Cost-effectiveness analysis of telemedicine and artificial intelligence-based diabetic retinopathy screening in urban and rural China

Authors:
Preprint
Publisher website
Google Scholar
Abstract
Objective To evaluate the cost-effectiveness of telemedicine-based diabetic retinopathy (DR) screening with artificial intelligence (AI)-based grading in rural and urban China. Methods The cost effectiveness of telemedicine-based diabetic retinopathy screening with AI-based grading was compared to no DR screening in rural area and urban area from social perspective. Increment cost-effectiveness ratio (ICER) using quality-adjusted life year (QALY) was calculated and compared to the per capita GDP in China 2022. Results The ICERs of AI and manual screening were $11132.39/QALY and $11239.22/QALY gained in rural area and $6764.12/QALY and $6923.77/QALY in urban area respectively as compared to no screening. The ICERs of both strategies were less than the threshold, and considered to be cost-effective in rural area and very cost-effective in urban area. Moreover, AI-based screening was more cost-effective than human assessor-based screening in both areas. Conclusion DR screenings based on fundus photography and telemedicine are both cost-effective in rural and urban area. AI-based screening is more cost-effective than human assessor-based screening, extending the application of DR screening across China.

This publication has 35 references indexed in Scilit: