Cervical cancer, one of the most preventable yet lethal malignancies among women, continues to threaten lives globally due to unequal access to quality screening and diagnosis. To close this gap, researchers developed the Intelligent Digital Education Tool for Colposcopy (iDECO), an AI-driven platform that blends real clinical cases, gamified learning, and personalized analytics. Involving 369 medical professionals across China, Mexico, and Mongolia, the study found that iDECO significantly enhanced diagnostic accuracy and decision-making. High-grade lesion identification doubled, and more than 85% of participants rated the program as highly satisfactory. The results highlight how intelligent learning can accelerate global efforts to eliminate cervical cancer.
Despite the availability of vaccines and screening programs, cervical cancer remains a major health challenge, particularly in low- and middle-income countries. The disease causes more than 660,000 new cases and 340,000 deaths annually, with incidence rates nearly three times higher in regions with limited healthcare resources. A critical bottleneck lies in the lack of well-trained colposcopists—specialists who visually assess and diagnose precancerous cervical lesions. Traditional in-person apprenticeships are costly, time-consuming, and often inaccessible. Online lectures and theoretical courses, while more scalable, rarely provide hands-on diagnostic experience or interactive feedback. Due to these persistent gaps, innovative, intelligent, and globally adaptable training solutions are urgently needed to strengthen cervical cancer prevention and control.
A new international study (DOI: 10.20892/j.issn.2095-3941.2025.0403) has demonstrated how artificial intelligence can transform the way colposcopists learn to detect cervical cancer. Using the Intelligent Digital Education Tool for Colposcopy (iDECO), researchers from the Chinese Academy of Medical Sciences and Peking Union Medical College and Tencent Sustainable Social Value Inclusive Health Lab trained nearly 400 clinicians from China, Mexico, and Mongolia through a three-week online program. Published in Cancer Biology & Medicine in October 2025, the findings reveal that this intelligent, bilingual platform markedly improved diagnostic accuracy and confidence—offering a powerful boost to global cervical cancer elimination efforts.
The research team conducted six online training programs between December 2024 and May 2025, engaging 369 gynecologists and resident physicians from 87 medical centers. Using the bilingual iDECO platform, participants completed a three-week course combining self-paced modules, virtual Q&A sessions, and performance-based feedback. The results were striking: diagnostic accuracy increased from 56.5% to 69.1% (odds ratio 1.72), with high-grade lesion detection improving more than twofold. Accuracy in transformation zone classification rose by 1.9 times, and biopsy decision-making improved by 2.09 times. Participants from Mexico and Mongolia, though starting from lower baselines, showed the greatest progress. The study also revealed that trainees who spent more time engaging with the platform achieved significantly higher posttest scores. Over 85% of users expressed high satisfaction, citing the system's interactive features and personalized learning pathways as key motivators. The researchers concluded that iDECO not only improves diagnostic accuracy but also reshapes medical education by turning learning into an adaptive, data-driven experience.
"Our study shows that intelligent digital education can dramatically improve diagnostic skills and confidence, even in resource-limited settings," said Prof. Youlin Qiao, corresponding author of the study. "By combining real-world medical cases with AI-driven analytics and gamified engagement, iDECO transforms the way clinicians learn and practice. This model brings global equity to professional training and ensures that expertise is no longer confined to major hospitals or high-income countries. It represents a powerful step toward a world free from cervical cancer."
The success of iDECO across three countries suggests that intelligent, cross-language training platforms can revolutionize global medical education. Beyond colposcopy, such tools could be adapted to other clinical disciplines requiring visual diagnosis, including dermatology, endoscopy, and pathology. By promoting skill standardization and accessibility, iDECO aligns closely with the WHO's "90-70-90" elimination targets—90% vaccination, 70% screening, and 90% treatment coverage by 2030. As healthcare systems embrace AI-driven learning, intelligent education tools like iDECO may play a decisive role in closing the global health training gap, empowering clinicians, and accelerating the elimination of cervical cancer worldwide.
###
References
DOI
10.20892/j.issn.2095-3941.2025.0403
Original Source URL
https://doi.org/10.20892/j.issn.2095-3941.2025.0403
Funding information
This study was supported by CAMS Innovation Fund for Medical Sciences (CIFMS 2021-I2M-1-004), Tencent Sustainable Social Value Inclusive Health Lab and through the ChongQing Tencent Sustainable Development Foundation “Comprehensive Prevention and Control Demonstration Project for Eliminating Cervical Cancer and Breast Cancer in Low Health Resource Areas of China” (Project No. SD20240904145730), Tencent Sustainable Social Value Inclusive Health Lab (Project No. SSVPJ202307060001), and Sanming Project of Medicine in Shenzhen (Project No. SZSM202211032).
About Cancer Biology & Medicine
Cancer Biology & Medicine (CBM) is a peer-reviewed open-access journal sponsored by China Anti-cancer Association (CACA) and Tianjin Medical University Cancer Institute & Hospital. The journal monthly provides innovative and significant information on biological basis of cancer, cancer microenvironment, translational cancer research, and all aspects of clinical cancer research. The journal also publishes significant perspectives on indigenous cancer types in China. The journal is indexed in SCOPUS, MEDLINE and SCI (IF 8.4, 5-year IF 6.7), with all full texts freely visible to clinicians and researchers all over the world.