Background: This study examined the changes in C-reactive protein (CRP), interleukin-6 (IL-6), white blood cell (WBC), neutrophil (NEU), lymphocyte (LYM), and eosinophil (EOS) parameters among severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) patient groups with Alpha (B.1.1.7), Beta (B.1.351), Delta (B.1.617.2), and Omicron (B.1.1.529) variants. Objectives: The present study aimed to examine the changes in CRP, IL-6, WBC, NEU, LYM, and EOS levels in patients infected with SARS-CoV-2 variants. Methods: Adults over the age of 18, who had a positive SARS-CoV-2 RT-PCR result and underwent molecular variant analysis (n = 40,133), were retrospectively included in the study. Changes in CRP (n = 7,712), IL-6 (n = 2,225), WBC (n = 6,885), NEU (n = 7,186), LYM (n = 8,224), and EOS (n = 7,901) parameters were analyzed in SARS-CoV-2 Alpha, Beta, Delta, and Omicron variant patient groups. Results: The incidence of women among patients with the Delta variant increased significantly (P = 0.001). The average age of Omicron variant patients was found to be higher (P < 0.001). In laboratory parameters, CRP levels were significantly higher in the Delta and Omicron variants compared to the others (P < 0.001). A decrease in the number of patients with high IL-6 values was observed from Alpha to Omicron (P < 0.001). The WBC values were significantly higher in the Delta variant than in the others (P < 0.001). Neutrophil levels were significantly higher in the Omicron variant (P < 0.001). There was an increase in the number of patients with normal LYM levels from Alpha to Omicron. Eosinophil levels were found to be lower in the Beta and Delta variants compared to the others (P < 0.001). Conclusions: The decrease in the number of patients with high IL-6 levels from Alpha to Omicron suggests that the rate of severe prognoses has decreased.

Background: It is known that the change in coagulation parameters has an effect on mortality and prognosis in COVID-19 patients. The SARS-CoV-2 virus has changed with mutations in the genome of the virus since the beginning of the pandemic, and the resulting variants have been recorded by the World Health Organization. With these variations, the clinical severity of the disease and laboratory parameters have also changed. Objectives: In this study, we examined the changes in D-dimer levels, fibrinogen levels, platelet count (PLT), and mean platelet volume (MPV) between SARS-CoV-2 Alpha (B.1.1.7), Beta (B.1.351) Delta (B.1.617.2), and Omicron (B.1.1.529) variants. Methods: The study was conducted retrospectively on 28 195 adult patients with SARS-CoV-2 infection. At the time of application, data on age, gender, SARS-CoV-2 variant status, D-dimer levels (n = 7090), fibrinogen (n = 5709), PLT (n = 7066), and MPV (n = 8330) were collected. Patients were divided according to alpha, beta, delta, and omicron variants. The changes in variants were examined statistically. Results: The incidence of the delta variant in women was higher than the other variants, followed by alpha and omicron (P = 0.001). The Beta variant was detected at a higher rate in males. The ages of the cases with the Omicron variant were higher than the cases with Alpha, Beta, and Delta variants (P = 0.001, P = 0.001, P = 0.001, and P < 0.01, respectively). In laboratory parameters, D-dimer and fibrinogen levels were detected to be significantly higher in Delta and Omicron variants. PLT and MPV were determined to be lower in delta and omicron than in alpha and beta variants. Conclusions: Examination of the changes in laboratory coagulation parameters according to variants shows that the tendency to clot increases from alpha to omicron.

Background/Objectives: This study aimed to develop and evaluate machine learning models for predicting ionized calcium levels in patients with hypoalbuminemia, compare their performance with classical correction formulas and unadjusted total calcium levels, and assess their transportability through external validation. Methods: In a retrospective development cohort of 14,745 adults with hypoalbuminemia, XGBoost and ordinary least squares (OLS) models used total calcium, albumin, total protein, and eGFR and were evaluated with nested cross-validation. Frozen models were then applied without recalibration to an independent external cohort of 2751 patients using the same analyzer platforms. Results: Development XGBoost performance was R² = 0.500 and AUC-ROC = 0.798 (95% CI 0.788–0.807), with 98.5% sensitivity and 26.0% specificity. External R² was 0.397 for XGBoost and 0.363 for OLS. External AUC-ROC was 0.818 (95% CI 0.791–0.845) for XGBoost, 0.823 (0.797–0.850) for OLS, and 0.819 (0.791–0.845) for total calcium. Threshold-matched and exploratory decision-curve analyses showed no clear incremental XGBoost advantage over total calcium. Conclusions: Machine learning models provided useful continuous ionized-calcium estimates and high sensitivity for hypocalcemia detection, although specificity was low. In independent external validation, hypocalcemia discrimination was comparable to unadjusted total calcium. The models should be considered complementary rather than substitutes for measured ionized calcium, and further multicenter and prospective evaluation is warranted.

Background/Objectives: This study aimed to develop and externally validate machine learning (ML) models for low-density lipoprotein cholesterol (LDL-C) estimation and compare their analytical and clinical performance with conventional formulas, particularly in individuals with elevated triglyceride (TG) levels. Methods: This retrospective study included 11,681 adults whose lipid profiles were retrieved using a laboratory information system. ML models (linear regression, random forest, support vector regression, and XGBoost) were developed using routine lipid parameters and evaluated using 10-fold cross-validation. Performance was assessed using the mean absolute error (MAE), root mean squared error (RMSE), bias, correlation, Bland–Altman agreement, and clinical classification according to LDL-C categories. Subgroup analyses were conducted across TG strata, with an emphasis on TG ≥ 400 mg/dL. Results: ML models generally demonstrated lower error and higher agreement with directly measured LDL-C levels than conventional formulas. XGBoost showed the best overall performance (MAE: 14.7 mg/dL; RMSE: 20.22 mg/dL; R² = 0.780; r = 0.88) and the lowest deviation. The ML models also showed a higher clinical classification accuracy (up to 66%). Performance declined with increasing TG levels, particularly for conventional formulas, whereas ML models remained more stable, including patients with TG ≥ 400 mg/dL. External validation across independent cohorts and analytical platforms demonstrated stable performance of the XGBoost model and generally higher classification accuracy than conventional LDL-C estimation formulas. Conclusions: ML-based LDL-C estimation may represent a complementary alternative to conventional formulas, particularly in hypertriglyceridemic populations.