Aims Study the treatment gap of guideline-indicated therapies in people with T2D and atherosclerotic cardiovascular disease (ASCVD) or heart failure (HF) or chronic kidney disease (CKD). Methods We extracted prescription history from 2005 to 2025 from a national dataset, a community-based health system, and an academic center. We assessed treatment gap (current and ever) within four subgroups defined using American Diabetes Association Standards of Care indications for SGLT2i and GLP-1RA use. Results We identified 6,951,624 people in the national dataset, 58,390 people at the community-based health system, and 15,235 people at the academic center. The current treatment gaps among people with ASCVD (without HF or CKD) were 72%, 67%, and 49%; with ASCVD and HF or CKD3 were 73%, 71%, and 55%; with CKD3 or HF without ASCVD were 75%, 71%, and 65%; with CKD4/5 were 87%, 89%, and 74% within the national dataset, community-based health system, and academic health system, respectively. The ever-prescription rates ranged from 23% to 39%, 30%-47%, 42%-64% within the national dataset, community-based health system, and academic center, respectively. Discussion Over half the population never received an indicated cardio-kidney protective prescription, and two-thirds lack a current prescription. These gaps were substantial across all systems; however, lowest at the academic center.

Objective: To conduct a pragmatic, randomized controlled trial (RCT) comparing effectiveness of six Registered Dietician-led Medical Nutrition Therapy (MNT) sessions to six virtual, hands-on Culinary Medicine (CM) sessions for improving glycemic control among patients with uncontrolled diabetes in a safety-net healthcare system. Research Design and Methods: Adults (age ≥18) with type 2 diabetes and HbA1c ≥7.0% were eligible. We assessed within and between group changes in HbA1c and Mediterranean Diet score (MEDI-LITE) using difference in differences analyses adjusted for the number of sessions completed. Results: 79 participants were randomized to either CM classes or health system MNT visits (43 MNT; 36 CM). Baseline characteristics were similar between groups. Participants with complete data at baseline and six months were included in HbA1c (N=47; 30 MNT and 17 CM) and MEDILITE (N=79; 43 MNT and 36 CM) analyses. HbA1c change over 6 months was -1.15% (p=0.01) in the MNT group and -0.55% (p=0.34) in the CM group. There was no difference in HbA1c change between groups (p=0.41). No significant within group (CM 0.75; p=0.08; MNT 0.11; p=0.78) or between group (p=0.28) differences in MEDILITE score were observed at 6 months. Conclusions: Despite the impact of COVID-19, participants in the diverse-format MNT intervention had clinically meaningful improvements in HbA1c at six months. Unmet recruitment and retention goals contributed to under-powered results. Additional RCTs evaluating the impact of CM on glycemic control and dietary measures are needed. Trial Registration: The trial was registered with http://ClinicalTrials.gov and given ID #NCT05019274. The Sponsor was University of Texas Southwestern Medical Center, and Responsible Party was Michael Edward Bowen, University of Texas Southwestern Medical Center. The Study Start was August 9, 2021 (with Trial Registration August 23, 2021) and Study Completion December 31, 2023. Article Highlights (127/130 words): · Why did we undertake this study? The effectiveness of CM compared with MNT on diabetes outcomes in resource limited settings is unknown. · What is the specific question(s) we wanted to answer? What is the comparative effectiveness of Culinary Medicine to RD-led MNT visits on glycemic control in patients with uncontrolled type 2 diabetes? · What did we find? Clinically significant reductions in HbA1c were observed in the MNT group. There was no difference in HbA1c change between groups (p=0.41). No significant within or between group changes in MEDILITE score were observed at 6 months. · What are the implications of our findings? Despite the shift to virtual format due to COVID-19, MNT participants had clinically meaningful improvements. Additional RCTs evaluating the impact of CM on glycemic control are needed.

Objective:Treatment guidelines can improve population health; however, their implementation within electronic health records (EHRs) can be challenging. We aimed to create an implementable framework using the American Diabetes Association (ADA) Standards of Care (SOC) for people with type 2 diabetes and cardiovascular or renal disease as an example. Materials and Methods:A multidisciplinary team used agile methods to translate the text-based ADA SOC into structured elements within the EHR, including logic-driven algorithms and ontology groupers for diagnoses, laboratory values, and medications, leveraging standard terminologies such as SNOMED CT, LOINC, and RxNorm. Results:The structured elements were used to implement 3 tools in the EHR: a real-time patient registry and 2 clinical decision support (CDS) instruments. The real-time registry enables dynamic, ongoing identification of patients eligible for guideline-directed medical therapy, supports more advanced analytics, and can be filtered to evaluate treatment gaps at the population and individual provider levels. The CDS tools allow clinicians to address these gaps directly within their EHR workflows. Discussion:Transforming clinical guidelines into executable constructs within the EHR is feasible but remains complex and labor-intensive. Broader and more consistent implementation could be achieved if guideline organizations provided technical frameworks, regular updates (through addenda or shared interfaces), and collaborated with EHR vendors to support the distribution and maintenance of implementable algorithms. Conclusion:The integration of executable logic into clinical guidelines, using deterministic frameworks such as Unified Modeling Language and standardized ontologies, would simplify guideline implementation across EHR platforms.

Background Repeat blood pressure (BP) measurements help ensure accurate identification of controlled versus uncontrolled BP. Within the Department of Medicine (DOM), we aimed to improve the rate of repeat BP measurement when the initial reading was ≥140/90 mmHg from the baseline of 40% to 50% between September 2022 and August 2023. Methods A DOM Quality Committee, with representatives from each division, led a centralized improvement effort to create a common data infrastructure, electronic dashboard for local use, feedback of data to clinical leaders, and educational materials for clinic use. Control and run charts were used to analyze the impact of repeat BP measurements on the process and outcome measures. Results The 61 DOM clinics completed a total of 273,704 patient encounters between September 2022 and August 2023. A total of 74,614 encounters had an initial high BP reading ≥140/90 mmHg. In these encounters, the rate of repeat BP measurement increased from a mean 41% to 61% and the BP control (<140/90 mmHg) rate increased from a mean 74% to 78%. Similar improvements were seen in the subgroup with a known diagnosis of hypertension. In addition, the percentage of encounters reclassified from uncontrolled to controlled BP (<140/90 mmHg) upon repeating the BP remained relatively stable with a median reclassification rate of 38%. Conclusion This centralized, department-level intervention increased rates of repeat BP measurement. Improvement in BP control was observed prior to the implementation of interventions and continued to improve after. Using a system-level approach to quality improvement with centralized infrastructure, we facilitated changes in diverse clinics to improve clinical care.

Dietary interventions for disease prevention have been well studied, yet standard American diets often fall short. Limited culinary skills and nutritional literacy are key contributors. Shared medical appointments (SMAs) with culinary education offer one solution to enhance culinary and nutrition literacy. In our model, patients were recruited from the University of Texas Southwestern Culinary Medicine Clinic to participate in a culinary medicine-focused SMA program located in local church kitchens in Dallas, TX including 6 classes over 2 months. Classes, led by a physician and culinary dietitian, included goal-setting, culinary skill demonstration, and supervised cooking. Classes were billed as primary care visits through patients' insurance. Health records and patient reported data were collected to assess feasibility. Sixty patients from four cohorts of SMAs had a 75% average attendance. Patients were predominantly Black (55%) and female (87%). Hypertension, diabetes, and obesity were the most common referral diagnoses. Qualitative telephone interviews (n = 18) reveal that co-learning new skills with peers is an important contributor to patient engagement. In conclusion, culinary medicine-focused SMAs are a feasible approach to deliver culinary nutrition education, demonstrate high levels of engagement and retention, and lay the foundation for a financially sustainable model.

BACKGROUND:Housing wealth can be leveraged to maintain economic security when expenses exceed income, allowing households flexibility when managing a new chronic disease diagnosis. We linked housing and electronic health record (EHR) data to examine how housing wealth and stability relate to type 2 diabetes (T2D) outcomes. METHODS:EHR data from patients diagnosed with T2D were linked to housing data (tenure, foreclosure, home equity, reverse mortgage, and loan-to-value ratio) using residential address. Multinomial logistic regression models were used to estimate associations between housing variables measured in the year before T2D diagnosis and glycemic control a year or more after T2D diagnosis. RESULTS:Among 5810 patients with T2D and complete housing data, patients with more home equity [relative risk ratio (rrr)=0.52, 95% CI: 0.323-0.838, P<0.001] were less likely to experience HbA1c >9% 1 year after diagnosis, and owners who were actively extracting home equity through a reverse mortgage (rrr=2.137, 95% CI: 0.008-1.511, P=0.048) were also more likely to have HbA1c >9% compared with patients with HbA1c<6.5%. Homeowners were less likely than renters to experience HbA1c >9% (rrr=0.798, 95% CI: 0.672-0.948, P=0.010). CONCLUSION:Patients diagnosed with T2D who had more housing wealth were less likely to experience challenges with glycemic control after diagnosis.

Purpose This study explores patient experience in dietary behavior change after nutrition and culinary medicine interventions.Design The qualitative study uses in-depth, semi-structured interviews and thematic analysis.Setting Researchers collected participant feedback after nutrition interventions in an urban, safety-net health clinic.Subjects Twenty-six adults with uncontrolled type 2 diabetes participated in nutrition or culinary medicine interventions and follow-up interviews.Method Study team members completed phone interviews focused on understanding support, challenges, and barriers during nutrition interventions for dietary change. Interviews were recorded, transcribed, and coded using NVivo software. Data analysis based on size and distribution of code applications led to thematic content and patterns of experience.Results Two key lessons emerged: (1) Participants valued practical nutrition, culinary, and technical support from the nutrition and research team members. Participants appreciated how team members alleviated doubts and filled knowledge gaps through non-judgmental listening and motivation that emphasized flexibility. (2) Participants valued personalized support to overcome barriers and challenges engaging in nutrition education and dietary change. Barriers included food costs, childcare, technology, and competing health demands, and some of these could be overcome with tailored support.Conclusion Integrating medical nutrition therapy and culinary medicine alongside food access resources may address upstream determinants of diet-sensitive disease. Programs that emphasize social connection and support, cultural relevance, and flexibility may be especially effective in safety-net settings.

Introduction and Objective: Large gaps persist in guideline-indicated prescription of cardiorenal protective medications (CRPM), namely SGLT2i and GLP-1RA, in people with T2D and cardiorenal disease, despite strong data and guidance for their use. Methods: We evaluated the treatment gap (Jan 2019-Dec 2024) in prescribing CRPM to people with T2D and cardiorenal disease using an EHR data aggregation initiative (Cosmos by Epic Systems) spanning 283 health systems across 49 US states and the Middle East. Eligible patients (N=7,800,815) had T2D and received care from either endocrinology, cardiology, nephrology, or primary care since 2019 (first guidelines with CRPM). Eligibility subgroups were defined using ADA 2022 Standards of Care. Current and past prescriptions for CRPM were extracted. Results: Eligibility subgroups included: ASCVD (N=2,367,381) - ‘SGLT2i or GLP1RA’; HF or CKD stage 3 (N=1,815,645) - ‘SGLT2i Only’; ASCVD and HF or CKD stage 3 (N=2,636,753) - ‘SGLT2i primary’; CKD stage 4/5 (N=981,022) - ‘GLP1RA Only’. The ever prescribed treatment gap ranged from 66.4% (SGLT2i primary) to 80.5% (GLP-1RA only) (Fig 1A). The treatment gap was higher for currently prescribed across all subgroups, ranging from 73.5% to 86.8% (Fig 1B). Conclusion: Current CRPM treatment gap is >73%, five years after the guidelines incorporated these recommendations for people with T2D. S. Agarwal: None. Y.A. ElNakieb: None. M.A. Basit: Advisory Panel; Pfizer Inc. M.E. Bowen: Research Support; Boehringer-Ingelheim. K. Marble: None. C. Mai: None. J. Pak: None. I. Lingvay: Consultant; Abbvie, Altimmune, Amgen, Alveus Tx, Antag Tx, Astra Zeneca, Bayer, Betagenon AB, Bioio Inc., Biomea, Boehringer-Ingelheim, Carmot, Cytoki Pharma, Eli Lilly, Intercept, Janssen/J&J, Juvena, Keros Ther, Novo Nordisk, Pharmaventures, Pfizer, Regeneron, Roche, Sanofi, Shionogi, Source Bio, Structure Therapeutics, TARGET RWE, TERNS Pharma, The Comm Group, WebMD, and Zealand Pharma. Research Support; Novo Nordisk, Sanofi, Boehringer-Ingelheim. This study was supported by BI. BI had no role in the design, analysis or interpretation of the results in this study. BI was given the opportunity to review the manuscript for medical and scientific accuracy as it relates to BI substances, as well as intellectual property considerations.

Evidence-based, practical nutrition and cooking guidance is seen as a strategy to address rising chronic disease burden. However, this resource remains limited in health care settings due to lack of time, expertise, funding, and access to registered dietitian nutritionists (RDNs). To address this challenge at an academic medical center, the culinary medicine (CM) clinical service line was developed and piloted at a community clinic beginning in December 2022. This unique, billable service provided outpatient consultations with both a physician and a dietitian certified in CM. The pilot study focuses on the design and evaluation of the first 2.5 years after implementation of this novel service, specifically highlighting the patients referred to the clinic, the source of referrals, and how payers reimburse the CM service. The model was developed as an interprofessional three-arm CM clinical service line with phased implementation of three billable encounter types: electronic consults (physician to physician or RDN electronic consult), one-to-one clinic consults (patient sees physician, physician discusses with RDN, patient sees RDN), and shared medical appointments (about 10-16 patients with physician, RDN, and volunteers at a community center with a kitchen). This article provides analysis of the clinical encounter, scheduling, and billing data over 30 months for the novel one-to-one clinic consult implementation and includes description of patient demographics (age, sex, race or ethnicity), referral data, referral diagnoses, appointment scheduling, reimbursement, and participant and stakeholder experiences. Between December 2022 and May 2025, the CM clinic received 387 total referrals, with 199 completed new patient consults (54% completion rate). Primary care clinicians generated most of the referrals (88%, N=327). The mean patient age at referral was 54 years, and patients were mostly women (78%) and African American (62%). The top three referral diagnoses were hypertension, hyperlipidemia, and type 2 diabetes. The gross insurance collection rate was 99.7% for 267 initial and follow-up visits; however, the mean contractually adjusted rate as a percentage of the charge varied by payer mix, from 15.8% to 69.8%. Most visits (97%) were covered under Medicare and various managed health maintenance organization and preferred provider organization plans. Based on a follow-up survey, 92% of 49 responding patients were very satisfied or satisfied with their experience, and qualitative feedback from referring physician stakeholders described the need for CM to fill a gap in access to nutrition support for their patients. This pilot demonstrated proof of concept of a novel, insurance-reimbursable CM service line. Initial data show successful reimbursement across payer plan types for common health conditions impacted by diet. Future directions include increasing clinic capacity, understanding patient-level impacts on health behaviors and disease control, and exploring the downstream economic impacts of this service.

Introduction and Objective: The Dysglycemia Risk Score (DRISK) is a validated, EHR-based risk score to identify patients at high risk for undiagnosed dysglycemia (prediabetes and T2D). DRISK performs better than screening guidelines to detect prevalent, undiagnosed dysglycemia; however, its ability to predict future development of T2D is unknown. Methods: Participants in a T2D screening study, excluding those with T2D on baseline screening, were analyzed. DRISK score (range 0-28; components: age, race, BMI, hypertension, random blood glucose (RBG)) was calculated from EHR data. Incident T2D was defined using a validated, EHR computable phenotype (2 of 3: HbA1c > 6.5%, T2D diagnosis codes; antihyperglycemic medications) calculated after the initial screening visit until the patients’ last EHR encounter. We used the baseline DRISK score to predict incident T2D using a Cox proportional hazard model with censoring for death or loss to followup. We adjusted for baseline HbA1c to address potential confounding during followup. Results: A total of 502 individuals without T2D at baseline (mean age 48y; BMI 30 kg/m2; 70% female; 69% Hispanic, 22% Black; 35% hypertension; 31% prediabetes (HbA1c≥5.7%); mean DRISK score 9.5) were analyzed. Over a mean followup of 5.8 years, 12% progressed to T2D. Those having higher BMI, hypertension, prediabetes, and higher HbA1c, RBG and DRISK scores at baseline were more likely to develop T2D (p<0.05 for all). Patients with DRISK scores ≥10 were more likely to progress to T2D than those with DRISK scores <10 (HR=1.9, p<0.015). ADA and USPSTF screening guidelines (HR 1.4 and 1.3 respectively; p>0.05 for both) did not predict future development of T2D in this cohort. Conclusion: DRISK can identify individuals at high risk of progression to T2D and has greater prognostic value than commonly used screening guidelines. By utilizing routinely available, structured EHR data, DRISK may help identify patients at high risk of progressing to T2D within health systems. A. Mamun: None. M. McGuire: None. V. Merrill: None. S. Zhang: None. N.O. Santini: None. B. Moran: None. L. Meneghini: Employee; Sanofi. Stock/Shareholder; Sanofi. I. Lingvay: Consultant; Abbvie, Altimmune, Amgen, Alveus Tx, Antag Tx, Astra Zeneca, Bayer, Betagenon AB, Bioio Inc., Biomea, Boehringer-Ingelheim, Carmot, Cytoki Pharma, Eli Lilly, Intercept, Janssen/J&J, Juvena, Keros Ther, Novo Nordisk, Pharmaventures, Pfizer, Regeneron, Roche, Sanofi, Shionogi, Source Bio, Structure Therapeutics, TARGET RWE, TERNS Pharma, The Comm Group, WebMD, and Zealand Pharma. Research Support; Novo Nordisk, Sanofi, Boehringer-Ingelheim. E. Halm: None. M.E. Bowen: Research Support; Boehringer-Ingelheim. National Institute of Diabetes Digestive and Kidney Diseases at NIH (K23DK104065)

PurposeSodium glucose co-transporter-2 inhibitors (SGLT2is) and glucagon-like peptide-1 receptor agonists (GLP-1RAs) have demonstrated cardioprotective effects in people with type 2 diabetes and atherosclerotic cardiovascular disease (ASCVD). In this patient group, there is treatment equipoise, from the standpoint of cardiovascular effect between these medication classes; however, factors associated with prescribing are poorly characterized.MethodsWe performed a retrospective real-world analysis by creating an electronic health record registry of people with type 2 diabetes and ASCVD (without additional indications for a specific cardioprotective class) who received a prescription for either an SGLT2i or GLP-1RA. We analyzed patient-, provider-, and clinical encounter-related predictors of being prescribed an SGLT2i or GLP-1RA using univariable and multivariable logistic regression analysis.ResultsA total of 573 eligible patients received either SGLT2i (N = 274) or GLP-1RA (N = 299) between January 2019 and October 2024. Care in cardiology (OR = 4.78; 95% CI, 2.53–9.04) strongly predicted SGLT2i prescription. Care in endocrinology (OR = 0.40; 95% CI, 0.23–0.68), higher BMI (OR = 0.92; 95% CI, 0.88–0.95, per BMI unit), and a higher recent estimated glomerular filtration (OR = 0.98; 95% CI, 0.96–0.99, per eGFR unit) predicted GLP-1RA prescription. The area under the receiver operating characteristic curve of the model was 0.78.ConclusionPrescriber's specialty strongly determined the selection of cardioprotective agents. Treatment guidelines should provide more specific guidance regarding patient selection and consider the holistic benefits of each drug class beyond their cardiovascular protective effects.

INTRODUCTION:Undiagnosed diabetes is associated with lack of insurance, which decreases access to preventive care. During the COVID-19 pandemic, uninsured patients previously unknown to health systems were hospitalized. METHODS:This is a cross-sectional analysis of electronic health record data from patients with diabetes hospitalized with COVID-19 in a safety-net health system from June 2020 to December 2021, examining the association between payor status and incident diagnosis of diabetes. Incident diagnosis of diabetes was defined by excluding a prior known diagnosis of diabetes based on diagnosis codes, medications, and HgbA1c from the past 5 years. Regression analysis evaluated the association between payor status and incident diagnosis of diabetes. Data were analyzed in 2023. RESULTS:Among 872 patients with diabetes hospitalized with COVID-19, 24.0% were uninsured, 34.6% received county-funded charity coverage, 17.1% received Medicaid, and 24.3% received Medicare. The rate of incident diagnosis of diabetes in the total sample was 20.3%; incident diagnosis of diabetes was more common among the uninsured (30.1%) than among county-funded charity coverage (18.2%) and Medicare (11.3%) patients. After adjusting for age, gender, race/ethnicity, and BMI, uninsured patients had higher odds of incident diagnosis of diabetes (AOR=2.64; 95% CI=1.41, 4.92; p=0.002) than Medicare patients. Odds of incident diagnosis of diabetes were similar for county-funded charity coverage and Medicare patients. CONCLUSIONS:Uninsured patients had higher odds of incident diagnosis of diabetes during COVID-19 hospitalization that may have gone undetected without hospitalization. These findings reflect decreased access to preventive care and missed opportunities to screen for diabetes among the uninsured.

BACKGROUND:Family history-based risk assessment for hereditary breast and ovarian cancer is guideline-recommended but clinical implementation remains limited. This is likely, in part, because it adds to the limited time primary care providers (PCPs) have to implement all guideline-recommended care. METHODS:We adapted Family History Screening 7 (or FHS7), designed for administration by a PCP, for self-report by primary care patients. We used the Framework for Reporting Adaptation and Modifications to Evidence-based Implementation Strategies (FRAME) to guide the modifications. We conducted a pilot feasibility study of hereditary prevention program using the adapted risk-assessment tool and report results from the first year of the program (February 2023-March 2024). RESULTS:Feedback from clinical stakeholders and our literature review revealed that, while hereditary cancer risk assessment was a priority for the primary care setting, implementation by PCPs was not feasible. We therefore adapted FHS7 for patient self-report by separating double-barreled items and eliminating jargon, resulting in nine items- six with binary (yes/no) and three with numeric responses. Outcomes from pilot implementation of the adapted FHS7 (n=4,355) showed high completion rate (77% completed all items), with greater completion via MyChart than in-person (87% vs. 13%), and higher non-response for the three items with numeric responses compared to the six with binary responses. Overall, positivity rate of the adapted FHS7 was 36%. CONCLUSION:This paper describes our team's process of adapting the FHS7 questionnaire to retain the core function (evaluating specific family history of cancer information) while adapting to fit the clinical context. Preliminary implementation data suggest high completion rate in the primary care setting.

OBJECTIVE We derive and validate D-RISK, an electronic health record (EHR)-driven risk score to optimize and facilitate screening for undiagnosed dysglycemia (prediabetes + diabetes) in clinical practice. RESEARCH DESIGN AND METHODS We used retrospective EHR data (derivation sample) and a prospective diabetes screening study (validation sample) to develop D-RISK. Logistic regression with backward selection was used to predict dysglycemia (HbA1c ≥5.7%) using diabetes risk factors consistently captured in structured EHR data. Model coefficients were converted to a points-based risk score. We report discrimination, sensitivity, and specificity and compare D-RISK to the American Diabetes Association (ADA) risk test and the ADA and United States Preventive Services Task Force (USPSTF) screening guidelines. RESULTS The derivation cohort included 11,387 patients (mean age 48 years; 65% female; 42% Hispanic; 32% non-Hispanic Black; mean BMI 32; 29% with hypertension). D-RISK included age, race, BMI, hypertension, and random glucose. The area under curve (AUC) for the risk score was 0.75 (95% CI 0.74–0.76). In the validation screening study (n = 519), the AUC was 0.71 (95% CI 0.66–0.75) which was better than the ADA and USPSTF diabetes screening guidelines (AUC = 0.52 and AUC = 0.58, respectively; P < 0.001 for both). Discrimination was similar to the ADA risk test (AUC = 0.67) using patient-reported data to supplement EHR data, although D-RISK was more sensitive (75% vs. 61%) at the recommended screening thresholds. CONCLUSIONS Designed for use in EHR, D-RISK performs better than commonly used screening guidelines and risk scores and may help detect undiagnosed cases of dysglycemia in clinical practice.

Introduction: In people with T2D and preexisting ASCVD, either SGLT2i or GLP1RA are indicated by treatment guidelines to reduce MACE. We evaluated predictors of prescription of SGLT2i vs GLP1RA in a population eligible for either. Methods: An electronic health record (EHR) based registry was created to identify people with T2D and ASCVD who were indicated either a GLP1RA or SGLT2i for cardiorenal protection within a large, academic health system. Data pertaining to demographics, lab and imaging results, ICD9/10 diagnoses, prescriptions, provider and clinic characteristics were extracted. Eligible encounters occurred in a primary care, endocrinology, cardiology, or nephrology clinic between January 1, 2019 and August 23, 2023. For each eligible encounter where a drug was prescribed, the first treatment type (GLP1RA or SGLT2i) was determined based on medication history. We estimated a logistic regression using stepwise variable selection to identify a best-predicting model and forced the variables of age, sex, and race into the model. Results: A total of 315 patients with T2D and ASCVD were eligible for either treatment and were prescribed one of these medications: 142 were prescribed a GLP1RA and 173 were prescribed SGLT2i. Lower BMI was associated with use of SGLT2i (OR = 0.91, 95% CI 0.87-0.96), as was being an established patient (OR 2.32, 95% CI 1.14-4.72). Compared to treatment in a primary care setting, treatment in a cardiology clinic was strongly associated with prescription of SGLT2i (OR = 7.77, 95% CI 3.18-19.04), whereas treatment in endocrinology clinic was strongly associated with prescription of a GLP1RA (OR = 0.35, 95% CI 0.18-0.68). Area under the receiver operating characteristic curve for the model was 0.82. Conclusion: In a real-world dataset from a large academic center, the selection of guideline directed therapy for patients with T2D and ASCVD was strongly determined by the provider’s specialty, highlighting an important opportunity for education. Disclosure S. Agarwal: None. M.A. Basit: None. M.E. Bowen: Research Support; Boehringer-Ingelheim. D. Heitjan: Consultant; Bluejay Diagnostics, Medcognetics, Sebela, Abbott, Macrogenics, Guardant, Bristol-Myers Squibb Company, Gilead Sciences, Inc. C. Mai: None. K. Marble: None. Z. Xiang: None. I. Lingvay: Consultant; Altimmune, Astra Zeneca, Bayer, Biomea, Boehringer-Ingelheim, Carmot, Cytoki Pharma, Eli Lilly, Intercept, Janssen/J&J, Mannkind, Mediflix, Merck, Metsera, Novo Nordisk, Pharmaventures, Pfizer, Sanofi. Research Support; NovoNordisk, Sanofi, Mylan, Boehringer-Ingelheim. Consultant; TERNS Pharma, The Comm Group, Valeritas, WebMD, and Zealand Pharma. Funding This study was supported by Boehringer Ingelheim Pharmaceuticals, Inc. (BIPI) and Lilly USA, LLC. The authors meet criteria for authorship as recommended by the International Committee of Medical Journal Editors (ICMJE) and were fully responsible for all aspects of the trial and publication development.