Prototyping neural networks to evaluate the risk of adverse cardiovascular outcomes in the population

Aim. To develop a neural network basis for the design of artificial intelligence software to predict adverse cardiovascular outcomes in the population.

Materials and Methods. Neural networks were designed using the database of 1,525 participants of PURE (Prospective Urban Rural Epidemiology Study), an international, multi-center, prospective study investigating disease risk factors in the urban and rural areas. As this study is still ongoing, we analysed only baseline data, therefore switching prognosis and diagnosis task. Because of its leading prevalence among other cardiovascular diseases, arterial hypertension was selected as an adverse outcome. Neural networks were designed employing STATISTICA Automated Neural Networks (SANN) software, manually selected, cross-validated, and transferred to the original graphical user interface software.

Results. Input risk factors were gender, age, place of residence, concomitant diseases (i.e., coronary artery disease, chronic heart failure, diabetes mellitus, chronic obstructive pulmonary disease, and asthma), active or passive smoking, regular use of medications, family history of arterial hypertension, coronary artery disease or stroke, heart rate, body mass index, fasting blood glucose and cholesterol, high- and low-density lipoprotein cholesterol, and serum creatinine levels. Our neural networks showed a moderate efficacy in the virtual diagnostics of arterial hypertension (84.5%, or 1,289 successfully predicted outcomes out of 1,525, area under the ROC curve = 0.88), with almost equal sensitivity (83.6%) and specificity (85.3%), and were successfully integrated into graphical user interface that is necessary for the development of the commercial prognostication software. Cross-validation of this neural network on bootstrapped samples of virtual patients demonstrated sensitivity of 82.7 – 84.7%, specificity of 84.5 – 87.3%, and area under the ROC curve of 0.88 – 0.89.

Conclusion. The artificial intelligence prognostication software to predict adverse cardiovascular outcomes in the population can be developed by a combination of automated neural network generation and analysis followed by manual selection, cross-validation, and integration into graphical user interface.

1. Shalnova SA, Ezhov MV, Metelskaya VA, Evstifeeva SE, Tarasov VI, Muromtseva GA, Balanova YuA, Imaeva AE, Kapustina AV, Shabunova AA, Belova OA, Trubacheva IA, Efanov AY, Astakhova ZT, Kulakova NV, Boytsov SA, Drapkina OM. Association Between Lipoprotein( a) and Risk Factors of Atherosclerosis in Russian Population (Data of Observational ESSE-RF study). Rational Pharmacotherapy in Cardiology. 2019;15(5):612-621. (In Russ.) https://doi.org/10.20996/1819-6446-2019-15-5-612-621

2. Boytsov SA, Shalnova SA, Deev AD. The epidemiological situation as a factor determining the strategy for reducing mortality in the Russian Federation. Therapeutic archive. 2020;92(1):4-9. (In Russ.) https://doi.org/10.26442/00403660.2020.01.000510

3. Muromtseva GA, Kontsevaya AV, Konstantinov VV, Artamonova GV, Gatagonova TM, Duplyakov DV, Efanov AYu, Zhernakova YuV, Il’in VA, Konradi AO, Libis RA, Minakov EV, Nedogoda SV, Oschepkova EV, Romanchuk SV, Rotar OP, Trubacheva IA, Deev AD, Shalnova SA, Chazova IE, Shlyakhto EV, Boytsov SA, Balanova YuA, Gomyranova NV, Evstifeeva SE, Kapustina AV, Litinskaya OA, Mamedov MN, Metelskaya VA, Oganov RG, Suvorova EI, Khudyakov MB, Baranova EI, Kasimov RA, Shabunova AA, Ledyaeva AA, Chumachek EV, Azarin OG, Babenko NI, Bondartsov LV, Furmenko GI, Khvostikova AE, Belova OA, Nazarova OA, Shutemova EA, Barbarash OL, Danilchenko YV, Indukaeva EV, Maksimov SA, Mulerova TA, Skripchenko AE, Cherkass NV, Basyrova IR, Isaeva EN, Kondratenko VYu, Lopina EA, Safonova DV, Gudkova SA, Cherepanova NA, Kaveshnikov VS, Karpov RS, Serebryakova VN, Medvedeva IV, Storozhok MA, Shava VP, Shalaev SV, Gutnova SK, Tolparov GV. the prevalence of non-infectious diseases risk factors in russian population in 2012-2013 years. The results of ECVD-RF. Cardiovascular Therapy and Prevention. 2014;13(6):4-11. (In Russ.) https://doi.org/10.15829/1728-8800-2014-6-4-11

4. Maksimov S, Artamonova G. Risks of arterial hypertension depending on occupational factors. Arterial hypertension 2017 as an interdisciplinary problem. Collection of theses of the XIII All-Russian Congress. 2017:10-11. (In Russ.).

5. Maximov SA, Skripnichenko AE, Ndukaeva EV, Artamonova GV. Factors in the system of prognostication of arterial hypertension. Kardiologiia. 2014;54(1):61-63. (In Russ). https://doi.org/10.18565/cardio.2014.1.61-62

6. Barbarash OL, Karetnikova VN, Kochergina AM, Indukaeva EV, Artamonova GV. Cardiovascular risk factors and its association with target blood pressure level inreachment in patients with arterial hypertension in Kemerovo. Medicine in Kuzbass. 2016;15(1):47-53. (In Russ).

7. Karunathilake SP, Ganegoda GU. Secondary Prevention of Cardiovascular Diseases and Application of Technology for Early Diagnosis. Biomed Res Int. 2018; 2018: 5767864. https://doi.org/10.1155/2018/5767864

8. Kilic A. Artificial Intelligence and Machine Learning in Cardiovascular Health Care. Ann Thorac Surg. 2020;109(5):1323-1329. https://doi.org/10.1016/j.athoracsur.2019.09.042

9. Ambale-Venkatesh B, Yang X, Wu CO, Liu K, Hundley WG, McClelland R, Gomes AS, Folsom AR, Shea S, Guallar E, Bluemke DA, Lima JAC. Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circ Res. 2017;121(9):1092-1101. https://doi.org/10.1161/CIRCRESAHA.117.311312

10. Hessler G, Baringhaus KH. Artificial Intelligence in Drug Design. Molecules. 2018;23(10):2520. https://doi.org/10.3390/molecules23102520

11. Miller DD, Brown EW. Artificial Intelligence in Medical Practice: The Question to the Answer? Am J Med. 2018;131(2):129-133. https://doi.org/10.1016/j.amjmed.2017.10.035

12. Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol. 2019;28(2):73-81. https://doi.org/10.1080/13645706.2019.1575882

13. Lim LJ, Tison GH, Delling FN. Artificial Intelligence in Cardiovascular Imaging. Methodist Debakey Cardiovasc J. 2020;16(2):138-145. https://doi.org/10.14797/mdcj-16-2-138

14. Darcy AM, Louie AK, Roberts LW. Machine Learning and the Profession of Medicine. JAMA. 2016;315(6):551-552. https://doi.org/10.1001/jama.2015.18421

15. Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M, Ashley E, Dudley JT. Artificial Intelligence in Cardiology. J Am Coll Cardiol. 2018;71(23):2668-2679. https://doi.org/10.1016/j.jacc.2018.03.521

16. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115-118. https://doi.org/10.1038/nature21056

17. Yu L, Chen H, Dou Q, Qin J, Heng PA. Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks. IEEE Trans Med Imaging. 2017;36(4):994-1004. https://doi.org/10.1109/TMI.2016.2642839.

18. Shimizu H, Nakayama KI. Artificial intelligence in oncology. Cancer Sci. 2020;111(5):1452-1460. https://doi.org/10.1111/cas.14377