Uterine Corpus Endometrial Carcinoma Prediction from Genomic Analysis with Machine Learning

Endometrial carcinoma (EC) is a common uterine malignancy that still contributes significantly to cancer-related morbidity and mortality. EC identified in an advanced stage has a poor treatment response. In the United States, the most frequent cancer of the female reproductive organs is endometrial carcinoma. The American Cancer Society’s estimations for uterine cancer in the United States in 2024 are approximately 67,880 new cases of uterine cancer will be diagnosed and approximately 13,250 women will die from uterine cancer. EC is the second most common gynecological malignancy in the world and the top in continental Europe. The clinically used EC diagnostic techniques are expensive, time-consuming, and not available to all patients. The fast expansion of computational biology has sparked significant research interest from both data scientists and oncologists, resulting in the creation of quick and cost-effective computer-aided malignancy monitoring systems. Machine learning (ML), a subset of artificial intelligence, enables drug development, early disease detection, successful therapy, and treatment modality selection. The use of ML methods in EC diagnosis, treatment, and prediction may be very important. This review provides a summary of EC, as well as risk factors and diagnostic procedures, before delving into a complete genetic investigation of prospective ML modalities for EC prevention, screening, detection, and prognosis.