Dataset Information

Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis.

ABSTRACT:

Background

Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models.

Objective

To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images.

Methods

We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed.

Results

Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected.

Conclusions

CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.

SUBMITTER: Bang CS

PROVIDER: S-EPMC8715364 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundRecent data imply young patients (age ≤50 years) undergoing small-bowel (SB) capsule endoscopy (CE) for iron deficiency anaemia (IDA) show higher diagnostic yield (DY) for sinister pathology. We aimed to investigate DY of CE in a large cohort of young IDA patients, and evaluate factors predicting significant SB pathology.Materials and methodsThis was a retrospective, multicentre study (2010-2015) in consecutive, young patients (≤50 years) from 18 centres/12 countries, with negative bidirectional gastrointestinal (GI) endoscopy undergoing SBCE for IDA. Exclusion criteria: previous/ongoing obscure-overt GI bleeding; age <19 or >50 years; comorbidities associated with IDA. Data retrieved: SBCE indications; prior investigations; medications; SBCE findings; final diagnosis. Clinical and laboratory data were analysed by multivariate logistic regression.ResultsData on 389 young IDA patients were retrieved. In total, 169 (43.4%) were excluded due to incomplete clinical data; data from 220 (122F/98M; mean age 40.5 ± 8.6 years) patients were analysed. Some 71 patients had at least one clinically significant SBCE finding (DY: 32.3%). They were divided into two groups: neoplastic pathology (10/220; 4.5%), and non-neoplastic but clinically significant pathology (61/220; 27.7%). The most common significant but non-neoplastic pathologies were angioectasias (22/61) and Crohn's disease (15/61). On multivariate analysis, weight loss and lower mean corpuscular volume(MCV) were associated with significant SB pathology (OR: 3.87; 95%CI: 1.3-11.3; p = 0.01; and OR: 0.96; 95%CI: 0.92-0.99; p = 0.03; respectively). Our model also demonstrates association between use of antiplatelets and significant SB pathology, although due to the small number of patients, definitive conclusions cannot be drawn.ConclusionIn IDA patients ≤50 years with negative bidirectional GI endoscopy, overall DY of SBCE for clinically significant findings was 32.3%. Some 5% of our cohort was diagnosed with SB neoplasia; lower MCV or weight loss were associated with higher DY for SB pathology.