BMC Medical Research Methodology

Background: In prospective cohort studies, where an exposure is collected repeatedly, interest often lies in determining whether the timing of that exposure has a differential effect on a later outcome. The Structured Life Course Modeling Approach (SLCMA), where users select between temporal hypotheses of exposure specified a priori, provides one way to analyse such longitudinal data. However, few studies using SLCMA consider the effect of time-varying covariates (TVC) which may impact associations. Methods: We present a modified version of the SLCMA - called direct and mediated effects (DME)-SLCMA - which corrects for TVC. We first develop the DME-SLCMA method, test it through simulation, and apply it to psychosocial data from the Drakenstein Child Health Study (DCHS, n=336) to investigate relationships between maternal psychopathology, TVC of socioeconomic status, and offspring depressive symptoms. Results: We found that, on average, offspring depressive symptoms score increased by 3.9% (95% CI: 1.0%-6.9%, p = 0.039) for each unit of maternal psychopathology (SRQ) at 48 months whilst adjusting for time-varying socioeconomic status (at 18, 30, 42 and 54 months). Our simulations identified several realistic scenarios where selections ignoring TVC - with TVC mediated exposure effects present - were prone to be incorrect, including our DCHS example. Conclusion: DME-SLCMA is a robust new approach for life course modelling in the presence of time-varying covariates. We recommend adjusting for TVC whenever possible, and, when not possible, our simulation study identified that scenarios where mediated effects are comparable, or greater, in magnitude to direct effects are most prone to confounding.

Background: Medical registries have gained importance in the evaluation of healthcare quality outcomes. In the absence of high-quality evidence, such as randomized controlled trials, studies based on registry data are essential for informing clinical guidelines. Methods for assessing data quality are rarely described in detail. To ensure the credibility of registry-based studies, registries must use all available technical and operational means to guarantee high data quality. Method: Eurocrine(R) is a pan-European endocrine surgical database and quality registry initially funded by the EU healthcare programme, which started in 2015 and now includes more than 200,000 interventions as of April 2025. To ensure high data quality, interactive and standardized reports are created via Microsoft Power BI, which are created both centrally and locally. In addition, comprehensive data quality analyses were performed via the R-based package dataquieR. Results: Although a multitude of technical measures (for example, input screen design and real-time plausibility checks during data entry) are in place, they are not sufficient to prevent human errors at data entry. Errors identified in the reports were corrected, and preventive measures were implemented. Overall, the data quality was assessed as very good in terms of completeness, accuracy, and consistency. Conclusion: It is very important to provide registry users with an efficient and smart tool to identify data issues, as they have the clinical information to correct them. Data quality reports generated with dataquieR represent an effective tool for registry administrators. Predesigned Microsoft Power BI reports enable participating Eurocrine(R) clinics to self-audit their data.

Background: In the absence of high-resolution response data, exposure-response modelling often relies on aggregated low-frequency exposure data, leading to loss of high-resolution information. Mixed Data Sampling (MIDAS) from econometrics offers an alternative but is limited due to its inability to make high-resolution predictions, inflexible likelihoods and penalised nonlinear functions, and limited visualization options. We propose a mixed-frequency Distributed Lag Non-linear Model (mf-DLNM) which can eliminate the need to aggregate exposure data in environmental epidemiology and provide high resolution predictions for time series studies. Methods: We evaluated the inference and predictive performance of the mf-DLNM. To evaluate its ability to estimate exposure-response relationships, we applied mf-DLNM and same-frequency (sf)-DLNM using data from the West Midlands, UK. Additionally, we compared the predictive performance of mf-DLNM with sf-DLNM and MIDAS across nine regions of England. As MIDAS cannot predict at the resolution of the predictor (daily), we compared the predictive performance of mf-DLNM and MIDAS at weekly resolution. To test the model's ability to predict high temporal resolution risk (daily), we compared sf-DLNM (with access to daily mortality counts) with mf-DLNM (with access only to weekly mortality counts). Results: In the West Midlands example, mf-DLNM performed comparably to sf-DLNM in estimating daily risk of temperature on respiratory mortality. Furthermore, mf-DLNM and MIDAS exhibited similar performance for weekly predictions. For high-resolution predictions, mf-DLNM and sf-DLNM showed nearly similar performance, despite mf-DLNM having access only to low-resolution response data. Conclusion: This mixed-frequency approach in environmental epidemiology overcomes the limitations of predicting health risks using aggregated exposure data and provides estimates of high-resolution outcomes in the absence of high-frequency health outcome datasets.

Objectives: Study design indexing of biomedical publications is crucial for evidence retrieval and synthesis. We sought to evaluate the accuracy and suitability of a transformer-based model (TM) for indexing clinical study designs, in comparison to National Library of Medicine (NLM) indexing. However, this is challenging for at least three reasons: First, to date, all automated systems have been trained and evaluated on manual NLM indexing assignments, itself subject to errors. Second, TM's probabilistic predictive scores take into account uncertainty, and can be converted to TRUE/FALSE assignments in different ways depending on the needs of users, while NLM labels are categorical. Third, our goal (to tag articles only that exhibit a given design) differs from NLM which tags articles that both discuss as well as exhibit that design. Materials and Methods: Therefore, we carried out a limited evaluation of the TM model that focuses only on the articles that received the most confident predictions, that is, the highest scores that are almost certainly TRUE and the lowest scores that are almost certainly FALSE, but which disagreed with NLM assignments. This was performed both for articles published in 2016 (when NLM decisions were manual) and in 2025 (when NLM decisions were automated). To establish ground truth, dual annotators indexed the articles independently, following written definitions, for four prominent study designs--cohort, case-control, cross-sectional, and case report. Results: For three designs (case-control, case report, cross-sectional), the articles having the top 100 predictive TM scores (when NLM failed to assign that design) were judged to exhibit that design in the great majority (86-100%) of cases. Conversely, the articles having the lowest 100 predictive TM scores (when NLM did assign the study design) exhibited the design only in relatively few (0-21%) of cases. The most confident predictions of the TM model were highly accurate and not redundant with automated NLM indexing; the exception was cohort studies articles, in which both TM and NLM labels showed high error rates of both omission and commission. Discussion and Conclusion: TM may have value for identifying articles exhibiting study designs, which is especially important for clinical decision-making as well as systematic reviews and other evidence syntheses. NLM indexing of cohort studies cannot be regarded as a reliable gold standard for training or evaluation of automated systems, warranting efforts to create a new manually annotated corpus.

Background: Machine learning models trained on population health surveys offer scalable tools for cardiovascular screening, but recurring methodological weaknesses undermine their credibility and equity: data leakage from synthetic oversampling, qualitative rather than quantitative explainability evaluation, and the absence of demographic fairness auditing at the clinical operating threshold. Methods: We present EXHEART, a leakage-free stacked ensemble pipeline trained on BRFSS 2015 (n = 253,680) and validated on BRFSS 2020 (n = 319,795; temporal transport and retrain) and a clinical cardiovascular examination dataset (n = 68,730). The pipeline combines XGBoost, LightGBM, Random Forest, and a multi-layer perceptron as base learners with 5-fold out-of-fold logistic regression stacking and Platt scaling calibration. A quantitative SHAP-LIME consistency framework, based on Kendall-tau rank correlation and Jaccard overlap, accompanies a decision-curve analysis, a subgroup-stratified SHAP interaction analysis, and an intersectional fairness audit (Sex x Age x Income) with threshold-shifting mitigation and a frontier of the fairness-utility trade-off. The framework also adds cross-instrument fairness-disparity attribution, an empirical diagnostic that provides evidence on whether an observed subgroup disparity is more consistent with a measurement-induced or a substantive explanation by re-validating it on a dataset that measures the same clinical construct objectively. On heart disease, this diagnostic associates 89% of the sex TPR gap (95% CI [0.65, 0.99]) with the self-reported survey outcome rather than with a substantive risk difference. Results: On BRFSS 2015, EXHEART achieves AUC-ROC = 0.850, AUPRC = 0.371, Brier score = 0.071, and reduces ECE by 96% (0.256 to 0.011) via Platt scaling. Global SHAP-LIME rank agreement is moderate-to-strong (Kendall-tau = 0.580, Spearman-rho = 0.818) with a substantial top-3 divergence (Jaccard@3 = 0.200), where Stroke flips from SHAP rank 8 to LIME rank 1. The Sex TPR gap is 0.124 at the screening threshold; intersectional Sex x Age disparities reach 0.649 among adequately-powered cells, 5.2x the single-attribute gap. Temporal transport to BRFSS 2020 collapses sensitivity from 0.776 to 0.267, while retraining restores AUC = 0.840 and ECE = 0.012. On clinical examination data, the Sex TPR gap collapses to 0.014; the attribution test indicates this gap is instrument-dependent, consistent with a measurement or outcome-definition explanation rather than a substantive risk difference. Cross-domain SHAP analysis identifies four instrument-independent CVD risk factors and two major portability failures. Conclusions: EXHEART combines three practices that population-scale cardiovascular classifiers usually apply in isolation: leakage-free training with calibrated probabilities, a test of whether the model's explanations are stable, and a fairness audit that examines intersecting subgroups rather than single attributes. Bringing them together proved worthwhile. The intersectional audit revealed disparities that single-attribute auditing missed, and the cross-instrument comparison indicated that much of the sex gap reflects how the outcome is measured in survey data rather than a substantive difference in risk. The temporal transport findings indicate that deployed BRFSS models warrant periodic monitoring and retraining to maintain clinical utility. EXHEART is a retrospective methodological evaluation on public de-identified data; it is not validated for direct clinical decision-making, diagnosis, or treatment recommendation without prospective clinical validation.

Background Emergency department (ED) triage is a high-stakes clinical decision process that determines patient prioritization and resource allocation under time pressure. Large language models (LLMs) have recently been proposed as decision-support tools for triage, yet most evaluations rely on simulated scenarios or curated datasets. Evidence from real-world clinical environments remains limited. The objective of this project was to systematically evaluate the performance, calibration, and reproducibility of multiple contemporary large language models for Emergency Severity Index (ESI) classification and sectoral allocation (ED vs. urgent care practice, UCP) using a comprehensive real-world triage dataset. Material and Methods Retrospective cross-sectional benchmarking study conducted at a tertiary academic emergency ED in Germany with an integrated central point of assessment (CPA). The study included all consecutive adult walk-in encounters (>18 years) presenting between October 2023 and February 2024 (N = 16,107). Data were collected from a structured clinical decision support system capturing presenting complaints, vital signs, and triage decisions recorded by specialized nursing staff. Structured clinical variables routinely collected at triage, including presenting complaint categories (CEDIS-PCL), vital signs according to the ABCDE framework, and additional structured or free-text clinical information. Results The primary outcome was the agreement between LLM-predicted and nurse-assigned ESI levels measured using quadratic-weighted Cohen's k. Secondary outcomes included sectoral assignment agreement, misclassification patterns (over- and under-triage), calibration metrics, and output reproducibility. Quadratic-weighted k values ranged from 0.18 to 0.75 across models. Only a structured stepwise prompting strategy achieved substantial agreement (k_qw = 0.747), approaching reported human inter-rater reliability. Most models demonstrated moderate or lower agreement and systematic overconfidence, with expected calibration errors (ECE) based on verbalized confidence ranging from 0.099 to 0.355. Sectoral assignment agreement (i.e. ED vs. urgent care practice, UCP) was uniformly low (k < 0.30). Reproducibility testing revealed substantial variability in 23% of cases, indicating non-deterministic output behavior for clinically relevant decisions. Conclusions Current large language models demonstrate heterogeneous and generally limited performance in real-world emergency triage tasks. Structured algorithm-guided prompting appears more influential than model architecture or size. Before clinical implementation, improvements in calibration, reliability, and workflow integration are required, alongside regulatory-compliant validation in prospective clinical settings.

Objective: Clinical phenotyping methods that rely on clinical and informatics expertise can be time-intensive and costly. We tested both manual and highly automated approaches using electronic health record (EHR) data to identify an FDA Sentinel Initiative health outcome of interest, acute pancreatitis. Materials and Methods: We trained and evaluated machine learning algorithms using EHR data with two approaches: a custom approach that included manually curated features and trained on outcomes data validated with medical record review, and a highly automated approach that greatly simplifies and automates feature engineering and relies on low-cost silver-standard outcomes for model training. Results: Custom algorithms using manually curated structured claims data discriminated cases from non-cases with a high degree of accuracy (cv-AUC 0.89 [95%CI 0.84-0.94]); the inclusion of natural language processing (NLP)-derived covariates from clinical notes increased performance slightly (cv-AUC 0.91[95%CI 0.86-0.97]). The automated algorithm trained on the outcome count of diagnosis codes performed less well (AUC 0.80 [95% CI 0.75-0.85]) but improved using maximum lipase value as an outcome (AUC 0.88 [95% CI 0.84-0.92]). At a positive predictive value of 90%, the custom algorithm had a sensitivity of 92%, the automated algorithm trained on diagnosis code count had a sensitivity of 45%, and the automated algorithm trained on maximum lipase value had a sensitivity of 84%. However, a prediction rule derived by clinicians during chart review was nearly as accurate (maximum lipase value [&ge;] 3 times upper limit of normal; AUC 0.86, PPV 85%, sensitivity 92%). Discussion: Machine learning algorithms with manually curated structured data and NLP features trained on validated outcomes data successfully identified validated events. Use of an outcome in the automated model based on specific phenotype knowledge (maximum lipase value) allowed for performance similar to the custom model and with considerably less resources.

Abstract Background. Area-level cancer disparities are routinely estimated from public county data in which rates based on small counts (fewer than 16 cases or deaths) are suppressed. Analysts typically drop suppressed counties (complete-case analysis). Because suppression depends on case counts tied to population size and demographic composition, this missingness may be informative, but its effect on the disparity estimate has not, to our knowledge, been quantified. Methods. In a cross-sectional ecological study of 3,143 U.S. counties (analytic sample 3,018 with computable exposure) using one frozen public release of NCI State Cancer Profiles incidence and mortality data and ACS 2018-2022 5-year data, we estimated the most- versus least-deprived ICE(race+income) quintile rate ratio (RR) and rate difference for female breast, stomach, and cervix cancers under four suppression-handling methods: complete-case, available-case, bounding, and model-based small-area estimation. We characterized which counties were erased, and, following the ADEMP framework, ran a Monte Carlo simulation (1,000 replicates per cell; Monte Carlo standard error of bias approximately 0.0025) calibrated to the release to measure bias against a known truth. Analyses were pre-registered. Results. The suppressed fraction rose with rarity: 7.4% of counties for breast, 61.3% for stomach, and 75.7% for cervix incidence. Suppression was concentrated in the most-deprived quintile (cervix, 81.8% suppressed vs 63.8% least-deprived) and overwhelmingly removed rural rather than minority residents (cervix: 81% of the rural but 9% of the minority population erased). For breast (little suppression) the RR was 0.87 (95% CI 0.85-0.89) and identical across methods; for cervix incidence the complete-case RR (1.56) exceeded the model-based estimate (1.50), and for cervix mortality (91% suppressed) complete-case (1.86) exceeded model-based (1.56) by 16% with a wide bounding interval (1.88-2.62). In calibrated simulation, population-weighted complete-case bias was small (less than 2%) at the observed deprivation-county-size correlation and grew with rarity, threshold, and unweighted aggregation; its direction was conditional, becoming positive (over-estimation) as deprived counties became smaller. Conclusions. Complete-case handling of suppressed counties over-estimates rare-cancer area disparities relative to methods that retain them, while silently erasing most of the rural and most-deprived communities the estimate is meant to represent. The effect is negligible for common cancers and grows with rarity. Public-data disparity analyses should report the suppressed fraction and use bounded or model-based estimates by default. Keywords: cancer disparities; small-count suppression; Index of Concentration at the Extremes; informative missingness; small-area estimation; rural health.

Background: Epic Cosmos is a relatively new centralized electronic health record dataset with high potential utility in perinatal epidemiologic research. Objectives: The study objectives were to develop replicable steps to create longitudinal, linked maternal-infant cohorts in Cosmos, assess completeness of key variables, evaluate potential selection bias with restrictions for longitudinal healthcare encounters, and provide an example epidemiologic analysis. Methods: We created maternal-infant cohorts by starting with live births during 2023-2024 recorded in the BirthFact data table and joining with additional data tables as needed. We selected and created variables for perinatal characteristics, common comorbidities, and routinely measured vital signs and laboratory values, and assessed variable completeness. We sequentially restricted the birth cohort for maternal-infant linkage and longitudinal healthcare from first-trimester prenatal care encounter through infant follow-up care within 12 weeks post-discharge from birth hospitalization. Finally, we conducted an example analysis of the association between high systolic blood pressure in the first trimester ([&ge;]140 mm Hg) and later onset of preeclampsia among those with chronic hypertension. Results: The total linked birth cohort included 2,624,186 pregnancies. Completeness was >90% for most variables assessed but was 77% for racial and ethnic group and 76% for body mass index at delivery. Characteristics of the cohort were similar to those reported for the entire United States birth population based on birth certificate data, including similar regional and racial-ethnic composition. Longitudinal cohort restriction requiring linked records from first trimester prenatal care through infant follow-up care reduced the cohort size to 509,148 pregnancies. However, restriction had minimal effects on cohort characteristics. In the example analysis, high systolic blood pressure was associated with increased risk of preeclampsia among those with chronic hypertension (aRR: 1.26; 95% CI: 1.22, 1.30). Conclusions: This study provides a rigorous and reproducible approach to creating longitudinal, linked maternal-infant cohorts in Epic Cosmos and the analytical findings suggest high data quality and representativeness.

Objective: To evaluate whether a locally hosted open-weight large language model (LLM) can extract documented psychosocial factors from pediatric psychiatric intake notes and apply validated extraction to a large emergency psychiatry cohort. Materials and Methods: We identified emergency department presentations at Cincinnati Children's Hospital Medical Center from January 1, 2016, through December 31, 2024, among patients younger than 18 years with psychiatric billing diagnoses. Using full-text intake notes, gpt-oss:120b classified peer conflict, sleep disruption, and school-related academic, attendance, and disciplinary issues as detected, negated, or indeterminate. Four human raters independently reviewed 50 notes. We compared Fleiss' kappa among humans alone versus humans plus the LLM, assessed repeated-query stability across 50 independent calls per note, and applied the workflow to all eligible notes. Results: Among 37,315 eligible admissions, 22,284 had eligible intake notes; 22,270 produced parseable JSON. In detected-versus-not-detected coding, human-plus-LLM reliability did not differ significantly from human-only reliability across measures (human {kappa} 0.71-0.94; human-plus-LLM {kappa} 0.70-0.93). Stability was associated with human agreement: mean LLM-human agreement increased from 42.6% for classifications with less than 80% stability to 82.7% for classifications with 100% stability (Pearson r = 0.36). Full-cohort extraction showed frequent and overlapping documented factors: sleep disruption was most frequently detected (57.7%), followed by peer conflict (47.2%), academic issues (43.4%), disciplinary issues (43.3%), and attendance issues (16.9%). Discussion: Agreement varied by construct and was strongest when repeated model outputs were stable. Conclusion: Locally hosted open-weight LLMs can support scalable structured extraction of documented psychosocial factors from pediatric psychiatric intake notes after local validation.

Background: The traditional wealth index, based on principal component analysis (PCA), used in the Demographic and Health Surveys (DHS) and Multiple Indicator Cluster Surveys (MICS), suffers from urban bias, distorting estimates of health inequality. We compared the traditional index (PEAR1) with an alternative two-component polychoric PCA index (POLY2) using annual expenditure from 12 LSMS surveys as the gold standard to determine which provides more accurate SEP measures for equitable policy targeting. Methods: We compared the traditional wealth index (PEAR1) with a two-component polychoric PCA approach (POLY2) using 12 LSMS (Living Standards Measurement Study) surveys (2015-2022) from 12 African countries. Annual household consumption expenditure was the gold standard. We assessed agreement using weighted Cohen's kappa and validated against education (proportion of households with secondary or higher education) using the concentration index (CIX) and slope index of inequality (SII). Results: The POLY2 index showed higher agreement with expenditure quintiles (average national weighted kappa = 43.3%) than the PEAR1 index (35.1%), with notable improvements in urban (43.5% vs. 27.5%) and rural (35.3% vs. 22.4%) areas. POLY2 also attenuated extreme household distributions observed in PEAR1. Education validation showed that POLY2 produced intermediate inequality gradients between the flatter expenditure-based gradient and the steeper PEAR1-based gradient. Conclusion: The POLY2 wealth index is superior to the traditional index, reducing urban-rural bias and providing more accurate socioeconomic classifications. Its adoption in large-scale surveys such as DHS and MICS is recommended to improve equitable monitoring of health inequalities in low- and middle-income countries.

Background Electronic health record documentation patterns may reflect workflow complexity, monitoring intensity, and operational strain in intensive care settings. However, documentation-derived features can be sensitive to local documentation culture, data capture systems, and outcome definitions. Retrospective validation across multiple datasets is therefore needed before these signals are used in workflow intelligence or clinical AI governance tools. Objective To evaluate whether documentation-density and documentation-timing features show reproducible retrospective signal for ICU workflow complexity and long-stay proxy outcomes across de-identified critical care datasets, while distinguishing workflow and long-stay associations from unsupported claims about mortality prediction, burden reduction, or deployment readiness. Methods We synthesized retrospective validation results from de-identified ICU and workflow datasets generated through a prespecified documentation-density validation program. Feature families included Documentation Burden Score style features, Shift-End Documentation Rate style features, documentation reliability style metadata, and all-documentation feature sets where available. Outcomes included long ICU length of stay proxies, mortality where available, and workflow proxy endpoints. Models compared baseline feature sets with enhanced models containing documentation-density or workflow features. Performance was summarized using area under the receiver operating characteristic curve, Brier score where reported, delta AUROC, bootstrap confidence intervals where reported, and label-shuffle controls where available. Results The strongest external long-stay proxy evidence came from the NWICU chartevents analysis, which included 28,612 ICU stays, 20,267 stays with chart events, and 9,619,759 chart events. For ICU length of stay greater than the median, baseline AUROC was 0.5252. Enhanced AUROC was 0.9512 for Documentation Burden Score features, 0.9214 for Shift-End Documentation Rate features, 0.8470 for documentation reliability style features, and 0.9517 for all documentation features. Corresponding label-shuffle enhanced AUROCs were near random, ranging from 0.4897 to 0.5064. For ICU length of stay greater than the 75th percentile, baseline AUROC was 0.5155. Enhanced AUROC was 0.9433 for Documentation Burden Score features, 0.9194 for Shift-End Documentation Rate features, 0.8118 for documentation reliability style features, and 0.9427 for all documentation features, with label-shuffle enhanced AUROCs from 0.4836 to 0.4999. Additional retrospective support was observed in eICU workflow analyses, HiRID first-24-hour documentation-density analyses, MIMIC-IV HF ICU internal analyses, MIMIC-IV-Note metadata extensions, and nursing-chart or lab density proxy analyses. However, cross-institution discrimination transfer was weak without recalibration, and several analyses remained proxy validations rather than final clinical validations. Conclusions Documentation-density and documentation-timing features show promising retrospective signal for ICU workflow complexity and long-stay proxy outcomes, especially in NWICU chartevents and selected internal dataset-specific analyses. These findings support further preregistered, prospective, silent-mode validation of documentation-derived workflow intelligence. They do not establish prospective clinical performance, mortality reduction, clinician burden reduction, autonomous deterioration prediction, or deployment readiness.

Large language models (LLMs) such as ChatGPT are rapidly reshaping healthcare education and simulation-based training in non-technical skills (NTS), yet no bibliometric analysis has mapped this landscape. We searched seven open-access databases (OpenAlex, PubMed, Europe PMC, Crossref, Semantic Scholar, CORE, DOAJ) for English-language publications from January 2020 to March 2026. From 100,277 initial records, a sequential keyword funnel yielded 830 candidate papers, which were screened by 83 independent Claude Sonnet 4.6 AI agents applying pre-specified inclusion criteria (PRISMA-trAIce compliant; Cohen's kappa = 0.86 pre-reconciliation, 1.0 post-reconciliation). The final AI-verified corpus comprised 551 papers with a compound annual growth rate of 109%, contributions from 2,398 authors across 279 journals in 58 countries, and an h-index of 41. ChatGPT dominated the model landscape (46% of papers), with open-source models virtually absent. Virtual patient chatbots were the leading simulation modality (106 papers). Among NTS domains, communication (145 papers) and decision-making (135 papers) were most studied, whereas teamwork, leadership, situational awareness, and crisis resource management were markedly underrepresented. Only 6 urology-relevant papers were identified, none examining LLM integration within boot camp training formats. The field is growing at extraordinary pace but remains concentrated in a narrow range of NTS domains and a single proprietary model. Critical gaps persist in team-based skills training, open-source model evaluation, and specialty-specific simulation. AI-assisted bibliometric screening using multiple independent agents is feasible, reliable, and scalable, offering a replicable methodology for mapping fast-evolving research fields.

Introduction Education is a core social determinant of health for children and adolescents. Unfortunately, academic achievement, health, and wellbeing of adolescents have decreased in many developed countries in the past decade. The purpose of the Wellbeing and Education linkages in school-aged children (WELL-ED) study is to examine associations of school absences and academic achievement with use of school-based and community-based health and social welfare services. In addition, we will assess user experiences and multi-sector services pathways of school-aged children for a better understanding of how the service system could respond to the needs of children. Methods and analysis WELL-ED is a large population-based study that combines register data on school absences and educational support from municipalities with register data on healthcare and social service use collected from wellbeing services counties in Finland. The study cohort includes all children who attended mandatory education in public schools in Southern Finland in school year 2023-2024. A smaller cohort of adolescents in school year 8 was invited to complete a user experience survey. The primary outcomes of this study are related to equity of service use. Ethics and dissemination The Regional Committee on Medical Research Ethics of the Helsinki and Uusimaa Hospital District (2803/2024) has approved the WELL-ED study protocol. For the survey, adolescents in year 8 and parents of adolescents younger than 15 provided informed consent. Results will be published in peer-reviewed journals, summaries will be sent to participating municipalities and wellbeing services counties and press releases will be written on key findings.

Accurate outbreak forecasts are critical for timely and effective public health response. In the United States, however, most forecasts are produced at the state level, which can mask substantial sub-state heterogeneity and limit their utility for local planning. We generated and evaluated forecasts of the percentage of Emergency Department visits attributable to influenza across 173 large metropolitan Health Service Areas (HSAs) using a gradient boosting quantile regression (GBQR) model, and compared their accuracy to forecasts derived from state-level data alone. At a one-week, two-week and three-week horizon, local forecasts outperformed state-based forecasts in 98.8%, 90.8%, and 78.6% of HSAs, respectively, achieving mean weighted interval scores that were on average a 39.2% lower (95% range: 5.9% to 76.7%), 19.6% lower (-6.3% to 59.5%) , and 11.4% lower (-11.7% to 44.9%), respectively. The performance advantage of local forecasting was strongest in HSAs representing a smaller share of their state's population and increased with the proportion of the HSA population living in urban areas and the number of metropolitan areas within a state. These results, based on an analysis of HSAs with populations greater than 250,000, demonstrate that fine-scale modeling can substantially improve forecast accuracy and highlight the potential value of local forecasts for outbreak preparedness and response.

End-of-rotation handoffs are critical for patient safety but add to documentation burden for hospitalists. Generative artificial intelligence (AI) may help automate handoff creation using electronic health record data, but its impact on quality and safety is unclear. Methods: We developed an AI handoff tool with a large language model using clinical notes as input and conducted a retrospective evaluation comparing AI-generated and clinician-authored handoffs. Handoffs were assessed across domains of quality and safety through a structured review. Results: Quality ratings were similar between AI and human handoffs (3.7 vs. 3.5, p=0.57). AI-generated handoffs were rated higher for organization (4.4 vs. 4.1, p=0.05) and completeness (4.1 vs. 3.6, p=0.01), but lower for conciseness (3.7 vs. 4.1, p=0.03) and accuracy (4.1 vs. 4.4, p=0.03). Error rates were comparable (0.3/handoff in both groups); however, AI-generated handoffs included inaccuracies (9% of AI errors) and hallucinations (1% of AI errors), while clinician-authored handoffs contained only omissions. Conclusion: Human and AI handoffs have differing error profiles and tradeoffs between completeness and conciseness. Prospective evaluation in clinical workflows is underway.

Background: Electrolyte replacement is ubiquitous in the acute care setting, but its familiarity cannot belie that even small dosing errors with potassium can cause lethal cardiac arrhythmias. Recently, MedAgentBench offered a benchmark for agentic artificial intelligence (AI) including the ability to correctly dose potassium based on a single rule; however, this does not adequately reflect the clinical complexity or safety concerns of an agent that has been used as the lethal injection. The purpose of this analysis was to a probe leaderboard large language model (LLM) capabilities to follow basic dosing rules to safely replace potassium in a series of clinician-annotated cases. Methods: Using a clinician panel, we developed a series of dosing principles and 20 clinical cases reflective of the complexity of potassium replacement. External clinicians were surveyed to assess practice variability and agreement to clinician panel answers. We tested GPT-5-chat with each case in triplicate, with and without the clinician curated dosing principles, and prompted the model to answer six questions involving potassium goals, dosing, route, lab frequency, concurrent interventions, and the model's perceived level of confidence for the output and complexity of the case. The primary outcome was the rate of appropriate recommendations in comparison to clinician answers. Results: A total of 54 clinicians reviewed the 20 hypokalemia cases and hypokalemia dosing guideline. Clinicians expressed "highly agree" or "somewhat agree" for 66.8% of the cases evaluated when asked if they agree with the guideline-recommended management. When given the potassium dosing guideline, total errors dropped from 165 to 104, and average accuracy improved from 45% to 65% with GPT-5-Chat. GPT-5-Chat conveyed a high level of confidence for 100% of responses, while labeling 80% and 76% of cases as highly complex with and without the criteria, respectively. Potential harm scores were considerable in both groups, however, a notable reduction in severity scores occurred with the dosing guidance document. Recommendations on concurrent interventions and dosing had the highest rate of errors in both groups. Conclusions: Benchmarks must appropriately reflect clinical complexity to be considered valuable for the deployment of agentic artificial intelligence tools in the healthcare domain. GPT-5-Chat assessment on a comprehensive medication management task for potassium replacement showed improvement with dosing guidance, yet unfit benchmarking performance.

Background: Mass gathering events (MGEs) are associated with several public health challenges and may cause a strain on healthcare services. Literature findings on the impact of MGEs on emergency departments (EDs) are heterogeneous. Objectives: To examine shifts in ED attendance characteristics during a major sporting tournament, namely the UEFA European Football Championship 2024 held in Germany. Methods: We conducted a retrospective observational study using ED data from the Emergency Department Data Registry. We compared baseline ED attendance characteristics between the tournament and the reference period, defined as two weeks before and two weeks after the tournament, and between Germany game days and non-Germany game days. Hourly attendance patterns were analysed for all Germany games using a reference range. Results: We included data from 41 EDs, totalling 253,493 attendances during the study period. A 1.57% increase in attendance was observed during the tournament compared to the reference period, with baseline characteristics remaining similar. The median daily attendance within all EDs was slightly lower on Germany game days (4066) compared to non-Germany game days (4128). Modest changes were observed in the hourly attendance on Germany game days, most notable during the last Germany game where a decrease in attendance below the reference range extended over three hours. Conclusions: The observed shifts in ED attendance were minimal, suggesting that no major changes of public health relevance occurred in ED attendance during the tournament. We highlight the utility of using ED data for monitoring and for enhancing the understanding of the public health risks and challenges associated with MGEs.

Background: Vascular cognitive impairment (VCI) and small vessel disease (SVD) involve many interconnected factors influencing multiple outcomes, also beyond cognitive decline. Bayesian networks (BNs) can help unravel these complex interrelations, which we demonstrate in this proof-of-concept study in the Heart-Brain Connection cohort, including memory-clinic patients with SVD, patients with heart failure, carotid occlusive disease, and reference participants. Methods: We trained BNs and jointly modelled cognitive decline (Clinical Dementia Rating (CDR) increase) and major adverse cardiovascular events (MACE) over five years as outcomes in relation to multiple demographic and disease factors and emerging imaging and plasma biomarkers, also considering possible non-random dropout. Results: Of 566 individuals (median age 68, 64% men), 134 had MACE and 112 experienced CDR increase. Diagnostic group and baseline cognition were key determinants of both outcomes. The BN identified baseline clinical severity as a non-random dropout source. Plasma biomarkers formed an interconnected subnetwork, linked to demographic and vascular factors, but without direct dependencies with outcomes. The trained BN also provides individualized inference under partial evidence, informing on outcome probabilities. Conclusion: This proof-of-concept study demonstrates how BNs quantify and visualize the dependency structure underlying prognostic heterogeneity in VCI and SVD, including non-random dropout and positioning of emerging biomarkers.

Background: Whole-population linked administrative data platforms provide an opportunity to generate evidence on early life multidimensional disadvantage to inform resourcing and service provision to families with complex needs. Methods: We used individual-level de-identified data from nine administrative data sources included in the Better Evidence Better Outcomes Linked Data (BEBOLD) platform. The population included all children born in South Australia between 2004-2011 (n=143,083), and their parents. We described the prevalence and distribution of multiple disadvantages affecting children from the 12 months before birth to age 5. Eleven domains of parental disadvantage were created: economic, education, access to services, mental health, substance misuse, smoking during pregnancy, domestic and family violence, health, child protection contact, justice system contact, and death. We investigated the concordance of our measure with an area-level socioeconomic measure used in government reporting. Results: One in two children (48%) were exposed to at least one disadvantage domain, and one in seven (14%) were exposed to three or more domains before age five. Economic disadvantage was most prevalent, affecting one in four (27%) children, of which 75% were exposed to additional forms of disadvantage. Substance misuse, domestic and family violence, and justice system contact were the least likely domains to occur in isolation. Only 54.4% who experienced five or more disadvantage domains were classified in the area-level socioeconomic measure's 'most disadvantaged' quintile. Conclusion: Early life exposure to parental disadvantage can be highly multidimensional. Measurement across different systems is important for informing coordinated service provision for families with complex needs.