European Radiology

Background. Tethered cord syndrome (TCS) is classically associated with a low-lying conus medullaris, yet many surgically treated children have a normally positioned conus (occult TCS). Large-scale normative data on conus position in children, and the diagnostic value of quantitative conus assessment, are limited. Purpose. To establish a large-cohort reference distribution for conus medullaris termination level in children, to quantify conus position in children surgically treated for presumed (occult) TCS, and to test whether automated conus segmentation and radiomics can distinguish TCS from normal. Materials and Methods. In this retrospective single-center study, conus termination level was extracted from structured radiology reports of consecutive pediatric lumbosacral MRI examinations and encoded numerically (L1 = 1, L2 = 2, etc.). Children surgically treated for tethered cord were identified by linkage to an operative registry (name and date of birth) and restricted to preoperative examinations. A deep-learning model (nnU-Net) was trained for conus segmentation on axial T2-weighted images. IBSI-compliant radiomic features were extracted; reproducibility was assessed by intra- and inter-observer intraclass correlation (ICC). A case-control radiomics analysis used batch-only ComBat harmonization and cross-validated L1-penalized logistic regression; discrimination was compared with conus level by paired bootstrap. Results. Among 9,808 examinations with a parseable conus level (98.5% of reports; parser validated against dual blinded annotation, 99.4% agreement, weighted kappa 0.946), the conus terminated in the L1 region in 85.7% and the L2 region in 14.3% of the reference cohort (postoperative examinations excluded, n = 9,655); a low-lying conus (>=L3) occurred in only 0.05% (5/9,655), and remained rare (0.14%, 14/9,808) including operated examinations (median L1; mean 1.13 +/- 0.33). A slightly more cephalad position was seen with increasing age (negligible correlation). Among 475 preoperative children surgically treated for tethered cord, 99.6% had a normally positioned conus (<=L2) and only 0.4% were low-lying. Automated conus segmentation achieved a held-out Dice of 0.85. Conus radiomics likewise did not distinguish TCS from controls (equivalence-tested null; full segmentation/radiomics pipeline reported in the companion methodological paper). Conclusion. In children, the conus medullaris terminates at L1-L2 in more than 99% of cases and is normally positioned in virtually all children surgically treated for TCS. Within the conus, neither position nor texture (radiomics) identifies tethered cord; whether the filum terminale carries a diagnostic signal was not tested here.

Background and rationale: Knee osteoarthritis (KOA) is a leading cause of lower limb disability worldwide, characterized by functional limitations, stiffness and pain. The incidence of KOA is especially tied to age and obesity. It is a disabling disease that often makes patients less physically active, thus increasing the risk of other diseases and mortality1. The clinical diagnosis of KOA is based on the symptoms and functional limitations of the joint. The diagnosis is usually supported with a radiograph (X-ray) of the weight-bearing knee. Radiographic features, such as Kellgren-Lawrence grade, are used as eligibility criteria for clinical studies while other features, such as joint space width (JSW), are used as endpoints for structural KOA progression2,3. While the use of these radiographic features is standard in academia, the use of JSW as a structural biomarker has received criticism. Critics point out that JSW is an indirect and projection dependent measure of cartilage deterioration which is sensitive to technical factors such as the angulation of the X-ray beam and the positioning of the knee. Small differences in these factors can alter the measured joint space and may not reflect true disease progression4,5. Despite limitations, minimum joint space width (mJSW) remains as one of the most widely used structural biomarkers in KOA trials and is currently one of the only structural imaging accepted in regulatory guidance as evidence of disease modification in OA drug development3. For JSW to be reliable and consistent in determining the advancement of KOA, the use of fixed-flexion devices is crucial to reduce the risk of unwanted narrowing or widening of the radiographic joint space width6,7. The LOSEIT trial, which the present study is based on, acknowledges the angulation problem and uses a standard clinical fixed-flexion device in weight-bearing PA views to get reliable JSW results8. Historically, a radiologist would draw on and grade radiographs of the knee-joint to extract the features. However, manual reading and annotation is time consuming with notable interobserver variance9. With increasing computational power and the use of deep neural networks, off-the-shelf artificial intelligence (AI) tools have become available for automatic extraction of radiograph features. Automation would free up time from radiologists and provide more consistent measurements due to the reproducible nature of the models10. These tools have received regulatory approval for commercial use, however, regulatory approval does not guarantee uniform or bias free performance when used on real-world data11. Furthermore, in a large multi-hospital chest X-ray study, Zech et al., showed that convolutional neural networks achieved worse results on data from other hospitals than on the original hospitals in which it was tested12. This highlights the risk of overestimating the accuracy of AI tools when only internally validated. It is therefore apparent that external validation is required when testing these AI models. Objectives: The aim of this analysis is to evaluate the agreement of a commercially available AI tool for measuring JSW with the best practice radiologist annotation in the tibiofemoral joint of the knee in radiographs stabilized with a fixed-flexion device and acquired as part of a clinical trial. Methods: This study is a secondary analysis of the data from the LOSEIT trial, a randomized, double-blind, placebo-controlled, single-center trial, where patients were randomized to either liraglutide or identically appearing placebo after an initial weight-loss period to investigate the effects on KOA. Radiographs of the tibiofemoral joint were acquired at enrollment (week -8) and at end-of-trial (week 52) for a total acquisition-to-acquisition time of 60 weeks13. The primary analysis will assess agreement between AI-derived and reference-derived change in JSW from enrolment to follow-up. Change will be calculated as follow-up minus enrolment separately for the AI tool and the reference measurement. The main measure of interest will be the change in medial minimal JSW (mmJSW), with change in lateral minimal JSW (lmJSW), medial fixed JSW (mfJSW) and lateral fixed JSW (lfJSW) as secondary measures. This study will follow an equivalence framework using the two one-sided tests (TOST) approach with a Bland-Altman analysis as the main outcome. The equivalence margin will be set at {delta} = 0.5 mm. Agreement consistent with equivalence will be considered established if the upper limit of the 95% confidence interval (95% CI) for the upper limit of agreement (LoA) and the lower limit of the 95% CI for the lower LoA are within the established margins. The reference JSW will be the average measurement of two independent resident radiologists. If there is a mismatch in the measurements of more than 0.40 mm between the two radiologists, the radiologists will re-annotate the case independently. If the difference remains greater than 0.40 mm, a musculoskeletal radiology consultant will review the radiograph and establish the reference JSW. The index test will be the measurements output by the AI tool. Populations: Patients aged 18 to 74 with symptomatic knee osteoarthritis, radiographically confirmed KL grade 1-3, with a BMI [&ge;]27, motivated for weight loss and in accordance with the LOSEIT trial inclusion criteria Further statistical details Sample size: Not applicable as this is a secondary analysis. Framework: This is an agreement study assessing the equivalence of a commercially available AI tool for radiographic evaluation of knee osteoarthritis with best practice radiologist measurements. Confidence intervals and P values: All 95% confidence intervals and P-values will be two-sided. Statistical software: SAS Studio and/or R version 4.2.2 (or newer).

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 [&ge;]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.

Introduction: Precise anatomical navigation is fundamental to safe endoscopic pituitary surgery, a high-stakes procedure characterised by a challenging learning curve. While traditional navigation systems often rely on workflow-disrupting probes or static preoperative imaging, advancements in computer vision AI (CVAI) now enable dynamic, real-time anatomical segmentation directly from live surgical video1-3. Our group has previously conducted a series of preclinical human-computer interaction studies to refine the system's design, alongside digital and high-fidelity physical simulations demonstrating the benefit of AI assistance in improving overall performance, training, and safety4-8. Building on this foundation, the current study represents a first-in-human application of real-time CVAI assistance in the neurosurgical operating room, serving to assess feasibility and safety, and to iteratively improve the system. Method: Guided by DECIDE-AI and IDEAL frameworks, this single-centre evaluation comprises an initial proof-of-concept phase (n=6) for endoscopic transsphenoidal pituitary surgeries. The AI model utilised a DINOv3-derived vision transformer architecture, deployed via a high-performance edge computing unit to achieve low-latency, real-time inference without reliance on cloud infrastructure2. Given the high-risk nature of the procedure and the early stage of clinical AI integration, the system was initially deployed as an educational adjunct on a secondary monitor, ensuring the primary surgical feed remains uncompromised. Functionality and safety were assessed via structured questionnaire, prospective observation, and blinded retrospective review of the recordings of the endoscopic surgical video feed and wider operating room environment. Continuous multi-stakeholder feedback through validated human factors surveys drove iterative technical refinements between cases. Results: Six patients with pituitary adenomas were enrolled. The CVAI system was successfully deployed in four cases, demonstrating acceptable real-time sella segmentation accuracy. Deployment failed pre-operatively in two cases owing to a single recurring system reboot bug. Iterative refinement between cases were driven by our experience and surgical team feedback. This resulted in the integration of additional anatomical structure segmentations (e.g., carotid arteries), enhanced model accuracy via training dataset expansion, and hardware firmware upgrades. Multi-stakeholder surveys demonstrated satisfactory system feasibility, usability, and acceptability among the surgical team. Both prospective observation and retrospective video review confirmed the absence of adverse events, including no significant distraction to the primary surgeon, and there were no AI-related clinical complications. Conclusion: This first-in-human early clinical evaluation demonstrates the feasibility, safety and iterative development of real-time, CVAI-based anatomical navigation during high-stakes neurosurgery. Future work will include a larger single-centre case series (IDEAL Stage 2a) with more surgical teams to further iterate the system and explore its impact on training and workflow. As the underpinning technology improves, deployment will transition to direct intra-operative decision support and integration with other intra-operative navigational technologies.

Introduction: Structural neuroimaging relies on T1-weighted (T1w) magnetic resonance imaging (MRI) for brain morphometry, yet at 7 Tesla (7 T) transmit field (B1+) inhomogeneity remains a major source of bias. Although Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) improves the tissue contrast, residual B1+ effects may persist and may be exacerbated in aging or clinical populations, where anatomical and physiological factors further challenge image quality and preprocessing. The impact of B1+ inhomogeneity on automated quality assessment and morphometric statistical inference remains insufficiently understood. Methods: Submillimeter 7 T MP2RAGE brain acquisitions from carriers of a mitochondrial gene mutation (m.3243A>G) and controls were retrieved from previous studies. Image quality before and after B1+ inhomogeneity correction was assessed by multiple automated pipelines. Case-control morphometric studies, including regional volume and mean cortical thickness, were analyzed in both registration based and deep learning based segmentation frameworks. Changes in image quality metrics (IQMs) and morphometric statistical significance were evaluated to determine the impact of B1+ inhomogeneity correction. Results: Overall image quality rating and metrics sensitive to intensity non-uniformity and topological integrity consistently improved after B1+ inhomogeneity correction. However, its impact on morphometric statistical inferences was strongly method-dependent. Some pipelines showed redistribution of significant regions, whereas others predominantly demonstrated increased effects in sensitivity. Across methods, B1+ inhomogeneity correction altered the findings of morphometric analyses, particularly in cortical regions. Conclusion: Residual B1+ inhomogeneity at 7 T substantially influences both image quality control and morphometric evaluations. Current automated quality control approaches can hardly capture these effects reliably. B1+ inhomogeneity correction will not only improve intensity uniformity, but also change sensitivity of morphometric statistical inferences. To establish reliable morphometric biomarkers at UHF strengths, explicit B1+ correction and customized preprocessing are practically necessary and highly recommended.

Background In 2016, the World Health Organization revised its antenatal care (ANC) recommendation from four to eight visits. For low- and middle-income countries like Uganda, where achieving even four visits remains a challenge, this transition has significant cost implications for both the health system and households. This study estimated the incremental costs of adopting the eight-visit model from a societal perspective. Methods The study was conducted in six government health facilities in southwestern Uganda. A micro-costing approach estimated health facility costs (personnel, equipment, consumables, and overhead). Costs incurred at patients end (transport, ultrasound, medical expenses, and time) were collected from 785 women using a questionnaire, with all costs in 2025 USD. Results For an average of 4.3 visits, total cost per woman was $100.1: facility costs $43.7 (43.7%), and patient costs $56.4 (56.3%). Transitioning to eight visits would increase total cost by $57.8 (57.8%), of which $36.4 (63.0%) would fall on households, equivalent to 68.8% of average monthly household income. Total costs would rise by 55.4% ($115.5 to $179.5) at Health Center IVs and 64.3% ($102.3 to $168.1) at Health Center IIIs, with facility costs up 43.4% and 62.9% and patient costs up 61.2% and 65.7%, respectively. Conclusion Transitioning to eight ANC visits would impose a large financial burden on households, with the incremental patient cost equivalent to more than two-thirds of average monthly household income. Equitable implementation requires improving availability of medicines and diagnostics, subsidizing transport, exploring telemedicine or community-based models, and improving efficiency at lower-tier health centers.

Objective: Outcome after surgical hematoma evacuation for intracerebral hemorrhage (ICH) depends on hematoma location. As corticospinal tract (CST) integrity affects motor recovery after stroke, we hypothesized that CST integrity drives heterogeneity in surgical outcomes and investigated this in a secondary analysis of MISTIE-III participants. Methods: Risk of CST injury was categorized into four levels, based on the interaction between the CST, the hematoma, and perihematomal edema (PHE) on automatically segmented stability CT: no risk, PHE infiltration, hematoma infiltration, and complete interruption of the CST. Associations with outcome were tested using multivariable linear regression for motor National Institutes of Health Stroke Scale (NIHSS) at day 180 and ordinal regression for modified Rankin Scale (mRS) at day 365, introducing an interaction term between CST risk and treatment group. Results: Day 180 motor NIHSS was significantly lower for 'no risk' ({beta}:-3.77, [95% confidence interval [CI]: -5.8 to -1.70], p=0.0003) and 'PHE infiltration' ({beta}:-2.3, [95%CI: -3.5 to -1.1]; p=0.0002) vs. 'complete interruption'. Surgery was associated with lower Day 180 motor NIHSS in participants with hematoma infiltration ({beta}:-2.07, [95%CI: -3.8 to -0.4], p=0.016). Compared to complete interruption, 'no risk' (adjusted odds ratio [aOR]:0.27, [95%CI: 0.10 to 0.74], p=0.01) and 'PHE infiltration' (aOR:0.41, [95%CI: 0.23 to 0.74]; p=0.003) were associated with lower odds of unfavorable day 365 mRS. Surgery was associated with lower mRS in participants with no risk (aOR:0.23, [95%CI: 0.05 to 0.97, p=0.045). Interpretation: Increasing CST risk is associated with worse motor recovery (day 180) and disability (day 365). CST risk modifies the effect of the MISTIE-III procedure on motor recovery and disability.

Background: In atrial fibrillation (AF), cerebral microbleed (CMB) burden guides anticoagulation decisions, yet AF is itself inconsistently associated with CMBs, a paradox unexplained by frameworks that treat CMBs as a unitary marker of small vessel disease. We hypothesized that the white matter hyperintensity (WMH) context in which CMBs arise modifies their vascular meaning, and that this context-dependence underlies the inconsistent AF-CMB association. Methods: From a multicenter Korean stroke registry, we analyzed 5,735 first-ever ischemic stroke patients imaged at nine centers using susceptibility-weighted MRI. WMH volume and CMB count were extracted by validated deep learning pipelines. Patients were cross-classified by age-adjusted WMH residual (median split) and CMB count (2) into four groups. The AF-CMB association was estimated by multivariable logistic regression within each WMH stratum with formal interaction testing. Spatial CMB distribution was analyzed against the Automated Anatomical Labeling atlas. Results: In the full cohort (mean age 69.5 years; 57.7% male), AF was not associated with CMBs (OR 1.04; 95% CI 0.87-1.25). Stratification yielded divergent estimates: the adjusted AF OR was 1.46 (1.11-1.93; P = 0.007) in the WMH-low stratum and 0.95 (0.73-1.22; P = 0.665) in the WMH-high stratum, with significant interaction (OR 0.56; P < 0.001). The discordant phenotype (low WMH, high CMB; 8.9%) was enriched for AF (28.0%) and showed fronto-temporal cortical predominance with deep structure sparing. AF independently reduced the proportion of deep CMBs (IRR 0.80; P = 0.040). The interaction was preserved across prespecified sensitivity analyses. Conclusions: The AF-CMB association is confined to patients with low WMH burden relative to age and is accompanied by a topographically distinct CMB distribution. Clinical assessment of small vessel disease based on WMH alone may overlook a CMB phenotype linked to AF.

PURPOSE: Alzheimer disease (AD) is associated with cognitive impairment, brain atrophy, and elevated amyloid-beta and tau. The study aimed to characterize regional atrophy associated with elevated amyloid-beta and tau, as measured by [18F]florbetapir (FBP) and [18F]flortaucipir (FTP) positron emission tomography (PET), respectively, and determine whether combining PET and atrophy data improves the prediction of cognitive impairment. METHODS: Alzheimer Disease Neuroimaging Initiative data (n = 381) were retrospectively analyzed. PET results were correlated with cortical thickness, gray matter (GM) volumes, Mini-Mental State Examination, and Montreal Cognitive Assessment. Linear/logistic regression and area under the curve (AUC) were used to evaluate for significant correlations and compare performances in distinguishing cognitive impairment, respectively. RESULTS: Incremental loss of cortical thickness and GM volume was observed from FBP-/FTP- (n = 205) to single PET-positive (FBP+/FTP-, n = 133; FBP-/FTP+, n = 5) and FBP+/FTP+ (n = 38) groups, particularly in the temporal and parietal lobes. FBP+/FTP+ showed the most severe cortical thickness loss in the entorhinal cortex, temporal lobe GM atrophy, and cognitive impairment. Adding brain atrophy as the third variable resulted in higher odds ratios and improved AUCs for cognitive impairment, with FBP+/FTP+/temporal GM or entorhinal cortical atrophy+ demonstrating the strongest associations with cognitive impairment. CONCLUSION: A multimodal approach combining PET and MRI may help improve the assessment of cognitive impairment in AD.

This study aims to assess women's perceptions of artificial intelligence (AI) used in breast cancer screening in France by examining their knowledge of AI and the barriers to their participation in organized screening. The results of a survey conducted in June 2025 among a national sample of 2000 women (aged 40-75) reveal limited participation and persistent concerns among women. Nevertheless, despite a low awareness of specific AI applications, a large majority of the women surveyed are very favorable to the use of AI in breast cancer diagnosis, even considering it a lever to increase screening participation.

Introduction: Early hospital presentation after stroke onset is necessary for rapid assessment and access to time-dependent acute management. This study examined the correlates of late presentation for stroke care among patients recorded at a tertiary hospital in Ondo State, Nigeria. Methods: A retrospective records review was conducted using secondary data from the Stroke Registry of the University of Medical Sciences Teaching Hospital, radiology department records, referral notes, and ambulance records. Records of stroke cases documented within the preceding 24 months were reviewed. Late presentation was defined as hospital presentation more than four hours after symptom onset. Frequencies, chi-square tests, and modified Poisson regression with robust standard errors were used to estimate adjusted prevalence ratios. Results: The analysis included 371 stroke cases. Of these, 317 (85.4%) presented after four hours, and the median time to presentation was 24 hours (interquartile range: 9-72 hours). Late presentation differed significantly by employment status, first-contact route, and pathway complexity at bivariate analysis. After adjustment, non-hospital first contact remained strongly associated with late presentation: patients whose first documented contact was non-hospital-based had almost 3 times the prevalence of delay compared with those whose first contact was hospital-based (adjusted prevalence ratio = 2.89; 95% confidence interval: 2.15-3.90; p < 0.001). Conclusion: Late presentation was pervasive in this tertiary hospital record cohort and was primarily associated with the initial direction of care-seeking. Stroke response interventions should emphasise immediate hospital presentation and strengthen urgent referral from non-hospital first-contact points.

Introduction: Stroke care is time-sensitive, yet patients in low-resource settings may reach tertiary services only after passing through multiple formal and informal care options. This study examined documented care-seeking pathways and time to presentation among stroke cases recorded at the University of Medical Sciences Teaching Hospital (UNIMEDTH), Ondo State, Nigeria. Methods: A retrospective hospital record review was conducted using secondary data from the Stroke Registry, radiology department records, referral notes, and ambulance records at UNIMEDTH. The analysis included 371 stroke cases with documented time from symptom onset to UNIMEDTH presentation and reconstructable care pathways. First-contact routes were classified as hospital/biomedical, self/informal or traditional/faith-based care, and the number of documented steps defined pathway complexity before and including tertiary presentation. Frequencies and percentages described pathway patterns; median presentation times were compared using Mann-Whitney U and Kruskal-Wallis tests. Results: The median time to tertiary presentation was 24 hours (interquartile range [IQR] 9-72), and 317 patients (85.4%) presented after four hours. Only 30 patients (8.1%) presented directly to UNIMEDTH; 44 distinct care-pathway sequences were recorded. Hospital-facility first contact was documented for 81 patients (21.8%). It was associated with a median presentation time of 3 hours (IQR 2-6), compared with 48 hours (IQR 24-72) among patients whose initial contact was outside a hospital facility (U = 699.50, p < 0.001). The median time also differed across grouped first-contact categories and pathway complexity levels (both p < 0.001). Conclusion: Non-hospital or multi-step care-seeking pathways commonly preceded tertiary stroke presentations in this setting. The findings indicate that delayed tertiary arrival is partly embedded in the pathway followed after symptom onset. Interventions should combine public recognition of stroke warning signs with urgent referral linkages involving hospitals, patent medicine vendors, traditional and faith-based providers, and emergency transport systems.

Context: Although knee extensor and flexor strength deficits are well-documented after anterior cruciate ligament reconstruction, limited data exist characterizing how strength recovery evolves over time. Understanding the temporal patterns of recovery, and how they differ by autograft type, is critical for optimizing rehabilitation and return-to-sport decision-making. Objective: To characterize temporal trends in knee extensor and flexor strength recovery during the first year post-ACLR and evaluate differences between patellar tendon and hamstring tendon autografts. Design: Case series. Setting: Sports physical therapy clinics within a large health system. Participants: Five hundred three patients (17.8 {+/-} 3.0 y) who underwent primary reconstruction with either patellar tendon or hamstring tendon autografts and completed a combined 730 return-to-sport tests within 12 months postoperatively. Main Outcome Measures: Normalized peak isokinetic concentric knee extension and flexion torques for involved and uninvolved limbs, and normalized symmetry indices for knee extension and flexion strength. Results: Knee extension strength on both limbs and extension strength symmetry improved over time. Patients with hamstring autografts demonstrated superior involved leg knee extension strength and better extension strength symmetry compared with those receiving patellar tendon autografts, although uninvolved leg strength was similar between autografts. Knee flexion strength on both limbs and flexion strength symmetry also improved over time. Patellar tendon autograft patients exhibited greater strength symmetry, despite no between autografts for flexion strength for the involved or uninvolved limb. Conclusions: Autograft significantly influences muscle strength recovery following anterior cruciate ligament reconstruction. Hamstring tendon autografts are associated with superior recovery of knee extension strength and strength symmetry compared to patellar tendon autografts. These findings underscore the need for graft-specific rehabilitation strategies and earlier identification of patients at risk for delayed recovery.

Abstract Introduction In-hospital cardiac arrest carries high mortality despite standardized ACLS training. Educators face increasing time constraints in developing assessment tools for ACLS training. Two possible solutions to this problem are using pre-medical students or using artificial intelligence to generate test questions. This study compared the quality of pre-medical student-generated ACLS test questions vs. AI-generated ACLS test questions, testing the hypothesis that AI-generated questions are non-inferior to student-generated questions. Methods Ten pre-medical students created ACLS questions following predefined criteria, while an AI model (Northwell's Artificial Intelligence Hub) generated comparable questions. A blinded ACLS-certified physician evaluated questions on the qualities of Alignment, Clarity, Cognitive Level, and Question Design using a standardized rubric (Likert scale: 1 = poor quality, 5 = excellent). Student's T-test and Chi-square analysis were used to compare the quality of questions on different rubric domains within each arm (student vs. AI) and within one domain (eg, question Clarity) between arms. The Student's T test was used when 2 comparator groups were compared (eg, Clarity of student-generated vs. AI-generated questions) within one arm. The ANOVA test was used when comparing more than 2 comparator groups (eg, Alignment vs. Clarity vs. Cognitive Level) within one arm. Statistical significance was set as a priority at p <0.05. Results Both student-generated and AI-generated questions were of high quality. AI-generated questions achieved the maximum score in the domains of Alignment, Clarity, and Question Design, but fell short of perfect scores in the domain of Cognitive Level (8 of 50 questions were less than 5). Student-generated questions achieved less-than-perfect scores in each domain. No significant difference was found in overall mean question scores between groups (students = 4.79, AI = 4.81; p = 0.9). However, AI-generated questions had significantly-greater Clarity (students = 4.8, AI = 5; p = .0461), while Alignment, Cognitive level, and Question Design showed no significant differences. Conclusion AI-generated questions demonstrated overall quality comparable to those generated by pre-medical students, supporting the potential role of AI as a scalable tool in ACLS educational assessment development. Further studies are warranted to evaluate additional AI platforms and determine optimal integration of AI in medical education assessment design.

Background: Low-intensity focused ultrasound (LIFU) is an emerging noninvasive neuromodulation technique capable of targeting deep cortical and subcortical structures with high spatial precision. In healthy human volunteers, LIFU has demonstrated a favorable safety and tolerability profile across multiple studies. However, its safety and tolerability in clinical populations remains poorly characterized, representing a critical barrier to clinical translation. Here, we prospectively evaluate the safety and tolerability of LIFU targeting the left dorsal anterior insula (dAI) in patients with fibromyalgia (FM). Methods: In a single-blind, sham-controlled, within-subjects crossover design, 13 individuals with FM (43.1 +/- 13.2 years; 12 female) received 10 minutes of active LIFU (500 kHz, 1 kHz PRF, 36% duty cycle, 4.2 W/cm2 Isppa; 100 x 1-second pulse trains with a 5-second inter-train interval) targeting the left dorsal anterior insula (dAI) or sham on separate visits. Safety was evaluated through neuroradiological review of post vs. pre LIFU FLAIR MRI, quantitative voxel-wise FLAIR analysis, and patient report of symptoms (ROS). Tolerability was assessed using an experience assessment. Efficacy of the LIFU intervention was assessed using quantitative sensory testing (QST) including temporal summation of pain (TSP) and conditioned pain modulation (CPM). Results: Neuroradiological review identified no new evidence of edema, microhemorrhage, acute ischemia, or white matter injury on post-LIFU structural imaging. Quantitative FLAIR analysis using contralateral-mirror-referenced relative FLAIR (rFLAIR) showed no significant within-subject change in the stimulated beam volume (delta rFLAIR = 0.002 +/- 0.025, t(12) = 0.30, P = 0.769, Cohen's dz = 0.08). No serious adverse events were documented and ROS indicated no change due to LIFU sonication. Participants rated the procedure as comfortable and could not distinguish active from sham LIFU. LIFU did not result in statistically significant changes for TSP (p = 0.797) or CPM (p = 0.465). Conclusions: Ten minutes of LIFU targeting the left dAI was safe and well tolerated in individuals with FM, with no neuroradiological or quantitative MRI evidence of tissue effects and no serious adverse events. Blinding was preserved, and participants rated the procedure as comfortable. Although no significant changes were observed in experimental pain measures, these findings support the feasibility of targeting deep salience and pain amplification circuitry with LIFU in patients with FM and provide a foundation for adequately powered efficacy trials.

Objective. Figure copy and recall tests are sensitive measures of visuoconstruction and visual episodic memory, but their clinical is constrained by labor-intensive manual scoring. We developed and validated an automated, element-level scoring pipeline using Vertex AI object detection for the tablet-based figure copy and recall tasks in the California Cognitive Assessment Battery (CCAB). The automated scoring pipeline duplicated the scoring procedures used by expert manual raters. Methods. A normative sample of 2,011 community-dwelling adults aged 18-90 completed figure copy and delayed recall trials at baseline, with subsamples retested at 1 day and at 6, 18, and 30 months. Participants completed the drawings with their index finger on a tablet computer with finger position digitized to analyze the speed and timing of individual drawing strokes A convolutional object-detection model trained on the Vertex AI AutoML Vision platform identified each of twelve canonical figure elements in rendered drawings. Separate element presence and location scores were computed after homographically warping drawings onto a canonical template to produce trial-level Element, Location, and Total scores. To compare Vertex and human scores, Vertex AI and expert human raters independently scored 1500 randomly selected drawings to evaluate inter-rater agreement, including a common subset of 100 drawings scored by Vertex AI and all raters. Results. Total scores were virtually indistinguishable (r = 0.966) from human-human agreement (mean r = 0.971) as were Element presence scores (mean r = 0.959 vs. r = 0.963). Location-score agreement (r = 0.951) was slightly below the human-human mean (r = 0.972) due to pixel-level analysis by Vertex AI that was impossible for human raters. The Vertex pipeline showed no preferential advantage for the single expert rater who categorized Elements during training. Automated scores showed strong demographic gradients, age effects on Recall (r = -0.32) were approximately twice those in Copy conditions (r = -0.16). A Memory Cost score (Recall - Copy) showed a monotonic age-related decline from +0.40 z in the youngest subjects to -0.54 z in the oldest. Kinetic analysis revealed that drawing speed and efficiency showed significant age-related changes. Overnight test-retest reliability was high (Recall r = 0.72) and the Recall trial showed a large overnight learning effect ({Delta} = +1.18) that continued with repeated tests up to 30 months ({Delta} = +0.75).

Introduction: Reduced or lost sensation and movement after a spinal cord injury (SCI) impairs the brain s ability to accurately localize paralyzed body parts, causing deficits in its internal body map, or mental body representations (MBR). These deficits hinder functional recovery and contribute to neuropathic pain. Medications for neuropathic pain are often ineffective and carry side effects. Our pilot trials found that in-person Cognitive Multisensory Rehabilitation (CMR), a physical therapy restoring MBR, led to prolonged pain reduction, improved sensorimotor function, and enhanced brain function, to greater extent than adaptive fitness. To explore more accessible interventions for those in rural areas or with transportation challenges, we examined whether 12 weeks of remotely delivered CMR or exercise would (1) improve function and reduce pain; (2) increase brain activity and connectivity related to sensorimotor function and MBR in adults with SCI. Methods: Of 19 adults with SCI who consented, 15 (51+/-15 years old, 8+/-10 years post-SCI) were randomized to 12 weeks of remotely delivered CMR or exercise (45min, 3x/week). Eight reported neuropathic pain equal or greater than 3/10. The Numeric Pain Rating Scale (NPRS), ASIA Impairment Scale (AIS), and Neuromuscular Recovery Scale (NRS) assessed pain and sensorimotor function at baseline, post-intervention, and 6-month follow-up. Functional MRI included resting-state and four tasks: imagining feeling the left leg, imagining moving the left leg, whole-body movement imagery, and a sensation task. Results: After CMR (n=8), participants improved on AIS (large effect sizes: touch: d=1.30; pinprick: d=1.21; lower limb motor function: d=1.83). Exercise (n=7) produced smaller improvements (touch: d=0.35; pinprick: d=0.36; lower limb motor function: d=0.80). CMR showed greater NRS effect sizes (core: d=1.48; upper limb: d=0.69; lower limb: d=1.25) than exercise (core: d=0.31; upper limb: d=0.74; lower limb: d=0.83). Benefits persisted at follow-up for both AIS and NRS, especially in the CMR group. Highest neuropathic pain intensity decreased in both groups post-intervention (CMR: d=-0.61; exercise: d=-0.73) and at 6-month follow-up (CMR: d=-0.55; exercise: d=-0.55). Unlike previous studies, group effects for CMR were not found due to high heterogeneity. Increased task-based activation, including in the lateral occipital cortex involved in visual body perception and spatial awareness, was seen for the exercise group (n=5). Discussion: These preliminary results support the potential of remotely delivered CMR and exercise to improve function and reduce neuropathic pain in adults with SCI, highlighting the need for larger trials. Clinicaltrial.gov: NCT05870189

Background: Occupational therapists can improve stroke survivors hand and arm movement and participation in daily activities through action observation (AO). AO involves watching another persons hand or arm complete a movement or task. While research generally supports the use of AO with stroke survivors, there are limited AO videos are available to occupational therapists which makes applying AO challenging. Objective: The purpose of this work is to develop structured and widely accessible tool to support access to AO for stroke survivors, occupational therapists, and researchers. Methods: To develop an AO video library for stroke rehabilitation, functional and non-functional upper limb task deficits were first identified through clinical observations and clinician interviews to establish a prioritized list of daily activities. In collaboration with media production specialists, healthy adult volunteers were recruited and filmed performing these tasks from both first- and third-person perspectives. The recorded videos were then systematically edited, enhanced with instructional title slides, and distributed via a public YouTube channel for clinical application and a categorized digital repository for research purposes. Results: Initial assessments revealed a complete lack of familiarity, awareness, and utilization of AO resources among local occupational therapists, despite high perceived clinical utility. To address this gap, a final library of 150 tasks was established, resulting in the production of 419 finalized, standardized videos featuring six healthy volunteers. For clinical application, these videos were hosted on a free, public YouTube channel organized into 18 functional playlists, while a parallel set was structured into distinct movement categories for research repository storage. Conclusion: By providing a structured and highly accessible tool, this repository enables clinicians, researchers, and caregivers to readily implement evidence-based action observation interventions in both clinical and home settings.

Background. Definitive diagnosis of Hirschsprung's disease (HD) requires pathological identification of enteric ganglion cells. This process is time-consuming and subject to inter-observer variability. Artificial intelligence (AI) tools have the potential to standardize and accelerate this workflow, but no study has determined which AI approach best serves intraoperative HD pathology diagnostics. Method. This study compared the U-Net and You Only Look Once version 26 (YOLO26) frameworks for ganglion cell detection using a single-centre retrospective dataset of 54 whole-slide images (WSIs) from rectal biopsies. WSIs were tiled into 397,731 image patches (128x128 pixels), further partitioned into training (70%), validation (15%), and testing (15%) sets. Models were evaluated on tile- and patient-level diagnostic metrics and processing latency. Results. The U-Net achieved a tile-level sensitivity of 82.9%, showing no statistically significant difference compared to YOLO26 (79.1%; p = 0.097). However, YOLO26 demonstrated a statistically significant advantage in tile-level specificity (96.1% vs. 93.9%; p < 0.001) and reduced mean inference latency (7.64 ms vs. 11.57 ms/tile). At the patient level, both models achieved 100% diagnostic sensitivity. Despite low patient-level specificity (0.0% U-Net; 11.8% YOLO26), the tissue-level diagnostic burden of false positives was 6.00% for U-Net and 3.50% for YOLO26. Conclusion. The U-Net is preferred when nominal gains in sensitivity are prioritized, while the YOLO26 is an alternative that optimizes efficiency and false positive suppression. Both models serve as robust screening filters to augment the pathologist's workflow and should be selected based on workflow requirements. Prospective validation on larger, multi-centre datasets is required before clinical implementation.

Introduction Care home (CH) influenza vaccination of staff improves resident health, yet uptake remains low at just over 11% (England, 2025/2026). We report an economic evaluation (EE) of "FluCare", an intervention to increase staff influenza vaccination through: vaccination clinics at CHs; promotional materials; and CH financial incentives. Method Seventy-five CHs were randomised to FluCare or control. A cost-consequence analysis took the influenza vaccination programme funder perspective, but also extended to the National Health Service (NHS) and CH perspective. Costs included: influenza vaccination; administration fee; FluCare components; CH resident NHS utilisation. Outcomes were: staff influenza vaccination rates; staff sickness; and resident mortality. Sensitivity analyses excluded intervention CHs that did not host vaccination clinics. Results Compared to control CHs, adjusted analysis found intervention homes with a mean absolute increase in vaccination rates of 1.8% (95% CI: -6.0%, 10.8%; p=0.572) at an increased cost of {pound}451 (95% CI: {pound}239, {pound}675; p<0.001) to the vaccination programme funders: {pound}249 per additional percentage point (PAPP) per CH. Vaccination clinics were delivered late in the influenza season, with 80% taking place from February 2023. Including only intervention CHs that hosted staff flu vaccination clinics (23/35), increases the mean difference to 10.1% (95% CI: 0.9%, 21.9%; p=0.018) and costs to {pound}805 (95% CI: {pound}603, {pound}1,079; p<0.001): {pound}79 PAPP per CH. Differences between trial arms in other costs and outcomes were marginal and generally non-significant. Conclusions FluCare delivered little improvement when staff flu vaccination clinics did not occur and had little impact on other costs/outcomes. Cost-effectiveness depends on willingness-to-pay for increased staff vaccination, but cost PAPP per CH improved from {pound}249 to {pound}79 when only CHs hosting clinics were considered. Late implementation, likely reduced impact by limiting clinic delivery, as reflected in sensitivity analysis. Future evaluations should implement FluCare earlier in the season.