Cervical cancer remains a global health challenge with substantial disparities between countries. High-quality colposcopy is essential for cervical cancer prevention, yet training opportunities remain inadequate worldwide. We developed the Intelligent Digital Education Tool for Colposcopy (iDECO) to address training gaps and evaluated the effect across diverse international settings.

Six pre-post interventional training programmes were conducted in China, Mexico, and Mongolia from December 2024 to May 2025. A total of 369 trainees from 87 centers participated in a 3-week online training programme using iDECO, a bilingual web-based platform featuring authentic colposcopy cases, gamified learning pathways, and personalized analytics. The primary outcomes included colposcopy competence in general assessment, colposcopic findings, diagnostic accuracy, and management decisions. The secondary outcomes focused on participant feedback and satisfaction.

Of 369 participants who completed pretests, 333 (90.24%) completed post-training assessments. Significant improvements were observed across all competency domains. Diagnostic accuracy increased with an odds ratio (OR) of 1.72 (95% CI: 1.60–1.86) with the greatest gains in high-grade lesion identification [OR = 2.27 (95% CI: 1.94–2.64)]. Squamocolumnar junction visibility and transformation zone type assessments improved with ORs of 1.41 (95% CI: 1.31–1.51) and 1.87 (95% CI: 1.73–2.01), respectively. Biopsy decision-making accuracy also showed significant improvement [OR = 2.09 (95% CI: 1.91–2.29)]. International participants showed lower baseline performance but achieved the greatest improvements. Greater than 85% of participants rated the training highly satisfactory and 83.56% preferred intelligent training over traditional methods.

iDECO-based training significantly improved colposcopy competence across diverse international settings with high user satisfaction. These findings support the potential for worldwide implementation of intelligent digital training tools to address colposcopy training gaps and contribute to the elimination of cervical cancer.

Drawbacks of human papillomavirus (HPV) primary screening, including high referral rates and low specificity, highlight the necessity for triage strategies to balance the screening benefits with potential harms.

A cross-sectional, population-based diagnostic study was conducted in rural Xinjiang, China involving 8,638 women ≥ 25 years of age who participated in organized cervical cancer screening between 2023 and 2024. The study evaluated the accuracy and efficiency of multiple HPV-based “screen-triage” strategies. Histologically confirmed cervical intraepithelial neoplasia grade 2 or worse (CIN2+ and CIN3+) served as disease outcomes.

Among single-step triage strategies, only extended genotyping for the seven most carcinogenic HPV types (HPV16/18/31/33/45/52/58) maintained sensitivity for CIN2+ comparable to HPV screening without triage (90.0% vs. 92.5%, P = 0.50) but significantly improved specificity (94.7% vs. 90.8%, P < 0.001). This approach led to a 38% reduction in colposcopy referrals (relative rate, 0.62; 95% CI: 0.59–0.65). Two-step triage algorithms (HPV16/18 with reflex ASC-US+ or methylation) showed slightly lower but non-significant sensitivity (87.5%, P = 0.13/89.6%, P =0.50) than HPV primary screening without triage, yet achieved significantly increased specificity (> 95%, P < 0.001) and reduced colposcopy referral by ~50% (relative rate, 0.5; P < 0.001). If negative for cytology or methylation, women positive for 12 high-risk HPV types (excluding HPV16/18) had a < 2% risk of CIN2+ (CIN3+ risk < 1%), indicating delayed follow-up.

Focusing on the seven high-risk HPV types within a one-step “screen-triage” framework effectively balances minimal sensitivity loss with significant gains in specificity, reducing unnecessary referrals and treatments, especially valuable in resource-limited settings. Integrating HPV genotyping with methylation results improves the accurate identification of women requiring immediate referral, which is advisable when resources allow.

To describe temporal changes associated with deployment of an optical character recognition (OCR)-enabled One-Identity (One-ID) digital platform for rural cervical cancer screening, focusing on over-screening rates, CIN2+ detection, colposcopy follow-up, and CIN2+ management.

A multi-county pre-post observational study was conducted in six rural counties in Shanxi, Yunnan, and Sichuan Provinces (2021–2024), encompassing 153,978 encounters. The digital platform integrates OCR identity capture, deterministic One-ID linkage, and real-time duplicate alerts. Over-screening proportions before and after digital deployment were compared, changes in CIN2+ detection rate were evaluated, and colposcopy follow-up and CIN2+ management were assessed. Differences were tested with χ² or Fisher’s exact tests.

Among 153,978 encounters, the proportion of over-screening decreased from 12.64% in 2023 to 0.17% in 2024 with an absolute reduction of 12.17% (95% CI: 11.94–12.40; P < 0.001). The share of women receiving a first screening within the preceding 3 y increased from 78.3% to 88.2% (P < 0.001). Colposcopy completion improved from 64.1% to 84.9%. The CIN2+ detection rate rose from 0.35% (2021–2023 pooled) to 0.67% in 2024 (P < 0.001) and CIN2+ management completion increased from 56.0% to 76.2% (95% CI: 13.3–27.2; P < 0.001). These improvements were consistent across age groups, counties, and screening strategies.

The OCR-enabled One-ID platform substantially reduced over-screening, increased CIN2+ detection rate, and strengthened case follow-up/management, particularly where baseline tracking was weak, supporting scalable digital reinforcement of rural screening programmes.

To evaluate the impact of government-organized screening on the economic burden among patients with cervical cancer and precancerous lesions, and explore mediating pathways across diagnosis, initial treatment, radiotherapy/chemotherapy, follow-up, and recurrence/progression/metastasis.

A multicentre, nationwide survey across 5 disease courses was conducted from 26 hospitals in China. Multivariable regression and structural equation modeling were used to assess the effects of government-organized screening on economic burden by comparing government-organized screening with workplace check-up, self-paid check-up, and symptom-based detection.

Workplace check-up, self-paid check-up, and symptom-based detection were associated with progressively higher costs across diagnosis [β: 1.10, 95% confidence interval (CI): 0.54–1.67; β: 1.46, 95% CI: 1.00–1.92; and β: 1.68, 95% CI: 1.25–2.11, respectively], initial treatment (β: 0.36, 95% CI: 0.18–0.55; β: 0.51, 95% CI: 0.35–0.66; and β: 0.56, 95% CI: 0.42–0.70, respectively), and follow-up (β: 0.63, 95% CI: 0.38–0.88; β: 0.83, 95% CI: 0.61–1.04; and β: 0.85, 95% CI: 0.65–1.06, respectively) compared to government-organized screening (all P < 0.05). Earlier clinical staging and greater use of lower-level hospitals mediated 44.74%–54.97% of cost differences in diagnosis, 73.27%–85.04% in initial treatment, and 30.38%–54.73% in follow-up. Fifteen percent of the cost differences during initial treatment were related to lower overtreatment for precancerous lesions.

Government-led cervical cancer screening was associated with lower economic burden with pathways involving earlier-stage diagnosis, reduced overtreatment, and decreased reliance on higher-level hospitals, suggesting potential clinical benefits, efficient resource use, and improved equity in cancer care.

Cervical cancer caused by persistent high-risk human papillomavirus (hrHPV) infection remains a leading cause of cancer-related mortality in women. As prophylactic HPV vaccines cannot eliminate existing infections, developing therapeutic vaccines targeting HPV E6/E7 oncoproteins is critical for reversing precancerous lesions. This study aimed to design a novel multi-epitope vaccine against HPV16, incorporating newly identified immunodominant epitopes and evaluating the therapeutic efficacy.

The multi-epitope vaccine HSP70-12P was bioinformatically designed to include cytotoxic T lymphocyte (CTL) and helper T lymphocyte (HTL) epitopes from HPV16 E6/E7, which were fused to the C-terminal domain (residues 359–610) of Mycobacterium tuberculosis HSP70 as an adjuvant. Two formulations were used, as follows: (1) protein-based Pro-HSP70-12P; and (2) DNA-based DNA-HSP70-12P. Therapeutic efficacy was evaluated in TC-1 tumor-bearing mouse models. Tumor regression, survival rates, and immune correlates (T cell responses and cytokine profiles) were assessed. Immunodominant epitopes were identified using ELISpot.

The Pro-HSP70-12P protein vaccine induced strong immune responses and provided lasting antitumor protection. The vaccine activated cell-mediated immunity and stimulated effector memory T cells in the HPV-16-related tumor mouse model, resulting in strong tumor clearance effects. Pro-HSP70-12P demonstrated superior performance compared to the DNA-HSP70-12P vaccine, achieving complete regression of small tumors (diameter < 2 mm) with a single dose and conferring long-lasting protection in TC-1 rechallenge experiments. Three novel immunodominant epitopes were identified (E6-38-45, E6-124-132, and E7-50-57). The E6 epitopes address a critical gap in E6-targeted vaccine design.

The multi-epitope protein vaccine, Pro-HSP70-12P, represents a potent therapeutic candidate against HPV-driven malignancies, which has the capacity to induce tumor regression and long-term immunity. These findings support further clinical development.