Academy & Industry Research Collaboration Center (AIRCC)

Volume 12, Number 11, June 2022

Mining Biomedical Literature to Discover Natural Cure for Recurrent Disease


Farhi Marir1, Hussein Fakhry1 and Aida J. Azar2, 1Zayed University, UAE, 2Mohammed Bin Rashid University of Medicine and Health Sciences (MBRU), UAE


The advances in digital data collection and storage technology allows the storage of a huge amount of medical publications in MEDLINE. This database contains more than 25 million references to journal articles and abstracts in life sciences and biomedicine. This research work builds on Swanson use of mathematical association between A and C concepts/terms through a list of B concept/terms retrieved from large medical literature databases that contain either A&B or B&C terms links A to C. Swanson discovered evidence that fish oil (A) may cure vessel blood disorder (C) and that magnesium (A) may be effective against migraine headache (C), which were clinically proven two years later. We present a cooccurrence mining algorithm and an A&C pre-defined domain Knowledge Base (containing for instance Garlic Composition and Blood pressure causes) to filter and reduce the exponential number of shared B terms retrieved from MEDLINE articles using Swanson’s Arrowsmith machine. The reduced number of relevant B terms makes it easier to build scientific evidence to validate publicly known remedies for recurrent diseases for instance establishing whether an important association exists between garlic and its impact on blood pressure.


Co-occurrence Text Mining, ABC Arrowsmith Discovery Machine, Dietary Aliments & Disease Knowledge Base, and MEDLINE medical database.