Drug Safety

Objectives. To present DrugSet, a validated R Shiny application supporting the construction medicinal products codelists based on the Anatomical Therapeutic Chemical (ATC) system and their mapping to Clinical Practice Research Datalink (CPRD) Aurum prodcodes within a single interactive workflow. Materials and Methods. DrugSet comprises four modules: data preparation, ATC-based hierarchical code selection, string-based CPRD Aurum prodcodes mapping, and codelist export. Validation was conducted against World Health Organization (WHO) ATC reference codelists and manually curated prodcodes mappings across three drug classes: metformin, beta-blocking agents, and topical salicylic acid. Sensitivity, specificity, and Positive Predictive Values (PPV) were calculated for ATC codelist generation. Agreement proportions (overlapping against total identified codes) were calculated for prodcodes mapping. Time needed for codelist construction using DrugSet was recorded and compared to manual approaches. Results. DrugSet ATC codelist generation against WHO manual reference achieved 100% sensitivity, specificity, and PPV across all medicinal products. Prodcodes mapping agreement ranged from 89.2% to 98.3% with discrepancies due to missing data in the prodcodes input vocabulary. DrugSet completed codelist construction in 9 minutes compared to 3 hours and 10 minutes manually, across all medicinal products classes. Discussion. DrugSet provides a unified workflow that runs directly on ATC and source CPRD Aurum vocabulary files. The reduction in codelist construction time and export of the generated codelists supports reproducibility in pharmacoepidemiologic studies where codelist creation can represent a significant proportion of study setup time. Conclusion. DrugSet is an open-source, validated tool that improves accuracy, and efficiency of codelist construction for medicinal products based on ATC codes towards CPRD Aurum prodcodes.

Introduction: Adverse drug withdrawal events (ADWEs) are a key safety concern with deprescribing but are infrequently reported in trials. Although pharmacovigilance systems have advanced our understanding of medication-related harms, it is unclear how extensively these systems have been used for ADWEs. Objectives: To examine the reporting patterns of ADWEs for all drugs recorded in United States and European pharmacovigilance databases between 2004 and 2023. Methods: A retrospective study was conducted using two pharmacovigilance databases, the publicly available FDA-FAERS dataset and EMA-EV Level 2A (individual-level) dataset. ADWE cases were identified using relevant MedDRA preferred terms. Data on patient characteristics, reporter type, drugs, indication, ADWE outcomes, dechallenge/rechallenge, seriousness criteria, time to onset, duration, and causality were summarised. Results: A total of 158,505 ADWE reports were analysed (FDA-FAERS: 145,514; EMA-EV: 12,987), with mean ages of 46.1 (FDA; 55.3% female) and 45.5 years (EMA; 57.1% female). The frequently reported drug classes were opioids (FDA: oxycodone, 29.8%; EMA: buprenorphine, 19%), antidepressants (FDA: duloxetine, 32%; EMA: venlafaxine, 25.9%) and gabapentinoids (FDA: pregabalin, 6.7%; EMA: pregabalin, 6.0%). The most common adverse outcomes were other serious medical conditions (FDA=63.9%; EMA=46.0%), hospitalisation (FDA=15.9%; EMA=28.3%), and disability (FDA=13.3%; EMA=6.2%) and these outcomes varied significantly based on sex and age group (p<0.05). Conclusions: This study provides novel evidence of reporting patterns and characteristics of ADWEs across drugs in pharmacovigilance data. These findings emphasise that adverse drug reaction reporting systems need to accommodate ADWEs (i.e., clarity on terminologies, dechallenge/rechallenge, causality assessment) to effectively capture ADWE-related data to support evidence-based deprescribing practices for better patient safety

Background: Retrieval of adverse event reports based on coded drug-event co-occurrence enables large-scale pharmacovigilance analyses, but yields candidate reports rather than validated cases, risking misinterpretation if used alone. Aim: To develop and apply a framework for identification and characterization of clinically meaningful case series in pharmacovigilance. Methods: We conducted two case studies. The first developed and refined the framework in an information-rich setting, focusing on drug-induced impulsivity across selected drugs; the second tested its applicability in a more routine, information-poor setting, focusing on drug-induced suicidality. Results: In Case 1, non-relevant reports were frequent for drugs with uncertain evidence and negative controls ({approx}20-40%) compared to drugs with established causal roles (4%). The emerging framework assessed relevance based on exposure, event, drug-event relationship, and population. For suspected adverse drug reactions, relevant reports were further characterized by reporter suspicion and evidentiary qualifiers supporting or refuting causality; higher suspicion was associated with more supportive qualifiers. Applied to Case 2, the framework ruled out 69% of reports as non-relevant but highlighted substantial non-assessability (17%). Conclusions: In pharmacovigilance, retrieval is not equivalent to case identification. Relevance is question-specific and shaped by how reports are captured, processed, and retrieved. This can be especially critical for emerging or bias-prone safety questions. Transparent and reproducible case definition and adjudication are essential for interpretable analyses.

Background Large Language Models (LLMs) are increasingly explored for pharmacovigilance tasks, including information extraction, case documentation, and single-case causality assessment. However, their ability to support causality assessment at the case series level -- a complex, time-intensive task requiring clinical reasoning across multiple reports -- remains unexplored. Objective To investigate how a large-scale general-purpose LLM can support pharmacovigilance professionals in assessing causality in a case series, and to explore how prompt design influences the quality of the model's reasoning. Methods GPT-4o was used to assess causality for five drug - adverse event combinations, using an adaptation of the Bradford Hill viewpoints for case series assessment. The combinations represented varying drugs and vaccines, adverse events, and case series sizes (5-402 reports). One combination served as a negative control. Structured prompts were iteratively developed and refined using one combination, then applied to all combinations. LLM-generated assessments for each viewpoint were qualitatively evaluated by human annotators for accuracy (precision), and the LLM's coverage of key aspects from the original signal text was assessed for one combination (recall). Results Across all five combinations, annotators agreed with 79-92% of the LLM's output sentences. Full disagreement was consistently low (3-7%), with errors typically involving misinterpretation of complex report details rather than outright fabrication. Prompt design substantially influenced output quality; providing Bradford Hill viewpoint descriptions, including case series data, and adding explicit anti-hallucination instructions improved specificity and grounding. For the recall assessment, 15 of 23 key segments from the original signal text were reflected in the LLM output. The overall summary assessments demonstrated balanced reasoning, correctly distinguishing between positive safety signals and the negative control, and provided a coherent synthesis suitable as a starting point for human assessors. Conclusions LLMs have the potential to generate contextually nuanced and largely accurate preliminary causality assessments of case series aligned with the Bradford Hill viewpoints, with a low but non-zero hallucination rate. These findings support LLMs as a tool to augment, not replace, expert judgment in signal assessment. Future work should address larger and more diverse signal sets, improved evaluation frameworks for generative output, and the integration of pre-computed summary statistics to reduce errors.

Private pharmacies are ubiquitous yet underutilized for HIV pre- and post-exposure prophylaxis (PrEP and PEP) delivery. In a cluster-randomized trial in Kenya (NCT05842122), we randomized 60 pharmacies 1:1:1:1 to: client-sustained delivery (~$2/visit user fee); implementor-sustained delivery (~$2/visit reimbursement); counselor-supported delivery (task shifting; ~$1/visit reimbursement); or clinic referral (control; ~$1/referral reimbursement). Commodities were supplied free to pharmacies from government stock. Primary outcomes were PrEP initiation and one-month continuation (any dispensing or refilling, respectively), self-reported by clients 60 days post-enrollment (multiple-comparisons threshold: p=0.017). From June 2023-April 2025, 5,808 clients enrolled; 64% were PEP candidates. Compared to referral, the counselor-supported arm had significantly higher PrEP initiation (RR=6.5, 95% CI [2.6, 16], p<0.001) and continuation rates (RR=5.1, 95% CI [1.4, 19], p=0.016); all intervention arms had significantly higher PEP initiation rates. One seroconversion, one social harm, and two provider needlestick injuries occurred. Pharmacy PrEP/PEP delivery outperformed clinic referral, particularly when fully subsidized and counselor-supported.

Background: HIV infection has long been associated with increased incidence of severe cutaneous adverse reactions (SCAR). It remains unknown whether this increased incidence is a direct biological result of HIV infection, differences in drug exposure, or other demographic factors. Objective: To evaluate the association between HIV and SCAR and determine whether this relationship persists after adjusting for demographic factors and structured drug exposure. Methods: We analyzed reports from the FDA Adverse Event Reporting System (FAERS) from 2013-2023. SCAR outcomes included Stevens-Johnson syndrome/toxic epidermal necrolysis (SJS/TEN), drug reaction with eosinophilia and systemic symptoms (DRESS), acute generalized exanthematous pustulosis (AGEP), and generalized bullous fixed drug eruption (GBFDE). HIV status was determined using antiretroviral exposure, indication text, and machine-learning imputation. Logistic regression models were constructed sequentially: unadjusted, demographic-adjusted, and fully adjusted with drug principal components to account for polypharmacy. Drug-level disproportionality and HIV-drug interaction analyses were also performed. Results: In unadjusted models, HIV was strongly associated with SCAR (OR ~2.0-2.7). Adjustment for demographics attenuated this association, and further adjustment for drug exposure reduced the effect to near null for overall SCAR and DRESS. A modest residual association persisted for SJS/TEN (OR ~1.3). Disproportionality analyses demonstrated enrichment of specific high-risk drugs in PLWH. Interaction modeling revealed drug-specific amplification of SCAR risk in HIV, notably for carbamazepine and clarithromycin, whereas other drugs showed minimal interaction. Conclusion: The association between HIV and SCAR is largely explained by differences in drug exposure and demographic factors. Residual risk is drug-specific rather than uniform, supporting a model in which HIV modifies susceptibility to select drug triggers rather than acting as a global risk factor. Further prospective and retrospective studies are required to quantify associations.

Objectives: To estimate hyperlipidemia medication order prevalence and associated variables in U.S. skilled nursing facility (SNF) residents. Design: Retrospective, observational study. Setting and Participants: Electronic Health Record data from 447,080 SNF residents with a hyperlipidemia diagnosis identified in PointClickCare's Life Sciences clinical database (January-April 2025) were reviewed. Methods: The presence and absence of medication orders for hyperlipidemia treatments recommended by the American Heart Association were assessed. Descriptive analyses summarized demographic and clinical characteristics, and a modified Poisson regression model was used to estimate risk ratios for having a medication order, adjusting for demographic, clinical, and facility characteristics. Results: Overall, 83.3% of residents diagnosed with hyperlipidemia had at least one hyperlipidemia medication order. Statins were ordered by 96.2% of active order residents, while other medication classes i.e., omega-3 fatty acids, cholesterol absorption inhibitors, fibrates were less common (<8%). Risk ratios (RRs) for medication orders ranged from 0.87-1.16. Factors most strongly associated with having an order included hypertension medication orders (RR=1.16), unspecified hyperlipidemia diagnosis (RR=1.10), and active diabetes medication orders (RR=1.09); female sex (RR=0.95) and private (0.94) or other (0.87) payer types were associated with a lower likelihood of having an order. Conclusions and Implications: Most residents with a hyperlipidemia diagnosis had an active relevant medication order, but use of non-statin therapies was rare. Differences in treatment patterns by sex and payer type, along with limited uptake of newer agents, warrant further investigation into prescribing practices and access within SNFs.

Background Despite available lipid-lowering therapies (LLT), many patients fail to achieve low-density lipoprotein cholesterol (LDL-C) targets. This gap persists across clinically relevant subgroups. Bempedoic acid has demonstrated effective LDL-C lowering with a favorable safety profile in the CLEAR Taiwan study; however, its effects across subgroups in Asian populations remains limited. Methods The phase IV CLEAR Taiwan study (NCT06925100) enrolled patients with inadequately controlled hypercholesterolemia who received bempedoic acid for 12 weeks in addition to background LLT. This analysis evaluated changes in lipid parameters, high-sensitivity C-reactive protein (hsCRP), and safety outcomes in clinically relevant subgroups, including cardiovascular risk, diabetes, age, statin tolerance, and sex. Results A total of 180 patients were included. Bempedoic acid achieved significant LDL-C reductions in all subgroups. Numerically greater LDL-C reductions were observed in primary prevention, statin-intolerant, younger (< 65 years), and female patients, while comparable reductions were observed across diabetes status. Reductions in non-high-density lipoprotein cholesterol, total cholesterol, and apolipoprotein B were consistent with LDL-C findings. Significant decreases in hsCRP were observed in all subgroups, with numerically greater reductions in patients aged < 65 years and those without diabetes. Bempedoic acid was well tolerated, with a low incidence of adverse events and no new safety signals identified. Changes in liver enzymes, renal function, and uric acid were minimal within subgroups. Conclusion Subgroup analyses from the CLEAR Taiwan study demonstrate consistent efficacy and safety of bempedoic acid across clinically relevant subgroups and support its use as a flexible option to address residual gaps in lipid management.

Drug repurposing offers a practical strategy to identify new therapeutic uses for approved drugs, potentially reducing the time and cost associated with conventional drug development. We present a novel three-stage drug repurposing pipeline that integrates knowledge graph-based gene prediction, network-based drug-disease association analysis, and systematic classification of candidate drugs by therapeutic class. The pipeline integrates DGLinker to predict novel disease-associated genes, SAveRUNNER to identify drug repurposing candidates, and ATC Category Enrichment Analysis (ATCEA) to prioritise candidates by pharmacological class. We benchmarked the pipeline across twelve diseases using DrugBank and MEDI2-HPS as validation resources. Utilising DGLinker-expanded disease-gene sets as input increased the number of predicted repurposed drugs, while overall discriminative performance remained stable across diseases (AUROC 0.71-0.77). Application of ATCEA consistently improved precision, F1-score, and specificity, while reducing recall, reflecting a conservative prioritisation strategy that contracts the candidate space while retaining pharmacologically coherent drug-disease candidates. We further applied the pipeline to amyotrophic lateral sclerosis (ALS), a neurodegenerative disease with limited therapeutic options, and performed a deeper literature-based validation of the results. Incorporation of DGLinker-predicted genes substantially increased the number of significant candidate drugs and uncovered enriched ATC categories not identified using known ALS genes alone, including antidepressants and antipsychotics. Moreover, several drugs with supporting evidence available in the literature were identified only when DGLinker-predicted genes were used. Overall, 77 candidate drugs were prioritised within significantly enriched ATC categories, several of which are supported by previously published studies. To provide exploratory real-world support for these findings, we further evaluated candidate drugs in a longitudinal electronic health record (EHR) dataset of 2361 patients with ALS from King's College Hospital. Although the number of evaluable drugs was limited due to sample size, the EHR analysis provided additional clinically relevant context for selected prioritised drugs and pharmacological classes. Our pipeline demonstrates potential to accelerate drug repurposing by integrating complementary computational approaches to each step of the process, providing an end-to-end framework that showed robust performance across benchmarking experiments and use cases.

Background: For US young adults aged 18-25 in the 2018-2024 period, fentanyl was involved in 78.2% of the 44,020 unintentional or undetermined-intent overdose deaths, most often co-involving stimulants and other non-opioid substances. While fatal overdose rates in this age group have fallen to their lowest recorded level, emergency medical services-attended non-fatal overdose events have reached record highs, shifting the decisive variable toward bystander recognition and response. College students report near-universal alcohol education but minimal education on the substances actually driving overdose mortality. Methods: We conducted a single-group pre-post evaluation of the DopaGE Portal, a gamified, mastery-based digital platform covering cocaine, MDMA, benzodiazepines, and opioid overdose response, deployed at a public university (UNL) and a multi-campus volunteer network (TACO). Paired pre/post surveys (N=42) measured self-efficacy (7 items; primary), behavioral intentions, risk perception, and knowledge/attitudes on 5-point scales, plus four factual knowledge questions. Paired t-tests, exact McNemar tests, and Benjamini-Hochberg correction across eight primary tests were applied. Institutional naloxone distribution at UNL was tracked as an ecological behavioral outcome. A mandated high-school cohort (N=94) provided supplementary acceptability data. Results: Self-efficacy increased from 2.82 to 4.46 (d=2.00, 95% CI 1.46-2.55; adjusted p<.001), and behavioral intentions from 4.24 to 4.81 (d=1.43; adjusted p<.001), with effects statistically indistinguishable across sites. Three of four knowledge items improved significantly (+31 to +41 percentage points). Risk perception was at ceiling at baseline (4.38/5) and did not change. In the two months following deployment, 38 naloxone kits were distributed on campus (limited to one per person from the campus pharmacy and health center) versus 14 in the preceding two years combined; the campus health center had distributed zero kits in 2025 despite stocked availability. Evaluation ratings were uniformly positive across voluntary and mandated cohorts, with zero negative ratings. Conclusions: A digital-only, gamified intervention produced large gains in overdose-response self-efficacy and substance-specific knowledge, with concurrent campus-level naloxone acquisition consistent with behavioral translation. These findings are preliminary -- single-group, modest N, ecological behavioral outcome -- and motivate a future randomized controlled trial.

We evaluated the blood pressure (BP) lowering efficacy and safety of triple vs dual therapy of antihypertensive drug (AHTD) combinations, among adults with hypertension. Seventeen randomized, double-blind trials (41 comparisons and 13,461 participants) comparing triple versus dual therapy for 3 weeks identified by multiple literature databases searches including PubMed, Cochrane Central Register of Controlled Trials (CENTRAL) until October 2024 were included in the meta-analysis. Triple therapy achieved a greater reduction in systolic BP (SBP) compared with dual therapy (26.9 vs. 21.7 mmHg, mean difference 5.4 mmHg [95% CI, 4.7 to 6.2]). Among patients receiving dual therapy at submaximal and maximal doses, the addition of a third drug further reduced SBP by 7.5 and 3.6 mmHg, respectively. BP control was significantly better with triple therapy (60% vs. 47%, RR=1.34 [1.27 to 1.41]). Withdrawal due to adverse events was slightly higher in the triple therapy group (4% vs. 3%, RR=1.5 [1.2 to 1.8]). Triple AHTD therapy provides superior BP reduction and is well-tolerated compared to dual therapy.

Background: Cardiotoxicity remains a key concern of HER2-directed therapies, with no proven prevention strategies. The success of cardioprotective interventions will depend not only on efficacy, but on patient acceptability, an underexplored determinant of trial participation and clinical implementation. Objectives: To evaluate willingness to take cardioprotective medication and identify factors influencing decision-making among individuals with HER2-positive breast cancer. Methods: We conducted a cross-sectional online survey of adults with HER2-positive breast cancer in Australia and the United States. The survey assessed willingness, beliefs regarding benefits and risks, and treatment preferences. Multivariable logistic regression examined associations between clinical and demographic characteristics and willingness. Results: Among 74 respondents (Australia n=24; United States n=50), 74.3% reported being likely or very likely to take cardioprotective medication. Physician recommendation emerged as a dominant driver (79.1%). While most participants valued long-term cardiovascular health (72.9%), uncertainty regarding benefit was common (60.4%). Cancer-related outcomes were prioritized over cardiovascular outcomes. Participants demonstrated flexibility regarding treatment burden, including willingness to take multiple medications and continue therapy long term. No demographic or clinical predictors of willingness were identified. Perceived acceptability, appropriateness, and feasibility were consistently high. Conclusions: Willingness to adopt cardioprotective strategies is high but conditional, shaped by cancer priorities, clinician endorsement, and uncertainty regarding benefit. These findings highlight patient acceptability as a critical, and often overlooked, determinant of successful trial participation and downstream clinical implementation in cardio-oncology.

Importance: Adverse drug events in older adults are a substantial public health burden, yet spontaneous reporting systems detect them poorly owing to underreporting and the lack of a defined population. These limitations are of particular concern for older adults, who are underrepresented in pre-approval trials yet at elevated risk owing to polypharmacy, multimorbidity, and age-related changes in drug metabolism. Objective: To develop and apply an active, claims-based pharmacovigilance framework using sequential target trial emulation to detect adverse drug event signals in older adults, with atorvastatin as the initial application. Methods: Using Medicare fee-for-service claims (2017-2019), we studied statin-naive beneficiaries aged 65 years or older following myocardial or cerebral infarction. We emulated up to 14 daily sequential trials from the discharge date, classifying patients as initiating atorvastatin (A1), initiating a different medication (A2), or no new medication (A0); the primary contrast was A1 versus A2. For each trial, incident outcomes were ascertained and classified into 552 outcomes based on the Clinical Classifications Software Refined categories. Per-protocol effects were estimated over a 6-month follow-up period using Fine-Gray regression models weighted by the inverse probability of treatment and censoring, treating death as a competing risk, with the false discovery rate controlled via the Benjamini-Hochberg procedure. A signal was declared when the q-value was 0.10 or lower and the subdistribution hazard ratio (sHR) was 1.20 or greater in any prespecified analytic stratum (sensitivity analyses used thresholds of q 0.20 or lower and sHR 1.20 or greater). Results: Of 70,130 eligible patients, 39,948 initiated atorvastatin (A1) and 19,182 initiated another new medication (A2); after weighting, baseline characteristics were closely balanced. After excluding outcomes with sparse cell counts, 295 outcomes were analyzed; five met the primary signal detection criteria: valve disorders (sHR 1.71, 1.20 to 2.43); sprains and strains (sHR 1.79, 1.26 to 2.54); general sensation/perception symptoms (sHR 1.23, 95 percent CI 1.11 to 1.36); abnormal findings without diagnosis (sHR 1.55, 1.18 to 2.05); and prediabetes (sHR 1.71, 1.24 to 2.36). In the sensitivity analysis, we additionally detected posthemorrhagic anemia, hemorrhagic stroke, varicose veins, and other circulatory and skin conditions. Conclusions: An active, claims-based framework using sequential target trial emulation detected both expected and previously unrecognized adverse drug event signals following atorvastatin initiation in older adults, offering a systematic alternative to passive surveillance that can be extended to other commonly prescribed medications.

Background. Polypharmacy is an important source of phenoconversion caused by drug interactions potentially modulated by genetic variability. Aims. To develop a linear phenoconversion model for TDM data and provide quantitative estimates of drug-drug-gene interactions (DDGIs) in the pharmacogenetic phenotype groups of CYP2C19. Methods. Escitalopram TDM data in a large real-world sample (n=2,852) was analysed for phenoconversion of CYP2C19 activity. Co-medication was identified by reprocessing high-resolution mass-spectra (Orbitrap). We developed a statistical model to identify inhibition from co-medication in the CYP2C19 and in alternative elimination pathways. We extended the model to estimate the inhibition ensuing from individual co-medications, using a single model for all data to account for multiple co-medications and confounders simultaneously. A Bayesian approach allowed us to stabilize the fit and provide well-calibrated credibility intervals. Results. Reprocessing of TDM analyses identified 17 co-medications, which were shown to phenoconvert CYP2C19 activity proportionally to the activity in non-medicated phenotypes. Phenoconversion decreased the original CYP2C19 activity by about one third for a co-medication that corresponded to a 100% substrate of CYP2C19. The extent of CYP2C19 phenoconversion correlated strongly with the fractional contribution of CYP2C19 to the metabolism of the specific co-medication reported in the pharmacogenetic literature (R2=0.55) so long as the mechanism was competitive inhibition. Conclusion. We provide the statistical methodology to estimate phenoconversion from co-medication in TDM data and combine TDM and pharmacogenetic datasets in future studies aiming at establishing quantitative models of DDGIs.

Background: Hyperbolic tapering is an increasingly recognized approach for discontinuing serotonin reuptake inhibitor (SRI) antidepressants that involves non-linear dose reductions with equal stepwise reductions in serotonin transporter (SERT) occupancy to mitigate withdrawal symptoms. Its theoretical basis is the hyperbolic relationship between SRI dose and SERT occupancy reported in radioligand imaging studies. Hyperbolic tapering implicitly assumes that changes in SERT occupancy approximate changes in biologic effect and withdrawal risk. Because SERT occupancy plateaus across the therapeutic dose range of SRIs, this framework predicts relatively small biologic effects and withdrawal risk within this range. However, SERT occupancy influences serotonergic activity only indirectly via its effects on extracellular serotonin concentrations, and the relationship between these two variables is poorly characterized. Methods: We developed a two-pathway clearance model derived from mass-action kinetics to evaluate the steady-state relationship between SERT occupancy and extracellular serotonin concentrations under chronic SRI treatment. Results: Our analysis indicates that serotonin concentrations increase hyperbolically as transporter occupancy increases, suggesting that biologically meaningful differences in serotonergic signaling persist across the therapeutic dose range of SRIs despite plateauing occupancy. Conclusions: Our model predicts a hyperbolic relationship between SERT occupancy and extracellular serotonin concentrations, suggesting that changes in occupancy may not map proportionally onto serotonergic effect. These findings provide a potential mechanistic explanation for dose-dependent clinical effects of SRIs despite plateauing transporter occupancy and generate testable hypotheses regarding antidepressant tapering strategies. Empirical validation is warranted.

Objectives: To compare real-world cardiovascular outcomes and safety events in patients with resistant hypertension following initiation of transdermal clonidine (TC) or spironolactone. Methods: A retrospective analysis was performed using Merative MarketScan(R) Databases in the USA to identify cohorts with resistant hypertension initiating TC or spironolactone as a fourth-line agent between January 2012 and September 2024. Major Adverse Cardiovascular Events (MACE) and safety events were assessed during variable follow-up periods. Inverse probability of treatment weighting (IPTW) was applied to adjust for differences in baseline characteristics. Cox proportional hazard models were used to adjust for post-index beta-blocker utilization as a time-varying covariate for MACE outcomes. Results: The analysis included 3,113 patients in the TC cohort and 30,640 in the spironolactone cohort. After IPTW, baseline characteristics were well balanced between cohorts (standardized mean differences <0.10; mean age 60 years, 54% male). Mean follow-up was 7.1 and 10.5 months for the TC and spironolactone cohorts, respectively. After IPTW no differences in MACE outcomes were observed between the two cohorts (weighted rate ratio 1.27 [0.79-2.06]). Results were consistent after adjusting for post-index beta-blocker use. The risk of hyperkalemia was significantly lower in the TC cohort (weighted rate ratio, 0.48 [0.33-0.70]. Conclusions: In this real-world analysis, patients with resistant hypertension treated with TC have similar risk for MACE outcomes as with spironolactone, but with significantly lower risk of hyperkalemia. Thus, in patients with resistant hypertension TC appears to provide similar cardiovascular protection, with a more favorable safety profile.

TikTok has emerged as a major source of health information, yet concerns persist regarding the accuracy of content and influence of financial conflicts. Gut health content is particularly vulnerable to misinformation. This study examined the relationship between creator profession ("medical" versus "non-medical") and the quality of gut health claims and the presence of financial conflicts on TikTok. We conducted a cross-sectional study of 412 TikTok creator accounts identified using the search terms "guthealth," "gutcleansing," and "digestion." One video per creator was analyzed. Creator profession was categorized as medical or non-medical. Health claim quality was coded as high, moderate, or poor. Financial conflicts (Showcase, Subscription, external links) were assessed. Modified Poisson regression was used to estimate prevalence ratios (PRs) of health claim quality (high versus poor- or moderate-quality) and financial conflicts between medical and non-medical creators, and negative binomial regression was used to evaluate associations between claim quality and number of video likes. Non-medical creators were more likely than medical creators to present poor- or moderate-quality health claims (adjusted PR: 2.33; 95% CI: 1.50-3.62). Most creators (92%) exhibited at least one financial conflict, and Showcase use was greater among non-medical creators (adjusted PR: 1.57; 95% CI: 1.02-2.42). Videos containing moderate- and poor-quality health claims received three times as many likes as videos containing high-quality claims. Non-medical creators disproportionately produced lower-quality gut health content on TikTok, and misleading claims received greater engagement. These findings highlight a misalignment between information quality and visibility, emphasizing the need for interventions promoting evidence-based health communication.

Purpose: To evaluate the efficacy of large language models (LLMs) in extracting medication-related information from glaucoma clinical notes in the electronic health record (EHR). Design: Cross-sectional. Subjects: 1,250 subjects in the Bascom Palmer Ophthalmic Repository. Methods: Extracted clinical notes from glaucoma-related encounters between 2014 and 2024 were labeled by two glaucoma specialists with a third serving as an adjudicator. Graders were asked to label current topical medications (CTM), proposed changes to topical medications ({Delta}TM), current oral medications (COM), and proposed changes to oral medications ({Delta}OM) in a structured fashion. The dataset was split into development (10%), validation (10%), and test (80%) sets stratified by clinician. Development and validation sets were used to engineer and refine prompts, and the held-out test set was used for model assessment. Five LLMs (Claude Opus 4.6, DeepSeek-V3.2, GPT 5.2, Grok 4.1, and Qwen3.6-35B-A3B) were accessed via Microsoft Azure AI Foundry within a HIPAA-compliant environment. Inter-grader agreement was assessed with Gwet AC1. LLM performance was initially assessed in a binary fashion with F1 scores, and the degree of text match among positive cases was evaluated using exact match accuracy and Jaccard Index (JI). Main Outcome Measures: F1 score, exact match accuracy, JI. Results: Gwet AC1 for intergrader agreement was 0.799, 0.888, 0.985, and 0.988 for CTM, {Delta}TM, COM, and {Delta}OM, respectively. F1 scores for CTM were 0.985, 0.971, 0.978, 0.968, and 0.970 for Claude, Deepseek, GPT, Grok, and Qwen, respectively; for {Delta}TM: 0.905, 0.826, 0.897, 0.842, 0.855, respectively; for COM: 0.923, 0.887, 0.899, 0.906, 0.894, respectively; for {Delta}OM: 0.958, 0.815, 0.937, 0.835, 0.940, respectively. Among positive cases, range of exact match accuracies for CTM (N=1354) was 0.730- 0.882 and range of JIs was 0.809-0.918. For {Delta}TM (N=404), exact match accuracy range was 0.619-0.780 and JI range was 0.668-0.827. For COM (N=47), exact match accuracy range was 0.766-0.872 and JI range was 0.765-0.870. For {Delta}OM (N=25), exact match accuracy range was 0.583-0.920 and JI range was 0.583-0.922. Conclusions: The GLLaucoMed pipeline demonstrated high performance in extracting and standardizing medication data from unstructured clinical notes, including both current medications and proposed changes. Claude and GPT exhibited the strongest performance.

Background Despite evidence that early intervention can prevent or delay progression to type 2 diabetes, more than 80% of individuals with prediabetes in the United States remain undiagnosed, underscoring the need for scalable strategies to increase uptake. In this study, we evaluated whether a single text message could increase completion of HbA1c-based diabetes screening in routine clinical practice. Methods We conducted a pragmatic randomized controlled trial within Duke University Health System (DUHS). Patients aged 35 years or older who met American Diabetes Association 2022 screening criteria, had no previous diagnosis of diabetes, had not undergone HbA1c testing within the preceding 3 years, and had opted to receive text messages from DUHS were randomly assigned to receive either a single text message encouraging guideline-based diabetes screening and discussion with a primary care provider (intervention group; n=55,494) or usual care (control group; n=5,748). The primary outcome was HbA1c test completion within 24 weeks following message delivery (or no message for controls), analyzed using a Cox proportional hazards model stratified by wave. Secondary outcomes included piecewise hazard ratios for early (weeks 1-4), mid (weeks 5-12), and late (weeks 13-24) intervals and the between-group difference in cumulative testing rate. Findings Text message outreach significantly increased HbA1c test completion over 24 weeks (HR, 1.18 [95% CI, 1.07-1.03]) with the strongest effect in the first four weeks (HR, 1.48 [95% CI, 1.18-1.86]). By the end of the 24-week observation period, cumulative testing reached 9.14% in the messaged group vs 7.83% in controls (between-group difference, 1.31% [95% CI, 0.59-2.07]), corresponding to one additional HbA1c test per 76 messages delivered ($0.51 in messaging costs per additional HbA1c test performed). Rates of prediabetes and diabetes among those screened were similar between groups, indicating no selection bias of higher-risk patients. One additional dysglycemia case was identified per 213 messages sent ($1.43 per case detected).

Background Antimicrobial stewardship in many settings assumes that community antimicrobial misuse reflects low awareness, and favours education-based interventions. Population-level evidence on healthcare seeking and antimicrobial practices in marginalised indigenous groups in low-income and middle-income countries is limited. We examined socioeconomic and identity-related determinants of healthcare-provider choice, antimicrobial awareness, and harmful antimicrobial practices in a tribal population in central India. Methods We did a cross-sectional survey of 1146 adults in the catchment area of Jan Swasthya Sahyog (JSS), a non-profit community health organisation, in Bilaspur and Mungeli districts, Chhattisgarh, India (January, 2021-April, 2022). Healthcare-provider choice was modelled with binary and multinomial logistic regression (government as reference), and antimicrobial awareness and ten harmful practices with logistic regression, applying Benjamini-Hochberg false discovery rate (FDR) correction within each family. A 30-day treatment-recall sub-study (n=284) assessed actual treatment location and out-of-pocket cost. Models with rare events or separation were refitted with Firth penalised regression. Findings Median per capita income was INR 8000 per year. Baiga identity was associated with higher odds of using informal (odds ratio 2.58) and private (2.55) providers rather than government facilities, but not JSS (1.36). Awareness of antimicrobials was 7.6% and was associated mainly with education (primary-or-less vs college 0.04). Baiga identity was independently associated with premature discontinuation (4.77), stopping for perceived intolerance (4.43), and financial discontinuation (6.81, 95% CI 3.51-13.25), but with lower odds of stopping because of perceived recovery (0.12). In the sub-study, predicted government-facility use was 1.6% for Baiga versus 18.1% for non-Baiga individuals. Findings were robust to Firth penalisation. Interpretation In this population, antibiotic non-completion was associated with poverty and access constraints rather than only with awareness, and a non-profit provider appeared to reach groups more equitably. Affordability-oriented, differentiated stewardship merits prospective evaluation. Findings are from a single catchment, are associational, and should be interpreted with the study's sampling in mind.