Passer au contenu de la page principale

Screening for diabetic retinopathy with artificial intelligence in a primary care setting in Canada: A cost-effectiveness analysis - 5311

Mon statut pour la session

Quand:
4:35 PM, Vendredi 20 Juin 2025 (5 minutes)
Author’s Name(s): Vishaal Bhambhwani, Livio Di Matteo, Noelle Whitestone

Author’s Disclosure Block: Vishaal Bhambhwani: Northern Ontario Academic Medicine Association, Grant/research support, Orbis Canada, Grant/research support, Eyenuk Inc, Grant/research support, iCare Inc, Grant/research support, Bayer Inc, Employment/honoraria/consulting fees, Roche Inc, Employment/honoraria/consulting fees; Livio Di Matteo: none; Noelle Whitestone: none

Abstract Body
Purpose:To review the cost-effectiveness of autonomous artificial intelligence (AI)-based screening for diabetic retinopathy (DR) at a primary care clinic in Canada. Study Design: A comparative cost analysis study comparing actual screening results using AI-based DR screening at a primary care clinic with counterfactual results based on all patients going through the traditional physician-based referral system. Methods: A cost-analysis was conducted using cost data from provincial billing codes, published sources, and statistical sources, and patient characteristics from a clinical study to compare autonomous AI-based screening for DR versus traditional physician-based screening. Costs considered included direct costs of operating the AI system, physician fees, as well as indirect costs to patient time (e.g., time spent to attend an ophthalmologist appointment). Along with total cost comparisons, a cost-effectiveness measure in terms of cost per DR case detected was estimated and a sensitivity analysis based on variation in AI costs provided. Results: 202 participants, mean age 70.8 (±11.7) years, 38.6% (n=78) female,were screened for DR utilizing autonomous AI at a primary care clinic in Canada. 93.6% (n=189) of AI-based DR screening exams were completed successfully. Only those that screened positive on the AI system (22.2%, n=42)and those with unsuccessful AI exams (6.4%, n=13)needed to see an ophthalmologist.The AI-based screening scenario results in total direct costs of $7,919.04 ($5,686 for AI screening and $2,233 for ophthalmologist fees) and indirect costs of $5,728.80; resulting in total costs of $13,647.84 per 100 patients. The traditional physician-based approach results in total direct costs of $8,240 (all for ophthalmologist fees) and indirect costs of $19,998.09; resulting in total costs of $28,238.09 per 100 patients. The total cost per diagnosed DR case (a cost-effectiveness measure) is $620.36 for the AI-based approach and $1,283.55 for the physician-based approach; the AI-based cost per diagnosed case being 52 percent lower. When AI fees are assumed to be 50% lower, direct costs of the AI-based approach are now $5,076.04 (36% reduction) and the cost per diagnosed case of DR falls to $491.13 (21% reduction). In this scenario, the total cost per diagnosed case of DR via the AI-based approach is 62 percent lower than the traditional physician-based approach. Conclusion: Primary care-based use of autonomous AI for DR screening is cost-effective compared to traditional physician-based screening, which may result in significant cost savings to the healthcare system.

Vishaal Bhambhwani

Conférencier.ère

Mon statut pour la session

Évaluer

Detail de session
Pour chaque session, permet aux participants d'écrire un court texte de feedback qui sera envoyé à l'organisateur. Ce texte n'est pas envoyé aux présentateurs.
Afin de respecter les règles de gestion des données privées, cette option affiche uniquement les profils des personnes qui ont accepté de partager leur profil publiquement.

Les changements ici affecteront toutes les pages de détails des sessions