Cervical cancer (CC) is the fourth most common type of cancer among women. Majority of CC cases (84%–90%) have been reported in low- and middle-income countries (LMICs). Persistent infection with high-risk human papilloma virus (HR-HPV) subtypes is responsible for >90% of the cervical cancers. CC is preventable by timely vaccination with HPV vaccine. Early diagnosis, treatment and disease recurrence prediction markers play a significant role in improving the patient outcome, yet LMICs are seeing a continuous increase in CC cases. Lack of sensitive self-screening technologies, effective diagnostic methods and accessible treatment options are predominantly contributing to this increase. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL) methods have revolutionized CC diagnosis, prognosis, and treatment agent selection by (a) enhancing the accuracy of screening and diagnostic methods; (b) assisting the clinicians in predicting various prognostic factors such as lymph node metastasis, treatment response, survival outcome, postoperative risk factors; and © providing dose prediction, treatment planning, segmentation of target volume and organ at risk. AI algorithms can analyze complex datasets, including medical images, patient data, and genetic information, to identify patterns and predict outcomes that might have not been considered by traditional methods. AI-based analysis provides more accurate diagnosis and improved risk stratification in a very short duration, while helping in the design of tailored treatment strategies. In this article, we aim to provide an overview of emerging ML and DL methods and comprehensively evaluate the role of AI-based approaches in the screening, diagnosis, prognosis and treatment of CC. Finally, we discuss challenges and limitations associated with the use of AI models in CC screening, diagnosis, prognosis and treatment. We have also focused on emerging AI models that can be applied in CC research and treatment to overcome the current challenges and limitations.