Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems
Drug–drug interactions (DDIs) can pose significant risks in clinical practice and pharmacovigilance. Although traditional association rule mining techniques, such as the Apriori algorithm, have been applied to drug safety signal detection, their performance in DDI detection has not been systematical...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/11/1710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850158965468430336 |
|---|---|
| author | Yajie He Jianping Sun Xianming Tan |
| author_facet | Yajie He Jianping Sun Xianming Tan |
| author_sort | Yajie He |
| collection | DOAJ |
| description | Drug–drug interactions (DDIs) can pose significant risks in clinical practice and pharmacovigilance. Although traditional association rule mining techniques, such as the Apriori algorithm, have been applied to drug safety signal detection, their performance in DDI detection has not been systematically evaluated, especially in the Spontaneous Reporting System (SRS), which contains a large number of drugs and AEs with a complex correlation structure and unobserved latent factors. This study fills that gap through comprehensive simulation studies designed to mimic key features of SRS data. We show that latent confounding can substantially distort detection accuracy: for example, when using the reporting ratio (RR) as a secondary indicator, the area under the curve (AUC) for detecting main effects dropped by approximately 30% and for DDIs by about 15%, compared to settings without confounding. A real-world application using 2024 VAERS data further illustrates the consequences of unmeasured bias, including a potentially spurious association between COVID-19 vaccination and infection. These findings highlight the limitations of existing methods and emphasize the need for future tools that account for latent factors to improve the reliability of safety signal detection in pharmacovigilance analyses. |
| format | Article |
| id | doaj-art-eacc1bddcbcd477a81ad6ee2da65a0cb |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-eacc1bddcbcd477a81ad6ee2da65a0cb2025-08-20T02:23:44ZengMDPI AGMathematics2227-73902025-05-011311171010.3390/math13111710Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting SystemsYajie He0Jianping Sun1Xianming Tan2Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USADepartment of Mathematics and Statistics, Univerisy of North Carolina at Greensboro, Greensboro, NC 27412, USADepartment of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USADrug–drug interactions (DDIs) can pose significant risks in clinical practice and pharmacovigilance. Although traditional association rule mining techniques, such as the Apriori algorithm, have been applied to drug safety signal detection, their performance in DDI detection has not been systematically evaluated, especially in the Spontaneous Reporting System (SRS), which contains a large number of drugs and AEs with a complex correlation structure and unobserved latent factors. This study fills that gap through comprehensive simulation studies designed to mimic key features of SRS data. We show that latent confounding can substantially distort detection accuracy: for example, when using the reporting ratio (RR) as a secondary indicator, the area under the curve (AUC) for detecting main effects dropped by approximately 30% and for DDIs by about 15%, compared to settings without confounding. A real-world application using 2024 VAERS data further illustrates the consequences of unmeasured bias, including a potentially spurious association between COVID-19 vaccination and infection. These findings highlight the limitations of existing methods and emphasize the need for future tools that account for latent factors to improve the reliability of safety signal detection in pharmacovigilance analyses.https://www.mdpi.com/2227-7390/13/11/1710drug–drug interactionsApriori algorithmspontaneous reporting systemlatent factor |
| spellingShingle | Yajie He Jianping Sun Xianming Tan Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems Mathematics drug–drug interactions Apriori algorithm spontaneous reporting system latent factor |
| title | Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems |
| title_full | Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems |
| title_fullStr | Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems |
| title_full_unstemmed | Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems |
| title_short | Performance of Apriori Algorithm for Detecting Drug–Drug Interactions from Spontaneous Reporting Systems |
| title_sort | performance of apriori algorithm for detecting drug drug interactions from spontaneous reporting systems |
| topic | drug–drug interactions Apriori algorithm spontaneous reporting system latent factor |
| url | https://www.mdpi.com/2227-7390/13/11/1710 |
| work_keys_str_mv | AT yajiehe performanceofapriorialgorithmfordetectingdrugdruginteractionsfromspontaneousreportingsystems AT jianpingsun performanceofapriorialgorithmfordetectingdrugdruginteractionsfromspontaneousreportingsystems AT xianmingtan performanceofapriorialgorithmfordetectingdrugdruginteractionsfromspontaneousreportingsystems |