Accurate kidney ultrasound segmentation is fundamental for clinical measurement and computer-aided diagnosis. However, domain shifts across devices and centers-manifested as differences in grayscale intensity, contrast, and speckle texture statistics-can substantially degrade model generalization, while acquiring new pixel-level annotations is costly. To address this, we propose a statistical spectral-similarity-guided ultrasound-to-ultrasound translation method to improve kidney segmentation performance without target-domain annotations. Motivated by frequency-domain analysis of renal ultrasound data, we observe that mid-to-low frequency components, which encode global organ structure, exhibit high consistency across domains, whereas mid-to-high frequency components, dominated by device-dependent speckle and texture statistics, vary substantially. Based on dataset-level frequency statistics, our method automatically identifies spectrally similar frequency bands shared by the source and target domains and derives structural guidance from them. This guidance is injected as a soft condition throughout a diffusion-based image generation process, enabling translation to target-device appearance while preserving anatomical structure. The translated images, paired with source-domain labels, are then used to train a segmentation network without requiring any target-domain annotations. Experiments on two public renal ultrasound datasets (OKUS and UNK) and an in-house multi-center dataset demonstrate superior structural preservation in image translation and consistently improved downstream segmentation performance, with particularly large reductions in boundary error. In the challenging OKUS to UNK adaptation scenario, our method boosts the mean Dice score by up to 20.52% (from 56.05% to 76.57%) and drastically reduces the 95% Hausdorff Distance (HD95) boundary error by 71.96 mm compared to the direct transfer baseline. Furthermore, consistent performance gains are achieved across the in-house multi-center dataset. These results indicate that the proposed spectral-similarity-based guidance effectively handles ultrasound domain shifts, substantially improving robustness and generalization for kidney segmentation under zero-shot and cross-center settings.
Conservation of post-translational modifications (PTMs) in histones across six plant species.
Neurodegenerative diseases, such as Alzheimer's disease, Parkinson's disease, Huntington's disease, and amyotrophic lateral sclerosis, are defined by the progressive loss of neurons through interconnected pathological mechanisms, including oxidative stress, mitochondrial dysfunction, protein aggregation, and neuroinflammation. Accumulating evidence implicates metal dyshomeostasis as a central and multifaceted contributor to these mechanisms, with roles ranging from a primary pathogenic driver in AD and PD, to a secondary amplifier of genetic pathology in HD and ALS, and as a contextual risk modifier in the presence of toxic metals. Essential trace metals such as iron, zinc, copper, manganese, selenium, iodine, and molybdenum are vital for neurotransmission, antioxidant defense, and cellular metabolism. Dysregulation of these metals disrupts redox balance, impairs proteostasis, and activates regulated cell death pathways, including ferroptosis and cuproptosis. Toxic metals, such as lead, cadmium, and mercury, exacerbate neurodegeneration by displacing essential metals, inducing oxidative injury, and promoting protein misfolding and neuroinflammation. This narrative review synthesizes mechanistic, experimental, genetic epidemiological, and clinical evidence to critically evaluate the contributions of both essential and toxic metals to neurodegeneration in AD, PD, HD, and ALS. We examine the genetic, environmental, and physiological determinants of metal homeostasis; the analytical techniques for quantifying metals in clinical samples; and clinical trial data on metal-targeted therapeutic strategies. Notably, iron chelation with deferiprone consistently reduces brain iron on neuroimaging but worsens clinical outcomes in both PD and AD, presenting a translational paradox that requires mechanistic re-evaluation. We also provide methodological recommendations for interpreting Mendelian randomization studies of metal exposures and propose translational priorities to advance metal-targeted diagnostics and therapeutics for neurodegenerative diseases.
The use of advanced analytics in public health policy remains hindered by a disconnect between researchers, policymakers and technical experts. Bridging this gap requires intentional knowledge translation strategies that facilitate interdisciplinary collaboration and real-world application of research findings. Hackathons, which bring together diverse stakeholders in a time-bound, solution-oriented format, offer an approach to address this challenge. In January 2025, the MRC Centre for Global Infectious Disease Analysis and the Centre for Epidemiological Modelling and Analysis at the University of Nairobi organised the Bridging the Gap Hackathon, designed to strengthen collaboration between academia, policy and public health practitioners in Kenya. The hackathon convened researchers, software engineers and policymakers to co-develop data-driven tools to tackle public health challenges identified by Kenya's Ministry of Health and the Directorate of Veterinary Services. Over five days and using a structured multi-stage process, six interdisciplinary teams developed prototype solutions to improve outbreak surveillance, vaccine deployment, data quality monitoring and health workforce estimation. This paper reflects on the hackathon's structure, participant experiences and project outcomes, highlighting key lessons for future knowledge translation initiatives. Our findings suggest that hackathons can serve as effective platforms for accelerating interdisciplinary research impact, fostering engagement between policymakers and researchers and promoting the development of solutions to public health issues.
Activity-dependent synaptic plasticity is governed by posttranslational mechanisms that regulate the stability and molecular organization of postsynaptic protein complexes. Proline-directed phosphorylation of the N-terminus of PSD-95 promotes synaptic weakening during NMDAR-dependent LTD, yet this type of phosphorylation also alters the cis-trans isomerization of the adjacent peptidyl-prolyl bond. Despite its predicted importance, these conformational changes have not been directly measurable using existing molecular tools. Here we describe the development of novel conformation-preferential antibodies that distinguish structural states of PSD-95 when Threonine 19 (T19), a site implicated in NMDAR-LTD, is phosphorylated. These antibodies were validated biochemically and in cellular assays, where signal increased following GSK3β-mediated phosphorylation and was lost upon dephosphorylation. These reagents represent the first conformation-preferential antibody-based tools capable of reporting phosphorylation-dependent conformational states of PSD-95 at T19. This strategy validates and expands prior framework for developing conformational-sensitive antibodies, an approach that can be applied to other synaptic proteins.Significance Statement Post-translational modifications regulate synaptic proteins not only through changes in chemical composition but also by altering protein conformation. Phosphorylation of PSD-95 at Threonine 19 is required for NMDA receptor-dependent synaptic weakening, yet the associated cis-trans isomerization of the adjacent proline bond has been inaccessible to experimental analysis. In this study, we introduce the first conformation-preferential antibodies capable of distinguishing phosphorylation-dependent structural states of PSD-95 at this site. These reagents provide a new molecular toolkit for investigating how proline-directed phosphorylation and isomerization regulate synaptic scaffolds during plasticity and disease.
Takeda G-protein-coupled receptor 5 (TGR5) and farnesoid X receptor (FXR) are bile acid-activated receptors involved in glucose, lipid, and energy homeostasis, making them promising therapeutic targets for type 2 diabetes mellitus (T2DM) and metabolic liver diseases. This review critically analyzes patents published between 2015 and 2025 retrieved from WIPO Patentscope, Espacenet, USPTO, and Google Patents using keyword- and IPC-based strategies. Major patented chemotypes include modified bile acids, benzoic acid-cholane hybrids, heteroaryl scaffolds, and sulfonylurea/sulfonamide derivatives. Several compounds demonstrated sub micromolar (µM) to nanomolar (nM) TGR5/FXR agonistic activity, while gut-restricted agonists showed enhanced GLP-1 secretion with reduced systemic adverse effects such as gallbladder filling and pruritus. Comparative patent analysis revealed a progressive transition from classical steroidal scaffolds toward tissue-selective and gut-restricted modulators designed to improve receptor selectivity, pharmacokinetics, and translational safety. Despite strong preclinical promise, the clinical translation of TGR5 and FXR agonists remains limited by mechanism-driven toxicities and inadequate long-term tolerability. Future progress will likely depend on tissue-selective, pathway-biased, and gut-restricted modulation rather than further increases in receptor potency.
The earliest stages of Alzheimer's disease (AD) are frequently characterized by neuropsychiatric symptoms (NPS) such as anxiety, agitation, depression, compulsivity, appetite dysregulation, and sleep disturbances, often preceding measurable cognitive decline. Evidence from clinical and animal studies implicates hyperactivity of the locus coeruleus-norepinephrine (LC-NE) system as a mechanistic driver of these behaviors. Here, we review noradrenergic circuits that can potentially underlie psychiatric disturbances to identify therapeutic targets for preventing and delaying onset of AD. Given that this system influences attention, arousal, mood, and stress responses, LC-NE hyperactivity across circuitry involving amygdala, thalamus, hypothalamus, anterior cingulate cortex, prefrontal cortex, and olfactory areas can contribute to NPS features in early AD. Advances in neuroimaging and physiological measures of noradrenergic function have enabled in vivo tracking of LC integrity and NE transmission, offering the opportunity to detect LC-NE dysfunction early in disease progression and potentially implement targeted pharmacologic and neuromodulatory interventions to restore optimal LC-NE tone. Overall, dissection of LC-NE circuitry and its clinical translation hold promise for developing biomarker-driven, stage-specific interventions to reduce NPS burden and enhance the efficacy of disease-modifying therapies in AD.
To provide a comprehensive review of the biological rationale, clinical evidence, and practical perioperative management of immunotherapy for the head and neck surgeon. Standard treatment for resectable head and neck squamous cell carcinoma (HNSCC) has reached a survival plateau, with over 50% of patients experiencing recurrence. The integration of immune checkpoint inhibitors (ICIs) into the neoadjuvant window represents a paradigm shift toward biologically adapted surgical intervention. Neoadjuvant immunotherapy capitalizes on an intact immune substrate to create an in situ vaccine, avoiding the post-surgical immune desert that limits adjuvant efficacy. Emerging phase III data confirm that perioperative ICI significantly improves event-free survival. Successful implementation requires the surgeon to navigate unique diagnostic challenges, such as distinguishing rare but anatomically risky pseudoprogression from true progression. While combination therapies (chemoimmunotherapy or immunoradiotherapy) yield higher pathologic complete response rates, they also increase toxicity. Intraoperatively, ICI monotherapy generally preserves tissue planes without increasing surgical delays or major wound complications. Standard biomarkers like PD-L1 and TMB, alongside emerging tools such as liquid biopsy (ctDNA), are essential for patient selection and dynamic monitoring. The transition to neoadjuvant immunotherapy facilitates future surgical de-escalation and function-preserving approaches. To optimize outcomes, the modern surgeon must act as a surgical immunologist, interpreting translational data to guide real-time operative planning.
Lactate's role in biochemistry and physiology has attracted considerable biochemical interest for over a century. Beyond its classical description as a glycolytic byproduct, lactate is now recognized as a central energy metabolite, a redox shuttle, and a signaling molecule. Modern advances in mass spectrometry have uncovered yet another dimension of lactate biology: lactate as a chemical modification on proteins and metabolites. Covalent conjugation of lactate to the ε-amine of a protein lysine side chain generates a posttranslational modification (lysine lactylation); in a related reaction on metabolites, conjugation of lactate to the α-amine of free amino acids produces a class of bioactive lactate-modified amino acids (the N-lactoyl amino acids). These lactate modifications represent a fundamental mechanism by which transient increases in glycolytic flux are translated into durable downstream effectors. Here, we review the detection, regulation, and function of these lactate-derived modifications in cellular and organismal homeostasis.
Sexual hormone receptors (SHRs) are essential for breast cancer (BCa) pathogenesis. BCa is a prevalent malignancy with high heterogeneity and high recurrence. Endocrine resistance remains a major clinical challenge. SHR-mediated transcription involves complex epigenetic, post-translational, and inter-receptor crosstalk, and dysregulation of these processes contributes to endocrine resistance. This review aims to summarize the current progress on the molecular mechanism underlying the function of nucleic SHRs in BCa, providing insights for the novel therapeutic strategies in BCa.
N7-methylguanosine (m7G) modification plays a critical role in RNA metabolism and is increasingly recognized for its implications in cancer biology. It can influence RNA stability, translation efficiency, and gene expression regulation. However, the specific role of m7G modification and its downstream genes in thyroid carcinoma (THCA) is not well understood. To comprehensively explore the impact of m7G methylation modification and the m7G-related gene ZNF831 on THCA, this study aims to identify key genes influencing m7G modification in THCA, with a particular focus on clarifying the role of ZNF831. This study is expected to further elucidate the pathological mechanisms of THCA and fill the current research gap in this field. Weighted gene co-expression network (WGCNA) analysis was used to evaluate the expression of m7G-related genes in the THCA expression data from the GEO (Gene Expression Omnibus) datasets. Machine learning algorithms, including the least absolute shrinkage and selection operator (LASSO), gradient boosting decision tree (XGBoost), and random forest (RF), were used to identify the feature genes, including GPSM3 and ZNF831, in the TCGA-THCA dataset. Immunohistochemistry was used to identify the expression difference of ZNF831 in 3 THCA tissues and 3 normal tissues. Finally, the changes of proliferation and migration of THCA cells after overexpression of ZNF831 were investigated. This study investigated m7G-related genes in THCA, focusing on ZNF831 as a key tumor suppressor. Differential expression analysis revealed significant dysregulation of m7G-related genes in THCA. Functional and bioinformatics analyses, including gene set enrichment analysis and protein-protein interaction network construction, identified ZNF831 as a candidate gene. Experimental validation demonstrated that ZNF831 overexpression significantly reduced the proliferation and migration of THCA cells. Additionally, tumor microenvironment analysis showed a positive correlation between ZNF831 expression and immune cell infiltration, indicating its potential role in enhancing anti-tumor immunity. These findings underscore the importance of m7G modifications and m7G-related gene ZNF831 in THCA pathogenesis, highlighting their potential as therapeutic targets. Further research is needed to elucidate the molecular mechanisms and explore clinical applications of these findings.
Vitiligo is a chronic autoimmune depigmenting disorder affecting 0.5%-2% of the global population, characterized by bidirectional interplay between psychological stress and disease progression, with accumulating evidence highlighting the central role and translational relevance of the neuro-endocrine-immune-cutaneous axis in its pathogenesis. Epidemiological data indicate over half of patients experience significant psychological stress prior to disease onset, while visible depigmentation markedly elevates the burden of depression and anxiety, establishing a self-amplifying pathogenic loop. Mechanistically, neural crest-derived melanocytes form functional "neuro-pigment units" with intraepidermal nerve endings, enabling bidirectional communication via neuropeptides including calcitonin gene-related peptide (CGRP) and substance P. Dynamic crosstalk among keratinocytes, sensory neurons, and melanocytes integrates neurotrophic and inflammatory signals to tightly regulate melanocyte survival and biological function. Sympathetic activation drives melanocyte injury via norepinephrine-mediated β2-adrenergic receptor signaling, while dopamine metabolites exacerbate apoptosis via the oxidative stress-Akt-Bad axis; context-dependent hypothalamic-pituitary-adrenal axis effects and light-melatonin-circadian clock disruption further promote immune dysregulation and melanocyte loss. Notably, neuromodulatory approaches like transcutaneous auricular vagus nerve stimulation show therapeutic promise by attenuating oxidative stress and limiting pathogenic CD8⁺ T-cell infiltration. These insights have fostered targeted strategies including CGRP receptor antagonists and dual antioxidant-neuroprotective natural compounds. Integrating neuroimmunological modulation with psychological and circadian interventions represents a promising precision medicine framework for vitiligo management.
Glioblastoma (GB) is a WHO grade 4 brain cancer with dismal prognosis, yet its aetiology remains poorly defined. Although viral involvement has been proposed, findings across studies remain inconsistent, reflecting inherent limitations of individual technologies and cohort size. Here we applied metaproteomic profiling to a publicly available GB proteome dataset (12 control, 21 adjacent, 159 tumour) and an independent cohort of 81 samples (37 control, 44 tumour) to detect viral proteins in tumour and controls tissues. Across cohorts, we detected viral proteins from diverse species, with human herpesviruses (HHV-1, 2, and 8) more frequently detected in GB tumours compared with control tissues. Analysis of the host tumour proteome revealed differential abundance of proteins related to transcriptional regulation, RNA processing, protein translation, immune responses, and mitochondrial-associated metabolism. Correlation analysis identified associations between viral and human proteins, with several linked to biological processes previously implicated in DNA virus-host interactions. Further stratification of tumour by HHV-1 status showed consistent alterations in proteins associated with mitochondrial-associated metabolism, protein turnover, and cell adhesion/signalling.In summary, this study demonstrates the feasibility of metaproteomics for detecting viral components in archival GB tissues. Using this approach, we observed differences in viral protein landscape across cohorts and identified associations between viral presence and host proteomic features, providing a protein-level framework for future studies of virus-host interactions in GB.
O-GlcNAcylation is a dynamic, reversible post-translational modification that attaches N-acetylglucosamine (GlcNAc) to the serine or threonine residues of intracellular proteins. Catalysed by O-GlcNAc transferase and removed by O-GlcNAcase, this modification acts as a key nutrient and stress sensor. Although cell adhesion is fundamental to tissue architecture and mechanotransduction, emerging evidence has shown that O-GlcNAcylation profoundly orchestrates these processes. By modulating the composition and signalling of adhesion complexes, O-GlcNAcylation regulates both cell-cell and cell-matrix interactions. Through crosstalk with phosphorylation, this modification drives cellular adhesion plasticity, with broad implications for development, immunity, and diseases, such as cancer and neurodegeneration. Recent advances revealed that O-GlcNAcylation fine-tunes key regulators, including Focal Adhesion Kinase (FAK), Zyxin, and integrins, to control focal adhesion turnover. These mechanistic insights pave the way for novel therapeutic strategies targeting glycosylation-dependent adhesion signalling.
Parturition depends on precise communication between the mother and fetus. While fetal lung signals are known to help initiate labor, the role of the placenta has remained unclear. Here we show that in steroid receptor coactivator (Src)-1 and -2 double-knockout mice, reduced placental amine oxidase, copper-containing 1 (Aoc1) leads to increased spermidine levels. In trophoblast cells, spermidine induces autophagy via hypusination of eukaryotic translation initiation factor 5 A (EIF5A), reducing estrogen and prostaglandin production. Estrogen reciprocally increases Aoc1 expression via estrogen receptor-α (ERα) in concert with SRC-1/2, forming a feedback loop maintaining placental autophagy homeostasis. AOC1 levels are elevated in preterm labor placentas from both mice and humans. Placenta-specific Aoc1 knockout dramatically delays labor by increasing trophoblast autophagy. Importantly, spermidine supplementation rescues inflammation-induced preterm labor in mice. Our findings reveal that placental AOC1-spermidine-EIF5A-autophagy axis is essential for parturition timing and offer a potential therapeutic strategy for preterm birth.
Accurate and timely assessment of consciousness is critical for triage, escalation of care, and patient safety in emergency and hospital settings. However, documentation using the AVPU scale (Alert, Verbal, Pain, Unresponsive) remains inconsistent owing to high workload, subjectivity, and fragmented workflows. This study developed and evaluated Consc.ia, a video-based clinical decision-support platform that automates AVPU inference while preserving clinician oversight and enabling seamless, interoperable documentation through HL7 FHIR. A simulated AVPU dataset comprising 136 videos from 58 healthcare professionals (physicians, nurses, paramedics, and first responders) was created under controlled conditions with ethics approval from the ISCTE - Instituto Universitário de Lisboa Ethics Commission (reference CE-ISTA/2025.08, July 2025). The system architecture combines edge-computing computer vision for real-time extraction of facial landmarks, eye state, arm movement, and verbal responses; a clinician-in-the-loop validation layer; and FHIR-mapped Observation resources for direct EHR integration. Three deployment scenarios (Emergency Medical Services, Emergency Departments, and Intermediate Care wards) were designed and compared. Technology adoption was modelled using Rogers' Innovation Adoption Curve and the Bass Diffusion Model (p = 0.01, q = 0.35, M = 111 Portuguese hospitals). The architecture achieves low-latency inference with privacy-by-design (local processing, no raw video storage). Stakeholder validation confirmed strong workflow fit and highlighted persistent documentation gaps during EMS-to-hospital transitions. Scenario analysis revealed distinct hardware and integration requirements (ambulance edge device versus ward multi-camera server). Bass modelling projects gradual adoption, reaching approximately 50% of Intermediate Care wards by 2037 in the realistic scenario, with the "chasm" phase occurring between 2030 and 2032. Sensitivity analysis identified early clinical evidence and FHIR integration support as the strongest accelerators of diffusion. As this constitutes a proof-of-concept study, no quantitative AVPU classification metrics (e.g., accuracy, sensitivity, specificity, or confusion matrix) are reported at this stage; empirical model evaluation against expert-annotated clinical recordings is identified as the primary prerequisite for future validation and clinical translation. As a proof-of-concept that has not yet undergone clinical validation, Consc.ia offers a feasible, interoperable solution for standardising AVPU documentation and strengthening early warning systems. By combining video analytics, edge computing, clinician validation, and FHIR integration, the platform addresses a longstanding gap in emergency-care digitalisation and provides a clear roadmap for real-world adoption.
Epitranscriptomic regulation of cellular RNAs is a major mechanism of gene expression control in the brain. N6-Methyladenosine (m6A) is installed on thousands of mRNAs and non-coding RNAs, where it functions as a context-dependent regulator of RNA-protein interactions to control the amplitude and kinetics of gene expression. In the nervous system, m6A is critical for neurodevelopment, synaptic plasticity and adaptive responses to physiological stimuli, and its dysregulation has been linked to various brain disorders. In this Review, we present a comprehensive synthesis of how m6A is deposited, interpreted and dynamically regulated, and integrate recent advances to present a unified framework for its function in neural cells. We discuss how m6A coordinates RNA stability, translation, localization and chromatin-associated processes across developmental and adult contexts and how disruption of these pathways contributes to neurological disease. Finally, we explore challenges and future directions for the field.
Accurate survival prediction in non-small cell lung cancer (NSCLC) requires integrating clinical, radiological, and histopathological data. Multimodal deep learning (MDL) can improve precision prognosis, but small cohorts and missing modalities limit its clinical applicability, as conventional approaches enforce complete-case filtering or imputation. We present a missing-aware multimodal survival framework that combines computed tomography (CT), whole-slide histopathology images (WSI), and structured clinical variables for overall survival modeling in unresectable stage II-III NSCLC. The framework uses foundation models (FMs) for modality-specific feature extraction and a missing-aware encoding strategy that enables intermediate multimodal fusion under naturally incomplete modality profiles. By design, the architecture processes all available data without dropping patients during training or inference. Intermediate fusion outperforms unimodal baselines and both early and late fusion strategies, with the trimodal configuration reaching a C-index of 74.42. Modality-importance analyses show that the fusion model adapts its reliance on each data stream according to representation informativeness, shaped by the alignment between FM pretraining objectives and the survival task. The learned risk scores produce clinically meaningful stratification of disease progression and metastatic risk, with statistically significant log-rank tests across all modality combinations, supporting the translational relevance of the proposed framework.
Engineering the genetic code-by reassigning multiple of the 64 natural codons-enables making organisms resistant to all viruses, preventing genetic information exchange, and allowing the biosynthesis of genetically encoded unnatural polymers. However, synonymous codon replacement-recoding-is frequently lethal, and how recoding impacts fitness remains poorly explored. Here, we explore these effects using genome synthesis, directed evolution, and genome-transcriptome-translatome-proteome co-profiling on multiple synthetic Escherichia coli genomes. We construct six partially recoded E. coli strains bearing up to 45.8% of a synthetic genome with a deleterious 57-codon genetic code. As our analyses revealed widespread defects-including unassigned codons in Syn61 and Syn57-we apply multi-omics to revise our genome design and mitigate defects. Using multi-omics, we show that recoding induces transcriptional and translational changes leading to fitness defects under hundreds of conditions. Finally, we develop a multi-omics-guided evolution strategy that rapidly restores fitness, enabling genome synthesis with radical changes.
Emergency EEG (emEEG) is increasingly used in the emergency department (ED), but its diagnostic yield remains uncertain. This protocol describes a multicentre observational study aiming to evaluate emEEG findings and their relationship with diagnostic pathways and therapeutic management of patients admitted to the ED. This multicentre retrospective study will analyse emEEGs performed on patients admitted to the ED of some Italian teaching and community hospitals over a 1-year period with a target sample size of 3850 patients. The diagnostic yield of emEEG will be evaluated by assessing abnormal and epileptiform findings and the relationship between emEEG findings and subsequent clinical decisions, including confirmation or revision of the initial diagnostic suspicion, decisions regarding home discharge or hospitalisation and medication changes. EEG will be classified according to the terminology of the American Clinical Neurophysiology Society. Clinical and instrumental data will be respectively reviewed by emergency physicians and neurologists/neurophysiologists. In particular, via traditional biostatistics and interpretable machine learning models, the study will evaluate the diagnostic yield of emEEG and its association with subsequent clinical management across defined clinical scenarios in the ED. This first large-scale multicentre protocol will provide valuable insights for emergency department (ED) clinicians in selecting appropriate candidates for an emergency EEG (emEEG), supporting ethically sound, proportionate use of this resource in a time- and risk-critical setting. By clarifying diagnostic yield and its relationship with subsequent clinical decisions, the study is expected to generate robust evidence to guide emEEG ordering, reduce unnecessary testing and delays, and promote safer, more equitable decision-making (including appropriate home discharge) while minimising potential harms from misdiagnosis or overtreatment. The study has been approved by the Ethics Committee Regione Toscana - Area Vasta Centro (n. 27241). Findings will be disseminated through peer-reviewed publications, conference presentations and engagement with relevant clinical societies to inform international recommendations and facilitate translation into ED practice. Furthermore, developed models will be made openly available for external and public validation.