Matrix decomposition in meta‐analysis for extraction of adverse event pattern and patient‐level safety profile

• Published in: Pharmaceutical statistics : the journal of the pharmaceutical industry Vol. 20; no. 4; pp. 806 - 819
• Main Authors: Matsuura, Kentaro, Tsuchida, Jun, Ando, Shuji, Sozu, Takashi
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Inc 01.07.2021; Wiley Subscription Services, Inc
• Subjects: clinical trial; Clinical trials; co‐occurrence; Main Paper; Main Papers; Meta-analysis; nonnegative matrix factorization; normal dynamic linear model; pattern extraction; Statistical analysis; clinical trial; normal dynamic linear model; co-occurrence; pattern extraction; nonnegative matrix factorization
• ISSN: 1539-1604; 1539-1612
• DOI: 10.1002/pst.2109

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.