Background/Objectives: Data availability can affect the performance of AI-based early warning scores (EWSs). This study evaluated how the extent of missing data and imputation strategies influence the predictive performance of the VitalCare–Major Adverse Event Score (VC-MAES), an AI-based EWS that uses last observation carried forward and normal-value imputation for missing values, to forecast clinical deterioration events, including unplanned ICU transfers, cardiac arrests, or death, up to 6 h in advance. Methods: We analyzed real-world data from 6039 patient encounters at Keimyung University Dongsan Hospital, Republic of Korea. Performance was evaluated under three scenarios: (1) using only vital signs and age, treating all other variables as missing; (2) reintroducing a full set of real-world clinical variables; and (3) imputing missing values drawn from a distribution within one standard deviation of the observed mean or using Multiple Imputation by Chained Equations (MICE). Results: VC-MAES achieved the area under the receiver operating characteristic curve (AUROC) of 0.896 using only vital signs and age, outperforming traditional EWSs, including the National Early Warning Score (0.797) and the Modified Early Warning Score (0.722). Reintroducing full clinical variables improved the AUROC to 0.918, whereas mean-based imputation or MICE decreased the performance to 0.885 and 0.827, respectively. Conclusions: VC-MAES demonstrates robust predictive performance with limited inputs, outperforming traditional EWSs. Incorporating actual clinical data significantly improved accuracy. In contrast, mean-based or MICE imputation yielded poorer results than the default normal-value imputation, potentially due to disregarding the “informative presence” embedded in missing data patterns. These findings underscore the importance of understanding missingness patterns and employing imputation strategies that consider the decision-making context behind data availability to enhance model reliability.

Objective: The heterogeneous nature of sepsis renders determining its underlying causes difficult, which may delay diagnosis and intervention. VitalCare-SEPsis Score (VC-SEPS) is a deep learning-based algorithm that predicts sepsis and monitors patient conditions based on electronic medical record data. However, few studies have prospectively compared medical artificial intelligence software algorithms and traditional scoring systems to predict sepsis. This prospective observational study attempted to validate the predictive performance and risk stratification of VC-SEPS for early prediction of sepsis. Methods: In this prospective observational study, we collected electronic medical record data from 6,797 patients hospitalised at Keimyung University Dongsan Hospital, Daegu, South Korea. The final version of the analysed set included 6,455 patients, 325 of whom were diagnosed with sepsis. Results: The area under the receiver operating characteristic curve of VC-SEPS was 0.880, indicating its superiority over traditional scoring systems. The algorithm performance showed a consistent trend within 24 hours. On patients’ initial admission, the VC-SEPS was associated with the risk of developing sepsis, and the score accurately predicted sepsis by an average of 68.05 min compared with diagnosis time by an operational definition of sepsis. Discussion: VC-SEPS could assist medical staff with early diagnosis and intervention in clinical practice by providing a sepsis risk score. Prompt recognition assisting recognition can significantly help shorten the time between recognition and intervention in clinical decision-making processes. Conclusion: This study suggests that using a clinical decision support system can help improve hospital workflows as well as the quality of medical care.

Studies that have assessed the associations between obesity and the estimated glomerular filtration rate (eGFR) have reported inconsistent results. This cross-sectional study was performed to investigate the associations between three waist circumference (WC)-related obesity metrics (waist-to-hip ratio (WHR), waist-to-height ratio (WHtR), and waist-to-height^0.5 ratio (WHt.5R)) and eGFRs. This study included 2133 men and 3443 women who were older than 40 years with eGFRs ≥ 60 mL/min/1.73 m² from the Korean Multi-Rural Communities Cohort. We calculated the residual body mass index (BMI) to reduce multicollinearity among the obesity metrics and performed multiple linear regression. For both sexes, among the adjusted models, most of the general obesity metrics were significantly associated with eGFRs. Particularly for women, the WC-related and general obesity metrics had a stronger effect on eGFRs in the quartile models that included the BMI and the residual BMI, respectively. When WC-related obesity metrics had a stronger effect than the general obesity metric, for both sexes, WHtR showed a significant impact than WHt.5R and WHR on eGFRs. Reducing multicollinearity had an important role in assessing the obesity metrics’ association with eGFRs. Overall, applying the residual method in further studies might help with evaluating the obesity paradox on renal function.

Background: Chronic kidney disease (CKD) is a common condition leading to renal dysfunction and is closely related to increased cardiovascular and mortality risk. CKD is an important public health issue, and recent genetic studies have verified common CKD susceptibility variants. This research examines the interrelationship between candidate genes polymorphisms of interferon lambda (IFNL) induction, its signaling pathway, and CKD. Methods: Seventy-five patients with advanced CKD and 312 healthy subjects (as controls) participated in this research. A replication set composed of 172 patients with advanced CKD and 365 controls was used for additional analysis. The genotype of single nucleotide polymorphisms (SNPs) was determined by the Axiom Genome-Wide Human Assay and SNaPshot assay. Results: The SNP of IFNL3 was significantly associated with CKD in the codominant (p = 0.02) and dominant models (p = 0.02). In addition, the SNPs of IFNL2 were significantly associated with CKD in the dominant model (p = 0.03), and the SNP of interferon alpha receptor 2 (IFNAR2) was significantly associated with CKD in the log-additive model (p = 0.03). Concerning rs148543092, in the IFNL3 gene, a significant association was observed after pooling the original and replication sets. Conclusion: These results indicate that SNPs in the IFNL induction and signal pathway may be associated with CKD risk in the Korean population. Finally, our results also show that the IFNL3 gene variant may be associated with CKD risk.

Background/Objectives: Adipsin, an adipokine, is known to play an important role in maintaining the function of pancreatic beta cells in mice. This study aimed to investigate whether adipsin could be a circulating biomarker for evaluating the function of beta cells in patients with type 2 diabetes (T2D). Methods: Plasma adipsin concentrations were measured using immunoassay in three distinct subject groups: normoglycemia, T2D without insulin treatment (T2D-w/o-insulin), and T2D treated with insulin (T2D-with-insulin). Adipsin expressions were evaluated in three distinct mouse groups: normal diet (ND), high-fat diet (HFD), and HFD with streptozotocin (STZ) and nicotinamide (NA). Results: The T2D-with-insulin group exhibited a significant decrease in plasma adipsin concentration (3.91 ± 1.51 μg/mL) compared to the T2D-w/o-insulin group (5.11 ± 1.53 μg/mL; p < 0.001), whereas the T2D-w/o-insulin group showed a significantly increased plasma adipsin concentration compared to the normoglycemia group (4.53 ± 1.15 μg/mL). Plasma adipsin concentration was positively correlated with fasting C-peptide level (p < 0.001), 2-h C-peptide level (p < 0.001), and 2-h C-peptidogenic index (p < 0.001) in the diabetic groups. HFD mice showed a significant increase in pancreatic islet size, plasma insulin and adipsin levels, as well as adipsin expression in white adipose tissue (WAT) compared to ND mice. In contrast, the insulin-deficient T2D model (HFD-STZ-NA) demonstrated a marked reduction in pancreatic islet size, plasma insulin and adipsin concentrations, and adipsin expression in WAT compared to the HFD mice. Conclusions: plasma adipsin may be useful for evaluating pancreatic beta cell function in patients with T2D.