Konferensartikel

Classifying the Severity of an Acute Coronary Syndrome by Mining Patient Data

Niklas Lavesson
Blekinge Institute of Technology, Sweden

Anders Halling
Blekinge Competence Center, Sweden

Michael Freitag
Herlev Hospital, Sweden

Jacob Odeberg
Dept. of Medicine, Karolinska Institutet and University Hospital, Sweden

Håkan Odeberg
Blekinge Competence Center, Sweden

Paul Davidsson
Blekinge Institute of Technology, Sweden

Ladda ner artikelhttp://www.ep.liu.se/ecp_article/index.en.aspx?issue=035;article=010

Ingår i: The Swedish AI Society Workshop May 27-28; 2009 IDA; Linköping University

Linköping Electronic Conference Proceedings 35:10, s. 55-63

Visa mer +

Publicerad: 2009-05-27

ISBN:

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

Abstract

An Acute Coronary Syndrome (ACS) is a set of clinical signs and symptoms; interpreted as the result of cardiac ischemia; or abruptly decreased blood flow to the heart muscle. The subtypes of ACS include Unstable Angina (UA) and Myocardial Infarction (MI). Acute MI is the single most common cause of death for both men and women in the developed world. Several data mining studies have analyzed di erent types of patient data in order to generate models that are able to predict the severity of an ACS. Such models could be used as a basis for choosing an appropriate form of treatment. In most cases; the data is based on electrocardiograms (ECGs). In this preliminary study; we analyze a unique ACS database; featuring 28 variables; including: chronic conditions; risk factors; and laboratory results as well as classi cations into MI and UA. We evaluate different types of feature selection and apply supervised learning algorithms to a subset of the data. The experimental results are promising; indicating that this type of data could indeed be used to generate accurate models for ACS severity prediction.

Nyckelord

Inga nyckelord är tillgängliga

Referenser

[1] R. Bassan; L. Pimenta; M. Scofano; and J. F. Soares. Accuracy of a neural diagnostic tree for the identi cation of acute coronary syndrome in patients with chest pain and no stsegment elevation. Critical Pathways in Car- diology; 3(2):72-78; 2004.

[2] Ricardo Blanco-Vega; Jose Hernandez-Orallo; and M. Jose Ramrez-Quintana. Analysing the trade-o between comprehensibility and accuracy in mimetic models. In Discovery Science; pages 338-346; 2004.

[3] L. Breiman; J. H. Friedman; R. A. Olshen; and C. J. Stone. Classi cation and Regression Trees. 1984.

[4] J. Chen; Y. Xing; G. Xi; J. Chen; J. Yi; D. Zhao; and J. Wang. A comparison of four data mining models: Bayes; neural network; svm and decision trees in identifying syndromes in coronary heart disease. In Fourth International Symposium on Neural Networks; 2007.

[5] M. Green; J. Bjork; J. Forberg; U. Ekelund; L. Edenbrandt; and M. Ohlsson. Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room. Arti cial Intelligence in Medicine; 38(3):305-318; 2006.

[6] K. Holmberg; M-L. Persson; M. Uhlen; and J. Odeberg. Pyrosequencing analysis of thrombosis-associated risk markers. Clinical Chemistry; 51:1549-1552; 2005.

7] R. D. King; C. Feng; and A. Sutherland. STATLOG: Comparison of classi cation algorithms on large real-world problems. Applied Arti cial Intelligence; 9(3):259-287; 1995.

[8] C. L. McCullough; A. J. Novobilski; and F. M. Fesmire. Use of neural networks to predict adverse outcomes from acute coronary syndrome for male and female patients. In Sixth Inter- national Conference on Machine Learning and Applications; 2004.

[9] J. Odeberg; M. Freitag; H. Odeberg; L. Rastam; and U. Lindblad. Severity of acute coronary syndrome is predicted by interactions between brinogen concentrations and polymorphisms in the GPIIIa and FXIII genes. Thrombosis and Haemostasis; 4:909-912; 2006.

[10] Foster Provost; Tom Fawcett; and Ron Kohavi. The case against accuracy estimation for comparing induction algorithms. In 15th In- ternational Conference on Machine Learning; pages 445-453; San Francisco; CA; USA; 1998. Morgan Kaufmann Publishers.

[11] R. A. Rusnak; T. O. Stair; K. Hansen; and J. S. Fastow. Litigation against the emergency physician: Common features in cases of missed myocardial infarction. Annals of Emergency Medicine; 18:1029-1034; 1989.

[12] H. Tunstall-Pedoe; K. Kuulasmaa; P. Amouyel; D. Arveiler; A. M. Rajakangas; and A. Pajak. Myocardial infarction and coronary deaths in the World Health Organization MONICA project. registration procedures; event rates; and case-fatality rates in 38 populations from 21 countries in four continents. Circulation; 90(1):583-612; 1994.

[13] L. Wallentin and B. Lindahl A. Siegbahn. Unstable coronary artery disease. In E. Falk; editor; Textbook of Cardiac Disease. Mosby; New York; 2002.

[14] Ian H. Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Tech- niques. Morgan Kaufmann Publishers; San Francisco; CA; USA; 2005.

[15] L. Xu; P. Yan; and T. Chang. Best rst strategy for feature selection. In Ninth In- ternational Conference on Pattern Recogni- tion; pages 706-708; New york City; NY; USA; 1988. IEEE Press.

Citeringar i Crossref