Geriatrics on beers criteria medications at risk of adverse drug events using real-world data

Bidirectional Long Short-Term Memory-Based Detection of Adverse Drug Reaction Posts Using Korean Social Networking Services Data: Deep Learning Approaches

Background

Social networking services (SNS) closely reflect the lives of individuals in modern society and generate large amounts of data. Previous studies have extracted drug information using relevant SNS data. In particular, it is important to detect adverse drug reactions (ADRs) early using drug surveillance systems. To this end, various deep learning methods have been used to analyze data in multiple languages in addition to English.

Objective

A cautionary drug that can cause ADRs in older patients was selected, and Korean SNS data containing this drug information were collected. Based on this information, we aimed to develop a deep learning model that classifies drug ADR posts based on a recurrent neural network.

Methods

In previous studies, ketoprofen, which has a high prescription frequency and, thus, was referred to the most in posts secured from SNS data, was selected as the target drug. Blog posts, café posts, and NAVER Q&A posts from 2005 to 2020 were collected from NAVER, a portal site containing drug-related information, and natural language processing techniques were applied to analyze data written in Korean. Posts containing highly relevant drug names and ADR word pairs were filtered through association analysis, and training data were generated through manual labeling tasks. Using the training data, an embedded layer of word2vec was formed, and a Bidirectional Long Short-Term Memory (Bi-LSTM) classification model was generated. Then, we evaluated the area under the curve with other machine learning models. In addition, the entire process was further verified using the nonsteroidal anti-inflammatory drug aceclofenac.

Results

Among the nonsteroidal anti-inflammatory drugs, Korean SNS posts containing information on ketoprofen and aceclofenac were secured, and the generic name lexicon, ADR lexicon, and Korean stop word lexicon were generated. In addition, to improve the accuracy of the classification model, an embedding layer was created considering the association between the drug name and the ADR word. In the ADR post classification test, ketoprofen and aceclofenac achieved 85% and 80% accuracy, respectively.

Conclusions

Here, we propose a process for developing a model for classifying ADR posts using SNS data. After analyzing drug name-ADR patterns, we filtered high-quality data by extracting posts, including known ADR words based on the analysis. Based on these data, we developed a model that classifies ADR posts. This confirmed that a model that can leverage social data to monitor ADRs automatically is feasible.

Use of potentially inappropriate medication for elderly patients in tertiary care hospital of Riyadh, Saudi Arabia

Background and objectives

The elderly population is affected by chronic diseases and lifelong medication. The American Geriatrics Society (AGS) Beers Criteria is a comprehensive approach to medication usage in the older population to reduce potentially inappropriate medication (PIM) use. The purpose of this study was to assess the usage of PIMs in elderly patients upon discharge from tertiary care hospital settings in Riyadh, Saudi Arabia, using the AGS Beers Criteria 2019.

Methods

The data was obtained from the medical records of 1237 patients (>65 years) who were discharged from medical or surgical wards at two hospitals affiliated with King Abdulaziz Medical City. The data was analyzed to determine the prevalence of PIM prescription, and the proportional odds of the independent factors influencing outcomes were estimated using ordinal regression analysis for criteria 1 and 2, while Binary regression analysis was conducted for criterion 3.

Results

There were approximately equal numbers of male and female participants in our study (male: 50.8 % vs. female: 49.2 %). One-third of the patients were above the age of 80 years, with 41 % being between the ages of 70 and 80 years. Moreover, almost 70 % of the samples had chronic illnesses. The overall prevalence of PIMs was 29.2 %, with 11 % of PIMs to be avoided in elderly patients and 17 % to be used with caution in the elderly, while disease-specific PIMs were identified in 1.2 % of the patients. The most common PIM class was proton pump inhibitors (44.41 %), and patients discharged from the surgical unit were more likely to be prescribed PIMs. Proton pump inhibitors (44.41 %) were the most inappropriately prescribed drug class, and patients discharged from the surgical unit were more likely to be prescribed PIMs.

Conclusion

The study noticed that male gender, the presence of multiple diseases, and obesity are associated with more than one PIM prescription. There is a need to streamline the surgical department's prescription procedure to eliminate prescription disparities. Prescription monitoring is recommended to avoid medication errors, particularly in patients who are taking multiple medications.