Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database
Adverse drug reaction (ADR) is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM) is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to autom...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
MECS Publisher
2015
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/30447/ |
| _version_ | 1848793986715615232 |
|---|---|
| author | Liu, Yihui Aickelin, Uwe |
| author_facet | Liu, Yihui Aickelin, Uwe |
| author_sort | Liu, Yihui |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Adverse drug reaction (ADR) is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM) is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to automatically extract the medical events or side effects from high-throughput medical events, which are collected from day to day clinical practice. In this study we propose a novel concept of feature matrix to detect the ADRs. Feature matrix, which is extracted from high-throughput medical data from The Health Improvement Network (THIN) database, is created to characterize the medical events for the patients who take drugs. Feature matrix builds the foundation for the irregular and high-throughput medical data. Then feature selection methods are performed on feature matrix to detect the significant features. Finally the ADRs can be located based on the significant features. The experiments are carried out on three drugs: Atorvastatin, Alendronate, and Metoclopramide. Major side effects for each drug are detected and better performance is achieved compared to other computerized methods. The detected ADRs are based on computerized methods, further investigation is needed. |
| first_indexed | 2025-11-14T19:09:01Z |
| format | Article |
| id | nottingham-30447 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:09:01Z |
| publishDate | 2015 |
| publisher | MECS Publisher |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-304472020-05-04T16:59:34Z https://eprints.nottingham.ac.uk/30447/ Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database Liu, Yihui Aickelin, Uwe Adverse drug reaction (ADR) is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM) is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to automatically extract the medical events or side effects from high-throughput medical events, which are collected from day to day clinical practice. In this study we propose a novel concept of feature matrix to detect the ADRs. Feature matrix, which is extracted from high-throughput medical data from The Health Improvement Network (THIN) database, is created to characterize the medical events for the patients who take drugs. Feature matrix builds the foundation for the irregular and high-throughput medical data. Then feature selection methods are performed on feature matrix to detect the significant features. Finally the ADRs can be located based on the significant features. The experiments are carried out on three drugs: Atorvastatin, Alendronate, and Metoclopramide. Major side effects for each drug are detected and better performance is achieved compared to other computerized methods. The detected ADRs are based on computerized methods, further investigation is needed. MECS Publisher 2015-02-01 Article PeerReviewed Liu, Yihui and Aickelin, Uwe (2015) Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database. International Journal of Information Technology and Computer Science, 7 (3). pp. 68-85. ISSN 2074-9015 Biomedical Informatics Data Mining http://www.mecs-press.org/ijitcs/ijitcs-v7-n3/v7n3-10.html doi:10.5815/ijitcs.2015.03.10 doi:10.5815/ijitcs.2015.03.10 |
| spellingShingle | Biomedical Informatics Data Mining Liu, Yihui Aickelin, Uwe Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title | Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title_full | Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title_fullStr | Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title_full_unstemmed | Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title_short | Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database |
| title_sort | feature selection in detection of adverse drug reactions from the health improvement network (thin) database |
| topic | Biomedical Informatics Data Mining |
| url | https://eprints.nottingham.ac.uk/30447/ https://eprints.nottingham.ac.uk/30447/ https://eprints.nottingham.ac.uk/30447/ |