PMID- 36794497
OWN - NLM
STAT- MEDLINE
DCOM- 20231102
LR  - 20231102
IS  - 1744-764X (Electronic)
IS  - 1474-0338 (Linking)
VI  - 22
IP  - 7
DP  - 2023 Jul-Dec
TI  - Application of tree-based machine learning classification methods to detect 
      signals of fluoroquinolones using the Korea Adverse Event Reporting System 
      (KAERS) database.
PG  - 629-636
LID - 10.1080/14740338.2023.2181341 [doi]
AB  - BACKGROUND: Safety issues for fluoroquinolones have been provided by regulatory 
      agencies. This study was conducted to identify signals of fluoroquinolones 
      reported in the Korea Adverse Event Reporting System (KAERS) using tree-based 
      machine learning (ML) methods. RESEARCH DESIGN AND METHODS: All adverse events 
      (AEs) associated with the target drugs reported in the KAERS from 2013 to 2017 
      were matched with drug label information. A dataset containing label-positive and 
      -negative AEs was arbitrarily divided into training and test sets. Decision tree, 
      random forest (RF), bagging, and gradient boosting machine (GBM) were fitted on 
      the training set with hyperparameters tuned using five-fold cross-validation and 
      applied to the test set. The ML method with the highest area under the curve 
      (AUC) scores was selected as the final ML model. RESULTS: Bagging was selected as 
      the final ML model for gemifloxacin (AUC score: 1) and levofloxacin (AUC: 
      0.9987). RF was selected in ciprofloxacin, moxifloxacin, and ofloxacin (AUC 
      scores: 0.9859, 0.9974, and 0.9999 respectively). We found that the final ML 
      methods detected additional signals that were not detected using the 
      disproportionality analysis (DPA) methods. CONCLUSIONS: The bagging-or-RF-based 
      ML methods performed better than DPA and detected novel AE signals previously 
      unidentified using the DPA methods.
FAU - Jang, Min-Gyo
AU  - Jang MG
AD  - College of Pharmacy, Research Institute of Pharmaceutical Sciences, Kyungpook 
      National University, Daegu, Republic of Korea.
FAU - Cha, SangHun
AU  - Cha S
AD  - Department of Statistics, College of Natural Sciences, Kyungpook National 
      University, Daegu, Republic of Korea.
FAU - Kim, Seunghwak
AU  - Kim S
AD  - Department of Statistics, College of Natural Sciences, Kyungpook National 
      University, Daegu, Republic of Korea.
FAU - Lee, Sojung
AU  - Lee S
AD  - Department of Statistics, College of Natural Sciences, Kyungpook National 
      University, Daegu, Republic of Korea.
FAU - Lee, Kyeong Eun
AU  - Lee KE
AD  - Department of Statistics, College of Natural Sciences, Kyungpook National 
      University, Daegu, Republic of Korea.
FAU - Shin, Kwang-Hee
AU  - Shin KH
AUID- ORCID: 0000-0002-0915-2700
AD  - College of Pharmacy, Research Institute of Pharmaceutical Sciences, Kyungpook 
      National University, Daegu, Republic of Korea.
LA  - eng
PT  - Journal Article
DEP - 20230223
PL  - England
TA  - Expert Opin Drug Saf
JT  - Expert opinion on drug safety
JID - 101163027
RN  - 0 (Fluoroquinolones)
RN  - 6GNT3Y5LMF (Levofloxacin)
RN  - 5E8K9I0O4U (Ciprofloxacin)
SB  - IM
MH  - Humans
MH  - *Fluoroquinolones/adverse effects
MH  - *Levofloxacin
MH  - Ciprofloxacin
MH  - Machine Learning
MH  - Republic of Korea
OTO - NOTNLM
OT  - Disproportionality analysis
OT  - fluoroquinolones
OT  - signal detection
OT  - spontaneous reporting system
OT  - tree-based machine learning
EDAT- 2023/02/17 06:00
MHDA- 2023/02/17 06:01
CRDT- 2023/02/16 04:04
PHST- 2023/02/17 06:01 [medline]
PHST- 2023/02/17 06:00 [pubmed]
PHST- 2023/02/16 04:04 [entrez]
AID - 10.1080/14740338.2023.2181341 [doi]
PST - ppublish
SO  - Expert Opin Drug Saf. 2023 Jul-Dec;22(7):629-636. doi: 
      10.1080/14740338.2023.2181341. Epub 2023 Feb 23.