Transforming Non-Digital, Clinical Workflows to Detect and Track Vision-Threatening Diabetic Retinopathy via a Digital Platform Integrating Artificial Intelligence: Implementation Research

In settings with pre-existing manual grading workflows, AI-assisted DR screening provided incremental optimisation rather than transformation.

“Conversely, in settings with pre-existing manual grading workflows, AI-assisted DR screening provided incremental optimisation rather than transformation”

After AI interpretation, delayed result communication, unclear referral pathways, insufficient patient-facing communication, referral loss, or inadequate treatment capacity can prevent automated detection from becoming completed care.

“After AI interpretation, delayed result communication, unclear referral pathways, insufficient patientfacing communication, referral loss, or inadequate treatment capacity can prevent automated detection from becoming completed care (17)(18)(19)(20)(21)(22)(23).”

Autonomous AI systems can provide same-visit results and reduce dependence on asynchronous grading; centralized AI/teleophthalmology models can support multisite quality assurance and specialist oversight; hybrid AI-plus-human models retain human review for selected or uncertain cases.

“Autonomous systems can provide same-visit results and reduce dependence on asynchronous grading, whereas centralized models may support multisite quality assurance and specialist oversight; hybrid models retain human review for selected or uncertain cases (8,10,11,14,17,21).”

Autonomous point-of-care, centralized AI or teleophthalmology, and hybrid AI-plus-human grading models cannot be universally ranked because each offers a different balance of immediacy, specialist oversight, infrastructure requirements, and workflow complexity.

“Autonomous point-of-care, centralized AI or teleophthalmology, and hybrid AI-plus-human grading models should not be ranked universally, because each offers a different balance of immediacy, specialist oversight, infrastructure requirements, and workflow complexity.”

Real-world implementation of diabetic retinopathy screening with artificial intelligence-assisted care pathways has accelerated globally since 2020.

“Real-world implementation of DR screening with AI-assisted care pathways has accelerated globally since 20208,13–22, yet evidence on clinical and health system outcomes such as referral uptake remains limited.”

Liu et al., Dow et al., and Chotcomwongse et al. demonstrated serious risk of bias due to confounding from co-interventions, sequential implementation with potential for temporal confounding, and fundamentally different comparators.

“Liu et al.17, Dow et al.15, and Chotcomwongse et al.16 demonstrated serious risk of bias due to confounding from co-interventions (automated reminders16, proactive scheduling calls17), sequential implementation with potential for temporal confounding15,17, and fundamentally different comparators (AI-targeted versus routine referrals)17.”

The included studies had two distinct status quo care pathways: routine referrals for people with diabetes without prior screening and manual grading workflows including asynchronous teleophthalmology.

“It should be noted there were two distinct, status quo care pathways: studies providing routine referrals for people with diabetes without prior screening13,17 and manual grading workflows including asynchronous teleophthalmology14–16,18.”

All studies consistently demonstrate improved referral uptake after AI-assisted DR screening.

“While all studies consistently demonstrate improved referral uptake after AI-assisted DR screening13–18, magnitude of benefit varies substantially from moderate improvements ( + 11.8%)16 to large effects ( + 42.0%)13.”

Studies comparing AI to routine referral approaches with lower baseline rates (18.7-22.0%) showed the largest effect sizes (+36.7% to +42.0%), while studies comparing AI to existing manual screening workflows with higher baseline rates (39.6-77.3%) showed more modest improvements (+11.8% to +19.4%).

“Studies comparing AI to routine referral approaches with typically lower baseline rates of uptake (18.7–22.0%) showed the largest effect sizes (+36.7% to +42.0%)13,17, while studies comparing AI to existing manual screening workflows with higher baseline rates of uptake (39.6–77.3%) showed more modest improvements (+11.8% to +19.4%)14,16,18.”

Studies comparing AI-assisted screening to existing manual grading workflows showed modest gains ranging from +11.8 to +23.5%.

“Conversely, studies comparing AI-assisted screening to existing manual grading workflows showed modest gains ranging from +11.8 to +23.5%14–16,18.”

Chotcomwongse et al.'s alternating-week study (n=304) found 89.1% versus 77.3% referral uptake for AI screening coupled with automated text reminders versus nurse-led manual grading (+11.8%, p=0.158, not statistically significant).

“Chotcomwongse et al.‘s alternating-week study design (n = 304) compared AI screening coupled with automated text reminders before scheduled follow-up to nurse-led manual grading, finding 89.1% versus 77.3% referral uptake (+11.8%, p = 0.158, not statistically significant)16.”

Co-intervention usage varied across studies, with some utilising automated reminders, scheduling calls, or providing patient education alongside AI screening.

“Secondly, co-intervention usage varied across studies, with some utilising automated reminders16, scheduling calls17, or providing patient education alongside AI screening13,18.”

Two studies that replaced routine referrals with targeted, AI-assisted referrals showed greater effect sizes than studies with a manual grading comparator.

“Firstly, comparator types whereby two studies replaced routine referrals with targeted, AI-assisted referrals13,17 showed greater effect sizes than those studies with a manual grading comparator14–16,18.”

Facilitated scheduling addresses social opportunity barriers.

“Facilitated scheduling addresses social opportunity barriers16,17”

Findings from the review suggest the status quo for DR screening involves asynchronous teleophthalmology with delayed feedback of results or no prior screening as was the case in two North American studies by Wolf et al. and Liu et al.

“However, findings from our review suggest the status quo for DR screening involves asynchronous teleophthalmology with delayed feedback of results14–16,18 or no prior screening as was the case in two North American studies by Wolf et al. and Liu et al.13,17.”

Three studies included ungradable images as referable DR, thus retaining them in the referral denominator.

“Three studies included ungradable images as referable DR, thus retaining them in the referral denominator15–17.”

Co-interventions (facilitated follow-up scheduling, text reminders, patient education, grading reports) were implemented alongside AI in most studies, precluding attribution of effects to specific pathway components.

“Third, co-interventions (facilitated follow-up scheduling, text reminders, patient education, grading reports) were implemented alongside AI in most studies13,16–18, precluding attribution of effects to specific pathway components.”

In Thailand, a digital platform integrating AI had to transform non-digital workflows, establish tracking, and coordinate follow-up for vision-threatening DR.

“In Thailand, a digital platform integrating AI had to transform non-digital workflows, establish tracking, and coordinate follow-up for vision-threatening DR (17).”

Chotcomwongse et al.'s AI platform provided automated text message reminders to patients with referable diabetic retinopathy several days before their scheduled referral appointment.

“Chotcomwongse et al.’s AI platform provided automated text message reminders to patients with referable DR several days before their scheduled referral appointment16.”

Several studies included co-interventions alongside AI-assisted diabetic retinopathy screening with variable effectiveness.

“Several studies included co-interventions alongside AI-assisted DR screening with variable effectiveness13,16–18.”

In higher-performing systems (baseline referral uptake 39.6-77.3%), the gains from AI-assisted screening compared to manual grading were modest.

“This was most pronounced in in higher-performing systems (baseline referral uptake 39.6–77.3%)14,16,18 which indicates diminishing returns in settings with already functional screening infrastructure.”

Rates of referral uptake across these studies ranged from 55.4% to 89.1% and effect sizes ranged from +11.8% to +42.0%.

“Rates of referral uptake across these studies ranged from 55.4%17 to 89.1%16 and effect sizes ranged from +11.8%16 to +42.0%13.”

The magnitude of benefit from AI-assisted DR screening varies substantially from moderate improvements (+11.8%) to large effects (+42.0%).

“While all studies consistently demonstrate improved referral uptake after AI-assisted DR screening13–18, magnitude of benefit varies substantially from moderate improvements ( + 11.8%)16 to large effects ( + 42.0%)13.”

In settings with pre-existing manual grading workflows, AI-assisted DR screening yielded modest improvements (+11.8-23.5%) despite higher baseline performance (39-77%), except Dow et al. (baseline 12%).

“yielding modest improvements ( + 11.8–23.5%)14–16,18 despite higher baseline performance (39–77%)14,16,18 save for Dow et al. (baseline of 12%)15.”

Baseline health system performance influenced the marginal gains, with settings with higher baseline rates of uptake experiencing relatively lower effect size, in contrast to lower-performing systems with greater margins for improvement.

“Thirdly, baseline health system performance appeared to influence the marginal gains, following a law of diminishing returns whereby settings with higher baseline rates of uptake experienced relatively lower effect size14,16,18, in contrast to lower-performing systems with greater margins for improvement13,15,17.”