoka , Oluwole C. Akinyokun und Joseph J. Andy

Veröffentlicht/Copyright: 6. September 2013

Veröffentlicht von

Veröffentlichen auch Sie bei De Gruyter Brill

Informationen für Autor*innen Erkunden Sie dieses Fachgebiet

Aus der Zeitschrift Bio-Algorithms and Med-Systems Band 9 Heft 3

Abstract

In this article, we present the conventional method and neuro-fuzzy model for the diagnosis and therapy of heart disease. The neuro-fuzzy system provides a basis for creating a decision support system that has a learning ability and the capacity to deal with vagueness and unstructuredness in disease management. The decision support engine carries out the cognitive and emotional filtering of the objective and subjective feelings of the medical practitioner. These filters further refine the diagnosis and therapy processes by taking care of the contextual elements.

Keywords: cardiovascular; diagnosis; emotional filter; fuzzy logic; heart failure; neural networks; neuro-fuzzy; therapy

Corresponding author: Faith-Michael Uzoka, Department of Computer Science and Information Systems, Mount Royal University, 4825 Mount Royal Gate SW, AB T3E 6K6, Calgary, Alberta, Canada

Appendix A

Rule base for diagnosis.

Rule	Orthop	HR	Clidys	Wheeze	PND	Hepa	Diagnosis
1	Mild	Mild	Mild	Mild	Mild	Mild	Very mild
2	Mild	Mild	Mild	Mild	Mild	Moderate	Very mild
3	Mild	Mild	Mild	Mild	Moderate	Moderate	Mild
4	Mild	Mild	Mild	Moderate	Moderate	Moderate	Mild
5	Mild	Mild	Moderate	Moderate	Moderate	Moderate	Mild
6	Mild	Moderate	Moderate	Moderate	Moderate	Moderate	Moderate
7	Moderate	Moderate	Moderate	Moderate	Moderate	Moderate	Moderate
8	Moderate	Moderate	Moderate	Moderate	Moderate	Mild	Moderate
9	Moderate	Moderate	Moderate	Moderate	Mild	Mild	Moderate
10	Moderate	Moderate	Moderate	Mild	Mild	Mild	Moderate
11	Moderate	Moderate	Mild	Mild	Mild	Mild	Moderate
12	Moderate	Mild	Mild	Mild	Mild	Mild	Mild
13	Moderate	Mild	Mild	Mild	Mild	Severe	Moderate
14	Moderate	Mild	Mild	Mild	Severe	Severe	Moderate
15	Mild	Mild	Mild	Mild	Severe	Severe	Moderate
16	Mild	Mild	Mild	Severe	Severe	Severe	Moderate
17	Mild	Mild	Severe	Severe	Severe	Severe	Severe
18	Mild	Severe	Severe	Severe	Severe	Severe	Very severe
19	Severe	Severe	Severe	Severe	Severe	Severe	Very severe
20	Moderate	Moderate	Moderate	Severe	Severe	Severe	Severe
21	Moderate	Moderate	Severe	Severe	Severe	Severe	Severe
22	Moderate	Severe	Severe	Severe	Severe	Severe	Very severe
23	Mild	Severe	Mild	Severe	Mild	Severe	Moderate
24	Mild	Moderate	Severe	Mild	Severe	Moderate	Moderate
25	Moderate	Mild	Severe	Severe	Moderate	Mild	Moderate
26	Severe	Moderate	Mild	Severe	Mild	Moderate	Moderate
27	Moderate	Mild	Moderate	Mild	Severe	Severe	Moderate
28	Mild	Mild	Moderate	Moderate	Severe	Severe	Moderate
29	Moderate	Moderate	Mild	Mild	Severe	Severe	Severe
30	Severe	Severe	Moderate	Moderate	Mild	Mild	Moderate
31	Severe	Mild	Mild	Severe	Moderate	Moderate	Moderate
32	Moderate	Mild	Mild	Moderate	Severe	Severe	Severe
33	Mild	Moderate	Severe	Severe	Mild	Moderate	Moderate
34	Severe	Mild	Mild	Mild	Mild	Mild	Mild
35	Severe	Severe	Severe	Severe	Severe	Mild	Very severe
36	Severe	Severe	Severe	Severe	Mild	Mild	Severe
37	Severe	Severe	Severe	Mild	Mild	Mild	Severe
38	Severe	Severe	Mild	Mild	Mild	Mild	Moderate
39	Severe	Mild	Mild	Mild	Mild	Mild	Moderate
40	Severe	Moderate	Moderate	Moderate	Moderate	Moderate	Moderate
41	Severe	Severe	Moderate	Moderate	Moderate	Moderate	Moderate
42	Severe	Severe	Severe	Moderate	Moderate	Moderate	Severe
43	Severe	Severe	Severe	Severe	Moderate	Moderate	Severe
44	Severe	Severe	Severe	Severe	Severe	Moderate	Very severe
45	Severe	Severe	Severe	Mild	Moderate	Moderate	Severe
46	Severe	Severe	Severe	Mild	Mild	Moderate	Severe
47	Severe	Moderate	Moderate	Mild	Severe	Mild	Moderate

Clidys, dyspnea while climbing; Hepa, hepatomegaly; HR, heart rate; Orthop, orthopnea; PND, paroxysmal nocturnal dyspnea; Wheez, wheezing.

Appendix B

Fuzzy rule base for therapy.

S/N	Enalapril	Linsonopril	Captropril	Bisoprolol	Hydralaxine	Metroprolol	Others	Therapy
1	Mil	Mild	0	0	Mild	Mild	Moderate	Mild
2	Mild	Moderate	Moderate	Moderate	0	0	Moderate	Moderate
3	Moderate	Moderate	0	Moderate	0	0	Moderate	Moderate
4	0	Moderate	Moderate	Moderate	Severe	Severe	Moderate	Severe
5	Moderate	Moderate	Severe	Moderate	0	0	Severe	Moderate
6	Severe	Severe	0	Severe	Severe	0	Moderate	Moderate
7	0	Moderate	0	Severe	0	Moderate	Moderate	Moderate
8	0	Mild	Mild	Mild	Mild	0	Mild	Mild
9	Moderate	Moderate	Moderate	Moderate	0	0	Moderate	Moderate
10	Moderate	0	0	Moderate	0	Mild	Mild	Moderate
11	Mild	Moderate	Mild	Moderate	0	0	Mild	Mild
12	Moderate	Severe	Severe	Moderate	0	Mild	Mild	Moderate
13	Severe	Moderate	Mild	Mild	Moderate	Severe	0	Moderate
14	Severe	Mild	Mild	Moderate	0	0	Moderate	Moderate
15	Moderate	Moderate	Severe	Severe	Severe	0	0	Severe
16	Mild	Moderate	Severe	Severe	Moderate	Moderate	Moderate	Severe
17	0	0	0	Severe	Severe	Severe	0	Severe
18	Severe	Severe	Moderate	0	0	0	Severe	Severe
19	Mild	Severe	Mild	Mild	Mild	0	0	Moderate
20	Mild	0	0	0	Severe	Mild	Mild	Moderate
21	0	0	Severe	Severe	0	0	Mild	Severe
22	Severe	Moderate	Moderate	Mild	0	0	0	Moderate
23	Mild	Moderate	Severe	0	Mild	Mild	0	Moderate
24	0	0	Mild	Mild	0	0	Mild	Mild
25	Mild	Mild	Moderate	Moderate	Severe	Severe	0	Severe
26	0	Mild	Severe	Moderate	Moderate	Severe	0	Moderate

S/N, Serial number.

References

1. Akinyokun OC, Shogbon JA. A framework of neuro-fuzzy expert system for capital investment appraisal. J ICAN 2006;556–65.Suche in Google Scholar

2. Obot OU, Uzoka FM. A framework for application of neuro-case-rule base hybridization in medical diagnosis. Appl Soft Comput 2009;9:245–53.10.1016/j.asoc.2008.01.010Suche in Google Scholar

3. Szolovits P. Uncertainty and decisions in medical informatics. Methods Inf Med 1995;34:111–21.10.1055/s-0038-1634594Suche in Google Scholar

4. Song Q, Kasabov N. A novel generic higher-order TSK fuzzy model for prediction and applications for medical decision support. In: Proc. 8th Australian and New Zealand Intelligence Information Systems Conference (ANZIIS2003), 10–12. December, 2003, Sydney, NSW, Australia, 2003:241–5.Suche in Google Scholar

5. Pople HE. Heuristic methods for imposing structure on ill-structured problems: the structuring of medical diagnostics. In: Szolovits P, editor. Artificial intelligence in medicine. Boulder, CO: Westview Press, 1982:chap 5.Suche in Google Scholar

6. Miller RA, Pople HE, Myers JD. INTERSIT-1: an experimental computer based diagnostic consultant for general internal medicine. N Engl J Med 1982;316:250–8.Suche in Google Scholar

7. Podgorelec V, Kokol P. Towards more optimal medical diagnosing with evolutionary algorithms. J Med Syst 2001;25:195–219.10.1023/A:1010733016906Suche in Google Scholar

8. Ochi-Okorie AS. Disease diagnosis validation in TROPIX using CBR. Artif Intell Med 1998;12:43–60.10.1016/S0933-3657(97)00039-0Suche in Google Scholar

9. Timpka T, Padgham L, Hedblom P, Wallin S, Tibblin G. A hypertext knowledge base for primary care. ACM 1989;23: 221–228.Suche in Google Scholar

10. Uzoka F-ME, Famuyiwa FO. A framework for the application of knowledge technology to the management of diseases. Int J Health Care Qual Assur 2004;17:194–204.10.1108/09526860410541513Suche in Google Scholar

11. Akinyokun OC, Adeniyi OA. Experimental study of intelligent computer aided medical diagnostics and therapy. AMSE J Model Simul Control 1991;27:1–20.Suche in Google Scholar

12. Bonnisone PP, Geobel K, Khedkar PS. Hybrid soft computing systems: industrial and commercial applications. Proc IEEE 1999;87:1641–67.10.1109/5.784245Suche in Google Scholar

13. Lefebvre C, Principe J. Object-oriented artificial neural network implementations. World Congr Neural Networks 1993;4:436–9.Suche in Google Scholar

14. Lefebvre C, Principe J. NeuroSolution 6.0. Gainesville, FL: NeuroDimension, 2007.Suche in Google Scholar

15. Economou GP, Hallas JA, Mariatos EP, Goutis CE. Artificial networks in medical decision making systems: an application to pulmonary diseases’ diagnosis through VHDL synthesis. Proc Eur Design Test Conf 1995:590.Suche in Google Scholar

16. Gomez-Ruiz JA, Jerez-Aragones JM, Munoz-Perez J. A neural network based model for prognosis of early breast cancer. Appl Intell 2004;20:231–8.10.1023/B:APIN.0000021415.88365.c4Suche in Google Scholar

17. Daniels JE, Cayton RM. Cadosa: a fuzzy expert system for differential diagnosis of obstructive sleep apnoea and related conditions. Expert Syst Appl 1997;12:163–77.10.1016/S0957-4174(96)00091-7Suche in Google Scholar

18. Wainer J, Sandri S. Fuzzy temporal/categorical information in diagnosis. J Intell Inf Syst 1999;13:9–29.10.1023/A:1008702804774Suche in Google Scholar

19. Obot OU, Uzoka FM. Fuzzy rule-based framework for the management of tropical diseases Int J Med Eng Inf 2008;1:7–17.10.1504/IJMEI.2008.019466Suche in Google Scholar

20. Marantz PR, Tobin JN, Watsertheil-Samaler S, Steingart RM, Wexler JP, Budner N. The relationship between left ventricular systolic function and congestive heart failure diagnosed by clinical criteria. Circulation 1988;77:607–12.10.1161/01.CIR.77.3.607Suche in Google Scholar

21. Obot OU, Akinyokun OC, Udoh SS. Application of soft computing methodologies to the management of hypertension. J Comput Appl 2008;15:131–47.Suche in Google Scholar

22. Anderson GR. Your guide to health. Pune, India: Oriental Watchman Publishing House, 1976.Suche in Google Scholar

23. Sutton GE, Fox KM. Heart diseases (pathological, clinical and investigatory features). Pune, India: Lippincot Company, 1990:43–47.Suche in Google Scholar

24. Braunwald E, Grossman W. Clinical aspects in heart failure. In: Braunwald E, editor. Heart disease: a textbook in cardiovascular medicine, 5th ed. 1997:445–70.Suche in Google Scholar

25. Davie AP, Francis CM, Caruana L, Sutherland GR, McMurray JJ. Assessing diagnosis in heart failure: which features are any use? QJM 1997;90:335–9.10.1093/qjmed/90.5.335Suche in Google Scholar

26. Hunt SA, Abraham WT, Chin MH, Feldman AM, Francis GS, Ganiats TG, et al. ACC/AHA 2005 guideline update for the diagnosis and management of chronic heart failure in the adult. Circulation 2005;112:1825–52.Suche in Google Scholar

27. Hobbs R, Boyle A. Disease Management Project ACC/AHA guidelines for the evaluation and management of chronic heart failure in the adult: executive summary: a report of the American College of Cardiology/American Heart Association, 2005. Available at: http://circ.ahajournals.org/content/112/12/1825.full.pdf+html?sid=d3454c8f-0fe5-4873-b4d7-459164dc8be1. Accessed on December 12, 2010.Suche in Google Scholar

28. Abraham A, Nath B. Evolutionary design of fuzzy control systems – a hybrid approach. In: 6th International Conference on Control, Automation, Robotics and Vision (ICARCV, 2000). 2000. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.17.1853&rep=rep1&type=pdf. Accessed on April 15, 2007.Suche in Google Scholar

29. Takagi T, Sugeno M. Derivation of fuzzy control rules from human operators control actions. In: Proceedings of the IAFC Symposium on Fuzzy Information, Knowledge Representation and Decision Analysis, 1993:55–60.10.1016/S1474-6670(17)62005-6Suche in Google Scholar

30. Shogbon JA. Neuro-fuzzy expert system for appraisal of capital investment, PhD thesis dissertation. Akure: Federal University of Technology, 2003.Suche in Google Scholar

31. Luneski A, Konstantinidis E, Bamidis PD. Affective medicine: a review of affective computing efforts in medical informatics. MIM 2010;49:207–18. Available at: http://www.schattauer.de/en/magazine/subject-areas/journals-a-z/methods/issue/special/manuscript/12987/show.html. Accessed on September 5, 2012.Suche in Google Scholar

32. Uzoka FM, Osuji J, Obot O. Clinical decision support system (DSS) in the diagnosis of malaria: a case comparison of two soft computing methodologies. Expert Syst Appl J 2011;38:1537–53.10.1016/j.eswa.2010.07.068Suche in Google Scholar

Received: 2013-4-24

Accepted: 2013-8-7

Published Online: 2013-09-06

Published in Print: 2013-09-01

Sie haben derzeit keinen Zugang zu diesem Inhalt.

Artikel in diesem Heft

https://doi.org/10.1515/bams-2013-0018

Schlagwörter für diesen Artikel

cardiovascular; diagnosis; emotional filter; fuzzy logic; heart failure; neural networks; neuro-fuzzy; therapy