Data Analysis and Mapping of Research Interest in Clinical Trials of Tuberculosis by Text Mining Platform of Artificial Intelligence using Open-Source Tool Orange Canvas

Abstract

Background: Reading every clinical trial for any disease is tedious, as is determining the current progress, especially when the number of clinical trials is huge. The Text Mining Platform of Artificial Intelligence (AI) can help to simplify the task. Methods: A large pool of tuberculosis clinical trials has been searched through the International Clinical Trial Registry Platform (ICTRP) and used as a textual dataset. The exported dataset of 1635 clinical studies, in a comma-separated format, is preprocessed for data analysis and text mining. Data preparation, corpus generation, text preprocessing, and finally, cluster analysis were carried out using the textmining widget of the open-source machine learning tool. The hierarchical cluster analysis was used for mapping research interests in tuberculosis clinical trials. Result and Conclusion: The data mining of the exported dataset of tuberculosis clinical trials uncovered interesting facts in terms of numbers. Text mining presented a total of 41 hierarchical clusters that were further mapped in twenty-five (25) different research interests among tuberculosis clinical trials. A novel technique for the rapid and practical review of major clinical trials is demonstrated. As an open-source and GUI-based tool is used for work, any researcher with working knowledge of text mining may also use this technique for other clinical trials.