scholarly journals Assessing the Performance of Artificial Intelligence Systems for the Screening of Diabetic Retinopathy: A Systematic Review and Meta-Analysis

2021 ◽  
Author(s):  
Ryan Sadjadi
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Meta Analysis ◽  
External Validation ◽  
Healthcare Providers ◽  
Vitreoretinal Surgery ◽  
Retinal Fundus ◽  
Screening Systems

Diabetic retinopathy is the most common microvascular complication of diabetes mellitus and one of the leading causes of blindness globally. Due to the progressive nature of the disease, earlier detection and timely treatment can lead to substantial reductions in the incidence of irreversible vision-loss. Artificial intelligence (AI) screening systems have offered clinically acceptable and quicker results in detecting diabetic retinopathy from retinal fundus and optical coherence tomography (OCT) images. Thus, this systematic review and meta-analysis of relevant investigations was performed to document the performance of AI screening systems that were applied to fundus and OCT images of patients from diverse geographic locations including North America, Europe, Africa, Asia, and Australia. A systematic literature search on Medline, Global Health, and PubMed was performed and studies published between October 2015 and January 2020 were included. The search strategy was based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines, and AI-based investigations were mandatory for studies inclusion. The abstracts, titles, and full-texts of potentially eligible studies were screened against inclusion and exclusion criteria. Twenty-one studies were included in this systematic review; 18 met inclusion criteria for the meta-analysis. The pooled sensitivity of the evaluated AI screening systems in detecting diabetic retinopathy was 0.93 (95% CI: 0.92-0.94) and the specificity was 0.88 (95% CI: 0.86-0.89). The included studies detailed training and external validation datasets, criteria for diabetic retinopathy case ascertainment, imaging modalities, DR-grading scales, and compared AI results to those of human graders (e.g., ophthalmologists, retinal specialists, trained nurses, and other healthcare providers) as a reference standard. The findings of this study showed that the majority AI screening systems demonstrated clinically acceptable levels of sensitivity and specificity for detecting referable diabetic retinopathy from retinal fundus and OCT photographs. Further improvement depends on the continual development of novel algorithms with large and gradable sets of images for training and validation. If cost-effectiveness ratios can be optimized, AI can become a financially sustainable and clinically effective intervention that can be incorporated into the healthcare systems of low-to-middle income countries (LMICs) and geographically remote locations. Combining screening technologies with treatment interventions such as anti-VEGF therapy, acellular capillary laser treatment, and vitreoretinal surgery can lead to substantial reductions in the incidence of irreversible vision-loss due to proliferative diabetic retinopathy.

scholarly journals Prevalence of retinopathy in prediabetes: protocol for a systematic review and meta-analysis

BMJ Open ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. e040997
Author(s):  
Varo Kirthi ◽  
Paul Nderitu ◽  
Uazman Alam ◽  
Jennifer Evans ◽  
Sarah Nevitt ◽  
...  
Keyword(s):  
Systematic Review ◽  
Diabetic Retinopathy ◽  
Data Extraction ◽  
Meta Analysis ◽  
International Diabetes Federation ◽  
Current Data ◽  
Risk Of Bias ◽  
Fundus Photography ◽  
Primary Data ◽  
Cochrane Library

IntroductionThere is growing evidence of a higher than expected prevalence of retinopathy in prediabetes. This paper presents the protocol of a systematic review and meta-analysis of retinopathy in prediabetes. The aim of the review is to estimate the prevalence of retinopathy in prediabetes and to summarise the current data.Methods and analysisThis protocol is developed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols (PRISMA-P) guidelines. A comprehensive electronic bibliographic search will be conducted in MEDLINE, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Google Scholar and the Cochrane Library. Eligible studies will report prevalence data for retinopathy on fundus photography in adults with prediabetes. No time restrictions will be placed on the date of publication. Screening for eligible studies and data extraction will be conducted by two reviewers independently, using predefined inclusion criteria and prepiloted data extraction forms. Disagreements between the reviewers will be resolved by discussion, and if required, a third (senior) reviewer will arbitrate.The primary outcome is the prevalence of any standard features of diabetic retinopathy (DR) on fundus photography, as per International Clinical Diabetic Retinopathy Severity Scale (ICDRSS) classification. Secondary outcomes are the prevalence of (1) any retinal microvascular abnormalities on fundus photography that are not standard features of DR as per ICDRSS classification and (2) any macular microvascular abnormalities on fundus photography, including but not limited to the presence of macular exudates, microaneurysms and haemorrhages. Risk of bias for included studies will be assessed using a validated risk of bias tool for prevalence studies. Pooled estimates for the prespecified outcomes of interest will be calculated using random effects meta-analytic techniques. Heterogeneity will be assessed using the I2 statistic.Ethics and disseminationEthical approval is not required as this is a protocol for a systematic review and no primary data are to be collected. Findings will be disseminated through peer-reviewed publications and presentations at national and international meetings including Diabetes UK, European Association for the Study of Diabetes, American Diabetes Association and International Diabetes Federation conferences.PROSPERO registration numberCRD42020184820.

scholarly journals Person-Centered Care in Persons Living with Dementia: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Kyung Hee Lee ◽  
Ji Yeon Lee ◽  
Bora Kim
Keyword(s):  
Systematic Review ◽  
Cognitive Function ◽  
Effect Size ◽  
Psychological Symptoms ◽  
Meta Analysis ◽  
Healthcare Providers ◽  
Clinical Excellence ◽  
Dementia Care ◽  
Person Centered Care ◽  
Centered Care

Abstract Background and Objectives The concept of person-centered care has been utilized/adapted to various interventions to enhance health-related outcomes and ensure the quality of care delivered to persons living with dementia. A few systematic reviews have been conducted on the use of person-centered interventions in the context of dementia care, but to date, none have analyzed intervention effect by intervention type and target outcome. This study aimed to review person-centered interventions used in the context of dementia care and examine their effectiveness. Research Design and Methods A systematic review and meta-analysis were conducted. We searched through five databases for randomized controlled trials that utilized person-centered interventions in persons living with dementia from 1998 to 2019. Study quality was assessed using the National Institute for Health and Clinical Excellence. The outcomes of interest for the meta-analysis were behavioral and psychological symptoms in dementia (BPSD) and cognitive function assessed immediately after the baseline measurement. Results In total, 36 studies were systematically reviewed. Intervention types were: reminiscence, music, and cognitive therapies, and multisensory stimulation. Thirty studies were included in the meta-analysis. Results showed a moderate effect size for overall intervention, a small one for music therapy, and a moderate one for reminiscence therapy on BPSD and cognitive function. Discussion and Implications Generally speaking, person-centered interventions showed immediate intervention effects on reducing BPSD and improving cognitive function, although the effect size and significance of each outcome differed by intervention type. Thus, healthcare providers should consider person-centered interventions as a vital element in dementia care.

scholarly journals Systematic review protocol to assess artificial intelligence diagnostic accuracy performance in detecting acute ischaemic stroke and large-vessel occlusions on CT and MR medical imaging

BMJ Open ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. e043665
Author(s):  
Srinivasa Rao Kundeti ◽  
Manikanda Krishnan Vaidyanathan ◽  
Bharath Shivashankar ◽  
Sankar Prasad Gorthi
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Diagnostic Accuracy ◽  
Ischaemic Stroke ◽  
Study Protocol ◽  
Systematic Reviews ◽  
Acute Ischaemic Stroke ◽  
Meta Analysis ◽  
Large Vessel ◽  
Sufficient Data

IntroductionThe use of artificial intelligence (AI) to support the diagnosis of acute ischaemic stroke (AIS) could improve patient outcomes and facilitate accurate tissue and vessel assessment. However, the evidence in published AI studies is inadequate and difficult to interpret which reduces the accountability of the diagnostic results in clinical settings. This study protocol describes a rigorous systematic review of the accuracy of AI in the diagnosis of AIS and detection of large-vessel occlusions (LVOs).Methods and analysisWe will perform a systematic review and meta-analysis of the performance of AI models for diagnosing AIS and detecting LVOs. We will adhere to the Preferred Reporting Items for Systematic Reviews and Meta-analyses Protocols guidelines. Literature searches will be conducted in eight databases. For data screening and extraction, two reviewers will use a modified Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies checklist. We will assess the included studies using the Quality Assessment of Diagnostic Accuracy Studies guidelines. We will conduct a meta-analysis if sufficient data are available. We will use hierarchical summary receiver operating characteristic curves to estimate the summary operating points, including the pooled sensitivity and specificity, with 95% CIs, if pooling is appropriate. Furthermore, if sufficient data are available, we will use Grading of Recommendations, Assessment, Development and Evaluations profiler software to summarise the main findings of the systematic review, as a summary of results.Ethics and disseminationThere are no ethical considerations associated with this study protocol, as the systematic review focuses on the examination of secondary data. The systematic review results will be used to report on the accuracy, completeness and standard procedures of the included studies. We will disseminate our findings by publishing our analysis in a peer-reviewed journal and, if required, we will communicate with the stakeholders of the studies and bibliographic databases.PROSPERO registration numberCRD42020179652.

scholarly journals Plasma microRNA signature associated with retinopathy in patients with type 2 diabetes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Donato Santovito ◽  
Lisa Toto ◽  
Velia De Nardis ◽  
Pamela Marcantonio ◽  
Rossella D’Aloisio ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
External Validation ◽  
Diabetic Patients ◽  
Disease Biomarkers ◽  
Response To Stress ◽  
Severity Of The Disease ◽  
Plasma Microrna

AbstractDiabetic retinopathy (DR) is a leading cause of vision loss and disability. Effective management of DR depends on prompt treatment and would benefit from biomarkers for screening and pre-symptomatic detection of retinopathy in diabetic patients. MicroRNAs (miRNAs) are post-transcriptional regulators of gene expression which are released in the bloodstream and may serve as biomarkers. Little is known on circulating miRNAs in patients with type 2 diabetes (T2DM) and DR. Here we show that DR is associated with higher circulating miR-25-3p (P = 0.004) and miR-320b (P = 0.011) and lower levels of miR-495-3p (P < 0.001) in a cohort of patients with T2DM with DR (n = 20), compared with diabetic subjects without DR (n = 10) and healthy individuals (n = 10). These associations persisted significant after adjustment for age, gender, and HbA1c. The circulating levels of these miRNAs correlated with severity of the disease and their concomitant evaluation showed high accuracy for identifying DR (AUROC = 0.93; P < 0.001). Gene ontology analysis of validated targets revealed enrichment in pathways such as regulation of metabolic process (P = 1.5 × 10–20), of cell response to stress (P = 1.9 × 10–14), and development of blood vessels (P = 2.7 × 10–14). Pending external validation, we anticipate that these miRNAs may serve as putative disease biomarkers and highlight novel molecular targets for improving care of patients with diabetic retinopathy.

An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-24
Author(s):  
Mohammad Shorfuzzaman ◽  
M. Shamim Hossain ◽  
Abdulmotaleb El Saddik
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Vision Loss ◽  
Final Diagnosis ◽  
Learning Rate ◽  
Ensemble Model ◽  
Fundus Images ◽  
Robust Detection ◽  
Retinal Fundus Images ◽  
Retinal Fundus

Diabetic retinopathy (DR) is one of the most common causes of vision loss in people who have diabetes for a prolonged period. Convolutional neural networks (CNNs) have become increasingly popular for computer-aided DR diagnosis using retinal fundus images. While these CNNs are highly reliable, their lack of sufficient explainability prevents them from being widely used in medical practice. In this article, we propose a novel explainable deep learning ensemble model where weights from different models are fused into a single model to extract salient features from various retinal lesions found on fundus images. The extracted features are then fed to a custom classifier for the final diagnosis of DR severity level. The model is trained on an APTOS dataset containing retinal fundus images of various DR grades using a cyclical learning rates strategy with an automatic learning rate finder for decaying the learning rate to improve model accuracy. We develop an explainability approach by leveraging gradient-weighted class activation mapping and shapely adaptive explanations to highlight the areas of fundus images that are most indicative of different DR stages. This allows ophthalmologists to view our model's decision in a way that they can understand. Evaluation results using three different datasets (APTOS, MESSIDOR, IDRiD) show the effectiveness of our model, achieving superior classification rates with a high degree of precision (0.970), sensitivity (0.980), and AUC (0.978). We believe that the proposed model, which jointly offers state-of-the-art diagnosis performance and explainability, will address the black-box nature of deep CNN models in robust detection of DR grading.

Sign in / Sign up

Export Citation Format

Share Document