Citations

Abstract Aims Left ventricular hypertrophy (LVH) is a strong predictor of cardiovascular disease. We previously compared supervised machine learning techniques to classify cardiac magnetic resonance (CMR)-derived LVH using electrocardiogram (ECG) and clinical variables in 37 534 UK Biobank participants, obtaining an area under the receiving operating curve (AUROC) of 0.85, but with limited specificity and requiring external validation. In this study, we develop a deep learning (DL) model to improve classification with external evaluation in the Study of Health in Pomerania (SHIP). Methods and results We analysed 12-lead ECGs of 48 835 participants from the UK Biobank imaging study. The dataset was split into a training set (70%), validation set (15%), and test set (15%) for performance evaluation. The model architecture was a fully convolutional network, for which the input was the participants’ median ECG and clinical variables and the predicted indexed left ventricular mass (iLVM) as the output. A subsequent logistic regression model was used to recalibrate iLVM predictions. In UK Biobank, 717 (1.5%) participants had CMR-derived LVH and the AUROC for the DL model was 0.97. The ECG components most predictive of LVH were the QRS complex and ventricular rate. The DL model outperformed our supervised algorithms, previous DL modelling efforts and clinical ECG benchmarks. There was modest generalizability of the DL model to 1423 participants in SHIP (AUROC 0.78), with differences in clinical profile, ECG acquisition, and CMR labelling as important factors. Conclusion Our findings support the feasibility of scalable DL-based screening tools for the prediction of LVH from the ECG, whilst highlighting the need for model development using larger datasets with greater diversity to ensure generalizability.

Lay Summary This meta-analysis of 8 randomized controlled trials compares the effectiveness of using high-definition scopes with virtual chromoendoscopy vs dye chromoendoscopy for detecting dysplasia in inflammatory bowel disease patients. Overall, the odds of dysplasia detection were not significantly different between dye chromoendoscopy and virtual chromoendoscopy.

Abstract INTRODUCTION Understanding neuroinflammation across the Alzheimer's disease (AD) spectrum is essential to elucidate disease mechanisms and individualize therapy. METHODS Human microglial translocator protein (TSPO) expression under inflammatory stimuli was assessed by immunoblot experiments. Ninety‐six participants were enrolled across four groups: cognitively unimpaired amyloid (CU A) + and −, mild cognitive impaired (MCI) A+, and Alzheimer's disease dementia (ADD) A+. Neuroinflammation using 11 C‐ER176 TSPO positron emission tomography (PET) was compared to amyloid and tau PET. Correlations between neuroinflammation, amyloid, and tau pathology were examined across disease stages. RESULTS TSPO was upregulated in human microglia under AD‐like inflammatory conditions. Neuroinflammation, defined by PET TSPO, increased in CU A+ participants and became more widespread with increasing disease severity, aligning with worsening amyloid and tau pathology. Associations with tau were particularly extensive in temporal and parietal regions. DISCUSSION These findings suggest probable amyloid association with early microglial activation, while tau pathology is closely tied to wider distribution of neuroinflammation. Highlights TSPO expression increases in human microglia under AD‐like inflammation. 11 C‐ER176 PET shows stage‐dependent neuroinflammation across the AD spectrum. Neuroinflammation overlaps with tau and is more widespread in amyloid‐positive individuals. Activity peaks in MCI, stabilizes later, and relates to vascular and neurodegenerative changes.

The iStent series constitutes a range of trabecular bypass minimally invasive glaucoma surgery (MIGS) devices, which offers intraocular pressure (IOP) reduction with favourable safety profiles, in patients with open-angle glaucoma (OAG). Having undergone significant evolution since its initial US FDA-approval in 2012, successive generations address previous limitations, while enhancing IOP-lowering efficacy through device and delivery system design iterations. Longer-term and real-world iStent data demonstrate the durability of IOP- and medication-lowering outcomes with minimal complications, while preliminary studies across a wider spectrum of glaucoma subtypes and severities provide limited evidence of successful outcomes beyond mild-to-moderate OAG, both with and without concomitant cataract surgery. Aqueous humour outflow assessment and novel intra-operative techniques may further facilitate more accurate and effective iStent positioning. Despite typically higher upfront costs, results from both cost-effectiveness and patient-reported outcome studies are encouraging. Combination MIGS with the iStent, leveraging on the multiple mechanisms of actions of various procedures, may provide greater IOP-lowering efficacy without compromising safety. With expanding clinical data and progressive enhancements, iStent technology is likely to remain a key component of the evolving MIGS landscape.

BACKGROUND & OBJECTIVE Sleep-disordered breathing (SDB) may be a remediable contributor to abnormal cognitive outcomes for children with myelomeningocele. We investigated the frequency of SDB among neonates with fetal vs postnatal myelomeningocele repair. METHODS In this nine-center, prospective, observational study, neonates with myelomeningocele born at more than 30 weeks gestational age underwent a 10-hour bedside polysomnogram at at least 35 weeks postmenstrual age, before hospital discharge. The primary outcome was SDB severity, reflected by the apnea-hypopnea index (AHI; number of respiratory events per hour of sleep). Decisions regarding surgical timing (fetal vs postnatal), technique (open fetal vs fetoscopic approach), and SDB treatment were made by the clinical teams. RESULTS Among 173 infants, 92/173 (53%) had SDB (median AHI 22.5, IQR 12.2–44.2). In unadjusted analysis, AHI was higher among the 90 neonates with fetal repair vs 83 with postnatal surgery (median 29, IQR 14–49, vs 19, IQR 10–36, P = .008). In propensity-adjusted multivariable models, prematurity was independently associated with AHI, whereas surgical timing (fetal vs postnatal) was not. Hindbrain herniation, myelomeningocele level, and clinical need for ventriculoperitoneal shunt did not predict AHI in adjusted models. Supplemental oxygen was commonly prescribed, for 44% of fetal vs 39% of postnatal myelomeningocele repair infants (P = .5). CONCLUSIONS SDB affects more than half of neonates with myelomeningocele. The higher AHI after fetal surgery could stem from the elevated incidence of prematurity in this group. As SDB is treatable and has a potential impact on neurodevelopment, routine screening could become an integral part of a strategy to optimize long-term medical and neurodevelopmental outcomes.