PMID- 33675157
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20211125
LR  - 20240403
IS  - 1539-1612 (Electronic)
IS  - 1539-1604 (Print)
IS  - 1539-1604 (Linking)
VI  - 20
IP  - 4
DP  - 2021 Jul
TI  - Matrix decomposition in meta-analysis for extraction of adverse event pattern and 
      patient-level safety profile.
PG  - 806-819
LID - 10.1002/pst.2109 [doi]
AB  - The purpose of assessing adverse events (AEs) in clinical studies is to evaluate 
      what AE patterns are likely to occur during treatment. In contrast, it is 
      difficult to specify which of these patterns occurs in each patient. To tackle 
      this challenging issue, we constructed a new statistical model including 
      nonnegative matrix factorization by incorporating background knowledge of 
      AE-specific structures such as severity and drug mechanism of action. The model 
      uses a meta-analysis framework for integrating data from multiple clinical 
      studies because insufficient information is derived from a single trial. We 
      demonstrated the proposed method by applying it to real data consisting of three 
      Phase III studies, two mechanisms of action, five anticancer treatments, 3317 
      patients, 848 AE types, and 99,546 AEs. The extracted typical treatment-specific 
      AE patterns coincided with medical knowledge. We also demonstrated patient-level 
      safety profiles using the data of AEs that were observed by the end of the second 
      cycle.
CI  - (c) 2021 The Authors. Pharmaceutical Statistics published by John Wiley & Sons Ltd.
FAU - Matsuura, Kentaro
AU  - Matsuura K
AUID- ORCID: 0000-0001-5262-055X
AD  - Department of Management Science, Graduate School of Engineering, Tokyo 
      University of Science, Tokyo, Japan.
FAU - Tsuchida, Jun
AU  - Tsuchida J
AUID- ORCID: 0000-0003-2349-2709
AD  - Department of Information and Computer Technology, Faculty of Engineering, Tokyo 
      University of Science, Tokyo, Japan.
FAU - Ando, Shuji
AU  - Ando S
AD  - Department of Information and Computer Technology, Faculty of Engineering, Tokyo 
      University of Science, Tokyo, Japan.
FAU - Sozu, Takashi
AU  - Sozu T
AD  - Department of Information and Computer Technology, Faculty of Engineering, Tokyo 
      University of Science, Tokyo, Japan.
LA  - eng
PT  - Journal Article
DEP - 20210305
PL  - England
TA  - Pharm Stat
JT  - Pharmaceutical statistics
JID - 101201192
SB  - IM
PMC - PMC8359197
OTO - NOTNLM
OT  - clinical trial
OT  - co-occurrence
OT  - nonnegative matrix factorization
OT  - normal dynamic linear model
OT  - pattern extraction
COIS- The authors declare no conflicts of interest.
EDAT- 2021/03/07 06:00
MHDA- 2021/03/07 06:01
PMCR- 2021/08/12
CRDT- 2021/03/06 05:46
PHST- 2021/01/08 00:00 [revised]
PHST- 2020/07/09 00:00 [received]
PHST- 2021/02/14 00:00 [accepted]
PHST- 2021/03/07 06:00 [pubmed]
PHST- 2021/03/07 06:01 [medline]
PHST- 2021/03/06 05:46 [entrez]
PHST- 2021/08/12 00:00 [pmc-release]
AID - PST2109 [pii]
AID - 10.1002/pst.2109 [doi]
PST - ppublish
SO  - Pharm Stat. 2021 Jul;20(4):806-819. doi: 10.1002/pst.2109. Epub 2021 Mar 5.