Detecting Drugs That Cause Thrombocytopenia: A Comparison of Three Methods: Tests for Drug-Dependent Anti-Platelet Antibodies (DDab), Published Case Reports, and Data Mining of the US FDA Adverse Event Reporting System (AERS) Database.

Blood ◽  
2007 ◽  
Vol 110 (11) ◽  
pp. 2087-2087 ◽  
Author(s):  
Xiaoning Li ◽  
Richard H. Aster ◽  
Brian R. Curtis ◽  
Daniel W. Bougie ◽  
Sara K. Vesely ◽  
...  
Keyword(s):  
Data Mining ◽  
Clinical Evidence ◽  
Case Reports ◽  
Adverse Event Reporting System ◽  
Data Mining Algorithm ◽  
Serum Samples ◽  
Drug Induced ◽  
Level Of Evidence ◽  
Post Marketing Surveillance ◽  
Drug Dependent

Abstract Acute thrombocytopenia is one of the most common serious adverse reactions to drugs and can be caused by many drugs. For evaluation of unexpected thrombocytopenia, it is important to know the relative risks of thrombocytopenia among the patient’s current medications. However identification of drugs that can cause thrombocytopenia is not standardized; multiple distinct methods are used: detection of drug-dependent antibodies, analysis of published case reports to establish the level of evidence for the drug as a cause of thrombocytopenia (http://moon.ouhsc.edu/jgeorge), and reporting to MedWatch, the FDA AERS. We have previously compared drugs that had “definite” or “probable” evidence for causing thrombocytopenia in published reports to drugs that had a significant association with thrombocytopenia determined by data mining of the FDA AERS database, defined as a signal of disproportionate reporting (SDR) that exceeded a standard predetermined value (Li, et al. Blood2006;108:140a). We have now expanded our analysis to include flow cytometry detection of DDab in the serum of patients with suspected drug-induced thrombocytopenia. 401 drugs have been suspected as a cause of thrombocytopenia by serum samples submitted for identification of DDab and in case reports. All 401 drugs, including drugs that were and were not shown to be associated with DDab and also drugs that did or did not have “definite” or “probable” evidence for causing thrombocytopenia in case reports, were searched for in the AERS database using a data mining algorithm to identify a significant association with thrombocytopenia. In this analysis, drugs that were not reported in a publication, were not tested for DDab, or were not found in the AERS database were coded as not significant for that method. 204 (51%) of the 401 drugs were significantly associated with thrombocytopenia by 1 or more methods; DDab identified 12% (47), case reports 19% (75), and data mining 36% (143). However, there was limited agreement among these 3 methods for identifying a significant association with thrombocytopenia. Significant by all 3 methods 13 drugs (3%) Significant by any 2 methods 35 drugs (9%) Significant only by detection of DDab 21 drugs (5%) Significant only by case reports 39 drugs (10%) Significant only by data mining 96 drugs (24%) Not significant by any of the 3 methods 197 drugs (49%) None of the 3 methods are sufficient to identify all drugs capable of causing thrombocytopenia. Data mining is a screening tool of existing data and therefore may be more sensitive but less specific than demonstration of DDab and reported clinical evidence. Reports to MedWatch are simple to submit but the reliability is uncertain. Critical assessment of clinical evidence from published case reports may be more specific for identifying drugs that can cause thrombocytopenia, but substantial effort is required to publish a case report. Detection of DDab specifically identifies drugs that can cause thrombocytopenia and also provides understanding of the biologic mechanisms, but tests for DDab are not standardized in routine clinical laboratories. Conclusions. Use of multiple approaches is important to enhance post-marketing surveillance and to provide a comprehensive understanding of drug-induced thrombocytopenia.

Detecting Drugs That Cause Thrombocytopenia: A Comparison of Published Case Reports and Data Mining of the US FDA Adverse Event Reporting System (AERS) Database.

Blood ◽  
2006 ◽  
Vol 108 (11) ◽  
pp. 462-462
Author(s):  
Xiaoning Li ◽  
Deirdra R. Terrell ◽  
James N. George ◽  
Sara K. Vesely
Keyword(s):  
Data Mining ◽  
Health Care Professionals ◽  
Clinical Evidence ◽  
Case Reports ◽  
Adverse Event Reporting System ◽  
Drug Induced ◽  
Significant Evidence ◽  
Post Marketing Surveillance ◽  
The Us ◽  
Us Fda

Abstract Acute thrombocytopenia is one of the most common serious adverse reactions to drugs. Identification of drugs that can cause thrombocytopenia may occur by publication of case reports based on clinical evidence. However there is currently no consensus for adjudicating causality of adverse drug reactions, which still requires the readers’ judgment of the case report. Detection of drug-associated thrombocytopenia may also be facilitated by statistical algorithms used by health authorities and pharmaceutical companies to screen large databases of spontaneous reporting to look for statistical associations between reported drugs and thrombocytopenia. AERS is a computerized database of suspected adverse drug reaction reports provided by pharmaceutical manufacturers by regulation and voluntarily submitted by health care professionals and consumers. We have systematically reviewed all published case reports of drug-induced thrombocytopenia through August 2004, using one set of criteria to assess a significant association of a drug with thrombocytopenia (Ann Int Med129:886,1999). We compared these data to results obtained by applying two mining algorithms to data derived from the US FDA AERS database. For purposes of this analysis a significant statistical association of a drug with thrombocytopenia from the AERS was defined as a signal of disproportionate reporting (SDR) that exceeded a standard predetermined value. SDRs do not necessarily reflect causality and can result from confounding or numerous reporting artifacts that plague spontaneous reports. 203 drugs have been reported as possibly causing thrombocytopenia in both published reports and in the FDA database. Among these 203 drugs, analysis of the case reports determined that a significant association with thrombocytopenia was present for 66 (33%) drugs; for 137 drugs, the association was not significant or the data were insufficient. In the data mining analysis SDRs exceeded the standard value for 135 (67%) of the drugs; the remainder were not associated with an SDR. However there was limited agreement between these 2 methods for identifying significant evidence for a drug association with thrombocytopenia. Significant relation by both methods 48 drugs (24%) Not significant by either method 50 drugs (25%) Significant by case reports but not by data mining 18 drugs (9%) Significant by data mining but not by case reports 87 drugs (42%) For the 48 drugs for which a significant association with thrombocytopenia was determined by published reports and was also statistically distinctive by data mining, we determined which method provided earlier identification of drug-induced thrombocytopenia. For 7 drugs the evidence for a significant association occurred in the same year; for 21 drugs, the significant evidence from published case reports preceded the SDR; for 20 drugs, the SDR preceded the evidence from published case reports. CONCLUSION. Neither published case reports nor data mining of the US FDA database are sufficient to identify all drugs with significant evidence for causing thrombocytopenia. The methods reported here have not been validated and implementation may vary between analysts/institutions. Data mining is a screening tool that may be more sensitive but less specific than reported clinical evidence. Use of multiple methods may enhance post-marketing surveillance for drug-induced thrombocytopenia.

scholarly journals Identifying drugs that cause acute thrombocytopenia: an analysis using 3 distinct methods

Blood ◽  
2010 ◽  
Vol 116 (12) ◽  
pp. 2127-2133 ◽  
Author(s):  
Jessica A. Reese ◽  
Xiaoning Li ◽  
Manfred Hauben ◽  
Richard H. Aster ◽  
Daniel W. Bougie ◽  
...  
Keyword(s):  
Case Reports ◽  
Adverse Event Reporting System ◽  
Adverse Event Reporting ◽  
Serum Samples ◽  
Drug Induced ◽  
Clinical Criteria ◽  
Data Mining Algorithms ◽  
Use Of Data ◽  
Drug Dependent ◽  
Mining Algorithms

Abstract Drug-induced immune thrombocytopenia (DITP) is often suspected in patients with acute thrombocytopenia unexplained by other causes, but documenting that a drug is the cause of thrombocytopenia can be challenging. To provide a resource for diagnosis of DITP and for drug safety surveillance, we analyzed 3 distinct methods for identifying drugs that may cause thrombocytopenia. (1) Published case reports of DITP have described 253 drugs suspected of causing thrombocytopenia; using defined clinical criteria, 87 (34%) were identified with evidence that the drug caused thrombocytopenia. (2) Serum samples from patients with suspected DITP were tested for 202 drugs; drug-dependent, platelet-reactive antibodies were identified for 67 drugs (33%). (3) The Food and Drug Administration's Adverse Event Reporting System database was searched for drugs associated with thrombocytopenia by use of data mining algorithms; 1444 drugs had at least 1 report associated with thrombocytopenia, and 573 (40%) drugs demonstrated a statistically distinctive reporting association with thrombocytopenia. Among 1468 drugs suspected of causing thrombocytopenia, 102 were evaluated by all 3 methods, and 23 of these 102 drugs had evidence for an association with thrombocytopenia by all 3 methods. Multiple methods, each with a distinct perspective, can contribute to the identification of drugs that can cause thrombocytopenia.

scholarly journals Drug-induced thrombocytopenia: pathogenesis, evaluation, and management

Hematology ◽  
2009 ◽  
Vol 2009 (1) ◽  
pp. 153-158 ◽  
Author(s):  
James N. George ◽  
Richard H. Aster
Keyword(s):  
Single Dose ◽  
Causal Relation ◽  
Severe Thrombocytopenia ◽  
Antithrombotic Agents ◽  
Drug Induced ◽  
Level Of Evidence ◽  
Common Cause ◽  
Fibrinogen Binding ◽  
Immune Mediated ◽  
Drug Dependent

AbstractAlthough drugs are a common cause of acute immune-mediated thrombocytopenia in adults, the drug etiology is often initially unrecognized. Most cases of drug-induced thrombocytopenia (DITP) are caused by drug-dependent antibodies that are specific for the drug structure and bind tightly to platelets by their Fab regions but only in the presence of the drug. A comprehensive database of 1301 published reports describing 317 drugs, available at www.ouhsc.edu/platelets, provides information on the level of evidence for a causal relation to thrombocytopenia. Typically, DITP occurs 1 to 2 weeks after beginning a new drug or suddenly after a single dose when a drug has previously been taken intermittently. However, severe thrombocytopenia can occur immediately after the first administration of antithrombotic agents that block fibrinogen binding to platelet GP IIb-IIIa, such as abciximab, tirofiban, and eptifibatide. Recovery from DITP usually begins within 1 to 2 days of stopping the drug and is typically complete within a week. Drug-dependent antibodies can persist for many years; therefore, it is important that the drug etiology be confirmed and the drug be avoided thereafter.

scholarly journals Level of Evidence Associated with FDA Safety Communications with Drug Labeling Changes: 2010-2014

2017 ◽  
Vol 8 (1) ◽  
Author(s):  
Benjamin Hixon ◽  
Joseph M. Lowrey ◽  
Lindsay N Hume ◽  
Katelynn Mayberry ◽  
Maisha Kelly Freeman
Keyword(s):  
Drug Safety ◽  
Clinical Evidence ◽  
Conflicts Of Interest ◽  
Case Reports ◽  
Package Insert ◽  
Original Research ◽  
Nominal Data ◽  
Level Of Evidence ◽  
Drug Labeling ◽  
Financial Interests

Purpose: Approximately 800,000 safety reports are submitted to the FDA annually, however, only significant issues generate drug safety communications (DSC). The purpose of this study was to determine the type of clinical evidence used to warrant a change in drug labeling for drugs with DSC between January 1, 2010 and December 31, 2014. Methods: Selected data was obtained from the FDA website. The primary endpoint of the study was the frequency of the types of clinical evidence used in FDA communications, as reported through the FDA DSC. Results were evaluated via descriptive statistics, and chi-squared for nominal data. Results: A total of 2521 drug safety labeling changes were identified and 99 (3.9%) of safety communications met the inclusion criteria. The majority of the labeling changes were associated with single agents (83.8%). The three most frequently reported labeling changes were warnings (68.7%), precautions (58.6%), and patient package insert/medication guide (23.2%). Case reports resulted in the greatest number of documented literature types (n = 791), followed by randomized controlled trials (n = 76), and case control/cohort studies (n = 74). Significantly more evidence for DSCs were classified as Level of Evidence B (LOE B, 68.6%), compared to LOE A (17.1%), and LOE C (14.1%) (p = 0.007). Conclusions: The majority of drug labeling change initiators was associated with LOE equivalent to B. Practitioners should evaluate data associated with labeling changes to determine how to interpret the information for their patients. Conflict of Interest We declare no conflicts of interest or financial interests that the authors or members of their immediate families have in any product or service discussed in the manuscript, including grants (pending or received), employment, gifts, stock holdings or options, honoraria, consultancies, expert testimony, patents and royalties.   Type: Original Research

MONITORING OF OPERATIONAL LOGISTIC PROCESSES IN GENERAL CARGO WAREHOUSES USING PREDICTIVE ANALYSIS

2019 ◽  
Vol 13 (1) ◽  
pp. 27-36
Author(s):  
Andreas Neubert
Keyword(s):  
Data Mining ◽  
Human Error ◽  
Predictive Analysis ◽  
Data Mining Algorithm ◽  
It Infrastructure ◽  
Monitoring Procedure ◽  
Manual Recording ◽  
Mining Tool ◽  
General Cargo ◽  
Different Characteristics

Due to the different characteristics of the piece goods (e.g. size and weight), they are transported in general cargo warehouses by manually-operated industrial trucks such as forklifts and pallet trucks. Since manual activities are susceptible to possible human error, errors occur in logistical processes in general cargo warehouses. This leads to incorrect loading, stacking and damage to storage equipment and general cargo. It would be possible to reduce costs arising from errors in logistical processes if these errors could be remedied in advance. This paper presents a monitoring procedure for logistical processes in manually-operated general cargo warehouses. This is where predictive analysis is applied. Seven steps are introduced with a view to integrating predictive analysis into the IT infrastructure of general cargo warehouses. These steps are described in detail. The CRISP4BigData model, the SVM data mining algorithm, the data mining tool R, the programming language C++ for the scoring in general cargo warehouses represent the results of this paper. After having created the system and installed it in general cargo warehouses, initial results obtained with this method over a certain time span will be compared with results obtained without this method through manual recording over the same period.

Implementation of data mining as a support of business application strategy

2018 ◽  
Vol 5 (1) ◽  
pp. 47-55
Author(s):  
Florensia Unggul Damayanti
Keyword(s):  
Data Mining ◽  
Random Forest ◽  
Business Strategy ◽  
Input Parameter ◽  
Data Mining Algorithm ◽  
Complex Data ◽  
Business Decision ◽  
Marketing Department ◽  
Business Application ◽  
Complex Data Sets

Data mining help industries create intelligent decision on complex problems. Data mining algorithm can be applied to the data in order to forecasting, identity pattern, make rules and recommendations, analyze the sequence in complex data sets and retrieve fresh insights. Yet, increasing of technology and various techniques among data mining availability data give opportunity to industries to explore and gain valuable information from their data and use the information to support business decision making. This paper implement classification data mining in order to retrieve knowledge in customer databases to support marketing department while planning strategy for predict plan premium. The dataset decompose into conceptual analytic to identify characteristic data that can be used as input parameter of data mining model. Business decision and application is characterized by processing step, processing characteristic and processing outcome (Seng, J.L., Chen T.C. 2010). This paper set up experimental of data mining based on J48 and Random Forest classifiers and put a light on performance evaluation between J48 and random forest in the context of dataset in insurance industries. The experiment result are about classification accuracy and efficiency of J48 and Random Forest , also find out the most attribute that can be used to predict plan premium in context of strategic planning to support business strategy.

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.

Sign in / Sign up

Export Citation Format

Share Document