Ark Medical Center

SpeakerRiddhi Modi, PhD, MPH, MMBS Associate Director in Global Clinical Trial Operations, Medical Writing and Disclosure, Merck & Co, Inc, Rahway, NJ

658 Background: Bladder cancer is the sixth most common malignancy in the United States and remains a significant contributor to cancer-related mortality. Despite diagnostic and therapeutic advances, comprehensive evaluation of long-term mortality trends by demographic and geographic factors remains limited. This study assessed national bladder cancer mortality patterns over a 25-year period. Methods: Age-adjusted mortality rates (AAMRs) for bladder cancer from 1999 to 2024 were obtained from the CDC WONDER database. Rates were calculated per 100,000 population using the U.S. standard population. Temporal trends were analyzed using Joinpoint regression to estimate annual percent change (APC) and average annual percent change (AAPC) with 95% confidence intervals (CI). Trends were examined by race/ethnicity, sex, age group, U.S. Census region, and urbanization level. Results: Overall bladder cancer mortality demonstrated a modest decline over the study period (AAPC: –0.26%; 95% CI: –0.34 to –0.18; p < 0.001). Mortality decreased among Hispanic (APC: –0.47%; 95% CI: –0.71 to –0.23) and Asian/Pacific Islander populations (APC: –0.57%; 95% CI: –0.86 to –0.28), while American Indian/Alaska Native populations showed a slight increase (APC: +0.19%). Black/African American populations demonstrated declining mortality until 2019 (APC: –0.98%) followed by a plateau. In 2024, Whites had the highest AAMR (17.90 per 100,000), followed by Black/African American (12.00), American Indian/Alaska Native (8.55), Hispanic (7.92), and Asian/Pacific Islander groups (5.95). Males exhibited an AAMR nearly four times higher than females in 2024 (27.63 vs. 7.04 per 100,000). Mortality increased with age, peaking among adults aged ≥85 years (63.80 per 100,000), followed by those aged 75–84 (24.82) and 65–74 years (6.73). Regionally, the Northeast experienced the greatest decline after 2012 (APC: –1.14%), whereas the South showed increasing mortality after 2019 (APC: +1.55%). Based on available urbanization data, non-metropolitan areas consistently had higher mortality compared to metropolitan regions. Conclusions: Bladder cancer mortality in the United States has declined modestly over the past two decades, though trends vary across race, sex, geography, age, and urbanization categories. Continued monitoring and targeted resource allocation may support improved outcomes in populations with persistently elevated mortality trends.

BackgroundDeep brain stimulation (DBS) is a treatment for dystonia, with most trials conducted in developed countries. Data from developing countries like Brazil are limited.ObjectiveTo evaluate the landscape of DBS for dystonia in Brazil, assessing motor outcomes compared with the existing literature.MethodsA retrospective multicenter cohort study was conducted via medical record review. Demographics and motor outcomes were collected and analyzed using the Burke-Fahn-Marsden Dystonia Rating Scale (BFMDRS) from patients across four of Brazil's five macro-regions.ResultsThe cohort included 60 patients (44.3% female), with DBS primarily targeting the globus pallidus internus (73.3%) or subthalamic nucleus (18.3%). The BFMDRS motor scores decreased from 63.0 ± 26.2 (n = 24) at baseline to 36.7 ± 24.6 at 1-year post-DBS (n = 22,p = 0.0018) and 43.6 ± 35.0 at the last assessment (n = 13,p = 0.0327).ConclusionThe use of DBS yielded significant, sustained motor improvements, consistent with developed countries, highlighting its feasibility and effectiveness in Brazil within diverse healthcare settings.

BACKGROUND: About one-fourth of ischemic strokes are recurrent. Finding a specific etiology facilitates targeted secondary prevention. The American Heart Association (AHA) Get-With-The-Guidelines-Stroke® Registry (GWTG-S) suggests more than 50% of patients are discharged with a cryptogenic or undocumented etiology. We sought to determine baseline characteristics associated with cryptogenic stroke and whether more thorough hospital investigation reduces cryptogenic classification. METHODS: In 2022, the AHA, along with HCA Healthcare and HCA Healthcare Foundation, designed and launched Getting to the Heart of Stroke TM (GTTHOS) in 10 HCA Healthcare advanced stroke centers to improve evidence-based stroke evaluation, promote neurology/cardiology collaboration, and better identify barriers to care. GTTHOS data from 2022-2024 were harvested from GWTG-S, noting baseline characteristics (demographics, insurance status, medical history, NIHSS) and utilization of three diagnostic tests: cervical carotid imaging, intracranial vascular imaging, and short-term cardiac rhythm monitoring. Multivariate analysis sought to associate baseline features and test utilization with cryptogenic vs. non-cryptogenic etiology. RESULTS: We identified 15,216 patients with cryptogenic (5,468, 35.94%) or non-cryptogenic (9,748, 64.06%) ischemic stroke. Cryptogenic patients had lower median age (69 vs. 72 years, p < 0.0001), more frequent vascular risk factors (hypertension, diabetes, dyslipidemia), and lower prevalence of heart failure or coronary disease (Table 1). Baseline differences were small and mostly nonsignificant when adjusted for covariates. Performing diagnostic tests was associated with higher likelihood of identifying a non-cryptogenic etiology (Table 2): intracranial vascular imaging (aOR = 1.24, p = 0.0146), carotid imaging (aOR = 1.67, p < 0.0001), and short-term cardiac rhythm monitoring (aOR = 1.23, p = 0.0004). Test utilization was highest in cryptogenic stroke. CONCLUSIONS: Performance of diagnostic tests (intracranial vascular imaging, carotid imaging, and short-term cardiac monitoring) was strongly associated with greater likelihood of identifying a non-cryptogenic stroke etiology. Cryptogenic patients were thoroughly, though not exhaustively, assessed with these tests, making it unlikely that cryptogenic strokes were simply under-tested. Opportunities exist for improved adherence to AHA acute and post-acute testing guidelines.

Cardiac amyloidosis is frequently overlooked, leading to delayed diagnosis and underestimation of its true impact on cardiac mortality. Using CDC WONDER (1999-2020), we identified U.S. decedents aged ≥ 25 years with amyloidosis (ICD-10 E85) as the underlying cause of death and at least one cardiac-related condition as a contributing cause. Age-adjusted mortality rates (AAMRs) per 100,000 population were calculated, and trends were analyzed using Joinpoint regression and autoregressive integrated moving average (ARIMA) forecasting through 2040. Among 16,673 deaths, the AAMR rose from 0.261 in 1999 to 0.608 in 2020, with inflection points in 2012 and 2017 and an overall annual increase of 3.96%. Mortality was higher in men (0.537 vs. 0.210) and Black individuals (0.83 vs. 0.32), with a sharp post-2017 rise, especially among Black decedents. Geographic disparities were also observed, with the highest rates in the Northeast and urban areas. Most deaths occurred in hospitals (43.2%) or at home (31.4%), and mortality rates peaked in those aged 85 and older. Forecasting models project continued increases in AAMR through 2040, reaching approximately 2.0 overall, with especially elevated rates among Black (≈ 5.9) and male (≈ 3.8) decedents. Cardiac mortality in amyloidosis has risen sharply since 2017, likely driven by improved ATTR-CM detection through non-biopsy imaging and guideline adoption. Disparities by sex, race, and geography persist, reflecting uneven diagnostic capacity concentrated in urban and Northeastern centers. Forecasts project continued increases, particularly among Black and male individuals, underscoring the need for more equitable access to diagnosis and treatment.

Abstract Objective To evaluate the ability of a natural language processing system to automatically reconstruct the SOFA score from unstructured clinical notes in patients with sepsis and validate its applicability in intensive care units. Materials and methods Retrospective study in the MIMIC-III database that included 284 adults with sepsis. The SOFA calculated with structured data was compared with the SOFA reconstructed by free text extraction. Clinical rules were applied for calculation at 24 h and 48 h. Variable completeness, severity reclassification, and association with hospital mortality were evaluated using logistic regression. Results Automated extraction increased the availability of critical variables (respiratory 33% to 100%, vasopressor 12% to 41%). The reconstructed SOFA increased by 3 points at 24 hours, reclassifying patients with high severity (SOFA ≥ 6) from 17% to 48% and SOFA ≥ 10 from 5% to 22%. Reconstructed scores remained associated with mortality at 24 h (OR 1.16, 95% CI 1.09-1.24) and at 48 h (OR 1.23, 95% CI 1.15-1.31), comparable to that based on structured data (p < 0.001). Discussion Automatic reconstruction of the SOFA from free text recovers information missing from structured fields, reducing underestimation of severity. Conclusion NLP approaches supported by large language models provide a more complete and clinically consistent SOFA score in sepsis when structured data are insufficient.

Cortical arousals are brief brain activations that disrupt sleep continuity and contribute to cardiovascular, cognitive, and behavioral impairments. Although polysomnography is the gold standard for arousal detection, its cost and complexity limit use in long-term or home-based monitoring. This study presents a noninvasive, machine learning–based framework for detecting cortical arousals using the RestEaze™ system, a leg-worn wearable that records multimodal physiological signals including accelerometry, gyroscope, photoplethysmography (PPG), and temperature. Across multiple methods tested, including logistic regression, XGBoost, and Random Forest classifiers, we found that features related to movement intensity were the most effective in identifying cortical arousals, while heart rate variability had a comparatively lower impact. The framework was evaluated in 14 children with attention-deficit/hyperactivity disorder (ADHD) undergoing assessment for restless leg syndrome–related sleep disruption. The Random Forest model achieved the best overall performance, with a ROC-AUC of 0.94 and an AUPRC of 0.55, substantially higher than the baseline prevalence of arousals (~ 0.07). For the arousal class specifically, it reached a precision of 0.57, recall of 0.78, and F1-score of 0.65. These findings support the feasibility of wearable-based machine learning for real-world arousal detection, demonstrated here in a pediatric ADHD cohort with sleep-related behavioral concerns.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-27739-7.

Abstract Background: Chronic kidney disease (CKD) is a leading global cause of morbidity and mortality, particularly in low- and middle-income countries (LMIC) where access to specialized laboratory tests is limited. Early detection is essential but often delayed due to reliance on serum creatinine-based estimated glomerular filtration rate (eGFR). Artificial intelligence (AI) offers opportunities for simple, sensitive screening models using routinely available variables. Methods: We trained and tested a low-cost machine learning algorithm in a multicenter Latin American dataset of 203,067 anonymized records to identify patients at risk of CKD, defined as an eGFR <60 mL/min/1.73m² (CKD-EPI 2021). Eight routinely available, non-invasive variables were used: age, sex, systolic and diastolic blood pressure, body mass index, hypertension, presence of type 2 diabetes (T2D), and diabetes duration (T2DD). To address the imbalance between CKD-positive and CKD-negative cases, oversampling techniques were applied before splitting the dataset into training (70%), validation (12%), and testing (18%). Using the Arkangel AutoML platform, 424 candidate models were generated, including decision trees, random forests, support vector machines, XGBoost, and deep neural networks. Models were prioritized based on predefined criteria: sensitivity >90%, followed by AUC, precision, specificity, and F1 score. Results: The final model was a decision tree trained in a non-stratified sample with the SMOTE augmentation technique. Sensitivity was 90.2%, specificity 92.7%, precision (PPV) 89%, and AUC 91.4%. Binary regression demonstrated the statistical relevance of all the model’s features in predicting CKD risk in our sample. SHAP analysis identified age and diabetes duration as the most influential features in the final ML model. Conclusions : A decision tree model trained with eight routine clinical variables accurately identified individuals at risk of CKD, achieving high sensitivity and balanced performance without requiring specialized tests. This approach is feasible for large-scale screening in low-resource settings and can be integrated into electronic health records to prioritize confirmatory diagnostics and timely care. It also represents one of the first approximations to CKD diagnosis using ML models trained exclusively on Latin American data.