Expert Systems with Applications

Stroke remains a leading cause of mortality and long-term disability worldwide, yet rapid diagnosis is often limited by the shortage of trained radiologists, particularly in resource-constrained settings. Automated analysis of CT imaging offers a potential solution, but existing methods often struggle to achieve clinically generalisable performance while jointly addressing multiple diagnostic tasks. Here we present the Intelligent Integrated Stroke Diagnosis System IISDS, an end-to-end deep learning framework built upon StrokeGNN, a graph-based architecture that integrates 3D contextual feature extraction with U-Net-based 2D lesion segmentation to enable comprehensive stroke analysis from non-contrast CT scans. IISDS performs stroke subtype classification, lesion segmentation and lesion volume estimation within a unified pipeline. To develop and validate the system, we collected and curated BGD-ISD through a collaboration between AI researchers, neurologists, radiologists and clinicians, resulting in a large multi-centre dataset comprising 1,507 CT scans from 597 stroke cases acquired across six hospitals and medical centres in Bangladesh. Across BGD-ISD and multiple publicly available datasets, IISDS achieves state-of-the-art performance on all tasks, improving segmentation accuracy by [≥]0.011 Dice score, reducing lesion volume estimation error by [≥]0.3 average symmetric surface distance (ASSD), and increasing classification performance by [≥]0.018 area under the receiver operating characteristic curve (AUC) compared with existing approaches. These results demonstrate the potential of graph-based deep learning to enable clinically generalisable, automated and scalable stroke diagnosis from CT imaging, supporting rapid clinical decision-making, particularly in healthcare environments with limited access to expert radiological interpretation.

Improvements in data availability, sharing, and integration, together with the development of explainable artificial intelligence (XAI) techniques, are advancing precision medicine for pediatric cancer by facilitating diagnosis, biomarker discovery, and drug development. Data sharing commons and initiatives like the Childhood Cancer Data Initiative (CCDI) provide access to pediatric-specific genomic and clinical data cohorts and improve data availability for pediatric cancer research. Based on CCDI, a scalable AI platform, Graph Artificial Intelligence for Pediatric Oncology (GAIPO), integrates various data modalities from bulk and single-cell omics data to clinical information. Such multi-modal data facilitates the training and development of advanced XAI models for pediatric cancers. We then developed an end-to-end multi-modality framework, PCGS, for pediatric cancer by incorporating omics-specific representation learning via GNN models with cross-attention fusion and multi-objective learning for downstream tasks such as classification, clustering, and survival analysis. This framework outperforms previous supervised multi-omics integration baseline approaches based on glioma and Wilms tumor cohorts and enables GNN model explainability via Shapley value-based feature attribution approaches to explain the contributions of gene-level features across various biomedical tasks, including classification and survival. Given specific background samples (e.g., age groups, sex, grades) as baselines, this explainable GNN model estimates and ranks the importance scores for input features from each omics modality. It identifies background-specific key features for biomarker discovery, risk group identification, and survival analysis in glioma and Wilms tumor, with potential applicability to other pediatric cancers.

Background. Patient stratification from multi-omics and clinical data is essential for uncovering disease heterogeneity and moving toward more personalized treatment strategies. However, integrating heterogeneous data layers while identifying robust patient strata remains challenging. Methods. We introduce Reduced Fusion of Multi-Omics Stratification (RedFuMOS), a novel three-step approach for patient stratification based on mixed-type multi-omics data. RedFuMOS extends Similarity Network Fusion to accommodate mixed-type data layers and layer-specific similarity measures for data integration, includes a dimensionality reduction step to mitigate the curse of dimensionality, and performs patient stratification using density-based hierarchical clustering with HDBSCAN. It also implemented an automated optimization procedure to identify the best set of hyperparameters, minimizing the need for manual tuning. Results. RedFuMOS outperformed six state-of-the-art tools for multi-omics patient stratification in a comprehensive simulated benchmarking study, which also confirmed that, although computationally expensive, the dimensionality reduction step is crucial for achieving good stratification performance. Additionally, RedFuMOS identified two clinically relevant patient strata in a small real-world cohort of patients with Philadelphia chromosome-positive chronic myeloid leukaemia. Conclusion. RedFuMOS provides a flexible framework for integrating heterogeneous multi-omics and clinical data. RedFuMOS is available as an R package at http://github.com/delucasara/RedFuMOS.

Automated lesion segmentation is increasingly central to PSMA PET/CT interpretation, supporting staging, treatment planning, and response assessment at a scale that outpaces available nuclear-medicine expertise. However, automated PSMA-PET/CT whole-body lesion segmentation models are trained on images alone, with no knowledge of where in the body prostate metastases actually tend to occur. Radiologists use clinical domain knowledge of metastatic spread, but its absence in machine learning models produces false positives in anatomically implausible locations and missed lesions in high-risk sites such as the liver. In this work, we explore whether population-level spatial knowledge of metastatic spread can be used to augment deep learning segmentation predictions, and how such a prior should be fused with a network's output, without additional training. We build a data-driven metastasis atlas from 375 expert-annotated whole-body PSMA PET/CT scans and investigate its fusion with a trained segmentation network under a Bayesian framework, in which prediction probabilities from an nnU-Net-based lesion segmentation model serve as the likelihood and the data-driven atlas as the prior. Because metastases occupy only a small fraction of whole-body voxels, the atlas's peak probability is too low, and standard power-scaled or naive Bayesian pooling references lack the tools to deal with this shortcoming. This causes these standard fusion strategies to fail and, in the naive Bayesian case, to sharply degrade performance. We instead derive a calibrated, background-referenced log-odds fusion, one of many possible approaches to combine a population atlas with a deep learning model's predictions, distinct from classical multi-atlas label fusion in that it fuses a single population prior with a trained network's softmax rather than combining several registered atlases. Furthermore, this approach is neutral outside atlas support by construction, reduces exactly to the baseline network when unweighted, and requires no retraining. This atlas fusion significantly improved mean Dice over the baseline nnU-Net on a disjoint internal test set ($+0.011$, Holm-adjusted $p=0.021$) and on an independent external cohort ($+0.0129$, Holm-adjusted $p=3.8\times10^{-16}$), with lesion sensitivity improving from 0.849 to 0.861 internally and Dice improving over baseline in every stratified anatomic region, including the rare, high-risk sites motivating this work, while naive Bayesian pooling degrades performance sharply and power-scaled pooling underperforms it throughout. Our findings suggest that population-level spatial priors can meaningfully augment deep learning predictions in whole-body oncologic segmentation, provided the fusion rule is calibrated to where the prior actually carries signal.

Objective: To examine how medial plantar nerve shear wave speed (Cs) and viscosity coefficient (Vi) are associated with the severity of diabetic peripheral neuropathy (DPN), and to assess their ability to differentiate adjacent severity categories. Materials and Methods: Based on TCSS, the 113 patients with type 2 diabetes mellitus were assigned to the non-DPN (n = 33), mild DPN (n = 46), and moderate DPN (n = 34) groups. Medial plantar nerve Cs and Vi were measured using shear wave elastography and viscosity imaging. Receiver operating characteristic analysis evaluated Cs, Vi, and their logistic regression-based combination; areas under the curves (AUCs) were compared using DeLong tests. Results: Cs and Vi increased progressively across the three groups (both P < 0.001). For non-DPN versus mild DPN, the AUCs of Cs, Vi, and the combined model were 0.688 (95% CI, 0.604-0.772), 0.741 (0.660-0.822), and 0.745 (0.665-0.826), respectively, without significant pairwise differences. For mild versus moderate DPN, the corresponding AUCs were 0.707 (0.625-0.789), 0.794 (0.724-0.865), and 0.799 (0.731-0.867). The combined model outperformed Cs (P = 0.045), whereas Cs versus Vi and Vi versus the combined model did not differ significantly (P = 0.162 and 1.000, respectively). Conclusion: Medial plantar nerve Cs and Vi increased with DPN severity. Their combination improved discrimination between mild and moderate DPN compared with Cs alone but not with Vi alone. Quantitative medial plantar nerve viscoelastic assessment may complement clinical severity grading.

Objectives To validate two computational fluid dynamics (CFD) models derived from computed tomography angiography (CTA) for estimating trans-stenotic pressure gradients, using invasive intra-arterial pressure measurements as the reference standard in patients with renal artery stenosis (RAS). Background We assessed whether non-invasive assessment of the pressure gradient using CFD could be a reliable alternative to intra-arterial measurements for identifying hemodynamically significant RAS. Methods We performed intra-arterial measurements at rest and during dopamine-induced hyperemia to assess the trans-stenotic pressure gradient in 28 patients with RAS. A pre-intervention CTA scan was used to simulate the pressure gradient with a CFD model using a strategy based on Murray's law (CFD-Mu) and cortical volume (CFD-C). The agreement between the simulated and measured pressure gradients was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis and diagnostic agreement on the presence of a hemodynamically significant stenosis. Results In 20 patients, successful measurements and simulations were obtained. The ICC between measured pressure gradient and the CFD pressure gradient was 0.78 and 0.94 during baseline and 0.86 and 0.72 during hyperemia, for CFD-Mu and CFD-C, respectively. The sensitivity of CFD-Mu and CFD-C was 70% for both models at rest and 100% compared to the hyperemic measurements, whereas the specificity was 90% and 70% at rest and 79% and 72% during hyperemia, respectively. Conclusions The results support the use of individualized CFD simulations for hemodynamic assessment of RAS using CTA as input. The CFD models demonstrated high accuracy for the identification of a hemodynamically significant stenosis.

Polycystic Ovary Syndrome is a common endocrine disorder characterized by ovulatory dysfunction, hyperandrogenism, and/or polycystic ovarian morphology, with significant reproductive and metabolic consequences. Due to heterogeneous symptom profiles, Polycystic Ovary Syndrome is frequently underdiagnosed or diagnosed late. In this study, we develop machine learning models for early Polycystic Ovary Syndrome prediction using a structured clinical dataset with 42 features and 542 patient records. After data cleaning and normalization, correlation-based feature selection was applied to retain the most predictive variables. Multiple models were trained and evaluated, including Logistic Regression, Decision Tree, KNN, and Random Forest. Results demonstrate that Random Forest achieves the best overall performance (approximately 88% accuracy), suggesting that ensemble models can effectively capture non-linear feature interactions in clinical data. We also contextualize findings with international clinical guidance and recent work on explainable and clinically applicable Polycystic Ovary Syndrome prediction systems.

Introduction Continuous Glucose Monitoring (CGM) is considered standard care in high-income countries. There is, however, limited published evidence on CGM use in low- and middle-income countries. The purpose of this study was to assess the usability, acceptability, and feasibility of CGM use among people living with type 1 diabetes (T1D) and caregivers in a low-resource setting. Research Design and Methods This prospective study conducted at the Kenyatta National Hospital purposively enrolled persons aged 4-25 years who had been on management for T1D for at least six months, and caregivers of those under 18 years. Fourty youth living with T1D used CGM for three months in place of self monitoring of blood glucose (SMBG). The System Usability Scale (SUS), a Theoretical Framework of Acceptability-based questionnaire, the Diabetes Distress Scale (DDS), the Glucose Monitoring Satisfaction Survey (GMSS), and a feasibility survey were administered. Outcomes were summarized descriptively, including means, medians, and frequencies using R statistical software. Results The median SUS score was 98.8 (IQR 92.5-100.0). Acceptability was high, and the median total GMSS score improved from 3.73 to 4.73. Among adolescents and adults, the median overall DDS score reduced from 1.54 to 1.36, with reductions in scores in all domains, except for hypoglycemia distress which increased, and physician distress which remained low. Among caregivers, the median overall DDS score declined from 2.05 (moderate distress) to 1.90 (low distress), with modest reductions in teen management and parent-teen relationship distress and a slight increase in personal distress. Median CGM active wear time was 89%. Conclusion This study comprehensively evaluated CGM across usability, acceptability, and feasibility outcomes, with the findings supporting the integration of CGM into routine diabetes management in low-resource settings. The short follow-up period, however, may not capture changing perceptions or long-term adherence.

Ultrathin endoscopy is highly attractive for real-time tissue imaging in narrow and hard-to-reach regions of the body. A single multimode fibre (MMF) is an attractive probe because of its small diameter, flexibility, and diffraction-limited spatial resolution enabled by the large number of transverse modes guided within a single core. Because the distal fibre tip is inaccessible during endoscopy, reflection-mode imaging, in which the same fibre delivers illumination and collects backscattered light, is more practical than transmission-mode imaging. However, image recovery from the resulting speckle pattern is challenging because light undergoes double-pass propagation through the MMF, with mode coupling and dispersion; the backscattered signal is weak, and the camera records intensity only, without phase information. Here, we propose a single-shot reflection-mode MMF imaging framework that combines a reflected real-valued intensity transmission matrix (reflected-RVITM) with an image restoration network. The reflected-RVITM is calibrated using intensity-only measurements, without interferometry or phase retrieval, and provides a physics-guided initial reconstruction from a single backscattered speckle frame. A restoration network then refines this initial reconstruction instead of inverting the raw speckle. Four restoration backbones are evaluated: HPM-Attention-UNet, GAM, MambaIRv2, and CICPNet. On matched datasets, hybrid models outperformed corresponding networks trained to map raw speckle directly to images. For example, HPM-Attention-UNet on MNIST improved mean PCC from 0.572 to 0.944 (+65.1%). Under domain shift, with training only on Fashion-MNIST and tested on unseen CIFAR scenes, hybrid models achieved mean PCC of 0.61-0.65, compared with 0.36-0.50 for direct learning. This framework is further demonstrated using physical objects at the distal fibre tip. These results demonstrate that a reflected-RVITM physics prior combined with a restoration network enables single-shot image recovery after intensity-only calibration, offering a phase-retrieval-free and generalisable route towards minimally invasive reflection-mode MMF endoscopy.

Background: People affected by cancer often face difficulty finding relevant clinical, psychological, and practical support services. AI-powered navigation assistants may improve access to these resources, but their retrieval performance must be reliable. Objective: To develop a single-pass retrieval-augmented generation assistant for cancer-care navigation and compare the retrieval strategies, including their robustness to reworded questions. Methods: We created a database of 853 cancer-support resources reviewed by librarians, clinicians, researchers, and patient partners. We evaluated the system using 100 questions derived from questions submitted by patients. We compared keyword-based, semantic, and hybrid retrieval using Precision@K, Hit@K, and nDCG@K. The best-performing configuration was then tested using semantically equivalent rewordings of the original questions. Results: Keyword-based retrieval performed poorly, achieving a P@1 of 25.0% and Hit@5 of 43.0%. Semantic retrieval improved these results to 58.0% and 86.0%, respectively. The best hybrid configuration achieved a P@1 of 64.0%, Hit@5 of 90.0%, and nDCG@5 of 51.0%. Performance remained relatively stable when the questions were reworded, with a P@1 of 61.0%, Hit@5 of 88.0%, and nDCG@5 of 46.1%. Conclusions: Hybrid retrieval performed best and remained relatively stable when questions were reworded. However, its limited ability to rank a relevant resource first highlights the limitations of single-pass retrieval for patient-facing cancer navigation. Future work will explore metadata filtering and a multi-agent architecture to improve retrieval reliability.

Introduction: Continuous glucose monitoring (CGM) offers an advancement over traditional self-monitoring of blood glucose (SMBG) for people living with type 1 diabetes (T1D). However, evidence on the acceptability and feasibility of different CGM use cases in African populations remains limited. Methods: This was a pragmatic three-arm, randomised controlled trial on CGM conducted among people living with T1D in three public healthcare clinics in South Africa. Participants were assigned to Arm 1 (continuous CGM), Arm 2 (periodic CGM), or Arm 3 (SMBG). Diabetes education was provided at all study visits. Feasibility was assessed by adherence to CGM use and through the Glucose Monitoring Satisfaction Survey (GMSS). Diabetes distress was measured by the Diabetes Distress Scale (DDS), health-related quality of life (HRQoL) by the EQ-5D scales, and acceptability using the Theoretical Framework of Acceptability (TFA). Surveys were collected on paper and transferred to OpenClinica. Analyses were performed in R. The trial was registered in the Clinical Trials Registry (NCT05944718) on July 13, 2023. Results: A total of 83 participants were included in Arm 1, 85 in Arm 2, and 80 in Arm 3. CGM mean active time was 55% in Arm 1 versus 69% in Arm 2. The proportion of participants meeting the [&ge;]70% active time threshold was higher in Arm 2 (52%) than in Arm 1 (34%). Diabetes' distress declined across arms during the intervention period, with no significant difference between arms; distress increased slightly six months post-intervention but remained below baseline. At 6 months, glucose monitoring satisfaction was significantly higher in both CGM arms than in the SMBG arm, and satisfaction increased over time in CGM arms. Health-related quality of life remained stable across arms during the intervention period with no significant difference between arms. High acceptability was observed in both CGM arms, with higher ratings in the periodic arm. Conclusions: CGM was acceptable to people living with type 1 diabetes and feasible to use in public-sector clinics in South Africa, with high acceptability under continuous and periodic use. Health-related quality of life remained stable across arms, and diabetes-related distress declined, during the intervention period, across arms. Glucose monitoring satisfaction rose significantly in both CGM arms compared to SMBG. Periodic CGM might be a promising and potentially more scalable option than continuous use for public-sector care.

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. Accurate delineation of the gross tumour volume (GTV) - primary tumour (GTVp) and nodal disease (GTVn) - on FDG-PET/CT is a critical step of head and neck radiotherapy planning. Comparisons between lightweight custom networks and the auto-configured nnU-Net v2 are usually reported as end-to-end pipelines, conflating the contribution of the network with that of the inference-time post-processing applied on top of it. We separated the two. Methods. MiniUNet3D (custom 3D U-Net, 18.3 M parameters) and nnU-Net v2 (3d_fullres, 88.2 M parameters) were trained on the same 578 FDG-PET/CT cases (85/15 author-defined split of the HECKTOR 2025 Task 1 set, 8 centres) and evaluated on the same internal cohort. Three arms were compared pairwise: MiniUNet3D raw output at a fixed 0.5 threshold, MiniUNet3D with a locked adaptive post-processing pipeline, and nnU-Net v2. Comparisons used paired Wilcoxon tests with bootstrap confidence intervals, Bonferroni and Benjamini-Hochberg correction, and Cohen's d; catastrophic failure (Dice < 0.01) was compared with an exact McNemar test. Cases with an empty reference for a given target were excluded from that target's analysis (n = 98 GTVp, n = 93 GTVn). Results. With post-processing matched off, nnU-Net v2 was superior: median GTVp Dice 0.799 versus 0.592 (mean difference -0.244, 95 % CI -0.300 to -0.191; d = -0.88) and GTVn 0.774 versus 0.598 (d = -0.82). Post-processing raised MiniUNet3D to 0.800 (GTVp) and 0.738 (GTVn), recovering 79 % of that difference. Post-processed, MiniUNet3D matched nnU-Net v2 on GTVp Dice (p = 0.113) but remained inferior on nodal disease after Bonferroni correction (Dice p = 0.041; surface Dice p = 0.049). Catastrophic GTVp failures were 25/98 raw, 8/98 post-processed and 1/98 for nnU-Net v2 (McNemar p = 0.016). Inference took 34 s versus 78 s per case on the same GPU. Conclusions. Post-processing recovered most, but not all, of the difference between the two models, and it did not confer robustness: an eight-fold higher rate of empty contours on small primaries persisted, which is the more consequential difference for planning safety. Pipeline comparisons reported without a post-processing ablation risk attributing to a network what post-processing supplied.

The widespread adoption of clinical large language models (LLMs) introduces significant risks of automation bias, premature closure, and clinician deskilling. Current interpretability paradigms, including latent space trajectories, Concept Activation Vectors, and Concept Bottleneck Models, suffer from topological stagnation, metric distortion, and epistemic occlusion, frequently masking intermediate diagnostic uncertainty behind falsely confident outputs. To address these structural vulnerabilities, this paper introduces a novel closed-loop, multi-agent framework designed to quantify and visualize dynamic epistemic uncertainty in clinical LLM reasoning. By coupling predictive Shannon entropy with non-linear Isometric Feature Mapping (ISOMAP), the architecture projects high-dimensional inference state vectors onto a calibrated two-dimensional latent space, thereby assigning a quantifiable thermodynamic energy state to the reasoning path to track diagnostic velocity, cognitive momentum, and trajectory efficiency across sequential diagnostic rounds. Pilot validation across representative emergency medicine scenarios demonstrated distinct topological and information-theoretic behaviors: unconfounded cases (cerebellar infarction) exhibited smooth geodesic progression toward the ground truth alongside monotonic Shannon entropy decay from 2.15 to 1.74; noisy environments with ambiguous findings (spontaneous pneumothorax) suffered from trajectory wandering, local minimum traps, and high sustained entropy (~2.41) due to insufficient repulsive weighting for negative evidence; and triage-conflicted cases (acute cholangitis) achieved precise geometric proximity to the true node but experienced top-1 rank stagnation because the model conflated acute severity triage (sepsis) with anatomical etiology. By rendering machine hesitation and cognitive divergence visually auditable before final diagnostic crystallization, this geometric-information framework enables dynamic trust calibration and human-AI co-regulation at the point of care while establishing a clear mathematical foundation for future architectural interventions, such as dual-channel safety decoupling and non-linear repulsive weighting. Moving forward, validating these architectural enhancements across large-scale electronic health record databases and prospective clinical trials will be essential to realize its full clinical utility, establishing a foundational blueprint for safe, transparent, and cognitively synergistic AI integration in future medical practice. By rendering the LLM's reasoning process visually auditable, this framework lays the groundwork for capturing and externalizing the clinician's own cognitive patterns within the AI, forming a coupled system. This enables the explicit visualization of cognitive gaps between physician hypotheses and AI inferences, transforming the interaction from simple answer-checking into a dynamic learning process for both human and machine that prevents diagnostic oversight. Ultimately, because the responsibility for final clinical decision-making remains with the human practitioner, this framework serves as a vital decision-support mechanism. Moving forward, validating these architectural enhancements across large-scale electronic health record databases and prospective clinical trials will be essential to realize its full clinical utility, establishing a foundational blueprint for safe, transparent, and cognitively synergistic AI integration in future medical practice.

Artificial intelligence applied to routine electrocardiograms (ECGs) has largely focused on detecting existing disease or predicting individual cardiovascular outcomes. Whether ECGs can support prediction of multiple future diseases across organ systems remains unclear. We developed ECG-RISK, a multitask survival model for 67 incident three-character ICD-10 endpoints using ECG waveforms, demographic characteristics and routinely collected laboratory data from 86,673 MIMIC-IV patients. Discrimination was highest for heart, brain, kidney and lung endpoints, with organ-level C-indices ranging from 0.796 to 0.825, whereas liver and pancreatic endpoints showed lower discrimination. The ECG-only model achieved strong discrimination across most endpoints, whereas the incremental improvement gained by incorporating ECG and laboratory inputs beyond demographic information varied substantially across endpoints. Across the nine exploratory aggregated outcomes, Kaplan Meier curves showed clear separation among model-score tertiles. Discrimination was highest for dementia (C-index, 0.891) and heart failure (C-index, 0.857). These findings support the feasibility of ECG-based longitudinal risk prediction across multiple diseases. External validation and competing-risk analyses are required to assess generalisability and clinical utility.

Background: Consumer use of AI chatbots for health advice is rising, yet triage safety relative to established services remains unclear. Australia's Healthdirect, a government-backed symptom checker with 2.4 million uses in FY2024-25, remains unevaluated against frontier large language models (LLMs), and whether premium subscriptions improve triage safety remains unexplored. This study compared the triage accuracy and safety of Healthdirect against six LLM configurations across ChatGPT, Claude, and Gemini, assessed whether paid subscriptions improve triage safety, and characterised each system's error patterns. Methods: Forty-five clinical vignettes from the Semigran et al. benchmark spanning emergency, non-emergent, and self-care categories (15 each) were evaluated across seven systems. Healthdirect was tested following a seven-rule interaction protocol. LLMs were evaluated using first-person patient-language prompts under free-tier and paid-tier conditions. Outcomes were triage accuracy, emergency sensitivity, under-triage, and critical misses, analysed using Cochran's Q, Bonferroni-corrected McNemar tests, Cohen's kappa, and Wilson intervals. Findings: Triage accuracy differed significantly (Cochran's Q = 36.79, p < 0.001). Healthdirect achieved 48.9% accuracy (95% CI 35.0% to 63.0%; kappa = 0.233) versus 73.3% to 86.7% for LLMs (kappa = 0.600 to 0.800). Healthdirect operated under conservative interactive defaults while LLMs received complete information in a single prompt, which may have disadvantaged Healthdirect. Emergency sensitivity was 46.7% versus 80.0% to 86.7% for LLMs. Healthdirect produced two critical misses; no LLM produced any across 270 evaluations (95% CI 0% to 1.4%). When LLMs undertriaged, they recommended GP care rather than self-care. No tier differences were significant (all p > 0.05), and most systems over-triaged self-care cases. Interpretation: Frontier LLMs demonstrated higher triage accuracy and safer error profiles than Healthdirect. All LLMs avoided critical misses; Healthdirect did not. Premium subscriptions did not significantly improve triage safety. These findings support clinical governance decisions about whether LLMs warrant formal evaluation alongside government-backed symptom checkers.

Objectives To evaluate whether access to a certified large language model (LLM)-based clinical decision support system improves physician diagnostic performance in rheumatology compared with conventional diagnostic resources alone. Methods In this multicentre, open-label, randomised controlled trial, 82 physicians from seven hospitals in two countries were randomised 1:1 to conventional diagnostic resources plus Prof. Valmed or conventional resources alone. Participants assessed three rheumatology vignettes before and after assistance. The primary outcome was top-1 diagnostic accuracy. Secondary outcomes included top-3 accuracy, diagnostic reasoning, confidence, case-processing time and perceived support quality. Results Top-1 accuracy increased from 22.2% to 33.3% in the intervention group and from 23.3% to 35.0% in the control group, with no between-group difference in improvement (adjusted OR 0.99, 95% CI 0.45 to 2.19; p=0.979). Differences in top-3 accuracy, diagnostic reasoning and confidence were also not significant. Assisted case-processing time was substantially shorter with LLM support (94 vs 206 s; adjusted mean difference -112 s, 95% CI -141 to -83; p<0.001). Information timeliness and perceived diagnostic support quality were rated significantly higher in the intervention group. Exploratory analyses showed persistent overconfidence and substantial AI over-reliance. Conclusions Certified LLM-based diagnostic support did not improve diagnostic accuracy compared with conventional resources, but substantially reduced case-processing time and improved perceived support quality. These findings suggest potential workflow benefits while highlighting overconfidence and over-reliance as important safety considerations.

Human immunodeficiency virus (HIV) and hepatitis B virus (HBV) coinfection is associated with accelerated liver disease, but whether coinfection is associated with newly documented social determinants of health (SDoH) is unclear. We conducted a retrospective cohort study using TriNetX across 110 U.S. healthcare organizations (2010-2026). We propensity score matched adults with HIV/HBV to adults with HIV or HBV monoinfection. We organized newly documented SDoH indicators using a dynamic individual-level framework with four clinically recognized domains of social disadvantage: material vulnerability, healthcare access and engagement, interpersonal adversity, and psychosocial vulnerability. Matched cohorts included 10,071 HIV/HBV-HIV pairs and 9,659 HIV/HBV-HBV pairs (mean age, 47 years; 79% male; 66% non-White; median follow-up, 3.3 years). Over 178,900 person-years, HIV/HBV was associated with higher risk of the primary SDoH composite compared with HIV (11.5% vs 9.7%; incidence rate, 2.50 vs 1.97 per 100 person-years; hazard ratio [HR], 1.25; 95% confidence interval [CI], 1.15-1.37) and HBV (11.0% vs 6.4%; incidence rate, 2.39 vs 1.67; HR, 1.50; 95% CI, 1.35-1.67). HIV/HBV was also associated with higher material vulnerability and healthcare access and engagement composites in both comparisons, including housing instability, food insecurity, financial insecurity, insurance instability, and care disengagement/nonadherence (HR range, 1.22-3.33 vs HIV; 1.31-1.94 vs HBV). In the HBV comparison, HIV/HBV was additionally associated with interpersonal adversity, primary support stressors, and violence or victimization (HR range, 1.36-2.16). Findings were robust across sensitivity analyses. HIV/HBV was associated with more newly documented SDoH than monoinfection, supporting dynamic SDoH assessment.

Background: Sickle cell anaemia (SCA) is characterised by chronic haemolysis, inflammation, platelet activation, and recurrent vaso-occlusive complications. Mean platelet volume (MPV) is a readily available platelet index, but evidence regarding its relationship with disease severity in paediatric SCA remains limited and inconsistent, particularly in African populations. Objective: To evaluate the relationship between MPV and disease severity among children with SCA in Kwara State, North-Central Nigeria. Methods: This hospital-based cross-sectional study included 51 clinically stable children with confirmed SCA consecutively recruited from the paediatric haematology clinic of Children Emergency Specialist Hospital, Ilorin. Complete blood count, including MPV, was performed using a Rayto RT-7600 automated haematology analyser. Disease severity was assessed using a composite clinical and laboratory scoring system based on a previously described method. Pearson's correlation, Spearman's rank correlation, simple linear regression, and the Kruskal-Wallis test were used as appropriate. Statistical significance was set at p < 0.05. Results: Of 51 participants, 14 (27.5%) had mild, 33 (64.7%) moderate, and 4 (7.8%) severe disease. Mean MPV was 9.34 +/- 0.76 fL (range, 8.0-11.2). Pearson's correlation showed a weak positive, non-significant linear relationship with severity score (r = 0.231, p = 0.103), whereas Spearman's analysis showed a weak positive monotonic association (rho = 0.286, p = 0.042). Regression explained 5.3% of severity-score variation (R2 = 0.053, p = 0.103). MPV did not differ significantly across severity categories (H = 2.163, p = 0.339). MPV correlated inversely with haemoglobin (r = -0.556, p < 0.001) and positively with platelet count (r = 0.307, p = 0.029). Conclusion: MPV showed a weak relationship with disease severity but inconsistent statistical evidence across analyses. The limited explained variance and absence of significant differences between severity categories do not support MPV as a standalone severity marker. Larger longitudinal studies are warranted. Keywords: Sickle cell anaemia; Mean platelet volume; Disease severity; Platelet indices; Paediatric haematology; Cross-sectional study; Nigeria.

Muscle architecture shapes muscle function and changes with age, growth, training and disease, yet quantifying three-dimensional (3D) muscle architecture in vivo remains challenging. We introduce a hybrid fascicle tractography approach for freehand 3D ultrasound data that accurately reconstructs 3D muscle fascicles with respect to an objective, anatomically relevant coordinate system defined by the muscle's central aponeurosis. The hybrid approach combines Hessian-based fascicle detection with wavelet-based refinement to generate volumetric fascicle orientations. In a synthetic dataset with known ground truth, fascicle orientations and lengths were estimated with errors of [&le;]2{degrees} and ~1.5%, respectively. In vivo, the approach detected physiologically plausible fascicle lengthening in the human tibialis anterior following a passive plantar flexion rotation, whereas diffusion tensor imaging of the same muscle did not. The proposed method enables anatomically relevant, objective and non-invasive quantification of 3D muscle architecture in vivo, providing a practical framework for applications in clinical and applied muscle physiology.