Screening for diabetic retinopathy with artificial intelligence in a primary care setting: a comparative cost analysis

Clinical Snapshot

Key Findings

• P Value: Not reported — no inferential statistics presented; this is a cost analysis, not a hypothesis-testing study

• Effect Size: Cost per DR case detected: C$620.36 (AI) versus C$1,283.55 (physician-based) — 52% lower cost per diagnosed case with AI

• Primary Outcome: Total cost per 100 patients screened: AI-based approach C$13,647.84 versus physician-based approach C$28,238.09 — a cost reduction of approximately 51.7% favouring AI screening

• Nnt Or Sensitivity: Cost per DR case detected (cost-effectiveness metric): C$620.36 (AI) vs C$1,283.55 (physician-based); AI system completion rate 93.6% (189/202 exams successfully completed); no NNT, sensitivity, or specificity data reported for the AI diagnostic performance

• Confidence Interval: Not reported — no confidence intervals or uncertainty ranges provided for any cost estimate

Clinical Application

Feasibility in primary care is supported by the 93.6% exam completion rate, suggesting the technology is operationally viable in a non-specialist setting. However, implementation requires capital investment in imaging hardware, AI software licensing, staff training, and a clear referral pathway for AI-detected cases. The cost advantage is sensitive to AI system costs, as acknowledged in the sensitivity analysis. Australia faces significant DR screening gaps, particularly in rural and remote areas and among Aboriginal and Torres Strait Islander communities with disproportionately high diabetes prevalence and DR burden. The TGA has pathways for AI-based medical device approval (Software as a Medical Device, SaMD), and several AI retinal screening platforms have received or are seeking TGA clearance. Medicare Benefits Schedule (MBS) item numbers for retinal photography in primary care exist but uptake is variable. The RACGP and Diabetes Australia guidelines recommend annual DR screening for all people with diabetes, yet screening rates remain suboptimal nationally. The cost-saving findings of this Canadian study are directionally relevant to Australian primary care, but direct cost translation requires recalculation using MBS fees, Australian wage data, and local DR prevalence figures. The Royal Australian and New Zealand College of Ophthalmologists (RANZCO) and optometry peak bodies would need to be engaged regarding scope-of-practice and referral pathway design for any national AI DR screening programme. Adults with type 1 or type 2 diabetes attending primary care, particularly in settings with limited access to ophthalmology or optometry services — most relevant to rural, remote, or underserved communities

Abstract

OBJECTIVE: Cost analysis of autonomous artificial intelligence (AI)-based screening of diabetic retinopathy (DR) for adults with diabetes at a primary care clinic. METHODS AND ANALYSIS: This study provides a comparative cost analysis of actual results using AI-based DR screening with counterfactual results based on all patients going through the physician-based referral system. A cost analysis is conducted using cost data from published sources, provincial billing codes, statistical sources, and patient characteristics from a clinical study to compare autonomous AI-based screening for DR versus physician-based screening. Costs considered include direct costs of operating the AI system, physician fees, and indirect costs to patient time. Along with total cost comparisons, a cost per DR case detected is estimated and a sensitivity analysis based on variations in AI costs is provided. RESULTS: Over the study period, 202 participants were screened for DR using autonomous AI. The majority (93.6%, n=189) of AI-based DR screening exams were completed successfully. The AI-based scenario results in total direct costs of $C7919.04 and indirect costs of $C5728.80, resulting in total costs of $C13 647.84 per 100 patients. The traditional physician-based approach results in total direct costs of $C8240 and indirect costs of $C19 998.09, resulting in total costs of $C28 238.09 for 100 patients. When costs are converted to costs per unit outcome, the total cost per diagnosed DR case is $C620.36 for the AI-based approach and $C1283.55 for the physician-based approach; the AI-based cost per diagnosed case was 52% lower. CONCLUSION: Given the lower cost per diagnosed case of the AI-based approach, there are advantages to the implementation of AI-based screening for DR.

References

1. 1.Di Matteo, L., Whitestone, N., & Bhambhwani, V. (2026). Screening for diabetic retinopathy with artificial intelligence in a primary care setting: a comparative cost analysis. BMJ Open Ophthalmology. https://doi.org/10.1136/bmjophth-2026-002904