The aim of this study was to evaluate the cost effectiveness of novel oral anticoagulants (NOACs) for stroke prevention among atrial fibrillation (AF) patients by incorporating Taiwanese demographic information derived from a population-based database, the National Health Insurance Research Database(NHIRD), into cost-effectiveness analysis. From 1January to 31December 2012, 98,213 AF patients were selected from the NHIRD database. A Markov model was constructed that combined published secondary data with the Taiwan NHIRD to compare the cost and incremental cost effectiveness of apixaban 5mg twice daily, dabigatran 110 or 150mg twice daily, rivaroxaban 20mg once daily, and warfarin. The lifetime costs of warfarin, dabigatran 110mg, dabigatran 150mg, rivaroxaban 20mg, and apixaban 5mg were US$10,660, US$13,693, US$13,426, US$13,455, US$15,965, respectively. Apixaban resulted in an incremental cost effectiveness of US$39,351, US$27,039, US$41,298, and US$48,896 per quality-adjusted life-year (QALY) compared with warfarin, dabigatran 110mg, dabigatran 150mg, and rivaroxaban 20 mg, respectively. In Monte-Carlo analyses, apixaban 5mg, rivaroxaban 20mg, warfarin, and dabigatran 110mg were cost effective in 83, 10.4, 7, and 0.8%, respectively, of the simulations using a willingness-to-pay (WTP) threshold of US$50,000 per QALY. Apixaban was more cost effective than warfarin, dabigatran, and rivaroxaban for stroke prevention in patients with AF. Among the anticoagulant therapies, the WTP threshold of apixaban was about US$50,000 per QALY gained. These cost-effectiveness estimations provide useful information to aid clinical decision making in stroke prevention for AF patients.