Objective. Self-collected HPV testing could substantially reduce disparities in cervical cancer screening, with slightly lower sensitivity compared to physician-collected specimens cross-sectionally. We aimed to evaluate the comprehensive long-term performance of self-collected HPV testing prospectively. Methods. In 1999, 1997 women were screened by HPV testing on self-collected and physician-collected samples, cytology and visual inspection with acetic acid (VIA) and followed up in 2005, 2010 and 2014, respectively. HPV testing was performed with Hybrid Capture II. Prospective performance, baseline clinical efficiency, and 15 year cumulative risk of cervical intraepithelial neoplasia grade 2 or higher (CIN2+) were analyzed. Results. Self-collected HPV testing prospectively detected 83.3% (95% CI:74.9%,89.3%), 70.3% (95% CI:62.5%,77.2%) and 63.3% (95% CI:55.7%, 70.2%) of cumulative CIN2+ at 6-year, 11-year and 15-year follow-up, respectively. Relative cumulative sensitivity of physician-collected HPV testing versus self-collected HPV testing was stable over 15 years at about 1.16. Cumulative sensitivity of self-collected HPV testing was comparable to cytology and significantly higher than VIA. Among women positive by self-collected HPV testing at baseline, 26.2% (95% CI:21.5%, 30.9%) developed CIN2+ during 6-year follow-up and no difference was observed with physician-collected HPV testing even 15 years after baseline. Negative self-collected HPV results provided greater protection against CIN2+ than VIA and ascertained CIN2+ cumulative incident rates as low as 1.1% at the 6-year follow-up. Conclusions. Self-collected HPV testing demonstrates lower sensitivity than physician-collected HPV testing but performs comparably to cytology prospectively and provides satisfactory assurance against CIN2+, indicating an alternative role in cervical cancer primary screening with five-year interval as an option especially in low resource settings. (C) 2018 Published by Elsevier Inc.