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; 3384 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.
References
- Jacobs AK, Faxon DP. High-risk angioplasty: identification and management. Textbook of Interventional Cardiology. Philadelphia: W.B. Saunders Company; 1994. p. 52038
- Ritchie JL, Phillips KA, Luft HS. Coronary angioplasty: Statewide experience in California. Circulation. 1993;88:27352743
[Abstract/Free Full Text] - Holmes DR, Holubkov R, Vlietstra RE. Comparison of complications during percutaneous transluminal coronary angioplasty from 1977 to 1981 and from 1985 to 1986: The National Heart, Lung and Blood Institute Percutaneous Transluminal Coronary Angioplasty Registry. J Am Coll Cardiol. 1988;12:11491155[Abstract]
- Ellis SG, Roubin GS, King III SB. In-hospital cardiac mortality after acute closure after coronary angioplasty. Analysis of risk factors from 8207 procedures. J Am Coll Cardiol. 1988;11:211216[Abstract]
- Ellis SG, Myer RF, King III SB. Causes and correlates of death after unsupported coronary angioplasty: Implications for use of angioplasty and advanced support techniques in high-risk settings. Am J Cardiol. 1991;68:14471451[CrossRef][Web of Science][Medline]
- Park DD, Laramee LA, Teirstein P. Major complications during PTCA: analysis of 5113 cases (Abstr). J Am Coll Cardiol. 1988;11:237[Abstract]
- Ellis SG, Weintraub W, Holmes D, Shaw R, Block PC, King III SB. Relation of operator volume and experience to procedural outcome of percutaneous transluminal revascularisation at hospitals with high interventional volumes. Circulation. 1997;95:24792484
[Abstract/Free Full Text] - Ellis SG, Elliott J, Horrigan M, Raymond RE, Howell G. Low-normal and excessive body mass index: newly identified and powerful risk factors for death and other complications with percutaneous coronary intervention. Am J Cardiol. 1996;78:642646[CrossRef][Web of Science][Medline]
- Detre K, Holmes DR, Holubkov R. Incidence and consequences of periprocedural occlusion: The 19851986 National Heart, Lung and Blood Institute Percutaneous Transluminal Coronary Angioplasty Registry. Circulation. 1990;82:739750
[Abstract/Free Full Text] - DeFeyter P, van den Brand M, Jaarman GJ, Van Domburg R, Serruys PW, Suryapranata H. Acute coronary artery occlusion during and after percutaneous transluminal coronary angioplasty. Circulation. 1991;83:927936
[Abstract/Free Full Text] - Buchalter MB, Been M, Williams DO, Adams PC, Reid DS. The occurrence of early sudden coronary artery occlusion following angioplasty may be predicted from the clinical characteristics of the patients and their coronary lesion morphology. Jpn Heart J. 1992;33:295302[Medline]
- Ellis SC, Roubin GS, King III SB. Angiographic and clinical predictors of acute closure after native vessel coronary angioplasty. Circulation. 1988;77:372379
[Abstract/Free Full Text] - Thompson RC, Holmes Jr DR, Gersh BJ, Bailey KR. Predicting early and intermediate-term outcome of coronary angioplasty in the elderly. Circulation. 1993;88:15791587
[Abstract/Free Full Text] - Ryan TJ, Faxon DP, Gunnar RM. Guidelines for percutaneous transluminal coronary angioplasty: A report of the American College of Cardiology/American Heart Association Task Force on assessment of diagnostic and therapeutic cardiovascular procedures. Circulation. 1988;78:486502
[Free Full Text] - Lincoff AM, Popma JJ, Ellis SG, Hacker JA, Topol EJ. Abrupt vessel closure complicating coronary angioplasty: Clinical, angiographic and therapeutic profile. J Am Coll Cardiol. 1992;19:926935[Abstract]
- Savchenko AP, Matchin IUG, Saed IR, Smirnov AA, Pavlov NA, Liakishev AA. Clinical and angiographic predictors of initial success of percutaneous transluminal balloon angio-plasty in patients with ischemic heart disease. Vestn Rentgenol Radiol. 1995;1:510
- Bergelson BA, Jacobs AK, Cupples LA. Prediction of risk factors for hemodynamic compromise during percutaneous transluminal coronary angioplasty. Am J Cardiol. 1992;70:15401545[CrossRef][Web of Science][Medline]
- Bauters C, Van Belle E, Lablanche JM, McFadden EP, Quandalle P, Bertrand ME. Predictive factors of primary success after coronary angioplasty. Qualitative and quantitative angiography of 3679 coronary stenoses before and after dilatation. Arch Mal Coeur. 1994;87:193199
- Reeder GS, Bryant SC, Suman VJ, Holmes Jr DR. Intracoronary thrombus: still a risk factor for PTCAs failure. Cathet Cardiovasc Diagn. 1995;34:191195[Web of Science][Medline]
- Tschoepe D, Schultheiss HP, Kolarow P. Platelet membrane activation markers are predictive for increased risk of acute ischemic events after PTCA. Circulation. 1993;88:3742
[Abstract/Free Full Text] - Myler RK, Stertzer SH. Cardiopulmonary support: The risk and benefits of assisted coronary angioplasty. J Am Coll Cardiol. 1990;15:3031[Web of Science][Medline]
- Michie D, Spiegelhalter HJ, Taylor CC. Machine learning, neural and statistical classification. New York, London, Toronto, Sydney, Tokyo, Singapore: Ellis Horwood; 1994.
- Görz G. Einführung in die künstliche Intelligenz. 2. Auflage. Bonn, Paris: Addison-Wesley Verlag; 1995.
- Haddad M, Adlassnig KP, Porenta G. Feasibility analysis of a case-based reasoning system for automated detection of coronary heart disease from myocardial scintigrams. Artif Intell Med. 1997;9:6178[CrossRef][Web of Science][Medline]
- Detrano R, Bobbio M, Olson H. Computer probability estimates of angiographic coronary artery disease: transportability and comparison with cardiologists estimates. Comput Biomed Res. 1992;25:468485[CrossRef][Web of Science][Medline]
- Dumay AC, Gerbrands JJ, Reiber JH. Automated extraction, labelling and analysis of coronary vasculature from arteriograms. Int J Card Imaging. 1994;10:205215[CrossRef][Medline]
- Violaris PG, Violaris AG, Leonard R, Cumberland DC. CASSPERTan expert system to guide choice and strategy in coronary angioplasty. Int J Clin Monit Comp. 1992;9:2330[CrossRef][Web of Science][Medline]
- Schecke T, Langen M, Popp HJ, Rau G, Kasmacher H, Kalff G. Knowledge-based decision support for patient monitoring in cardioanesthesia. Int J Clin Monit Comput. 1992;9:111[CrossRef][Web of Science][Medline]
- Starren JB, Hripcsak G, Jordan D, Allen B, Weissman C, Clayton PD. Encoding a post-operative artery bypass surgery care plan in the Arden Syntax. Comput Biol Med. 1994;24:411417[CrossRef][Web of Science][Medline]
- Downs J, Harrison RF, Kennedy RL, Cross SS. Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks. Artif Intell Med. 1996;8:406428
- Delamarre D, Burgun A, Seka LP, Le Beux P. Automated coding of patient discharge summaries using conceptual graphs. Methods Inf Med. 1995;34:345351[Web of Science][Medline]
- Eliuotina SI. Computer methods of assessment of patients state for practical use in clinical laboratory. Medinfo. 1995;8:1030
- Dorffner G, Porenta G. On using feedforward neural networks for clinical diagnostic tasks. Artif Intell Med. 1994;6:417435[CrossRef][Medline]
- Bottaci L, Drew PJ, Hartley JE. Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. Lancet. 1997;350:469472[CrossRef][Web of Science][Medline]
- Budde T, Haude M, Höpp HW. A prognostic computer model to predict individual outcome in interventional cardiologyThe Intervent Project. Eur Heart J. 1997;18:16111619
[Abstract/Free Full Text] - Lefkovits J, Blankenship JC, Anderson KM. Increased risk of non-Q-wave myocardial infarction after directional atherectomy is platelet dependent: evidence from the EPIC trial. Evaluation of C7E3 for the prevention of ischemic complications. J Am Coll Cardiol. 1996;28:849855[Abstract]
- Waksman R, Ghazzal ZM, Baim DS. Myocardial infarction as a complication of new interventional devices. Am J Cardiol. 1996;78:751756[CrossRef][Web of Science][Medline]
- Fleisch M, Meier B. The ultimate interventional cardiologista computer. Eur Heart J. 1997;18:1527
[Free Full Text]
This article has been cited by other articles:
![]() |
J. E. Tcheng, I. H. Lim, S. Srinivasan, J. Jozic, C. M. Gibson, J. C. O'Shea, J. A. Puma, and D. I. Simon Stent Parameters Predict Major Adverse Clinical Events and the Response to Platelet Glycoprotein IIb/IIIa Blockade: Findings of the ESPRIT Trial Circ Cardiovasc Interv, February 1, 2009; 2(1): 43 - 51. [Abstract] [Full Text] [PDF] |
||||
![]() |
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] |
||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||


