Immunophenotyping of circulating leukocytes as a tool to optimize diagnosis of carotid atherosclerosis using machine learning approach

The aim of the present study was to investigate the possibility of using immunophenotyping of circulating lymphocytes, neutrophils and monocytes to diagnose prognostically unfavorable carotid atherosclerosis using machine learning algorithms.

Material and methods. A sample of patients aged 40 to 64 years, who underwent duplex scanning of the carotid arteries and the lower limb arteries, served as a source of patients for analysis. Phenotyping and differentiation of subpopulations of lymphocytes, neutrophils, and monocytes were performed by flow cytometry using the “Navios 6/2” device (Beckman Coulter, USA) device. Data were statistically processed using software package SPSS 23 and our own software programs created using main libraries of Python 3.8 programming language (Scikit-learn, Pandas, Numpy, Scipy) and IDE Spyder.

Results. Seventy-eight patients, 39 (50.0 %) males and 39 (50.0 %) females, median age 50.0 years, were included in the study. Age over 56 (р = 0,001), elevated low density lipoprotein (LDL) cholesterol (р < 0.001) and uric acid (р = 0.001), as well as immunosuppressive neutrophils level (р = 0.005) were statistically significantly associated with the development of carotid plaque. At the same time, decreased cell populations of proangiogenic neutrophils (р = 0.009), classical monocytes expressing CD36 (р = 0.019), nonclassical monocytes (р = 0.021), intermediate monocytes expressing TLR4 (р = 0.033), and classical monocytes expressing TLR2 (р = 0.044) were statistically significantly associated with an increased chance of carotid plaque. Taking into account the selected parameters, two prognostic models were created. The first model included basic clinical and laboratory parameters (age, LDL cholesterol and uric acid), and the second model included all selected parameters as well as immunological parameters. Inclusion of the identified immunological predictors in the model resulted in a significant increase in all standard quality metrics of the binary classification. Model accuracy increased by 13 % (р = 0.014), sensitivity by 20 % (р = 0.003), specificity by 6 % (р = 0.046), predictive value of a positive result by 9 % (р = 0.037), predictive value of a negative result by 16 % (р = 0.011). According to the ROC analysis, without the inclusion of immunological predictors in the model, the area under the ROC curve (AUC) was 0.765 [0.682; 0.848], the inclusion of immunological predictors resulted in a statistically significant increase in AUC (0.906 [0.854; 0.958], р = 0.041).

Conclusions. In patients 40–64 years old without established atherosclerotic cardiovascular disease, inclusion of immunological markers derived from leukocyte immunophenotyping in the model allowed increasing its diagnostic efficacy with regard to the detection of prognostically unfavorable carotid atherosclerosis. Subpopulations of monocytes expressing TLR2, TLR4, and CD36, as well as immunosuppressive and proangiogenic neutrophils, demonstrated diagnostic value.

1. Circulation, 2021; 143 (8): e254– e743. doi: 10.1161/CIR.0000000000000950

2. Wu W.Y., Berman A.N., Biery D.W., Blankstein R. Recent trends in acute myocardial infarction among the young. Curr. Opin. Cardiol., 2020; 35 (5): 524– 530. doi: 10.1097/HCO.0000000000000781

3. Garg N., Muduli S.K., Kapoor A., Tewari S., Kumar S., Khanna R., Goel P.K. Comparison of different cardiovascular risk score calculators for cardiovascular risk prediction and guideline recommended statin uses. Indian Heart J., 2017; 69 (4): 458–463. doi: 10.1016/j.ihj.2017.01.015

4. Martins A.M.A., Paiva M.U.B., Paiva D.V.N., de Oliveira R.M., Machado H.L., Alves L.J.S.R., Picossi C.R.C., Faccio A.T., Tavares M.F.M., Barbas C., Giraldez V.Z.R., Santos R.D., Monte G.U., Atik F.A. Innovative Approaches to Assess Intermediate Cardiovascular Risk Subjects: A Review From Clinical to Metabolomics Strategies. Front. Cardiovasc. Med., 2021; 8: 788062. doi: 10.3389/fcvm.2021.788062

5. Klesareva E.A., Afanasieva O.I., Sherstyuk E.E., Tmoyan N.A., Razova O.A., Tyurina A.V., Afanasieva M.I., Ezhov M.V., Pokrovsky S.N. The relationship between the level of Lр(а) and the prevalence of atherosclerosis among young patients. Terapevticheskiy arkhiv (Ter. arkh.), 2022; 94 (4): 479–484. (In Russ.) 10.26442/00403660.2022.04.201454

6. Hoogeveen R.M., Pereira J.P.B., Nurmohamed N.S., Zampoleri V., Bom M.J., Baragetti A., Boekholdt S.M., Knaapen P., Khaw K.T., Wareham N.J., Groen A.K., Catapano A.L., Koenig W., Levin E., Stroes E.S.G. Improved cardiovascular risk prediction using targeted plasma proteomics in primary prevention. Eur. Heart. J., 2020; 41 (41): 3998–4007. doi: 10.1093/eurheartj/ehaa648

7. Vaes B., Indestege P., Serneels T., Hegendörfer E., van Peet P.G., Poortvliet R.K.E., Wallemacq P., Gussekloo J., Degryse J. Biomarkers versus traditional risk factors to predict cardiovascular events in very old adults: cross-validated prospective cohort study. BMJ Open, 2020; 10 (6): e035809. doi: 10.1136/bmjopen-2019-035809

8. Kurilova O.V., Kiseleva A.V., Meshkov A.N., Sotnikova E.A., Ershova A.I., Ivanova A.A., Limonova A.S., Drapkina O.M. Scales for assessing the genetic risk of developing type 2 diabetes mellitus. Profilakticheskaya meditsina. 2021; 24 (12): 115–122. (In Russ.) doi: 10.17116/profmed202124121115

9. Libby P. Inflammation in atherosclerosis – no longer a theory. Clin. Chem., 2021; 67 (1): 131–142. doi: 10.1093/clinchem/hvaa275

10. Reddy A.S., Uceda D.E., Al Najafi M., Dey A.K., Mehta N.N. PET Scan with Fludeoxyglucose/Computed Tomography in Low-Grade Vascular Inflammation. PET Clin., 2020; 15 (2): 207–213. doi: 10.1016/j.cpet.2019.11.009

11. Hong L.Z., Xue Q., Shao H. Inflammatory Markers Related to Innate and Adaptive Immunity in Atherosclerosis: Implications for Disease Prediction and Prospective Therapeutics. J. Inflamm. Res., 2021; 14: 379–392. doi: 10.2147/JIR.S294809

12. Björkegren J.L.M., Lusis A.J. Atherosclerosis: Recent developments. Cell., 2022; 185 (10): 1630–1645. doi: 10.1016/j.cell.2022.04.004

13. Li H., Zhang P., Yuan S., Tian H., Tian D., Liu M. Modeling analysis of the relationship between atherosclerosis and related inflammatory factors. Saudi J. Biol. Sci., 2017; 24 (8): 1803–1809. doi: 10.1016/j.sjbs.2017.11.016

14. Wainstein M.V., Mossmann M., Araujo G.N., Gonçalves S.C., Gravina G.L., Sangalli M., Veadrigo F., Matte R., Reich R., Costa F.G., Andrades M., da Silva A.M.V., Bertoluci M.C. Elevated serum interleukin-6 is predictive of coronary artery disease in intermediate risk overweight patients referred for coronary angiography. Diabetol. Metab. Syndr., 2017; 9: 67. doi: 10.1186/s13098-017-0266-5

15. Stakhneva E.M., Ragino Yu.I. Modern methods for studying atherosclerosis and coronary artery disease: flow cytometry. Bulletin of Siberian Medicine. 2021; 20 (2): 184–190. (In Russ.) doi: 10.20538/1682-0363-2021-2184-190

16. Baumer Y., Gutierrez-Huerta C.A., Saxena A., Dagur P.K., Langerman S.D., Tamura K., Ceasar J.N., Andrews M.R., Mitchell V., Collins B.S., Yu Q., Teague H.L., Playford M.P., Bleck C.K.E., Mehta N.N., McCoy J.P., Powell-Wiley T.M. Immune cell phenotyping in low blood volumes for assessment of cardiovascular disease risk, development, and progression: a pilot study. J. Transl Med., 2020; 18 (1): 29. doi: 10.1186/s12967-020-02207-0

17. Kaledina E.A., Kaledin O.E., Kulyagina T.I. Applying machine learning for prediction of cardiovascular diseases on small data sets. Problems of Informatics, 2022; 1 (54): 66–75. (In Russ.) doi: 10.24412/2073-0667-2022-1-66-76

18. Sánchez-Cabo F., Rossello X., Fuster V., Benito F., Manzano J.P., Silla J.C., Fernández-Alvira J.M., Oliva B., Fernández-Friera L., López-Melgar B., Mendiguren J.M., Sanz J., Ordovás J.M., Andrés V., Fernández-Ortiz A., Bueno H., Ibáñez B., GarcíaRuiz J.M., Lara-Pezzi E. Machine Learning Improves Cardiovascular Risk Definition for Young, Asymptomatic Individuals. J. Am Coll. Cardiol., 2020; 76 (14): 1674–1685. doi: 10.1016/j.jacc.2020.08.017

19. Genkel V.V., Kuznetsova A.S., Lebedev E.V., Shaposhnik I.I. Factors associated with the presence of prognostically unfavorable carotid atherosclerosis in men and women over age 40. Atherosclerosis and Dyslipidemia, 2021; 4 (45): 33–40. (In Russ.) doi: 10.34687/2219-8202.JAD.2021.04.0004

20. Johri A.M., Nambi V., Naqvi T.Z., Feinstein S.B., Kim E.S.H., Park M.M., Becher H., Sillesen H. Recommendations for the Assessment of Carotid Arterial Plaque by Ultrasound for the Characterization of Atherosclerosis and Evaluation of Cardiovascular Risk: From the American Society of Echocardiography. J. Am Soc. Echocardiogr., 2020; 33 (8): 917–933. doi: 10.1016/j.echo.2020.04.021

21. Vassalle C. New biomarkers and traditional cardiovascular risk scores: any crystal ball for current effective advice and future exact prediction? Clin. Chem. Lab. Med., 2018; 56 (11): 1803–1805. doi: 10.1515/cclm2018-0490

22. Stakhneva E.M., Striukova E.V., Ragino Y.I. Proteomic Studies of Blood and Vascular Wall in Atherosclerosis. Int. J. Mol. Sci., 2021; 22 (24): 13267. doi: 10.3390/ijms222413267

23. Bargieł W., Cierpiszewska K., Maruszczak K., Pakuła A., Szwankowska D., Wrzesińska A., Gutowski Ł., Formanowicz D. Recognized and Potentially New Biomarkers-Their Role in Diagnosis and Prognosis of Cardiovascular Disease. Medicina (Kaunas), 2021; 57 (7): 701. doi: 10.3390/medicina57070701

24. Fani L., van der Willik K.D., Bos D., Leening M.J.G., Koudstaal P.J., Rizopoulos D., Ruiter R., Stricker B.H.C., Kavousi M., Ikram M.A., Ikram M.K. The association of innate and adaptive immunity, subclinical atherosclerosis, and cardiovascular disease in the Rotterdam Study: A prospective cohort study. PLoS Med., 2020; 17 (5): e1003115. doi: 10.1371/journal.pmed.1003115

25. Hong L.Z., Xue Q., Shao H. Inflammatory Markers Related to Innate and Adaptive Immunity in Atherosclerosis: Implications for Disease Prediction and Prospective Therapeutics. J. Inflamm. Res., 2021; 14: 379–392. doi: 10.2147/JIR.S294809

26. Feinstein M.J., Buzkova P., Olson N.C., Doyle M.F., Sitlani C.M., Fohner A.E., Huber S.A., Floyd J., Sinha A., Thorp E.B., Landay A., Freiberg M.S., Longstreth W.T.Jr., Tracy R.P., Psaty B.M., Delaney J.A. Monocyte subsets, T cell activation profiles, and stroke in men and women: The Multi-Ethnic Study of Atherosclerosis and Cardiovascular Health Study. Atherosclerosis, 2022; 351: 18–25. doi: 10.1016/j.atherosclerosis.2022.05.007

27. Genkel V., Dolgushin I., Baturina I., Savochkina A., Nikushkina K., Minasova A., Kuznetsova A., Shaposhnik I. Associations between Circulating VEGFR2hiNeutrophils and Carotid Plaque Burden in Patients Aged 40-64 without Established Atherosclerotic Cardiovascular Disease. J. Immunol. Res., 2022; 2022: 1539935. doi: 10.1155/2022/1539935

28. Dolgushi I.I., Genkel V.V., Baturina I.L., Savochkina A.Yu., Minasova A.A., Nikushkina K.V., Pykhova L.R., Kuznetsova A.S., Shaposhnik I.I. Interactions between immunosuppressor neutrophiles, innate and adaptive immunity indexes in the patients with subclinical atherosclerosis. Medical Immunology (Russia), 2022; 24 (2): 283–294. (In Russ.) doi: 10.15789/1563-0625-IBI-2463

29. Gupta S., Maratha A., Siednienko J., Natarajan A., Gajanayake T., Hoashi S., Miggin S. Analysis of in flammatory cytokine and TLR expression levels in Type 2 Diabetes with complications. Sci. Rep., 2017; 7 (1): 7633. doi: 10.1038/s41598-017-07230-8

30. Sadeghi K., Wisgrill L., Wessely I., Diesner S.C., Schüller S., Dürr C., Heinle A., Sachet M., Pollak A., Förster-Waldl E., Spittler A. GM-CSF Down-Regulates TLR Expression via the Transcription Factor PU.1 in Human Monocytes. PLoS One., 2016; 11 (10): e0162667. doi: 10.1371/journal.pone. 0162667

31. Zamora C., Cantó E., Nieto J.C., Angels Ortiz M., Juarez C., Vidal S. Functional consequences of CD36 downregulation by TLR signals. Cytokine, 2012; 60 (1): 257–265. doi: 10.1016/j.cyto.2012.06.020

32. Gazatova N.D., Meniailo M.E., Malashchenko V.V., Goncharov A.G., Melashchenko O.B., Morozova E.M., Seledtsov V.I. Direct effects of gm-csf on the functions of human monocytes/macrophages. Medical Immunology (Russia), 2019; 21 (3): 419–426. (In Russ.) doi: 10.15789/1563-0625-2019-3-419-426

33. Boyer J.F., Balard P., Authier H., Faucon B., Bernad J., Mazières B., Davignon J.L., Cantagrel A., Pipy B., Constantin A. Tumor necrosis factor alpha and adalimumab differentially regulate CD36 expression in human monocytes. Arthritis Res. Ther., 2007; 9 (2): R22. doi: 10.1186/ar2133

34. Herrero-Cervera A., Soehnlein O., Kenne E. Neutrophils in chronic inflammatory diseases. Cell. Mol. Immunol., 2022; 19 (2): 177–191. doi: 10.1038/s41423-021-00832-3

35. Qi X., Yu Y., Sun R., Huang J., Liu L., Yang Y., Rui T., Sun B. Identification and characterization of neutrophil heterogeneity in sepsis. Crit. Care., 2021; 25 (1): 50. doi: 10.1186/s13054-021-03481-0

36. Filep J.G. Targeting Neutrophils for Promoting the Resolution of Inflammation. Front. Immunol., 2022; 13: 866747. doi: 10.3389/fimmu.2022.866747

37. Salminen A. Increased immunosuppression impairs tissue homeostasis with aging and age-related diseases. J. Mol. Med. (Berl.), 2021; 99 (1): 1–20. doi: 10.1007/s00109-020-01988-7

38. Williams M.C., Newby D.E. Machine learning to predict cardiac events in asymptomatic individuals. Atherosclerosis, 2021; 318: 38–39. doi: 10.1016/j.atherosclerosis.2020.12.006