Estimation of Risk Factors Related to Heart Diseases With Multilayer Perceptron Model

Öz

Aim: Heart diseases (HD) refer to many diseases such as coronary heart disease, heart failure, and heart attack. Every year, approximately 647.000 people die in the United States (U.S.) from HD. Genetic and environmental risk factors have been identified due to numerous studies to determine HD risk factors.
Material and Method: In this study, the Multilayer Perceptron (MLP) model was constructed to predict the risk factors related to HD in both genders. The relevant dataset consisted of 270 individuals, 13 predictors, and one response/target variable. Model performance was evaluated using overall accuracy, the area under the ROC (Receiver Operating Characteristics) curve (AUC), sensitivity, and specificity metrics.
Results: The performance metric values for accuracy, AUC, sensitivity and specificity were obtained with 95% CI, 0.876 (0.79-0.937), 0.935 (0.877-0.992), 0.921 (0.786-0.983) and 0.843 (0.714-0.93), respectively. According to the relevant model findings, blood pressure, the number of significant vessels coloured by fluoroscopy, and cholesterol variables were the three most crucial HD classification factors.
Discussion: It can be said that the model used in the present study offers an acceptable estimation performance when all performance metrics are considered. In addition, when compared with the studies in the literature from both data science and statistical point of view, it can be stated that the findings in the current study are more satisfactory.
Conclusion: Due to the predictive performance in this study, the MLP model can be recommended to clinicians as a clinical decision support system. Finally, we propose solutions and future research pathways for the various computational materials science challenges for early HD diagnosis.

Anahtar Kelimeler

• heart disease
• multilayer perceptron
• risk factors
• prediction
• clinical decision support system.

Kalp Hastalıklarına İlişkin Risk Faktörlerinin Multilayer Perceptron Modeli ile Tahmini

Öz

Amaç: Kalp hastalıkları (HD); koroner kalp hastalığı, kalp yetmezliği ve kalp krizi gibi birçok hastalığı ifade eder. Amerika Birleşik Devletleri’nde (U.S.) her yıl yaklaşık 647.000 kişi HD’den ölmektedir. HD risk faktörlerini belirlemeye yönelik çok sayıda çalışma neticesinde genetik ve çevresel risk faktörleri tanımlanmıştır.
Materyal ve Metot: Bu çalışmada, her iki cinsiyette de kalp hastalığına bağlı risk faktörlerini tahmin etmek için Multilayer Perceptron (MLP) modeli oluşturulmuştur. İlgili veri seti 270 kişiden, 13 tahmin ediciden ve bir yanıt/hedef değişkeninden oluşmaktadır. Model performansı, genel doğruluk, ROC (Alıcı Çalışma Karakteristikleri) eğrisi (AUC) altındaki alan, duyarlılık ve özgüllük metrikleri kullanılarak değerlendirildi.
Bulgular: Doğruluk, AUC, duyarlılık ve özgüllük için performans metrik değerleri sırasıyla 95% CI, 0.876 (0.79-0.937), 0.935 (0.877-0.992), 0.921 (0.786-0.983) ve 0.843 (0.714-0.93) şeklinde elde edildi. İlgili model bulgularına göre, kan basıncı, floroskopi ile renklendirilen önemli damar sayısı ve kolesterol değişkenleri en önemli üç HD sınıflandırma faktörü olarak görüldü.
Tartışma: Bu çalışmada kullanılan modelin tüm performans ölçütleri dikkate alındığında kabul edilebilir bir tahmin performansı sunduğu söylenebilir. Ayrıca hem veri bilimi hem de istatistiksel açıdan literatürdeki çalışmalarla karşılaştırıldığında, mevcut çalışmadaki bulguların daha tatmin edici olduğu ifade edilebilir.
Sonuç: Bu çalışmadaki öngörücü performans nedeniyle, MLP modeli klinik karar destek sistemi olarak klinisyenlere önerilebilir. Son olarak, erken HD teşhisi için çeşitli hesaba dayalı bilim alanında çözümler ve yeni araştırmalar öneriyoruz.

Anahtar Kelimeler

• Kalp hastalığı
• çok katmanlı algılayıcı
• risk faktörleri
• tahmin
• klinik karar destek sistemi.

Kaynakça

1. Hose DR, Lawford PV, Huberts W, Hellevik LR, Omholt SW, van de Vosse FN. Cardiovascular models for personalised medicine: Where now and where next? Med Eng Phys. 2019;72:38-48. doi:10.1016/j.medengphy.2019.08.007
2. Rasheed J, Hameed AA, Djeddi C, Jamil A, Al-Turjman F. A machine learning-based framework for diagnosis of COVID-19 from chest X-ray images. Interdiscip Sci. 2021;13(1):103-17. doi:10.1007/s12539-020-00403-6
3. Zhang R, Guo Z, Sun Y, Lu Q, Xu Z, Yao Z, et al. COVID19XrayNet: A Two-Step Transfer Learning Model for the COVID-19 Detecting Problem Based on a Limited Number of Chest X-Ray Images. Interdiscip Sci. 2020;12(4):555-65. doi:10.1007/s12539-020-00393-5
4. Yu AZ, Ramsey SA. A Computational Systems Biology Approach for Identifying Candidate Drugs for Repositioning for Cardiovascular Disease. Interdiscip Sci. 2018;10(2):449-54. doi:10.1007/s12539-016-0194-3
5. Gunata M, Parlakpinar H. A review of myocardial ischaemia/reperfusion injury: Pathophysiology, experimental models, biomarkers, genetics and pharmacological treatment. Cell Biochem Funct. 2021;39(2):190-217. doi:10.1002/cbf.3587
6. Wang HD, Naghavi M, Allen C, Barber RM, Bhutta ZA, Carter A, et al. Global, regional, and national life expectancy, all-cause mortality, and cause-specific mortality for 249 causes of death, 1980-2015: a systematic analysis for the Global Burden of Disease Study 2015. Lancet. 2016;388(10053):1459-544. doi:Doi 10.1016/S0140-6736(16)31012-1
7. Mendis S, Puska P, Norrving B, Organization WH. Global atlas on cardiovascular disease prevention and control: World Health Organization; 2011.
8. Benjamin EJ, Muntner P, Alonso A, Bittencourt MS, Callaway CW, Carson AP, et al. Heart Disease and Stroke Statistics-2019 Update: A Report From the American Heart Association. Circulation. 2019;139(10):e56-e528. doi:10.1161/CIR.0000000000000659

9. Fryar CD, Chen T-C, Li X. Prevalence of uncontrolled risk factors for cardiovascular disease: United States, 1999-2010: US Department of Health and Human Services, Centers for Disease Control and …; 2012.
10. Lopez AD, Mathers CD, Ezzati M, Jamison DT, Murray CJ. Global and regional burden of disease and risk factors, 2001: systematic analysis of population health data. Lancet. 2006;367(9524):1747-57. doi:10.1016/S0140-6736(06)68770-9
11. Berry JD, Dyer A, Cai X, Garside DB, Ning H, Thomas A, et al. Lifetime risks of cardiovascular disease. N Engl J Med. 2012;366(4):321-9. doi:10.1056/NEJMoa1012848
12. Webber BJ, Seguin PG, Burnett DG, Clark LL, Otto JL. Prevalence of and risk factors for autopsy-determined atherosclerosis among US service members, 2001-2011. Jama-J Am Med Assoc. 2012;308(24):2577-83. doi:10.1001/jama.2012.70830
13. Koton S, Schneider AL, Rosamond WD, Shahar E, Sang Y, Gottesman RF, et al. Stroke incidence and mortality trends in US communities, 1987 to 2011. Jama-J Am Med Assoc. 2014;312(3):259-68. doi:10.1001/jama.2014.7692
14. George J, Rapsomaniki E, Pujades-Rodriguez M, Shah AD, Denaxas S, Herrett E, et al. How does cardiovascular disease first present in women and men? Incidence of 12 cardiovascular diseases in a contemporary cohort of 1 937 360 people. Circulation. 2015;132(14):1320-8.
15. Ritchey MD, Wall HK, Gillespie C, George MG, Jamal A, Division for Heart D, et al. Million hearts: prevalence of leading cardiovascular disease risk factors--United States, 2005-2012. Mmwr-Morbid Mortal W. 2014;63(21):462-7.
16. Moran AE, Forouzanfar MH, Roth GA, Mensah GA, Ezzati M, Flaxman A, et al. The global burden of ischemic heart disease in 1990 and 2010: the Global Burden of Disease 2010 study. Circulation. 2014;129(14):1493-501. doi:10.1161/CIRCULATIONAHA.113.004046
17. Yusuf S, Hawken S, Ounpuu S, Dans T, Avezum A, Lanas F, et al. Effect of potentially modifiable risk factors associated with myocardial infarction in 52 countries (the INTERHEART study): case-control study. Lancet. 2004;364(9438):937-52. doi:10.1016/S0140-6736(04)17018-9
18. Patel J, Al Rifai M, Scheuner MT, Shea S, Blumenthal RS, Nasir K, et al., editors. Basic vs more complex definitions of family history in the prediction of coronary heart disease: the Multi-Ethnic Study of Atherosclerosis. Mayo Clinic Proceedings; 2018: Elsevier.
19. Paixao AR, Berry JD, Neeland IJ, Ayers CR, Rohatgi A, de Lemos JA, et al. Coronary artery calcification and family history of myocardial infarction in the Dallas heart study. JACC Cardiovasc Imaging. 2014;7(7):679-86. doi:10.1016/j.jcmg.2014.04.004
20. Ranthe MF, Carstensen L, Oyen N, Tfelt-Hansen J, Christiansen M, McKenna WJ, et al. Family history of premature death and risk of early onset cardiovascular disease. J Am Coll Cardiol. 2012;60(9):814-21. doi:10.1016/j.jacc.2012.06.018
21. MacRae CA, Vasan RS. The Future of Genetics and Genomics: Closing the Phenotype Gap in Precision Medicine. Circulation. 2016;133(25):2634-9. doi:10.1161/CIRCULATIONAHA.116.022547
22. Jan M, Ebert BL, Jaiswal S, editors. Clonal hematopoiesis. Seminars in hematology; 2017: Elsevier.
23. Finegold JA, Asaria P, Francis DP. Mortality from ischaemic heart disease by country, region, and age: statistics from World Health Organisation and United Nations. Int J Cardiol. 2013;168(2):934-45. doi:10.1016/j.ijcard.2012.10.046
24. D'Adamo E, Guardamagna O, Chiarelli F, Bartuli A, Liccardo D, Ferrari F, et al. Atherogenic dyslipidemia and cardiovascular risk factors in obese children. Int J Endocrinol. 2015;2015:912047. doi:10.1155/2015/912047
25. Association AH. Understand your risk of heart attack. American Heart Association. 2012.
26. Sullivan MJ, Higginbotham MB, Cobb FR. Exercise training in patients with chronic heart failure delays ventilatory anaerobic threshold and improves submaximal exercise performance. Circulation. 1989;79(2):324-9. doi:10.1161/01.cir.79.2.324
27. Jackson R, ChambIess I, Higgins М, Kuulasmaa К, Wijnberg L, Williams O, et al. Gender differences in ischaemic heart disease mortality and risk factors in 46 communities: аn ecologic analysis. Cardiovascular Risk Factors. 1997(7):43-54.
28. D’agostino RB, Vasan RS, Pencina MJ, Wolf PA, Cobain M, Massaro JM, et al. General cardiovascular risk profile for use in primary care. Circulation. 2008;117(6):743-53.
29. Kappert K, Bohm M, Schmieder R, Schumacher H, Teo K, Yusuf S, et al. Impact of sex on cardiovascular outcome in patients at high cardiovascular risk: analysis of the Telmisartan Randomized Assessment Study in ACE-Intolerant Subjects With Cardiovascular Disease (TRANSCEND) and the Ongoing Telmisartan Alone and in Combination With Ramipril Global End Point Trial (ONTARGET). Circulation. 2012;126(8):934-41. doi:10.1161/CIRCULATIONAHA.111.086660
30. Rapsomaniki E, Timmis A, George J, Pujades-Rodriguez M, Shah AD, Denaxas S, et al. Blood pressure and incidence of twelve cardiovascular diseases: lifetime risks, healthy life-years lost, and age-specific associations in 1.25 million people. Lancet. 2014;383(9932):1899-911. doi:10.1016/S0140-6736(14)60685-1
31. Prescott E, Hippe M, Schnohr P, Hein HO, Vestbo J. Smoking and risk of myocardial infarction in women and men: longitudinal population study. BMJ. 1998;316(7137):1043-7. doi:10.1136/bmj.316.7137.1043
32. Micha R, Michas G, Mozaffarian D. Unprocessed red and processed meats and risk of coronary artery disease and type 2 diabetes--an updated review of the evidence. Curr Atheroscler Rep. 2012;14(6):515-24. doi:10.1007/s11883-012-0282-8
33. Franchini M, Mannucci PM. Air pollution and cardiovascular disease. Thromb Res. 2012;129(3):230-4. doi:10.1016/j.thromres.2011.10.030
34. Sun Q, Hong X, Wold LE. Cardiovascular effects of ambient particulate air pollution exposure. Circulation. 2010;121(25):2755-65. doi:10.1161/CIRCULATIONAHA.109.893461
35. Kalantary S, Pourbabaki R, Jahani A, Yarandi MS, Samiei S, Jahani R. Development of a decision support system tool to predict the pulmonary function using artificial neural network approach. Concurr Comp-Pract E. 2021;33(16):e6258. doi:ARTN e625810.1002/cpe.6258
36. Fajardo JE, Lotto FP, Vericat F, Carlevaro CM, Irastorza RM. Microwave tomography with phaseless data on the calcaneus by means of artificial neural networks. Med Biol Eng Comput. 2020;58(2):433-42. doi:10.1007/s11517-019-02090-y
37. Vivekanandan T, Sriman Narayana Iyengar NC. Optimal feature selection using a modified differential evolution algorithm and its effectiveness for prediction of heart disease. Comput Biol Med. 2017;90:125-36. doi:10.1016/j.compbiomed.2017.09.011
38. Cherian RP, Thomas N, Venkitachalam S. Weight optimized neural network for heart disease prediction using hybrid lion plus particle swarm algorithm. J Biomed Inform. 2020;110:103543. doi:10.1016/j.jbi.2020.103543
39. Ledolter J. Data mining and business analytics with R: John Wiley & Sons; 2013.