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

Risa M Wolf; Roomasa Channa; T Y Alvin Liu; Anum Zehra; Lee Bromberger; Dhruva Patel; Ajaykarthik Ananthakrishnan; Elizabeth A Brown; Laura Prichett; Harold P Lehmann; Michael D Abramoff

doi:10.1038/s41467-023-44676-z

Back

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

Journal article

Open access

Peer reviewed

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

Risa M Wolf, Roomasa Channa, T Y Alvin Liu, Anum Zehra, Lee Bromberger, Dhruva Patel, Ajaykarthik Ananthakrishnan, Elizabeth A Brown, Laura Prichett, Harold P Lehmann, …

Nature communications, Vol.15(1), 421

01/11/2024

DOI: 10.1038/s41467-023-44676-z

PMCID: PMC10784572

PMID: 38212308

Files and links (1)

url

https://doi.org/10.1038/s41467-023-44676-zView

Published (Version of record) Open Access

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.

Adolescent

Artificial Intelligence

Child

Diabetes Mellitus, Type 2

Diabetic Retinopathy - diagnosis

Follow-Up Studies

Humans

Referral and Consultation

Details

Title: Subtitle: Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial
Creators: Risa M Wolf - Johns Hopkins University School of Medicine
Roomasa Channa - University of Wisconsin–Madison
T Y Alvin Liu - Johns Hopkins University School of Medicine
Anum Zehra - Johns Hopkins University School of Medicine
Lee Bromberger - Johns Hopkins University School of Medicine
Dhruva Patel - Johns Hopkins University School of Medicine
Ajaykarthik Ananthakrishnan - Johns Hopkins University School of Medicine
Elizabeth A Brown - Johns Hopkins University School of Medicine
Laura Prichett - Data Management (Italy)
Harold P Lehmann - Johns Hopkins University
Michael D Abramoff - Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, USA
Resource Type: Journal article
Publication Details: Nature communications, Vol.15(1), 421
DOI: 10.1038/s41467-023-44676-z
PMID: 38212308
PMCID: PMC10784572
NLM abbreviation: Nat Commun
eISSN: 2041-1723
Grant note: K23 EY030911 / NEI NIH HHS R01 EY033233 / NEI NIH HHS
Language: English
Date published: 01/11/2024
Academic Unit: Electrical and Computer Engineering; Fraternal Order of Eagles Diabetes Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984546259902771

Metrics

33 Record Views

67 Times Cited - Web of Science