Special Issue on Biosignal Sensing and Intelligent Information ProcessingNo Access

INTELLIGENT DATA ANALYSIS FOR THE CLASSIFICATION OF BODY SURFACE POTENTIAL MAPS

School of Computing and Mathematics, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, Newtownabbey, BT37 0QB Northern Ireland, UK

Search for more papers by this author

CHRIS D. NUGENT

School of Computing and Mathematics, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, Newtownabbey, BT37 0QB Northern Ireland, UK

Search for more papers by this author

DEWAR D. FINLAY

School of Computing and Mathematics, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, Newtownabbey, BT37 0QB Northern Ireland, UK

Search for more papers by this author

, and

NORMAN D. BLACK

School of Computing and Mathematics, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, Newtownabbey, BT37 0QB Northern Ireland, UK

Search for more papers by this author

https://doi.org/10.1142/S1469026808002284Cited by:1 (Source: Crossref)

Abstract

Body surface potential maps were investigated to identify a set of optimal recording sites required to discriminate between several diseases. Specifically, recordings captured from subjects exhibiting myocardial infarction or left ventricular hypertrophy, as well as a control group consisting of healthy subjects, were investigated. Owing to the fact that multi-class problems are inherently difficult to solve we divided the problem into several two-class scenarios. Six data sets were generated from the available 744 records, each viewing the available data differently, to form several two-class problems. A data-driven selection algorithm was applied to each of the generated data sets to produce six classification models, each utilizing as features those recording sites offering most to the discrimination task being investigated. Subsequently, a framework was introduced to facilitate the combination of outputs from each classifier. Essentially, the framework used the outputs from half of the classification models to determine which of the remaining models would be employed to form a final decision. A benchmark, in the form of a multi-group classifier, was introduced to evaluate the perceived benefits of the proposed approach. An improvement of approximately 10% upon the benchmark was observed resulting in an overall accuracy of 79.19%.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

T. L. Stedman, Stedman's Medical Dictionary, 26th edn. (Williams and Wilkins, 1995). Google Scholar
B. Taccardi and B. Punske, Cardiac Electrophysiology: From Cell to Bedside, 4th edn., eds. D. Zipes and J. Jalife (W. B. Saunders Company, Philadelphia, 2004) pp. 803–811. Crossref, Google Scholar
F. Kornreich, Card. Electrophysiol. Rev. 3, 304 (1997). Google Scholar
D. H. Brooks and R. S. MacLeod, IEEE Trans. Sig. Process. Mag. 14(2), 24 (1997), DOI: 10.1109/79.560322. Crossref, Google Scholar
D. Mirvis, Circulation 75(4), 684 (1987). Crossref, Google Scholar
L. I. Horwitz, J. Invasive Cardiol. 7(9), 265 (1995). Google Scholar
S. D. Carley, Emerg. Med. 13, 143 (2003). Google Scholar
F. Kornreichet al., Am. J. Cardiol. 60, 1230 (1987), DOI: 10.1016/0002-9149(87)90600-X. Crossref, Google Scholar
R. L. Lux, J. Electrocardiol. 35, 213 (2002), DOI: 10.1054/jelc.2002.37148. Google Scholar
R. Hoekema, G. J. H. Uijen and A. van Oosterom, J. Electrocardiol. 32(2), 93 (1999), DOI: 10.1016/S0022-0736(99)90088-2. Crossref, Google Scholar
J. A. Kors and G. van Herpen, J. Electrocardiol. 35(Suppl.), 7 (2002), DOI: 10.1054/jelc.2002.37149. Crossref, Google Scholar
R. L. Luxet al., IEEE Trans. Biomed. Eng. 25(3), 270 (1978). Google Scholar
R. L. Luxet al., Circulation 59(2), 356 (1979). Crossref, Google Scholar
R. C. Barr, M. S. Spach and G. S. Herman-Giddens, IEEE Trans. Biomed. Eng. 18(2), 125 (1971). Google Scholar
D. D. Finlayet al., BMC Med. Inform. Decision Making 6(9), (2006). Google Scholar
F. Kornreichet al., Am. J. Cardiol. 58(10), 863 (1986), DOI: 10.1016/S0002-9149(86)80001-7. Crossref, Google Scholar
F. Kornreichet al., Am. J. Cardiol. 56, 852 (1985), DOI: 10.1016/0002-9149(85)90768-4. Crossref, Google Scholar
D. D. Finlayet al., Biomed. Eng. 4(51), (2005). Google Scholar
M. P. Donnellyet al., Int. J. Assist. Robotic Mechatronics 8(2), 44 (2007). Google Scholar
F. Kornreichet al., J. Electrocardiol. 22(Suppl.), 169 (1989), DOI: 10.1016/S0022-0736(07)80119-1. Crossref, Google Scholar
M. P. Donnellyet al., Optimal electrode placements for the indentification of old MI and LVH, Proc. 33rd Ann. Int. Conf. Computers in Cardiology33 (2006) pp. 437–440. Google Scholar
S. R. McMechanet al., J. Electrocardiol. 27(Suppl.), 117 (1994), DOI: 10.1016/S0022-0736(94)80068-5. Crossref, Google Scholar
D. Finlayet al., J. Electrocardiol. 40(3), 292 (2007), DOI: 10.1016/j.jelectrocard.2006.12.015. Crossref, Google Scholar
J. C. Sharkley , Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems ( Springer , London , 1999 ) . Crossref, Google Scholar
J. Kittleret al., IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226 (1998), DOI: 10.1109/34.667881. Crossref, Google Scholar
M. B. Horaceket al., An automated system for body-surface potential maps, Proc. Computers in Cardiology (1977) pp. 399–407. Google Scholar
T. J. Montagueet al., Circulation 63(11), 1166 (1981). Crossref, Google Scholar
M. J. Gardneret al., Circulation 73, 684 (1986). Crossref, Google Scholar
J. R. Kohavi, Artif. Intell. 97(1–2), 273 (1996), DOI: 10.1016/S0004-3702(97)00043-X. Crossref, Google Scholar
P. Pudil, F. J. Novovicová and J. Kittler, Pattern Recogn. Lett. 15(11), 1119 (1994), DOI: 10.1016/0167-8655(94)90127-9. Crossref, Google Scholar
S. D. Stearns, On selecting features for pattern classifiers, Proc. 3rd Int. Joint Conf. Pattern Recogition (1976) pp. 71–75. Google Scholar