Dataset Information

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis.

ABSTRACT: Importance:The recent advances in the field of machine learning have raised expectations that computer-aided diagnosis will become the standard for the diagnosis of melanoma. Objective:To critically review the current literature and compare the diagnostic accuracy of computer-aided diagnosis with that of human experts. Data Sources:The MEDLINE, arXiv, and PubMed Central databases were searched to identify eligible studies published between January 1, 2002, and December 31, 2018. Study Selection:Studies that reported on the accuracy of automated systems for melanoma were selected. Search terms included melanoma, diagnosis, detection, computer aided, and artificial intelligence. Data Extraction and Synthesis:Evaluation of the risk of bias was performed using the QUADAS-2 tool, and quality assessment was based on predefined criteria. Data were analyzed from February 1 to March 10, 2019. Main Outcomes and Measures:Summary estimates of sensitivity and specificity and summary receiver operating characteristic curves were the primary outcomes. Results:The literature search yielded 1694 potentially eligible studies, of which 132 were included and 70 offered sufficient information for a quantitative analysis. Most studies came from the field of computer science. Prospective clinical studies were rare. Combining the results for automated systems gave a melanoma sensitivity of 0.74 (95% CI, 0.66-0.80) and a specificity of 0.84 (95% CI, 0.79-0.88). Sensitivity was lower in studies that used independent test sets than in those that did not (0.51; 95% CI, 0.34-0.69 vs 0.82; 95% CI, 0.77-0.86; P?

SUBMITTER: Dick V

PROVIDER: S-EPMC6584889 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis.

Dick Vincent V Sinz Christoph C Mittlböck Martina M Kittler Harald H Tschandl Philipp P

JAMA dermatology 20191101 11

<h4>Importance</h4>The recent advances in the field of machine learning have raised expectations that computer-aided diagnosis will become the standard for the diagnosis of melanoma.<h4>Objective</h4>To critically review the current literature and compare the diagnostic accuracy of computer-aided diagnosis with that of human experts.<h4>Data sources</h4>The MEDLINE, arXiv, and PubMed Central databases were searched to identify eligible studies published between January 1, 2002, and December 31, ...[more]

PMID: 31215969

Similar Datasets

Project description:BackgroundColonoscopy reduces the incidence of colorectal cancer (CRC) by allowing detection and resection of neoplastic polyps. Evidence shows that many small polyps are missed on a single colonoscopy. There has been a successful adoption of artificial intelligence (AI) technologies to tackle the issues around missed polyps and as tools to increase the adenoma detection rate (ADR).ObjectiveThe aim of this review was to examine the diagnostic accuracy of AI-based technologies in assessing colorectal polyps.MethodsA comprehensive literature search was undertaken using the databases of Embase, MEDLINE, and the Cochrane Library. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines were followed. Studies reporting the use of computer-aided diagnosis for polyp detection or characterization during colonoscopy were included. Independent proportions and their differences were calculated and pooled through DerSimonian and Laird random-effects modeling.ResultsA total of 48 studies were included. The meta-analysis showed a significant increase in pooled polyp detection rate in patients with the use of AI for polyp detection during colonoscopy compared with patients who had standard colonoscopy (odds ratio [OR] 1.75, 95% CI 1.56-1.96; P<.001). When comparing patients undergoing colonoscopy with the use of AI to those without, there was also a significant increase in ADR (OR 1.53, 95% CI 1.32-1.77; P<.001).ConclusionsWith the aid of machine learning, there is potential to improve ADR and, consequently, reduce the incidence of CRC. The current generation of AI-based systems demonstrate impressive accuracy for the detection and characterization of colorectal polyps. However, this is an evolving field and before its adoption into a clinical setting, AI systems must prove worthy to patients and clinicians.Trial registrationPROSPERO International Prospective Register of Systematic Reviews CRD42020169786; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42020169786.

Project description:PurposeThe present systematic review aimed to investigate the accuracy of zygomatic implant (ZI) placement using dynamic computer-aided surgery (d-CAIS), static computer-aided surgery (s-CAIS), and a free-hand approach in patients with severe atrophic edentulous maxilla and/or deficient maxilla.MethodsElectronic and manual literature searches until May 2023 were performed in the PubMed/Medline, Scopus, Cochrane Library, and Web of Science databases. Clinical trials and cadaver studies were selected. The primary outcome was planned/placed deviation. Secondary outcomes were to evaluate the survival of ZI and surgical complications. Random-effects meta-analyses were conducted and meta-regression was utilized to compare fiducial registration amounts for d-CAIS and the different designs of s-CAIS.ResultsA total of 14 studies with 511 ZIs were included (Nobel Biocare: 274, Southern Implant: 42, SIN Implant: 16, non-mentioned: 179). The pooled mean ZI deviations from the d-CAIS group were 1.81 mm (95% CI: 1.34-2.29) at the entry point and 2.95 mm (95% CI: 1.66-4.24) at the apex point, and angular deviations were 3.49 degrees (95% CI: 2.04-4.93). The pooled mean ZI deviations from the s-CAIS group were 1.19 mm (95% CI: 0.83-1.54) at the entry point and 1.80 mm (95% CI: 1.10-2.50) at the apex point, and angular deviations were 2.15 degrees (95% CI: 1.43-2.88). The pooled mean ZI deviations from the free-hand group were 2.04 mm (95% CI: 1.69-2.39) at the entry point and 3.23 mm (95% CI: 2.34-4.12) at the apex point, and angular deviations were 4.92 degrees (95% CI: 3.86-5.98). There was strong evidence of differences in the average entry, apex, and angular deviation between the navigation, surgical guide, and free-hand groups (p < 0.01). A significant inverse correlation was observed between the number of fiducial screws and the planned/placed deviation regarding entry, apex, and angular measurements.ConclusionUsing d-CAIS and modified s-CAIS for ZI surgery has shown clinically acceptable outcomes regarding average entry, apex, and angular deviations. The maximal deviation values were predominantly observed in the conventional s-CAIS. Surgeons should be mindful of potential deviations and complications regardless of the decision making in different guide approaches.

Dataset Information

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis.

Publications

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets