David A. Hanauer

Objectives: To evaluate the utility of large language models (LLMs) without and with retrieval-augmented generation (RAG) resources for automating Research Electronic Data Capture (REDCap) support at a large academic medical center, focusing on ticket complexity, categorization, and response drafting. Materials and Methods: We randomly selected 90 REDCap support tickets from 6316 received in 2023, stratified by estimated complexity (low, moderate, high) using ticket metadata. Four LLM configurations (GPT-4o Default; GPT-4o + Vanderbilt REDCap documentation; GPT-4o + University of Michigan [UM] REDCap documentation; GPT-4o + combined documentation) were evaluated on 3 tasks per ticket: complexity assessment, category assignment, and email response drafting. Human REDCap experts provided gold-standard ratings and assessed email drafts. Results: Compared to the gold standard, the GPT-4o Default environment most closely matched human complexity ratings, while specialized RAG environments tended to overestimate complexity. For ticket support categorization, all LLM configurations achieved high agreement with human judgments (Cohen’s kappa ≈0.85), correctly categorizing 81%-89% of tickets. In generating ticket responses, the GPT-4o + REDCap + UM environment provided the most correct answers, particularly for low and moderate complexity tickets, where about two-thirds of responses were substantially or fully correct. Discussion: Large language models have potential to automate ticket triage and response drafting for routine REDCap support, with context augmentation improving response accuracy for lower complexity tickets. Conclusion: Large language model-based support tools hold promise for reducing human workload for REDCap support tickets. Continued human oversight, iterative prompt engineering, and expanded local documentation are needed for reliable, effective deployment.

This cross-sectional study investigates rates and characteristics of emoji use in clinical notes within electronic health records.

Venous thromboembolism (VTE) is a highly prevalent medical condition with limited therapeutic options and an incomplete understanding of its acquired and inherited subtypes. The zebrafish is a model with the benefits of external development, fecundity, optical transparency, and hemostasis that demonstrates conservation with mammals. We utilized zebrafish as a phenotypic screening tool to identify novel therapeutic options for preventing VTE. A library of FDA-approved compounds was screened for suppression of acquired (elevated estrogen) and spontaneous (protein C deficiency) thrombosis. We found that thyroid hormone, receptor tyrosine kinase (RTK) inhibitors, and proton-pump inhibitors (PPIs) effectively modulated levels of thrombosis, particularly in the estrogen-induced model. These also showed a more favorable hemostatic profile than standard therapies, suggesting alternative mechanisms. Genome editing of thyroid hormone receptor proved that thyroid hormone action is on target. A retrospective electronic health record (EHR) analysis found that thyroid-hormone prescriptions in hormonal contraceptive users correlated with a higher VTE risk, potentially limiting direct repurposing but highlighting thyroid signaling as a pathway involved in estrogen-induced thrombosis. Together, these data identify several drug classes that can be tailored to specific subtypes of VTE and help elucidate distinct pathways driving thrombosis.

This study evaluated the readability of ClinicalTrials.gov trial information using traditional readability measures (TRMs) and compared it to summaries generated by large language models (LLMs), specifically ChatGPT and a fine-tuned BART-Large-CNN (FBLC). The study involved: 1) assessing required reading levels (RRL) with TRMs, 2) generating sample LLM-based summaries, and 3) evaluating summary quality based on scores provided by two independent reviewers. The results show that the original ClinicalTrials.gov trial descriptions were scored above the recommended readability level. In contrast, ChatGPT-generated summaries had significantly lower RRLs and higher quality scores. We conclude that ChatGPT shows great promise of creating readable, high-quality summaries. Future research is warranted to assess whether LLMs could be a viable solution to improve the readability of ClinicalTrials.gov to facilitate comprehension by laypersons.

Background: The mental health crisis among college students intensified amid the COVID-19 pandemic, suggesting an urgent need for innovative solutions to support them. Previous efforts to address mental health concerns have been constrained, often due to the underuse or shortage of services. Mobile health (mHealth) technology holds significant potential for providing resilience-building support and enhancing access to mental health care. Objective: This study aimed to examine the trends in mental health and well-being outcomes over 3 years among college students, with an exploratory aim to assess the potential impact of the Roadmap mHealth app on these outcomes. Methods: A fully automated longitudinal observational study was conducted remotely from a large public academic institution in the Midwestern United States, evaluating mental health and well-being outcomes among college students using the Roadmap mHealth app over 3 fall semesters from 2020 to 2022. The study enrolled 2164 college students in Year I, with 1128 and 1033 students returning in Years II and III, respectively. Participants completed various self-reported measures, including the Patient Health Questionnaire-9 for depression, Generalized Anxiety Disorder-7 for anxiety, and additional metrics for coping, flourishing, and loneliness. Results: The findings indicated an evolving trajectory in students’ mental health. In Year I, depression and anxiety levels were higher compared with levels reported between 2014 and 2019, remaining stable into Year II. However, significant decreases were noted by Year III for both depression (Year I mean 7.78, SD 5.65 vs Year III mean 6.21, SD 4.68; t108=–2.90; P=.01) and anxiety (Year I mean 6.61, SD 4.91 vs Year III mean 5.62, SD 4.58; t116=–2.02; P=.046). Problem-focused coping decreased initially from Year I (mean 2.46, SD 0.58) to Year II (mean 2.36, SD 0.60; t1073=–5.87; P<.001), then increased by Year III (mean 2.40, SD 0.63; t706=2.26; P=.02). Emotion-focused (Year I mean 2.33, SD 0.41 vs Year III mean 2.22, SD 0.47; t994=–7.47; P<.001) and avoidant coping (Year I mean 1.76, SD 0.37 vs Year III mean 1.65, SD 0.38; t997=–8.53; P=.02) consistently decreased. Loneliness significantly decreased from Year I (mean 5.79, SD 1.74) to Year III (mean 5.17, SD 1.78; t1013=–10.74; P<.001), accompanied by an increase in flourishing from Year I (mean 63.78, SD 14.76) to Year III (mean 66.98, SD 15.06; t994=7.22; P<.001). Analysis of app usage indicated that the positive piggy bank and gratitude journal were the favored activities. Greater engagement with the app was positively correlated with enhanced flourishing, even after adjusting for demographic and sociobehavioral factors (β=.04, SE .016; t3974=2.17; P=.03). Conclusions: In this study, students’ mental health and well-being improved, with notable reductions in depression, anxiety, and loneliness, associated with an increase in flourishing. The app did not appear to worsen students’ mental health. Based on the usage pattern, it is possible the app enhanced positive psychology-based practices. Future research should explore the efficacy of mHealth interventions through randomized controlled trials to further understand their impact on college students’ mental health outcomes. Trial Registration: ClinicalTrials.gov NCT04766788; https://clinicaltrials.gov/ct2/show/NCT04766788 International Registered Report Identifier (IRRID): RR2-10.2196/29561

Background: Hematopoietic stem cell transplantation (HCT) is a potentially life-saving therapy for individuals with blood diseases, but involves a challenging recovery process that requires dedicated caregivers. The complex interplay between emotional distress, care partner (or unpaid caregiver) burden, and treatment outcomes necessitates comprehensive physiological and psychological measurements to fully understand these dynamics. Findings: We collected longitudinal data from 166 HCT caregiver-patient dyads over 120 days post-transplant as part of a randomized controlled trial ( NCT04094844 ). Data were gathered using the Fitbit® Charge 3 device, a custom mood-reporting app with positive psychology-based activities (Roadmap), PROMIS® health measures, and clinical events. The dataset includes minute-level heart rate, daily sleep metrics, step counts, self-reported mood scores, app usage metrics, PROMIS® T-scores (i.e. global health, depression), infection and readmission records, and clinical outcomes (e.g., acute and chronic graft-versus-host disease, relapse, mortality). Physiological data were available for both caregivers and patients. Data validation confirmed high compliance with mood reporting and the presence of physiological patterns between caregivers and patients that differed (i.e., lower activity in patients compared with caregivers across time). Conclusions: This dataset offered an unprecedented view into the daily fluctuations of caregiver and patient well-being throughout the critical post-HCT period. It provided a valuable resource for researchers investigating the impact of mHealth app interventions, including emotional distress and physiological markers on treatment course and clinical outcomes. Our unique dataset informs interventions that may address caregiver support, patient care, or dyadic-focused strategies and enable novel analyses of single member or dyadic dynamics in HCT treatment.

BACKGROUND The mental health crisis among college students intensified amid the COVID-19 pandemic, suggesting an urgent need for innovative solutions to support them. Previous efforts to address mental health concerns have been constrained, often due to the underuse or shortage of services. Mobile health (mHealth) technology holds significant potential for providing resilience-building support and enhancing access to mental health care. OBJECTIVE This study aimed to examine the trends in mental health and well-being outcomes over 3 years among college students, with an exploratory aim to assess the potential impact of the Roadmap mHealth app on these outcomes. METHODS A fully automated longitudinal observational study was conducted remotely from a large public academic institution in the Midwestern United States, evaluating mental health and well-being outcomes among college students using the Roadmap mHealth app over 3 fall semesters from 2020 to 2022. The study enrolled 2164 college students in Year I, with 1128 and 1033 students returning in Years II and III, respectively. Participants completed various self-reported measures, including the Patient Health Questionnaire-9 for depression, Generalized Anxiety Disorder-7 for anxiety, and additional metrics for coping, flourishing, and loneliness. RESULTS The findings indicated an evolving trajectory in students’ mental health. In Year I, depression and anxiety levels were higher compared with levels reported between 2014 and 2019, remaining stable into Year II. However, significant decreases were noted by Year III for both depression (Year I mean 7.78, SD 5.65 vs Year III mean 6.21, SD 4.68; t108=–2.90; P=.01) and anxiety (Year I mean 6.61, SD 4.91 vs Year III mean 5.62, SD 4.58; t116=–2.02; P=.046). Problem-focused coping decreased initially from Year I (mean 2.46, SD 0.58) to Year II (mean 2.36, SD 0.60; t1073=–5.87; P<.001), then increased by Year III (mean 2.40, SD 0.63; t706=2.26; P=.02). Emotion-focused (Year I mean 2.33, SD 0.41 vs Year III mean 2.22, SD 0.47; t994=–7.47; P<.001) and avoidant coping (Year I mean 1.76, SD 0.37 vs Year III mean 1.65, SD 0.38; t997=–8.53; P=.02) consistently decreased. Loneliness significantly decreased from Year I (mean 5.79, SD 1.74) to Year III (mean 5.17, SD 1.78; t1013=–10.74; P<.001), accompanied by an increase in flourishing from Year I (mean 63.78, SD 14.76) to Year III (mean 66.98, SD 15.06; t994=7.22; P<.001). Analysis of app usage indicated that the positive piggy bank and gratitude journal were the favored activities. Greater engagement with the app was positively correlated with enhanced flourishing, even after adjusting for demographic and sociobehavioral factors (β=.04, SE .016; t3974=2.17; P=.03). CONCLUSIONS In this study, students’ mental health and well-being improved, with notable reductions in depression, anxiety, and loneliness, associated with an increase in flourishing. The app did not appear to worsen students’ mental health. Based on the usage pattern, it is possible the app enhanced positive psychology-based practices. Future research should explore the efficacy of mHealth interventions through randomized controlled trials to further understand their impact on college students’ mental health outcomes. CLINICALTRIAL ClinicalTrials.gov NCT04766788; https://clinicaltrials.gov/ct2/show/NCT04766788 INTERNATIONAL REGISTERED REPORT RR2-10.2196/29561

Few studies examining the patient outcomes of concurrent neurological manifestations during acute COVID-19 leveraged multinational cohorts of adults and children or distinguished between central and peripheral nervous system (CNS vs. PNS) involvement. Using a federated multinational network in which local clinicians and informatics experts curated the electronic health records data, we evaluated the risk of prolonged hospitalization and mortality in hospitalized COVID-19 patients from 21 healthcare systems across 7 countries. For adults, we used a federated learning approach whereby we ran Cox proportional hazard models locally at each healthcare system and performed a meta-analysis on the aggregated results to estimate the overall risk of adverse outcomes across our geographically diverse populations. For children, we reported descriptive statistics separately due to their low frequency of neurological involvement and poor outcomes. Among the 106,229 hospitalized COVID-19 patients (104,031 patients ≥18 years; 2,198 patients <18 years, January 2020-October 2021), 15,101 (14%) had at least one CNS diagnosis, while 2,788 (3%) had at least one PNS diagnosis. After controlling for demographics and pre-existing conditions, adults with CNS involvement had longer hospital stay (11 versus 6 days) and greater risk of (Hazard Ratio = 1.78) and faster time to death (12 versus 24 days) than patients with no neurological condition (NNC) during acute COVID-19 hospitalization. Adults with PNS involvement also had longer hospital stay but lower risk of mortality than the NNC group. Although children had a low frequency of neurological involvement during COVID-19 hospitalization, a substantially higher proportion of children with CNS involvement died compared to those with NNC (6% vs 1%). Overall, patients with concurrent CNS manifestation during acute COVID-19 hospitalization faced greater risks for adverse clinical outcomes than patients without any neurological diagnosis. Our global informatics framework using a federated approach (versus a centralized data collection approach) has utility for clinical discovery beyond COVID-19.

Background: An effective and scalable information retrieval (IR) system plays a crucial role in enabling clinicians and researchers to harness the valuable information present in electronic health records. In a previous study, we developed a prototype medical IR system, which incorporated a semantically based query recommendation (SBQR) feature. The system was evaluated empirically and demonstrated high perceived performance by end users. To delve deeper into the factors contributing to this perceived performance, we conducted a follow-up study using query log analysis. Objective: One of the primary challenges faced in IR is that users often have limited knowledge regarding their specific information needs. Consequently, an IR system, particularly its user interface, needs to be thoughtfully designed to assist users through the iterative process of refining their queries as they encounter relevant documents during their search. To address these challenges, we incorporated “query recommendation” into our Electronic Medical Record Search Engine (EMERSE), drawing inspiration from the success of similar features in modern IR systems for general purposes. Methods: The query log data analyzed in this study were collected during our previous experimental study, where we developed EMERSE with the SBQR feature. We implemented a logging mechanism to capture user query behaviors and the output of the IR system (retrieved documents). In this analysis, we compared the initial query entered by users with the query formulated with the assistance of the SBQR. By examining the results of this comparison, we could examine whether the use of SBQR helped in constructing improved queries that differed from the original ones. Results: Our findings revealed that the first query entered without SBQR and the final query with SBQR assistance were highly similar (Jaccard similarity coefficient=0.77). This suggests that the perceived positive performance of the system was primarily attributed to the automatic query expansion facilitated by the SBQR rather than users manually manipulating their queries. In addition, through entropy analysis, we observed that search results converged in scenarios of moderate difficulty, and the degree of convergence correlated strongly with the perceived system performance. Conclusions: The study demonstrated the potential contribution of the SBQR in shaping participants' positive perceptions of system performance, contingent upon the difficulty of the search scenario. Medical IR systems should therefore consider incorporating an SBQR as a user-controlled option or a semiautomated feature. Future work entails redesigning the experiment in a more controlled manner and conducting multisite studies to demonstrate the effectiveness of EMERSE with SBQR for patient cohort identification. By further exploring and validating these findings, we can enhance the usability and functionality of medical IR systems in real-world settings. Trial Registration: