We present a model for describing correlated binocular data from reader-based diagnostic studies, where the same group of readers evaluates the presence or absence of certain diseases on binocular organs (e.g., fellow eyes) of patients. Multiple random effects are incorporated to meaningfully delineate various associations in the data including crossed random effects to account for reader-specific variability and to incorporate cross correlations. To overcome the computational complexity involved in the evaluation and maximization of the marginal likelihood, we adopt the data cloning approach, which calculates maximum likelihood estimates under the Bayesian paradigm. The bias and efficiency of the estimates are assessed in two simulation studies. We apply our model to data from a diabetic retinopathy study.

Download full-text PDF

Source
http://dx.doi.org/10.1002/sim.6584DOI Listing

Publication Analysis

Top Keywords

random effects
12
crossed random
8
reader-based diagnostic
8
data cloning
8
data
6
joint estimation
4
estimation multiple
4
multiple disease-specific
4
disease-specific sensitivities
4
sensitivities specificities
4

Similar Publications

The optimal endovascular management of cervical carotid dissection causing tandem occlusion remains uncertain. We investigated the impact of emergent carotid stenting during endovascular treatment (EVT) for acute ischemic stroke (AIS) in patients with tandem occlusion secondary to cervical carotid artery dissection. This was a secondary analysis of patients treated with EVT for AIS due to occlusive carotid artery dissection and tandem occlusion included in the retrospective international Antithrombotic Treatment for Stroke Prevention in Cervical Artery Dissection (STOP-CAD) study.

View Article and Find Full Text PDF

Background: Remote ischemic conditioning (RIC) is a simple and low-cost intervention that is thought to increase collateral blood flow through the vasodilatory effects of nitric oxide (NO) produced by the endothelium and red blood cells (RBCs). This study aims to investigate whether RIC affects RBC deformability and levels of NO and nitrite in patients with ischemic stroke.

Methods: This is a predefined substudy to the RESIST (Remote Ischemic Conditioning in Patients With Acute Stroke Trial) randomized clinical trial conducted in Denmark.

View Article and Find Full Text PDF

Ultra-Early Hematoma Expansion Is Associated With Ongoing Hematoma Growth and Poor Functional Outcome.

Stroke

January 2025

Departments of Medicine and Neurology, Melbourne Brain Centre @ The Royal Melbourne Hospital, University of Melbourne, AUSTRALIA.

There is limited data on ultra-early hematoma growth dynamics and its clinical relevance in primary intracerebral hemorrhage (ICH). We aimed to estimate the incidence of hematoma expansion (HE) within the hyperacute period of ICH, describe hematoma dynamics over time, investigate the associations between ultra-early HE and clinical outcomes after ICH, and assess the effect of tranexamic acid on ultra-early HE. We performed a planned secondary analysis of the STOP-MSU international multicenter randomized controlled trial.

View Article and Find Full Text PDF

Background: A minority of patients with stroke qualify for intravenous thrombolysis (IVT) within 4.5-hour window. The safety and efficacy of IVT beyond this period have not been well studied.

View Article and Find Full Text PDF

Background: Ventricular arrhythmias (VAs) frequently occur in the acute phase of myocarditis. Possible arrhythmic recurrences and the risk of sudden cardiac death (SCD) in this setting are reasons for concern, and limited data have been published to guide clinical management of these patients. The aim of the present paper is to report the incidence of major arrhythmic events, defined as sustained VA, SCD and appropriate implantable cardiac-defibrillator (ICD) treatment, in patients with acute myocarditis and ventricular arrhythmic phenotype.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!