|
An innovative framework for extracting adverse drug reactionsof single medication and combined medicationsfrom medical transcriptions and online reviews |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Lakshmi K. S. 2. Liya Varghese |
| Title | An innovative framework for extracting adverse drug reactionsof single medication and combined medicationsfrom medical transcriptions and online reviews |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2565 |
| Journal Title | Songklanakarin Journal of Science an Technology (SJST) |
| Journal Vol. | 44 |
| Journal No. | 5 |
| Page no. | 1365-1372 |
| Keyword | ADRs, DDIs, text mining, weighted association rule mining, NLP, KeyBERT |
| URL Website | https://sjst.psu.ac.th/ |
| ISSN | 0125-3395 |
| Abstract | Adverse drug reactions (ADRs) are unintentional and detrimental reactions arising due to normal drug usage.Identifying ADRs is vital in spheres of health and pharmacology. ADRs occur due to a single drug or a combination of multipledrugs. In the pharmaceutical industry, recognizing this type of medication interactions is viewed as a significant task. In thispaper, we discuss the extraction of ADRs from combined medications (two drugs) by using medical transcripts and onlinereviews as the primary sources. Here, Natural Language Processing (NLP) techniques are combined with weighted associationrule mining for extracting ADRs due to a single drug from medical transcripts. Single drug ADRs are also obtained from onlinehealth reviews using an ensemble classifier. These drugs along with their ADRs are used for constructing two-drug (combinedmedication) associated ADRs dataset. Further, by using the dataset of combined medications, the interaction of the medicationsand the reactions that are associated with that drug combination are predicted. In the first two phases of single drug associatedADR prediction, weighted association rule mining and ensemble classifier got an accuracy of 88%. The proposed model obtainedan accuracy of 85.3%. |
