Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 9 appraisals
Biomedical physics & engineering express
Automated ventricular and midline segmentation in cranial ultrasound with metrology
Ultrasound imaging through sonolucent cranial implants is an emerging modality for post-neurosurgical monitoring of the adult brain, but quantitative interpretation remains challenging due to speckle, attenuation, shadowing, and the difficulty of consistently delineating thin anatomical landmarks. We present a deep learning system developed atLongeviti Neuro Solutionsfor segmenting key intracranial structures-the ipsilateral and contralateral lateral ventricles and the cranial midline-in coronal-plane adult cranial ultrasound images from patients withLongeviti ClearFit®Acoustic Brain Interface (ABI)TMimplants. The dataset comprises 457 proprietary, de-identified ultrasound frames with known pixel spacing, annotated in CVAT with ventricle and midline labels. We benchmark multiple encoder-decoder segmentation architectures and address severe class imbalance using class-weighted optimization with Dice and midline-focused focal-Tversky terms, followed by horizontal-flip test-time averaging. The best-performing configuration achieved a foreground macro Dice of 0.856 on a held-out test set, with Dice values of 0.926, 0.921, and 0.720 for the contralateral ventricle, ipsilateral ventricle, and midline, respectively. Finally, predicted masks are converted into geometry-based metrology overlays by estimating maximal perpendicular ventricle spans and ventricle-to-midline distances. These outputs provide standardized, millimeter-calibrated measurement visualizations for downstream review and future clinical validation.
28 July 2026
Read appraisal →Neurosurgical review
Prognostic value of automated pupillometry in traumatic brain injury: a systematic review and meta-analysis
Traumatic brain injury (TBI) remains a major global cause of mortality and long-term disability. Early prognostication is critical for guiding management decisions. Quantitative pupillometry (QP), using automated devices such as the NeurOptics NPi-200/300, enables bedside measurement of pupillary reactivity through indices like the Neurological Pupil Index (NPi), constriction velocity (CV), and dilation velocity (DV). We conducted a PRISMA-compliant systematic review and meta-analysis to evaluate the prognostic value of QP in adults with TBI. Observational studies of quantitative pupillometry within 72 h of traumatic brain injury in adult ICU patients were included. Studies limited to mild TBI were excluded, although mixed-severity cohorts were eligible. Primary outcomes were mortality and poor functional outcome at 3-6 months (GOS ≤ 3 or mRS ≥ 3). Secondary analyses assessed differences in pupillometry metrics according to intracranial hypertension defined by direct ICP measurements (> 20-25 mmHg) or proxy markers reflecting ICP-directed interventions. Odds ratios were pooled for dichotomous outcomes and mean differences for continuous outcomes using random-effects models, with heterogeneity quantified by I². Four studies (n = 354) reported mortality data. Abnormal quantitative pupillary metrics (most commonly NPi < 3 or absent reflexes) were associated with increased odds of in-hospital death (OR 1.84, 95% CI 1.01-3.35; I² = 84%). Five studies (n = 384) assessed functional outcomes, showing significantly greater odds of poor outcome among patients with abnormal pupillary metrics (OR 3.64, 95% CI 1.63-8.10; I² = 39%). Three studies (n = 190) evaluated intracranial pressure, demonstrating lower NPi values in patients with intracranial hypertension compared with those without elevated ICP, though this difference did not reach statistical significance (MD - 1.05, 95% CI - 2.65 to 0.54). Early quantitative pupillometry is associated with increased mortality and worse functional outcomes in TBI in observational studies. Lower quantitative pupillary metrics were also observed in the presence of intracranial hypertension. Despite substantial heterogeneity, these findings support its potential as a prognostic tool. Further standardization, validation and controlled studies are needed to refine its clinical application.
21 July 2026
Read appraisal →Translational stroke research
Quantitative Cerebrovascular Analysis for Improved Prediction of Post-Stroke Complications
Endovascular thrombectomy (EVT) has transformed the treatment of acute ischemic stroke (AIS). However, a substantial proportion of AIS patients experience poor outcomes despite successful recanalization, often due to severe neurological deterioration or life-threatening complications. Early identification of these high-risk patients remains a major unmet need. In this study, we developed and validated machine-learning (ML) models that integrate automated quantitative brain arterial morphology and collateral grading with demographic, clinical, laboratory, and imaging variables to predict major post-EVT complications and early neurological outcomes. Using a prospectively collected database of 727 AIS patients that underwent EVT, we developed ML models to incorporate patient-specific vascular morphometry with conventional clinical, laboratory, and imaging data to predict emergence of early neurological deterioration (END), symptomatic intracranial hemorrhage (sICH), malignant brain edema (MBE) requiring surgical decompression, and neurogenic respiratory failure and dysphagia requiring tracheostomy/gastrostomy (TC/PEG). Our analysis of morphological features, including increased tortuosity and reduced vessel diameter, showed strong associations with complications. Morphology-informed (MI) models consistently outperformed baseline-clinical (BC) models for patients with END (AUROC 0.81 for MI model vs. 0.73 for BC), sICH (AUROC 0.68 MI vs. 0.56 BC model), MBE (AUROC 0.67 MI model vs. 0.56 BC), or patients who underwent TC/PEG (AUROC 0.66MI vs. 0.58 BC model). Statistical testing confirmed significant AUROC improvements for END, sICH and mRS (p < 0.05), Finally, patient-specific calibrated probability profiles enabled individualized, multidimensional risk stratification, revealing distinct complication-specific risk patterns across patients. These findings demonstrate that cerebrovascular structure-an often overlooked yet physiologically fundamental determinant of ischemic injury and reperfusion dynamics-provides significant predictive information that is not captured by standard clinical or visual imaging assessments. Automated vascular segmentation and collateral grading techniques enable rapid and objective integration of cerebrovascular metrics into prognostic models, offering a scalable tool for precision risk stratification, supporting earlier intervention, targeted monitoring, and improved post-EVT management.
9 July 2026
Read appraisal →Studies in health technology and informatics
AI-Integrated EEG Decision Support for Neurocritical Care: A Conceptual and Feasibility Framework
The clinical use of electroencephalography (EEG) for neuro-prognostication in neurocritical care remains limited, despite its ability to provide non-invasive insight into brain activity. This study presents a conceptual framework and early-stage prototype of an AI-assisted EEG decision-support system. Using a literature-informed design and system architecture approach, a web-based prototype was developed to support automated EEG analysis and interpretable brain response reporting. Feasibility testing with four users demonstrated reliable system operation and generation of within-patient decision-support indicators. We highlight the system design and feasibility of operationalizing EEG-based analytics into a clinically interpretable decision-support framework for neurocritical care.
24 May 2026
Read appraisal →Neurosurgical review
Preoperative predictors of seizure outcomes after epilepsy surgery for mesial temporal sclerosis: A systematic review
Mesial temporal lobe epilepsy (MTLE) due to hippocampal sclerosis (HS) is a leading cause of drug-resistant epilepsy. Surgical resection, particularly anterior temporal lobectomy (ATL), achieves high rates of seizure freedom, but outcomes vary. Identifying reliable preoperative predictors may optimize patient selection and surgical success. To systematically evaluate preoperative clinical, neuroimaging, and neuropsychological factors associated with postoperative seizure outcomes in MTLE. A systematic review was conducted according to PRISMA 2020 guidelines. PubMed, Scopus, and Web of Science were searched for cohort studies (2010-2025) reporting predictors of seizure freedom after MTLE-HS surgery. Eligible studies assessed one or more preoperative factors (clinical, EEG, imaging, neuropsychological) in relation to postoperative outcomes. Data were extracted for qualitative synthesis, and methodological quality was assessed with the Newcastle-Ottawa Scale (NOS). From 615 records, 24 studies were included, encompassing patients treated with ATL, selective amygdalohippocampectomy (SAHE), or stereotactic laser ablation. Seizure freedom rates (Engel I/ILAE 1) ranged from 50% to 75%, with ATL achieving ~ 70% at 1-2 years. Multimodal concordance-MRI-visible HS, unilateral seizure onset on EEG, and concordant PET hypometabolism-was the strongest predictor of seizure freedom. Bilateral EEG/PET abnormalities consistently predicted poorer outcomes, whereas structural measures, such as hippocampal subfield volumes and HS subtypes, showed little prognostic value. Multimodal presurgical concordance is a robust predictor of favorable outcomes in MTLE-HS surgery, whereas bilateral or discordant findings indicate a higher risk of failure. Comprehensive presurgical evaluation remains essential to optimize surgical decision-making.
21 May 2026
Read appraisal →Journal of neural engineering
Physiologically inspired modeling of cortical dynamics through spiking neural networks
Objective. The characterization of neural activity underlying neurophysiological function presents a major challenge in computational neuroscience. Several methods have been proposed to investigate cortical network dynamics by reconstructing underlying neural activity from electroencephalography (EEG) signals. However, these methods generally pose significant mathematical challenges.Approach. This study introduces a novel framework to model the underlying brain activity network from a functional and physiologically-inspired perspective, combining spiking neural networks with EEG signal analysis. The dynamics of single neurons are described by the well-known Izhikevich model, and distinct populations of cortical inhibitory and excitatory neurons are employed to model experimental EEG recordings. Functional interactions among distinct populations are mathematically formalized through connective probabilities.Main results. The proposed framework is validated by testing it on synthetic data, as well as on two experimental datasets comprising data from 30 healthy subjects undergoing a cold-pressure test (CPT), and 36 subjects undergoing a mental arithmetic stressor. Experimental results suggest that the proposed framework provides novel and complementary insights into characterizing neuronal changes in comparison to standard EEG power analysis.Significance. The proposed framework constitutes a promising tool for functionally characterizing the underlying cortical dynamics under pathophysiological conditions.
20 Apr 2026
Read appraisal →Scientific reports
Association between estimated plasma volume status and all-cause mortality in critically ill patients with non-traumatic subarachnoid hemorrhage: analysis of the MIMIC-IV database
BACKGROUND: The estimated plasma volume status (ePVS) is an independent risk factor for poor prognosis in certain cardiovascular disease populations. However, the relationship between ePVS and prognosis in critically ill patients with non-traumatic subarachnoid hemorrhage (NSAH) remains unclear. This study aims to explore the association between ePVS and all-cause mortality (ACM) in NSAH patients. METHODS: A total of 750 NSAH patients were included in this retrospective study. The primary outcome was 1-month ACM. A Cox proportional hazards model was constructed to examine the relationship between ePVS and ACM in critically ill NSAH patients. A restricted cubic spline model was used to assess the relationship between ePVS and the outcome. RESULTS: In this patient cohort, 1-month, 3-month, and 1-year ACM rates were 21%, 25%, and 29%, respectively. After adjusting for potential confounders, we found a U-shaped relationship between ePVS and 1-month ACM, with an inflection point at 3.94. Specifically, when ePVS is below the inflection point, each unit increase in ePVS reduces the mortality risk by 56% [HR, 0.44 (95% CI 0.25, 0.76)]. However, once the inflection point is surpassed, each unit increase in ePVS increases the mortality risk by 1.8 times [HR, 2.80 (95% CI 1.58, 4.97)]. CONCLUSION: We identified a U-shaped relationship between ePVS and ACM in critically ill patients with NSAH, suggesting both low and high ePVS levels may portend adverse outcomes. Prospective multicenter studies are warranted to validate these findings and elucidate underlying mechanisms.
10 Apr 2026
Read appraisal →Brain : a journal of neurology
Multimodal multicentre investigation of diagnostic and prognostic markers in disorders of consciousness
Severely brain-injured patients may enter a spectrum of conditions collectively known as disorders of consciousness. This spectrum includes clinical conditions such as unresponsive wakefulness syndrome or minimally conscious state, where the behavioural assessment of consciousness can often be deceptive. To bridge this dissociation, neuroimaging techniques are employed to identify the residual brain functions. Each neuroimaging modality imperfectly captures distinct aspects of brain preservation-functional, anatomical, or both. In this study, we adopt a comprehensive approach by integrating the neurophysiology and neuroimaging modalities available from the standard and advanced clinical assessments through interpretable machine learning. The electrophysiological modalities included high-density EEG (resting state and task), whereas neuroimaging modalities included anatomical and resting-state functional MRI, diffusion MRI and 18F-fluorodeoxyglucose PET. Our investigation reveals that specific modalities, such as functional assessments, provide comprehensive insights into the currently evaluated state of consciousness, the diagnosis of the patients. Conversely, structural modalities offer valuable information about the patient's evolution within the consciousness spectrum. We validate the proposed analysis with data coming from other centres with different acquisition parameters. Importantly, we demonstrate that model performance improves with an increase in the number of modalities. We observe a higher inter-modality disagreement for minimally conscious state patients and those patients who improve. Lastly, we observe a difference in feature importances between diagnosis and prognosis, with an interaction between modality and anatomical structures: some subcortical markers tend to contribute more to prognosis, while other cortical markers are more informative for diagnosis. This integrative multimodal and machine learning methodology presents a promising avenue for a more nuanced understanding of disorders of consciousness, contributing to enhanced diagnostic precision, prognostic capabilities and the personalization of rehabilitative strategies in clinical practice.
9 Apr 2026
Read appraisal →Neuroscience
Comparative analysis of key phagocytic genes in humans and mice using machine learning integrated with single-cell RNA sequencing
Microglial phagocytosis is essential for neurological recovery after intracerebral hemorrhage (ICH). Using single-cell RNA sequencing, we compared microglial responses in murine and human ICH and identified striking species-specific temporal patterns. Murine microglia exhibited a sustained enhancement of phagocytic activity, whereas human microglia showed only a transient increase followed by a decline and persistent inflammation. To identify genes associated with phagocytic differences, we evaluated five machine learning models and selected XGBoost as the best-performing model. This analysis identified Tlr2 in mice and CLEC7A in humans as genes associated with microglial phagocytic status. Inferred transcription factor activity analysis further revealed stronger phagocytosis- and inflammation-associated transcriptional activity in murine phagocytic microglial subclusters, whereas human microglia were predominantly characterized by inflammation-associated transcription factors. Consistent with these results, Tlr2 expression was markedly increased at day 14 in single-cell data, and immunostaining confirmed its colocalization with IBA1+ microglia and upregulation at days 3 and 7 after ICH. Together, our findings demonstrate that integrating single-cell RNA sequencing with machine learning facilitates the identification of phagocytosis-associated genes and reveals both conserved and divergent patterns of microglial phagocytosis, providing new insights into species-specific responses to ICH.
6 Apr 2026
Read appraisal →