Using large language model to guide patients to create efficient and comprehensive clinical care message.

OBJECTIVE: This study aims to investigate the feasibility of using Large Language Models (LLMs) to engage with patients at the time they are drafting a question to their healthcare providers, and generate pertinent follow-up questions that the patient can answer before sending their message, with the goal of ensuring that their healthcare provider receives all the information they need to safely and accurately answer the patient's question, eliminating back-and-forth messaging, and the associated delays and frustrations. METHODS: We collected a dataset of patient messages sent between January 1, 2022 to March 7, 2023 at Vanderbilt University Medical Center. Two internal medicine physicians identified 7 common scenarios. We used 3 LLMs to generate follow-up questions: (1) Comprehensive LLM Artificial Intelligence Responder (CLAIR): a locally fine-tuned LLM, (2) GPT4 with a simple prompt, and (3) GPT4 with a complex prompt. Five physicians rated them with the actual follow-ups written by healthcare providers on clarity, completeness, conciseness, and utility. RESULTS: For five scenarios, our CLAIR model had the best performance. The GPT4 model received higher scores for utility and completeness but lower scores for clarity and conciseness. CLAIR generated follow-up questions with similar clarity and conciseness as the actual follow-ups written by healthcare providers, with higher utility than healthcare providers and GPT4, and lower completeness than GPT4, but better than healthcare providers. CONCLUSION: LLMs can generate follow-up patient messages designed to clarify a medical question that compares favorably to those generated by healthcare providers.

Structure and Funding of Clinical Informatics Fellowships: A National Survey of Program Directors.

BACKGROUND: In 2011, the American Board of Medical Specialties established clinical informatics (CI) as a subspecialty in medicine, jointly administered by the American Board of Pathology and the American Board of Preventive Medicine. Subsequently, many institutions created CI fellowship training programs to meet the growing need for informaticists. Although many programs share similar features, there is considerable variation in program funding and administrative structures. OBJECTIVES: The aim of our study was to characterize CI fellowship program features, including governance structures, funding sources, and expenses. METHODS: We created a cross-sectional online REDCap survey with 44 items requesting information on program administration, fellows, administrative support, funding sources, and expenses. We surveyed program directors of programs accredited by the Accreditation Council for Graduate Medical Education between 2014 and 2021. RESULTS: We invited 54 program directors, of which 41 (76%) completed the survey. The average administrative support received was $27,732/year. Most programs (85.4%) were accredited to have two or more fellows per year. Programs were administratively housed under six departments: Internal Medicine (17; 41.5%), Pediatrics (7; 17.1%), Pathology (6; 14.6%), Family Medicine (6; 14.6%), Emergency Medicine (4; 9.8%), and Anesthesiology (1; 2.4%). Funding sources for CI fellowship program directors included: hospital or health systems (28.3%), clinical departments (28.3%), graduate medical education office (13.2%), biomedical informatics department (9.4%), hospital information technology (9.4%), research and grants (7.5%), and other sources (3.8%) that included philanthropy and external entities. CONCLUSION: CI fellowships have been established in leading academic and community health care systems across the country. Due to their unique training requirements, these programs require significant resources for education, administration, and recruitment. There continues to be considerable heterogeneity in funding models between programs. Our survey findings reinforce the need for reformed federal funding models for informatics practice and training.

A Systematic Approach to the Design and Implementation of Clinical Informatics Fellowship Programs.

Clinical Informatics (CI), a medical subspecialty since 2011, has grown from the initial four fellowship programs accredited by the Accreditation Council for Graduate Medical Education (ACGME) in 2014 to more than 50 and counting in the present day. In parallel, the literature guiding Clinical Informatics Fellowship training and the curriculum evolved from the original core content published in 2009 to the more recent CI Subspecialty Delineation of Practice and the updated ACGME Milestones 2.0 for CI. In this paper, we outline this evolution and its impact on CIF Curricula. We then propose a framework, specific processes, and tools to standardize the design and optimize the implementation of CIF programs.

Development and Validation of Inpatient Hypoglycemia Models Centered Around the Insulin Ordering Process.

BACKGROUND: The insulin ordering process is an opportunity to provide clinicians with hypoglycemia risk predictions, but few hypoglycemia models centered around the insulin ordering process exist. METHODS: We used data on adult patients, admitted in 2019 to non-ICU floors of a large teaching hospital, who had orders for subcutaneous insulin. Our outcome was hypoglycemia, defined as a blood glucose (BG) <70 mg/dL within 24 hours after ordering insulin. We trained and evaluated models to predict hypoglycemia at the time of placing an insulin order, using logistic regression, random forest, and extreme gradient boosting (XGBoost). We compared performance using area under the receiver operating characteristic curve (AUCs) and precision-recall curves. We determined recall at our goal precision of 0.30. RESULTS: Of 21 052 included insulin orders, 1839 (9%) were followed by a hypoglycemic event within 24 hours. Logistic regression, random forest, and XGBoost models had AUCs of 0.81, 0.80, and 0.79, and recall of 0.44, 0.49, and 0.32, respectively. The most significant predictor was the lowest BG value in the 24 hours preceding the order. Predictors related to the insulin order being placed at the time of the prediction were useful to the model but less important than the patient's history of BG values over time. CONCLUSIONS: Hypoglycemia within the next 24 hours can be predicted at the time an insulin order is placed, providing an opportunity to integrate decision support into the medication ordering process to make insulin therapy safer.

Clinician collaboration to improve clinical decision support: the Clickbusters initiative.

OBJECTIVE: We describe the Clickbusters initiative implemented at Vanderbilt University Medical Center (VUMC), which was designed to improve safety and quality and reduce burnout through the optimization of clinical decision support (CDS) alerts. MATERIALS AND METHODS: We developed a 10-step Clickbusting process and implemented a program that included a curriculum, CDS alert inventory, oversight process, and gamification. We carried out two 3-month rounds of the Clickbusters program at VUMC. We completed descriptive analyses of the changes made to alerts during the process, and of alert firing rates before and after the program. RESULTS: Prior to Clickbusters, VUMC had 419 CDS alerts in production, with 488 425 firings (42 982 interruptive) each week. After 2 rounds, the Clickbusters program resulted in detailed, comprehensive reviews of 84 CDS alerts and reduced the number of weekly alert firings by more than 70 000 (15.43%). In addition to the direct improvements in CDS, the initiative also increased user engagement and involvement in CDS. CONCLUSIONS: At VUMC, the Clickbusters program was successful in optimizing CDS alerts by reducing alert firings and resulting clicks. The program also involved more users in the process of evaluating and improving CDS and helped build a culture of continuous evaluation and improvement of clinical content in the electronic health record.

A Unified Approach to Clinical Informatics Education for Undergraduate and Graduate Medical Education.

Vanderbilt University Medical Center has adopted a unified approach to undergraduate and graduate clinical informatics education. Twenty-three learners have completed the course which is designed around four key activities: 1) didactic sessions 2) informatics history and physical where learners observe clinical areas, document workflows, identify a problem to solve and propose an informatics-informed solution 3) informatics clinic where learners are side-by-side with practicing clinical informaticians and 4) interactive learning activities where student groups work through case-based informatics problems with an informatics preceptor. These experiences are coupled with opportunities for asynchronous projects, reflections, and weekly assessments. The curriculum learning objectives are modeled after the clinical informatics fellowship curriculum. Feedback suggests the course is achieving the planned goals. It is a feasible model for other institutions and addresses knowledge gaps in clinical informatics for undergraduate and graduate medical education learners.

International Comparison of Six Basic eHealth Indicators Across 14 Countries: An eHealth Benchmarking Study.

BACKGROUND: Many countries adopt eHealth applications to support patient-centered care. Through information exchange, these eHealth applications may overcome institutional data silos and support holistic and ubiquitous (regional or national) information logistics. Available eHealth indicators mostly describe usage and acceptance of eHealth in a country. The eHealth indicators focusing on the cross-institutional availability of patient-related information for health care professionals, patients, and care givers are rare. OBJECTIVES: This study aims to present eHealth indicators on cross-institutional availability of relevant patient data for health care professionals, as well as for patients and their caregivers across 14 countries (Argentina, Australia, Austria, Finland, Germany, Hong Kong as a special administrative region of China, Israel, Japan, Jordan, Kenya, South Korea, Sweden, Turkey, and the United States) to compare our indicators and the resulting data for the examined countries with other eHealth benchmarks and to extend and explore changes to a comparable survey in 2017. We defined "availability of patient data" as the ability to access data in and to add data to the patient record in the respective country. METHODS: The invited experts from each of the 14 countries provided the indicator data for their country to reflect the situation on August 1, 2019, as date of reference. Overall, 60 items were aggregated to six eHealth indicators. RESULTS: Availability of patient-related information varies strongly by country. Health care professionals can access patients' most relevant cross-institutional health record data fully in only four countries. Patients and their caregivers can access their health record data fully in only two countries. Patients are able to fully add relevant data only in one country. Finland showed the best outcome of all eHealth indicators, followed by South Korea, Japan, and Sweden. CONCLUSION: Advancement in eHealth depends on contextual factors such as health care organization, national health politics, privacy laws, and health care financing. Improvements in eHealth indicators are thus often slow. However, our survey shows that some countries were able to improve on at least some indicators between 2017 and 2019. We anticipate further improvements in the future.

A Randomized Controlled Trial on the Safety and Efficacy of Exenatide Therapy for the Inpatient Management of General Medicine and Surgery Patients With Type 2 Diabetes.

OBJECTIVE: This multicenter, open-label, randomized trial examined the safety and efficacy of exenatide alone or in combination with basal insulin in non-critically ill patients with type 2 diabetes (T2D). RESEARCH DESIGN AND METHODS: A total of 150 patients with blood glucose (BG) between 140 and 400 mg/dL, treated at home with diet, oral agents, or insulin at a total daily dose <0.5 units/kg, were randomized to exenatide alone (5 µg twice daily), exenatide plus basal insulin, or a basal-bolus insulin regimen. The primary end point was difference in mean daily BG concentration among groups. RESULTS: Mean daily BG was similar between patients treated with exenatide plus basal and a basal-bolus regimen (154 ± 39 vs. 166 ± 40 mg/dL, P = 0.31), and exenatide plus basal resulted in lower daily BG than did exenatide alone (177 ± 41 mg/dL, P = 0.02). Exenatide plus basal resulted in a higher proportion of BG levels in target range between 70 and 180 mg/dL compared with exenatide and basal-bolus (78% vs. 62% vs. 63%, respectively, P = 0.023). More patients in the exenatide and exenatide plus basal groups experienced nausea or vomiting than in the basal-bolus group (10% vs. 11% vs. 2%, P = 0.17), with three patients (6%) discontinued exenatide owing to adverse events. There were no differences in hypoglycemia <54 mg/dL (2% vs. 0% vs. 4%, P = 0.77) or length of stay (5 vs. 4 vs. 4 days, P = 0.23) among basal plus exenatide, exenatide, and basal-bolus groups. CONCLUSIONS: The results of this pilot study indicate that exenatide alone or in combination with basal insulin is safe and effective for the management of hospitalized general medical and surgical patients with T2D.

X Marks the Spot: Mapping Similarity Between Clinical Trial Cohorts and US Counties.

When patients and doctors collaborate to make healthcare decisions, they rely on clinical trial results to guide discussions. Trials are designed to recruit diverse participants. The question remains - how well do trial results apply to me or to people who live in our area? This study compared one complete clinical trial dataset (SPRINT) and one published study (ACCORD) to the Community Health Status Indicators dataset to assess the similarity of the trial populations to US county populations. Counties up to 495 miles to the closest SPRINT trial site and up to 712 miles to the closest ACCORD trial site had populations that were significantly more similar to the study cohort than counties farther away. The investigators detail a generalizable method for both assessing recruitment gaps in large multicenter trials and creating maps for clinicians to provide intuition on trial applicability in their area.

The place of GLP-1-based therapy in diabetes management: differences between DPP-4 inhibitors and GLP-1 receptor agonists.

Type 2 diabetes is a progressive disease characterized by the need for additional antidiabetic agents overtime to maintain a stable level of glycemic control. The discovery of the glucagon like peptide 1, 1 of the 2 major incretins, was pivotal to the development of novel therapies, which can be used in individuals with type 2 diabetes. Two classes of drugs, GLP-1 receptor agonists and dipeptidyl peptidase inhibitors, provide comparable or superior glycemic effects to previous antidiabetic agents without increasing side effects, such as weight gain and hypoglycemia. Therefore, they represent valuable additions to the current therapeutic options for type 2 diabetes.