Castaneda, Regina

Background/Objectives: Individuals with type 2 diabetes (T2D) achieve less total body weight loss (TBWL) with obesity medications compared to those without T2D. The individualized metabolic surgery (IMS) score, originally developed to predict T2D remission after bariatric surgery, inversely correlates with TBWL response to semaglutide. IMS reflects T2D severity, incorporating HbA1c and T2D duration and medication use. This study aims to evaluate TBWL with tirzepatide across IMS severity categories and identify predictors of response in a real-world cohort. Methods: This retrospective analysis included 717 adults with T2D using tirzepatide for overweight or obesity within the Mayo Clinic Health System. Patients were stratified by IMS severity (mild, moderate, severe) and quartiles. Primary endpoint: TBWL% at 15 months. Secondary endpoints: categorical thresholds (≥5%, ≥10%, ≥15%, ≥20%) and predictors of TBWL%. Linear mixed-effects models and regression models were employed. Results: At 15 months, TBWL was greater in mild versus severe IMS groups (14.8% vs. 11.0%, p = 0.015), with similar trends across quartiles. The proportion achieving ≥ 20% TBWL was nearly two-fold higher in mild versus severe IMS (27% vs. 14%, p = 0.03). Female sex independently predicted greater TBWL, whereas insulin use, higher T2D medication burden (particularly weight-promoting agents), and HbA1c > 7% were associated with less TBWL. Conclusions: Tirzepatide produced clinically meaningful TBWL across all IMS categories, although TBWL declined with increasing IMS severity. Glycemic control and T2D medication use emerged as strong predictors of TBWL. The IMS score may serve as a practical tool to anticipate weight-loss trajectories, guide personalized treatment decisions, and inform patient counseling.

Background: Peripheral artery disease (PAD) is a global health challenge. Advances in artificial intelligence (AI), such as large language models (LLMs) and chain-of-thought (CoT) reasoning, offer novel approaches for clinical recommendations. This study compared the readability and guideline adherence of responses from physicians and AI for a standardized PAD case. Methods: This cross-sectional study gathered responses from 30 specialized physicians (11 cardiologists, 19 vascular surgeons) across seven Latin American countries and 13 LLM systems (10 standard, three CoT). Both groups addressed diagnosis, treatment, risks, and prognosis; LLMs responded as vascular specialists. Responses were blindly evaluated with five validated Spanish readability indices and compared to the 2024 ACC/AHA multisocietal PAD guideline. Three experts scored guideline adherence; nonparametric tests were applied. Results: Guideline adherence did not differ significantly between physicians (median 5.8 [3.4–7.6]) and LLMs (7.3 [4.7–9.7], p = 0.169), though CoT-LLMs achieved the highest scores (9.7 [8.5–11.0]). LLMs more often recommended supervised exercise (84.6% vs 30.0%, p = 0.002) and revascularization for quality of life (69.2% vs 20.0%, p = 0.004), whereas physicians favored cilostazol (60.0% vs 30.8%, p = 0.104). LLM responses had lower Readability μ values (46.9 vs 51.4, p = 0.012). Inter-rater reliability was highest for CoT-LLMs (intraclass correlation coefficient [ICC] = 0.98) versus physicians (ICC = 0.76). Conclusion: LLM showed comparable guideline adherence to physicians although CoT models achieved the highest scores. The difference in physician and AI treatment preferences suggest the potential of AI as adjunct clinical tools and warrants further study.