Advertisement

Artificial Intelligence and Data Mining Methods for Cardiovascular Risk Prediction

  • Eleni I. Georga
  • Nikolaos S. Tachos
  • Antonis I. Sakellarios
  • Vassiliki I. Kigka
  • Themis P. Exarchos
  • Gualtiero Pelosi
  • Oberdan Parodi
  • Lampros K. Michalis
  • Dimitrios I. FotiadisEmail author
Chapter
Part of the Series in BioEngineering book series (SERBIOENG)

Abstract

This chapter describes the state-of-the-art in artificial intelligence and machine learning methods for cardiovascular disease diagnosis and prognosis, focusing on Coronary Artery Disease (CAD). We aim at providing a cohesive overview of the existing methodologies in the topic and the most exploitable predictors for CAD staging and evolution. Thus, the relevant literature is analysed and contrasted with respect to the acquired dataset, the examined feature space, the employed predictive modelling schemes and their discriminative or predictive capacity. Moreover, important challenges stemming from the increasing ubiquity of electronic health records, personal health records and big data are discussed and, given the limitations of current approaches, future directions are delineated.

Keywords

Machine learning Artificial intelligence Cardiovascular disease Coronary artery disease Atherosclerosis Diagnosis Prediction 

List of Abbreviations

ATS

Atherosclerosis

AUC

Area Under the ROC Curve

BMI

Body Mass Index

CA

Coronary Angiography

CAD

Coronary Artery Disease

CART

Classification and Regression Trees

CFS

Correlation-based Feature Selection

CTA

Computed Tomography Angiography

CVD

Cardiovascular Disease

DBN

Dynamic Bayesian Network

EHR

Electronic Health Record

FFNN

Feed-forward Neural Network

FRS

Framingham Risk Score

FURIA

Fuzzy Unordered Rule Induction Algorithm

GAM

Generalized Additive Model

GBT

Gradient Boosted Trees

HDL

High-density Lipoprotein

IVUS

Intravascular Ultrasound

LAD

Left Anterior Descending

LCX

Left Circumflex

LDL

Low-density Lipoprotein

LR

Logistic Regression

MRI

Magnetic Resonance Imaging

NPV

Negative Predictive Value

OCT

Optical Coherence Tomography

PHR

Personal Health Record

PPV

Positive Predictive Value

RBF

Radial Basis Function Network

RCA

Right Coronary Artery

RF

Random Forest

ROC

Receiver Operating Curve

RTF

Rotation Forest

SMOTE

Synthetic Minority Oversampling Technique

SOFM

Self-organizing Feature Map

SVM

Support Vector Machine

TA

Temporal Abstraction

Notes

Acknowledgements

This work is partially funded by the European Commission: Project SMARTOOL, “Simulation Modeling of coronary ARTery disease: a tool for clinical decision support—SMARTool” GA number: 689068.

References

  1. 1.
    Stone PH, Saito S, Takahashi S, Makita Y, Nakamura S, Kawasaki T, Takahashi A, Katsuki T, Nakamura S, Namiki A, Hirohata A, Matsumura T, Yamazaki S, Yokoi H, Tanaka S, Otsuji S, Yoshimachi F, Honye J, Harwood D, Reitman M, Coskun AU, Papafaklis MI, Feldman CL (2012) Prediction of progression of coronary artery disease and clinical outcomes using vascular profiling of endothelial shear stress and arterial plaque characteristics: the PREDICTION study. Circulation 126(2):172–181.  https://doi.org/10.1161/circulationaha.112.096438CrossRefGoogle Scholar
  2. 2.
    Sakellarios A, Bourantas CV, Papadopoulou S-L, Tsirka Z, de Vries T, Kitslaar PH, Girasis C, Naka KK, Fotiadis DI, Veldhof S, Stone GW, Reiber JHC, Michalis LK, Serruys PW, de Feyter PJ, Garcia-Garcia HM (2017) Prediction of atherosclerotic disease progression using LDL transport modelling: a serial computed tomographic coronary angiographic study. Eur Heart J Cardiovasc Imaging 18(1):11–18.  https://doi.org/10.1093/ehjci/jew035CrossRefGoogle Scholar
  3. 3.
    Piepoli MF, Hoes AW, Agewall S, Albus C, Brotons C, Catapano AL, Cooney MT, Corra U, Cosyns B, Deaton C, Graham I, Hall MS, Hobbs FD, Lochen ML, Lollgen H, Marques-Vidal P, Perk J, Prescott E, Redon J, Richter DJ, Sattar N, Smulders Y, Tiberi M, van der Worp HB, van Dis I, Verschuren WM (2016) European Guidelines on cardiovascular disease prevention in clinical practice: the Sixth Joint Task Force of the European Society of Cardiology and other societies on cardiovascular disease prevention in clinical practice (constituted by representatives of 10 societies and by invited experts) Developed with the special contribution of the European Association for Cardiovascular Prevention & Rehabilitation (EACPR). Eur Heart J 37(29):2315–2381.  https://doi.org/10.1093/eurheartj/ehw106CrossRefGoogle Scholar
  4. 4.
    Ferguson JF, Allayee H, Gerszten RE, Ideraabdullah F, Kris-Etherton PM, Ordovas JM, Rimm EB, Wang TJ, Bennett BJ (2016) Nutrigenomics, the microbiome, and gene-environment interactions: new directions in cardiovascular disease research, prevention, and treatment: a scientific statement from the American Heart Association. Circ Cardiovasc Genet 9(3):291–313.  https://doi.org/10.1161/hcg.0000000000000030CrossRefGoogle Scholar
  5. 5.
    D’Agostino RB Sr, Vasan RS, Pencina MJ, Wolf PA, Cobain M, Massaro JM, Kannel WB (2008) General cardiovascular risk profile for use in primary care: the Framingham Heart Study. Circulation 117(6):743–753.  https://doi.org/10.1161/circulationaha.107.699579CrossRefGoogle Scholar
  6. 6.
    Conroy RM, Pyorala K, Fitzgerald AP, Sans S, Menotti A, De Backer G, De Bacquer D, Ducimetiere P, Jousilahti P, Keil U, Njolstad I, Oganov RG, Thomsen T, Tunstall-Pedoe H, Tverdal A, Wedel H, Whincup P, Wilhelmsen L, Graham IM (2003) Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J 24(11):987–1003CrossRefGoogle Scholar
  7. 7.
    Hippisley-Cox J, Coupland C, Robson J, Brindle P (2010) Derivation, validation, and evaluation of a new QRISK model to estimate lifetime risk of cardiovascular disease: cohort study using QResearch database. BMJ (Clinical research ed) 341:c6624.  https://doi.org/10.1136/bmj.c6624CrossRefGoogle Scholar
  8. 8.
    Damen JA, Hooft L, Schuit E, Debray TP, Collins GS, Tzoulaki I, Lassale CM, Siontis GC, Chiocchia V, Roberts C, Schlussel MM, Gerry S, Black JA, Heus P, van der Schouw YT, Peelen LM, Moons KG (2016) Prediction models for cardiovascular disease risk in the general population: systematic review. BMJ (Clinical research ed) 353:i2416.  https://doi.org/10.1136/bmj.i2416CrossRefGoogle Scholar
  9. 9.
    Goldstein BA, Navar AM, Carter RE (2017) Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J 38(23):1805–1814.  https://doi.org/10.1093/eurheartj/ehw302CrossRefGoogle Scholar
  10. 10.
    Volzke H, Schmidt CO, Baumeister SE, Ittermann T, Fung G, Krafczyk-Korth J, Hoffmann W, Schwab M, Meyer zu Schwabedissen HE, Dorr M, Felix SB, Lieb W, Kroemer HK (2013) Personalized cardiovascular medicine: concepts and methodological considerations. Nat Rev Cardiol 10(6):308–316.  https://doi.org/10.1038/nrcardio.2013.35CrossRefGoogle Scholar
  11. 11.
    Ng K, Steinhubl SR, deFilippi C, Dey S, Stewart WF (2016) Early detection of heart failure using electronic health records: practical implications for time before diagnosis, data diversity, data quantity, and data density. Circ Cardiovasc Qual Outcomes 9(6):649–658.  https://doi.org/10.1161/circoutcomes.116.002797CrossRefGoogle Scholar
  12. 12.
    Karaolis MA, Moutiris JA, Hadjipanayi D, Pattichis CS (2010) Assessment of the risk factors of coronary heart events based on data mining with decision trees. IEEE Trans Inf Technol Biomed 14(3):559–566.  https://doi.org/10.1109/TITB.2009.2038906CrossRefGoogle Scholar
  13. 13.
    Nahar J, Imam T, Tickle KS, Chen Y-PP (2013) Association rule mining to detect factors which contribute to heart disease in males and females. Expert Syst Appl 40(4):1086–1093.  https://doi.org/10.1016/j.eswa.2012.08.028CrossRefGoogle Scholar
  14. 14.
    Austin PC, Tu JV, Ho JE, Levy D, Lee DS (2013) Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. J Clin Epidemiol 66(4):398–407.  https://doi.org/10.1016/j.jclinepi.2012.11.008CrossRefGoogle Scholar
  15. 15.
    Kurt I, Ture M, Kurum AT (2008) Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert Syst Appl 34(1):366–374.  https://doi.org/10.1016/j.eswa.2006.09.004CrossRefGoogle Scholar
  16. 16.
    Choi E, Schuetz A, Stewart WF, Sun J (2017) Using recurrent neural network models for early detection of heart failure onset. J Am Med Inform Assoc JAMIA 24(2):361–370.  https://doi.org/10.1093/jamia/ocw112CrossRefGoogle Scholar
  17. 17.
    Hassan N, Sayed OR, Khalil AM, Ghany MA (2016) Fuzzy soft expert system in prediction of coronary artery disease. Int J Fuzzy Syst.  https://doi.org/10.1007/s40815-016-0255-0CrossRefGoogle Scholar
  18. 18.
    Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH, Andreini D, Budoff MJ, Cademartiri F, Callister TQ, Chang H-J, Chinnaiyan K, Chow BJW, Cury RC, Delago A, Gomez M, Gransar H, Hadamitzky M, Hausleiter J, Hindoyan N, Feuchtner G, Kaufmann PA, Kim Y-J, Leipsic J, Lin FY, Maffei E, Marques H, Pontone G, Raff G, Rubinshtein R, Shaw LJ, Stehli J, Villines TC, Dunning A, Min JK, Slomka PJ (2017) Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur Heart J 38(7):500–507.  https://doi.org/10.1093/eurheartj/ehw188CrossRefGoogle Scholar
  19. 19.
    Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N (2017) Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One 12(4):e0174944.  https://doi.org/10.1371/journal.pone.0174944CrossRefGoogle Scholar
  20. 20.
    Rao VSH, Kumar MN (2013) Novel approaches for predicting risk factors of atherosclerosis. IEEE J Biomed Health Inform 17(1):183–189.  https://doi.org/10.1109/TITB.2012.2227271CrossRefGoogle Scholar
  21. 21.
    Kukar M, Kononenko I, Grošelj C (2011) Modern parameterization and explanation techniques in diagnostic decision support system: a case study in diagnostics of coronary artery disease. Artif Intell Med 52(2):77–90.  https://doi.org/10.1016/j.artmed.2011.04.009CrossRefGoogle Scholar
  22. 22.
    Shouman M, Turner T, Stocker R (2012) Using data mining techniques in heart disease diagnosis and treatment. In: 2012 Japan-Egypt conference on electronics, communications and computers, 6–9 March 2012, pp 173–177.  https://doi.org/10.1109/jec-ecc.2012.6186978
  23. 23.
    Melillo P, Izzo R, Orrico A, Scala P, Attanasio M, Mirra M, De Luca N, Pecchia L (2015) Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis. PLoS One 10(3):e0118504.  https://doi.org/10.1371/journal.pone.0118504CrossRefGoogle Scholar
  24. 24.
    Rumsfeld JS, Joynt KE, Maddox TM (2016) Big data analytics to improve cardiovascular care: promise and challenges. Nat Rev Cardiol 13(6):350–359.  https://doi.org/10.1038/nrcardio.2016.42CrossRefGoogle Scholar
  25. 25.
    Groeneveld PW, Rumsfeld JS (2016) Can big data fulfill its promise? Circ Cardiovasc Qual Outcomes 9(6):679–682.  https://doi.org/10.1161/circoutcomes.116.003097Google Scholar
  26. 26.
    Tsipouras MG, Exarchos TP, Fotiadis DI, Kotsia AP, Vakalis KV, Naka KK, Michalis LK (2008) Automated diagnosis of coronary artery disease based on data mining and fuzzy modeling. IEEE Trans Inf Technol Biomed 12(4):447–458.  https://doi.org/10.1109/TITB.2007.907985CrossRefGoogle Scholar
  27. 27.
    Anooj PK (2012) Clinical decision support system: Risk level prediction of heart disease using weighted fuzzy rules. J King Saud Univ-Comput Inf Sci 24(1):27–40.  https://doi.org/10.1016/j.jksuci.2011.09.002CrossRefGoogle Scholar
  28. 28.
    Karabulut EM, Ibrikci T (2012) Effective diagnosis of coronary artery disease using the rotation forest ensemble method. J Med Syst 36(5):3011–3018.  https://doi.org/10.1007/s10916-011-9778-yCrossRefGoogle Scholar
  29. 29.
    Nahar J, Imam T, Tickle KS, Chen Y-PP (2013) Computational intelligence for heart disease diagnosis: a medical knowledge driven approach. Expert Syst Appl 40(1):96–104.  https://doi.org/10.1016/j.eswa.2012.07.032CrossRefGoogle Scholar
  30. 30.
    Alizadehsani R, Habibi J, Hosseini MJ, Mashayekhi H, Boghrati R, Ghandeharioun A, Bahadorian B, Sani ZA (2013) A data mining approach for diagnosis of coronary artery disease. Comput Methods Programs Biomed 111(1):52–61.  https://doi.org/10.1016/j.cmpb.2013.03.004CrossRefGoogle Scholar
  31. 31.
    Alizadehsani R, Zangooei MH, Hosseini MJ, Habibi J, Khosravi A, Roshanzamir M, Khozeimeh F, Sarrafzadegan N, Nahavandi S (2016) Coronary artery disease detection using computational intelligence methods. Knowl-Based Syst 109:187–197.  https://doi.org/10.1016/j.knosys.2016.07.004CrossRefGoogle Scholar
  32. 32.
    Verma L, Srivastava S, Negi PC (2016) A hybrid data mining model to predict coronary artery disease cases using non-invasive clinical data. J Med Syst 40(7):178.  https://doi.org/10.1007/s10916-016-0536-zCrossRefGoogle Scholar
  33. 33.
    Detrano R, Janosi A, Steinbrunn W, Pfisterer M, Schmid JJ, Sandhu S, Guppy KH, Lee S, Froelicher V (1989) International application of a new probability algorithm for the diagnosis of coronary artery disease. Am J Cardiol 64(5):304–310CrossRefGoogle Scholar
  34. 34.
    Das R, Turkoglu I, Sengur A (2009) Effective diagnosis of heart disease through neural networks ensembles. Expert Syst Appl 36(4):7675–7680.  https://doi.org/10.1016/j.eswa.2008.09.013CrossRefGoogle Scholar
  35. 35.
    Exarchos KP, Carpegianni C, Rigas G, Exarchos TP, Vozzi F, Sakellarios A, Marraccini P, Naka K, Michalis L, Parodi O, Fotiadis DI (2015) A multiscale approach for modeling atherosclerosis progression. IEEE J Biomed Health Inform 19(2):709–719.  https://doi.org/10.1109/jbhi.2014.2323935CrossRefGoogle Scholar
  36. 36.
    Kennedy EH, Wiitala WL, Hayward RA, Sussman JB (2013) Improved cardiovascular risk prediction using nonparametric regression and electronic health record data. Med Care 51(3):251–258.  https://doi.org/10.1097/MLR.0b013e31827da594CrossRefGoogle Scholar
  37. 37.
    Orphanou K, Stassopoulou A, Keravnou E (2016) DBN-extended: a dynamic Bayesian network model extended with temporal abstractions for coronary heart disease prognosis. IEEE J Biomed Health Inform 20(3):944–952.  https://doi.org/10.1109/jbhi.2015.2420534CrossRefGoogle Scholar
  38. 38.
    Goff DC, Lloyd-Jones DM, Bennett G, Coady S, D’Agostino RB, Gibbons R, Greenland P, Lackland DT, Levy D, O’Donnell CJ, Robinson J, Schwartz JS, Shero ST, Smith SC, Sorlie P, Stone NJ, Wilson PWF (2013) 2013 ACC/AHA guideline on the assessment of cardiovascular risk. A report of the American College of Cardiology/American Heart Association Task Force on practice guidelines.  https://doi.org/10.1161/01.cir.0000437741.48606.98CrossRefGoogle Scholar
  39. 39.
    Goldstein BA, Navar AM, Pencina MJ, Ioannidis JP (2017) Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review. J Am Med Inform Assoc 24(1):198–208.  https://doi.org/10.1093/jamia/ocw042CrossRefGoogle Scholar
  40. 40.
    Batal I, Valizadegan H, Cooper GF, Hauskrecht M (2013) A temporal pattern mining approach for classifying electronic health record data. ACM Trans Intell Syst Technol 4(4).  https://doi.org/10.1145/2508037.2508044CrossRefGoogle Scholar
  41. 41.
    Batal I, Cooper GF, Fradkin D, Harrison J, Moerchen F, Hauskrecht M (2016) An efficient pattern mining approach for event detection in multivariate temporal data. Knowl Inf Syst 46(1):115–150.  https://doi.org/10.1007/s10115-015-0819-6CrossRefGoogle Scholar
  42. 42.
    Moskovitch R, Shahar Y (2015) Fast time intervals mining using the transitivity of temporal relations. Knowl Inf Syst 42(1):21–48.  https://doi.org/10.1007/s10115-013-0707-xCrossRefGoogle Scholar
  43. 43.
    Moskovitch R, Shahar Y (2009) Medical temporal-knowledge discovery via temporal abstraction. AMIA Annu Symp Proc 2009:452–456Google Scholar
  44. 44.
    Orphanou K, Stassopoulou A, Keravnou E (2014) Temporal abstraction and temporal Bayesian networks in clinical domains: a survey. Artif Intell Med 60(3):133–149.  https://doi.org/10.1016/j.artmed.2013.12.007CrossRefGoogle Scholar
  45. 45.
    Bellazzi R, Sacchi L, Concaro S (2009) Methods and tools for mining multivariate temporal data in clinical and biomedical applications. In: Conference proceedings: annual international conference of the IEEE engineering in medicine and biology society IEEE engineering in medicine and biology society annual conference 2009:5629–5632.  https://doi.org/10.1109/iembs.2009.5333788
  46. 46.
    Miotto R, Li L, Kidd BA, Dudley JT (2016) Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci Rep 6:26094.  https://doi.org/10.1038/srep26094CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Eleni I. Georga
    • 1
  • Nikolaos S. Tachos
    • 2
  • Antonis I. Sakellarios
    • 2
  • Vassiliki I. Kigka
    • 1
    • 2
  • Themis P. Exarchos
    • 1
  • Gualtiero Pelosi
    • 3
  • Oberdan Parodi
    • 3
  • Lampros K. Michalis
    • 4
  • Dimitrios I. Fotiadis
    • 1
    • 2
    Email author
  1. 1.Unit of Medical Technology and Intelligent Information Systems, Materials Science and Engineering DepartmentUniversity of IoanninaIoanninaGreece
  2. 2.Biomedical Research DepartmentFORTH, Institute of Molecular Biology and BiotechnologyIoanninaGreece
  3. 3.Institute of Clinical Physiology, National Research CouncilPisaItaly
  4. 4.Department of Cardiology, Medical SchoolUniversity of IoanninaIoanninaGreece

Personalised recommendations