Bin Fu

End-stage renal disease (ESRD) is a severe chronic renal disorder with high mortality, requiring dialysis treatment or kidney transplantation. The endothelial activation and stress index (EASIX), reflecting inflammatory status and endothelial dysfunction, has demonstrated predictive value for outcomes in multiple diseases. However, its association with in-hospital mortality (IHM) risk in ESRD patients remains unclear, and machine learning prediction models remain unestablished. Clinical data for ESRD patients were extracted from the MIMIC-IV (3.1) database. The outcome was IHM. The link between EASIX and IHM risk was explored using Cox proportional hazards regression, Kaplan-Meier survival curves, restricted cubic splines (RCS), and subgroup analysis. The Boruta algorithm and LASSO regression were employed to screen important features. Multiple models were established using machine learning algorithms, validated, and compared. SHAP analysis was applied to the optimal model. The study included 997 ESRD patients, with 194 in-hospital deaths, accounting for 19.5% of the total cohort. The Kaplan-Meier curve revealed the highest IHM rate among patients with the highest EASIX level (Q4). Elevated EASIX levels showed a significant positive link with an enhanced IHM risk in ESRD patients (HR [95% CI] = 2.086 [1.697, 2.564]). RCS showed an approximate linear relationship, with this association consistent across multiple subgroups. The gradient boosting machine was identified as the optimal model (AUC of training set = 0.822, AUC of validation set = 0.763). SHAP analysis identified EASIX as a key contributor to IHM risk. EASIX is significantly positively correlated with an elevated IHM risk in ESRD patients, making it a crucial predictor of IHM in ESRD. EASIX can serve as an early predictive tool to guide the identification, intervention, and prevention of adverse outcomes in ESRD. Not applicable.

Background: Liver cancer (LivCa) is one of the most prevalent malignancies globally, and can result from viral hepatitis, non-alcoholic steatohepatitis (NASH), and alcohol use. LivCa is of increasing concern in Asia, but the burden of etiology-specific LivCa and future projections remain to be elucidated. Methods: We extracted the incidence, mortality, and disability-adjusted life years (DALYs) of LivCa across Asia and in 34 Asian countries in 1990-2021 from the Global Burden of Disease Study 2021 (GBD 2021). We then calculated their estimated annual percentage change (EAPC) and percentage variation to quantify the changes in the burden of LivCa. The association of the level of social development with LivCa burden was explored using the sociodemographic index (SDI). Moreover, the trend of the epidemiology of LivCa burden in Asia from 2022 to 2040 was predicted using the Bayesian age-period-cohort (BAPC) model. Results: Overall, the age-standardized incidence, mortality, and DALYs rates of LivCa in Asia showed a general declining trend, with EAPCs of -0.47, -0.73, and -1.14, respectively. Notably, hepatitis B virus remained the predominant cause. However, the burdens attributed to non-alcoholic steatohepatitis and alcohol use increased significantly, while that of hepatoblastoma decreased. Regarding demographic distribution, the highest disease burden was observed among males and the elderly population aged 85–94 years. Geographically, Nepal, Taiwan (Province of China), India, and Malaysia contributed most substantially to the increasing burden. In terms of risk factors, high BMI and alcohol use were prominent in Central Asia, whereas smoking was a key factor in East and Southeast Asia. Additionally, a positive correlation was observed between the SDI and the burden of LivCa. Finally, projections from the BAPC model indicated a persistent decline in the burden of LivCa from 2022 to 2040. Conclusions: Despite the overall decreasing trend, targeted strategies addressing etiology-specific risks and regional disparities are urgently needed to further reduce the future burden of LivCa in Asia.

Introduction: Recent phase III programs, EV-302 and CheckMate-901, showed that enfortumab vedotin plus pembrolizumab (EV + P) and nivolumab with gemcitabine-cisplatin (N + GC) deliver superior clinical outcomes when used as initial therapy for advanced urothelial cancer. What remains uncertain is their relative economic value when assessed under Chinese and US payer conditions. To address this gap, we compared the value for money of EV + P versus N + GC as first-line management for la/mUC from the perspectives of healthcare payers in China and the US. Methods: We performed a model-based economic evaluation using a time-dependent state-transition framework implemented in TreeAge Pro (2022). Health benefits were measured as quality-adjusted life-years (QALYs) derived from health-state utilities, and comparative value was expressed as incremental cost-effectiveness ratios (ICER). The robustness of the model was assessed through one-way sensitivity analysis (OWSA) to evaluate the impact of key parameter uncertainties. Results: In the US, EV + P cost $1,863,624.32 and provided 3.34 QALYs, while N + GC cost $881,979.07 for 2.36 QALYs, resulting in an ICER of $1,001,626.19 per QALY, exceeding the $150,000/QALY threshold. In China, EV + P cost $485,374.69 and provided 2.95 QALYs, compared to $203,811.61 for 2.15 QALYs with N + GC, yielding an ICER of $351,960.68/QALY, above the $40,451.64/QALY threshold. Therefore, N + GC is the more cost-effective first-line strategy in both countries. Conclusion: Under current pricing and reimbursement assumptions, N + GC is economically preferable to EV + P as a first-line strategy for la/mUC in both the US and China. EV + P may warrant consideration only in tightly selected scenarios or with substantial coordinated price reductions and policy changes. Meanwhile, it should be noted that due to the inherent limitations of the indirect comparison method between drugs, the conclusions of this study should be regarded as exploratory analysis results.

Background: IgA nephropathy (IgAN) is a leading cause of renal failure, characterized by significant clinical and pathological heterogeneity. Accurate subtype classification remains challenging due to overlapping clinical manifestations and the multidimensional nature of data. Traditional methods often fail to fully capture IgAN’s complexity, limiting their clinical applicability. This study introduces MAL-Net, a deep learning framework for multi-label classification of IgAN subtypes, leveraging multidimensional clinical data and incorporating sensor-based inputs such as laboratory indices and symptom tracking. Methods: MAL-Net integrates Long Short-Term Memory (LSTM) networks with Multi-Head Attention (MHA) mechanisms to effectively capture sequential and contextual dependencies in clinical data. A memory network module extracts features from clinical sensors and records, while the MHA module emphasizes critical features and mitigates class imbalance. The model was trained and validated on clinical data from 500 IgAN patients, incorporating demographic, laboratory, and symptomatic variables. Performance was evaluated against six baseline models, including traditional machine learning and deep learning approaches. Results: MAL-Net outperformed all baseline models, achieving 91% accuracy and an AUC of 0.97. The integration of MHA significantly enhanced classification performance, particularly for underrepresented subtypes. The F1-score for the Ni-du subtype improved by 0.8, demonstrating the model’s ability to address class imbalance and improve precision. Conclusions: MAL-Net provides a robust solution for multi-label IgAN subtype classification, tackling challenges such as data heterogeneity, class imbalance, and feature interdependencies. By integrating clinical sensor data, MAL-Net enhances IgAN subtype prediction, supporting early diagnosis, personalized treatment, and improved prognosis evaluation.