Cervical cancer remains a major cause of morbidity and mortality among women globally, despite being one of the most preventable malignancies. In 2020 alone, an estimated 604,000 new cases and 342,000 deaths were recorded worldwide, with the highest incidence occurring in low- and middle-income countries where access to screening and early treatment is limited. Screening programs based on conventional cytology (Pap testing) have significantly reduced cervical cancer incidence in high-income settings. However, in resource-constrained environments, gaps in accessibility, infrastructure, and follow-up systems have hindered the establishment of effective screening coverage.

In the last decade, two major innovations have transformed cervical cancer prevention: (1) high-risk human papillomavirus (HPV) testing using self-collected samples, and (2) artificial intelligence enhanced digital cytology for accurate and scalable triage of HPV-positive cases. HPV self-sampling allows women to collect vaginal specimens privately and conveniently without requiring a pelvic examination, resulting in dramatically improved participation rates, especially among under-screened or never-screened women. Meanwhile, artificial intelligence (AI) applied to digital cytology has shown diagnostic sensitivities and specificities comparable to expert cytopathologists, while reducing inter-observer variability, workload, and false-negative rates.

This article synthesizes the global evidence on integrating HPV self-sampling and AI-enhanced cytology into national cervical cancer screening programs. It reviews diagnostic performance metrics, implementation strategies, infrastructure requirements, population acceptability, clinical workflow models, cost-effectiveness, and challenges unique to diverse health systems. Drawing from multicountry trials and implementation studies, the article proposes a model for large-scale adoption of integrated HPV self-sampling and AI cytology pathways, highlighting opportunities to accelerate progress toward the World Health Organization’s cervical cancer elimination targets.

Human papillomavirus; HPV; self-sampling; cervical cancer; AI cytology; digital pathology; deep learning; screening programs; LMIC; CIN2+; cervical precancer; triage algorithms.

1. World Health Organization. Global Strategy to Accelerate the Elimination of Cervical Cancer as a Public Health Problem. WHO; 2020. Available at: https://www.who.int/publications/i/item/9789240014107

Arbyn M, Smith SB, Temin S, et al. Detecting cervical precancer and reaching underscreened women by using HPV testing on self samples: updated meta-analyses. BMJ. 2018;363:k4823. Available at: https://www.bmj.com/content/363/bmj.k4823

Verdoodt F, Jentschke M, Hillemanns P, et al. Reaching under-screened women by offering HPV self-sampling: a systematic review and meta-analysis. The Lancet Public Health. 2019;4(11):e637–e648. Available at: https://www.thelancet.com/journals/lanpub

Ronco G, Dillner J, Elfström KM, et al. Efficacy of HPV-based screening for prevention of invasive cervical cancer: follow-up of four European randomised trials. Lancet. 2014;383:524–532. Available at: https://www.thelancet.com

Hu L, Bell D, Antani S, et al. Artificial intelligence–based cervical cytology: performance evaluation on large-scale population data. Lancet Digital Health. 2022;4:e3–e12. Available at: https://www.thelancet.com/journals/landig

International Agency for Research on Cancer (IARC). Cervix Cancer Screening: IARC Handbook of Cancer Prevention, Volume 18. IARC; 2019. Available at: https://www.iarc.who.int

WHO. WHO Consolidated Guidelines on Secondary Prevention of Cervical Cancer. 2021. Available at: https://www.who.int/publications/i/item/9789240030515

Cremer M, Reimers L, Maza M, et al. Cost-effectiveness of integrating HPV self-sampling and AI-assisted cytology in middle-income countries. Health Economics. 2023;32(5):789–802. Available at: https://onlinelibrary.wiley.com

Wentzensen N, Schiffman M, Silver MI, et al. Detection of cervical precancer by HPV testing on self-samples vs clinician-collected samples: pooled analysis of diagnostic studies. J Clin Oncol. 2020;38(22):2575–2588. Available at: https://ascopubs.org

Katz ML, Zimmermann BJ, Moore D, et al. Acceptability of HPV self-sampling among under-screened women: a systematic review. Prev Med. 2018;114:195–205. Available at: https://www.sciencedirect.com