Accounting for Multiplicity in the Evaluation of “Signals” Obtained by Data Mining from Spontaneous Report Adverse Event Databases

2007 ◽  
Vol 49 (1) ◽  
pp. 151-165 ◽  
Author(s):  
A. Lawrence Gould
Keyword(s):  
Data Mining ◽  
Adverse Event ◽  
Spontaneous Report

Novel Adverse Events of Iloperidone: A Disproportionality Analysis in US Food and Drug Administration Adverse Event Reporting System (FAERS) Database

2019 ◽  
Vol 14 (1) ◽  
pp. 21-26 ◽  
Author(s):  
Viswam Subeesh ◽  
Eswaran Maheswari ◽  
Hemendra Singh ◽  
Thomas Elsa Beulah ◽  
Ann Mary Swaroop
Keyword(s):  
Data Mining ◽  
Adverse Event ◽  
Adverse Events ◽  
Reporting System ◽  
Adverse Event Reporting System ◽  
Adverse Event Reporting ◽  
Disproportionality Analysis ◽  
Positive Signal ◽  
Data Mining Algorithms ◽  
Mining Algorithms

Background: The signal is defined as “reported information on a possible causal relationship between an adverse event and a drug, of which the relationship is unknown or incompletely documented previously”. Objective: To detect novel adverse events of iloperidone by disproportionality analysis in FDA database of Adverse Event Reporting System (FAERS) using Data Mining Algorithms (DMAs). Methodology: The US FAERS database consists of 1028 iloperidone associated Drug Event Combinations (DECs) which were reported from 2010 Q1 to 2016 Q3. We consider DECs for disproportionality analysis only if a minimum of ten reports are present in database for the given adverse event and which were not detected earlier (in clinical trials). Two data mining algorithms, namely, Reporting Odds Ratio (ROR) and Information Component (IC) were applied retrospectively in the aforementioned time period. A value of ROR-1.96SE>1 and IC- 2SD>0 were considered as the threshold for positive signal. Results: The mean age of the patients of iloperidone associated events was found to be 44years [95% CI: 36-51], nevertheless age was not mentioned in twenty-one reports. The data mining algorithms exhibited positive signal for akathisia (ROR-1.96SE=43.15, IC-2SD=2.99), dyskinesia (21.24, 3.06), peripheral oedema (6.67,1.08), priapism (425.7,9.09) and sexual dysfunction (26.6-1.5) upon analysis as those were well above the pre-set threshold. Conclusion: Iloperidone associated five potential signals were generated by data mining in the FDA AERS database. The result requires an integration of further clinical surveillance for the quantification and validation of possible risks for the adverse events reported of iloperidone.

scholarly journals Systematic analysis of safety profile for darunavir and its boosted agents using data mining in the FDA Adverse Event Reporting System database

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xiaojiang Tian ◽  
Yao Yao ◽  
Guanglin He ◽  
Yuntao Jia ◽  
Kejing Wang ◽  
...  
Keyword(s):  
Data Mining ◽  
Adverse Event ◽  
Reporting System ◽  
Proportional Reporting Ratio ◽  
Adverse Event Reporting System ◽  
Adverse Event Reporting ◽  
Reporting Odds Ratio ◽  
Systematic Analysis ◽  
Event Reporting ◽  
Exfoliative Dermatitis

AbstractThis current investigation was aimed to generate signals for adverse events (AEs) of darunavir-containing agents by data mining using the US Food and Drug Administration Adverse Event Reporting System (FAERS). All AE reports for darunavir, darunavir/ritonavir, or darunavir/cobicistat between July 2006 and December 2019 were identified. The reporting Odds Ratio (ROR), proportional reporting ratio (PRR), and Bayesian confidence propagation neural network (BCPNN) were used to detect the risk signals. A suspicious signal was generated only if the results of the three algorithms were all positive. A total of 10,756 reports were identified commonly observed in hepatobiliary, endocrine, cardiovascular, musculoskeletal, gastrointestinal, metabolic, and nutrition system. 40 suspicious signals were generated, and therein 20 signals were not included in the label. Severe high signals (i.e. progressive extraocular muscle paralysis, acute pancreatitis, exfoliative dermatitis, acquired lipodystrophy and mitochondrial toxicity) were identified. In pregnant women, umbilical cord abnormality, fetal growth restriction, low birth weight, stillbirth, premature rupture of membranes, premature birth and spontaneous abortion showed positive signals. Darunavir and its boosted agents induced AEs in various organs/tissues, and were shown to be possibly associated with multiple adverse pregnant conditions. This study highlighted some novel and severe AEs of darunavir which need to be monitored prospectively.

Using Data Mining to Predict Safety Actions from FDA Adverse Event Reporting System Data

2007 ◽  
Vol 41 (5) ◽  
pp. 633-643 ◽  
Author(s):  
Alan M. Hochberg ◽  
Stephanie J. Reisinger ◽  
Ronald K. Pearson ◽  
Donald J. O’Hara ◽  
Kevin Hall
Keyword(s):  
Data Mining ◽  
Adverse Event ◽  
Reporting System ◽  
Adverse Event Reporting System ◽  
Adverse Event Reporting ◽  
Event Reporting ◽  
System Data ◽  
Using Data

Comparison of Adverse Drug Reactions for Patients Treated with Tyrosine Kinase Inhibitors: Data Mining of the Public Version of the FDA Adverse Event Reporting System (AERS)

Blood ◽  
2011 ◽  
Vol 118 (21) ◽  
pp. 1698-1698
Author(s):  
Tetsuya Tanimoto ◽  
Yasuo Oshima ◽  
Koichiro Yuji ◽  
Masahiro Kami
Keyword(s):  
Data Mining ◽  
Adverse Event ◽  
Odds Ratio ◽  
Kinase Inhibitors ◽  
Reporting System ◽  
Adverse Event Reporting System ◽  
Adverse Event Reporting ◽  
Drug Reactions ◽  
Suspected Drug ◽  
Event Reporting

Abstract Abstract 1698 Backgrounds: The consecutive approvals of tyrosine kinase inhibitors (TKIs) have been changing the landscape of treatment strategy for patients with chronic myeloid leukemia (CML). Currently, three TKIs are available worldwide, including imatinib (Glivec/Gleevec; Novartis Pharmaceuticals, East hanover, NJ), nilotinib (Tasigna; Novartis Pharmaceuticals) and dasatinib (Sprycel; Bristol-Myers Squibb, Princeton, NJ). Although second generation TKIs (nilotinib and dasatinib) have shown their efficacy and safety in recent clinical trials, additional data are needed for better understanding and differences in their safety profiles may be helpful when choosing a TKI. We compared the adverse drug reactions (ADRs) for patients treated with three TKIs using spontaneous adverse event reporting after approval to investigate the characteristics of safety profiles. Method: To compare adverse events characteristics among three TKIs, the case/noncase adverse events reports associated with TKIs use were retrieved from the U.S. Food and Drug Administration Adverse Event Reporting System (AERS) between 2004 and 2010. We calculated the reporting odds ratio (ROR), which is known as one of data mining algorithms for signal detection techniques of ADRs, characterized by providing a fast and cost-efficient way of detecting possible ADR signals. All events in the AERS have been coded for data entry in accordance with the standardized terminology, known as Preferred Terms, in the Medical Dictionary for Regulatory Activities. The ROR is similar to the idea of odds ratio, calculating the odds of exposure of the suspected drug in patients who had events divided by the odds of exposure of the suspected drug in those without events. The ROR -1.96 standard error greater than 1 with at least 4 ADR reports was used as a signal criterion in this study. Results: We identified 18,979 ADRs for imatinib, 5,388 ADRs for nilotinib, and 2,482 ADRs for dasatinib. The number of ADRs flagged by our signal criterion was 91 for imatinib, 82 for nilotinib, and 109 for dasatinib. Top 10 lists of ADRs with higher ROR are shown in Table for each TKI. The safety profiles were almost different among TKIs. ADRs related to skin and hepatic function were noted for imatinib, whereas ADRs related to cardiac events were prominent for nilotinib, and ADRs related to lymphocytosis, edema and effusion were noticeable for dasatinib. The different dosing requirements of dasatinib and nilotinib may be an additional factor of ADRs. Conclusions: ADRs reported in the AERS for each TKI were relatively consistent with known characteristics of ADRs reported in previous clinical trials. Our information would be supportive data for choosing a TKI for CML patients based on comorbidities and drug safety profiles. The choice of therapy in a given patient with CML may depend on age, past history and comorbidities as well as disease risk score and mutational analysis. Disclosures: Oshima: Sanofi Aventis: Employment.

Large scale adverse event data mining for targeted therapies development.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. 2538-2538
Author(s):  
Mayur Sarangdhar ◽  
Bruce Aronow ◽  
Anil Goud Jegga ◽  
Brian Turpin ◽  
Erin Haag Breese ◽  
...  
Keyword(s):  
Data Mining ◽  
Clinical Trials ◽  
Adverse Event ◽  
Big Data ◽  
Real World ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Large Scale ◽  
Checkpoint Inhibitors ◽  
Anaplastic Lymphoma

2538 Background: Targeted anti-cancer small molecule drugs & immune therapies have had a dramatic impact in improving outcomes & the approach to clinical trials. Increasingly, regulatory approvals are expedited with small studies designed to identify strong efficacy signals. However, this may limit the extent of safety profiling. The use of large scale/big data meta-analyses can identify novel safety & efficacy signals in "real-world" medical settings. Methods: We used AERSMine, an open-source data mining platform to identify drug toxicity signatures in the FDA’s Adverse Event Reporting System of 8.6 million patients. We identified patients (n = 732,198) who received either traditional and targeted cancer therapy & identified therapy-specific toxicity patterns. Patients were classified based on exposures: anthracyclines (n = 83,179), platinum (117,993), antimetabolites (93,062), alkylators (81,507), antimicrotubule agents (97,726), HER2 inhibitors (40,040), VEGFis (79,144), VEGF-TKis (90,734), multi TKis (34,457), anaplastic lymphoma Kis (7,635), PI3K-AKT-mTOR inhibitors (33,864), Bruton TKis (9,247), MEKis (4,018), immunomodulatory agents (174,810), proteasome inhibitors (44,681), immune checkpoint inhibitors (20,287). Pharmacovigilance metrics [Relative Risks & safety signals] were used to establish statistical correlation & toxicity signatures were differentiated using the Kolmogorov–Smirnov test. Results: To validate the use of the AERSMine to detect AEs, we focused on cardiotoxicity. It identified classic drug associated AEs (e.g. ventricular dysfunction with anthracyclines, HER2is & VEGFis; VEGFi hypertension & vascular toxicity; multi TKIs vascular events). AERSMine also identified recently reported uncommon toxicities of myositis/myocarditis with immune checkpoint inhibitors. It indicated a higher frequency of myositis/myocarditis with combination immune checkpoint therapy, paralleling industry corporate safety databases. These toxicities were reported at higher frequencies in patients > 65 yrs. Conclusions: AERSMine “big data” analyses provide a sensitive tool to detect potential new patterns of AEs simultaneously across multiple clinical trials & in the real-world setting.

Sign in / Sign up

Export Citation Format

Share Document