Artificial intelligence-driven screening, early diagnosis, and treatment strategies for cervical cancer: an overview
- PMID: 41316410
- PMCID: PMC12763967
- DOI: 10.1186/s13027-025-00716-5
Artificial intelligence-driven screening, early diagnosis, and treatment strategies for cervical cancer: an overview
Abstract
Cervical cancer (CC) is a significant global health issue, particularly in low-income countries. Early detection and successful treatment techniques are critical for decreasing death rates. Artificial intelligence (AI) has emerged as one of the major transformational tools in cancer prediction, improved screening, diagnosis, and therapy. This comprehensive narrative review describes applications of AI in diagnosis, biomarker prediction, development of drugs, and tailored treatment for cervical cancer. Various studies reporting the use of AI-driven imaging methods, multi-omics data analysis, and deep learning algorithms were evaluated for their influence on enhancing CC treatment. AI-powered screening approaches, such as automated Pap (Papanicolaou) smear analysis and colposcopy interpretation, outperformed traditional techniques in terms of accuracy and efficiency. Machine learning algorithms helped in identifying crucial biomarkers, such as microbial and metabolic fingerprints, which improved early diagnosis. AI-assisted drug development has resulted in the identification of new therapeutic targets and improved chemotherapy regimens. Personalized medical techniques, based on AI-driven multi-omics data analysis have helped to increase patient outcomes. However, issues including dataset constraints, clinical validation, and ethical considerations must be resolved before the broad adoption of AI-based diagnosis and therapy. Future research should focus on improving AI models and incorporating them into clinical practice to improve CC management.
Keywords: AI algorithms; Artificial intelligence; Cervical cancer; Metabolome; Vaginal microbiome.
Conflict of interest statement
Declarations. Ethical considerations: This study involved the synthesis of existing, publicly available data, requiring no additional ethical approval. The process adhered to principles of academic integrity through proper attribution of all included studies, contact with authors for clarification when needed, Transparent reporting of conflicts of interest, and Avoidance of selective reporting of results. Since no data was generated during the study, the ‘clinical trial number is not applicable’. Consent for publication: For this type of study, consent for publication is not required. Competing interests: The authors declare no competing interests.
Figures
References
-
- Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209–49. 10.3322/caac.21660. - PubMed
-
- Swain M. Update in pathological classification of cervical intraepithelial neoplasia and cervical cancer. J Colposcopy Low Genit Tract Pathol. 2023;1(2):56–63. 10.4103/JCLGTP.JCLGTP_17_23.
-
- Bogale AL, Teklehaymanot T, Kassie GM, et al. Performance of visual inspection with acetic acid for cervical cancer screening as compared to human papillomavirus deoxyribonucleic acid testing among women with HIV in Ethiopia: a comparative cross-sectional study. Cancer Control. 2022;1–7. 10.1177/10732748221114980. - PMC - PubMed
Publication types
LinkOut - more resources
Full Text Sources
Research Materials
