--- title: >- Johns Hopkins Children's Center / Johns Hopkins Medicine: Autonomous AI diabetic eye exam at point of care (ACCESS RCT; LumineticsCore/IDx-DR) slug: johns-hopkins-access stable_id: 0bbf6e47dd114b1f company: Johns Hopkins Children's Center / Johns Hopkins Medicine function_code: healthcare_screening pattern_codes: - point_of_care_relocation - queue_elimination - autonomous_with_backstop evidence_strength: verified publication_tier: showcase freshness: current reviewed_at: '2026-08-23' updated_at: '2026-08-22' source_quality_summary: 3 peer reviewed, 2 primary; publication outcomes are verified. caveat_summary: >- Peer-reviewed RCT under trial conditions. Outcome is process completion, not vision preserved. Control-arm denominator appears as n=83 in the abstract and 18/82 (Table 3, n=163) in the body; both round to 22%. Denominators differ by design (intervention: DED-positive participants completing ECP follow-up; control: participants completing the ECP exam), so the comparison is not like-for-like; the paper defines the secondary outcome this way explicitly. Pre/post observational, single center, reported in a peer-reviewed implementation review by the operating team. collections: - queue-eliminated - regulated-autonomy - embodied-work bundle_version: 1.0.0 bundle_fingerprint: sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93 canonical_url: https://brianletort.ai/transformations/johns-hopkins-access --- # Johns Hopkins Children's Center / Johns Hopkins Medicine: Autonomous AI diabetic eye exam at point of care (ACCESS RCT; LumineticsCore/IDx-DR) Closing the diabetic eye-screening care gap requires persuading youth to attend a separate specialist appointment. Instead, the diagnostic exam itself is brought into the routine diabetes visit and read autonomously by AI in under a minute. Function: Healthcare screening. Patterns: Point-of-care relocation; Queue elimination; Autonomous with a backstop. Evidence: verified. Freshness: current. Reviewed: 2026-08-23. Updated: 2026-08-22. Source quality: 3 peer reviewed, 2 primary; publication outcomes are verified. ## Before 1. **Study coordinator / diabetes clinic staff** — Refers youth to an external eye-care provider with scripted education and a paper guide. (control: Referral documentation; completion tracked via EHR and phone follow-up) 2. **Patient and family** — Schedule, travel to, and attend a separate eye appointment within 6 months (control: Patient initiative; 78% of the control arm never completed the exam in the window) 3. **Eye care provider** — Perform dilated diabetic eye exam and return results (control: ECP clinical judgment) ## After 1. **Trained clinic operator (no ML expertise required)** — Captures two fundus images during the routine endocrinology visit without pharmacologic dilation. (control: AI image-quality algorithm guides acquisition and forces retakes (max 3 attempts)) 2. **Autonomous AI diagnostic system (LumineticsCore)** — Returns one of three results within 60 seconds: DED present, absent, or insufficient image quality. (control: Locked deterministic medical device under FDA De Novo regulation; in this off-label youth deployment, all images were additionally overread by a board-certified retina specialist (estimated sensitivity 100%, specificity 78.9% vs level-4 reference standard)) 3. **Clinic staff** — Communicates the result and, if DED is present, gives scripted referral education. (control: Scripted educational intervention) ## Decision rights The AI makes the screening diagnosis autonomously (its FDA De Novo authorization basis for adults is diagnosis without human oversight). In the youth trial, the AI output was the result communicated to the patient and drove the referral decision, with a retina-specialist overread of every image as a safety layer because the device is not cleared for under-22s. Treatment decisions remain with eye care providers. ## Exception path Insufficient image quality after 3 attempts triggers referral for eye care; a 'DED present' output triggers scripted referral to an eye care provider for a dilated exam. ## Outcomes - **Diabetic eye exam completion within 6 months (care-gap closure)** (verified): 22% (18/82) in the control arm (scripted ECP referral plus education) → 100% (81/81) in the intervention arm; difference 78 percentage points (95% CI 69-87), p<0.001; no significant differences by race, ethnicity, SES, or education. Peer-reviewed RCT under trial conditions. Outcome is process completion, not vision preserved. Control-arm denominator appears as n=83 in the abstract and 18/82 (Table 3, n=163) in the body; both round to 22%. - **Follow-through with an eye care provider when indicated** (verified): 22% in the control arm → 64% (16/25) in the intervention arm (difference 42 points, 95% CI 21-63), p<0.001. Denominators differ by design (intervention: DED-positive participants completing ECP follow-up; control: participants completing the ECP exam), so the comparison is not like-for-like; the paper defines the secondary outcome this way explicitly. - **DED screening adherence in the routine pediatric deployment (pre-trial)** (verified): 49% baseline adherence → 95% after autonomous AI implementation; 310 exams in the first year; 85.7% sensitivity and 79.3% specificity vs level-2 reference. Pre/post observational, single center, reported in a peer-reviewed implementation review by the operating team. ## Executive lesson The binding constraint on screening was never diagnostic capacity; it was the separate appointment. Moving an autonomous, minute-long diagnostic into a visit the patient already attends closed a care gap that referral-plus-education could not, and it did so without introducing racial, ethnic, or socioeconomic disparities. ## Anti-pattern Citing the 100% vs 22% trial result as proof of operational performance; the trial proves efficacy under RCT conditions, and the separate routine-care deployment evidence is what proves durability. ## Questions for leaders - Which of our screening or compliance gaps are actually attendance problems that point-of-care automation could eliminate? - Where would we accept an off-label AI deployment with a specialist overread backstop, and who signs that protocol? - Screening completion is a process metric; what is our path to the outcome metric (here, vision preserved)? ## Sources - [Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial](https://www.nature.com/articles/s41467-023-44676-z) — Nature Communications (15, 421) - [Autonomous Artificial Intelligence for Diabetic Eye Disease Testing Improves Access and Equity in the Pediatric and Adult Populations: The Johns Hopkins Medicine Experience](https://pmc.ncbi.nlm.nih.gov/articles/PMC11825398/) — Diabetes Spectrum 38(1):19-22 (American Diabetes Association) - [Clinical Implementation of Autonomous Artificial Intelligence Systems for Diabetic Eye Exams: Considerations for Success](https://pmc.ncbi.nlm.nih.gov/articles/PMC10788651/) — Clinical Diabetes 42(1):142-149 (American Diabetes Association) - [Study finds AI-driven eye exams increase screening rates for youth with diabetes](https://www.hopkinsmedicine.org/news/newsroom/news-releases/2024/01/study-finds-ai-driven-eye-exams-increase-screening-rates-for-youth-with-diabetes) — Johns Hopkins Medicine newsroom - [ACCESS 2: AI for pediatriC diabetiC Eye examS Study 2 (NCT05463289)](https://clinicaltrials.gov/study/NCT05463289) — ClinicalTrials.gov (Johns Hopkins University, with NEI and JDRF)