Background: Currently, no large, nationwide studies have been conducted to analyze the demographic factors, underlying comorbidities, clinical outcomes, and health care utilization in rhabdomyolysis patients with and without acute kidney injury (AKI). Methods: We queried the National Inpatient Sample of Healthcare Cost and Utilization Project (HCUP) with patients with rhabdomyolysis from 2016 to 2018. The chi-squared test was used to compare categorical variables, and the adjusted Wald test was employed to compare quantitative variables. The logistic regression model was applied to calculate adjusted odds ratios (ORs) with 95% confidence intervals (95% CIs) to estimate the impact of AKI on outcomes in patients with rhabdomyolysis. Results: Among 111,085 rhabdomyolysis-related hospitalizations, a higher prevalence of AKI was noticed in older patients (mean age ± SD, 58.2 ± 21.6 vs. 53.8 ± 22.2), Medicare insurance (48.5% vs. 43.2%), and patients with a higher Charlson Comorbidity Index score (CCI 3–5, 15.1% vs. 5.5%). AKI was found to be independently associated with higher mortality (adjusted odds ratio [aOR] 3.33, 95% CI 2.33–4.75), longer hospital stays (adjusted difference 1.17 days, 95% CI: 1.00−1.34), and higher cost of hospital stay (adjusted difference $11,315.05, 95% CI: $9493.02–$13,137.07). Conclusions: AKI in patients hospitalized with rhabdomyolysis is related to adverse clinical outcomes and significant economic and survival burden.

Celiac disease (CD) is a chronic autoimmune disorder that affects the small intestine in genetically predisposed individuals. Previous studies have investigated the potential link between CD and cardiovascular disease (CVD); however, the findings have been inconsistent. We aimed to provide an updated review of the literature on the association between CD and CVD. PubMed was searched from inception to January 2023 using keywords including CD, cardiovascular disease, coronary artery disease, cardiac arrhythmia, heart failure, cardiomyopathy, and myocarditis. We summarized the results of the studies, including meta-analyses and original investigations, and presented them according to the different forms of CVD. Meta-analyses published in 2015 provided mixed results regarding the relationship between CD and CVD. However, subsequent original investigations have shed new light on this association. Recent studies indicate that individuals with CD are at a higher risk of developing overall CVD, including an increased risk of myocardial infarction and atrial fibrillation. However, the link between CD and stroke is less established. Further research is needed to determine the link between CD and other cardiac arrhythmias, such as ventricular arrhythmia. Moreover, the relationship between CD and cardiomyopathy or heart failure, as well as myopericarditis, remains ambiguous. CD patients have a lower prevalence of traditional cardiac risk factors, such as smoking, hypertension, hyperlipidemia, and obesity. Therefore, it is important to discover strategies to identify patients at risk and reduce the risk of CVD in CD populations. Lastly, it is unclear whether adherence to a gluten-free diet can diminish or increase the risk of CVD among individuals with CD, necessitating further research in this area. To fully comprehend the correlation between CD and CVD and to determine the optimal prevention strategies for CVD in individuals with CD, additional research is necessary.

Background: Alzheimer disease and related dementias (ADRD) rank as the sixth leading cause of death in the United States, underlining the importance of accurate ADRD risk prediction. While recent advancements in ADRD risk prediction have primarily relied on imaging analysis, not all patients undergo medical imaging before an ADRD diagnosis. Merging machine learning with claims data can reveal additional risk factors and uncover interconnections among diverse medical codes. Objective: The study aims to use graph neural networks (GNNs) with claim data for ADRD risk prediction. Addressing the lack of human-interpretable reasons behind these predictions, we introduce an innovative, self-explainable method to evaluate relationship importance and its influence on ADRD risk prediction. Methods: We used a variationally regularized encoder-decoder GNN (variational GNN [VGNN]) integrated with our proposed relation importance method for estimating ADRD likelihood. This self-explainable method can provide a feature-important explanation in the context of ADRD risk prediction, leveraging relational information within a graph. Three scenarios with 1-year, 2-year, and 3-year prediction windows were created to assess the model’s efficiency, respectively. Random forest (RF) and light gradient boost machine (LGBM) were used as baselines. By using this method, we further clarify the key relationships for ADRD risk prediction. Results: In scenario 1, the VGNN model showed area under the receiver operating characteristic (AUROC) scores of 0.7272 and 0.7480 for the small subset and the matched cohort data set. It outperforms RF and LGBM by 10.6% and 9.1%, respectively, on average. In scenario 2, it achieved AUROC scores of 0.7125 and 0.7281, surpassing the other models by 10.5% and 8.9%, respectively. Similarly, in scenario 3, AUROC scores of 0.7001 and 0.7187 were obtained, exceeding 10.1% and 8.5% than the baseline models, respectively. These results clearly demonstrate the significant superiority of the graph-based approach over the tree-based models (RF and LGBM) in predicting ADRD. Furthermore, the integration of the VGNN model and our relation importance interpretation could provide valuable insight into paired factors that may contribute to or delay ADRD progression. Conclusions: Using our innovative self-explainable method with claims data enhances ADRD risk prediction and provides insights into the impact of interconnected medical code relationships. This methodology not only enables ADRD risk modeling but also shows potential for other image analysis predictions using claims data.

INTRODUCTION: Liver disease is a significant public health problem in the United States, with notable racial disparities in mortality. This study examines liver disease mortality trends among Black and White populations during 1999–2020. METHODS: We used CDC WONDER database to ascertain liver disease age-standardized mortality rates in Black and White Americans. Annual percent change was calculated. Age-standardized absolute rate difference and rate ratios were computed by subtracting and dividing the White population's rate from that of the Black population. RESULTS: Liver diseases accounted for 171,627 Black and 1,314,903 White deaths during 1999–2020. Age-standardized mortality rates for Blacks decreased from 22.5 to 20.1 per 100,000 person-years (annual percentage change −0.4%, −0.6% to −0.2%), whereas an increase was observed for Whites, from 17.9 to 25.3 per 100,000 person-years (annual percentage change 1.4%, 1.4% to 1.7%). The rate ratio decreased from 1.26 (1.22–1.29) in 1999 to 0.79 (0.78–0.81) in 2020. This pattern was evident in all census regions, more pronounced among the younger (age 25–64 years) than older (age 65+ years) population and observed across different urbanization levels. The pattern may be attributable to increasing alcohol-related liver disease and metabolic dysfunction–associated steatotic liver disease–related deaths in Whites and tapering in viral hepatitis and primary liver cancer–related deaths in Blacks. Despite notable improvement, racial disparities persist in primary liver cancer and viral hepatitis among the Black population. DISCUSSION: The rise in alcohol-related liver disease and metabolic dysfunction–associated steatotic liver disease–related deaths among Whites, and enduring liver cancer and viral hepatitis disparities in the Black population, underscores the urgent need for tailored public health interventions.

Background and Aim: Effective clinical event classification is essential for clinical research and quality improvement. The validation of artificial intelligence (AI) models like Generative Pre‐trained Transformer 4 (GPT‐4) for this task and comparison with conventional methods remains unexplored.Methods: We evaluated the performance of the GPT‐4 model for classifying gastrointestinal (GI) bleeding episodes from 200 medical discharge summaries and compared the results with human review and an International Classification of Diseases (ICD) code‐based system. The analysis included accuracy, sensitivity, and specificity evaluation, using ground truth determined by physician reviewers.Results: GPT‐4 exhibited an accuracy of 94.4% in identifying GI bleeding occurrences, outperforming ICD codes (accuracy 63.5%, P < 0.001). GPT‐4's accuracy was either slightly lower or statistically similar to individual human reviewers (Reviewer 1: 98.5%, P < 0.001; Reviewer 2: 90.8%, P = 0.170). For location classification, GPT‐4 achieved accuracies of 81.7% and 83.5% for confirmed and probable GI bleeding locations, respectively, with figures that were either slightly lower or comparable with those of human reviewers. GPT‐4 was highly efficient, analyzing the dataset in 12.7 min at a cost of 21.2 USD, whereas human reviewers required 8–9 h each.Conclusion: Our study indicates GPT‐4 offers a reliable, cost‐efficient, and faster alternative to current clinical event classification methods, outperforming the conventional ICD coding system and performing comparably to individual expert human reviewers. Its implementation could facilitate more accurate and granular clinical research and quality audits. Future research should explore scalability, prompt and model tuning, and ethical implications of high‐performance AI models in clinical data processing.