Computers in Biology and Medicine

The increasing availability of portable ultrasound systems motivates exploration of novel approaches to respiratory signal assessment. In this in-vitro study, we investigate whether pulsed-wave (PW) Doppler ultrasound can capture structured spectral patterns from replayed lung sound recordings. Digitized respiratory sounds were replayed through a tissue-mimicking ultrasound phantom, generating 1,478 PW Doppler spectral images from recordings associated with healthy subjects and several externally labeled disease categories. Exploratory classification experiments using a ResNet-18 architecture demonstrated that these Doppler representations contain learnable differences under controlled conditions. These findings motivate further investigation into PW Doppler as a potential representation of respiratory acoustics.

Skin cancer requires early detection for improved survival rates. Most existing methods rely on deep learning based image classification, which is affected by visual similarity among lesions. Fewer studies use Gene Expression (GE) analysis, which captures molecular characteristics but lacks structural and visual details. To overcome limitations of individual modalities, this paper proposes a multimodal framework integrating dermoscopic images and GE profiles for skin cancer classification. EfficientNet and logistic regression are used for image based analysis and genomic skin lesion profiling, respectively, followed by fuzzy rule based decision systems to reduce uncertainty within individual modalities. Finally, fuzzy fusion combines predictions from both modalities using uncertainty based weighting of classifier outputs. The experimental findings show that both the image based and GE based classification models individually achieved accuracies of nearly 92%. However, the integration of prediction results through the proposed fuzzy fusion strategy further enhanced the classification performance, achieving an overall accuracy of 94.25%. The results obtained outperform contemporary methods, highlighting the effectiveness of combining complementary multimodal information compared with single modality approaches.

**Abstract** **Background:** Transcatheter edge-to-edge repair (TEER) is an established treatment for mitral regurgitation but remains highly dependent on operator experience and complex transesophageal echocardiography (TEE)-guided intraprocedural imaging. Artificial intelligence (AI)-based semantic segmentation may improve procedural reproducibility and intraprocedural guidance; however, no TEER-specific segmentation framework has been reported. **Objectives:** To develop and evaluate AutoClip, a clinician-driven AI-guided TEE semantic segmentation model designed for simultaneous delineation of mitral valve anatomy and in-vivo TEER device components. **Methods:** A retrospective proof-of-concept study was conducted using 987 intraprocedural TEE frames derived from 10 video clips in 3 patients undergoing MitraClip G4 implantation. Seven semantic labels, including mitral leaflets and device components, were manually annotated using ITK-SNAP. Following standardized preprocessing and region-of-interest extraction, an Attention U-Net architecture was trained frame-wise on bicommissural and corresponding X-plane TEE views. Model performance was assessed using mean intersection-over-union (IoU) and Dice coefficient on an independent test set. **Results:** The Attention U-Net demonstrated improved sensitivity to small device structures compared with conventional U-Net architectures. Preliminary training performance achieved a mean IoU of approximately 0.93, while independent test performance reached a mean IoU of 0.46 across foreground classes. Qualitative assessment demonstrated feasible simultaneous segmentation of mitral leaflets, clip arms, grippers, and delivery shaft during TEER procedures. **Conclusions:** AutoClip represents a proof-of-concept TEER-specific TEE semantic segmentation framework initiated through a clinician-oriented workflow without formal computer science expertise. Although preliminary accuracy remains modest due to limited sample size, this study establishes a reproducible pathway for future AI-assisted intraprocedural guidance systems and larger multicenter development efforts in structural heart interventions.

Background. Capillary refill time, an examiner-dependent bedside test of distal microvascular perfusion, has become a resuscitation target in septic shock,1,2,3,4 motivating a continuous surrogate computed from the photoplethysmogram (PPG, the optical waveform the pulse oximeter on every ICU patient already records).5,6,7,8 Objective. We attempted three PPG-derived candidate measures on the MIMIC-IV Waveform Database (MIMIC-IV-WDB v0.1.0) and asked, by inspecting randomly drawn examples, whether each captured its intended physiology before any downstream modeling. Methods. MIMIC-IV-WDB v0.1.09 was linked to MIMIC-IV.10 The signals were a cuff-anchored perfusion-index recovery (reactive hyperemia when the cuff shares an arm with the probe), a slow Mayer-wave-band power ratio of the perfusion index (sympathetic vasomotor tone), and a per-beat diastolic exponential decay time constant (a refill-like recovery time). For each signal we drew 10 random examples at a fixed seed and checked them against a checklist fixed in advance. Each was read by the author and, separately, by MedGemma 1.5, a multimodal medical language model run locally. A synthetic test with a known time constant checked the third signal. Results. The cuff-anchored signal showed the expected occlusion-reperfusion shape on 268 of 6,236 evaluable cuff cycles (4.30%) in 15 of 19 patients, consistent with opposite-limb placement of the probe and cuff. The slow-band ratio returned a stable cohort value, but a clear, stationary peak appeared in only4 of 10 random windows. The per-beat fit met its goodness-of-fit threshold in 10 of 10 beats, yet a cardiac-frequency heuristic flagged a possible fit on the heart-rate oscillation in 7 of 10, and in 5 of 17 patients the time constant lay where an exponential is indistinguishable from a straight line. A 0.5Hz high-pass pre-filter implanted its own approximately 318 ms time constant regardless of truth. The language model tracked the human on clear positives but reported the pattern present on every call it returned, never absent. Conclusions. Two of the three candidate signals did not reflect their intended physiology in most examples, and the third was constrained by sensor placement. Inspecting a few random raw inputs against a checklist written in advance is an inexpensive upstream check before downstream inference on PPG-derived microvascular signals.

Objective: Several endotypes contribute to the development of Obstructive Sleep Apnea (OSA). However, efforts to measure these endotypes have been challenging. In this paper, we propose a new method that overcomes some of these challenges. Methods: To test the feasibility of this new method, data from the Sleep Heart Health Study (SHHS) were analyzed and two oxygen-based endotypes were identified and plotted on a graphical model: the steady-state SpO2 and the SpO2 arousal threshold. The first is the oxygen saturation that would occur during sleep if there were no arousals, and it is a measure of upper airway collapsibility (a more collapsible airway produces a lower SpO2). The latter is the oxygen saturation that triggers arousals. These endotypes were validated by assessing their ability to detect positional and state-related changes in airway collapsibility and arousal threshold. Results: The study showed that it was feasible to measure oxygen-based endotypes in 95% of SHHS participants. As expected, steady-state SpO2 was lower during supine vs. non-supine sleep, as well as during REM vs. NREM sleep. Also, the SpO2 arousal threshold was similar between supine and non-supine sleep. However, SpO2 arousal threshold was not lower in REM sleep vs. NREM sleep. Therefore, in 3 of the 4 conditions, the oxygen-based endotypes moved in the expected direction due to positional or sleep state changes. Conclusion: Although further validation experiments are required, this study indicates that OSA endotyping using the pulse oximetry signal is feasible. The oxygen-based endotypes could be used to aid therapeutic decision making.

AIMS Cardiometabolic risk factors may impair health by altering the autonomic modulation of the cardiovascular system, a physiological process described by heart rate (HR) circadian oscillations. However, the impact of cardiometabolic health determinants on HR circadian oscillations remains scarcely characterized in real-world, population-based settings. To address this, we applied digital health technologies to investigate how cardiometabolic health determinants shape HR circadian oscillations in a real-world cohort of individuals free of cardiometabolic diseases. METHODS First, a 10-fold cross-validation of a model was performed, aiming at mitigating wearables measurement error caused by motion artifacts. This process was informed by 10,056 epochs of concurrent wearable-derived and polysomnographic HR assessment, yielding an average 1.3 bpm reduction in wearables measurement error. We subsequently applied this model to over 2 million 1-minute epochs of HR data, derived from 7-day continuous actigraphic recordings of 245 individuals free of cardiometabolic disorders. Functional-on-scalar regression modelling and both parametric and nonparametric analyses characterized HR circadian profiles and their relationships with demographics, lifestyle, chronotype, sleep health, and chronic insomnia diagnosis. A 6-dimension sleep health index was calculated. RESULTS Sex, chronotype, and sleep health predominantly shaped HR circadian oscillations. In detail, females consistently showed higher HR across the 24 hours. Moreover, chronotype was associated to a phase shift in HR circadian profiles, with later timings corresponding to eveningness. Notably, sleep health impacted HR circadian oscillations in a dose-dependent fashion: each additional impaired sleep dimension was associated with a 1.2 bpm HR increase during nighttime, alongside reduced circadian robustness and delayed oscillation timings. Finally, the earlier occurrence of morning HR peaks served as a digital biomarker of insomnia (80% specificity, 74% sensitivity). CONCLUSIONS This work provides a digital health framework to characterize HR circadian oscillations in free-living populations and supports its clinical utility in capturing the autonomic disruptions related to cardiometabolic health determinants.

The objective assessment of patients with disorders of consciousness (DOC) remains a significant clinical challenge. Behavioral scales like the Coma Recovery Scale-Revised (CRS-R) are susceptible to rater subjectivity and have difficulty in detecting patients with cognitive-motor dissociation (CMD), while existing electrophysiological paradigms typically evaluate isolated processing levels, especially in visual functions. To address these limitations, we developed a novel, hierarchical visual EEG framework that evaluates three progressive tiers of visual processing--sensory input, selective attention, and object discrimination--within a single, unified paradigm. This framework uses steady-state and event-related potentials, analyzed with statistical testing and machine learning, to provide objective detection. In a cohort of 85 participants, the framework demonstrated a robust alignment with behavioral CRS-R levels and successfully identified CMD patients missed by bedside behavioral examinations. Notably, model predictions derived from this framework showed a significant correlation with 3-month clinical outcomes. This prognostic utility generalized effectively and remained consistent across distinct EEG acquisition systems in an independent validation cohort of 17 patients. In summary, this work offers electrophysiological validation for the hierarchical design of the CRS-R and provides a practical tool for bedside objective assessment of DOC.

Background: Aortic stenosis (AS) is a progressive valvular disease associated with poor prognosis once symptoms develop, yet routine echocardiographic screening is impractical. While artificial intelligence (AI)-based electrocardiogram (ECG) models have shown promise for AS detection, it remains unclear whether they primarily reflect conventional left ventricular hypertrophy (LVH) voltage criteria or capture additional ECG features. Methods and Results: We developed a deep learning model using 244,816 ECGs from 51,713 patients across six academic institutions in Japan (CLIDAS database). AS labels were derived from inpatient Diagnosis Procedure Combination (DPC) codes. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.849 (95% confidence interval 0.832-0.865) in the independent test cohort, with consistent performance across institutions, sex, and age. At a threshold of 0.1, sensitivity was 79.1%, specificity was 73.9%, and negative predictive value (NPV) was 98.0%. Conventional LVH voltage criteria (Sokolow-Lyon AUC 0.706; Cornell AUC 0.692) showed lower performance, and adding them to the AI model conferred no incremental benefit (AUC 0.849 vs. 0.847). Gradient-weighted class activation mapping (Grad-CAM) revealed predominant attention around QRS complexes in limb leads, beyond regions typically assessed in LVH evaluation. Conclusions: This multicenter AI-ECG model demonstrated strong discrimination for AS and captured ECG features beyond conventional LVH voltage criteria. The high NPV supports its use as a rule-out pre-screening tool.

Background. Lung metastases in osteosarcoma (OS) are the main cause of the death. The accuracy of the diagnosis of nodules by computed tomography (CT) of the lungs is critically important for determining the disseminated stage of the disease and planning surgical treatment. The use of artificial intelligence (AI) in the search for lung nodules increases the accuracy of diagnosis and reduces the chance of missing metastases. Objective: to evaluate the accuracy of lung nodules diagnosis in adolescents with OS using AI. Methods. A retrospective assessment of CT scans of adolescents with OS was performed. A pathological nodule with an average size of [≥]4 mm was considered a target finding. The diagnostic accuracy of an AI algorithm previously trained on an adult dataset was evaluated, and the number of false positives (FP) and false negatives (FN) was determined. Sensitivity, specificity, accuracy, area under the ROC curve (AUC), positive predictive value, negative predictive value, and F1-measure were calculated. Based on the obtained results, the effectiveness of the algorithm was assessed. Results. 248 CT scans of adolescents with OS were evaluated. The following results were obtained: in 5 cases, the AI algorithm showed a FP result (2.02%), in 34 cases, it showed a FN result (13.71%), and in 209 cases, a correct result (both true positive and true negative) (84.27%). The diagnostic accuracy of the algorithm was 0.843 (95% CI 0.794-0.887). The application of the AI algorithm in the practice of an X-ray doctor in a specific clinical task would allow to increase the sensitivity from 0.805 to 0.891, while ensuring an absolute decrease in the number of FN results by 8.59% and a relative decrease by 44%. Conclusion. The obtained results confirm the practical value of the application of the AI algorithm and justify the implementation of AI-assisted systems in the diagnostic protocols for lung metastases in adolescents with OS.

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.

Objective: Tumor-infiltrating lymphocytes (TILs) in breast cancer are one of the most important indicators of the immune response within the tumor microenvironment. They play a particularly significant prognostic and predictive role in triple-negative and HER2-positive subtypes. However, substantial inter-observer variability has been reported in TIL scoring among pathologists, which limits its reliability in clinical practice. The aim of this study was to evaluate the agreement between artificial intelligence (AI) models and pathologists in TIL scoring and to compare this agreement using different statistical approaches, thereby assessing the potential of AI integration into pathology practice. Materials and Methods: Digitized histopathological images of breast cancer cases were included in the study. Tumor regions annotated by pathologists were evaluated for both stromal TIL percentage and the proportion of stromal tumor area within each ROI, with assessments performed independently by three pathologists and two AI models. Agreement was assessed among pathologists, between pathologists and AI, and between AI models. Statistical analyses included intraclass correlation coefficient (ICC), Cohen and Fleiss kappa, correlation tests, and Bland-Altman analysis. In addition, categorical agreement was examined using different cut-off values. Results: Inter-pathologist agreement was high, with an ICC of 0.81. In contrast, the global agreement between pathologists and AI models was lower (ICC 0.41). Pairwise comparisons of pathologist-AI agreement yielded substantially lower ICC values (0.12-0.21), although this improved to 0.53 when three pathologists were assessed jointly with a single AI model. The strongest categorical agreement was observed with dichotomized TIL scores ([≤]10% vs. >10%), whereas multi-category classifications were associated with a marked reduction in kappa values. Spearman correlation coefficients between pathologists and AI models ranged from moderate to good ({rho} = 0.48-0.81). Agreement between the two AI models themselves was moderate, with an ICC of 0.64

Background. Fairness-aware machine learning increasingly targets demographic performance disparities in clinical prediction, yet whether standard bias mitigation strategies genuinely improve equity in physiological signal analysis remains unclear. Age-based disparities in photoplethysmography (PPG)-based heart rate prediction present a particular challenge, as age-related performance differences may reflect context-dependent physiological structure rather than correctable artifacts. Methods. We evaluated three fairness interventions, inverse-frequency weighting (IF), Group Distributionally Robust Optimization (GroupDRO), and adversarial debiasing (ADV), applied via fine-tuning of a PPG foundation model across three clinical datasets spanning intensive care unit, laboratory, and consumer wearable contexts. Outcomes were assessed using a 2x2 framework classifying each intervention-dataset combination by the joint direction of change in mean absolute error (MAE) and fairness gap (FG) across age groups, yielding four outcome types: genuine improvement (G), leveling down (L), selective benefit (S), and both worse (W). Results. Across nine intra-domain conditions, no intervention simultaneously improved both MAE and FG (0/9 genuine improvement). The dominant pattern was leveling down (5/9): FG decreased but was accompanied by MAE degradation, indicating that apparent fairness gains were achieved at the cost of overall predictive performance. Age-group difficulty ordering varied across clinical contexts at baseline and was not preserved under intervention. In 18 cross-domain transfer conditions, genuine improvement was rare (4/18) and observed exclusively in non-MIMIC source configurations; models fine-tuned on MIMIC-sourced data yielded no genuine improvements (0/6). Embedding-level representation changes following fine-tuning did not reliably predict fairness outcomes. Conclusions. Age-based fairness interventions in PPG heart rate prediction indicate a leveling-down pattern rather than genuine equity improvement, suggesting that age-related performance gaps reflect context-dependent physiological structure not fully addressable through standard bias mitigation. Cross-domain transfer further amplifies this instability. These findings suggest that fairness evaluation frameworks for age-stratified physiological prediction should account for context-dependent performance structure rather than treating observed gaps as correctable bias.

High-frequency physiological monitoring in ICUs can identify impending deterioration hours before clinical recognition yet extracting reliable early-warning signals from noisy vital-sign streams remains challenging. We present SIgnose, an interpretable prediction framework for early detection of abnormal shock index (SI), built from routinely monitored vital signs using physiologic variability and nonlinear time-series features. SIgnose was developed on the eICU Collaborative Research Database and externally validated on the MIMIC-III adult database and a pediatric SafeICU cohort (AIIMS New Delhi), with additional prospective validation in the pediatric ICU. We benchmarked three representation strategies: (i) engineered physiologic variability and nonlinear time-series features, (ii) deep learning, and (iii) Llama-3.1-8B embeddings with low-rank adaptation. Physiologic variability features consistently demonstrated superior cross-cohort generalization. The final model used 3,970 features from five vital signs to predict abnormal SI up to 8 hours ahead, achieving AUROC 0.861 (95% CI 0.859-0.863) and AUPRC 0.927 (95% CI 0.925-0.929) on eICU. External validation yielded AUROC 0.870 (95% CI 0.863-0.876) and AUPRC 0.935 (95% CI 0.930-0.940) on MIMIC-III, and AUROC 0.875 (95% CI 0.863-0.888) and AUPRC 0.915 (95% CI 0.898-0.930) on SafeICU; prospective pediatric validation (n = 88) achieved AUROC 0.885 (95% CI 0.868-0.902) and AUPRC 0.911 (95% CI 0.882-0.936). SHAP interpretability analysis identified heart rate variability, respiratory trend dynamics, and multi-scale blood pressure variability as key early-warning signatures. These findings establish SIgnose as a reproducible, low-compute, early-warning framework and demonstrate that physiologic variability features provide robust, generalizable representations for early deterioration detection across adult and pediatric critical care.

Background: Sleep fragmentation and reduced sleep efficiency are markers of disrupted sleep architecture linked to cognitive and age-related decline. Current assessments rely on subjective reports prone to recall bias, limiting their effectiveness for longitudinal monitoring. Data-driven analysis of sleep using physiological signals such as EEG and EMG remains underutilised, particularly in mid-to-older adults. Objective: We present a deep learning pipeline for automated sleep staging and label-free abnormality scoring, with the primary objective of quantifying deviations in sleep architecture to capture progressive sleep disruption and longitudinal change. Methods: Temporal and attention-based models were benchmarked using datasets from the National Sleep Research Resource and PhysioBank. To improve class-specific performance, we introduce a stacking-based ensemble of sleep stage classifiers, each trained to specialise in a different stage. For longitudinal scoring, we develop a reconstruction loss-based abnormality metric using a temporal convolutional autoencoder trained on hypnograms generated by the sleep staging models. Results: Attention-based models, particularly AttnSleep, achieved the highest performance in both multimodal and single-channel settings (accuracy: 0.85 and 0.83; F1: 0.79 and 0.74, respectively). The encoder-decoder ensemble model improved overall classification accuracy by 3% compared to the best-performing biased base classifier, with a modest gain in N1-stage F1 score (0.444). The proposed abnormality score correlated with Pittsburgh Sleep Quality Index components and showed sensitivity to synthetic hypnogram degradation, highlighting its potential as a label-free indicator of sleep disruption. Conclusion: Automated classification and annotation-free scoring enable an end-to-end multimodal pipeline that supports scalable, objective sleep health monitoring, with relevance for future clinical deployment.

Background Pulse-field ablation (PFA) is regarded as a non-thermal ablation modality, but there is an increasing range of complications that could be due to thermal effects. Methods The hydrogel undergoes permanent colour change when a target temperature is reached allowing direct visualisation of the surface thermal footprint and depth. Comparative lesion sets using a variable loop circular catheter (VP), circular over-the-wire catheter (PS) and pentaspline catheter (FP) were performed. Protocols included single and stacked applications with variation of force, irrigation, and voltage. The hydrogel lesions were analysed en-face and by section using digital image analysis. Results All 3 PFA catheters tested had significant thermal footprints. The VP catheter had the largest mean surface footprint (156.1mm2) and thermal depth (1.31mm) compared to the other two catheters (PS 55.4mm2 & 1.1mm, FP 29.8mm2 & 1.05mm, p<0.005). Increasing irrigation showed a trend to reduce thermal footprint but did not achieve statistical significance. Increasing voltage increased thermal footprint, but increasing force had negligible effect. Stacked lesions incrementally increased thermal lesion footprint and depth in all catheters. Thermal depths of up to 2.4mm were observed. Areas of darkening and degradation of the hydrogel were observed with the VP and FP catheters, consisting of up to 47% of lesion area. No darkening was observed with the PS catheter. Conclusions There are significant thermal footprints in all the systems tested. Temperatures exceeding 60oC have been demonstrated, comparable to radiofrequency ablation, and this may explain the mechanism of injury in some reports of collateral damage during PFA.

Background: Digital decision-support tools such as triage systems and symptom checkers support millions of health-related decisions each year. Their quality and safety are commonly evaluated using textual patient cases, known as case vignettes. However, existing vignette sets written by medical experts cover only a limited spectrum of real-world patient presentations and lack population weights, which would allow extrapolating evaluation results to the underlying patient population. Objective: This study aims to develop a data-driven framework for automatically generating a human-manageable set of case vignettes from nationwide triage data that captures broad presentation diversity and links each vignette to a quantitative weight reflecting the number of underlying patient assessments. Methods: From 3.2 million triage assessments conducted over one year using structured triage software in the German medical on-call service (telephone triage and online self-triage) and at the joint contact points of the outpatient emergency care service and hospital emergency departments, we randomly sampled 50,000 cases. Triage questionnaires were converted into semantic embeddings using a German Sentence Transformer Model and grouped by agglomerative clustering. For clusters containing sufficient assessments, we generated one representative assessment using a two-phase simulated-annealing optimization. The optimization minimized the distance to the cluster centroid while maximizing the number of answered triage questions, aiming for high representativeness and information content. Each representative assessment was assigned the size of its source cluster as its sample-based weight. A similarity-based sensitivity analysis was performed to examine whether these weights were preserved in the full 1-year population. Finally, the question-answer pairs of the representative assessments were converted into structured textual case vignettes using controlled prompting of a large language model. Results: The cluster analysis yielded 514 included clusters covering 96.8% of the sampled 50,000 assessments. The generated representatives showed strong agreement with the majority treatment-urgency recommendation of their source cluster (Spearman's {rho}=0.78, p<0.001) and contained on average 4.3 more answered triage questions than the original assessments within their clusters. When weighted by cluster size, the representatives approximated the sample distributions of treatment urgency, demographics, and symptoms, although some systematic deviations remained, most notably an overrepresentation of female cases (+13.5%), patients aged 14-49 years (+8.0%), and the urgency category "As soon as possible" (+6.6%). Of 121 recorded symptoms, 101 (83.5%) were covered by the representatives; the rest each occurred in <0.5% of the sample. In a sensitivity analysis, cluster-based vignette weights were strongly correlated with similarity-based population weights (Spearman's {rho}=0.77, p<0.001), and 90.1% of assessments in the full 1-year population were matched to at least one vignette. Conclusions: We present a data-driven framework for deriving a manageable set of population-weighted case vignettes from nationwide triage data. The resulting vignettes captured broad presentation diversity, approximated key sample characteristics, and provided an explicit quantitative link to the number of underlying patient assessments. After medical expert review and refinement, the vignettes may support more population-aware evaluation and quality assurance of digital decision-support tools.

Machine learning (ML) has emerged as a transformative technology across biomedical and life science sectors, with applications spanning drug discovery, medical imaging, genomics, and clinical decision support (Goecks et al., 2020; Patel et al., 2020). Despite exponential growth in ML-related publications, from fewer than 100 articles in 2003 to nearly 25,000 by 2021 (NCBI, 2022), adoption among industry professionals remains uneven and sector-dependent. Understanding what drives or inhibits this adoption is critical for organisations seeking to leverage ML capabilities in research and clinical practice. Technology adoption in organisational contexts has been extensively studied through the Technology Acceptance Model (TAM), originally proposed by Davis (1989) and subsequently extended to incorporate external variables influencing perceived usefulness (PU) and perceived ease of use (PEU) (Venkatesh & Davis, 1996). While TAM has been applied across multiple industries, its application within biomedical and life science contexts remains limited, and the industry-specific factors that shape ML acceptance in this sector have not been systematically examined. Two external variables are particularly relevant to life science professionals. First, the bibliometric journal impact factor (JIF) functions as a cognitive signal of scientific credibility, a sector where evidence-based decision-making is culturally embedded, and publication quality serves as a proxy for technological legitimacy (Garfield, 1996). Second, technology hype, operationalised through the Gartner Hype Cycle framework, represents a social influence variable that shapes organisational expectations and investment decisions around emerging technologies (Gartner Inc., 2018). Whether these variables influence ML acceptance among life science professionals, alongside individual knowledge and experience, has not been empirically tested. This study addresses that gap by investigating ML technology acceptance among 213 biomedical and life science professionals across EMEA, LATAM, and North America, using a cross-sectional quantitative survey and PLS-SEM analysis. The TAM model is extended with three external variables, JIF, technology hype, and prior knowledge and experience, to test their influence on PU and PEU in this specific professional context. Additionally, the study examines demographic and regional differences in ML acceptance, with particular attention to variation between academic researchers and healthcare professionals. The findings contribute a validated, sector-specific extension of TAM for life sciences, provide actionable insights for organisations seeking to accelerate ML implementation, and establish a framework for future subsector-specific research.

In spite of well-established global immune landscape, SARS-CoV-2 is still able to further spread and continue causing infection waves. The current understanding about the reason behind is limited, and it is still difficult to predict the evolution or spreading tread of SARS-CoV-2. Therefore, it is necessary to investigate whether the establishment of population immunity has changed the virus evolution or spreading pattern. In this investigation, one overall analysis of the SARS-CoV-2 spreading in the past several years have been carried out through one thorough genomic epidemiology study, with Germany being chosen as one representative location in view of the systemic efforts for genomic surveillance. The growth advantage of a few predominant variants in its early spreading period has been evaluated through a logistic regression model. The results have revealed that the major circulating SARS-CoV-2 variants since 2023 are mainly derived from the Omicron BA.2 family. Since middle of 2024, most predominant variants were produced primarily through recombination, indicating that the evolution derived from recombination might be the major driving force for the continuous spread of SARS-CoV-2 despite the existence of population immunity. Furthermore, the lower growth advantage of recently emerged variants might possibly lead to a tread of reduction in the frequency of infection wave. The information revealed from this investigation suggests that although short-term spreading tread can be affected by specific virus feature as well as local immunity landscape, the long-term spreading tread is mainly decided by the genomic diversity of the viruses, and can be predicted through phylogenetic and genomic epidemiology investigation. The results have emphasized the importance of maintaining the efforts for genomic surveillance of SARS-CoV-2, which is essential from both medical and research perspectives.

Background Emergency department (ED) triage is a high-stakes clinical decision process that determines patient prioritization and resource allocation under time pressure. Large language models (LLMs) have recently been proposed as decision-support tools for triage, yet most evaluations rely on simulated scenarios or curated datasets. Evidence from real-world clinical environments remains limited. The objective of this project was to systematically evaluate the performance, calibration, and reproducibility of multiple contemporary large language models for Emergency Severity Index (ESI) classification and sectoral allocation (ED vs. urgent care practice, UCP) using a comprehensive real-world triage dataset. Material and Methods Retrospective cross-sectional benchmarking study conducted at a tertiary academic emergency ED in Germany with an integrated central point of assessment (CPA). The study included all consecutive adult walk-in encounters (>18 years) presenting between October 2023 and February 2024 (N = 16,107). Data were collected from a structured clinical decision support system capturing presenting complaints, vital signs, and triage decisions recorded by specialized nursing staff. Structured clinical variables routinely collected at triage, including presenting complaint categories (CEDIS-PCL), vital signs according to the ABCDE framework, and additional structured or free-text clinical information. Results The primary outcome was the agreement between LLM-predicted and nurse-assigned ESI levels measured using quadratic-weighted Cohen's k. Secondary outcomes included sectoral assignment agreement, misclassification patterns (over- and under-triage), calibration metrics, and output reproducibility. Quadratic-weighted k values ranged from 0.18 to 0.75 across models. Only a structured stepwise prompting strategy achieved substantial agreement (k_qw = 0.747), approaching reported human inter-rater reliability. Most models demonstrated moderate or lower agreement and systematic overconfidence, with expected calibration errors (ECE) based on verbalized confidence ranging from 0.099 to 0.355. Sectoral assignment agreement (i.e. ED vs. urgent care practice, UCP) was uniformly low (k < 0.30). Reproducibility testing revealed substantial variability in 23% of cases, indicating non-deterministic output behavior for clinically relevant decisions. Conclusions Current large language models demonstrate heterogeneous and generally limited performance in real-world emergency triage tasks. Structured algorithm-guided prompting appears more influential than model architecture or size. Before clinical implementation, improvements in calibration, reliability, and workflow integration are required, alongside regulatory-compliant validation in prospective clinical settings.

Background The European Association for the Study of the Liver (ESAL) - Steatotic Liver Disease (SLD) screening algorithm involves two steps; initial screening with FIB-4 followed by referral for vibration-controlled transient elastography (VCTE) in patients likely to have significant fibrosis (SF). However, VCTE is not widely available in resource-limited settings. Aim To optimise the EASL SLD screening algorithm for resource-poor settings using machine learning (ML). Methods We analysed data from 964 adults aged [&ge;]35 years who underwent VCTE at a tertiary referral centre in Sri Lanka between November 2024 and 2025. Multiple ML models using different methods and variable combinations were trained on 80% of the dataset and tested on the remaining 20%. Best models were selected based on performance and externally validated using data from 430 patients who underwent VCTE before November 2024. Model performance was compared with the FIB-4 using confusion matrices. Results A Random Forest model incorporating age, AST, ALT, and platelet count separately, rather than using FIB-4, outperformed. The all-variable ML model showed the best predictive performance for SF, with accuracy of 77.2%, recall of 0.762, precision of 0.778, and AUC-ROC of 0.818. The variables used in the model, in descending order of feature importance, were AST, platelet count, BMI, ALT, age, diabetes mellitus, hypertension, dyslipidaemia, sex, family history, hypothyroidism, diabetes complication and smoking. External validation demonstrated 75.1% accuracy and an AUC of 0.779. When used as the first step of the SLD screening algorithm, the all-variable ML model identified 37 (17.1%) additional true positives and reduced false-negative diagnoses by 50% compared with FIB-4. Conclusions ML-based models were more effective than the FIB-4 score as the first-line screening tool for VCTE referral, substantially improving the identification of patients with significant fibrosis in this South Asian cohort.