Expert Systems with Applications

Background: In Japan, acute inpatient care is divided into approximately 335 secondary medical care areas, which serve as the basic units for planning healthcare delivery systems under the 8th National Health Care Plan. While comparisons between regions and facilities typically rely on a single risk-adjusted metric, this approach confuses differences in patient demographics with differences in the actual infrastructure of intensive care units (ICUs). This paper presents a framework - MedZone Embedder - for deriving data-driven indicators of regional structural vulnerability by mapping secondary medical care areas onto a learned similarity space, together with its working implementation. The paper sets out the concept, the method, a proof of concept, and an explicit staged validation program, rather than national empirical results. Methods: Each area is represented by a feature vector consisting of aggregated values of intensive care provision indicators derived directly from the Japan Intensive Care Patient Database (JIPAD) - specifically, risk-adjusted mortality rates (standardized mortality ratios and an in-hospital composite indicator), technical efficiency, length of stay, readmission rates, case severity, and case composition - with the within-area variance of these indicators also taken into account. No hierarchical processing by facility type is performed. A contrastive autoencoder (multilayer perceptron encoder 32 -> 16 -> 8, symmetric decoder) is trained by self-supervised learning, using an objective function that combines reconstruction and normalized temperature cross-entropy (NT-Xent) on noise-augmented views. The resulting 8-dimensional embedding supports area searches based on cosine similarity and anomaly scoring in the embedding space (using isolation forest, Mahalanobis distance, or k-nearest-neighbor density), which is normalized to a vulnerability score ranging from 0 to 1. If deep learning libraries are unavailable, or if the number of areas is small, an alternative method using deterministic principal component analysis is employed. Results: This method was implemented and deployed within an operational ICU decision support system on a managed cloud platform. The proof of concept (PoC) is structured around five secondary medical care areas within Kyoto Prefecture and runs entirely on synthetic facility-level aggregate data constructed to follow the JIPAD indicator schema; no registry data were accessed. It generated: an aggregate provision profile for each area; an area embedding space equipped with a similar-area search function; and a vulnerability ranking that identifies areas with low patient numbers and low diversity that exhibit overall poor outcomes. At this scale, the contrastive autoencoder falls back to principal component projection. The deep learning pathway has been implemented and unit testing has been completed; training and evaluation on actual registry data are pending data-use approval and the expansion of data integration. Validation is staged: Stage 2 will train the contrastive pathway over JIPAD-covered areas to assess construct validity against public structural indicators (ICU/HCU beds, population, accessibility), and Stage 3 will extend coverage to all areas via National Database (NDB) linkage. Conclusion: MedZone Embedder reframes regional comparison from single-indicator ranking to structural representation: which areas are alike, and which are structural outliers. The contribution of this paper is the framework - the proposal that the intensive care provision structure of Japanese secondary medical care areas can be learned from a national outcomes registry and read through the lens of what we call institutional debt - together with a deployed implementation and a pre-specified validation program. To our knowledge, this is a candidate first application of contrastive representation learning to Japanese secondary medical care areas.

BACKGROUND: Artificial intelligence (AI) medical scribes rely on speech-to-text (STT) models for transcription. Evaluations of STT models in non-English settings remain scarce. We benchmarked ten STT models on medical consultations from Latin American (LatAm) Spanish and assessed whether fine-tuning improves transcription accuracy. METHODS: Ten YouTube videos depicting medical consultations. Human transcriptions were the ground truth. Five open-source models were evaluated: Whisper Large, Whisper Large v3, Whisper Large v3 Turbo, Voxtral Mini 3B, and Canary 1B v2; and so were five close-source models: gpt-4o-transcribe, gpt-4o-mini-transcribe, gemini-2.5-pro, Eleven Labs, and Assembly AI. Whisper Large v3 was fine-tuned. One video was withheld from training. Performance assessed using Word Error Rate (WER), Character Error Rate (CER), BLEU Score, ROUGE-L, BERT Score, and Semantic Similarity on the one withheld video. RESULTS: None of the fine-tuning iterations outperformed the vanilla Whisper Large v3. With the withheld video, Gemini-2.5-pro was the close-source model with the best performance in four of six metrics. In comparison to the close-source models, the fine-tuned model never outperformed the other models (withheld video); conversely, in comparison to the close-source models, the fine-tuned model showed better performance across metrics, for instance: BLEU score (63% vs to 58% for the second-ranking model), BERT (89% vs to 86%), and semantic similarity (89% vs to 83%), CER (19% vs 20%). CONCLUSIONS: Whisper Large v3 and its fine-tuned variant are the best open-source STT models for transcribing medical conversations in LatAm Spanish. These findings provide an evidence base for developing AI medical scribes tailored to Spanish-speaking LatAm.

Pneumonia is a leading cause of infectious disease mortality worldwide, accounting for approximately 2.5 million deaths annually and 15% of deaths in children under five. Chest X-ray imaging remains the primary diagnostic tool, but accurate interpretation requires radiological expertise that is disproportionately concentrated in high-income settings, creating a diagnostic gap where disease burden is highest. Automated deep learning offers a scalable complement to specialist-dependent diagnosis, yet clinical adoption requires both high accuracy and transparent, interpretable reasoning. Convolutional neural networks (CNNs) have shown strong potential for pneumonia detection from chest X-rays, but two barriers impede clinical translation: the interpretability of black-box models and the computational feasibility of large architectures in resource-constrained settings. Explainable AI (XAI) methods such as Grad-CAM, Grad-CAM++, and Score-CAM address the interpretability barrier, yet systematic quantitative comparisons across multiple CNN architectures remain scarce. Furthermore, CNN architectures widely used for medical image classification carry high parameter counts that limit feasibility in resource-constrained settings, motivating architectures that achieve competitive accuracy with substantially fewer parameters. Here we propose a parameter-efficient deep learning framework for pneumonia detection based on transfer learning, evaluated across three CNN architectures representing distinct architectural families: EfficientNet-B0 with fine-tuning (proposed method), ResNet50, and DenseNet121, trained under identical conditions on the Kaggle chest X-ray dataset (5,863 images). Our method achieved 90% classification accuracy, outperforming both baselines while requiring 4.8x fewer parameters than ResNet50. To evaluate explainability, Grad-CAM, Grad-CAM++, and Score-CAM were applied across all three architectures and compared quantitatively using Intersection over Union against manually annotated lung segmentation masks, Insertion score, and Deletion score, with pairwise statistical validation via Wilcoxon signed-rank tests and Bonferroni correction. Findings show that classification accuracy and XAI explanation quality must be evaluated independently, and that the proposed parameter-efficient architecture offers a favorable trade-off for resource-constrained clinical deployment.

The Cancer Genome Atlas (TCGA) holds clinical data for over 11,000 patients across 33 cancer types, but access is hard because of complex file structures, heterogeneous formats, and the need for programming. We present an agentic system for natural language querying and statistical analysis of TCGA clinical data. The system uses a large language model as an autonomous ReAct agent that selects from eight computational tools, including data extraction, descriptive statistics, Kaplan-Meier survival analysis with log-rank tests, hypothesis testing, and verification against the curated TCGA Pan-Cancer Clinical Data Resource (CDR). The agent reasons about intermediate results, adapts its approach, and returns clinically contextualized responses with source attribution and auditable traces. We introduce TCGA-Agent-Bench, 440 queries across five difficulty tiers with ground truth from the independently curated TCGA-CDR, evaluated with dual metrics of numerical accuracy and clinical completeness. The system achieves 93.4% overall accuracy (100% single-patient lookups, 99.1% cohort statistics, 92.8% comparative analyses), outperforming a fixed rule-based pipeline (87.1%), a single-pass LLM (81.8%), and retrieval-augmented generation (66.9% on a subset). Most of the benchmark is answerable from the CDR alone, so we locate the extraction layer's value in fields the CDR lacks (drug treatments, TNM components, biomarkers, biospecimen metadata): on 26 queries targeting these, the full system answers 100% versus 3.8% for CDR-only. Ablations show the reasoning loop is most impactful (+9.1% accuracy, +22.0 completeness points). A tool-based agentic architecture enables accurate, auditable analysis of clinical repositories, with value driven by tool design and recovered fields rather than model scale.

Background: Venous thromboembolism (VTE), including deep vein thrombosis (DVT), remains a major global health burden. Diagnostic pathways rely on ultrasound but are limited by availability and prolonged time-to-imaging. Novel artificial intelligence (AI) guidance systems have been designed to enable non-ultrasound-trained operators to acquire proximal lower extremity compression ultrasounds for remote clinician interpretation. Methods: This multicenter, double-blinded, prospective, nonrandomized study evaluated the performance of an AI guidance system (ThinkSono Guidance, ThinkSono, GmbH). Patients underwent AI-guided ultrasound(s) and standard of care ultrasound(s). Primary and secondary endpoints were image quality, sensitivity and specificity for proximal DVT, and prioritization specificity, a measure of specificity in identifying patients requiring standard of care ultrasound after AI-guided scan. Results: Of 634 recruited subjects, 594 were analyzed, with 67 DVTs across 700 scans. 86.83% of AI-guided scans achieved diagnostic image quality. Triage sensitivity was 92.86%, triage specificity 39.12%, prioritization specificity 97.96%. Standard of care ultrasounds could be avoided in 35.32% of patients. Total median AI-guided scan and review time was 7.57 minutes. Conclusions: Clinician-reviewed AI-guided scans were rapid, sensitive for DVT, and specific for prioritizing patients requiring standard of care ultrasounds. These findings suggest AI-guided ultrasound may be a scalable triage strategy to expand DVT evaluation access, particularly in resource-constrained and after-hours settings

Rising costs, slow accrual and molecular substratification of cancers necessitate novel clinical trial designs. We demonstrate that artificial intelligence-generated synthetic patients can replace real controls to reproduce results of the SORAML trial. Using external multimodal data from 1,377 acute myeloid leukemia (AML) patients from previous trials and a real-world registry, we fine-tuned a tabular foundation model to generate synthetic patients, reproducing clinical and genetic features and outcome associations. Synthetic patients were then matched to the original SORAML intervention group using Cox risk scores, replacing the original control and reproducing the original trial result with near-identical median event-free survival (EFS) and treatment effect (original hazard ratio [HR] 0.64, 95%-confidence interval [CI] 0.47-0.87, p=0.004; with synthetic control HR 0.66, 95%-CI 0.48-0.90, p=0.009). Our findings demonstrate that AI-generated synthetic patients can serve as statistically rigorous controls supporting novel trial designs.

Background Unsupervised machine learning has become a cornerstone of computational phenotyping across clinical medicine, genomics, imaging, and multi-omics research. However, phenotype discovery relies on a sequence of analytical decisions - including missing-data handling, preprocessing, dimensionality reduction, clustering methodology, and stochastic initialization - that are rarely evaluated collectively. Although clustering stability has been extensively investigated, the robustness of complete analytical workflows remains largely unexplored. Results We developed an Analytical Perturbation Framework that systematically quantifies the robustness of phenotype discovery by perturbing complete unsupervised learning workflows rather than individual clustering algorithms. Using a real-world cohort of 1,286 women with polycystic ovary syndrome (PCOS), we generated 116 valid analytical pipelines comprising alternative preprocessing strategies, missing-data handling methods, dimensionality reduction approaches, clustering algorithms, and random initializations. Agreement between independently generated phenotype solutions was consistently low (median Adjusted Rand Index = 0.079), indicating substantial sensitivity of phenotype discovery to routine analytical decisions. Variance decomposition identified preprocessing as the largest contributor to phenotype instability (22.8%), followed by clustering methodology (14.6%), whereas stochastic initialization explained only 3.1% of the observed variability. At the patient level, most individuals exhibited reproducible phenotype assignments (median Patient Robustness Score = 0.719), although a substantial subgroup showed markedly lower assignment stability. Feature perturbation analyses identified follicle-stimulating hormone, anti-thyroglobulin antibodies, anti-thyroid peroxidase antibodies, total testosterone, luteinizing hormone, and androstenedione as the strongest contributors to computational robustness, rather than biological importance. Finally, phenotype solutions demonstrating greater computational robustness also exhibited greater biological coherence during independent validation.

INTRODUCTION: The biomarker-based amyloid/ tau/ neurodegeneration (A/T/N) framework has become a popular staging method for Alzheimer's disease (AD) research. Previous studies use the framework either as a rule-based or data-driven approach but typically sacrifice either adaptivity or interpretability. METHODS: We present an interpretable, hybrid method, called Neurosymodal Data Fusion, for predicting incident AD in the ADNI dataset. Specifically, we encode the A/T/N framework as a logic program, where the input biomarker features are extracted by one or more neural networks. RESULTS: Our pipeline predicted four-year incident AD with a sensitivity of up to 0.84. Additionally, our models learned scores for each A/T/N profile, denoting relative importances to model predictions. These scores also indicated that empirically-derived cut-off values for the A and T criteria might be uninformative for the ADNI data. DISCUSSION: Our pipeline provides a novel way to use the A/T/N framework that could potentially improve early AD screening years before clinical manifestations.

Purpose: Nonresponse to routinely collected patient-reported outcome measures (PROMs) threatens the representativeness of aggregated data. We characterized patient-, provider-, and clinic-level factors associated with PROMIS Global-10 nonresponse in routine radiation oncology care. Methods: In this retrospective cohort study, all adults seen at five Mass General Brigham radiation oncology clinics over one year were included. The primary outcome was patient-level nonresponse, defined as never completing the portal-administered Global-10 versus completing it at least once. Using iterative mixed-effects logistic regression, we modeled patient-, provider-, and clinic-level factors. Results: Among 12,214 patients, 71 providers, and five clinics, patient- and appointment-level response rates were 35.4% and 10.9%, with patient-level response ranging nearly fivefold across clinics (12.8% to 66.2%). In Model 1, male sex, lower education, not working, and recent surgery had higher odds of nonresponse, and longer time since diagnosis lower odds. After provider- and clinic-level factors were added, patient sex, education, and employment became nonsignificant, whereas recent surgery (adjusted odds ratio [aOR] 1.97) and longer time since diagnosis (aOR 0.46 for >12 months) persisted. A provider's historical collection rate was protective but attenuated at the clinic level. There, a later program launch (aOR 0.29) and higher historical collection rate (aOR 0.79) correlated with lower nonresponse, whereas academic versus community setting did not. Conclusions: Nonresponse to routinely collected PROMs is a multilevel phenomenon driven substantially by clinic-level implementation factors, not patient characteristics alone. Because response rate is only a proxy for representativeness, PROMs programs and PRO-based performance measures should prioritize representative collection over volume.

Controlled human infection models (CHIMs) are increasingly used in infectious disease research to study pathogen dynamics and evaluate interventions under controlled conditions. However, these studies are resource-intensive and involve ethical and safety constraints, making efficient study design critical. Dose-finding is a key early component in CHIMs, where the aim is to identify a challenge dose that achieves a target infection probability. Traditional rule-based designs are commonly used but can be inefficient, motivating the use of model-based adaptive approaches such as the Bayesian Continual Reassessment Method (CRM). Although CRM has been extensively studied and widely adopted in Phase I oncology trials for identifying the maximum tolerated dose of therapeutics, its application in CHIM settings remains limited, particularly when the endpoint of interest is infection. This tutorial provides step-by-step guidance for implementing a Bayesian CRM in dose-finding CHIMs, using an oropharyngeal Neisseria gonorrhoeae challenge as a motivating case study. The framework outlines key design components, including dose-grid specification, dose-response model, prior elicitation, Bayesian updating, decision rules, and stopping criteria, with particular emphasis on a clinically interpretable parameterisation. Trial operating characteristics are evaluated through simulation studies under multiple dose-response scenarios and prior-predictive analyses, and compared with a commonly used '3+3' type rule-based design. This work highlights the advantages of Bayesian model-based designs for dose-finding in CHIMs over classic rule-based designs and provides a structured, reproducible framework for implementing CRM, supporting their application in future CHIM studies.

Background and Aims The optimal treatment for first episodes and first recurrences of Clostridioides difficile infections (CDI) is unknown and there is emerging evidence for pulse and taper (P-T) regimens. Therefore, we sought to estimate the relative efficacy of treatment options. Methods MEDLINE and CENTRAL were searched from database inception to May 21, 2025 and unpublished conference abstracts were searched from recent infectious disease conferences. RCTs on the treatment of first episodes or first recurrences of CDI comparing fixed-dose or P-T regimens of fidaxomicin or vancomycin were included. The primary and secondary outcomes were 40- and 56-day CDI recurrence, respectively. A random-effects network meta-analysis on the risk ratio (RR) scale was conducted using a standard regimen (10-14 days) of vancomycin as the comparator. Treatments were ranked using the surface under the cumulative ranking curve (SUCRA). Results 8 RCTs were included comprising a total of 2181 patients. For 40-day recurrence, fidaxomicin P-T had the highest probability of ranking best (RR=0.10, 95%Confidence Interval [95%CI]=0.10-0.49, SUCRA=1.00), followed by vancomycin P-T (RR=0.49, 95%CI=0.32-0.76, SUCRA=0.61), fixed-dose fidaxomicin (RR=0.61, 95%CI=0.49-0.76, SUCRA=0.39), and, finally, fixed-dose of vancomycin (SUCRA=0.00). The treatments ranked in the same order for 56-day recurrence, though only 3 RCTs reported on this timepoint. Conclusion Vancomycin P-T, fidaxomicin P-T, and fixed-dose fidaxomicin were all superior to a fixed-dose vancomycin. Head-to-head comparative effectiveness RCTs are needed to quantify their relative effect sizes of and impact on long-term prevention of recurrent CDI.

Background The 2022-2023 global mpox outbreak highlighted the critical need for robust genomic surveillance capabilities to track mpox virus (MPXV) evolution and transmission dynamics. Methods Building upon our established SARS-CoV-2 sequencing infrastructure, we implemented a Molecular Loop probe-based long-read sequencing approach using Pacific Biosciences Sequel II technology for comprehensive MPXV genomic surveillance across the United States (US). From August 2024 to June 2025, we generated 326 high-quality whole genome sequences from residual mpox-positive clinical specimens collected by Labcorp across all 10 US Department of Health and Human Services regions. Results Our analysis identified two samples containing clade Ib MPXV in January and June 2025 and captured shifting trends in clade IIb diversity, with 13 distinct lineages observed. We also identified multiple instances of large (~1.6-17.6kb) deletions proximal to the inverted terminal repeats in clade IIb genomes. APOBEC3 mutation analysis indicated substantial evidence of human-to-human transmission among both clades. Further, we observed significantly higher APOBEC3-associated SNPs per kilobase (P<0.001) in clade IIb genomic variable regions relative to their central conserved region. Our assay exhibited strong reproducibility across biological replicates from individual patients and accuracy was confirmed via parallel sequencing of select specimens by US Centers for Disease Control and Prevention (CDC) using metagenomic sequencing. We also demonstrated via custom simulation that our assay discriminates all known MPXV clades and lineages, including those we have not observed in the US. Conclusions Our integrated nationwide surveillance system facilitates real-time genomic tracking of outbreak evolution, with demonstrated capacity across SARS-CoV-2 and MPXV, positioning this platform for rapid deployment during future pathogen emergence.

Background: Monoclonal antibodies have emerged as a prophylactic strategy to prevent symptomatic SARS-CoV-2 infection in immunocompromised individuals. However, the evolutionary and clinical implications of breakthrough infections under this regime remain unclear. Methods: A male in their 80s with a haematological/oncological diagnosis received a 2000 mg intravenous infusion of sotrovimab in March 2023 and was diagnosed with COVID-19 by RT-qPCR from a nasopharyngeal swab in August 2023. Weekly samples (n=24) were collected through February 2024 (171 days). All samples underwent whole-genome sequencing, with select mutations subjected to functional assessment. Findings: Sequencing identified the GE.1 lineage at all timepoints. An intra-host recombination event in ORF1ab (positions 8942-12458) was detected prior to 23 weeks post-detection, followed by a 14-fold increase in viral load (7.42e+06 to 1.00e+08 RNA copies/mL) and a marked shift in the viral population. E340D, a sotrovimab resistance mutation, was detected at low abundance (46%) within the first week post-infection, fluctuated over time, and was nearly fixed by week 15 (107 days) post-detection. We assessed five spike mutations - V36M, S98F, and V213G in the N-terminal domain, Y505P in the receptor-binding domain, and P681Q near the S1/S2 cleavage site - and additionally evaluated the impact of E340D. V36M conferred the highest infectivity across all cell lines, with the most significant effect in low-TMPRSS2 cells. While all mutations showed enhanced infectivity with the addition of E340D, the effect was most pronounced in mutations with lower baseline infectivity. The addition of E340D significantly decreased relative neutralizing titres for V36M, S98F, and V213G, enabling escape from neutralizing antibodies in XBB-responsive individuals, illustrating an enhanced phenotypic advantage. Patient neutralizing activity was absent pre-sotrovimab, and sotrovimab-induced neutralization was further compromised by selection of E340D. Interpretation: Sotrovimab pre-exposure prophylaxis in an immunocompromised patient did not prevent SARS-CoV-2 infection, and selected for resistant mutation E340D, with unexpected fitness consequences across non-receptor binding domain spike regions.

Stochastic epidemic models are a cornerstone of infectious disease epidemiology and are often used to study intervention scenarios. However, large run-to-run variability can make intervention effects difficult to estimate precisely. We revisit the epidemic Sellke construction, which assigns each individual an infection threshold for the cumulative infection hazard such that, conditional on the thresholds, the epidemic trajectory becomes deterministic. This enables coupling of simulations with and without an intervention, yielding low-variance effect estimates even when outcomes such as final size or peak incidence vary widely between runs. We develop an exact, event-driven implementation that maintains infection and recovery events in priority queues. Cumulative infection-hazard updates require O(log N) time per event, yielding overall complexity O(Elog N) for E events in a population of size N. The implementation achieves computational performance comparable to the classical Gillespie algorithm while naturally accommodating non-Markovian infectious periods and complex infectiousness profiles. We illustrate the approach using distance-dependent spread of avian influenza between poultry farms in the Netherlands and a multilayer population with households, schools, and workplaces. In both examples, coupling enables efficient within-run comparisons of intervention scenarios across stochastic realisations.

Background: Opioid use disorder (OUD) is heritable, yet most genome-wide association studies (GWAS) have focused on European populations, leaving the genetic architecture of OUD in non-European populations underexplored. Methods: We conducted GWAS of OUD across three ancestries using electronic health records and genomic data from 52,357 All of Us Research Program participants (8,912 cases; 43,445 matched opioid-exposed controls; 48.5% female). Participants were stratified into European (EUR), African (AFR), and Admixed American (AMR) ancestry groups for logistic regression GWAS, with independent replication in the Million Veteran Program. We then applied the deep-learning model AlphaGenome to predict the tissue-specific transcriptomic and splicing consequences of top risk variants across 13 reward-pathway brain regions. Results: We identified and replicated a novel DDX6 risk locus, alongside established OPRM1 and FURIN signals. AlphaGenome predicted the DDX6 regulatory allele downregulates the stress-resistance gene FOXR1 in the nucleus accumbens, while the protective OPRM1 variant (rs1799971) upregulates OPRM1 expression across reward networks. Other signals of interest included IL6R and SHISA9 (EUR); GHR (AFR); and ASTN2 (AMR). Conclusions: This study identifies DDX6 as a novel OUD risk locus, replicates associations with OPRM1 and FURIN, and highlights biologically plausible ancestry-specific signals in AFR and AMR populations. We also replicated top variants in an independent population. Finally, integrating GWAS with deep-learning annotations provides specific, localized biological hypotheses to guide future experimental validation and targeted therapeutics.

Patients and caregivers seek informational and emotional support throughout medical care, especially when interpreting unfamiliar laboratory test results. Although resources such as patient portals and online health communities (OHCs) help address questions, gaps remain. The emergence of large language models (LLMs) offers the potential to be a complementary source of support to assist patients and caregivers in understanding and using their test results. The objective of our study is to empirically compare LLM responses to patients online questions containing their laboratory test results to responses written by peers in an OHC. We compared the 519 peer replies to 122 laboratory test-related posts from an OHC to 488 responses generated from four LLMs using mixed computational and qualitative methods. LLMs frequently provided clear explanations of medical terminology and structured interpretations of numeric results but were longer and less readable. Peers offered more personalized, context-specific emotional support. Overall, LLMs have the potential to complement peer responses in OHCs, but require greater emotional depth, reasoning transparency, and alignment with community norms.

Estimating dengue force of infection (FOI) is essential for understanding transmission dynamics and targeting intervention programmes, yet surveillance data in endemic settings required for estimations are often incomplete, with varying formats. We developed a Bayesian hierarchical catalytic model that jointly fits age-stratified case data, aggregate case data, and seroprevalence surveys within a single framework, incorporating external covariates to improve parameter identifiability. Synthetic validation showed that covariates alone recovered accurate FOI point estimates even when most districts contributed only aggregate data, but did so with poorly calibrated uncertainty; anchoring the model with a single seroprevalence survey was necessary to bring credible interval coverage close to nominal. Applied to 128 districts across Java and Bali, Indonesia (2016-2024), the model revealed substantial spatial heterogeneity in FOI and reporting rates. Many districts in Java exceeded the WHO-suggested seroprevalence threshold for vaccine introduction, yet were classified as low-priority when using reported incidence as prioritisation criterion, particularly in areas with weak surveillance. Model-based seroprevalence estimation, integrating multiple data sources, offers a more consistent basis for identifying high-priority districts for vaccine introduction, and is less susceptible to surveillance bias than reported incidence.

Background: Children born prematurely (before 37 weeks) or admitted to the neonatal unit (NNU) are at increased risk of adverse long-term physical health outcomes. It is also recognised that there is an association with later academic performance and special educational needs, however it is not clear whether these broad risk factors could be used as stand-alone heuristics to identify children who may benefit from additional support in educational settings. We aimed to examine the associations between neonatal unit (NNU) admission and educational attainment in mid-childhood. Methods and Findings: Pregnancy data from a prospective birth cohort (Pregnancy Outcome Prediction Study, Cambridge, United Kingdom, 2008-2012) were linked to national educational outcomes (Department for Education, United Kingdom). Multivariable regression models adjusted for maternal, child, and socioeconomic factors were used to evaluate associations between (i) all NNU admissions, (ii) at term NNU admissions >48 hours, (iii) preterm birth without ongoing physical health needs, and educational outcomes at ages 5-11 years. Children who required any NNU care were more likely not to meet expected educational standards across multiple ages and domains in early and mid-childhood: age 5 early year foundation (aOR 1.64, 95% CI 1.19-2.27, p=0.003), phonics at age 6 (aOR 2.43, 95% CI 1.72-3.57, p<0.001), and at age 7 (here assessments were divided into multiple domains): reading (aOR 1.67, 95% CI 1.18-2.38, p=0.004), writing (aOR 1.72, 95% CI 1.25-2.38, p<0.001), mathematics (aOR 1.56, 95% CI 1.09-2.22, p=0.020), and science (aOR 1.85, 95% CI 1.22-2.78, p=0.003). Similar patterns were observed among both at term-born infants who stayed >48hrs in NNU (phonics assessment at age 6 aOR 2.26, 95% CI 1.51-3.36, p<0.001) and in children born preterm without long-term physical health sequelae (phonics assessment at age 6 aOR 3.07, 95% CI 1.96-4.81, p<0.001). These associations were robust to adjustment for demographic, perinatal, and socio-economic factors. By age 11, differences in academic attainment were attenuated and no longer clearly distinguishable across all exposure groups. However, there was an increased likelihood of special educational needs (SEN) at age 11 associated with any NNU admission (aOR 1.78, 95% CI 1.15-2.73, p=0.009), at term NNU admission for >48hrs (aOR 1.88, 95% CI 1.19-3.00, p=0.007), and children born preterm without long-term physical health sequelae (aOR 1.50, 95% CI 1.00-2.25, p=0.049). Predictive performance of any NNU admission for SEN at age 11 was moderate (AUC 0.70, 95% CI: 1.14-2.65, p=0.010), with balanced sensitivity and specificity and high negative predictive value. Conclusions: NNU admission, for both term and preterm infants, is associated with poorer educational outcomes and an increased likelihood of special educational needs in mid-childhood.

Background Post-infection conditions (PICs), such as Long Covid, are associated with heterogeneous, fluctuating symptoms that profoundly affect daily functioning. Despite moderate-certainty evidence from the NIHR-funded LISTEN trial (COV-LT2-0009) that personalised self management support improves outcomes and may reduce societal and economic impacts of Long Covid, many people living with PICs still receive condition-specific services, generic advice, or stand-alone digital tools that do not address their complex needs. Aim To map care approaches in general practice and synthesise UK evidence for PIC management. Design and setting Scoping review and online survey. Method A two-phase study was conducted: (1) a scoping review of UK evidence on PIC management in general practice; and (2) a supplementary online survey of practitioners working in UK general practice to provide contextual insights. Results The scoping review identified 32 studies focused on Long Covid. One study included a comparator group (ME/CFS). Study populations were predominantly white ethnicity and female. Evidence for non-Covid PICs in UK general practice was largely absent. The supplementary survey (n=46) provided preliminary practice-level insights. Healthcare practitioners reported varied PIC presentations, diagnostic uncertainty, limited referral pathways, inequitable access, and low confidence in managing PICs. Conclusion Evidence informing PIC management in UK general practice remains predominantly Long Covid-focused and may not reflect the range of PICs encountered in practice. While survey findings are preliminary and require confirmation in larger samples, they highlight uncertainty around PIC management. Further research is needed to evaluate whether existing Long Covid pathways should be expanded or complemented by broader PIC models. Keywords general practice; Long Covid; self-management; post-viral syndromes

Objective: There is a bidirectional relationship between emotional distress and pain. However, this relationship is understudied in people with HIV in low-resource settings. This study sought to describe the temporal relationship between emotional distress and pain in people with HIV. Design: Longitudinal observational study. Methods: Participants with virally suppressed HIV, reporting either no pain or persistent pain at baseline, provided weekly remote ratings of distress, worst pain, and average pain using 0-10 visual analogue scales. Within-individual fluctuations in distress and pain were visualised over time. Group-level correlations were determined using Spearman's correlation tests. Cumulative link mixed models assessed whether distress and pain each predicted the other in the following week. Results: 72 participants provided responses over 49 weeks. The participants had a median (IQR) age of 43 (37-51) years, 63% (n=45) were unemployed and most were females (n=51;71%). Distress and pain fluctuated concurrently within individuals: distress was positively correlated with worst pain ({rho}=0.66, 95% CI= 0.60-0.72, p<0.001) and average pain ({rho}=0.70, 95% CI=0.64-0.75, p<0.001) intensity within the same week. Worst pain (OR=1.42, 95% CI=1.17-1.71, p<0.001) and average pain (OR=1.43, 95% CI=1.20-1.71, p<0.001) intensity both predicted distress in the next week. Distress predicted worst pain intensity (OR=1.25, 95% CI=1.07-1.46, p=0.023) but not average pain intensity (OR=1.19, 95% CI=1.01-1.40, p=0.152) in the next week. Conclusions: The temporal relationship between distress and worst pain intensity was bidirectional, whereas distress did not temporally predict average pain intensity. Both pain and emotional distress should receive attention from HIV research and clinical care in low-resource settings.