Cervical cancer diagnostics: non-coding RNAs and biosensors to AI-derived methods
Cervical cancer ranks fourth in terms of cancer mortality among women. The most important risk factor for cervical cancer is infection with HPV 16 and HPV 18. The prevalence and mortality rates of this cancer are much higher in countries with low and medium development indices than in developed countries. Improving health, access to vaccination, and screening tests are highly helpful in preventing this type of cancer. Recent advances have revealed novel biomarkers, particularly noncoding RNAs, including microRNAs, long noncoding RNAs, and circular RNAs, which are promising biomarkers for early detection and disease monitoring. Concurrently, artificial intelligence (AI)-derived methods, which leverage machine learning and deep learning algorithms, have revolutionized diagnostic accuracy by enhancing image analysis and pattern recognition in cytology and histopathology. This review focused on the latest developments in cervical cancer diagnostic technologies, with a focus on the role of noncoding RNAs, biosensors, and AI-derived methods (machine learning and deep learning approaches) in clinical diagnosis. By evaluating the strengths, challenges, and future potential of these innovations, we aim to provide a deeper understanding of noncoding RNAs and AI-derived methods as a future for the laboratory diagnosis of cervical cancer.