Exploring the predictive values of CRP and lymphocytes in coronary artery disease based on a machine learning and

Yuan Liu1,2, Xin Yuan1,2, Yu-Chan He1,2

  • 1Department of Cardiology, Liuzhou People's Hospital, Affiliated of Guangxi Medical University, Liuzhou, Guangxi, China.

PubMed

Insights

Leukocyte subsets and C-reactive protein (CRP) predict coronary artery disease (CAD). High lymphocyte counts and low CRP levels reduce major adverse cardiovascular events, while high CRP with low lymphocytes indicate a poor prognosis.

Area of Science:

  • Cardiovascular Medicine
  • Immunology
  • Genetics

Background:

  • Coronary artery disease (CAD) remains a leading cause of mortality worldwide.
  • Identifying reliable biomarkers for CAD risk prediction is crucial for effective prevention and management.
  • Leukocyte subsets and C-reactive protein (CRP) are implicated in inflammatory processes relevant to atherosclerosis.

Purpose of the Study:

  • To investigate the predictive value of leukocyte subsets and C-reactive protein (CRP) in coronary artery disease (CAD).
  • To establish the causal relationship between specific leukocyte subsets, CRP, and CAD risk.
  • To evaluate the combined diagnostic and prognostic utility of CRP and lymphocyte levels in CAD patients.

Main Methods:

  • A Mendelian randomization (MR) analysis was performed using data from 46,664 patients undergoing coronary angiography.
  • Propensity score matching (PSM), logistic regression, LASSO regression, and random forest (RF) algorithms were employed for risk factor assessment.
  • Receiver operating characteristic (ROC) curves evaluated model sensitivity and specificity, complemented by 36-month survival analysis.

Main Results:

  • Basophil count, CRP levels, and lymphocyte count were identified as significant risk factors for CAD via inverse variance weight (IVW) analysis.
  • LASSO, logistic regression, and RF analyses consistently identified CRP and lymphocyte counts as CAD risk factors, both before and after PSM.
  • The combination of lymphocyte and CRP levels demonstrated a high diagnostic value (0.85) post-PSM.
  • Survival analysis indicated that high lymphocyte counts and low CRP levels were associated with a decreased risk of Major Adverse Cardiovascular Events (MACE) (P < 0.001).

Conclusions:

  • A causal relationship exists between lymphocytes, CRP, and CAD.
  • The combined assessment of CRP and lymphocyte levels provides significant diagnostic value for CAD.
  • High CRP levels coupled with low lymphocyte counts are associated with a poorer prognosis in CAD patients.
Abstract