Cervical cancer is the primary cause of death for women worldwide, negatively impacting both their physical and mental well-being.  Although cervical cancer can now be easily detected and prevented because to technological breakthroughs, a number of variables make precise diagnosis difficult. One of the leading causes of cancer-related mortality in women globally is cervical cancer. Survival rates are greatly increased by early diagnosis and continuous health monitoring. The Internet of Things (IoT) has emerged as a promising technology for health care by enabling real-time health monitoring, data collection, and intelligent disease prediction. The paper presents a comparative analysis of different IoT based techniques for prediction of cervical cancer. A comparative analysis of various machine learning and deep learning models along with IoT systems on accuracy, precision, recall, F1-score, computational complexity, scalability and real-time performance is performed. The study highlights the pros and cons of each technique and gives an insight for selection of suitable IoT-enabled predictive models for healthcare applications.