Cost-Utility Analysis of Deep Learning and Trained Human Graders for Diabetic Retinopathy Screening in a Nationwide Program

Table 2 Total costs, quality-adjusted life-years, and incremental cost-effectiveness ratios between the screening modalities from the base case analysis

Screening modality	Total cost (THB)	Total effectiveness		Incremental cost (THB)	Incremental effectiveness		ICER (THB per QALY gained)	iNMB (THB)
Screening modality	Total cost (THB)	LY	QALY	Incremental cost (THB)	LY	QALY	ICER (THB per QALY gained)	iNMB (THB)
Societal perspective
HG	163,565.04	18.5325	12.8574
DL	163,478.16	18.5325	12.8617	− 86.88	0.0000	0.0043	Dominant	771.50
Provider perspective
HG	41,941.10	18.5325	12.8574
DL	44,135.95	18.5325	12.8617	2194.85	0.0000	0.0043	512,955.12	− 1510.24

BB bilateral blindness, DL deep learning, DME diabetic macular edema, ICER incremental cost-effectiveness ratio, iNMB incremental net monetary benefit, LY life year, HG trained human graders, QALY quality-adjusted life year, STDR sight-threatening diabetic retinopathy, THB Thai baht