BMC Medical Research Methodology

Target trial emulation (TTE) offers a principled way to estimate treatment effects using real-world observational data, but analyses of time-varying treatment strategies remain vulnerable to immortal time bias. The clone-censor-weight (CCW) approach is increasingly used to address this problem, yet key aspects of its causal interpretation and implementation remain unclear. In this work, we emulate a target trial using electronic health records (EHRs) to compare completion of a 3-dose 9-valent human papillomavirus vaccination (HPV) series within 12 months versus remaining partially vaccinated among vaccine initiators. We link CCW to the classic potential outcome framework in causal inference, evaluate the role of different weighting mechanisms, and account for within-subject correlation induced by cloning using cluster-robust variance estimation. Our study provides practical guidance for applying CCW in real-world comparative effectiveness studies to address immortal time bias and supports more rigorous and interpretable treatment effect estimation in TTE.

Background Depressive symptoms among reproductive-aged women represent a major public health concern in low- and middle-income countries, yet systematic screening remains limited. In most population survey datasets, the low prevalence of depression results in severe class imbalance, which challenges conventional machine learning models. Therefore, we develop and evaluate a bagging-based ensemble machine learning framework to predict depressive symptoms among reproductive-aged women using highly imbalanced Bangladesh demographic and health survey (BDHS) 2022 data. Methods The sample comprised women aged 15-49 years drawn from BDHS 2022 data. Depressive symptoms were defined using the Patient Health Questionnaire (PHQ-9 [≥]10). Candidate predictors were drawn from sociodemographic, reproductive, nutritional, psychosocial, healthcare access, and environmental domains. Feature selection was performed using Elastic Net (EN), Random Forest (RF), and XGBoost model. Five classifiers (EN, RF, Support Vector Machine (SVM), K-nearest neighbors (KNN), and Gradient Boosting Machine (GBM)) were trained using both oversampling-based approaches and the proposed ensemble framework. Model performance was evaluated on an independent test set using accuracy, sensitivity, specificity, F1-score, and the normalized Matthews correlation coefficient (normMCC). Results Approximately 4.8% of women were identified with depressive symptoms. The proposed bagging ensemble framework consistently achieved more balanced predictive performance than oversampling-based models. Average normMCC improved from 0.540 (oversampling) to 0.557 (ensemble). RF and GBM ensembles demonstrated notable improvements in identifying depressive cases, while the EN ensemble achieved the highest overall performance and sensitivity. Threshold optimization yielded stable normMCC across models, indicating robust trade-offs between sensitivity and specificity. Conclusions Bagging-based ensemble learning provides a more robust and balanced approach than synthetic oversampling for predicting depressive symptoms in highly imbalanced population survey data. This approach has important implications for improving early identification and population-level mental health surveillance in resource-constrained settings.

BackgroundType 2 diabetes mellitus (T2DM) is a leading global public health challenge. Machine learning (ML) combined with Explainable AI (XAI) is increasingly applied to T2DM risk prediction, but the field lacks a quantitative overview of methodological trends and integration gaps. MethodsWe present a structured synthesis and critical analysis of the XAI literature on T2DM risk prediction, combining (i) quantitative bibliometric analysis of a two-database corpus (N = 2,048 documents from Scopus and PubMed/MEDLINE, deduplicated via a transparent three-tier pipeline) and (ii) an in-depth selective review of 15 highly cited papers. Reporting follows PRISMA 2020, adapted for metadata-based synthesis; analyses include keyword frequency, rule-based thematic clustering, and publication trend analysis. ResultsThe field grew rapidly, from 36 documents (2020) to 866 (2025). SHAP and LIME dominate XAI methods; XGBoost and Random Forest dominate ML models. Critically, KG/GNN terms appeared in only 17 documents ([~]0.83%) compared with 906 for XAI methods, a 53.3:1 disparity. This gap is consistent across both databases, which share 33.2% of their records, ruling out a single-database artifact. The selective review confirmed that none of the 15 highly cited papers combined all three components, ML, XAI, and KG, in T2DM risk prediction. ConclusionsThe XAI for T2DM risk prediction field exhibits a clinical interpretability gap: statistical explanations are rarely linked to structured clinical pathways. We propose a three-layer conceptual framework (Predictive [->] Explainability [->] Knowledge) that integrates KG as a supplementary semantic layer, with potential applications in clinical decision support and population-level screening. The framework does not perform true causal inference but structures explanations around established pathophysiological knowledge. This study contributes a transferable methodology and a quantified research gap to guide future work integrating ML, XAI, and structured medical knowledge.

Background: The increasing availability of routinely collected health data offers new opportunities for population-level research, yet access to comprehensive, linked, and standardised datasets remains limited. We describe EST-Health-30, a large-scale, population-representative health data resource from Estonia. Methods: EST-Health-30 comprises a random 30% sample of the Estonian population (~500,000 individuals), with longitudinal data from 2012 to 2024 and annual updates planned through 2026. Individual-level records are linked across five nationwide databases, including electronic health records, health insurance claims, prescription data, cancer registry, and cause of death records. A privacy-preserving hashing approach ensures consistent cohort inclusion over time while maintaining pseudonymisation. All data are harmonised to the Observational Medical Outcomes Partnership (OMOP) Common Data Model (version 5.4) using international standard vocabularies. Data quality was assessed using established OMOP-based validation frameworks. Results: The dataset contains rich multimodal information on diagnoses, procedures, laboratory measurements, prescriptions, free-text clinical notes, healthcare utilisation, and costs, with high population coverage and longitudinal depth. Data quality assessment showed high completeness and consistency, with 99.2% of applicable checks passing. The age-sex distribution closely reflects the national population, supporting representativeness, though coverage is marginally below the target 30% (29.2%), primarily attributable to recent immigrants without health system contact. The dataset enables construction of detailed clinical cohorts, analysis of disease trajectories, and evaluation of healthcare utilisation and outcomes across the life course. Conclusions: EST-Health-30 is a comprehensive, standardised, and population-representative real-world data resource that supports epidemiological, clinical, and methodological research. Its alignment with the OMOP CDM facilitates reproducible analytics and participation in international federated research networks, while secure access infrastructure ensures compliance with data protection regulations.

Mediation analysis quantifies how an exposure affects an outcome through an intermediate variable. We extend mediation analysis to capture the cumulative effects of longitudinal predictors on longitudinal outcomes. Our proposed model examines how mediators transmit the effects of the current and previous exposure on the current outcome. We construct a least-squared estimator for cumulative indirect effect (CIE) and used three approaches (exact form, delta method, and bootstrap procedure) to estimate its standard error (SE). The estimator of CIE is unbiased with no unmeasured confounding and independent model errors between mediator model and outcome model at all time points, as shown in statistical inference and in simulations. While three SE estimates are numerically similar, bootstrap procedure is recommended due to its simplicity in implementation. We apply this method to Framingham Heart Study offspring cohort to assess if DNA methylation mediates the association of alcohol consumption with systolic blood pressure over two time points. We identify two CpGs (cg05130679 and cg05465916) as mediators and construct a composite DNA methylation score from 11 CpGs, which mediates for 39% of the cumulative effect. In conclusion, we propose an unbiased estimator for CIE. Future studies will investigate the missingness in mediators and outcomes.

Despite the evolution of epidemiological analysis and modeling tools, difficulties still remain, especially in developing countries, regarding the availability and use of these tools. Often expensive, requiring high technical expertise, demanding constant connectivity of several or sometimes even significant resources, these tools, although efficient, present a major gap with the operational realities of health districts. It is in this context that we introduce Episia, an open-source Python library designed and conceived to provide a framework to facilitate epidemiological analysis and modeling. It integrates a suite of compartmental epidemic models (SIR, SEIR, SEIRD) with a sensitivity analysis using the Monte Carlo method, a complete biostatistics suite validated against the OpenEpi reference standard, as well as a native DHIS2 client for automated data ingestion. Developed in Burkina Faso, it is optimized and aims not only to address these health challenges encountered in Africa but also remains a versatile tool for global health informatics.

BackgroundClinical pharmacists, trainees, and educators rely on multi-database literature retrieval and structured evidence synthesis to answer drug-information questions. Existing workflows require navigation across PubMed, DailyMed, LactMed, interaction checkers, and specialty guideline repositories with manual de-duplication, appraisal, and synthesis. Commercial platforms that integrate these functions are costly and often unavailable in community, rural, and international training contexts. ObjectiveThis report describes the architecture of AuditMed, a single-file, browser-based clinical evidence audit platform, and reports preliminary stress-test results against a complex multi-morbidity case corpus. AuditMed is intended for research and educational use and is not a substitute for clinical judgment or validated commercial clinical decision-support systems. MethodsAuditMed integrates nineteen free, publicly available clinical and biomedical application programming interfaces into a six-stage Search [->] Select [->] Parse [->] Analyze [->] Infer [->] Create pipeline and supports browser-local patient-case ingestion with regex-based HIPAA Safe Harbor de-identification. Preliminary stress-testing was conducted against eleven cases (Cases 30 through 40) from the Complex Clinical Case Compendium Software Validation Suite, each featuring over twenty concurrent active disease states. For each case, the one-click inference pipeline was executed with default settings and the full Clinical Inference Report was captured verbatim. No retrieval-sensitivity, synthesis-fidelity, or time-to-answer endpoints were pre-specified; the exercise was qualitative and oriented toward pipeline behavior under extreme multi-morbidity. ResultsThe pipeline completed without fatal errors for all eleven cases and produced a structured Clinical Inference Report in each instance. Quantitative-finding detection performed as designed for hematologic parameters and cardiac biomarkers. Two parser defects were identified and are reproduced in the appendix: an age-as-fever regex-precedence defect affecting seven cases and a diagnosis-versus-medication parsing defect affecting one case. Evidence-linkage rate varied from zero evidence-linked statements in seven cases to eleven in one case, reflecting dependence of the inference layer on MeSH-indexed literature coverage of the specific case diagnoses. ConclusionsAuditMed is an early-stage, open-source platform whose value at this stage is in providing a free, transparent, auditable workflow for multi-source evidence synthesis with explicit uncertainty flagging. The preliminary results document both robust end-to-end completion under extreme case complexity and specific, reproducible parser defects that will be addressed before formal evaluation. Planned evaluation studies are described.

Background Electronic health record (EHR) phenotyping underpins observational research, cohort discovery, and clinical trial screening. Large language models (LLMs) offer new capabilities for extracting phenotypes from unstructured text, but their performance depends on pipeline design choices-including prompting, text segmentation, and aggregation. No systematic framework has previously examined how these parameters shape accuracy and reproducibility. Methods We evaluated LLM-based phenotyping pipelines using 1,388 discharge summaries across 16 clinical phenotypes. A full factorial experiment with LLaMA-3B, 8B, and 70B systematically varied three pipeline components: prompting (zero-shot, few-shot, chain-of-thought, extract-then-phenotype), chunking (none, naive, document-based), and aggregation (any-positive, two-vote, majority), yielding 24 configurations per model. To compare intrinsic model capabilities, biomedical domain-adapted, commercial frontier (LLaMA-405B, GPT-4o, Gemini Flash 2.0), and reasoning-optimized models (DeepSeek-R1) were evaluated under a fixed configuration. Performance was assessed using precision, recall, and macro-F1; secondary analyses examined prediction consistency (Shannon entropy), self-confidence calibration, and the development of a taxonomy of recurrent model errors. Results Factorial ANOVAs showed that chunking and aggregation were the dominant drivers of performance, whereas the prompting strategy contributed minimally. Configuration effects were stable across model sizes, with no significant Model x Parameter interactions. Phenotype difficulty varied substantially (macro-F1 = 0.40-0.90), yet the highest-performing configuration-whole-document inference without aggregation-was consistent across phenotypes, as confirmed by mixed-effects modeling. In cross-model comparisons, DeepSeek-R1 achieved the highest macro-F1 (0.89), while LLaMA-70B matched GPT-4o and LLaMA-405B at substantially lower cost. Prediction entropy was low overall and driven primarily by phenotype difficulty rather than prompting or temperature. Self-confidence calibration was only moderately informative: high-confidence predictions were more accurate, but larger models exhibited systematic overconfidence. Conclusions LLM performance in EHR phenotyping is governed primarily by input structure and model capacity, not prompt engineering. Simple, document-level inference yields robust performance across diverse phenotypes, providing practical design guidance for LLM-based cohort identification while underscoring the continued need for human oversight for challenging phenotypes.

BackgroundTuberculosis (TB) remains a leading cause of infectious disease mortality worldwide, and treatment failure contributes to ongoing transmission, drug resistance, and poor clinical outcomes. Artificial intelligence and machine learning approaches have attracted growing interest for predicting tuberculosis treatment outcomes, but the literature is heterogeneous and lacks a comprehensive synthesis. MethodsWe conducted a systematic review and meta-analysis of studies that developed or validated machine learning models to predict TB treatment failure. We searched PubMed/MEDLINE and Embase from January 2000 to October 2025. Studies were eligible if they developed, validated, or implemented an artificial intelligence or machine learning model for the prediction of TB treatment failure or a closely related poor outcome in patients receiving anti-TB treatment. Risk of bias was assessed using the Prediction model Risk Of Bias Assessment Tool. Random-effects meta-analysis was performed to pool area under the curve values, with subgroup analyses and meta-regression to explore heterogeneity. ResultsThirty-four studies were included in the systematic review, of which 19 reported area under the curve values suitable for meta-analysis (total participants, 100,790). Studies were published between 2014 and 2025, with 91% published from 2019 onward. Tree-based methods were the most common algorithm family (52.9%), and multimodal models integrating three or more data types were used in 41.2% of studies. The pooled area under the curve was 0.836 (95% confidence interval 0.799-0.868), with substantial heterogeneity (I{superscript 2} = 97.9%). In subgroup analyses, studies including HIV-positive participants showed lower discrimination (pooled area under the curve 0.748) compared to those excluding them (0.924). Only eight studies (23.5%) performed external validation, and only one study (2.9%) was rated as low risk of bias overall, primarily due to methodological concerns in the analysis domain. Eggers test suggested publication bias (p = 0.024). Major evidence gaps included underrepresentation of high-burden countries, HIV-affected populations, social determinants, pediatric TB, and extrapulmonary disease. ConclusionsMachine learning models for predicting TB treatment failure show promising discrimination but are not yet ready for routine clinical implementation. Performance varies substantially across populations and settings, and methodological limitations, including inadequate validation, poor calibration assessment, and high risk of bias, limit confidence in current estimates. Future research should prioritize rigorous external validation, calibration assessment, and development in underrepresented populations, particularly HIV-affected and high-burden settings. Author SummaryTB kills over a million people annually. While curable, treatment failure remains common and drives ongoing transmission and drug resistance. Researchers increasingly use artificial intelligence and machine learning to predict which patients will fail treatment, but it is unclear if these models are ready for clinical use. We reviewed 34 studies including nearly 1.1 million participants from 22 countries. On average, models correctly distinguished patients who would fail treatment from those who would not 84% of the time, a performance generally considered good. However, this average hid enormous variation. Models developed in populations including HIV-positive people performed substantially worse, suggesting prediction is harder with HIV co-infection. Worryingly, only one study used high-quality methods; 97% had serious flaws in handling missing data, checking calibration, or testing in new populations. Only eight studies validated their models in different settings. To conclude, we found that machine learning is promising in predicting TB treatment failure, but it is not ready for clinical use. Researchers should prioritize validation in high-burden settings, include social determinants, and improve methodological rigor before these tools can help patients.

Introduction Secondary use of electronic health records (EHRs) often requires transforming raw clinical information into research-grade data. A central step in this process is EHR phenotyping - the identification of patient cohorts defined by specific medical conditions. Although numerous approaches exist, from ICD-based heuristics to supervised learning and large language models (LLMs), the field lacks standardized benchmark datasets, limiting reproducibility and hindering fair comparison across methods. Methods We developed the MIMIC-IV Phenotype Atlas (MIPA) dataset, an adaptation of MIMIC-IV that provides expert-annotated discharge summaries across 16 phenotypes of varying prevalence and complexity. Two independent clinicians reviewed and labeled the discharge summaries, resolving disagreements by consensus. In parallel, we implemented a processing pipeline that extracts multimodal EHR features and generates training, validation, and testing datasets for supervised phenotyping. To illustrate MIPA's utility, we benchmarked four phenotyping methods : ICD-based classifiers, keyword-driven Term Frequency-Inverse Document Frequency (TF-IDF) classifiers, supervised machine learning (ML) models, and LLMs on the task. Results The final MIPA corpus consists of 1,388 expert-annotated discharge summaries. Annotation reliability was high (mean document-level kappa = 0.805, mean label-level kappa = 0.771), with 91% of disagreements resolved through consensus review. MIPA provides high-quality phenotype labels paired with structured EHR features and predefined train/validation/test splits for each phenotype. In the benchmarking case study, LLMs achieved the highest F1 scores in 13 of 16 phenotypes, particularly for conditions requiring contextual interpretation of clinical narrative, while supervised ML offered moderate improvements over rule-based baselines. Conclusion MIPA is the first publicly available benchmark dataset dedicated to EHR phenotyping, combining expert-curated annotations, broad phenotype coverage, and a reproducible processing pipeline. By enabling standardized comparison across ICD-based heuristics, ML models, and LLMs, MIPA provides a durable reference resource to advance methodological development in automated phenotyping.

Abstract Objective To address the unresolved bottleneck of selecting cohort-relevant clinical concepts for treatment trajectory analysis in observational health data, we introduce CohortContrast, an OMOP-compatible R package for enrichment-based concept identification, temporal and semantic noise reduction, and concept aggregation, enabling cohort-level characterization and downstream trajectory analysis. Materials and Methods We developed CohortContrast and applied it to OMOP-mapped observational data from the Estonian nationwide OPTIMA database, which includes all cases of lung, breast, and prostate cancer, focusing here on lung and prostate cancer cohorts. The workflow combines target-control statistical enrichment, temporal/global noise filtering, hierarchical concept aggregation and correlation-based merging, with optional patient clustering for downstream trajectory exploration. We validated the approach with a clinician-based plausibility assessment of extracted diagnosis-concept pairs and evaluated a large language model (LLM) as an auxiliary filtering step. Results We analyzed 7,579 lung cancer and 11,547 prostate cancer patients. The workflow reduced concept dimensionality from 5,793 to 296 concepts (94.9%) in lung cancer and from 5,759 to 170 concepts (97.0%) in prostate cancer, and identified three exploratory patient subgroups in both cohorts. In a plausibility assessment of 466 diagnosis-concept pairs, validators rated 31.3% as directly linked and 57.5% as indirectly linked. Discussion CohortContrast reduces manual concept curation by prioritizing and aggregating cohort-relevant concepts while preserving clinically interpretable treatment patterns in OMOP-based real-world data. Conclusion CohortContrast enables scalable reduction of broad OMOP concept spaces into clinically interpretable, cohort-specific representations for exploratory trajectory analysis and real-world evidence research.

BackgroundSouth Africas public healthcare system serves most of the population through approximately 3,900 primary healthcare clinics characterised by long waiting times and high volumes of repeat-prescription visits. No published pre-arrival digital triage system operates across all 11 official South African languages while aligning with the South African Triage Scale (SATS). This paper reports the design and preliminary safety validation of BIZUSIZO, a hybrid deterministic-AI WhatsApp triage system. MethodsBIZUSIZO delivers SATS-aligned triage via WhatsApp, combining AI-assisted free-text classification (Claude Haiku 4.5) with a Deterministic Clinical Safety Layer (DCSL) that overrides AI output for 53 clinical discriminator categories (14 RED, 19 ORANGE, 20 YELLOW) coded in all 11 official languages and independent of AI availability. A five-domain risk factor assessment can only upgrade triage level. One hundred and twenty clinical vignettes in patient language (English, isiZulu, isiXhosa, Afrikaans; 30 per language) were scored against a developer-assigned gold standard with independent blinded nurse review. A 121-vignette multilingual DCSL safety consistency check across all 11 languages and a 220-call post-hoc framing sensitivity evaluation (110 paired vignettes) were also conducted. ResultsUnder-triage was 3.3% (4/120; 95% CI: 0.9%-8.3%) with no RED under-triage; exact concordance was 80.0% (96/120) and quadratic weighted kappa 0.891 (95% CI: 0.827-0.932). One two-level under-triage was observed on a non-RED presentation (V072, isiXhosa burns vignette, ORANGEGREEN); one two-level over-triage was observed (V054, isiZulu deep laceration, YELLOWRED). In the framing sensitivity evaluation, AI-only classification achieved 50.9% RED invariance under adversarial framing; full-pipeline classification achieved 95.0% in four validated languages, with the DCSL rescuing 18 of 23 AI drift cases. ConclusionsA hybrid deterministic-AI triage system with DCSL-based emergency detection achieved zero RED under-triage and consistent RED detection across all 11 official languages. The 16.7% over-triage rate falls within published South African SATS ranges (13.1-49%). A single two-level under-triage event was observed on an isiXhosa burns vignette (ORANGEGREEN) and is discussed in Limitations. Findings are preliminary; prospective validation against independent nurse triage is the necessary next step.

BackgroundNon-adherence to lipid-lowering therapy (LLT) affects up to half of patients and contributes substantially to preventable cardiovascular morbidity and mortality. Existing measures, such as the proportion of days covered, provide cross-sectional summaries but fail to capture the dynamic patterns of adherence over time. Although group-based trajectory modelling identifies distinct longitudinal adherence patterns, no approach currently predicts trajectory membership prospectively while incorporating patient-reported barriers. We developed BRIDGE, a barrier-informed Bayesian model to predict adherence trajectories and identify their underlying drivers. MethodsBRIDGE incorporates patient-reported barriers as structured prior information within a Bayesian framework for adherence-trajectory prediction. The model was designed not only to estimate which patients are likely to follow different adherence trajectories, but also to generate clinically interpretable probability estimates that help explain why those trajectories may arise and what modifiable factors may be most relevant for intervention. ResultsBRIDGE achieved a macro AUROC of 0.809 (95% CI 0.806 to 0.813), comparable to random forest (0.815 (95% CI 0.812 to 0.819)) and XGBoost (0.821 (95% CI 0.818 to 0.824)), two widely used machine-learning benchmarks for structured clinical prediction. Calibration was superior to random forest (Brier score 0.530 vs 0.545; ), and performance was stable across six independent training runs (AUROC SD = 0.003). Incorporating barrier-informed priors improved accuracy by 3.5% and calibration by 5.5% compared to flat priors, showing that incorporation of patient-reported barriers added value beyond electronic medical record data alone. Four clinically distinct adherence trajectories were identified: gradual decline associated with treatment deprioritisation amid polypharmacy (10.4%), early discontinuation linked to asymptomatic risk dismissal (40.5%), rapid decline associated with intolerance (28.8%), and persistent adherence (20.2%). Counterfactual analysis identified trajectory-specific intervention levers. ConclusionsBRIDGE provides accurate and well-calibrated prediction of adherence trajectories while offering clinically actionable insights into their underlying drivers. By integrating patient-reported barriers with routine clinical data, the model supports targeted, mechanism-informed interventions at the point of prescribing to improve adherence to cardioprotective therapies. FundingMRFF CVD Mission Grant 2017451 Evidence before this studyWe searched PubMed and Scopus from database inception to December 2025 using the terms "medication adherence", "trajectory", "prediction model", "Bayesian", "lipid-lowering therapy", and "barriers", with no language restrictions. Group-based trajectory modelling has consistently identified three to five adherence patterns across cardiovascular cohorts; however, these applications have been descriptive rather than predictive. Machine-learning models for adherence prediction achieve moderate discrimination but treat adherence as a binary or continuous outcome, thereby overlooking the clinically meaningful heterogeneity captured by trajectory approaches. One prior study applied a Bayesian dynamic linear model to examine adherence-outcome associations, but it did not predict adherence trajectories or incorporate patient-reported barriers. To our knowledge, no published model integrates patient-reported barriers into trajectory prediction. Added value of this studyBRIDGE is, to our knowledge, the first model to incorporate patient-reported adherence barriers as hierarchical domain-informed priors within a Bayesian framework for trajectory prediction. Using 108 predictors derived from routine electronic medical records, the model achieves discrimination comparable to state-of-the-art machine-learning approaches while additionally providing uncertainty quantification, barrier-level interpretability, and counterfactual insights to inform intervention strategies. The identified trajectories differed not only in adherence level but also in switching behaviour, drug-class evolution, and medication burden, suggesting distinct underlying mechanisms of non-adherence that may require tailored clinical responses. Implications of all the available evidenceEach adherence trajectory implies a distinct intervention target: asymptomatic risk communication for early discontinuers (40.5% of patients), proactive tolerability management for rapid decliners, medication simplification for patients with gradual decline associated with polypharmacy, and maintenance support for persistent adherers. By integrating routinely collected clinical data with patient-reported barriers, BRIDGE can be deployed within existing primary care EMR infrastructure to generate actionable, trajectory and patient--specific recommendations at the point of prescribing, helping to bridge the gap between adherence measurement and targeted adherence management.

Background: The instability-plasticity framework proposes that multimorbidity trajectories periodically enter instability phases that are vulnerable to escalation but also potentially modifiable through relational intervention. Whether such phases commonly resolve without acute care, or predominantly progress to hospitalisation, has not been quantified at scale. Objective: To quantify instability window outcomes across a longitudinal monitoring cohort; to test whether the characteristics distinguishing admitted from resolved windows reflect within-patient trajectory dynamics or between-patient severity; and to characterise which patient-reported and operator-rated signals reliably precede admission, using both a curated pilot sub-cohort and the full monitoring cohort with an explicit cross-cohort comparison. Methods: Two complementary analyses were conducted on data from the MonashWatch Patient Journey Record (PaJR) relational telehealth system. Instability windows were identified algorithmically (>=2 consecutive calls with Total_Alerts >=3) across the full longitudinal dataset (16,383 calls, 244 patients, 2.5 years) and classified by linkage to ED and hospital admission data. Window characteristics were compared at window, patient, and paired within-patient levels. Pre-admission signal cascades were analysed in two configurations: a curated pilot sub-cohort (64 patients, 280 calls, +/-10-day window, 103 admissions, December 2016-September 2017) and the full monitoring cohort (175 patients, 1,180 pre-admission calls, +/-14-day window, December 2016-July 2019). A three-way cross-cohort comparison decomposed differences between the two configurations into pipeline and population effects. Results: 621 instability windows were identified across 157 patients (64% of the monitored cohort). 67.3% resolved without hospital admission or ED attendance, a rate stable across alert thresholds 1-5. In paired within-patient analysis (n = 70), duration in days (p = 0.002) and multi-domain breadth (p < 0.001) distinguished admitted from resolved windows; alert intensity did not. In the pilot sub-cohort, patient-reported illness prognosis (Q21) was the dominant pre-admission signal (GEE beta = +0.058, AUC = 0.647, p-BH = 0.018). This finding did not replicate in the full cohort: Q21 was non-significant (GEE beta = -0.008, p = 0.154, AUC = 0.507). Cross-cohort analysis identified selective curation of the pilot sub-cohort as the primary explanation. In the full cohort, six signals escalated significantly before admission after Benjamini-Hochberg correction: total alerts, health impairment (Q26), red alerts, self-rated health (Q3), patient concerns (Q1), and operator concern (Q34). Health impairment achieved the highest individual AUC (0.605) and showed the longest pre-admission lead. No individual signal exceeded AUC 0.61. Conclusions: Two thirds of instability phases resolve without hospitalisation, providing direct empirical support for trajectory plasticity as a clinically frequent phenomenon. Within the same patient, persistence - in duration and in the consistency of high-severity multi-domain flagging across calls - distinguishes trajectories that tip into admission from those that resolve. The Q21 signal reversal between cohorts illustrates how selective curation can produce compelling but non-replicable findings in monitoring research. In the full population, objective alert signals and operator judgement, rather than patient illness prognosis, carry the pre-admission signal

Objectives: Large language models (LLMs) have shown promise in creating clinical codelists for research purposes, a time-consuming task requiring expert domain knowledge. Here, we evaluate the performance and assess failure modes of a retrieval augmented generation (RAG) approach to creating clinical codelists for the large and complex medical terminology used by the Clinical Practice Research Datalink (CPRD). Materials & Methods: We set up a RAG system using a database of word embeddings of the medical terminology that we created using a general-purpose word embedding model (gemini-embedding). We developed 7 reference codelists presenting different challenges and tagged required and optional codes. We ran 168 evaluations (7 codelists, 2 different database subsets, 4 models, 3 epochs each). Scoring was based on the omission of required codes, and inclusion of irrelevant codes. We used model-grading (i.e., grading by another LLM with the reference codelists provided as context) to evaluate the output codelists (a score of 0% being all incorrect and 100% being all correct). Results: We saw varying accuracy across models and codelists, with Gemini 3 Pro (Score 43%) generally performing better than Claude Sonnet 4.6 (36%), Gemini 3 Flash, and OpenAI GPT 5.2 performing worst (14%). Models performed better with shorter target codelists (e.g., Eosinophilic esophagitis with four codes, and Hidradenitis suppurativa with 14 codes). For example, all models consistently failed to produce a complete Wrist fracture codelist (with 214 required codes). We further present evaluation summaries, and failure mode evaluations produced by parsing LLM chat logs. Discussion: Besides demonstrating that a single-shot RAG approach is currently not suitable for codelist generation, we demonstrate failure modes including hallucinations, retrieval failures and generation failures where retrieved codes are not used. Conclusions: Our findings suggest that while RAG systems using current frontier LLMs may create correct clinical codelists in some cases, they still struggle with large and complex terminologies and codelists with a large number of codes. The failure mode we highlight can inform the creation of future workflows to avoid failures.

BackgroundDiabetic kidney disease (DKD) is a leading cause of kidney failure in individuals with type 2 diabetes (T2D), yet risk identification in routine clinical practice remains incomplete. A critical and often overlooked barrier is risk observability: how much of a patients underlying risk is actually captured in their clinical record at the time of screening. Existing prediction models evaluate performance using model-specific thresholds, making it difficult to understand how additional data sources alter real-world screening behavior or which individuals benefit when models are expanded. MethodsWe developed a series of five nested machine learning models evaluated at a one-year landmark following T2D diagnosis using data from the All of Us Research Program (N = 39,431; cases = 16,193). Each successive model added a distinct information layer -- intrinsic risk, laboratory snapshots, medication exposure, longitudinal care trajectories, and social determinants of health (SDOH) -- while retaining all prior features. All models were evaluated under a fixed screening policy targeting 90% specificity, so that the false positive rate remained constant as the information available to the model grew. External validation was conducted in the BioMe Biobank (N = 9,818) without retraining. ResultsDiscrimination improved consistently across layers, from AUROC 0.673 (M1) to 0.797 (M5). Under the fixed screening policy, sensitivity nearly doubled from 0.27 to 0.49, with a cumulative recovery of 30.4% of cases missed by the base model. Gains were driven by distinct subgroups at each transition: laboratory features identified biologically high-risk individuals; medication features captured those with high treatment intensity reflecting advanced cardiometabolic burden; longitudinal care trajectory features rescued cases with biological instability observable only through repeated measurements; and SDOH features recovered individuals with limited clinical observability, with rescue probability highest among those with the fewest recorded monitoring domains. Sparse data in the clinical record indicated low observability, not low risk. Social and genetic features each contributed most when downstream physiologic signal was limited, supporting a contextual rather than universal role for each. In BioMe, discrimination was attenuated (M4 AUROC 0.659), but the relative ordering of information layers was fully preserved, and a systematic upward shift in predicted probability distributions underscored the need for recalibration before deployment in a new setting. ConclusionsDKD risk detection in T2D is substantially improved by integrating complementary information layers under a fixed clinical screening policy, with gains arising from distinct domains that identify at-risk individuals in different clinical contexts. The layered landmark framework introduced here reveals how risk observability -- shaped by monitoring intensity, healthcare engagement, and access -- determines what a screening model can detect, and provides a foundation for context-aware EHR-based screening that accounts for data availability at the time of risk assessment. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=140 SRC="FIGDIR/small/26351384v1_ufig1.gif" ALT="Figure 1"> View larger version (51K): org.highwire.dtl.DTLVardef@1cc7f4borg.highwire.dtl.DTLVardef@b92956org.highwire.dtl.DTLVardef@48ffbcorg.highwire.dtl.DTLVardef@8dc627_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOGraphical abstract.C_FLOATNO Study design and layered DKD screening framework The top row defines the cohort timeline, in which predictors are derived from clinical data collected between T2D diagnosis and the 1-year landmark, and incident DKD is ascertained after the landmark. The second row depicts the nested model architecture, in which five successive models sequentially incorporate intrinsic risk, laboratory snapshot features, medication exposure, longitudinal care trajectories, and social determinants of health, while retaining all features from prior layers. The third row summarizes model development in the All of Us Research Program (N = 39,431) and external validation in the BioMe Biobank (N = 9,818), where the same trained models and risk thresholds were applied without retraining. The bottom row highlights the three evaluation domains: predictive performance, fixed-policy screening, and missed-case recovery context. DKD, diabetic kidney disease; T2D, type 2 diabetes; PRS, polygenic risk scores; AUROC, area under the receiver operating characteristic curve; AUPRC, area under the precision-recall curve; PPV, positive predictive value; SHAP, SHapley Additive exPlanations. C_FIG

BackgroundRecruitment remains a major barrier to timely clinical trial completion. Trialshub is an LLM-powered, chat-based platform intended to help users identify relevant trials and connect with coordinators to streamline recruitment workflows. ObjectiveTo evaluate the perceived usability and operational value of Trialshub, and identify implementation considerations for real-world deployment. MethodsA usability test was conducted at Morehouse School of Medicine for the Trialshub application. Purposively selected participants included clinical research coordinators and individuals with and without clinical trial search experience. Participants completed a pre-test survey assessing demographics, digital health information behaviors, and familiarity with AI tools, followed by a moderated usability session using a Trialshub prototype. Users completed scenario-based tasks (locating a breast cancer trial, reviewing results, and initiating coordinator contact) using a think-aloud protocol. Task ratings, screen recordings, and transcribed feedback were analyzed descriptively and thematically, and reported. ResultsParticipants reported high comfort with using digital tools and moderate-to-high familiarity with AI. Trialshubs chat-first design, guided prompts, and checklist-style eligibility display were perceived as intuitive and reduced cognitive load. Fast access to trials and the coordinator-contact workflow were viewed positively. Key usability issues included uncertainty at step transitions, insufficient cues for selecting results and next actions, and inconsistent system reliability (loading delays, errors, and broken trial detail pages). Participants also noted redundant questioning due to limited conversational memory, requested improved filtering/sorting, and clearer calls-to-action. All participants indicated that Trialshub has strong potential to meaningfully improve clinical trial processes. ConclusionsTrialshub shows promise for improving trial discovery and recruitment workflows, with identified design implications for real-world deployment.

Standard analysis of amyotrophic lateral sclerosis (ALS) clinical trials evaluates therapeutic efficacy by comparing linear slopes of total ALS Functional Rating Scale (ALSFRS) scores between treatment arms. This approach compresses multidomain ordinal data into a single scalar trajectory, discarding distributional structure. When subgroup-level trends differ in timing or direction, such aggregation can attenuate or eliminate them, a phenomenon known as Simpsons paradox. Here we apply Shannon entropy, computed from item-level score distributions within each ALSFRS functional domain following the framework established in [8], to the PRO-ACT database, stratified by treatment arm (Active: n = 4,581; Placebo: n = 2,931; 19 monthly time points). The entropy trajectories of drug-treated and placebo populations diverge visibly and systematically across all four functional domains (Bulbar, Fine Motor, Gross Motor, Respiratory). In the Fine Motor domain, the placebo population reaches peak entropy at month 8 and reverses, while the active population does not peak until month 13, a five-month delay in the populations transit toward functional loss. This divergence is model-independent: it is present in the raw Shannon entropy trajectories before any dynamical model is applied. A permutation test shuffling patient-level arm labels (n = 1,000 permutations) confirms that the total integrated absolute divergence across all four domains exceeds the null distribution at p < 0.001 (observed: 4.48; null: 2.03 {+/-} 0.33; 7.5 standard deviations above the null mean), with Fine Motor (p = 0.001) and Respiratory (p < 0.001) individually significant. The quantity that differs between arms, the shape and timing of the populations distributional evolution, does not exist as a measurable quantity in the total-score linear-slope framework used to evaluate these trials. Whether this signal reflects genuine treatment effects, compositional artifacts from pooling heterogeneous trials, or both cannot be determined from the anonymized public database alone. What can be determined is that the standard ALS clinical trial endpoint makes an implicit assumption, that the distributional information it discards is uninformative, and the present results demonstrate empirically that this assumption is false.

BackgroundAn upsurge in Streptococcus pyogenes infections 2022-2023 highlighted potential benefits of point-of-care tests (POCT) to support clinical pathways, prevent outbreaks, and optimise antibiotic use. ObjectivesWe conducted a pilot research study in a west London paediatric emergency department (ED) to determine whether a molecular POCT had potential to alter management in children who were also having a conventional throat swab taken for culture. MethodsChildren <16 years presenting to ED who had a throat swab requested by a clinician were invited to have a second swab taken for research purposes only. Clinical management was unaffected by the research swab result, which was processed using a molecular POCT that was not approved for use in the host NHS Trust. ResultsPrevalence of streptococcal infection was low during the study (May 2023-June 2025); swab positivity in symptomatic children was 12.8% (6/47). Overall, 38/49 (77.6%) participants who had throat swabs received antibiotics. Of those children recommended to receive antibiotics, 29/38 (76.3%) had a negative POCT. Mean time to reporting of positive throat swab culture results was 3.67 days (range 3-5 days) leading to occasional delay in treatment, although POCT identified positive results within minutes. ConclusionAntibiotic use was frequent and could be avoided or stopped by use of a rule out POCT in over three-quarters of children in the ED, if suspicion of S. pyogenes is the main driver for prescribing. POCT were easy to process and produced immediate results compared with culture, in theory enabling timely decision-making and avoiding treatment delay.

Background: Lung cancer screening can reduce lung cancer mortality through early detection, but uptake of the NHS Targeted Lung Health Check (TLHC) programme remains low. Behaviourally informed invitation messages have been proposed as a low-cost approach to increase attendance, but evidence of their effectiveness in lung cancer screening is mixed. Few intervention studies used evidence-based behaviour change frameworks, and rarely tailored invitation strategies to empirically identified barriers and enablers. Methods: In an online experiment, 3,274 adults aged 55-74 years and with a history of smoking were randomised to see one of four behaviourally informed invitation messages or a control message. Participants then rated their intention to attend a TLHC appointment, and selected barriers and enablers to attending from a pre-defined list, which were classified according to the Theoretical Domains Framework. Invitation messages were mapped to Behaviour Change Techniques using the Theory and Techniques Tool. Message conditions were compared on intention to attend TLHC using bootstrapped ANOVA followed by pairwise comparisons. Exploratory counterfactual mediation analyses examined the role of fear in intention to attend. Results: Behaviourally informed invitation messages did not meaningfully increase intention to attend TLHC compared with the control message. While a GP-endorsed message showed a small potential benefit relative to the other conditions, this finding was not robust after adjustment for multiple comparisons. Participants most frequently reported barriers related to Emotion (particularly fear), Social Influence, and Knowledge, while Beliefs about Consequences emerged as the primary enabler of attendance. Only around half of reported barriers and enablers were addressed by the invitation messages. Exploratory analyses found that fear was associated with lower intention to attend a TLHC appointment, yet none of the behaviourally informed messages appeared to reduce fear compared to the control message. Conclusions: Improving lung cancer screening uptake will likely require invitation messages that directly address emotional concerns, particularly fear, alongside credible recommendations. These findings highlight the importance of systematically aligning invitation message content with empirically identified behavioural influences when designing scalable interventions to improve lung cancer screening uptake.