Delray Medical Center

<b>Conclusions:</b> LAIs, especially SG formulations, are associated with reduced rehospitalization in BD-I compared to OAs, supporting their broader use to improve adherence and reduce readmissions.

565 Background: Multidisciplinary reviews (MDR) can significantly impact the management of oncologic patients, yet these are often underutilized. We previously presented more than 400 anonymized oncologic cases, including genitourinary (GU) cancer cases, to a MDR panel consisting of specialists belonging to medical oncology, surgical oncology, and radiation oncology. Here, we compare MDR recommendations to those produced by 3 different foundational AI models. Methods: We selected 35 complex GU cancer cases reviewed by MDR panels between 2020 and 2021 from a larger database that included several tumor types. These were then evaluated by OpenAI’s ChatGPT 4.5, Anthropic’s Claude Opus 4, and Google’s Gemini Ultra using PrecisCa’s proprietary prompting method. Recommendations from each system were scored on a 1-5 scale (with 5 being the highest) for completeness, reasoning, clarity, menu of options, recency, and relevance, and compared with those from the MDR panel. A maximum score of 30 points per scenario and 1,050 points overall was possible. Final AI recommendations were also compared with current National Comprehensive Cancer Network (NCCN) guidelines. Comparison in reverse (i.e., additional AI options that the experts had missed) was not conducted due to interval treatment recommendation changes in the preceding 4 years. Results: Patient characteristics, histology, and aggregate competence scores are shown (Table 1). Across all AI models, performance was the best in cases involving testicular cancer and worst in bladder cancer cases. For testicular cancer cases, recency and relevance scores were the highest while scores for reasoning, clarity, and menu of options were the worst. For bladder cancer cases, clarity scores were the highest, and recency the worst. Overall, AI systems excelled in relevance, but less so in completeness and recency. While there was some variation in the concordance and competence ratings from the 3 AI models, there was good concordance with expert opinion for all of them. Discordant cases revealed minor differences that would not have significantly impacted patient management otherwise. Conclusions: This study demonstrates a high degree of concordance between 3 leading AI models and expert panel decisions for common, complex GU cancer clinical scenarios. The findings show that it is not premature to incorporate AI as a decision support tool, in conjunction with human specialists, in daily practice. Patient characteristics, histology, and aggregate competence scores (n=35). Median Age (Range) 52.5 (25-80) Histology Bladder 7 (20%) Kidney 11 (31.4%) Prostate 15 (42.9%) Testicular 2 (5.7%) Aggregate/Median Competence Scores (Range) ChatGPT 4.5 880/23.5 (17-30) Claude Opus 4 931/23.5 (17-30) Gemini Ultra 889/24 (18-30)

Introduction: Liver diseases are major causes of mortality, and their association with depression remains underexplored. Understanding this relationship is essential in identifying high-risk populations and developing targeted public health interventions.Aims: This study aims to analyze mortality trends and demographic disparities in liver disease with depression as a contributing cause, using the Centers for Disease Control and Prevention (CDC) Multiple Cause of Death (MCD) database (1999-2020).Methodology: A retrospective observational study was conducted using the CDC MCD database to assess mortality trends in individuals aged 25 years and older in the United States from 1999 to 2020. The study included deaths where liver disease (ICD-10: K70-K76) was listed as the underlying cause and depression (ICD-10: F32) as a contributing cause. Data were analyzed by age, gender, race, geographic region, and place of death. Age-adjusted mortality rates (AAMR) and annual percentage change (APC) were calculated.Results: A total of 3,945 deaths were recorded. The AAMR initially increased (+8.25% APC from 1999 to 2007) and kept increasing slightly (+8.41% APC from 2010 to 2020). The highest mortality was observed in males (N = 2075, 52.6%), White individuals (N = 3647, 92.4%), and metropolitan regions (N = 3142, 79.7%). Temporal trends showed a higher AAMR in females from 2011 to 2020 (+11.99% APC) compared to 1999-2006 (+11.94%).Conclusions: Overall, AAMR is trending upward. Our findings emphasize the need for targeted prevention strategies and improved healthcare access across all demographics.

Background: Pharmacogenomic assisted prescribing of medications utilizes individual genetic information to identify drug-gene interactions. We aimed to assess potential pharmacogenomic drug-gene interactions in geriatric emergency department (ED) patients that have sustained a fall. Methods: This was a prospective study involving 25 older adult ED patients with fall related injury. Data collected included current medications, demographics and mechanism of injury. All patients provided a DNA sample for pharmacogenomic testing, MatchMyMeds (DNA Labs, Boca Raton, FL) which assessed genetic data for 23 enzyme systems and reports on potential drug-gene interactions for 134 medications. Each patients medications were reviewed against their pharmacogenomic report and categorized as Green (go), Yellow (caution) or Red (stop) based on their genetic information and published interactions by the Clinical Pharmacogenetics Implementation Consortium (CPIC), Dutch Pharmacogenetics Working Group (DPWG) and Food and Drug Administration-approved drug label information. The main study outcome was pharmacogenomic drug-gene interactions. Results: Of the 25 patients enrolled (median age, 81 years, IQR: 76-85), 68% were female. Patients were taking a median of 8 medications (IQR: 5-11). The most common types were antihypertensives, statins, anticoagulants, and anti-platelet medications. Significant drug-gene interactions (Yellow or Red) were identified in 14/25 (56%) patients. Further, 6/25 (24%) had one or more potentially serious (Red) interactions identified. Conclusions: In geriatric ED patients with a fall-related injury, a majority have a significant pharmacogenomic drug-gene interactions. DNA testing identifies these interactions and can assist with pharmacogenomic-guided medication prescribing which may decrease ADEs and improve clinical outcomes.

ABSTRACT Objective To compare outcomes between geriatric andnon-geriatric patients with traumatic brain injury (TBI) transferred to traumacenter and effects of anticoagulants/antiplatelets (AC/AP) and reversaltherapy. Methods A retrospective review of 1,118 patients with TBI transferred from acute care facilities tolevel 1 trauma center compared in groups: geriatric versus non-geriatric,geriatric with AC/AP therapy versus without, and geriatric AC/AP with AC/APreversal therapy versus without. Results Patients with TBI constituted 54.4% oftrauma transfers. Mean transfer time was 3.9 h. Propensity matched byInjury Severity Score and Abbreviated Injury Score (AIS) head geriatriccompared to non-geriatric patients had more AC/AP use (53.9% vs 8.8%), repeathead computed tomography (93.7% vs 86.1%), intensive care unit (ICU) admissions(57.4% vs 45.7%) and mortality (9.8% vs 3.2%), all p < 0.004. Patients onAC/AP versus without had more ICU admissions (69.1% vs 51.8%, p < 0.001).Patients with AC/AP reversals compared to without reversals had more AIS head 5(32.0% vs 13.1%), brain surgeries (17.8% vs 3.5%) and ICU admissions (84.8% vs57.1%), all p < 0.001. Conclusion TBI constituted half of trauma transfers and10% required surgery. Based on higher ICU admissions, mortality, and prevalenceof AC/AP therapy requiring reversal, geriatric patients with TBI onanticoagulants/antiplatelets should be considered for direct trauma centeradmission.

To determine the factors that might limit Hispanic patients from participating in dermatological clinical trials. From January 2022 to July 2022, we administered a 31-item, in-person questionnaire to patients recruited in the waiting area of the Caridad Center, one of the largest free clinics in the United States with a predominately Hispanic population, and a nearby private primary care clinic. Overall, Hispanic patients agreed significantly more with statements in the domain of attitude and behavioral beliefs compared to non-Hispanic survey respondents. The Hispanic ethnicity was associated with increased odds of agreeing with the following statements: "My community would really benefit from skin cancer clinical trials" (OR=0.52; 95% CI 0.30, 0.92), "My participation in a skin cancer study would be very good" (OR=0.59; 95% CI 0.35, 0.99), and "I like to do good for others" (OR=0.41; 95% CI 0.22, 0.77). While the United States population is composed of 18.5% Hispanics, they only account for 1% of patients enrolled in clinical trials. This study helps identify potential motivational factors for Hispanic patients to participate in skin cancer clinical trials.