Background: Chronic kidney disease is a growing public health problem worldwide, and the number of patients requiring renal replacement therapy is steadily increasing. Türkiye has experienced a similar rise in both the incidence and prevalence of renal replacement therapy over the past decades; however, national‐level projections of future renal replacement therapy demand are lacking. Aims: This study aimed to forecast the future burden of renal replacement therapy in Türkiye by modeling historical incidence and prevalence trends using national registry data and demographic projections. Methods: National renal replacement therapy registry data from 2012 to 2024 were analyzed together with demographic projections from the Turkish Statistical Institute extending to 2035. Four models were constructed separately for incidence and prevalence. Model performance was compared using the coefficient of determination, root mean square error, and Akaike information criterion. Leave‐one‐out cross‐validation was used to assess model robustness. The modeling was further validated on data from Japan and the United Kingdom. Results: All models indicated a consistent upward trend in renal replacement therapy incidence in Türkiye over the next decade. By 2035, the prevalence of renal replacement therapy in Türkiye is projected to reach approximately 1150–1250 per million population. The models demonstrated strong goodness of fit, and cross‐validation supported good internal consistency, although the machine‐learning model showed some overfitting for prevalence. Conclusion: The national demand for renal replacement therapy in Türkiye is projected to continue increasing through 2035. Incorporating predictive modeling into national registry surveillance can help guide proactive capacity planning and fair resource distribution for dialysis and transplantation services. At the same time, public health strategies aimed at preventing and slowing the progression of chronic kidney disease remain essential to mitigate the growing burden of end‐stage renal disease.

Background and Objectives: Contrast-associated acute kidney injury (CA-AKI) is a frequent and clinically significant complication in patients with acute myocardial infarction (AMI) undergoing coronary angiography. Early and accurate risk stratification remains challenging with conventional models that rely on linear assumptions and limited variable integration. This study aimed to evaluate and compare the predictive performance of multiple machine learning (ML) algorithms with traditional logistic regression and the Mehran risk score for CA-AKI prediction and to explore key determinants of risk using explainable artificial intelligence methods. Materials and Methods: This retrospective, single-center study included 1741 patients with AMI who underwent coronary angiography. CA-AKI was defined according to KDIGO criteria. Multiple ML models, including gradient boosting machine (GBM), random forest (RF), XGBoost, support vector machine, elastic net, and standard logistic regression were developed using routinely available clinical and laboratory variables. A weighted ensemble model combining the best-performing algorithms was constructed. Model discrimination was assessed using area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Model interpretability was evaluated using feature importance and SHapley Additive exPlanations (SHAP). Results: CA-AKI occurred in 356 patients (20.4%). In multivariable logistic regression, lower left ventricular ejection fraction, higher contrast volume, lower sodium, lower hemoglobin, and higher neutrophil-to-lymphocyte ratio (NLR) were independently associated with CA-AKI. Among ML approaches, the weighted ensemble model demonstrated the highest discriminative performance (AUC 0.721), outperforming logistic regression and the Mehran risk score (AUC 0.608). Importantly, the ensemble model achieved a consistently high NPV (0.942), enabling reliable identification of low-risk patients. Explainability analyses revealed that inflammatory markers, particularly NLR, along with sodium, uric acid, baseline renal indices, and contrast burden, were the most influential predictors across models. Conclusions: In patients with AMI undergoing coronary angiography, interpretable ML models, especially ensemble and gradient boosting-based approaches, provide superior risk stratification for CA-AKI compared with conventional methods. The high negative predictive value highlights their clinical utility in safely identifying low-risk patients and supporting individualized, risk-adapted preventive strategies.

Background: Maternal mortality has declined in Türkiye over the past three decades, yet regional disparities are persistent. Understanding temporal and spatial variation is essential for assessing progress toward Sustainable Development Goal 3.1 and for guiding sub-national interventions. Methods: This ecological time-series study analysed regional maternal mortality ratios (MMR, per 100,000 live births) across twelve NUTS-1 regions of Türkiye between 2008 and 2023, using data from the Ministry of Health and Turkish Statistical Institute. Linear regression was used to estimate annual slopes and average percent change (APC) for each region. Inter-regional inequality was assessed annually with the Gini coefficient and coefficient of variation (CV). Within-region volatility, peak–trough ranges, and largest single-year changes were also examined to capture temporal instability. Results: National MMR declined consistently from 2008 to 2023, indicating broad progress. The Gini and CV both showed a downward trend, demonstrating increasing equitable access to maternal healthcare, although inequality temporarily widened around 2022. Eastern and Southeastern Anatolia and the Western Black Sea showed the steepest declines, while Western Marmara and Central Anatolia displayed marked inter-annual oscillations. Several regions experienced sharp one-year reversals, possibly related to system shocks such as the COVID-19 pandemic or unexpected migration. Conclusions: Türkiye achieved substantial reductions in maternal mortality while simultaneously narrowing regional gaps, yet volatility persists. Tracking both the level and stability of MMR, through inequality and variability metrics, offers a more complete picture of system performance and resilience. Strengthening sub-national surveillance and maintaining service stability remain critical for achieving equitable maternal health outcomes.

Adolescent fertility is a significant indicator of reproductive health, gender equity and social development. While Türkiye’s total fertility has declined below population replacement level, regional patterns of adolescent childbearing remain insufficiently understood. To examine adolescent fertility trends across Türkiye’s 13 NUTS-1 regions from 2009 to 2024, quantifying rates of decline, assessing regional convergence, and exploring the relationship with total fertility. Regional fertility indicators were reconstructed using official birth registration and population data. We calculated adolescent fertility rates (AFR, per 1000 women aged 15–19), adolescent birth share (percentage of total births), and total fertility rates (TFR). Temporal trends were estimated using log-linear regression. Regional convergence was assessed through dispersion analysis and fixed-effects panel regression. National AFR declined from 36.6 to 9.9 per 1000 (annual percentage change [APC] = − 8.4%; R ² = 0.99), while adolescent birth share fell from 8.8 to 3.3% (APC = − 6.6%; R ² = 0.98)—both far exceeding TFR decline from 2.08 to 1.48 children per woman (APC = − 2.3%; R ² = 0.83). The steepest reductions occurred in Northeast Anatolia (− 3.16 per year), Central East Anatolia (− 2.72), and Central Anatolia (− 2.63). Regional dispersion narrowed substantially: interquartile range for adolescent birth share contracted from 8–11% in 2009 to 4–6% in 2024. Adolescent birth share and TFR were strongly correlated (r = 0.71; Spearman ρ = 0.76), with fixed-effects regression confirming within-region associations (β = 0.561, p < 0.001; R ² = 0.97). However, adolescent fertility declined 2.3 times faster than total fertility, indicating that adolescent fertility declined even in regions where overall fertility changed minimally, suggesting that early-age childbearing trends do not mechanically mirror total fertility decline. Adolescent fertility in Türkiye declined at more than double the pace of overall fertility between 2009 and 2024, highlighting distinct temporal dynamics in early-age childbearing relative to overall fertility decline. However, persistent geographic disparities highlight the need for targeted, culturally sensitive reproductive health and educational interventions, particularly in southeastern provinces.

Microinflammation and functional iron deficiency are major contributors to anemia and treatment burden in maintenance hemodialysis (HD). Medium cutoff (MCO) membranes enhance the removal of middle‐ and large‐sized solutes implicated in these pathways, yet real‐world data using routinely measured inflammatory and iron‐related markers are scarce. This study examined the effects of MCO‐based expanded HD on inflammatory indices, iron metabolism, and anemia‐related treatment requirements. In this single‐center retrospective study, 22 maintenance HD patients (11 who continued on high‐flux dialyzers and 11 who were switched to MCO dialyzers) were followed for 24 weeks. Baseline and 24‐week assessments included C‐reactive protein (CRP), the CRP/albumin ratio, neutrophil count, and composite inflammatory indices, as well as serum iron, transferrin saturation (TSAT), total iron‐binding capacity (TIBC), and ferritin. Monthly intravenous iron supplementation and weekly erythropoiesis‐stimulating agent (ESA) doses were also documented. Baseline characteristics were comparable between groups. Over the 24‐week period, the MCO group showed a significant decline in neutrophil count ( p = 0.042) and downward trends in CRP and the CRP/albumin ratio, while both markers increased significantly in patients maintained on high‐flux dialyzers. Serum albumin remained stable in all participants. Parallel to the improvement in inflammation, the MCO group demonstrated significant enhancements in iron‐handling parameters, with higher serum iron ( p = 0.008) and TSAT ( p = 0.005), and lower TIBC ( p = 0.007), none of which were observed in the high‐flux group. Between‐group Δ‐differences were significant for CRP ( p = 0.010), CRP/albumin ratio ( p = 0.013), serum iron ( p = 0.040), TIBC ( p = 0.005), and TSAT ( p = 0.005). Hemoglobin levels remained stable in both groups, while intravenous iron and ESA requirements showed modest within‐group reductions in the MCO cohort. In this exploratory retrospective analysis, MCO membrane use was associated with favorable trends in inflammatory markers and iron‐handling parameters, alongside modest within‐group reductions in intravenous iron and ESA requirements, without compromising serum albumin. These findings suggest that MCO therapy may help mitigate microinflammation and support more efficient anemia management in real‐world HD practice.