Skip to main content

Advertisement

SpringerLink
Log in

Machine learning algorithm-based risk prediction model of coronary artery disease

  • Original Article
  • Published:
Molecular Biology Reports Aims and scope Submit manuscript

Abstract

In view of high mortality associated with coronary artery disease (CAD), development of an early predicting tool will be beneficial in reducing the burden of the disease. The database comprising demographic, conventional, folate/xenobiotic genetic risk factors of 648 subjects (364 cases of CAD and 284 healthy controls) was used as the basis to develop CAD risk and percentage stenosis prediction models using ensemble machine learning algorithms (EMLA), multifactor dimensionality reduction (MDR) and recursive partitioning (RP). The EMLA model showed better performance than other models in disease (89.3%) and stenosis prediction (82.5%). This model depicted hypertension and alcohol intake as the key predictors of CAD risk followed by cSHMT C1420T, GCPII C1561T, diabetes, GSTT1, CYP1A1 m2, TYMs 5′-UTR 28 bp tandem repeat and MTRR A66G. MDR and RP models are in agreement in projecting increasing age, hypertension and cSHMTC1420T as the key determinants interacting in modulating CAD risk. Receiver operating characteristic curves exhibited clinical utility of the developed models in the following order: EMLA (C = 0.96) > RP (C = 0.83) > MDR (C = 0.80). The stenosis prediction model showed that xenobiotic pathway genetic variants i.e. CYP1A1 m2 and GSTT1 are the key determinants of percentage of stenosis. Diabetes, diet, alcohol intake, hypertension and MTRR A66G are the other determinants of stenosis. These eleven variables contribute towards 82.5% stenosis. To conclude, the EMLA model exhibited higher predictability both in terms of disease prediction and stenosis prediction. This can be attributed to higher number of iterations in EMLA model that can increase the prediction accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Adam AM, Rehan A, Waseem N, Iqbal U, Saleem H, Ali MA, Shaikh AT, Godil A (2017) Prevalence of conventional risk factors and evaluation of baseline indices among young and elderly patients with coronary artery disease. J Clin Diagn Res 11(7):OC34–OC39

    PubMed  PubMed Central  Google Scholar 

  2. Mager A, Orvin K, Koren-Morag N, Lev IE, Assali A, Kornowski R, Shohat M, Battler A, Hasdai D (2009) Impact of homocysteine-lowering vitamin therapy on long-term outcome of patients with coronary artery disease. Am J Cardiol 104(6):745–749

    Article  CAS  PubMed  Google Scholar 

  3. Loehrer FM, Angst CP, Haefeli WE, Jordan PP, Ritz R, Fowler B (1996) Low whole-blood S-adenosylmethionine and correlation between 5-methyltetrahydrofolate and homocysteine in coronary artery disease. Arterioscler Thromb Vasc Biol 16(6):727–733

    Article  CAS  PubMed  Google Scholar 

  4. Post WS, Goldschmidt-Clermont PJ, Wilhide CC, Heldman AW, Sussman MS, Ouyang P, Milliken EE, Issa JP (1999) Methylation of the estrogen receptor gene is associated with aging and atherosclerosis in the cardiovascular system. Cardiovasc Res 43(4):985–991

    Article  CAS  PubMed  Google Scholar 

  5. Sedding DG, Tröbs M, Reich F, Walker G, Fink L, Haberbosch W, Rau W, Tillmanns H, Preissner KT, Bohle RM, Langheinrich AC (2009) 3-Deazaadenosine prevents smooth muscle cell proliferation and neointima formation by interfering with Ras signaling. Circ Res 104(10):1192–1200

    Article  CAS  PubMed  Google Scholar 

  6. Kim YR, Kim CS, Naqvi A, Kumar A, Kumar S, Hoffman TA, Irani K (2012) Epigenetic upregulation of p66shc mediates low-density lipoprotein cholesterol-induced endothelial cell dysfunction. Am J Physiol Heart Circ Physiol 303(2):H189–H196

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Guay SP, Brisson D, Munger J, Lamarche B, Gaudet D, Bouchard L (2012) ABCA1 gene promoter DNA methylation is associated with HDL particle profile and coronary artery disease in familial hypercholesterolemia. Epigenetics 7(5):464–472

    Article  CAS  PubMed  Google Scholar 

  8. Chang PY, Chen YJ, Chang FH, Lu J, Huang WH, Yang TC, Lee YT, Chang SF, Lu SC, Chen CH (2013) Aspirin protects human coronary artery endothelial cells against atherogenic electronegative LDL via an epigenetic mechanism: a novel cytoprotective role of aspirin in acute myocardial infarction. Cardiovasc Res 99(1):137–145

    Article  CAS  PubMed  Google Scholar 

  9. Guay SP, Brisson D, Lamarche B, Gaudet D, Bouchard L (2014) Epipolymorphisms within lipoprotein genes contribute independently to plasma lipid levels in familial hypercholesterolemia. Epigenetics 9(5):718–729

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Niu PP, Cao Y, Gong T, Guo JH, Zhang BK, Jia SJ (2014) Hypermethylation of DDAH2 promoter contributes to the dysfunction of endothelial progenitor cells in coronary artery disease patients. J Transl Med 12:170

    Article  PubMed  PubMed Central  Google Scholar 

  11. Fiorito G, Guarrera S, Valle C, Ricceri F, Russo A, Grioni S, Mattiello A, Di Gaetano C, Rosa F, Modica F, Iacoviello L, Frasca G, Tumino R, Krogh V, Panico S, Vineis P, Sacerdote C, Matullo G (2014) B-vitamins intake, DNA-methylation of one carbon metabolism and homocysteine pathway genes and myocardial infarction risk: the EPICOR study. Nutr Metab Cardiovasc Dis 24(5):483–488

    Article  CAS  PubMed  Google Scholar 

  12. Lakshmi SV, Naushad SM, Reddy CA, Saumya K, Rao DS, Kotamraju S, Kutala VK (2013) Oxidative stress in coronary artery disease: epigenetic perspective. Mol Cell Biochem 374(1–2):203–211

    Article  CAS  PubMed  Google Scholar 

  13. Vijaya Lakshmi SV, Naushad SM, Rupasree Y, Seshagiri Rao D, Kutala VK (2011) Interactions of 5′-UTR thymidylate synthase polymorphism with 677C → T methylene tetrahydrofolate reductase and 66A → G methyltetrahydrofolate homocysteine methyl-transferase reductase polymorphisms determine susceptibility to coronary artery disease. J Atheroscler Thromb 18(1):56–64

    Article  PubMed  Google Scholar 

  14. Lakshmi SV, Naushad SM, Saumya K, Rao DS, Kutala VK (2012) Role of CYP1A1 haplotypes in modulating susceptibility to coronary artery disease. Indian J Biochem Biophys 49(5):349–355

    CAS  PubMed  Google Scholar 

  15. Sanvisens A, Zuluaga P, Pineda M, Fuster D, Bolao F, Juncà J, Tor J, Muga R (2017) Folate deficiency in patients seeking treatment of alcohol use disorder. Drug Alcohol Depend 180:417–422

    Article  CAS  PubMed  Google Scholar 

  16. Naushad SM, Radha Rama Devi A, Nivetha S, Lakshmitha G, Stanley AB, Hussain T, Kutala VK (2017) Neurofuzzy model of homocysteine metabolism. J Genet 96(6):919–926

    Article  CAS  PubMed  Google Scholar 

  17. Yamada K, Chen Z, Rozen R, Matthews RG (2001) Effects of common polymorphisms on the properties of recombinant human methylenetetrahydrofolate reductase. Proc Natl Acad Sci USA 98(26):14853–14858

    Article  CAS  PubMed  Google Scholar 

  18. Tanis BC, Blom HJ, Bloemenkamp DG, van den Bosch MA, Algra A, van der Graaf Y, Rosendaal FR (2004) Folate, homocysteine levels, methylenetetrahydrofolate reductase (MTHFR) 677C --> T variant, and the risk of myocardial infarction in young women: effect of female hormones on homocysteine levels. J Thromb Haemost 2(1):35–41

    Article  CAS  PubMed  Google Scholar 

  19. George J, Ahmed A, Patnaik M, Adler Y, Levy Y, Harats D, Gilburd B, Terrybery J, Shen GQ, Sagie A, Herz I, Snow P, Brandt J, Peter J, Shoenfeld Y (2000) The prediction of coronary atherosclerosis employing artificial neural networks. Clin Cardiol 23(6):453–456

    Article  CAS  PubMed  Google Scholar 

  20. She J, Deng Y, Wu Y, Xia Y, Li H, Liang X, Shi R, Yuan Z (2017) Hemoglobin A1c is associated with severity of coronary artery stenosis but not with long term clinical outcomes in diabetic and nondiabetic patients with acute myocardial infarction undergoing primary angioplasty. Cardiovasc Diabetol 16(1):97

    Article  PubMed  PubMed Central  Google Scholar 

  21. Edlinger M, Wanitschek M, Dörler J, Ulmer H, Alber HF, Steyerberg EW (2017) External validation and extension of a diagnostic model for obstructive coronary artery disease: a cross-sectional predictive evaluation in 4888 patients of the Austrian Coronary Artery disease Risk Determination In Innsbruck by diaGnostic ANgiography (CARDIIGAN) cohort. BMJ Open 7(4):e014467

    Article  PubMed  PubMed Central  Google Scholar 

  22. Vijaya Lakshmi SV, Naushad SM, Seshagiri Rao D, Kutala VK (2013) Oxidative stress is associated with genetic polymorphisms in one-carbon metabolism in coronary artery disease. Cell Biochem Biophys 67(2):353–361

    Article  CAS  PubMed  Google Scholar 

  23. Sun K, Song J, Liu K, Fang K, Wang L, Wang X, Li J, Tang X, Wu Y, Qin X, Wu T, Gao P, Chen D, Hu Y (2017) Associations between homocysteine metabolism related SNPs and carotid intima-media thickness: a Chinese sib pair study. J Thromb Thrombolysis 43(3):401–410

    Article  CAS  PubMed  Google Scholar 

  24. Nilsson BB, Lunde P, Grøgaard HK, Holm I (2018) Long-term results of high-intensity exercise-based cardiac rehabilitation in revascularized patients for symptomatic coronary artery disease. Am J Cardiol 121(1):21–26

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through research Group No. (RG-1435-066).

Author information

Authors and Affiliations

  1. Sandor Lifesciences Pvt Ltd, Banjara Hills, Road No. 3, Hyderabad, India

    Shaik Mohammad Naushad & Khatoon Samreen

  2. Center of Excellence in Biotechnology Research, College of Science, King Saud University, Riyadh, Saudi Arabia

    Tajamul Hussain

  3. Department of Clinical Pharmacology and Therapeutics, Nizam’s Institute of Medical Sciences, Hyderabad, India

    Bobbala Indumathi & Vijay Kumar Kutala

  4. Department of Biochemistry, College of Science, King Saud University, Riyadh, Saudi Arabia

    Salman A. Alrokayan

  5. Biochemical Genetics & Pharmacogenomics, Sandor Lifesciences Pvt Ltd, Banjara Hills, Road No. 3, Hyderabad, 500034, India

    Shaik Mohammad Naushad

Authors
  1. Shaik Mohammad Naushad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tajamul Hussain
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bobbala Indumathi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Khatoon Samreen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Salman A. Alrokayan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Vijay Kumar Kutala
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shaik Mohammad Naushad.

Ethics declarations

Conflict of interest

None of the authors has a financial or other relationship with other people or organizations that may inappropriately influence this work.

Ethical approval

The study protocol was approved by Institutional Ethical committee of Nizam’s Institute of Medical Sciences, Hyderabad. This study complied with the ethical principles outlined in the Declaration of Helsinki.

Informed consent

Informed consent was obtained from all the study participants (cases as well as controls) during their enrollment for the study.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 199 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Naushad, S.M., Hussain, T., Indumathi, B. et al. Machine learning algorithm-based risk prediction model of coronary artery disease. Mol Biol Rep 45, 901–910 (2018). https://doi.org/10.1007/s11033-018-4236-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11033-018-4236-2

Keywords

Search

Navigation