STM Journals Peer-reviewed research from Consortium e-Learning Network

Research and Reviews: A Journal of Health Professions Review Article

Development of a Machine Learning and Artificial Intelligence Based Model Aimed at Forecasting the Prognostic Impact of C-Reactive Protein in Myocarditis

  1. Indra Singh Department of AI & ML and data Science, Moddlakatte Institute of Technology, Kundapura
  2. Abdul Kareem Department of AI & ML and data Science, Moddlakatte Institute of Technology, Kundapura

Abstract

The specific role of inflammation markers in myocarditis remains uncertain. We investigated the diagnostic and prognostic significance of C-reactive protein (CRP) levels at the initial diagnosis among myocarditis patients. Our retrospective study enrolled patients clinically suspected (CS) or biopsy-proven (BP) with myocarditis, with available CRP data at diagnosis. We collected patient information, including clinical, laboratory, and imaging findings at diagnosis and follow-up visits. We utilized machine learning methods, specifically random forest for survival data analysis, to identify factors predicting death or the need for a heart transplant (Htx). Our cohort included 409 patients, predominantly male (74%), with an average age of 37 ± 15 years and a median follow-up period of 2.9 years. Elevated CRP levels were observed in 288 patients, particularly in those with CS myocarditis (p < 0.001), recent viral infections, shorter symptom duration (p = 0.001), chest pain (p < 0.001), better functional status at diagnosis (p = 0.018), and higher troponin I levels (p < 0.001). Among the 13 patients experiencing death or requiring heart transplant, 10 had BP myocarditis, yielding an overall 10-year survival rate of 94%. However, survival rates did not significantly differ based on CRP levels (p = 0.23). The most robust predictors of survival were left ventricular ejection fraction (LVEF), presence of anti-nuclear autoantibodies (ANA), and biopsy-confirmed myocarditis. In conclusion, elevated CRP levels at diagnosis may suggest CS myocarditis and milder clinical manifestations but do not significantly contribute to predicting long-term survival. Primary predictors of adverse outcomes include reduced LVEF, biopsy-proven diagnosis, and the presence of ANA.

Keywords

References (61)

  1. Aha, D. W., Kibler, D., and Albert, M. K. (1991). Instance-based learning algorithms. Machine learn-ing, 6(1):37–66.
  2. Anagnostis, P., Stevenson, J. C., Crook, D., Johnston, D. G.,and Godsland, I. F. (2015). Effects of menopause, gender and age on lipids and high-density lipoprotein cholesterol subfractions. Maturitas, 81(1):62–68. Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.
  3. Chen, S., Bergman, D., Miller, K., Kavanagh, A., Frown-felter, J., and Showalter, J. (2020). Using applied machine learning to predict healthcare utilization based on socioeconomic determinants of care. Am J Manag Care, 26(01):26–31.
  4. Colak C, Colak MC, Ermis N, Erdil N, Ozdemir R. Prediction of cholesterol level in patients with myocardial infarction based on medical data mining methods. Kuwait Journal of Science. 2016 Aug 8;43(3).
  5. Cortes, C. and Vapnik, V. (1995). Support-vector networks.Machine learning, 20(3):273–297.
  6. Crouse SF, O'Brien BC, Rohack JJ, Lowe RC, Green JS, Tolson HO, Reed JL. Changes in serum lipids and apolipoproteins after exercise in men with high cholesterol: influence of intensity. Journal of Applied Physiology. 1995 Jul 1;79(1):279-86.
  7. Indra VS, Maninder SS, BageSree S, Revathi R. Assessment of Output Radiation Density of Cell Phone for Epidemiological Studies: A Pilot Study in Navi Mumbai. JOURNAL OF ENVIRONMENTAL INFORMATICS LETTERS. 2024 Apr 10;11(1):21-8.
  8. Indra Vijay Singh and M.S Setia, Investigation of Power Density of Emerging Cellular Towers against the Distance and Frequency-A Case Study,. Scopus Index, IOS Press IOS Press, NieuweHemweg, 61013 BG Amsterdam, the Netherlands, ISSN online 2352-7528, Jan-2023.
  9. Singh IV, Alam MS. Inter-modulation linearity investigation of an optimally designed and optimally biased LNA for wireless LAN. Radioelectronics and Communications Systems. 2015 May;58:191-200.
  10. Avan A, Tavakoly Sany SB, Ghayour‐Mobarhan M, Rahimi HR, Tajfard M, Ferns G. Serum C‐reactive protein in the prediction of cardiovascular diseases: Overview of the latest clinical studies and public health practice. Journal of cellular physiology. 2018 Nov;233(11):8508-25.
  11. Boncler M, Wu Y, Watala C. The multiple faces of C-reactive protein—physiological and pathophysiological implications in cardiovascular disease. Molecules. 2019 May 30;24(11):2062.
  12. Osman R, L'Allier PL, Elgharib N, Tardif JC. Critical appraisal of C-reactive protein throughout the spectrum of cardiovascular disease. Vascular Health and Risk Management. 2006;2(3):221-237. doi:10.2147/vhrm.2006.2.3.221
  13. Schwuchow-Thonke S, Göbel S, Emrich T, Schmitt VH, Fueting F, Klank C, et al. Increased C reactive protein, cardiac troponin I and GLS are associated with myocardial inflammation in patients with non-ischemic heart failure. Scientific Reports. 2021;11(1). doi:10.1038/s41598-021-82592-8
  14. Kim JT, Cho S, Lee SY, Kim D, Lim SH, Kang TS, et al. THE USE OF MACHINE LEARNING ALGORITHMS FOR THE IDENTIFICATION OF STABLE OBSTRUCTIVE CORONARY ARTERY DISEASE. Journal of the American College of Cardiology. 2020;75(11):254. doi:10.1016/s0735-1097(20)30881-0
  15. Nakanishi R, Dey D, Commandeur F, Slomka P, Betancur J, Gransar H, et al. MACHINE LEARNING IN PREDICTING CORONARY HEART DISEASE AND CARDIOVASCULAR DISEASE EVENTS: RESULTS FROM THE MULTI-ETHNIC STUDY OF ATHEROSCLEROSIS (MESA). Journal of the American College of Cardiology. 2018;71(11):A1483. doi:10.1016/s0735-1097(18)32024-2
  16. Ambale-Venkatesh B, Yang X, Wu CO, Liu K, Hundley WG, McClelland R, et al. Cardiovascular Event Prediction by Machine Learning. Circulation Research. 2017;121(9):1092-1101. doi:10.1161/circresaha.117.311312
  17. Sampedro-Gómez J, Dorado-Díaz PI, Vicente-Palacios V, Sánchez-Puente A, Jiménez-Navarro M, San Roman JA, et al. Machine Learning to Predict Stent Restenosis Based on Daily Demographic, Clinical, and Angiographic Characteristics. Canadian Journal of Cardiology. 2020;36(10):1624-1632. doi:10.1016/j.cjca.2020.01.027
  18. Dong P, Ye G, Kaya M, Gu L. Simulation-Driven Machine Learning for Predicting Stent Expansion in Calcified Coronary Artery. Applied Sciences. 2020;10(17):5820. doi:10.3390/app10175820
  19. Caforio ALP, Baritussio A, Marcolongo R, Cheng CY, Pontara E, Bison E, et al. Serum Anti-Heart and Anti-Intercalated Disk Autoantibodies: Novel Autoimmune Markers in Cardiac Sarcoidosis. Journal of Clinical Medicine. 2021;10(11):2476. doi:10.3390/jcm10112476
  20. Seferović PM, Tsutsui H, McNamara DM, Ristić AD, Basso C, Bozkurt B, et al. Heart Failure Association of the ESC, Heart Failure Society of America and Japanese Heart Failure Society Position statement on endomyocardial biopsy. European Journal of Heart Failure. 2021;23(6):854-871. doi:10.1002/ejhf.2190
  21. Breiman L. Random Forest. Learn. 2001;45:5–32. doi:10.1023/A:1010933404324. [CrossRef] [Google Scholar]
  22. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. The Annals of Applied Statistics. 2008;2(3). doi:10.1214/08-aoas169
  23. Ishwaran H, Kogalur UB, Gorodeski EZ, Minn AJ, Lauer MS. High-Dimensional Variable Selection for Survival Data. Journal of the American Statistical Association. 2010;105(489):205-217. doi:10.1198/jasa.2009.tm08622
  24. Harrell F.E., Jr., Lee K.L., Mark D.B. Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Med. 1996;15:361–387. doi:10.1002/(SICI)1097-0258(19960229)15:43.0.CO;2-4. [PubMed] [CrossRef] [Google Scholar]
  25. Shaikhina T, Lowe D, Daga S, Briggs D, Higgins R, Khovanova N. Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation. Biomedical Signal Processing and Control. 2019;52:456-462. doi:10.1016/j.bspc.2017.01.012
  26. R Development Core Team . 0.1. A Language and Environment for Statistical Computing. Volume 2. R Foundation for Statistical Computing; Vienna, Austria: 2019. [(accessed on 1 June 2020)]. Available online: http://www.R-project.org [Google Scholar]
  27. Harrell F.E., Jr. Package ‘rms’: Regression Modeling Strategies. R Foundation for Statistical Computing; Vienna, Austria: 2019. [(accessed on 1 June 2020)]. pp. 1–246. Available online: https://cran.rorg/web/packages/rms/rms.pdf [Google Scholar]
  28. Therneau T., Grambsch P. Modeling Survival Data: Extending the Cox Model. Springer; New York, NY, USA: 2000. [Google Scholar]
  29. Alboukadel K., Marcin K., Przemyslaw B., Scheipl F. Drawing Survival Curves Using ‘ggplot2’ [R package Survminer Version 0.4.3] R Foundation for Statistical Computing; Vienna, Austria: 2018. R Package Version 0.4.3. [Google Scholar]
  30. Harrell F.E., Jr., Lee K.L., Matchar D.B., Reichert T.A. Regression models for prognostic prediction: Advantages, problems, and suggested solutions. Cancer Treat. Rep. 1985;69:1071– 1077. [PubMed] [Google Scholar]
  31. Peduzzi P, Concato J, Feinstein AR, Holford TR. Importance of events per independent variable in proportional hazards regression analysis II. Accuracy and precision of regression estimates. Journal of Clinical Epidemiology. 1995;48(12):1503-1510. doi:10.1016/0895-4356(95)00048-8
  32. Concato J, Peduzzi P, Holford TR, Feinstein AR. Importance of events per independent variable in proportional hazards analysis I. Background, goals, and general strategy. Journal of Clinical Epidemiology. 1995;48(12):1495-1501. doi:10.1016/0895-4356(95)00510-2
  33. Ogundimu EO, Altman DG, Collins GS. Adequate sample size for developing prediction models is not simply related to events per variable. Journal of Clinical Epidemiology. 2016;76:175-182. doi:10.1016/j.jclinepi.2016.02.031
  34. Salkind N.J. Encyclopedia of Research Design. Volume 1 SAGE; Newbury Park, CA, USA: 2010. [Google Scholar]
  35. Steele AJ, Denaxas SC, Shah AD, Hemingway H, Luscombe NM. Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease. PLOS ONE. 2018;13(8):e0202344. doi:10.1371/journal.pone.0202344
  36. Ammirati E, Cipriani M, Moro C, Raineri C, Pini D, Sormani P, et al. Clinical Presentation and Outcome in a Contemporary Cohort of Patients With Acute Myocarditis. Circulation. 2018;138(11):1088-1099. doi:10.1161/circulationaha.118.035319
  37. Verdonschot JAJ, Merlo M, Dominguez F, Wang P, Henkens MTHM, Adriaens ME, et al. Phenotypic clustering of dilated cardiomyopathy patients highlights important pathophysiological differences. European Heart Journal. 2020;42(2):162-174. doi:10.1093/eurheartj/ehaa841
  38. Caforio ALP, De Luca G, Baritussio A, Seguso M, Gallo N, Bison E, et al. Serum Organ-Specific Anti-Heart and Anti-Intercalated Disk Autoantibodies as New Autoimmune Markers of Cardiac Involvement in Systemic Sclerosis: Frequency, Clinical and Prognostic Correlates. Diagnostics. 2021;11(11):2165. doi:10.3390/diagnostics11112165
  39. Baritussio A, Schiavo A, Basso C, Giordani AS, Cheng CY, Pontara E, et al. Predictors of relapse, death or heart transplantation in myocarditis before the introduction of immunosuppression: negative prognostic impact of female gender, fulminant onset, lower ejection fraction and serum autoantibodies. European Journal of Heart Failure. 2022;24(6):1033-1044. doi:10.1002/ejhf.2496
  40. Abbate A, Toldo S, Marchetti C, Kron J, Van Tassell BW, Dinarello CA. Interleukin-1 and the Inflammasome as Therapeutic Targets in Cardiovascular Disease. Circulation Research. 2020;126(9):1260-1280. doi:10.1161/circresaha.120.315937
  41. Ridker PM, Everett BM, Thuren T, MacFadyen JG, Chang WH, Ballantyne C, et al. Antiinflammatory Therapy with Canakinumab for Atherosclerotic Disease. New England Journal of Medicine. 2017;377(12):1119-1131. doi:10.1056/nejmoa1707914
  42. Abbate A, Van Tassell BW, Biondi-Zoccai G, Kontos MC, Grizzard JD, Spillman DW, et al. Effects of Interleukin-1 Blockade With Anakinra on Adverse Cardiac Remodeling and Heart Failure After Acute Myocardial Infarction [from the Virginia Commonwealth University-Anakinra Remodeling Trial (2) (VCU-ART2) Pilot Study]. The American Journal of Cardiology. 2013;111(10):1394-1400. doi:10.1016/j.amjcard.2013.01.287
  43. Buckley LF, Viscusi MM, Van Tassell BW, Abbate A. Interleukin-1 blockade for the treatment of pericarditis. European Heart Journal - Cardiovascular Pharmacotherapy. 2017;4(1):46-53. doi:10.1093/ehjcvp/pvx018
  44. Brucato A, Imazio M, Gattorno M, Lazaros G, Maestroni S, Carraro M, et al. Effect of Anakinra on Recurrent Pericarditis Among Patients With Colchicine Resistance and Corticosteroid Dependence. JAMA. 2016;316(18):1906. doi:10.1001/jama.2016.15826
  45. Blanco-Domínguez R, Sánchez-Díaz R, de la Fuente H, Jiménez-Borreguero LJ, Matesanz-Marín A, Relaño M, et al. A Novel Circulating Noncoding Small RNA for the Detection of Acute Myocarditis. New England Journal of Medicine. 2021;384(21):2014-2027. doi:10.1056/nejmoa2003608
  46. Caforio ALP, Calabrese F, Angelini A, Tona F, Vinci A, Bottaro S, et al. A prospective study of biopsy-proven myocarditis: prognostic relevance of clinical and aetiopathogenetic features at diagnosis. European Heart Journal. 2007;28(11):1326-1333. doi:10.1093/eurheartj/ehm076
  47. Anzulovic-Mirosevic D, Razzolini R, Zaninotto M, Plebani M, Mion M, Rozga A, et al. The C-Reactive Protein Levels in Left Ventricular Dysfunction of Different Etiology. Inflammation & Allergy-Drug Targets. 2009;8(4):247-251. doi:10.2174/187152809789352212
  48. Lee SS, Singh S, Link K, Petri M. High-Sensitivity C-Reactive Protein as an Associate of Clinical Subsets and Organ Damage in Systemic Lupus Erythematosus. Seminars in Arthritis and Rheumatism. 2008;38(1):41-54. doi:10.1016/j.semarthrit.2007.09.005
  49. Oikonomou EK, Marwan M, Desai MY, Mancio J, Alashi A, Hutt Centeno E, et al. Non-invasive detection of coronary inflammation using computed tomography and prediction of residual cardiovascular risk (the CRISP CT study): a post-hoc analysis of prospective outcome data. The Lancet. 2018;392(10151):929-939. doi:10.1016/s0140-6736(18)31114-0
  50. Baritussio A, Vacirca F, Ocagli H, Tona F, Pergola V, Motta R, et al. Assessment of Coronary Inflammation by Pericoronary Fat Attenuation Index in Clinically Suspected Myocarditis with Infarct-Like Presentation. Journal of Clinical Medicine. 2021;10(18):4200. doi:10.3390/jcm10184200
  51. Goeller M, Achenbach S, Herrmann N, Bittner DO, Kilian T, Dey D, et al. Pericoronary adipose tissue CT attenuation and its association with serum levels of atherosclerosis-relevant inflammatory mediators, coronary calcification and major adverse cardiac events. Journal of Cardiovascular Computed Tomography. 2021;15(5):449-454. doi:10.1016/j.jcct.2021.03.005
  52. Baritussio A, Williams MC. Gaining evidence on coronary inflammation. Journal of Cardiovascular Computed Tomography. 2021;15(5):455-456. doi:10.1016/j.jcct.2021.04.004
  53. Imazio M, Brucato A, Maestroni S, Cumetti D, Dominelli A, Natale G, et al. Prevalence of C-Reactive Protein Elevation and Time Course of Normalization in Acute Pericarditis. Circulation. 2011;123(10):1092-1097. doi:10.1161/circulationaha.110.986372
  54. KANEKO K, KANDA T, HASEGAWA A, SUZUKI T, KOBAYASHI I, NAGAI R. C-reactive Protein as a Prognostic Marker in Lymphocytic Myocarditis. Japanese Heart Journal. 2000;41(1):41-47. doi:10.1536/jhj.41.41
  55. Ammirati E, Veronese G, Brambatti M, Merlo M, Cipriani M, Potena L, et al. Fulminant Versus Acute Nonfulminant Myocarditis in Patients With Left Ventricular Systolic Dysfunction. Journal of the American College of Cardiology. 2019;74(3):299-311. doi:10.1016/j.jacc.2019.04.063
  56. Anzini M, Merlo M, Sabbadini G, Barbati G, Finocchiaro G, Pinamonti B, et al. Long-Term Evolution and Prognostic Stratification of Biopsy-Proven Active Myocarditis. Circulation. 2013;128(22):2384-2394. doi:10.1161/circulationaha.113.003092
  57. Ammirati E, Cipriani M, Lilliu M, Sormani P, Varrenti M, Raineri C, et al. Survival and Left Ventricular Function Changes in Fulminant Versus Nonfulminant Acute Myocarditis. Circulation. 2017;136(6):529-545. doi:10.1161/circulationaha.117.026386
  58. Mason JW, O'Connell JB, Herskowitz A, Rose NR, McManus BM, Billingham ME, et al. A Clinical Trial of Immunosuppressive Therapy for Myocarditis. New England Journal of Medicine. 1995;333(5):269-275. doi:10.1056/nejm199508033330501
  59. Frustaci A, Russo MA, Chimenti C. Randomized study on the efficacy of immunosuppressive therapy in patients with virus-negative inflammatory cardiomyopathy: the TIMIC study. European Heart Journal. 2009;30(16):1995-2002. doi:10.1093/eurheartj/ehp249
  60. Kandolin R, Lehtonen J, Salmenkivi K, Räisänen-Sokolowski A, Lommi J, Kupari M. Diagnosis, Treatment, and Outcome of Giant-Cell Myocarditis in the Era of Combined Immunosuppression. Circulation: Heart Failure. 2013;6(1):15-22. doi:10.1161/circheartfailure.112.969261
  61. Tymińska A, Ozierański K, Caforio AL, Marcolongo R, Marchel M, Kapłon-Cieślicka A, Baritussio A, Filipiak KJ, Opolski G, Grabowski M. Myocarditis and inflammatory cardiomyopathy in 2021: An update. Pol. Arch. Intern. Med. 2021 May 24;131(6):594-606.
Support