Search Results (515)

This study aims to guide the management and service of highways towards a more efficient and intelligent direction, and also provides intelligent and green data support for achieving sustainable development goals. The forecasting of traffic flow at highway stations serves as the cornerstone for spatiotemporal analysis and is vital for effective highway management and control. Despite considerable advancements in data-driven traffic flow prediction, the majority of existing models fail to differentiate between directions. Specifically, entrance flow prediction has applications in dynamic route guidance, disseminating real-time traffic conditions, and offering optimal entrance selection suggestions. Meanwhile, exit flow prediction is instrumental for congestion and accident alerts, as well as for road network optimization decisions. In light of these needs, this study introduces an enhanced heterogeneous spatiotemporal graph network model tailored for predicting highway station traffic flow. To accurately capture the dynamic impact of upstream toll stations on the target station’s flow, we devise an influence probability matrix. This matrix, in conjunction with the covariance matrix across toll stations, updated graph structure data, and integrated external weather conditions, allows the attention mechanism to assign varied combination weights to the target toll station from temporal, spatial, and external standpoints, thereby augmenting prediction accuracy. We undertook a case study utilizing traffic flow data from the Chengdu-Chengyu station on the Sichuan Highway to gauge the efficacy of our proposed model. The experimental outcomes indicate that our model surpasses other baseline models in performance metrics. This study provides valuable insights for highway management and control, as well as for reducing traffic congestion. Furthermore, this research highlights the importance of using data-driven approaches to reduce carbon emissions associated with transportation, enhance resource allocation at toll plazas, and promote sustainable highway transportation systems. Full article

Background/Objectives: Chronic exercise training reduces markers of systemic inflammation; however, less is known about how to optimize this adaptation using nutrition. Dairy products, especially fermented ones, like Greek yogurt (GY), contain anti-inflammatory constituents. This secondary analysis aimed to examine the influence of post-exercise GY consumption vs. an isoenergetic carbohydrate pudding (CP; control) on markers of systemic inflammation during an exercise training intervention. Methods: Thirty healthy young males completed 12 weeks of resistance and plyometric exercise training and were randomized to consume GY (n = 15) or CP (n = 15). Rested/fasted blood samples were acquired at baseline, and weeks 1 and 12, and inflammatory biomarkers (tumor necrosis factor-alpha [TNF-α], interleukin [IL]-6, IL-1 receptor antagonist [IL-1ra], IL-1Beta [IL-1β], IL-10, and C-reactive protein [CRP]) were measured. Linear mixed models were run on the absolute concentrations, and linear regressions were performed on the absolute change (baseline to week 12), allowing us to account for important covariates. Results: In both groups, CRP (pro) and IL-1ra (anti) increased at week 1 vs. baseline and week 12, while IL-1β (pro) decreased at week 12 vs. baseline (main time effects). We observed significant interactions for IL-6, TNF-α, and the TNF-α/IL-10 ratio, indicating that at week 12, IL-6 (pro) was lower in GY, whereas TNF-α and TNF-α/IL-10 (both pro-inflammatory) were higher in CP vs. week 1 and baseline, respectively. Additionally, within our linear regression models, higher baseline concentrations of IL-1ra (anti), IL-10 (anti) and CRP (pro) predicted greater change over the intervention. Conclusions: These results indicate that our intervention benefited circulating inflammatory markers, and GY supplementation may enhance these effects. Full article

Background: Physical inactivity is a major contributor to increased mortality among aging populations, especially in middle-aged and older adults. Methods: Data were derived from the China Health and Retirement Longitudinal Study (CHARLS, 2011–2020). Participants self-reported their physical activity frequency, categorized as low (≤1 day/week), medium (2–4 days/week), or high (≥5 days/week). All-cause mortality was tracked through verified records. Cox proportional hazards models were used to estimate hazard ratios (HRs), with adjustments for demographics, lifestyle factors, and baseline health conditions. Results: A total of 2092 participants (mean age = 63.7 ± 10.4 years) were included in the final analytic sample. Higher physical activity frequency was significantly associated with lower mortality in unadjusted models. Participants engaging in activity ≥5 days/week had a 67% reduced mortality risk compared to the low-frequency group (HR = 0.33, p < 0.001). However, after adjusting for health-related covariates, the protective effect was attenuated and no longer statistically significant. In the fully adjusted model, advanced age, current smoking, and ADL limitations emerged as the strongest independent risk factors for mortality, while being married and residing in a rural area were significantly protective effects. Conclusions: The association between frequent physical activity and reduced mortality risk among Chinese older adults is profoundly mediated by baseline health status and functional capacity. These findings highlight the importance of integrated, multifactorial public health interventions that address chronic disease management and functional rehabilitation alongside physical activity promotion. Full article

Sweetpotato virus disease (SPVD) poses a significant threat to global sweetpotato production; therefore, early, accurate field-scale detection is necessary. To address the limitations of the currently utilized assays, we propose PLCNet (Plant-Level Classification Network), a rapid, non-destructive SPVD identification framework using UAV-acquired hyperspectral imagery. High-resolution data from early sweetpotato growth stages were processed via three feature selection methods—Random Forest (RF), Minimum Redundancy Maximum Relevance (mRMR), and Local Covariance Matrix (LCM)—in combination with 24 vegetation indices. Variance Inflation Factor (VIF) analysis reduced multicollinearity, yielding an optimized SPVD-sensitive feature set. First, using the RF-selected bands and vegetation indices, we benchmarked four classifiers—Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), Residual Network (ResNet), and 3D Convolutional Neural Network (3D-CNN). Under identical inputs, the 3D-CNN achieved superior performance (OA = 96.55%, Macro F1 = 95.36%, UA_mean = 0.9498, PA_mean = 0.9504), outperforming SVM, GBDT, and ResNet. Second, with the same spectral–spatial features and 3D-CNN backbone, we compared a pixel-level baseline (CropdocNet) against our plant-level PLCNet. CropdocNet exhibited spatial fragmentation and isolated errors, whereas PLCNet’s two-stage pipeline—deep feature extraction followed by connected-component analysis and majority voting—aggregated voxel predictions into coherent whole-plant labels, substantially reducing noise and enhancing biological interpretability. By integrating optimized feature selection, deep learning, and plant-level post-processing, PLCNet delivers a scalable, high-throughput solution for precise SPVD monitoring in agricultural fields. Full article

Background/Objectives: This study aimed to evaluate and compare the perioperative outcomes of robot-assisted partial nephrectomy (RAPN) for complex renal tumors performed using the novel Japanese Hinotori Surgical Robot System (HSRS) and the established Da Vinci Surgical System (DVSS). Methods: Of 484 consecutive patients who underwent RAPN at our institution, 126 with complex renal tumors were included in the DVSS group, and 48 such patients were included in the HSRS group. Complex tumors in this series were defined by the presence of at least one of the following factors: cT1b, completely endophytic, hilar, cystic, or ipsilateral multiple tumors. Results: Following 1:2 propensity score matching, 74 and 37 patients were included in the DVSS and HSRS groups, respectively. Post-matching, most covariates’ absolute standardized mean difference (SMD) was less than 0.1, indicating effective baseline imbalance correction. All RAPN procedures using HSRS were completed without conversion to open surgery, nephrectomy, or Clavien–Dindo ≥3 postoperative complications. No significant differences in major perioperative outcomes were observed between DVSS and HSRS, including operative time (178 vs. 186 min), console time (115 vs. 115 min; encompassing cockpit time for HSRS), warm ischemia time (15 vs. 15 min), and estimated blood loss (51 vs. 30 mL). Positive surgical margin rates (DVSS 1.4% vs. HSRS 5.4%) and Trifecta achievement rates (94.6% vs. 91.9%) were also comparable, with no significant differences. Conclusions: These findings suggest that, even in patients with complex renal tumors, RAPN performed using the HSRS can achieve perioperative outcomes comparable to those obtained with the established DVSS. Full article

Background: GSK3β is an intracellular regulatory kinase that is dysregulated in multiple tissues in Type 1 myotonic dystrophy (DM-1). Tideglusib inhibits GSK3β activity in preclinical models of DM-1 and promotes cellular maturation, normalising aberrant molecular and behavioural phenotypes. It is currently in clinical development for the treatment of paediatric and adult patients affected by congenital and juvenile-onset DM-1. Here, we summarise the development of a population pharmacokinetic model and subsequent characterisation of influential demographic and clinical factors on the systemic exposure to tideglusib. The availability of a population PK model will allow further evaluation of age-and weight-related changes in drug disposition, supporting the dose rationale and implementation of a paediatric extrapolation plan. Methods: Given the sparse pharmacokinetic sampling scheme in patients receiving tideglusib, model development was implemented in two steps. First, data from Phase I studies in healthy elderly subjects (i.e., 1832 plasma samples, n = 54) were used to describe the population pharmacokinetics of tideglusib in adults. Then, pharmacokinetic model parameter estimates obtained from healthy subjects were used as priors for the evaluation of the disposition of tideglusib in adolescent and adult DM-1 patients (51 plasma samples, n = 16), taking into account demographic and clinical baseline characteristics, as well as food intake. Secondary pharmacokinetic parameters (AUC, C_max and T_max) were derived and summarised by descriptive statistics. Results: Tideglusib pharmacokinetics was described by a two-compartment model with first-order elimination and dose-dependent bioavailability. There were no significant differences in disposition parameters between healthy subjects and DM-1 patients. Body weight was a significant covariate on clearance and volume of distribution. Median AUC_(0–12) and C_max were 1218.1 vs. 3145.7 ng/mL∙h and 513.5 vs. 1170.9 ng/mL, following once daily doses of 400 and 1000 mg tideglusib, respectively. In addition, the time of food intake post-dose or the type of meal appeared to affect the overall exposure to tideglusib. No accumulation, metabolic inhibition, or induction was observed during the treatment period. Conclusions: Even though clearance was constant over the dose range between 400 and 1000 mg, a less than proportional increase in systemic exposure appears to be caused by the dose-dependent bioavailability, which reflects the solubility properties of tideglusib. Despite large interindividual variability in the tideglusib concentration vs. time profiles, body weight was the only explanatory covariate for the observed differences. This finding suggests that the use of weight-banded or weight-normalised doses should be considered to ensure comparable exposure across the paediatric population, regardless of age or body weight. Full article

Background and Aims: Multiple genetic variants have been associated with disease prevalence and outcomes in middle-aged people with metabolic dysfunction-associated fatty liver disease (MAFLD). However, genetic studies in older adults have been lacking. We aimed to understand their clinical relevance in healthy older persons. Methods: A secondary analysis of the ASPREE (ASPirin in Reducing Events in the Elderly) randomized trial involving community-dwelling older adults ≥ 70 years without prior cardiovascular disease events or life-limiting illness at enrolment. The Fatty Liver Index (FLI) was used to identify MAFLD at baseline. We assessed the associations between six previously reported MAFLD-associated genetic variants with prevalent MAFLD at baseline, and the associations of these variants with cardiovascular disease events and all-cause mortality. Results: A total of 8756 participants with genetic data were stratified according to the FLI, with 3310 having MAFLD at baseline. The follow-up was for a median of 8.4 (IQR 7.3–9.5) years. Variants in two genes (GCKR and HSD17B13) were associated with prevalent MAFLD (p < 0.05); PNPLA3, TM6SF2, LYPLAL1, and MBOAT7 were not. PNPLA3, TM6SF2, HSD17B13, GCKR, and LYPLAL1 were not associated with major adverse cardiovascular events (MACEs) or mortality in the overall cohort or in participants with MAFLD during the follow-up (all p > 0.05). Within the MAFLD group, homozygosity for the rs641738 C > T variant in the MBOAT7 gene was associated with a reduced risk of MACEs (HR 0.68 [95% CI 0.48–0.97]), but not all-cause mortality (HR 1.14 [95% CI 0.89–1.47]). This protective association remained significant after adjusting for multiple key covariates (aHR 0.64 [95% CI 0.44–0.92]). The results were similar when using the metabolic dysfunction-associated steatotic liver disease definition rather than MAFLD. Conclusions: The rs641738 C > T variant in MBOAT7 may confer protection against MACEs in older adults with MAFLD, independent of other clinical risk factors. Further validation using external cohorts is needed. Full article

Introduction: A validated clinical decision tool predictive of favorable functional outcomes following endovascular thrombectomy (EVT) in acute ischemic stroke (AIS) remains elusive. We performed a retrospective case series of patients at our regional Comprehensive Stroke Center, over a four-year period, who have undergone EVT to elucidate patient characteristics and factors associated with a favorable functional outcome after EVT. Methods: We reviewed all cases of EVT at our institution between February 2018 and February 2022 in the extended time window from 6–24 h. Demographic, clinical, imaging, and procedure co-variates were included. A favorable clinical outcome was defined as a modified Rankin scale of 0–2. We included patients with M1 or internal carotid artery occlusion treated with EVT within 6–24 h after symptom onset. We used a univariate and multivariate logistic regression analysis to identify patient factors associated with a favorable clinical outcome at 90 days. Results: Our study included evaluation of 121 patients who underwent EVT at our comprehensive stroke center. Our analysis demonstrates that a higher recanalization score based on the modified Thrombolysis In Cerebral Infarction (mTICI) scale (2B-3) was a strong indicator of a favorable outcome (OR 7.33; CI 2.06–26.07; p = 0.0021). Our data also showed that a higher baseline National Institutes of Health Stroke Scale (NIHSS) score (p = 0.0095) and the presence of pre-existing hypertension (p = 0.0035) may also be predictors of an unfavorable outcome (mRS > 2) per our multivariate analysis. Conclusion: Patients without pre-existing hypertension had more favorable outcomes following EVT in the expanded time window. This is consistent with other multicenter data in the expanded time window that demonstrates greater odds of a poor outcome with elevated pre-, peri-, and post-endovascular-treatment blood pressure. Our data also demonstrate that the mTICI score is a strong predictor of favorable outcome, even after controlling for other variables. A lower baseline NIHSS at the time of thrombectomy may also indicate a favorable outcome. Furthermore, the presence of clinical or radiographic mismatch based on the Alberta Stroke Program Early Computed Tomography Score (ASPECTS) and NIHSS per DAWN and DEFUSE-3 criteria did not emerge as a predictor of favorable outcome, which is congruent with recent randomized controlled trials and meta-analyses. Full article

Background/Objective: Understanding how chronic conditions such as knee osteoarthritis (OA) and chronic obstructive pulmonary disease (COPD) influence long-term physical activity (PA) is essential for developing condition-specific rehabilitation strategies. This study aimed to examine whether baseline diagnoses of knee OA and COPD are independently associated with the trajectories of PA decline over five years in U.S. adults, informed by the disablement process model. Methods: We analyzed data from 855 adults aged ≥45 years enrolled in the Osteoarthritis Initiative (OAI). The participants were categorized into three baseline groups, control (n = 122), knee OA (n = 646), and COPD (n = 87), based on self-reports and prior clinical assessments. PA was measured annually for five years using the Physical Activity Scale for the Elderly (PASE). General linear mixed models assessed changes in PA over time, adjusting for demographic, behavioral, and clinical covariates. Results: Compared to the controls, participants with knee OA had a significant decline in PA over time (β = −6.62; 95% CI: −15.4 to −2.19; p = 0.014). Those with COPD experienced an even greater decline compared to the knee OA group (β = −11.2; 95% CI: −21.7 to −0.67; p = 0.037). These associations persisted after adjusting for age, sex, body mass index, comorbidities, and smoking. Conclusions: Baseline knee OA and COPD were independently associated with long-term reductions in PA. These findings underscore the importance of early, tailored rehabilitation strategies, particularly pulmonary rehabilitation, in preserving functional independence among older adults with chronic conditions. Full article

Background/Objectives: Conventional ketogenic diets, although effective for weight loss, often contain high total and saturated fat intake, which leads to increased low-density lipoprotein cholesterol (LDL-C). Thus, the Healthy Ketogenic Diet (HKD) was developed to address these concerns. It emphasizes calorie restriction, limiting net carbohydrate intake to 50 g per day, prioritizing unsaturated fats, and reducing saturated fat intake. However, adherence to the HKD remains a challenge in urban, time-constrained environments. Therefore, this pilot randomized controlled trial aimed to investigate the effects of Healthy Ketogenic Diet Ready-To-Eat (HKD-RTE) meals (provided for the first month only) versus HKD alone on weight loss and metabolic parameters among overweight adults. Methods: Multi-ethnic Asian adults (n = 50) with a body mass index (BMI) ≥ 27.5 kg/m² were randomized into the HKD-RTE group (n = 24) and the HKD group (n = 26). Both groups followed the HKD for six months, with the HKD-RTE group receiving HKD-RTE meals during the first month. Five in-person workshops and mobile health coaching through the Nutritionist Buddy Keto app helped to facilitate dietary adherence. The primary outcome was the change in body weight at 6 months. Linear regression was performed on the change from baseline for each continuous outcome, adjusting for demographics and relevant covariates. Logistic regression was performed on binary weight loss ≥ 5%, adjusting for demographics and relevant covariates. Results: In the HKD group, participants’ adherence to the 50 g net carbohydrate target was 15 days, while that in the HKD-RTE group was 19 days over a period of 30 days. Participants’ adherence to calorie targets was 21 days in the HKD group and 23 days in the HKD-RTE. The average compliance with the HKD-RTE meals provided in the HKD-RTE group was 55%. The HKD-RTE group experienced a greater percentage weight loss at 1 month (−4.8 ± 3.0% vs. −1.8 ± 6.2%), although this was not statistically significant. This trend continued up to 6 months, with the HKD-RTE group showing a greater percentage weight reduction (−8.6 ± 6.8% vs. −3.9 ± 8.6%; p = 0.092). At 6 months, the HKD-RTE group had a greater reduction in total cholesterol (−0.54 ± 0.76 mmol/L vs. −0.05 ± 0.56 mmol/L; p = 0.283) and LDL-C (−0.43 ± 0.67 mmol/L vs. −0.03 ± 0.52 mmol/L; p = 0.374) compared to the HKD group. Additionally, the HKD-RTE group exhibited greater reductions in systolic blood pressure (−8.3 ± 9.7 mmHg vs. −5.3 ± 11.0 mmHg), diastolic blood pressure (−7.7 ± 8.8 mmHg vs. −2.0 ± 7.0 mmHg), and HbA1c (−0.3 ± 0.5% vs. −0.1 ± 0.4%) than the HKD group (not statistically significant for any). Conclusions: Both HKD-RTE and HKD led to weight loss and improved metabolic profiles. The HKD-RTE group tended to show more favorable outcomes. Short-term HKD-RTE meal provision may enhance initial weight loss, with sustained long-term effects. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

Background/Objectives: Overt hypothyroidism during pregnancy has been linked to adverse outcomes, including preterm birth, low birth weight, and impaired fetal neurocognitive development. This study aimed to evaluate pregnancy complications in women with overt hypothyroidism (TSH ≥ 10) through a cross-sectional study. Methods: Data from 259,897 live-birth pregnancies (2013–2022) from Clalit Health Services (CHS) were analyzed. The study included all CHS-insured women aged ≥ 18 years with available TSH results during pregnancy. Overt hypothyroidism was defined as a mean TSH ≥ 10 mIU/L, while the euthyroid reference group had TSH levels < 4 mIU/L and no history of hypothyroidism or levothyroxine use. Cases of overt hypothyroidism were matched with 15 controls using propensity score-based matching. Covariates included maternal age, ethnicity, socioeconomic status, IVF use, recurrent pregnancy loss, and smoking. Pregnancy complications were compared between groups using descriptive statistics and univariate analysis. A quasi-Poisson regression model was used to assess complication risk in overt hypothyroidism versus matched controls. Results: The final analysis included 9125 euthyroid and 611 overt hypothyroid pregnancies, with comparable baseline characteristics between groups. No significant differences were found in maternal age, ethnicity, socioeconomic scores, IVF rates, recurrent pregnancy loss, diabetes, smoking, gestational age at delivery, or rates of preterm birth, pre-eclampsia, gestational diabetes, cesarean section, and intrauterine growth restriction. Overall, overt hypothyroidism was not associated with increased complications. Sensitivity analyses using maximum TSH levels during pregnancy showed a slightly elevated risk for pregnancy complications (IRR 1.1, CI 1.04–1.18; p = 0.002). Conclusions: Overt hypothyroidism was not associated with an increased risk of adverse pregnancy outcomes when adjusted for confounding factors, suggesting that treatment decisions should be made on an individual basis. Full article

Estimating heterogeneous treatment effects (HTEs) across multiple correlated outcomes poses significant challenges due to complex dependency structures and diverse data types. In this study, we propose a novel deep learning framework integrating empirical copula transformations with a CNN-LSTM (Convolutional Neural Networks and Long Short-Term Memory networks) architecture to capture nonlinear dependencies and temporal dynamics in multivariate treatment effect estimation. The empirical copula transformation, a rank-based nonparametric approach, preprocesses input covariates to better represent the underlying joint distributions before modeling. We compare this method with a baseline CNN-LSTM model lacking copula preprocessing and a nonparametric tree-based approach, the Causal Forest, grounded in generalized random forests for HTE estimation. Our framework accommodates continuous, count, and censored survival outcomes simultaneously through a multitask learning setup with customized loss functions, including Cox partial likelihood for survival data. We evaluate model performance under varying treatment perturbation rates via extensive simulation studies, demonstrating that the Empirical Copula CNN-LSTM achieves superior accuracy and robustness in average treatment effect (ATE) and conditional average treatment effect (CATE) estimation. These results highlight the potential of copula-based deep learning models for causal inference in complex multivariate settings, offering valuable insights for personalized treatment strategies. Full article

As shared micromobility grows quickly in metropolitan settings, e-scooter safety issues have become more urgent. This paper uses a Bayesian hierarchical model applied to census block groups in several Texas metropolitan areas to construct a spatial risk assessment methodology for e-scooter crashes. Based on crash statistics from 2018 to 2024, we develop a severity-weighted crash risk index and combine it with variables related to land use, transportation, demographics, economics, and other factors. The model comprises a geographically structured random effect based on a Conditional Autoregressive (CAR) model, which accounts for residual spatial clustering after capture. It also includes fixed effects for covariates such as car ownership and nightlife density, as well as regional random intercepts to account for city-level heterogeneity. Markov Chain Monte Carlo is used for model fitting; evaluation reveals robust spatial calibration and predictive ability. The following key predictors are statistically significant: a higher share of working-age residents shows a positive association with crash frequency (incidence rate ratio (IRR): ≈1.55 per +10% population aged 18–64), as does a greater proportion of car-free households (IRR ≈ 1.20). In the built environment, entertainment-related employment density is strongly linked to elevated risk (IRR ≈ 1.37), and high intersection density similarly increases crash risk (IRR ≈ 1.32). In contrast, higher residential housing density has a protective effect (IRR ≈ 0.78), correlating with fewer crashes. Additionally, a sensitivity study reveals that the risk index is responsive to policy scenarios, including reducing car ownership or increasing employment density, and is sensitive to varying crash intensity weights. Results show notable collision hotspots near entertainment venues and central areas, as well as increased baseline risk in car-oriented urban environments. The results provide practical information for targeted initiatives to lower e-scooter collision risk and safety planning. Full article

Background: The atherogenic index of plasma (AIP), a prognostic indicator for cardiovascular disease, has not been fully explored in relation to clinical outcomes in patients receiving peritoneal dialysis. This study aims to elucidate the relationship between baseline AIP levels and all-cause mortality, cardiovascular mortality, and the peritonitis risk in this population. Methods: This retrospective cohort study included incident peritoneal dialysis patients in our center from 1 January 2006 through 31 December 2021. The end of the follow-up time was 31 December 2023. The participants were stratified by baseline AIP levels. Kaplan–Meier curves, Cox regression analyses, and subgroup analyses were used to evaluate associations with clinical outcomes. Results: The average age of the 2460 participants in this study was 45.9 years, and 1456 (59.2%) of them were men. Diabetic nephropathy (19.5%) was the second most common kidney disease, after primary glomerulonephritis (60.8%). The higher AIP tertile group was significantly associated with increased risks of all-cause mortality, cardiovascular mortality, and peritonitis compared to the lowest AIP group, as evidenced by the Kaplan–Meier curves and the multivariate analyses. Continuous AIP levels also showed a positive correlation with the all-cause mortality and peritonitis risk, even after controlling for covariates. Conclusions: Our study highlights AIP as a predictive marker for adverse outcomes in PD patients, emphasizing its potential utility in risk stratification and clinical management. Full article