Copyright © 1999 by the European Society of Cardiology.
A prognostic computer model to individually predict post-procedural complications in interventional cardiology; the INTERVENT Project
a Department of Cardiology and Angiology, Institute for Research in Arteriosclerosis, Hospital of the Westfälische Wilhelms-University of Münster, Münster
b Department of Internal Medicine and Cardiology, Alfried Krupp Hospital, Essen
c Cardiology Department, University of Essen, Essen
d Clinic III for Internal Medicine, University of Cologne, Cologne
e Laboratory for Artificial Intelligence, University of Bremen, Bremen, Germany
revised June 13, 1998; accepted June 17, 1998
Abstract
Aims
The purpose of this part of the INTERVENT project was (1) to redefine and individually predict post-procedural complications associated with coronary interventions, including alternative/adjunctive techniques to PTCA and (2) to employ the prognostic INTERVENT computer model to clarify the structural relationship between (pre)-procedural risk factors and post-procedural outcome.
Methods and Results
In a multicentre study, 2500 data items of 455 consecutive patients (mean age: 61·1±8·3 years; 33–84 years) undergoing coronary interventions at three university centres were analysed. 80·4% of the patients were male, 16·7% had unstable angina, and 5·1%/10·1% acute/subacute myocardial infarction. There were multiple or multivessel stenoses in 16·0%, vessel bending >90° in 14·5%, irregular vessel contours in 65·0%, moderate calcifications in 20·9%, moderate/severe vessel tortuosity in 53·2% and a diameter stenosis of 90%–99% in 44·4% of cases. The in-lab (out-of-lab) complications were: 0·4% (0·9%) death, 1·8% (0·2%) abrupt vessel closure with myocardial infarction and 5·5% (4·0) haemodynamic disorders.
Conclusion
Computer algorithms derived from artificial intelligence were able to predict the individual risk of these post-procedural complications with an accuracy of >95% and to explain the structural relationship between risk factors and post-procedural complications. The most important prognostic factors were: heart failure (NYHA class), use of adjunctive/alternative techniques (rotablation, atherectomy, laser), acute coronary ischaemia, pre-existent cardiac medication, stenosis length, stenosis morphology (calcification), gender, age, amount of contrast agent and smoker status. Pre-medication with aspirin or other cardiac medication had a beneficial effect. Techniques, such as laser angioplasty or atherectomy were predictors for post-procedural complications. Single predictors alone were not able to describe the individual outcome completely.
Key Words: Artificial intelligence • computer model • interventional cardiology • postprocedural complications • PTCA • risk prediction
f1 Correspondence: PD Dr med. Thomas Budde, Klinik für Innere Medizin I und Kardiologie, Alfried Krupp Krankenhaus, Alfried-Krupp-Str. 21, D-45117 Essen, Germany.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  M. A. Qureshi, R. D. Safian, C. L. Grines, J. A. Goldstein, D. C. Westveer, S. Glazier, M. Balasubramanian, and W. W. O'Neill Simplified scoring system for predicting mortality after percutaneous coronary intervention J. Am. Coll. Cardiol., December 3, 2003; 42(11): 1890 - 1895. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 A. Vogt Letters to the Editor: Predicting complications in interventional cardiology Eur. Heart J., October 1, 1999; 20(19): 1435 - 1435. [PDF]
|
|