Comparison between statistical and machine learning methods to detect the hematological indices with the greatest

Somayeh Ghiasi Hafezi1, Bahareh Behkamal2, Mohammad Rashidmayvan3

  • 1International UNESCO center for Health-Related Basic Sciences and Human Nutrition, Mashhad University of Medical Sciences, Mashhad, Iran; Department of Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, Iran.

PubMed

Insights

Complete blood count (CBC) parameters like hemoglobin and platelet count are linked to high LDL cholesterol. Red cell distribution width (RDW) is a key predictor in women, while RDW-PLT ratio and PLT-HDL ratio are crucial for men.

Area of Science:

  • Cardiovascular Disease Research
  • Hematology
  • Biomarker Discovery

Background:

  • Elevated low-density lipoprotein-cholesterol (LDL-C) is a major risk factor for cardiovascular diseases (CVD).
  • Associations between complete blood count (CBC) indices and dyslipidemia have been observed.
  • Understanding these links can aid in CVD risk assessment.

Purpose of the Study:

  • To investigate the relationship between CBC parameters and serum LDL levels.
  • To identify specific CBC biomarkers predictive of high LDL-C.
  • To explore sex-specific differences in these associations.

Main Methods:

  • Prospective study of 9704 participants (aged 35-65).
  • Comprehensive screening of LDL-C levels and CBC indicators.
  • Analysis using Logistic Regression, Decision Tree, Random Forest, Neural Network, and Support Vector Machine.

Main Results:

  • Age, hemoglobin (HGB), hematocrit (HCT), platelet count (PLT), lymphocyte (LYM), PLT-LYM ratio (PLR), PLT-HDL ratio (PHR), HGB-LYM ratio (HLR), red blood cell count (RBC), Neutrophil-HDL ratio (NHR), and PLT-RBC ratio (PRR) were significantly associated with LDL levels (p<0.05).
  • Red cell distribution width (RDW) significantly predicted higher LDL in women.
  • RDW-PLT ratio (RPR) and PHR were most influential for men, while RDW was key for women.

Conclusions:

  • Sex influences LDL-C odds, with females showing higher odds (52.9%).
  • Age and HCT also increase LDL-C odds (4.1% and 5.5%, respectively).
  • RPR and PHR are key predictors for both genders; RDW is significant for women, particularly for high HDL-C levels.
Abstract