Dataset Information

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

ABSTRACT: Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children's diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence diabetic eye exam at the point of care), or control (scripted eye care provider referral and education) in an academic pediatric diabetes center. The primary outcome was diabetic eye exam completion rate within 6 months. The secondary outcome was the proportion of participants who completed follow-through with an eye care provider if deemed appropriate. Diabetic eye exam completion rate was significantly higher (100%, 95%CI: 95.5%, 100%) in the intervention group (n = 81) than the control group (n = 83) (22%, 95%CI: 14.2%, 32.4%)(p < 0.001). In the intervention arm, 25/81 participants had an abnormal result, of whom 64% (16/25) completed follow-through with an eye care provider, compared to 22% in the control arm (p < 0.001). Autonomous AI increases diabetic eye exam completion rates in youth with diabetes.

SUBMITTER: Wolf RM

PROVIDER: S-EPMC10784572 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

Wolf Risa M RM Channa Roomasa R Liu T Y Alvin TYA Zehra Anum A Bromberger Lee L Patel Dhruva D Ananthakrishnan Ajaykarthik A Brown Elizabeth A EA Prichett Laura L Lehmann Harold P HP Abramoff Michael D MD

Nature communications 20240111 1

Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children's diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence dia ...[more]

PMID: 38212308

Similar Datasets

Project description:ImportanceDiabetic retinopathy (DR) is a leading cause of blindness in adults worldwide. Early detection and intervention can prevent blindness; however, many patients do not receive their recommended annual diabetic eye examinations, primarily owing to limited access.ObjectiveTo evaluate the safety and accuracy of an artificial intelligence (AI) system (the EyeArt Automated DR Detection System, version 2.1.0) in detecting both more-than-mild diabetic retinopathy (mtmDR) and vision-threatening diabetic retinopathy (vtDR).Design, setting, and participantsA prospective multicenter cross-sectional diagnostic study was preregistered (NCT03112005) and conducted from April 17, 2017, to May 30, 2018. A total of 942 individuals aged 18 years or older who had diabetes gave consent to participate at 15 primary care and eye care facilities. Data analysis was performed from February 14 to July 10, 2019.InterventionsRetinal imaging for the autonomous AI system and Early Treatment Diabetic Retinopathy Study (ETDRS) reference standard determination.Main outcomes and measuresPrimary outcome measures included the sensitivity and specificity of the AI system in identifying participants' eyes with mtmDR and/or vtDR by 2-field undilated fundus photography vs a rigorous clinical reference standard comprising reading center grading of 4 wide-field dilated images using the ETDRS severity scale. Secondary outcome measures included the evaluation of imageability, dilated-if-needed analysis, enrichment correction analysis, worst-case imputation, and safety outcomes.ResultsOf 942 consenting individuals, 893 patients (1786 eyes) met the inclusion criteria and completed the study protocol. The population included 449 men (50.3%). Mean (SD) participant age was 53.9 (15.2) years (median, 56; range, 18-88 years), 655 were White (73.3%), and 206 had type 1 diabetes (23.1%). Sensitivity and specificity of the AI system were high in detecting mtmDR (sensitivity: 95.5%; 95% CI, 92.4%-98.5% and specificity: 85.0%; 95% CI, 82.6%-87.4%) and vtDR (sensitivity: 95.1%; 95% CI, 90.1%-100% and specificity: 89.0%; 95% CI, 87.0%-91.1%) without dilation. Imageability was high without dilation, with the AI system able to grade 87.4% (95% CI, 85.2%-89.6%) of the eyes with reading center grades. When eyes with ungradable results were dilated per the protocol, the imageability improved to 97.4% (95% CI, 96.4%-98.5%), with the sensitivity and specificity being similar. After correcting for enrichment, the mtmDR specificity increased to 87.8% (95% CI, 86.3%-89.5%) and the sensitivity remained similar; for vtDR, both sensitivity (97.0%; 95% CI, 91.2%-100%) and specificity (90.1%; 95% CI, 89.4%-91.5%) improved.Conclusions and relevanceThis prospective multicenter cross-sectional diagnostic study noted safety and accuracy with use of the EyeArt Automated DR Detection System in detecting both mtmDR and, for the first time, vtDR, without physician assistance. These findings suggest that improved access to accurate, reliable diabetic eye examinations may increase adherence to recommended annual screenings and allow for accelerated referral of patients identified as having vtDR.

Project description:BackgroundArtificial intelligence deployed to triage patients post-cataract surgery could help to identify and prioritise individuals who need clinical input and to expand clinical capacity. This study investigated the accuracy and safety of an autonomous telemedicine call (Dora, version R1) in detecting cataract surgery patients who need further management and compared its performance against ophthalmic specialists.Methods225 participants were recruited from two UK public teaching hospitals after routine cataract surgery between 17 September 2021 and 31 January 2022. Eligible patients received a call from Dora R1 to conduct a follow-up assessment approximately 3 weeks post cataract surgery, which was supervised in real-time by an ophthalmologist. The primary analysis compared decisions made independently by Dora R1 and the supervising ophthalmologist about the clinical significance of five symptoms and whether the patient required further review. Secondary analyses used mixed methods to examine Dora R1's usability and acceptability and to assess cost impact compared to standard care. This study is registered with ClinicalTrials.gov (NCT05213390) and ISRCTN (16038063).Findings202 patients were included in the analysis, with data collection completed on 23 March 2022. Dora R1 demonstrated an overall outcome sensitivity of 94% and specificity of 86% and showed moderate to strong agreement (kappa: 0.758-0.970) with clinicians in all parameters. Safety was validated by assessing subsequent outcomes: 11 of the 117 patients (9%) recommended for discharge by Dora R1 had unexpected management changes, but all were also recommended for discharge by the supervising clinician. Four patients were recommended for discharge by Dora R1 but not the clinician; none required further review on callback. Acceptability, from interviews with 20 participants, was generally good in routine circumstances but patients were concerned about the lack of a 'human element' in cases with complications. Feasibility was demonstrated by the high proportion of calls completed autonomously (195/202, 96.5%). Staff cost benefits for Dora R1 compared to standard care were £35.18 per patient.InterpretationThe composite of mixed methods analysis provides preliminary evidence for the safety, acceptability, feasibility, and cost benefits for clinical adoption of an artificial intelligence conversational agent, Dora R1, to conduct follow-up assessment post-cataract surgery. Further evaluation in real-world implementation should be conducted to provide additional evidence around safety and effectiveness in a larger sample from a more diverse set of Trusts.FundingThis manuscript is independent research funded by the National Institute for Health Research and NHSX (Artificial Intelligence in Health and Care Award, AI_AWARD01852).

Project description:ImportanceEffective management of proliferative diabetic retinopathy (PDR) and diabetic macular edema (DME) requires reliable patient follow-up to prevent disease progression.ObjectiveTo investigate the sociodemographic and clinical factors associated with being lost to follow-up (LTFU) among individuals with PDR or DME treated with anti-vascular endothelial growth factor (VEGF) intravitreal injections (IVIs) or panretinal photocoagulation (PRP).Design, setting, and participantsThis cohort study included a multicenter, retrospective review of patients with PDR or DME treated in Toronto, Canada, from January 1, 2012, to December 31, 2021. Data were analyzed from February 1 to May 31, 2024.ExposuresAll patients received at least 1 anti-VEGF IVI or PRP session.Main outcomes and measuresThe primary outcome was the LTFU rate, defined as the absence of an ophthalmic visit or intervention in the 1-year period following an individual's last visit with the treating retinal specialist. Univariable and multivariable logistic regression models were conducted to evaluate associations between sociodemographic and clinical factors with the LTFU rate.ResultsOverall, 2961 patients with PDR or DME (mean [SD] age, 71 [13] years; 1640 [55.4%] male) were included, of whom 507 (17.1%) were LTFU over a mean (SD) follow-up period of 61 (22) months. In the multivariable analysis, older patients (age ≥85 years vs age <65 years: odds ratio [OR], 0.58; 95% CI, 0.40-0.81; P = .002), those with worse baseline visual acuity (>20/200 Snellen vs 20/40 Snellen or better: OR, 0.68; 95% CI, 0.48-0.97; P = .04), those with DME (OR vs no DME, 0.60; 95% CI, 0.43-0.83; P = .003), those with frequent clinic visits (≥6 visits vs <6 visits: OR, 0.78; 95% CI, 0.62-0.98; P = .04), and those with a high anti-VEGF IVI burden in the first year (OR vs low anti-VEGF burden, 0.40; 95% CI, 0.21-0.76; P = .006) were less likely to be LTFU. In contrast, males (OR vs females, 1.23; 95% CI, 1.04-1.52; P = .04), patients living further from the point of care (>200 vs ≤20 km OR, 2.65; 95% CI, 1.85-3.76; P < .001), and those treated with PRP (OR vs anti-VEGF IVIs, 2.10; 95% CI, 1.24-3.55; P < .001) were more likely to be LTFU. Compared with White patients, Black patients (OR, 2.10; 95% CI, 1.50-2.95; P < .001) and Hispanic patients (OR, 1.54; 95% CI, 1.05-2.21; P = .03) were more likely to be LTFU.Conclusions and relevanceThis cohort study found multiple factors associated with LTFU rates. Identifying individuals at higher risk of LTFU and developing targeted strategies may reduce disease progression and vision loss in individuals with PDR.

Project description:IntroductionDiabetic retinopathy (DR) is the leading cause of preventable blindness in Saudi Arabia. With a prevalence of up to 40% of patients with diabetes, DR constitutes a significant public health burden on the country. Saudi Arabia has not yet established a national screening program for DR. Mounting evidence shows that Artificial intelligence (AI)-based DR screening programs are slowly becoming superior to traditional screening, with the COVID-19 pandemic accelerating research into this topic as well as changing the outlook of the public toward it. The main objective of this study is to evaluate the perception and acceptance of AI in DR screening among eye care professionals in Saudi Arabia.MethodsA cross-sectional study using a self-administered online-based questionnaire was distributed by email through the registry of the Saudi Commission For Health Specialties (SCFHS). 309 ophthalmologists and physicians involved in diabetic eye care in Saudi Arabia participated in the study. Data analysis was done by SPSS, and a value of p < 0.05 was considered significant for statistical purposes.Results54% of participants rated their level of AI knowledge as above average and 63% believed that AI and telemedicine are interchangeable. 66% believed that AI would decrease the workforce of physicians. 79% expected clinical efficiency to increase with AI. Around 50% of participants expected AI to be implemented in the next 5 years.DiscussionMost participants reported good knowledge about AI. Physicians with more clinical experience and those who used e-health apps in clinical practice regarded their AI knowledge as higher than their peers. Perceived knowledge was strongly related to acceptance of the benefits of AI-based DR screening. In general, there was a positive attitude toward AI-based DR screening. However, concerns related to the labor market and data confidentiality were evident. There should be further education and awareness about the topic.

Dataset Information

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

Publications

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets