Adverse drug event detection using natural language processing: A scoping review of supervised learning methods.
To reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), a computerized approach to analyze text data, has shown promising results for the purpose of ADE detection in the context of...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0279842 |
| _version_ | 1797866808444715008 |
|---|---|
| author | Rachel M Murphy Joanna E Klopotowska Nicolette F de Keizer Kitty J Jager Jan Hendrik Leopold Dave A Dongelmans Ameen Abu-Hanna Martijn C Schut |
| author_facet | Rachel M Murphy Joanna E Klopotowska Nicolette F de Keizer Kitty J Jager Jan Hendrik Leopold Dave A Dongelmans Ameen Abu-Hanna Martijn C Schut |
| author_sort | Rachel M Murphy |
| collection | DOAJ |
| description | To reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), a computerized approach to analyze text data, has shown promising results for the purpose of ADE detection in the context of pharmacovigilance. However, a detailed qualitative assessment and critical appraisal of NLP methods for ADE detection in the context of ADE monitoring in hospitals is lacking. Therefore, we have conducted a scoping review to close this knowledge gap, and to provide directions for future research and practice. We included articles where NLP was applied to detect ADEs in clinical narratives within electronic health records of inpatients. Quantitative and qualitative data items relating to NLP methods were extracted and critically appraised. Out of 1,065 articles screened for eligibility, 29 articles met the inclusion criteria. Most frequent tasks included named entity recognition (n = 17; 58.6%) and relation extraction/classification (n = 15; 51.7%). Clinical involvement was reported in nine studies (31%). Multiple NLP modelling approaches seem suitable, with Long Short Term Memory and Conditional Random Field methods most commonly used. Although reported overall performance of the systems was high, it provides an inflated impression given a steep drop in performance when predicting the ADE entity or ADE relation class. When annotating corpora, treating an ADE as a relation between a drug and non-drug entity seems the best practice. Future research should focus on semi-automated methods to reduce the manual annotation effort, and examine implementation of the NLP methods in practice. |
| first_indexed | 2024-04-09T23:31:18Z |
| format | Article |
| id | doaj.art-e572a27fbe4447e98b0016740a193951 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-09T23:31:18Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-e572a27fbe4447e98b0016740a1939512023-03-21T05:31:57ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01181e027984210.1371/journal.pone.0279842Adverse drug event detection using natural language processing: A scoping review of supervised learning methods.Rachel M MurphyJoanna E KlopotowskaNicolette F de KeizerKitty J JagerJan Hendrik LeopoldDave A DongelmansAmeen Abu-HannaMartijn C SchutTo reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), a computerized approach to analyze text data, has shown promising results for the purpose of ADE detection in the context of pharmacovigilance. However, a detailed qualitative assessment and critical appraisal of NLP methods for ADE detection in the context of ADE monitoring in hospitals is lacking. Therefore, we have conducted a scoping review to close this knowledge gap, and to provide directions for future research and practice. We included articles where NLP was applied to detect ADEs in clinical narratives within electronic health records of inpatients. Quantitative and qualitative data items relating to NLP methods were extracted and critically appraised. Out of 1,065 articles screened for eligibility, 29 articles met the inclusion criteria. Most frequent tasks included named entity recognition (n = 17; 58.6%) and relation extraction/classification (n = 15; 51.7%). Clinical involvement was reported in nine studies (31%). Multiple NLP modelling approaches seem suitable, with Long Short Term Memory and Conditional Random Field methods most commonly used. Although reported overall performance of the systems was high, it provides an inflated impression given a steep drop in performance when predicting the ADE entity or ADE relation class. When annotating corpora, treating an ADE as a relation between a drug and non-drug entity seems the best practice. Future research should focus on semi-automated methods to reduce the manual annotation effort, and examine implementation of the NLP methods in practice.https://doi.org/10.1371/journal.pone.0279842 |
| spellingShingle | Rachel M Murphy Joanna E Klopotowska Nicolette F de Keizer Kitty J Jager Jan Hendrik Leopold Dave A Dongelmans Ameen Abu-Hanna Martijn C Schut Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. PLoS ONE |
| title | Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. |
| title_full | Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. |
| title_fullStr | Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. |
| title_full_unstemmed | Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. |
| title_short | Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. |
| title_sort | adverse drug event detection using natural language processing a scoping review of supervised learning methods |
| url | https://doi.org/10.1371/journal.pone.0279842 |
| work_keys_str_mv | AT rachelmmurphy adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT joannaeklopotowska adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT nicolettefdekeizer adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT kittyjjager adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT janhendrikleopold adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT daveadongelmans adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT ameenabuhanna adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods AT martijncschut adversedrugeventdetectionusingnaturallanguageprocessingascopingreviewofsupervisedlearningmethods |