Abstract
Background
Known coronary artery disease (CAD) risk scores (e.g., Framingham) estimate the CAD-related event risk rather than presence/absence of CAD. Artificial intelligence (AI) is rarely used in this context.
Aims
This study aims to evaluate the diagnostic power of AI (memetic pattern-based algorithm (MPA)) in CAD and to expand its applicability to a broader patient population.
Methods and results
Nine hundred eighty-seven patients of the Ludwigshafen Risk and Cardiovascular Health Study (LURIC) were divided into a training (n = 493) and a test population (n = 494). They were evaluated by the Basel MPA. The “training population” was further used to expand and optimize the Basel MPA, and after modifications, a final validation was carried out on the “test population.” The results were compared with the Framingham Risk Score (FRS) using receiver operating curves (ROC; area-under-the-curve (AUC)). Of the 987 LURIC patients, 71% were male, age 62 ± 11 years and 68% had documented CAD. AUC of Framingham and BASEL MPA to diagnose CAD in “LURIC training” were 0.69 and 0.80, respectively. AUC of the optimized MPA in the training and test cohort were 0.88 and 0.87, respectively. The positive predictive values (PPV) of the optimized MPA for exclusion of CAD in “training” and “test” were 98 and 95%, respectively. The PPV of MPA for identification of CAD was 93 and 94%, respectively.
Conclusions
The successful use of the MPA approach has been demonstrated in a broad-risk spectrum of patients undergoing CAD evaluation, as an element of predictive, preventive, personalized medicine, and may be used instead of further non-invasive diagnostic procedures.
Similar content being viewed by others
Abbreviations
- AI:
-
Artificial intelligence
- CAD:
-
Coronary artery disease
- FRS:
-
Framingham Risk Score
- PROCAM:
-
Prospective Cardiovascular Münster Study
- LURIC:
-
Ludwigshafen Risk and Cardiovascular Health Study
- MPA:
-
Memetic pattern-based algorithm
- PPPM:
-
Predictive, preventive, and personalized medicine
- MCV:
-
Mean corpuscular volume of red blood cells
- MCHC:
-
Mean corpuscular hemoglobin concentration of red blood cells
- INR:
-
International normalized ratio (anticoagulation)
- GGT:
-
Gamma-glutamyl transferase
- ALAT:
-
Alanine aminotransferase
- ASAT:
-
Aspartate aminotransferase
- LDL:
-
Low-density lipoprotein
- HDL:
-
High-density lipoprotein
- H+:
-
Healthy patients/individuals (coronary artery disease excluded)
- CAD+:
-
Patients with coronary artery disease
- TP:
-
True-positive result
- FP:
-
False-positive result
- AUC:
-
Area under the curve
References
Executive Summary of the Third Report of the National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, and Treatment of High Blood Cholesterol in Adults (Adult Treatment Panel III). JAMA. 2001;285(19):2486–97.
D'Agostino RB, Russell MW, Huse DM, Ellison RC, Silbershatz H, Wilson PW, et al. Primary and subsequent coronary risk appraisal: new results from the Framingham study. Am Heart J. 2000;139(2 Pt 1):272–81.
Assmann G, Cullen P, Schulte H. The Munster Heart Study (PROCAM). Results of follow-up at 8 years. Eur Heart J. 1998;19(Suppl A):A2–11.
Assmann GCP, Schulte H. The Münster Heart Study. Results of follow-up at 8 years. (PROCAM). Eur Heart J. 1998;19(Suppl A):A2–11.
Ridker PM, Buring JE, Rifai N, Cook NR. Development and validation of improved algorithms for the assessment of global cardiovascular risk in women: the Reynolds risk score. JAMA. 2007;297(6):611–9. https://doi.org/10.1001/jama.297.6.611.
Ridker PM, Paynter NP, Rifai N, Gaziano JM, Cook NR. C-reactive protein and parental history improve global cardiovascular risk prediction: the Reynolds Risk Score for men. Circulation. 2008;118(22):2243–51, 4p following 51. https://doi.org/10.1161/circulationaha.108.814251.
Brunner-La Rocca HP, Fleischhacker L, Golubnitschaja O, Heemskerk F, Helms T, Hoedemakers T, et al. Challenges in personalised management of chronic diseases-heart failure as prominent example to advance the care process. EPMA J. 2015;7:2. https://doi.org/10.1186/s13167-016-0051-9.
Golubnitschaja O, Baban B, Boniolo G, Wang W, Bubnov R, Kapalla M, et al. Medicine in the early twenty-first century: paradigm and anticipation-EPMA position paper 2016. The EPMA Journal. 2016;7:–23. https://doi.org/10.1186/s13167-016-0072-4.
Golubnitschaja O, Costigliola V. EPMA summit 2014 under the auspices of the presidency of Italy in the EU: professional statements. EPMA J. 2015;6(1):4. https://doi.org/10.1186/s13167-015-0026-2.
Polivka J Jr, Altun I, Golubnitschaja O. Pregnancy-associated breast cancer: the risky status quo and new concepts of predictive medicine. EPMA J. 2018;9(1):1–13. https://doi.org/10.1007/s13167-018-0129-7.
Zellweger MJ, Brinkert M, Bucher U, Tsirkin A, Ruff P, Pfisterer ME. A new memetic pattern based algorithm to diagnose/exclude coronary artery disease. Int J Cardiol. 2014;174(1):184–6. https://doi.org/10.1016/j.ijcard.2014.03.184.
Ngwa JS, Cabral HJ, Cheng DM, Pencina MJ, Gagnon DR, LaValley MP, et al. A comparison of time dependent cox regression, pooled logistic regression and cross sectional pooling with simulations and an application to the Framingham heart study. BMC Med Res Methodol. 2016;16(1):148. https://doi.org/10.1186/s12874-016-0248-6.
D'Agostino RB, Lee ML, Belanger AJ, Cupples LA, Anderson K, Kannel WB. Relation of pooled logistic regression to time dependent Cox regression analysis: the Framingham heart study. Stat Med. 1990;9(12):1501–15.
Siontis GC, Tzoulaki I, Siontis KC, Ioannidis JP. Comparisons of established risk prediction models for cardiovascular disease: systematic review. BMJ. 2012;344:e3318.
Shaw LJ, Polk DM, Kahute TA, Wong ND, Moon J, Miranda-Peats R, et al. Prognostic accuracy of B-natriuretic peptide measurements and coronary artery calcium in asymptomatic subjects (from the early identification of subclinical atherosclerosis by noninvasive imaging research [EISNER] study). Am J Cardiol. 2009;104(9):1245–50. https://doi.org/10.1016/j.amjcard.2009.06.041.
Grossi E. How artificial intelligence tools can be used to assess individual patient risk in cardiovascular disease: problems with the current methods. BMC Cardiovasc Disord. 2006;6:20. https://doi.org/10.1186/1471-2261-6-20.
Ioannidis JP. Personalized genetic prediction: too limited, too expensive, or too soon? Ann Intern Med. 2009;150(2):139–41.
Itchhaporia D, Snow PB, Almassy RJ, Oetgen WJ. Artificial neural networks: current status in cardiovascular medicine. J Am Coll Cardiol. 1996;28(2):515–21. https://doi.org/10.1016/0735-1097(96)00174-x.
Tzoulaki I, Liberopoulos G, Ioannidis JP. Assessment of claims of improved prediction beyond the Framingham risk score. JAMA. 2009;302(21):2345–52. https://doi.org/10.1001/jama.2009.1757.
Winkelmann BR, Marz W, Boehm BO, Zotz R, Hager J, Hellstern P, et al. Rationale and design of the LURIC study—a resource for functional genomics, pharmacogenomics and long-term prognosis of cardiovascular disease. Pharmacogenomics. 2001;2(1 Suppl 1):S1–73. https://doi.org/10.1517/14622416.2.1.s1.
Reibnegger G, Schrabmair W. Optimum binary cut-off threshold of a diagnostic test: comparison of different methods using Monte Carlo technique. BMC Med Inform Decis Making. 2014;14:99. https://doi.org/10.1186/s12911-014-0099-1.
Carpenter GA, Grossberg S, Markuzon N, Reynolds JH, Rosen DB. Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans Neural Netw. 1992;3(5):698–713. https://doi.org/10.1109/72.159059.
Catto JW, Linkens DA, Abbod MF, Chen M, Burton JL, Feeley KM, et al. Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. Clin Cancer Res. 2003;9(11):4172–7.
Hammer B, Micheli A, Sperduti A, Strickert M. Recursive self-organizing network models. Neural Netw. 2004;17(8–9):1061–85. https://doi.org/10.1016/j.neunet.2004.06.009.
Johnson DS, Hoeting JA. Autoregressive models for capture-recapture data: a Bayesian approach. Biometrics. 2003;59(2):341–50.
Knowles JD, Corne DW. Approximating the nondominated front using the Pareto archived evolution strategy. Evol Comput. 2000;8(2):149–72. https://doi.org/10.1162/106365600568167.
Kohonen T. Self-organizing neural projections. Neural Netw. 2006;19(6–7):723–33. https://doi.org/10.1016/j.neunet.2006.05.001.
Kuncheva LI. Evaluation of computerized medical diagnostic decisions via fuzzy sets. Int J Biomed Comput. 1991;28(1–2):91–100.
Mobley BA, Schechter E, Moore WE, McKee PA, Eichner JE. Predictions of coronary artery stenosis by artificial neural network. Artif Intell Med. 2000;18(3):187–203.
Mobley BA, Schechter E, Moore WE, McKee PA, Eichner JE. Neural network predictions of significant coronary artery stenosis in men. Artif Intell Med. 2005;34(2):151–61. https://doi.org/10.1016/j.artmed.2004.08.003.
Moon H, Ahn H, Kodell RL, Baek S, Lin CJ, Chen JJ. Ensemble methods for classification of patients for personalized medicine with high-dimensional data. Artif Intell Med. 2007;41(3):197–207. https://doi.org/10.1016/j.artmed.2007.07.003.
Ontrup J, Ritter H. Large-scale data exploration with the hierarchically growing hyperbolic SOM. Neural Netw. 2006;19(6–7):751–61. https://doi.org/10.1016/j.neunet.2006.05.015.
Montalescot G, Sechtem U, Achenbach S, Andreotti F, Arden C, Budaj A, et al. 2013 ESC guidelines on the management of stable coronary artery disease: the task force on the management of stable coronary artery disease of the European Society of Cardiology. Eur Heart J. 2013;34(38):2949–3003. https://doi.org/10.1093/eurheartj/eht296.
Kurt I, Ture M, Kurum AT. Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert Syst Appl. 2008;34(34):366–74.
Acknowledgments
The MPA modeling process, used in this study has received the 2018 Swiss Biolabs Award for its implementation in a prototype “Cardioexplorer.” The jury consisted of Universities (University Hospital Basel, School of Life sciences Biotechnet Switzerland), industry partners (Sensile Medical, Roche Diagnostics, Omya International AG, Ava Science, Bühlmann Laboratories), and Associations (Swiss Biolabs Association, Economic Development Agency Olten, Basel Area).
Funding
The study was in part funded by the Swiss Heart Foundation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Michael J. Zellweger is an advisory board member of Exploris AG. Peter Ruff is part owner, board member, and head of Exploris AG, which is a privately owned Swiss research company focusing on development of novel diagnostic solutions. Andrew Tsirkin is head in the modeling and development team of Exploris AG. Vasily Vasilchenko is a data analyst of Exploris AG. Michael Failer is head for regulatory affairs of Exploris AG. Alexander Dressel and Marcus E. Kleber declare that they have no conflict of interest. Winfried März is an advisory board member of Exploris AG.
Ethical approval
All procedures performed in this study involving human participants were in accordance with the ethical standards of the locally appointed ethics committees (Basel: Ethikkommission beider Basel; reference number: 67/08; LURIC: Ethics Committee at the “Ärztekammer Rheinland-Pfalz”; reference number: 837.255.97 (1394)). The study is also in accordance with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Consent
Informed consent has been obtained from all of the patients.
Rights and permissions
About this article
Cite this article
Zellweger, M.J., Tsirkin, A., Vasilchenko, V. et al. A new non-invasive diagnostic tool in coronary artery disease: artificial intelligence as an essential element of predictive, preventive, and personalized medicine. EPMA Journal 9, 235–247 (2018). https://doi.org/10.1007/s13167-018-0142-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13167-018-0142-x