International Journal of Medical Informatics

In this work, we demonstrate the unprecedented value of NIH's "All of Us Research Program" (AoURP) dataset in studying maternal morbidity and building predictive machine learning (ML) models across heterogeneous populations in the United States. We developed robust and data-driven preprocessing pipelines to curate a longitudinal, multi-site, multimodal, and demographically diverse pregnancy dataset (20,253 subjects; 27,525 pregnancy episodes) from AoURP data, using electronic health records (EHR) (Conditions, Labs, Measurements) and survey responses (Social Determinant of Health (SDoH)), focusing on 7 crucial maternal health adverse outcomes. After characterizing data quality, missingness, and heterogeneity, we performed statistical correlation analysis to identify risk factors. We subsequently developed XGBoost and sequential LSTM models to predict the adverse outcomes, reaching state-of-the-art performance for multiple outcomes. We conducted model interpretability post-hoc analysis to understand success points and fairness analysis to evaluate implications for socio-economic disparities. Four practicing physicians reviewed the set of statistically significant and ML model identified features to assess their clinical validity and novelty. Most features identified through either statistical correlations or ML feature importance analysis aligned with known clinical risk factors. Several features were identified that the ML models used but that are not currently used in clinical practice and may merit further clinical investigation. Fairness analysis revealed certain associations with SDoH and age highlight areas that warrant continued monitoring. Overall, we demonstrate that meaningful populational level patterns can be extracted, and high-performing machine learning models can be trained on this longitudinal, diverse, multi-site dataset. Important risk features, particularly novel ones identified, if validated, could inform new strategies for maternal care or enable development and validation of outcome-specific, clinically deployable ML models.

Background: Machine learning models leveraging electronic health records (EHRs) can support earlier detection of sepsis in intensive care units (ICUs). However, their clinical utility depends on reproducibility across institutions and patient populations. Building on a published pipeline from the Children's Hospital of Philadelphia (CHOP), this study examines how a neonatal sepsis prediction framework performs and can be adapted to a range of intensive care environments, paediatric, cardiac, and neonatal, at Great Ormond Street Hospital (GOSH). Methods: We extracted de-identified ICU EHR data from GOSH and applied feature derivation, unit harmonisation, and temporal sampling to align with the CHOP dataset used by Masino et al. (2019). Seven classifiers were first evaluated using CHOP-trained weights to characterise cross-domain behaviour and then retrained on local data to assess recoverability and site-specific adaptation. Model discrimination was summarised by AUC and F1, and learning curves were used to explore sample efficiency and bias-variance dynamics. Results: Models achieved strong discrimination on the CHOP neonatal cohort but demonstrated reduced performance when transferred to the mixed GOSH ICU population, reflecting anticipated domain and population shift. Retraining on GOSH data restored discrimination (AUC range 0.69-0.86), with Gradient Boosting (AUC 0.86 vs AUC 0.87 at CHOP) and KNN (AUC 0.80 vs AUC 0.79 at CHOP) models performing comparably to their CHOP benchmarks. DeLong's test confirmed statistically significant gains across all classifiers (p < 0.001). Conclusion: ICU cohort and baseline demographic differences between CHOP and GOSH introduced domain shift that limited direct model transfer. Elements of the original preprocessing pipeline could not be reproduced, further constraining transportability. Yet, retraining on local data restored high discrimination, showing that the modelling framework remains robust when re-estimated in new settings. These results highlight local adaptation as a practical route to recover performance and support safe, generalisable deployment of clinical prediction models in mixed clinical environments.

Acute kidney injury (AKI) is a frequent complication within intensive care units, with its sudden onset often missed. This is especially important because a timely window for intervention is required as delayed detection leads to progressively worse outcomes. Existing machine learning and deep learning models have contributed to closing this gap, but their complexity, requiring hundreds to thousands of features, and lack of generalisation pose a limitation that prevents them from being integrated into clinical workflows across different electronic health-record ecosystems. This study presents a 37-feature XGBoost model trained on the MIMIC-IV dataset with 5.4% positive cases, with hyperparameters optimised via Optuna and probabilities calibrated using isotonic regression, designed for transportability across clinical settings. Validation was conducted internally using a temporal patient-level split simulating prospective deployment, training on 2008-2016 data and testing on 2017-2022 data"External validation was performed on the eICU Collaborative Research Database, a multi-centre dataset spanning 208 US hospitals, using the trained model without retraining. SHAP TreeExplainer was used to provide feature-level explainability for individual predictions. Internal testing yielded an AUROC score of 0.794 for predicting AKI onset within a 12-24 hour window. External validation produced a 0.750 AUROC without retraining. Equitable discrimination was observed across gender, age, chronic kidney disease presence, race, and AKI stages on both datasets, with a 95% internal CI of 0.789-0.799 confirming the model's estimate stability. These results suggest that clinically useful prediction systems are achievable with substantially fewer features than current models require.

Background: Sepsis is a life-threatening condition triggered by infection and associated with dysregulated immune response of the patient followed often by multiorgan dysfunction or failure. In the clinical evolution of sepsis towards organ dysfunction, early initiation of a suited therapy significantly increases patient outcomes and reduces mortality rates. Since electronic health records provide data in a machine-readable format, this process could be supported by computerized systems. Methods: We developed an interoperable, time-sensitive CDSS that able to detect systemic inflammation and the different classifications of sepsis (bacterial/viral, suspected/proven, on admission/PICU acquired) in pediatric patients based on the analysis of routine clinical data. This application is provided as part of this publication as an open demonstrator (web application), and the usability and accuracy of the CDSS is shown by a retrospective creation of sepsis outcome labels for a routine data set of 4,655 pediatric patients. As a reference standard, the patients were manually assessed by blinded clinical experts. Results: In comparison with the reference standard, the CDSS achieved sensitivity of 96.9% (95% CI: 80.9-99.6%) and specificity of 99.1% (95% CI: 95.1-99.8%). In the context of a sepsis outcome labeling for 4,655 patients, the CDSS detected 4,342 episodes of inflammation of which 1,723 were classified as sepsis. Conclusions: We demonstrated that our routine-data based CDSS is able to perform a complex sepsis detection process with high diagnostic accuracy. Such CDSS with the ability to differentiate between SIRS, sepsis on admission, suspected and proven sepsis can prospectively support clinical management, monitoring and quality management.

Background: Whether benchmark performance reflects robust clinical reasoning rather than surface-level pattern recognition remains uncertain. We evaluated the robustness of state-of-the-art large language models (LLMs) on nephrology board renewal questions using "None of the other answers" (NOTA) substitution. Methods: From 210 Japanese Society of Nephrology board renewal questions (2014-2023), two nephrologists independently reviewed all items. Questions in which NOTA became the sole correct answer after replacement were included, yielding 145 validated questions. GPT-5, GPT-4o, Gemini 2.5 Pro, and Gemini 2.0 Flash were evaluated via application programming interfaces under default settings. The primary endpoint was accuracy, and paired differences were assessed using the exact two-sided McNemar test. Results: Accuracy was significantly lower after NOTA substitution for all models: GPT-4o, 66.21% to 19.31% (drop, 46.90 percentage points [pp]); GPT-5, 87.59% to 73.10% (14.48 pp); Gemini 2.0 Flash, 58.62% to 31.03% (27.59 pp); and Gemini 2.5 Pro, 86.90% to 55.86% (31.03 pp); all P < .001. GPT-5 showed the smallest decline and the highest accuracy in both versions. Conclusions: All evaluated LLMs showed a significant robustness gap after NOTA replacement. Newer models may be more robust, but multiple-choice accuracy remains an incomplete measure of clinical reasoning robustness.

Evidence-based medicine (EBM) concepts are difficult for medical students to grasp. We developed a Python-Streamlit web application providing interactive visualizations to enhance EBM education. Preliminary use with first year medical students demonstrated high engagement and improved conceptual understanding, supporting the feasibility of integrating interactive, web-based tools into EBM curricula.

Objectives: Characterizing patient portal message content at scale can help target efforts to manage administrative work. We developed and validated a large language model (LLM) pipeline for multi-label classification of messages using an expert-derived topic taxonomy, then characterized topic distribution across a two-year corpus. Materials and Methods: We studied all medical advice request messages sent to ambulatory clinicians at an academic medical center from 2024-2025. We convened an expert panel that derived an 11-category taxonomy through a modified Delphi process. Two annotators labeled 750 randomly selected messages (Cohen kappa 0.80), holding out 500 for evaluation. The pipeline used GPT-4o-mini in a zero-shot prompt. On the held-out set, we measured micro- and macro-averaged precision, recall, and F1, and label stability across runs. We then characterized topic distribution and co-occurrence across the corpus. Results: The pipeline achieved micro- and macro-averaged F1 of 0.89 and 0.86. Labels were identical across runs for 93.6% of messages. Across 2.4 million messages, content concentrated on a few topics. The two most common topics, Problems & Management and Medications & Prescriptions, were present in 67.9% of messages, and the four most common in 93.9%. 51.7% of messages addressed multiple topics. Discussion and Conclusion: The pipeline classified patient message topics accurately and stably across millions of messages. Message content was concentrated within a small number of topics, highlighting opportunities for targeted interventions and enabling more efficient triage, routing, and patient-facing support.

The performance of an EHR-based deep learning model trained on a small sample can be improved if more data is collected. Instead of collecting more data, the model can be trained on additional data from an analogous external source. However, this risks the model learning patterns in the external data that do not generalize to the target sample. Furthermore, data use agreements often prohibit combining datasets with medical records of different sources. We consider utilizing pre-existing methods in continual learning, namely the elastic weight consolidation (EWC) loss function and variational continual learning (VCL), both of which are regularization-based methods that we use to borrow external data and incorporate parameters from a model on external data into local model training. To investigate the utility of this modeling framework, we consider two binary classification tasks: (1) predicting which children will be diagnosed with autism spectrum disorder (ASD) from medical claims up to 18 months, and (2) predicting which patients with end-stage renal disease (ESRD) will be re-hospitalized within 30 days. Target datasets were derived from Duke University's EHR warehouse, and external datasets were sourced from either NC Medicaid claims for the ASD prediction task, or the United States Renal Data System (USRDS) for the rehospitalization prediction task. For both of these tasks, borrowing models - using either the EWC loss function or VCL - performed similarly to that of a model trained only on the full external data, when the sample size of target data used to train the model was small. That is, while a model that does not borrow using our methods performed poorly in low data regimes, the borrowing model instead matched the performance of a model trained on external data even when sample size of target data was small. In addition, an analysis of model predictions showed that models with small samples are better calibrated and more functionally similar to a model trained only on external data when the sample size is small.

Caesarean section in Bangladesh reached 51.8% of deliveries in 2025, and elective caesarean, meaning caesarean before labour began, reached 31.6%. Risk models built on national household surveys are increasingly proposed for pointing audit toward places where scheduled surgery is outrunning clinical need, but they are usually validated in ways that flatter them. Using the 2025 Bangladesh Multiple Indicator Cluster Survey, we developed four models on 9,538 women (logistic regression, elastic net, random forest, gradient boosting) and ran the same procedure under three validation designs: random five-fold cross-validation; five-fold cross-validation grouped by sampling cluster; and leave-one-division-out cross-validation. We also tested transfer between the 2019 and 2025 rounds and audited subgroup calibration. No model improved on logistic regression by a margin worth acting on: the area under the receiver operating characteristic curve ranged from 0.724 to 0.736 under cluster-grouped validation, a spread of 0.012. Validation design mattered far more than the algorithm. Grouping folds by sampling cluster changed discrimination by at most 0.0004, this survey contributing a median of 3 eligible women per enumeration area. Withholding a whole division cost 0.044 to 0.060, more than 100 times as much, and still cost 0.033 to 0.056 after the strongest predictor, an outcome-derived district rate, was removed from every model. A model fitted to 2019 data lost 0.083 when applied to 2025, and the two rounds agreed only moderately on which predictors mattered (Spearman rank correlation 0.61). Calibration held in every wealth quintile, both residence categories and seven of eight divisions; Sylhet was the exception. Elective caesarean is predictable from routine survey items, but that predictability is local. Cross-validation, including cluster-aware cross-validation, does not measure what a model would do in a district it has never seen; a geographic holdout is the cheapest design that does.

Background Stroke remains one of the leading causes of mortality and long-term disability worldwide, with low- and middle-income countries bearing a disproportionate share of the global disease burden. In India, delays in risk identification, fragmented referral pathways, and limited continuity of preventive care present significant challenges, particularly in rural communities. As a frontline health worker Accredited Social Health Activists (ASHAs) are strategically positioned to support community-based stroke prevention; however, existing workflows are frequently constrained by multi-tasking, predominantly paper-based documentation and fragmented digital systems. Advances in mobile health, artificial intelligence along with digital health ecosystem provided by Ayushman Bharat Digital Mission (ABDM) provide an opportunity to strengthen community healthcare through integrated digital platforms. Objective This protocol describes the design, system architecture, and prospective evaluation framework of ASHA Assist India, an integrated AI-assisted mobile health platform intended to support community-based stroke prevention by connecting citizens, ASHA workers, Primary Health Centres (PHCs), and higher levels of healthcare facilities within a unified digital ecosystem. Methods ASHA Assist India has been designed as a modular, cloud-based digital health platform supporting standardized data collection, longitudinal health monitoring, referral management, and AI-assisted clinical decision support. The proposed system comprises four user-facing applications corresponding to citizens, ASHA workers, PHCs, and referral hospitals, integrated through a centralized backend providing authentication, secure data management, interoperability, analytics, and notification services. The AI framework includes three planned analytical modules: (i) population-level stroke risk stratification, (ii) longitudinal stroke risk prediction, and (iii) acute stroke symptom recognition. A prospective implementation study is planned to evaluate platform usability, feasibility, workflow integration, implementation outcomes, and operational performance within routine community healthcare settings. Future validation of the AI modules will be conducted using prospectively collected longitudinal datasets. Expected Impact The proposed platform aims to strengthen community-based stroke prevention by improving digital workflow integration, facilitating coordinated referral pathways, and supporting longitudinal monitoring through the existing healthcare providers at health and wellness centres like ASHA, Community Health Officers (CHOs), ANM, etc. Beyond stroke prevention, the modular architecture is intended to provide a scalable framework for future digital health programmes addressing multiple non-communicable diseases within primary healthcare systems. Publication of this protocol establishes a transparent implementation and evaluation framework that may guide future research, digital health innovation, and implementation science in resource-constrained settings.

Patients with a brain tumour receive evidence-based clinical care in Australia but a focus on supportive care, including social connection, is often deficient. Digital health platforms hold promise to support these patients and their carers. Existing platforms often lack end-user co-design, evidence-based development and rigorous evaluation. Recognising this unmet need, we co-designed Brain Tumours Online, a digital supportive care platform to streamline access to educational resources, symptom management tools, and peer support for patients, carers, and healthcare professionals. In this article, we present our evaluation approach for Brain Tumours Online to advance methodological thinking in the evaluation of multi-faceted, co-designed digital health platforms. In contrast to standardised procedures in clinical trials, digital health interventions such as supportive care platforms are more complex due to their interactive nature, no prescriptive protocols for usage and the dynamic content of web-based information. Thus, traditional evaluation approaches often fall short in evaluating such multi-faceted digital health supportive care platforms. To address these challenges, we developed a bespoke, logic-modelling based evaluation approach to assess the usability, engagement, impact, and economic value of our platform. Our pragmatic but rigourous evaluation approach required the adaptation of existing evaluation frameworks, subject-matter, and lived experience expert knowledge. Our implementation science and co-design approach are shared in different papers. Our study outcomes will also be shared in a separate paper. In the current paper, we share our approach to the evaluation of Brain Tumours Online and provide insights that may be of value for other researchers interested in the nuances of trialing multi-faceted digital health supportive care platforms.

Background: Adverse events (AEs) after hospitalization are common and disproportionately affect adults with multiple chronic conditions (MCC). Capturing patient-reported symptoms and self-assessed health may enable earlier detection of post-discharge AEs. Objective: To identify and test user requirements for an automated remote monitoring system to enhance AE surveillance during the transition home following discharge. Methods: We conducted a mixed-methods study using an iterative, user-centered design approach. Semi-structured interviews with patients and clinicians informed system requirements, followed by real-world field testing in 20 patients who used the system for up to 7 days after discharge. The prototype leveraged interoperable electronic health record data services, delivered automated post-discharge check-ins using a combined questionnaire assessing new or worsening symptoms and patient-reported outcomes (PROs), provided risk-stratified health advice (when and with whom to initiate contact), and escalated high-risk symptoms to clinicians in real-time. Descriptive statistics assessed feasibility and utilization; conventional content analysis identified user needs and implementation considerations. Results: Thirty-seven patients with MCC and 23 clinicians participated. Key requirements for patients included clear communication of personalized risk based on red-flag symptoms, and actionable guidance aligned with discharge instructions. Key requirements for clinicians included explicit delineation of responsibility across inpatient and outpatient setting, and selective escalation to minimize burden. Field testing patients completed 60% of the combined questionnaires. Seven patients received Level 2 or Level 3 health advice after reporting new or worsening symptoms. Three patients triggered Level 3 alerts, resulting in one-time, secure escalation emails to clinicians. Four of the 7 patients who received Level 2 or 3 health advice had chart-confirmed emergency department visits within 1 week of discharge. Patients found the system understandable and helpful, while clinicians noted challenges interpreting PRO trends. Conclusions: These observations support the feasibility and acceptability among patients and clinicians of collecting patient-reported symptoms and PROs during the early post-discharge period. Future iterations should prioritize clear risk communication, role clarity, and interpretable patient-reported data. Formal validation is required to assess predictive performance and clinical utility of symptom-based escalation for post-discharge AE surveillance.

Purpose Prevention and early detection of osteoporosis remains a global challenge, more so in regions like the Philippines where screening barriers exist. Chest x-rays meanwhile are relatively inexpensive, and more frequently done, and therefore can be used for opportunistic screening. This study aimed to develop a deep learning model for osteoporosis detection from chest x-rays using DXA as the gold standard. Methods A convolutional neural network called Osteo-AI was developed using 406 pairs of chest x-rays and DXA scans of Filipino patients aged 50 and above. With data augmentation, the training set expanded to 6,300 pairs. Gradient-weighted class activation mapping technique was applied to localize and identify patterns and areas in the chest x-ray images correlating with osteoporosis. Results Training data consisted of 369 female patients and 37 males. Ages of the patients ranged from 50 to 89 with a mean age of 63 years old. Initial testing yielded promising results, with Osteo-AI achieving a diagnostic accuracy of 85.71%, easily outperforming a benchmark of 33.33% Conclusion Our findings suggest the potential of Osteo-AI to enhance osteoporosis screening accessibility, aiding in early intervention to prevent fragility fractures. Further research involving larger datasets is warranted to refine and optimize the model, potentially improving detection accuracy and expanding its utility in global healthcare settings.

Objective To measure the accuracy of clinical coding, clinician review, and a locally deployed large language model (LLM) in identifying alcohol, drug, and self-harm involvement in emergency department (ED) attendances, and quantify prevalence. Design Two-phase diagnostic accuracy study. In a validation week, the identification strategies were assessed against a conflict-adjudicated reference standard (n=2,256); the LLM was then applied to n=105,096 annual attendances at the same site. Setting UK Type 1 Emergency Department treating patients [&ge;]16yrs. Main outcome measures Prevalence quantification compared with the reference standard; sensitivity, specificity, and balanced accuracy of each strategy; monthly identification rates and adjusted annual prevalence. Results The reference standard identified 12.1% of attendances as involving alcohol, drugs, or self-harm (coding 6.0%; clinician 10.0%, LLM 15.6%). LLM balanced accuracy matched or outperformed clinician review in all three domains (alcohol 0.942 v 0.930, p=0.635; drug 0.959 v 0.791, p<0.001; self-harm 0.982 v 0.908, p=0.004). Coding recorded 1.07 domains per identified patient against 1.32 in the reference standard. Adjusted annual prevalence corresponded to 12,890 domain involvements per year not identifiable in coded data. Subdomain classification found at least 81.6% of self-harm attendances required medical assessment for injury or overdose before psychiatric review. Conclusions Clinical coding identified fewer than half of presentations involving alcohol, drugs, and self-harm and rarely captured co-occurring domains; under-recording was present across a full year. A locally deployed LLM generated more complete structured data from existing clinical text within NHS infrastructure, at a scale which is not feasible for manual review.

Maternal healthcare prediction systems often suffer from algorithmic biases due to socio-economic disparities and imbalanced datasets, limiting their effectiveness for equitable healthcare policymaking. This paper introduces MaternaAI, a fairness-aware and explainable learning framework designed to enhance maternal healthcare predictions in Kerala, India. The framework focuses on three critical health indicators:(1) Tetanus Toxoid (TT) booster uptake,(2) immunization coverage rates, and (3) the percentage of pregnant women completing four or more Antenatal Care (ANC) visits. To address fairness, we propose Adaptive Equity Score Optimization (AESO), a novel optimization algorithm that dynamically integrates fairness constraints into model training. AESO is model-agnostic and adapts group equity weights in response to real-time disparities. We integrate SHAP, LIME, and feature permutation techniques for explainability, enabling transparent global and local interpretation. Empirical results demonstrate that MaternaAI significantly improves fairness metrics and model accuracy across diverse machine learning and deep learning models, offering interpretable and equitable decision support for public health stakeholders.

The openEHR standard provides an open, vendor-neutral architecture for clinical data repositories (CDRs), yet its real-world deployment has not been systematically documented. We conducted a dual-perspective survey combining a vendor survey of openEHR CDR providers with a community survey of openEHR practitioners. Eleven vendor organisations reported deployments across 22 countries and over 100 institutions and health regions. A complementary community survey (n=29, 17 countries) provided context on regulatory environments, adoption drivers, and barriers. Combined, the surveys cover 28 countries, 26 of them with a reported openEHR CDR deployment. Three findings emerge: openEHR has achieved national-scale presence through two distinct channels. Through vendor-market convergence, openEHR-based systems cover the majority of regional health authorities without a national mandate, including 19 of 21 Swedish regions, 3 of 4 Norwegian health regions, and 16 of 21 Finnish wellbeing services counties. Through national health record adoption, governments have built or procured national systems on openEHR as their technical foundation, including Ireland, Malta, Greece, Jamaica and Slovenia. Across Europe, this constitutes an openEHR-based interoperability infrastructure already in place across multiple EU member states. We identified no country in which openEHR is named in binding national regulation, creating structural fragility and an unrealised opportunity for alignment with the European Health Data Space (EHDS). Second, 61% of deployments serve primary use only, and 12% support both primary and secondary use. Third, lack of openEHR-specific knowledge is the most consistent adoption barrier across all geographies and deployment tiers. Adoption is driven by practitioner need and innovation, not by regulatory mandate.

Importance. Cancer is the second leading cause of death among patients in the Caribbean, where outcomes are associated with delayed clinical navigation to screening, diagnosis, and treatment. Artificial intelligence is increasingly used to guide patients with cancer to care, but whether these systems provide clinically actionable, facility-verified guidance for individuals in this population, and whether governance of the system is associated with the quality of that guidance, has not been evaluated. Objective. We tested whether a governed community learning platform navigates Caribbean cancer patients better than four ungoverned AI systems, and we tracked how community intelligence accumulates over time. Design, Setting, and Participants. We deployed a community learning ledger (CaribChat.ai) across ten Caribbean jurisdictions beginning March 2, 2026, and report all sessions through June 1, 2026 (N=207). An initial actively-promoted accrual period (March 2 - April 6, 2026; 168 sessions) was followed by continued organic use after active clinical promotion ceased. We then submitted the same 28 patient screening queries to ChatGPT (GPT-4o), Claude Haiku 4.5, DeepSeek-Chat, and OpenEvidence on April 5-6, 2026. Claude Haiku 4.5 powers CaribChat; testing it without governance isolates the governance effect. The platform requires no registration. Exempt under 45 CFR 46.104(d)(4)(ii). Main Outcomes and Measures. We classified 207 community sessions by thematic domain and temporal phase. We scored each of five systems on Caribbean facility citation, actionable navigation, and US-resource leakage across 28 screening queries. Results. The ledger accumulated 207 sessions - 168 during an actively-promoted accrual period (March 2 - April 6) and 39 after active clinical promotion ceased. Community engagement evolved from screening questions to active treatment navigation and diaspora engagement. CaribChat cited verified Caribbean facilities in 28/28 (100%) responses versus 10/28 (35.7%) for ChatGPT and 9/28 (32.1%) for OpenEvidence. CaribChat provided actionable navigation in 28/28 (100%) versus 2/28 (7.1%) for OpenEvidence (P<=.001). The same model scored 100% with governance and 54% without (P<=.001). DeepSeek cited US resources in 57.1% of Caribbean responses. After active clinical promotion ceased, off-codebook queries rose from 2.4% to 26.7% across phases while the governance contract continued to reject every adversarial probe - the community persisted but drifted from the cancer codebook absent clinician curation. The deployment operated within the OECS Health Strategy 2030 and CARICOM regional health frameworks, with queries originating across Caribbean jurisdictions led by Trinidad and Tobago. Conclusions and Relevance. Every ungoverned AI system we tested failed Caribbean cancer navigation. The best scored 68%. The most widely adopted physician platform scored 7%. The same foundation model scored 100% with governance and 54% without. Community intelligence accumulated from the population it serves, not published literature, is what makes health AI work in SIDS. The post-promotion decay shows the requirement is bidirectional: sustained, on-codebook engagement depends on patients and clinicians working together - community participation and active clinical curation are jointly necessary for maximum AI leverage.

Background: Free-text notes in electronic health records (EHRs) contain fine-grained psychiatric information that is essential for psychiatric research and clinical care, and often absent or under-recorded in structured codes alone. Clinical natural language processing (cNLP) can support extraction of this information from EHR notes, yet Spanish-language cNLP remains under-developed. Moreover, broad evaluations comparing multiple encoder-based language models across extensive, fine-grained psychiatric concept sets remain scarce, and it remains unclear how these models compare with traditional NLP (tNLP) systems and much larger generative large language models (LLMs). In addition, cross-site performance of fine-tuned models is rarely tested, and limited annotated training data remains a major challenge, especially for rare symptoms. Objectives: We aimed to advance scalable, global psychiatric cNLP by fine-tuning multiple encoder-based models with differing architectures and pre-training strategies for detecting fine-grained psychiatric concepts in Spanish EHRs. We further evaluated the impact of augmenting the fine-tuning data with precision-weighted weak labels for less-frequent concepts, and compared the performance of the encoder-based models to that of tNLP and a fine-tuned generative LLM trained on the same data. Finally, we evaluated model cross-site generalizability on an external EHR dataset. Methods: Three encoder-based models (BETO, XLM-RoBERTa-large, and bsc-bio-ehr-es) were fine-tuned on 1,642 clinician-annotated EHR documents from Colombia to detect 110 psychiatric concepts in Spanish text. To address the limited annotated examples available for less-frequent concepts, 12,000 additional documents were weakly-labeled for less-frequent concepts using tNLP, and incorporated into the fine-tuning data with labels weighted by pattern precision. Models were compared with tNLP and a generative LLM, and evaluated on an external EHR dataset from another psychiatric hospital in Colombia. Results: Encoder model performance varied substantially, with macro-F1 ranging from 0.64 to 0.81. BETO achieved the highest macro-F1 (0.81; median F1=0.88 [IQR=0.77-0.96]). Adding precision-weighted weak labels for less-frequent concepts improved BETO's overall macro-F1 to 0.83 and increased mean F1 for the 55 augmented concepts from 0.82 to 0.86. Under matched fine-tuning conditions, fine-tuned BETO and the tNLP method were equivalent in F1, whereas the LLM significantly outperformed BETO in F1. After weak-label augmentation, BETO significantly outperformed tNLP in F1 (PFDR<.001) and narrowed the performance gap with the LLM, although equivalence was not established. Lastly, fine-tuned BETO maintained reasonably strong performance on data from an external hospital not used for model fine-tuning (out-of-domain macro-F1=0.78). Conclusions: General-purpose pre-trained encoders had strong performance for psychiatric concept extraction from Spanish EHRs. Weak-label augmentation improved BETO's performance and strengthened results relative to a tNLP baseline, while reducing, but not eliminating, the performance gap with a much larger fine-tuned generative LLM. These findings highlight the utility of these relatively lightweight models for scalable, accurate and reproducible detection of psychiatric concepts in Spanish-language EHRs.

ObjectiveTo establish a standardized training program for endoscopic pathogen visualization literacy (EPVL) based on fluorescence rapid on-site evaluation (ROSE) technology for gastroenterologists, and to evaluate its training efficacy. MethodsA prospective quasi-experimental study was conducted. A total of 54 gastroenterology trainees were non-randomly allocated into the EPVL training group (Group A, n=28, 16-hour comprehensive training) and the control group (Group B, n=26, 3.5-hour traditional teaching). Pre- and post-training assessments included theoretical examinations, fluorescence ROSE image interpretation tests (30 parallel images per set), interpretation speed measurement, and clinical decision-making integration evaluation. The primary outcome was the change in image interpretation accuracy, analyzed by ANCOVA with pre-test scores as the covariate. ResultsBaseline characteristics were comparable between groups (P>0.05 for all demographic variables and pre-test scores). Group A showed significant improvement in image interpretation accuracy from 57.8{+/-}13.6% pre-training to 82.5{+/-}11.2% post-training (improvement of 24.7%, paired t=-12.86, P<0.001), while Group B improved from 58.5{+/-}13.0% to 71.0{+/-}13.5% (improvement of 12.5%, paired t=-5.24, P<0.001). After ANCOVA adjustment for pre-test scores, the between-group difference was significant (F(1, 51)=10.95, P=0.0017, 2=0.177), with Cohens d=0.94 (large effect size). Interpretation speed in Group A (19.2{+/-}2.8 s/image) was significantly faster than in Group B (32.5{+/-}6.0 s/image, t=-10.45, P<0.001). Clinical decision-making scores were significantly higher in Group A (80.5{+/-}8.0 vs. 65.3{+/-}11.5, t=5.60, P<0.001). The Kappa agreement with the gold standard in Group A improved from 0.56{+/-}0.18 to 0.84{+/-}0.11 (t=-8.35, P<0.001). Participant satisfaction exceeded 88%. ConclusionThe EPVL training program significantly improves gastroenterologists fluorescence ROSE image interpretation accuracy, speed, and clinical decision-making integration, providing a novel and effective standardized training paradigm for digestive endoscopy education.

Objectives. To assess how digital inclusion factors and physical access barriers are associated with user trust in smartphone-based remote photoplethysmography (rPPG) hypertension screening, and to identify implications for digital health pol- icy, procurement and implementation in low-resource settings. Methods. Cross-sectional mixed-methods survey in five outpatient clinics in Kebbi State, northern Nigeria (N =287). Trust was measured using comfort, confidence and perceived usefulness Likert scales. Primary analyses used binary logistic models with HC3 robust standard errors; sensitivity analyses are reported in supplementary material. Free-text responses were thematically analysed. Results. Smartphone ownership was 51.2%; Transsion-brand devices comprised 56.5% of owners. Greater distance to a blood pressure facility was independently associated with lower perceived usefulness (OR 0.51, 95% CI 0.30-0.87; p=0.013) and lower comfort (OR 0.61, 0.37-0.98; p=0.042). Among owners, Transsion versus Samsung showed higher confidence odds (OR 3.82, 1.02-14.27; p=0.046). Qualitative themes supported the implementation interpretation: platform-fit and device speed requests among Transsion owners; connectivity and offline-first concerns among those with greater travel distance. No brand contrast achieved FDR-adjusted significance; brand findings are exploratory. Conclusions. Digital health policy and health technology assessment for smartphone-based screening should incorporate local device ecology, connectivity constraints, physical access burden and trust-calibration safeguards. Pre-implementation assessment of these factors is necessary for equitable and safe rPPG adoption in low-resource health systems.