A systematic review of machine learning applications in predicting opioid associated adverse events
Abstract Machine learning has increasingly been applied to predict opioid-related harms due to its ability to handle complex interactions and generating actionable predictions. This review evaluated the types and quality of ML methods in opioid safety research, identifying 44 studies using supervise...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01312-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594396401369088 |
|---|---|
| author | Carlos R. Ramírez Medina Jose Benitez-Aurioles David A. Jenkins Meghna Jani |
| author_facet | Carlos R. Ramírez Medina Jose Benitez-Aurioles David A. Jenkins Meghna Jani |
| author_sort | Carlos R. Ramírez Medina |
| collection | DOAJ |
| description | Abstract Machine learning has increasingly been applied to predict opioid-related harms due to its ability to handle complex interactions and generating actionable predictions. This review evaluated the types and quality of ML methods in opioid safety research, identifying 44 studies using supervised ML through searches of Ovid MEDLINE, PubMed and SCOPUS databases. Commonly predicted outcomes included postoperative opioid use (n = 15, 34%) opioid overdose (n = 8, 18%), opioid use disorder (n = 8, 18%) and persistent opioid use (n = 5, 11%) with varying definitions. Most studies (96%) originated from North America, with only 7% reporting external validation. Model performance was moderate to strong, but calibration was often missing (41%). Transparent reporting of model development was often incomplete, with key aspects such as calibration, imbalance correction, and handling of missing data absent. Infrequent external validation limited the generalizability of current models. Addressing these aspects is critical for transparency, interpretability, and future implementation of the results. |
| format | Article |
| id | doaj-art-36a8cc58c73d4e95b9687e00ce6d503e |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-36a8cc58c73d4e95b9687e00ce6d503e2025-01-19T12:39:52ZengNature Portfolionpj Digital Medicine2398-63522025-01-018111310.1038/s41746-024-01312-4A systematic review of machine learning applications in predicting opioid associated adverse eventsCarlos R. Ramírez Medina0Jose Benitez-Aurioles1David A. Jenkins2Meghna Jani3Centre for Epidemiology Versus Arthritis, Centre for Musculoskeletal Research, Division of Musculoskeletal and Dermatological Sciences, The University of ManchesterDivision of Informatics, Imaging and Data Science, The University of ManchesterDivision of Informatics, Imaging and Data Science, The University of ManchesterCentre for Epidemiology Versus Arthritis, Centre for Musculoskeletal Research, Division of Musculoskeletal and Dermatological Sciences, The University of ManchesterAbstract Machine learning has increasingly been applied to predict opioid-related harms due to its ability to handle complex interactions and generating actionable predictions. This review evaluated the types and quality of ML methods in opioid safety research, identifying 44 studies using supervised ML through searches of Ovid MEDLINE, PubMed and SCOPUS databases. Commonly predicted outcomes included postoperative opioid use (n = 15, 34%) opioid overdose (n = 8, 18%), opioid use disorder (n = 8, 18%) and persistent opioid use (n = 5, 11%) with varying definitions. Most studies (96%) originated from North America, with only 7% reporting external validation. Model performance was moderate to strong, but calibration was often missing (41%). Transparent reporting of model development was often incomplete, with key aspects such as calibration, imbalance correction, and handling of missing data absent. Infrequent external validation limited the generalizability of current models. Addressing these aspects is critical for transparency, interpretability, and future implementation of the results.https://doi.org/10.1038/s41746-024-01312-4 |
| spellingShingle | Carlos R. Ramírez Medina Jose Benitez-Aurioles David A. Jenkins Meghna Jani A systematic review of machine learning applications in predicting opioid associated adverse events npj Digital Medicine |
| title | A systematic review of machine learning applications in predicting opioid associated adverse events |
| title_full | A systematic review of machine learning applications in predicting opioid associated adverse events |
| title_fullStr | A systematic review of machine learning applications in predicting opioid associated adverse events |
| title_full_unstemmed | A systematic review of machine learning applications in predicting opioid associated adverse events |
| title_short | A systematic review of machine learning applications in predicting opioid associated adverse events |
| title_sort | systematic review of machine learning applications in predicting opioid associated adverse events |
| url | https://doi.org/10.1038/s41746-024-01312-4 |
| work_keys_str_mv | AT carlosrramirezmedina asystematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT josebenitezaurioles asystematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT davidajenkins asystematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT meghnajani asystematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT carlosrramirezmedina systematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT josebenitezaurioles systematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT davidajenkins systematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents AT meghnajani systematicreviewofmachinelearningapplicationsinpredictingopioidassociatedadverseevents |