Aims: To systematically evaluate the diagnostic value of an artificial intelligence (AI) algorithm model for various types of diabetic retinopathy (DR) in prospective studies over the previous five years, and to explore the factors affecting its diagnostic effectiveness.
Materials And Methods: A search was conducted in Cochrane Library, Embase, Web of Science, PubMed, and IEEE databases to collect prospective studies on AI models for the diagnosis of DR from January 2017 to December 2022. We used QUADAS-2 to evaluate the risk of bias in the included studies. Meta-analysis was performed using MetaDiSc and STATA 14.0 software to calculate the combined sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of various types of DR. Diagnostic odds ratios, summary receiver operating characteristic (SROC) plots, coupled forest plots, and subgroup analysis were performed according to the DR categories, patient source, region of study, and quality of literature, image, and algorithm.
Results: Finally, 21 studies were included. Meta-analysis showed that the pooled sensitivity, specificity, pooled positive likelihood ratio, pooled negative likelihood ratio, area under the curve, Cochrane Q index, and pooled diagnostic odds ratio of AI model for the diagnosis of DR were 0.880 (0.875-0.884), 0.912 (0.99-0.913), 13.021 (10.738-15.789), 0.083 (0.061-0.112), 0.9798, 0.9388, and 206.80 (124.82-342.63), respectively. The DR categories, patient source, region of study, sample size, quality of literature, image, and algorithm may affect the diagnostic efficiency of AI for DR.
Conclusion: AI model has a clear diagnostic value for DR, but it is influenced by many factors that deserve further study.
Systematic Review Registration: https://www.crd.york.ac.uk/prospero/, identifier CRD42023389687.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10296189 | PMC |
| http://dx.doi.org/10.3389/fendo.2023.1197783 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Cost-effectiveness of camrelizumab plus rivoceranib for advanced hepatocellular carcinoma in the context of regional disparities in China.
Front Oncol
December 2024
Department of Oncology, Binzhou Medical University Hospital, Binzhou, Shandong, China.
Objective: To assess the cost-effectiveness of combining camrelizumab with rivoceranib versus sorafenib as initial treatment options for advanced hepatocellular carcinoma (HCC) across different developmental regions in China.
Methods: Utilizing TreeAge Pro and data from the phase III randomized CARES-310 clinical trial, a model based on Markov state transitions was developed. Health state utility values were derived from the CARES-310 trial, and direct medical costs were obtained from relevant literature and local pricing data.
Intra-arterial cocktail therapy for patients with anterior circulation large vessel occlusion who achieved endovascular reperfusion.
Front Neurol
December 2024
Department of Neurology, General Hospital of Northern Theater Command, Shenyang, China.
Background: Clinically ineffective reperfusion (CIR) refers to the discrepancy between successful reperfusion and a favorable functional outcome in patients with large vessel occlusion (LVO) stroke after endovascular treatment (EVT). The Improving Neuroprotective Strategy for Ischemic Stroke with Sufficient Recanalization after Thrombectomy by Intra-arterial Cocktail Therapy (INSIST-CT) trial aimed to explore the safety, feasibility, and efficacy of intra-arterial cocktail therapy using argatroban, dexamethasone, and edaravone in patients who achieved sufficient reperfusion after EVT.
Methods: In this prospective, single-arm, pilot study, eligible patients with anterior circulation LVO who achieved sufficient reperfusion after EVT were enrolled in the INSIST-CT trial.
Background: The geroscience hypothesis posits that aging biological processes contribute to many age-related deficits, including the accumulation of multiple chronic diseases. Though only one facet of mitochondrial function, declines in muscle mitochondrial bioenergetic capacities may contribute to this increased susceptibility to multimorbidity.
Methods: The Study of Muscle, Mobility and Aging (SOMMA) assessed muscle mitochondrial energetics in 764 older adults (mean age =76.
Background: The increasing clinical use of combining structural MRI (sMRI) with General Movements Assessment (GMA) or Hammersmith Infant Neurological Exam (HINE) before five months corrected age (CA) for early diagnosis of cerebral palsy (CP) lacks sufficient prognostic data for children with CP, especially those with Gross Motor Function Classification System (GMFCS) I.
Objective: Evaluate the predictive value of sMRI, GMA, and HINE individually and in combination for early CP diagnosis and assess accuracy across varying GMFCS levels in a regional cohort of preterm infants.
Methods: We performed sMRI between 39-44 weeks postmenstrual age and GMA and HINE between 12-18 weeks CA in 395 preterm infants born at ≤32 weeks' gestation across five NICUs in Greater Cincinnati.
Objectives: The number of mosquito bites a person receives determines the risk of acquiring malaria and the likelihood of transmitting infections to mosquitoes. We assessed heterogeneity in biting and associated factors in two settings in Uganda with different endemicity.
Methods: parasites in blood-fed indoor caught mosquitoes were quantified using qPCR targeting the Pf18S rRNA gene.
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!