BERTopic Modelling with P53 in Ovarian Cancer

Abstract

Ovarian cancer is the cancerous growth that begins in the ovaries. It has been identified as the most common cause of cancer related death around the world. It is known for its complexity and low survival rate due to late diagnosis and ineffective early detection mechanism. The mutation of p53 tumour suppressor gene is prevalent in High Grade Serious Ovarian Cancer (HGSOC). In this paper BERTopic Topic modelling an unsupervised machine learning technique was used to extract the keywords p53 and ovarian cancer from PubMed database using the Entrez Global Query Cross-Database Search System. The resulting data was then processed using the regex approach and the Natural Language Tool Kit (NLTK). The result showed useful insight in p53 ovarian cancer topic areas.