Objective: To measure accuracy and reliability of the computer-based Retinal Image Multiscale Analysis (RISA) system compared with those of recognized retinopathy of prematurity (ROP) experts, for plus disease diagnosis.
Design: Evaluation of diagnostic test or technology.
Participants: Eleven recognized ROP experts and the RISA image analysis system interpreted a set of 20 wide-angle retinal photographs for presence of plus disease.
Methods: All experts used a secure Web site to review independently 20 images for presence of plus disease. Images were also analyzed by measuring individual computer-based system parameters (integrated curvature [IC], diameter, and tortuosity index) for arterioles and venules and by computing linear combinations and logical combinations of those parameters. Performance was compared with a reference standard, defined as the majority vote of experts.
Main Outcome Measures: Diagnostic accuracy was measured by calculating sensitivity, specificity, and receiver operating characteristic area under the curve (AUC) for plus disease diagnosis by each expert, and by each computer-based system parameter, compared with the reference standard. Diagnostic agreement was measured by calculating the mean kappa value of each expert compared with all other experts and the mean kappa value of each computer-based system parameter compared with all experts.
Results: Among the 11 experts, sensitivity ranged from 0.167 to 1.000, specificity ranged from 0.714 to 1.000, AUC ranged from 0.798 to 1.000, and mean kappa compared with all other experts ranged from 0.288 to 0.689. Among individual computer system parameters, arteriolar IC had the highest diagnostic accuracy, with sensitivity of 1.000; specificity, 0.846; and AUC, 0.962. Arteriolar IC had the highest diagnostic agreement with experts, with a mean kappa value of 0.578.
Conclusions: A computer-based image analysis system has the potential to perform comparably to recognized ROP experts for plus disease diagnosis.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ophtha.2007.10.006 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Safety and efficacy of intrathecal antibodies to Nogo-A in patients with acute cervical spinal cord injury: a randomised, double-blind, multicentre, placebo-controlled, phase 2b trial.
Lancet Neurol
January 2025
Spinal Cord Injury Center, Balgrist University Hospital, University of Zurich, Zurich, Switzerland.
Background: Spinal cord injury results in permanent neurological impairment and disability due to the absence of spontaneous regeneration. NG101, a recombinant human antibody, neutralises the neurite growth-inhibiting protein Nogo-A, promoting neural repair and motor recovery in animal models of spinal cord injury. We aimed to evaluate the efficacy of intrathecal NG101 on recovery in patients with acute cervical traumatic spinal cord injury.
View Article and Find Full Text PDFAutomated Computerized-Based Intervention to Identify Hypomagnesemia in Primary Care Patients With Arrhythmia.
J Patient Saf
December 2024
Department of Radiology, University of Missouri, Columbia, Missouri.
Objectives: Hypomagnesemia early diagnosis and consequently early, timely magnesium supplementation is of utmost benefit, but it often goes underdiagnosed. The objective was to show and monitor an intervention to identify hypomagnesemia in patients with arrhythmia.
Methods: A cross-sectional study was designed in the laboratory.
A virtual patient authoring tool for transcatheter aortic valve replacement.
Int J Comput Assist Radiol Surg
December 2024
Faculty of Computer Science, University of Magdeburg, Magdeburg, Germany.
Purpose: Computer-based medical training scenarios, derived from patient's records, often lack variability, modifiability, and availability. Furthermore, generating image datasets and creating scenarios is resource-intensive. Therefore, patient authoring tools for rapid dataset-independent creation of virtual patients (VPs) is a pressing need.
View Article and Find Full Text PDFNurse-Led Interventions for Improving Medication Adherence in Chronic Diseases: A Systematic Review.
Healthcare (Basel)
November 2024
Department of Public Health and Pediatrics, University of Torino, 10126 Torino, Italy.
: Poor medication adherence results in negative health outcomes and increased healthcare costs. Several healthcare professionals provide interventions to improve medication adherence, with the effectiveness of nurse-led interventions in people with chronic diseases remaining unclear. : This study sought to evaluate the effectiveness of nurse-led interventions for improving medication adherence in adults with chronic conditions.
View Article and Find Full Text PDFThe effect of computer-based Stress Inoculation Training (SIT) approach on the pelvic pain, depression, and anxiety in students with primary dysmenorrhea: a clinical trial study.
BMC Med Educ
December 2024
Social Determinants of Health Research Center, Health Research Institute, Department of Nursing and Midwifery, Babol University of Medical Sciences, Babol, Iran.
Background: Primary dysmenorrhea (PD) is one of the most common pains experienced by women. Stress Inoculation Training (SIT) is a cognitive-behavioral technique that immunizes them against future periods of stress. The purpose of this research is to investigate the effectiveness of a computer-based stress inoculation approach on pelvic pain, depression, and anxiety symptoms in students with PD.
View Article and Find Full Text PDFWant 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!