Cost-effectiveness of using artificial intelligence versus polygenic risk score to guide breast cancer screening

BMC Cancer

Table 2 Lifetime Costs, QALYs and Breast Cancer Outcomes by Screening Strategy

Strategy	Cost (in 1000 $)	Effectiveness (in QALYs)	No. (%) of true high risk women classified as high risk	No. (%) of true low risk women classified as low risk	No. of breast cancer deaths (per 100,000 women)	No. of false positive diagnoses (per 100,000 women)
No screening	1,745,808	1,976,720	–	–	3367	0
Family history + no screening for low risk	1,823,664	1,978,241	15,461 (36.0)	56,444 (100)	2988	121,737
AI + no screening for low risk	1,843,441	1,980,830	24,525 (57.0)	49,122 (87.0)	2956	141,339
PRS + no screening for low risk	1,852,227	1,980,713	24,381 (56.7)	48,805 (86.4)	2936	141,443
Family history + biennial screening for low risk	1,879,254	1,980,731	15,461 (36.0)	56,444 (100)	2916	170,917
PRS + biennial screening for low risk	1,909,968	1,978,418	24,381 (56.7)	48,805 (86.4)	2885	180,219
AI + biennial screening for low risk	1,910,153	1,978,604	24,525 (57.0)	49,122 (87.0)	2903	180,163
Annual screening for all	2,022,120	1,978,717	–	–	2778	290,325

All costs are in 2020 US dollars ($). Costs and effectiveness are calculated per 100,000 women. All strategies (except ‘No screening’) involve annual screening for women identified as high-risk. ‘AI’ refers to risk prediction accounting for both AI and other risk factors. ‘PRS’ refers to risk prediction accounting for both PRS and other risk factors. Beyond age 50, women without family history are screened biennially and those with family history are screened annually in all strategies except ‘No screening’ and ‘Annual screening for all’ strategies. ‘No. of false positive diagnoses’ refers to total number of false positive diagnoses among all mammograms performed during the lifetimes of 100,000 women. As specificity of each mammogram is < 100%, a woman can have more than one false-positive diagnosis in her lifetime

ISSN: 1471-2407