Diabetic retinopathy (DR), a major complication of type 2 diabetes mellitus (T2DM), remains a growing global health concern. This study aimed to evaluate the relationship between systemic inflammatory markers and both the presence and severity of DR. Special attention was given to the pan-immune-inflammation value (PIV), a novel composite index of immune response, whose association with DR remains underexplored. A prospective cross-sectional study was conducted involving 310 patients with T2DM, grouped based on the International Clinical Diabetic Retinopathy Disease Severity Scale (ICDR): no DR (NDR, n = 100), non-proliferative DR (NPDR, n = 100), and proliferative DR (PDR, n = 110). Clinical and laboratory data—including neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), neutrophil-to-HDL cholesterol ratio (NHR), systemic immune-inflammation index (SII), and PIV—were analyzed. Statistical methods included ANOVA, Kruskal-Wallis, and receiver operating characteristic (ROC) analyses. PDR patients had significantly elevated NLR (p = 0.005), MLR (p < 0.001), NHR (p = 0.016), C-reactive protein-to-albumin ratio (CAR) (p < 0.001), and PIV (p = 0.002) levels. In NPDR, PLR (p = 0.012) and SII (p = 0.005) were significantly higher than in the other groups. NLR showed the highest predictive performance in ROC analysis (sensitivity: 84.8%), followed by SII (78.1%), PLR (76.2%), and PIV (53.3%). Among patients with T2DM, inflammatory markers—particularly NLR, PLR, SII, and PIV—suggested potential relevance in identifying DR and its progression. PLR and SII may have utility in the early identification of NPDR, while PIV appears to be a potentially valuable inflammatory marker. These cost-effective and easily accessible indices may contribute to the screening and monitoring of DR in clinical settings.

This study aimed to assess neutrophil-to-high-density lipoprotein cholesterol ratio (NHR) and other inflammatory and biochemical parameters as potential biomarkers for predicting gestational hypertension (GH) and preeclampsia (PE) in pregnant women. A total of 180 pregnant women were enrolled and divided into 3 groups: 58 with GH, 42 with PE, and 80 normotensive controls. Clinical, demographic, and laboratory data (inflammatory markers, lipid profiles, liver enzyme levels, and kidney function) were also collected. NHR and other biomarkers such as C-reactive protein (CRP) and white blood cell counts were compared across the groups. Statistical analyses, including univariate and multivariate regression, were conducted to identify significant predictors of GH and PE. The NHR was significantly higher in the GH (4.5 ± 1.1) and PE (5.2 ± 1.2) groups than in the normotensive controls (3.6 ± 1.1, P ˂ .001). Inflammatory markers, such as CRP, white blood cell count, and monocyte levels, were elevated in the GH and PE groups. In addition, the levels of glucose, creatinine, and liver enzymes were notably higher in the PE group. The NHR demonstrated a positive correlation with CRP levels. Regression analysis revealed that the NHR (P < .001), CRP (P = .002), and platelet count (P < .001) were independent predictors of GH and PE. The NHR may serve as an early inflammatory biomarker for predicting GH and PE. This finding suggests that NHR, along with other biomarkers, could be incorporated into clinical practice to improve the early identification and management of hypertensive disorders during pregnancy. Further prospective studies are needed to confirm these results and evaluate their clinical utility.

Background and Objectives: This study aimed to investigate the relationship between Maresin-1 (MaR1), Chitinase-3-like protein 1 (CHI3L1), and inflammatory as well as hematological markers in patients with type 2 diabetes mellitus (T2DM) and diabetic nephropathy (DN). Materials and Methods: This cross-sectional study included 90 participants divided into three groups: healthy controls (n = 30), patients with T2DM (n = 30), and patients with diabetic nephropathy (n = 30). The serum levels of MaR1 and CHI3L1 were measured using ELISA. Biochemical and hematological parameters were also assessed. Statistical comparisons were conducted using non-parametric tests, and correlations were analyzed via Spearman correlation. Results: Serum MaR1 levels were significantly higher in DN patients compared to both T2DM patients and controls (p < 0.01), while CHI3L1 levels were significantly lower in the DN group compared to controls (p = 0.007). MaR1 showed a positive correlation with CRP, BUN, and creatinine, and a negative correlation with GFR. CHI3L1 levels were positively correlated with GFR and negatively with BUN. Inflammatory markers such as CRP were elevated in the diabetic groups, while no significant differences were found in NLR values. Conclusions: Elevated MaR1 levels in DN patients and their correlation with renal dysfunction markers suggest that MaR1 may serve as a potential prognostic biomarker in diabetic nephropathy. The unexpected decrease in CHI3L1 levels in DN patients indicates the need for further research to clarify their role. These findings indicated that MaR1 and CHI3L1 should be further investigated in future studies as indicators for the early detection and monitoring of diabetic complications.

Background and Objectives: Polycystic ovary syndrome (PCOS) is one of the most common endocrine disorders in women of reproductive age. The etiology of PCOS is complex and is associated with low-grade chronic inflammation. The current study aimed to investigate inflammation markers in PCOS patients with and without metformin treatment. Materials and Methods: This cross-sectional study included 30 age-matched PCOS patients not receiving metformin treatment, 50 PCOS patients receiving metformin treatment, and 30 healthy controls. The groups were compared according to inflammatory (hs-CRP, NLR, and PLR) and metabolic parameters (lipids, fasting blood-sugar insulin, HOMA-IR). Results: Insulin (p < 0.001) and HOMA-IR (p < 0.001) score median values of PCOS patients were found to be significantly higher than the control group. CRP levels of PCOS patients receiving metformin treatment were found to be higher than both control and PCOS patients not receiving metformin treatment (p < 0.001). There was a significant difference between the groups in terms of PLR mean value (p = 0.031). The mean PLR value of PCOS patients, both those receiving metformin treatment and those not receiving treatment, was found to be significantly higher than the control group. In PCOS patients not receiving metformin treatment, there was a negative significant correlation between NLR and HDL level (r: −0.384; p: 0.036), NLR and insulin (r: 0.422; p: 0.020), and HOMA-IR score (r: 0.439; p: 0.015). There was a positive significant correlation between them. Conclusions: In the current study, PLR was significantly increased in all PCOS patients compared to controls. CRP levels in PCOS patients receiving metformin treatment were significantly higher than both control and untreated PCOS patients. PLR is positively associated with insulin and HOMA-IR scores in PCOS patients.

Objective: This study aims to construct a high-precision decision support model by integrating explainable artificial intelligence (XAI) techniques utilizing urinary and plasma biomarkers. Methods: We used an open-access dataset published by Debernardi et al. (2020) containing the biomarkers Lymphatic Vessel Endothelial Hyaluronan Receptor 1 (LYVE1), Regenerating Family Member 1 Beta (REG1B), Trefoil Factor 1 (TFF1), and plasma CA19-9. The preprocessing phase involved missing value imputation, Z-score normalization, and feature engineering. An autoencoder (AE)-based unsupervised learning framework was employed for dimensionality reduction. Classification was performed using an XGBoost algorithm optimized via the Optuna framework. Class imbalance was addressed through the Synthetic Minority Over-sampling Technique (SMOTE). Model interpretability was ensured using SHapley Additive Explanations (SHAP). Results: The proposed Autoencoder–XGBoost model optimized with Optuna outperformed conventional methods, achieving an accuracy of 95.8%, 95% precision, 93% recall, 93% F1-score, and an AUC of 0.984. SHAP analysis identified plasma CA19-9, LYVE1, creatinine, and age as the most influential predictors contributing to model decisions. Conclusion: The developed XAI framework offers high diagnostic accuracy and transparent decision logic for the early detection of PDAC. By leveraging the clinical potential of urinary biomarkers, the model demonstrates strong applicability for integration into screening and risk stratification modules of clinical decision support systems.