Refining adverse drug reactions using association rule mining for electronic healthcare data
Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an association between two variables is identified due to them both bei...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2014
|
| Online Access: | https://eprints.nottingham.ac.uk/28259/ |
| _version_ | 1848793537054769152 |
|---|---|
| author | Reps, Jenna M. Aickelin, Uwe Ma, Jiangang Zhang, Yanchun |
| author_facet | Reps, Jenna M. Aickelin, Uwe Ma, Jiangang Zhang, Yanchun |
| author_sort | Reps, Jenna M. |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an association between two variables is identified due to them both being associated to a third variable).
In this paper we propose a proof of concept method that learns common associations and uses this knowledge to automatically refine side effect signals (i.e. exposure-outcome associations) by removing instances of the exposure-outcome associations that are caused by confounding. This leaves the signal instances that are most likely to correspond to true side effect occurrences. We then calculate a novel measure termed the confounding-adjusted risk value, a more accurate absolute risk value of a patient experiencing the outcome within 60 days of the exposure.
Tentative results suggest that the method works. For the four signals (i.e. exposure-outcome associations) investigated we are able to correctly filter the majority of exposure-outcome instances that were unlikely to correspond to true side effects. The method is likely to improve when tuning the association rule mining parameters for specific health outcomes.
This paper shows that it may be possible to filter signals at a patient level based on association rules learned from considering patients’ medical histories. However, additional work is required to develop a way to automate the tuning of the method's parameters. |
| first_indexed | 2025-11-14T19:01:52Z |
| format | Conference or Workshop Item |
| id | nottingham-28259 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:01:52Z |
| publishDate | 2014 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-282592020-05-04T20:17:43Z https://eprints.nottingham.ac.uk/28259/ Refining adverse drug reactions using association rule mining for electronic healthcare data Reps, Jenna M. Aickelin, Uwe Ma, Jiangang Zhang, Yanchun Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an association between two variables is identified due to them both being associated to a third variable). In this paper we propose a proof of concept method that learns common associations and uses this knowledge to automatically refine side effect signals (i.e. exposure-outcome associations) by removing instances of the exposure-outcome associations that are caused by confounding. This leaves the signal instances that are most likely to correspond to true side effect occurrences. We then calculate a novel measure termed the confounding-adjusted risk value, a more accurate absolute risk value of a patient experiencing the outcome within 60 days of the exposure. Tentative results suggest that the method works. For the four signals (i.e. exposure-outcome associations) investigated we are able to correctly filter the majority of exposure-outcome instances that were unlikely to correspond to true side effects. The method is likely to improve when tuning the association rule mining parameters for specific health outcomes. This paper shows that it may be possible to filter signals at a patient level based on association rules learned from considering patients’ medical histories. However, additional work is required to develop a way to automate the tuning of the method's parameters. 2014 Conference or Workshop Item PeerReviewed Reps, Jenna M., Aickelin, Uwe, Ma, Jiangang and Zhang, Yanchun (2014) Refining adverse drug reactions using association rule mining for electronic healthcare data. In: IEEE International Conference of Data Mining: Data Mining in Biomedical Informatics and Healthcare (DMBIH) Workshop 2014, 14 Dec 2014, Shenzhen, China. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7022672 |
| spellingShingle | Reps, Jenna M. Aickelin, Uwe Ma, Jiangang Zhang, Yanchun Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title | Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title_full | Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title_fullStr | Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title_full_unstemmed | Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title_short | Refining adverse drug reactions using association rule mining for electronic healthcare data |
| title_sort | refining adverse drug reactions using association rule mining for electronic healthcare data |
| url | https://eprints.nottingham.ac.uk/28259/ https://eprints.nottingham.ac.uk/28259/ |