BMC Medical Informatics and Decision Making

Background: Conventional discrimination metrics, such as the area under the receiver operating characteristic curve (AUROC), do not characterize the composition of outcomes among patients flagged as high risk by clinical prediction models. This limitation is particularly relevant in critical care, where competing deaths and incomplete follow-up can complicate the interpretation of prediction alerts. We developed the Balanced Risk Integrity Index (BRII), a stratum-level metric defined as the proportion of target events among target events, competing deaths, and early-censored observations in a flagged high-risk stratum. BRII is algebraically related to positive predictive value (PPV) and is reported alongside its component decomposition to characterize the outcome composition of flagged patients. Methods: We evaluated BRII using seven acute kidney injury (AKI) prediction models developed in MIMIC-IV and externally validated in MIMIC-III and eICU-CRD (116,010 patients in total). Additional simulations examined the effects of competing deaths and early censoring on BRII and conventional model performance metrics. Results: For 48-hour AKI prediction in the top 10% risk stratum, BRII ranged from 0.90 to 0.96 in MIMIC-III, compared with less than 0.26 across all models in eICU-CRD, where 61.5% of evaluated patients were censored before the prediction horizon. In the eICU-CRD top 10% strata for the same target, 37.0% to 50.2% of patients were censored early, 12.2% to 15.5% had AKI, and 3.4% to 8.1% died before AKI. BRII and PPV ordered at least one model pair differently in 34 of 48 cohort-outcome-top-k groups. Under simulated random censoring for 48-hour AKI prediction, BRII declined by up to 0.80 while binary-label AUROC changed by less than 0.02. Conclusions: BRII provided complementary information on high-risk stratum composition, yielding different model rankings from PPV and revealing substantial differences across external validation cohorts. Interpreted alongside PPV and its component decomposition, BRII offers a standardized approach to evaluating clinical prediction alerts across models and observation environments.

Background and Objective: The volume of patient portal messages has grown substantially and artificial intelligence (AI) can support clinical staff and improve the timeliness of patient care. Our objective is to test if an AI tool for managing the electronic inbox In-Basket reduces response times to patient portal messages in neurology. Methods: We conducted an implementation study from January to May 2026 in the neurology department at two clinical sites within a regional medical system. A single AI tool was implemented to auto-categorize and auto-route all patient messages received in the electronic inbox. The tool also generates optional draft replies to messages. Primary process measures were the median weekly time (hours) from message creation to the first action and to closure. Impact was analyzed using a controlled interrupted time-series (ITS) design, comparing message-volume-matched control divisions. Results: Among 24,142 messages analyzed, pre-intervention median weekly time to first action was 11.3 hours [IQR: 5.6, 15.1] (Site A) and 16.1 hours [IQR: 13.8, 19.0] (Site B), falling post-intervention to 1.0 hour [IQR: 0, 3.1] (Site A) and 0.6 hours [IQR: 0.2, 2.4] (Site B). Controlled interrupted time-series analysis showed a significant immediate differential level change in median weekly hours to first action at Site A (-92.5%, 95% CI: -97.5% to -78.0%), and a significant downward trend at Site B (-43.5%, 95% CI: -65.2% to -8.2%). Changes in time to closure were directionally favorable but not statistically significant at either site. There was low use of the generated draft replies, only 0.5% at Site A and 3% at Site B. Discussion: Implementation of AI-assisted message categorization and routing was associated with a substantially reduced initial action time for patient In-Basket messages in Epilepsy. The utilization of AI-generated draft-replies to messages was low. These findings support the feasibility and effectiveness of AI-augmented workflows to improve inbox management.

Biomedical artificial intelligence (AI) increasingly relies on heterogeneous data sources, yet differences in data structure, terminology, evidence quality, and provenance complicate their integration into reliable knowledge resources. Here, we develop an evidence-aware framework for processing and integrating heterogeneous pharmacovigilance data from FDA Adverse Event Reporting System (FAERS) reports, biomedical literature, clinical trials, and electronic health records in Mass General Brigham. The framework combines large language model (LLM)-based information extraction, ontology-driven semantic normalization, cross-source evidence assessment, statistical and machine learning-based prioritization, and ingredient-based adverse drug event (ADE) relationship inference to transform heterogeneous evidence into a structured and evidence-based knowledge resource. The constructed knowledge system contains 11,588 drug nodes, 44,843 ingredient nodes, 3,275 ADE nodes, 993 indication nodes, and more than 2.47 million relationships, with each drug-ADE relationship assigned a confidence score. We further developed a drug-level web interface for accessing the knowledge resource and validated its utility in downstream AI tasks. Specifically, incorporating the developed knowledge resource improved the comprehensiveness, relevance, and overall quality of LLM-based drug-specific ADE synthesis and improved the precision and F1 score of clinical ADE relation extraction. These results demonstrate that AI-assisted processing combined with evidence-aware curation can transform heterogeneous biomedical evidence into reusable, AI-ready knowledge with explicit provenance and evidence strength information. The framework provides a general strategy for integrating heterogeneous biomedical data to support reproducible knowledge construction and downstream biomedical AI applications.

Objective: To determine how cohort versus nested case-control (NCC) design affects EHR-based prediction of a rare outcome. Materials and Methods: We compared two cohort and five NCC designs for predicting early-onset gastrointestinal cancer using L1-regularized logistic regression (LASSO), XGBoost, and multilayer perceptron (MLP). Models underwent nested five-fold cross-validation with model-specific hyperparameter tuning and temporal evaluation in a held-out prospective cohort representing intended deployment. Model discrimination was assessed using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). Model calibration was assessed using Brier scores and calibration plots before and after recalibration with isotonic regression. Feature-ranking similarity was quantified using rank-biased overlap. Results: The cohort development datasets included 256,854-415,529 patients, with 2-yr cumulative incidence of 0.12%-0.17%, compared with approximately 9% in the 1:10 matched NCC datasets. NCC designs generally produced higher internal discrimination, but temporal performance varied by algorithm and index-date definition. Cohort designs achieved the highest temporal AUPRC for LASSO (0.068), whereas diagnosis-anchored NCC achieved the highest temporal AUPRC for XGBoost (0.086) and MLP (0.070). Temporal AUPRC generally decreased as the required lead time before diagnosis increased. Raw predicted probabilities substantially overestimated observed risks in the temporal cohort. Isotonic recalibration improved probability scaling while largely preserving discrimination, although residual miscalibration remained. Cohort-based feature rankings were more consistent across algorithms, whereas NCC-based rankings depended more strongly on algorithm and index-date anchoring. Conclusion: Study design should be selected and evaluated according to the intended clinical prediction task and deployment setting.

Stroke is a leading cause of mortality and disability in Uganda, with a prevalence of approximately 2.5% and a 25-30% 30-day mortality rate, exacerbated by limited access to predictive tools and advanced diagnostics. Machine learning (ML) offers potential for early stroke risk stratification, but its application in resource-constrained settings like Uganda requires tailored models and rigorous performance evaluation, as well as assessment of misclassification patterns. This study aimed to develop and internally validate an ML-based predictive model for stroke using clinical and socio-demographic characteristics among patients at Mulago National Referral Hospital (MNRH) and residents of Wakiso District, Uganda, identify key predictors and assess misclassification patterns to enhance targeted prevention. A retrospective case-control study utilized secondary data from 1,016 participants (254 stroke cases, 762 controls) across three prior studies conducted between 2006 and 2015. Eight ML algorithms were evaluated using 5-fold cross-validation, with performance metrics including accuracy, sensitivity, positive predictive value, F1-score, and area under receiver operator characteristics curve (AU-ROC). McNemars test compared model classification performance of the top 2 models. Feature importance identified key predictors, and misclassification patterns were analyzed using classification matrix and line graphs. The Random Forest (RF) model achieved the highest performance (95.18% accuracy, 90.10% F1-score, 97% AU-ROC). McNemars test confirmed RFs superior classification (p=0.01). Age, systolic blood pressure, total cholesterol, and waist-hip ratio were the top drivers of RF stroke predictions. RF misclassified 8.3% of stroke cases and 3.3% of non-stroke cases, due to overlaps in risk profiles (e.g., lower cholesterol, systolic blood pressure and age in false negatives). The RF model demonstrates strong potential for stroke risk prediction in Uganda, leveraging routine data to prioritize high-risk individuals. Misclassification analysis highlights areas for model refinement, supporting its potential for integration into clinical workflows for early intervention and stroke prevention in resource-limited settings. Future external validation across diverse populations is recommended.

Awareness of comorbidities in people with dementia is vital context for dementia research and clinical management. Natural Language Processing (NLP) applied to free text in the electronic health record (EHR) may help ascertain comorbidity presence. Our aim was to assess the validity of the MedCAT Comorbidity NLP app in a cohort of people with dementia. We used text from the EHR of South London and Maudsley NHS Mental Health Trust via Clinical Records Interactive Search (CRIS), linked to structured data from local primary care (Lambeth DataNet) and hospital admission data in a cohort of 3,543 people with dementia. We evaluated MedCAT Comorbidity, examining internal validity via manual review of text and external validity by cross-validation against linked primary care and hospital data; and comparison of the predictive value of comorbidity measures for mortality. Internal precision was highest for atrial fibrillation (100%) and lowest for diabetes (78%). Cross-validation with linked data varied substantially across conditions, with precision from 96% to 59% and recall 77% to 4%. The median number of comorbidities identified was two using any single source, or three when combined. MedCAT Comorbidity demonstrated predictive ability for mortality (HR 1.11 per condition), although the model fit was better using comorbidity from hospital admission data. In people with dementia, the MedCAT Comorbidity app showed high precision for most conditions during internal validation. The variability of precision and recall on external validity assessment partly reflects incomplete documentation. Results from the MedCAT comorbidity app can assist researchers in understanding comorbidity of cohorts, particularly when primary care or hospital data is not available. Our findings highlight the need to develop quality assurance protocols that include internal and external validity checks before deploying general data extraction apps for specific clinical subpopulations.

This paper examines the impact of Cancer Care Ontario's regionalization of lung cancer surgery on blood transfusion use for thoracic surgery at The Ottawa Hospital. Using aggregate data scraped from the paper ''Changing trends in blood transfusion: an analysis of 244,013 hospitalizations'' by Shehata et al. (2014) we estimated the effect regionalization on the log mean number of blood transfusions among thoracic surgeons (who treat lung cancer), utilizing other surgical specialties as controls. We found that the average number of blood transfusions increased significantly among thoracic surgeons following the opening of a new cancer care centre at the hospital in December 2009, while control specialties showed no parallel change. Contextualizing these results in a modified ''population level'' treatment threshold model, it is argued that the main driver of this increase in blood transfusions among thoracic surgeons was due to the influx of less skilled thoracic surgeons to The Ottawa Hospital, and the closing of thoracic surgery units at smaller hospitals which was part of the broader regionalization process.

Personalized medicine aims to tailor treatments to individual patients, but its implementation is limited by scarce clinical resources and heterogeneous treatment effects. Electronic health records now offer longitudinal data that can support data-driven therapy selection. We focus on SGLT2 inhibitors, medications with broad metabolic and cardiovascular benefits, whose clinical impact varies significantly based on individual patient profiles. We propose a counterfactual Structural Causal Model (SCM) to estimate individual treatment effects (ITE) of SGLT2 inhibitors from observational data. The model assumes counterfactual stability and uses a Gumbel-Max sampling mechanism to capture stochastic treatment assignment while enabling differentiable inference. Optimal treatments are defined by maximizing the counterfactual value of future diagnostic outcomes. We evaluate the Counterfactual Gumbel-Max SCM using a doubly robust value estimator and show that, across diagnostic categories, it outperforms real-world prescriptions in predicted treatment value, highlighting subpopulations where SGLT2 inhibitors yield superior outcomes. By integrating causal inference with electronic health data, this framework provides individualized counterfactual reasoning about SGLT2 treatment effects and can support clinicians in identifying optimal therapies for type 2 diabetes and comorbid conditions.

Background. Research data enclaves such as the All of Us Research Program do not allow participant-level data, or models fitted to them, to leave, which makes it hard to deliver case-finding models, which flag patients with possibly uncoded conditions for clinician review, to patients and clinicians. Objectives. We describe and technically evaluate a system that fits models outside an enclave from released summary counts and delivers them through standard health information technology interfaces. Methods. We exported dissemination-compliant summary counts from the All of Us Researcher Workbench and, outside the enclave, fitted versioned models for Long COVID, chronic fatigue, fibromyalgia, endometriosis, Lyme disease, lupus, migraine, depression, and anxiety. A model contract (a model file and a written specification), a Python reference implementation, and synthetic Fast Healthcare Interoperability Resources (FHIR) test patients define the expected outputs. One JavaScript scorer runs in a patient demonstration, a SMART on FHIR clinician application, and a CDS Hooks service. An atlas displays aggregate results. We evaluated the system on synthetic records with automated tests, cross-implementation output comparison, launches through the public SMART sandbox, and a counterexample review of the scoring and display rules. Results. The deployed Long COVID model had an area under the receiver operating characteristic curve of 0.67 in a random validation split. The eight self-report models reached 0.61 to 0.82 in identifying self-reporters without a code. The JavaScript scorer reproduced all 162 reference outputs exactly, and all 437 automated tests passed. A counterexample review found 5 classes of failure, including scoring ineligible patients and treating unavailable data as absent, all fixed and added as tests. Conclusions. Models fitted from released summary counts can be delivered through FHIR, SMART on FHIR, and CDS Hooks with reproducible scoring on synthetic records. Real-record interoperability, usability, and prospective clinical performance remain to be evaluated.

Large language models (LLMs) are increasingly evaluated for clinical tasks, but safe use requires reliable uncertainty estimates as well as high accuracy. We tested eight general-purpose LLMs on 100 validated neurology board-style multiple-choice questions and compared three confidence signals: self-reported confidence, critique-implied confidence from an independent model instance, and consistency-based confidence from repeated sampling. Accuracy varied from 45% (Llama 3.1 8B) to 92% (Gemini 3 Flash/Pro), but confidence was generally overestimated, particularly in lower-accuracy models. Consistency-based confidence provided the best discrimination between correct and incorrect answers (pooled AUROC 0.74), outperforming self-report, although calibration differences between methods were not significant. Calibration should therefore be reported alongside accuracy when clinical LLMs are evaluated.

Background. Regulatory pressure to avoid confusingly similar drug names appears to have pushed manufacturers to coin more distinctive proprietary names, but no one has quantitatively analyzed this trend. Objective. To determine whether proprietary drug names became more orthographically distinctive (unusual in spelling) over time. Methods. We examined 1,321 US Food and Drug Administration (FDA) new molecular entity (NME) names (1985-2024), 2,769 FDA Orange Book trade names (1982-2026), 177,337 US pharmaceutical trademarks (1980-2026), and 1,273 generic names (1982-2025). Compared to prior names (including those already marketed) and ordinary English, we scored each name's character trigram (three-letter sequence) surprisal (statistical unexpectedness) and its edit-distance similarity to the closest existing names. Linear regression tested time trends, controlling for name length. Results. Mean NME trigram surprisal rose in every decade between the 1980s and 2020s, from 7.21 to 8.50 nats (natural-logarithm units, higher meaning less predictable), an 18% increase (b = 0.038, p < .001, R2 = 0.34). Half of 2020s names (7% in the 1980s) contained a letter sequence found in no common English word (e.g., Jesduvroq, Omvoh). Nearest-neighbor similarity fell after the early 1990s. Trademark data showed the same trend (b = 0.016, p < .001). Generic names showed a weaker trend (b = 0.011, R2 = 0.063). Conclusions. Over four decades, drug names became more orthographically distinctive, consistent with namespace crowding, deliberate efforts to avoid confusing names, and branding strategy. Because unfamiliar letter sequences can introduce other error pathways, increased distinctiveness does not necessarily imply improved safety.

INTRODUCTION: The digital clock drawing test (dCDT) is a cognitive screening tool capturing high-resolution pen-movement data. Existing approaches for classifying cognitive impairment from dCDTs rely on selected features or image-based methods. We propose representing dCDTs as structural networks to classify cognitive impairment and characterize spatial organization in clock drawings. METHODS: Weighted networks were constructed from 3,362 Framingham Heart Study participants, with and without cognitive impairment. Network representations were generated separately for command and copy conditions, with nodes representing pre-defined clock components (digits, hands, clock face) and edges capturing pairwise spatial relationships between components. Random forest models and graph convolutional networks were trained to predict cognitive impairment from the networks. Models were benchmarked against demographics-only and established summary feature baselines. RESULTS: Network-based models achieved AUC values comparable to the established summary feature baseline across command-only and copy-only conditions. Differences in spatial organization between the cognitively intact and impaired groups were greatest in the upper-right clock region, involving digits 1 and 2, the clock hands, and the surrounding clock face. Differences between the command and copy networks were larger among cognitively impaired participants. DISCUSSION: The proposed network representations provide an objective, scalable, and flexible framework for representing clock drawings for use in classification models. dCDT networks matched the predictive performance of established summary feature-based approaches and identified clock regions where spatial organization differed by cognitive status. After external validation, this approach has the potential to be incorporated within a clinical workflow to support automated and interpretable cognitive screening.

Clinical records routinely document medical interventions but often omit the reasoning connecting patient-specific evidence to medical action. This limits the decision-relevant supervision available for training models for personalized care. Here we evaluate a data-augmentation approach that makes selected clinical decision relationships explicit in an 8-billion-parameter Qwen3 model, ChronIQ-DRx2. Using the same training cases and model architecture, expert-guided logic reconstruction was applied across four chronic diseases. On the held-out evaluation, the enhanced model had the highest plotted end-to-end task-completion rate among evaluated systems and higher plotted scores across diagnostic, medication and follow-up measures. The serious clinical error rates shown were 16.7% for the baseline and 12.5% for the enhanced model. In the human-AI evaluation, physician accuracy was 87.40% alone and 88.20% with AI assistance, while mean completion time was 0.959 and 0.780 min, respectively; medical-student accuracy was 62.71% and 74.80%, and mean completion time was 0.210 and 0.195 min. These results are descriptive point estimates; inferential comparisons are not reported here. Structured outputs may make recommendations easier to review, but rationale faithfulness, generalizability and effects on clinical safety require further evaluation.

Objective: Case-finding models for underdiagnosed conditions are usually trained on diagnosis codes, which are missing from the records of many patients with a clinical diagnosis. We asked whether models trained on self-reported diagnoses rank uncoded self-reporters higher than models trained on later codes, and how a score fit only from released summary counts compares with a participant-level model. Methods: In the All of Us Research Program, we followed survey respondents with no qualifying diagnosis code by the survey date for later codes. For chronic fatigue, fibromyalgia, and endometriosis (participants recorded as female at birth), we fit a naive Bayes score with empirical-Bayes shrinkage, from released feature-by-label counts for the self-reported diagnosis and from exact counts inside the data enclave for a later code, and an elastic net on participant-level data for each label. In a random 20% validation split, we measured discrimination of self-report, of uncoded self-reporters (no qualifying code observed), and of later codes. Results: For chronic fatigue (149,860 respondents, including 7,770 self-reporters, 95% with no code observed), the summary-count score trained on self-report ranked uncoded self-reporters with an area under the receiver operating characteristic curve (AUROC) of 0.74 (95% CI, 0.72-0.75), against 0.67 (95% CI, 0.65-0.69) when trained on later codes. For later codes, the two scores were similar (0.69 vs 0.70). Fibromyalgia showed the same pattern (0.73 vs 0.64 and 0.74 vs 0.72). Elastic nets trained on self-report ranked uncoded self-reporters higher than the summary-count scores (0.80 vs 0.74 and 0.78 vs 0.73) but discriminated later codes less well than code-trained elastic nets. For endometriosis, the self-report score also ranked uncoded self-reporters above the code-trained score (0.61 vs 0.53), but discrimination was low and it did not discriminate later codes (0.50 vs 0.70). Conclusion: The choice of training label changes which patients a case-finding model ranks highly. For all 3 conditions, self-reported diagnoses were the more useful label for finding uncoded self-reporters. For chronic fatigue and fibromyalgia, the self-report score also discriminated later codes as well as the code-trained score. Independent clinical validation is needed before these models guide case finding.

Longitudinal clinical cohorts contain heterogeneous progression patterns that are obscured by coarse diagnostic labels. Discovering these latent progression phenotypes requires models that distinguish patients not only by their outcomes, but also by how their clinical trajectories evolve. This paper proposes TRACE, an interpretable temporal phenotyping method that enables the learning of outcome-informed progression phenotypes from longitudinal trajectories. TRACE combines a trajectory- and outcome-aware contrastive objective with a probabilistic predictive phenotype layer, encouraging phenotypes to capture progression structure while remaining predictive of diagnostic state. A dual-attention mechanism further supports interpretation by identifying the visits and clinical variables most associated with each phenotype assignment. TRACE is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for cognitive disease modeling, showing improved performance in both diagnostic prediction and phenotype discovery compared with other temporal phenotyping baselines. Finally, by allowing the number of phenotypes to exceed the diagnostic labels, TRACE enables discovering additional progression patterns that are not captured by labels defined a priori.

Background: Cost-effectiveness analyses (CEA) built on simulation models are usually delivered through project-specific scripts. Each new model, and often each new question, rebuilds the same scaffolding: parameter management, calibration, base-case analysis, sensitivity analysis and export. This is costly, and is where traceability between an estimate and the model version producing it is lost. We present THALASSA, a web application providing this infrastructure once, for any model satisfying a small programming contract. Methods: A simulation model is connected by one file implementing a fixed contract of R functions that determine its behaviour. THALASSA exposes the complete CEA workflow in a browser: a generated overview of the connected model, parameter editing, calibration, base-case comparison with the efficiency curve, and deterministic and probabilistic sensitivity analysis at a willingness-to-pay threshold, each with timestamped file export carrying the parameter values it was run with. Every session is bound to a repository version, so results carry their generating model version. Results: We demonstrate THALASSA on two public models of contrasting difficulty: a simple tutorial model and a generic cancer screening model with two competing natural-history pathways and a 21-dimensional calibration deliberately built to be more complex. Both ran on the same unmodified setup, implementing the same contract, with no code changes. Conclusions: Separating analysis infrastructure from model logic makes the CEA workflow reusable across projects and reproducible by construction. A modelling team can move from a versioned repository to audit-ready, exportable CEA outputs without writing analysis code. The integration effort does not grow with model size and one installation serves unrelated projects.

Background: Hospital readmission is a common and costly outcome in patients with chronic obstructive pulmonary disease (COPD). Multimodal deep learning models combining structured electronic health record (EHR) data with physiological, imaging, and textual data have been proposed to improve its prediction, but whether such fusion outperforms EHR data alone, once temporal-leakage safeguards are applied, remains unclear. Methods: Using a stratified MIMIC-IV cohort of COPD patients enriched to about 50% readmission (natural prevalence 18.1%; n=1,279; 895/192/192 training/validation/test), we predicted 30-day, all-cause readmission from four frozen, pre-trained encoders (electrocardiogram, chest radiograph, clinical notes, structured EHR). We audited and corrected temporal leakage in the admission-linkage pipeline of each modality, then compared three fusion architectures (naive concatenation, scalar gated fusion, EHR-anchored residual fusion) against unimodal baselines and an EHR-alone reference, using bootstrap significance testing, a missingness stress test, and calibration analysis with and without post-hoc recalibration. Results: The audit corrected three previously undetected temporal-alignment issues, affecting 5-9% of patients for clinical notes, 29-43% for chest radiographs, and 53-58% for ECG. After correction, every modality except EHR showed near-chance discrimination alone (ROC-AUC 0.46-0.53), confirmed with a non-linear adapter probe. No fusion architecture significantly outperformed the EHR-alone baseline (ROC-AUC 0.63); removing auxiliary modalities improved rather than degraded fusion performance under stress testing. The raw Brier score was lower for all three fusion architectures than for EHR-alone (about 0.24 versus 0.32), but this reflected overconfidence of the EHR-alone probe (calibration slope 0.12); after logistic recalibration fitted on the validation set, Brier scores were indistinguishable (EHR-alone 0.239; fusion 0.240-0.244; all paired bootstrap 95% CIs included zero). Conclusions: Structured EHR data alone matched the discrimination and, after recalibration, the calibration of more complex multimodal fusion for 30-day COPD readmission prediction. These findings highlight the importance of rigorous temporal-leakage auditing in multimodal clinical prediction research and suggest that reformulating this task around temporal proximity to the outcome, rather than refining the fusion mechanism further, may be more productive for future work.

Large language models (LLMs) are increasingly consulted for health advice, but they can produce fluent statements that are false or unsupported, known as hallucinations, and this risk is poorly characterised in low-resource languages such as Bangla. We measured hallucinations of locally deployable open-weight LLMs in Bangla diabetes question answering and tested whether retrieval-augmented generation (RAG) grounded in Bangladeshs National Guideline on Diabetes Mellitus reduces them. Forty patient questions spanning six clinical sub-domains were each answered twice, under zero-shot prompting, by Qwen3.5-9B, TigerLLM-9B, Qwen3.6-35B-A3B and Gemma-4-26B-A4B, and by BanglaDiaRAG, which adds hybrid dense (BGE-M3) and sparse (BM25) retrieval from a physician-reviewed Bangla guideline knowledge base to Qwen3.5-9B. Two physicians rated the 400 de-identified responses by consensus for medical accuracy, completeness, safety, readability and reliability on a 0-1 scale, and responses with accuracy below 0.70 were classified as hallucinated. Hallucination rates were 2.5% for Gemma-4-26B-A4B, 3.8% for TigerLLM-9B, 22.5% for Qwen3.6-35B-A3B and 77.5% for Qwen3.5-9B. Guideline grounding lowered the rate of Qwen3.5-9B to 11.3% (difference -66.3 percentage points; 95% CI -76.3 to -55.0) and raised every criterion by 0.24 to 0.38 points (Holm-adjusted p < 0.001). BanglaDiaRAG outscored Qwen3.6-35B-A3B on all five criteria and matched or exceeded TigerLLM-9B, but it remained below Gemma-4-26B-A4B in safety, readability and reliability, and its residual errors were specific, confident and potentially harmful. Guideline grounding can turn a weak general-purpose model into a much safer Bangla diabetes assistant, but the choice of base model mattered as much as retrieval and no configuration was free of hallucination, so clinical oversight remains essential before patient-facing use.

Background: The first thousand days are a sensitive window for child health and social health inequalities. When routine care falls short, parents of young children turn to online sources and, recently, to generative artificial intelligence (AI). Evidence on their concerns, child-health literacy, and AI use is scarce. Objective: To describe health informational needs and concerns, child-health literacy, and use of AI for child-health questions, including differences by parental role and parity, among parents of young children. Methods: In this cross-sectional study, two anonymous self-administered online questionnaires were disseminated through a digital health application between May 12 and June 11, 2026, to French-speaking parents of at least one child aged 0 to 47 months in France. Questionnaire 1 covered unmet information needs, concerns across 16 topics, perceived intra-couple concordance, and confidence in routine care. Questionnaire 2 covered a four-item child-health literacy quiz and AI use (frequency, topics, 12-month trend, barriers, trust conditions, perceived effect on consultations, and disclosure). Results: In total, 12,634 parents responded (Questionnaire 1, n=5,410; Questionnaire 2, n=7,224), mostly mothers (94.6% and 92.9%). Most (61.8%) had searched for information without finding a clear, reliable answer, selecting a median of 4 (Interquartile range [IQR] 3-7) over 16 topics. Leading concerns were sleep (51.3%), nutrition (48.1%), and education (i.e., upbringing and behavior) (47.8%). Mothers were nearly twice as likely as fathers to select accident prevention (26.5% vs 16.3%) and parental mental health (38.7% vs 28.6%); first-time parents selected most topics more often than experienced parents, most markedly dental hygiene (43.8% vs 27.6%). The median child-health literacy score was 3 (IQR 3-4) on a 0-to-4 quiz, with 19.9% of parents scoring 2 or below; tooth-brushing age was the weakest item (68.4% correct). Mothers outscored fathers on every item. More than half of parents (54.2%) had used AI for a child-health question, 11.2% weekly; among those reporting a trend, 68.3% had increased AI use for child-health questions over the year and 6.2% decreased it. The main barriers to AI use were a preference for professionals (55.9%) and reliability concerns (48.7%); trust depended most on medical oversight of the tool (76.6%). AI use appeared additive, with 66.8% reporting no change in healthcare visit frequency. One third (35.5%) had told an AI something shared with neither a professional nor their network, rising to 64.1% among regular users. Conclusions: Parental informational needs were widespread and frequently unmet. AI has become a common and fast-rising source for child-health questions, at times a confidential one, used alongside rather than instead of professionals. Child-health literacy was generally high but uneven, with oral health the clearest gap. Strengths include the sample size and early-generative-AI timing; limitations include the cross-sectional design, self-report, digital-recruitment selection bias, and the small proportion of fathers.

Objective A diversity of approaches and cohorts have been published in research literature for suicide risk estimation, leading to some uncertainty around which factors and conditions are most strongly contributing to risk. Methods exist for weighting estimates by propensity score, removing simplifying the interpretation of model effects. Few studies have explored the use of these tools to assess when the effect of certain factors is uncertain or inconsistent. Method A mix of 1,001,737 suicide decedents and living patients were evaluated for suicide risk, relying on a subset of commonly identified factors: demographics, psychiatric conditions, substance use disorders, and social needs. Care utilization patterns were then assessed controlling for these factors in a hospital care setting. Four methods were considered for controlling multivariate confounding of odds predicting death by suicide: multivariate logistic regression, 1-to-1 sample matching, inverse propensity weighting (IPTW), and entropy balancing (EBAL). Results Test statistics showed suicide decedents were much more likely to have various psychiatric and substance use diagnoses, social needs and more likely to heightened care utilization across sampling intervals. Greater utilization was found close to date of death. Effect sizes after IPTW and EBAL weighting were also generally greater than would have been documented by regression alone. Conclusions Propensity weighting is a useful alternative to exploring nuanced effects, especially when the direction and strength of an association differ from traditional statistics. By weighting, the overall imbalance of cases remains consistent and effect terms might reflect more nuanced associations than regression or sample matching alone.