A data mining approach to selecting herbs with similar efficacy: Targeted selection methods based on medical subject headings (MeSH)

Abstract

This study reveals and proves that the proposed algorithm is significantly more accurate and efficient in finding alternative herbs of similar efficacy than the random selection method. As such, it is hoped that this approach will be used in diverse applications in the ethno-pharmacology field.

Prediction of Medicinal Properties Using Mathematical Models and Computation, and Selection of Plant Materials

“…Various research institutes and pharmaceutical industries have taken up different approaches that can be categorized into four broad groups-ethnobotany-directed, random selection, chemotaxonomic, and integrated approach, respectively. Approaches of ethnobotany-directed, chemotaxonomic, and integrated approach can be part of targeted approach (Yea et al, 2016).…”

“…Data mining is the process of sorting through large datasets to identify patterns and establish relationships to solve problems through data analysis by using machine-learning and statistical methods (Afendi et al, 2013;Yea et al, 2016). Data mining methods use various kinds of information obtained from sources such as bibliographic literature, experimental data, clinical data, and curated data.…”

“…In the data mining approaches, random selection approach does not consider taxonomic affinities, ethnomedicinal contexts, or other intrinsic qualities. However, random screening is associated with extremely low probability of discovery of useful compounds (Yea et al, 2016). Considering the limitations of random selection, some advanced methods have been proposed.…”

“…Still today, mining of biomedical data to unearth knowledge or generate hypothesis is an active research field. One major innovation is inclusion of semantic information of the Medical Subject Headings (MeSH) thesaurus to cluster documents of MEDLINE database (Yea et al, 2016). In the approach, three categories containing terms related to herbal compounds, efficacy, toxicity, and the metabolic processes, were selected and subjected to similarity measurement method.…”

Clustering‐based approach for medical data classification

“…The fundamental approach for data mining is to extract underlying fruitful information from the enormous pile of data records and then transform it into an understandable outcome for future use. In the past, several predictive systems for medical data analysis had been introduced, which possess categorization and forecast of medical records . After the exploration of knowledge from the obtained data machine learning process is executed, in particular, training phase will be started by which intelligent decisions were trained to make in future based on the sample training data .…”