Breast cancer patients using mobile applications: An automated biomedical literature curation model (BLCM)

Abstract

Natural Language Processing (NLP) is increasingly drawing researchers’ attention to mine for valuable knowledge in the massive literature arising in our technological era. Text mining is one of the NLP tools that can take the lead over manual curation of articles from different medical databases. It offers appreciable help by automating the whole information extraction process to get the required information saving effort and time. As Mobile Health (mHealth) for breast cancer patients is showing a clear positive impact on their treatment and recovery journey, text mining techniques can help in the continuous tracking of related research articles to figure out the drawbacks and highlight future directions. Therefore, this article proposes a model that initiate a deep search to curate articles dataset using National Center for Biotechnology Information (NCBI) database applying five different queries. The model preprocesses the curated dataset to remove outliers and extract the target articles only. In addition, it analyzes the articles’ titles to extract required information. Total number of retrieved articles was 610 that are further reduced to 13 after the applied filtration steps. Two of which are review articles that are concerned with effect of mobile apps on patients undergoing chemotherapy which is a cancer critical stage. The retrieval process took from few seconds to several minutes according to the number of articles related to the entered query, while the preprocessing stage is achieved in one second.