Mining association patterns of drug-interactions using post marketing FDA’s spontaneous reporting data

Ibrahim, Heba Ezzat; A, Saad; Abdo, A.; Eldin, Ahmed Sharaf

doi:10.1016/j.jbi.2016.02.009

Cited by 73 publications

(44 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Effective early detection of DDIs has been a desirable goal for pharmaceutical companies and clinicians to avoid serious health complications for patients. A variety of studies have been done for discovering DDIs based on clinical and computational approaches, for example through mining DDIs from scientific literature (Tari et al, 2010; (Ibrahim et al, 2016), and the Electronic Health Record (Pathak et al, 2013). Clinical studies are conducted to determine suspected interactions (Wienkers and Heath, 2005), yet their investigative processes are slow and often consider only a small numbers of drugs and targets (Bjornsson et al, 2003) suspected to result in interactions.…”

Section: Discussionmentioning

confidence: 99%

D4: Deep Drug-drug interaction Discovery and Demystification

Noor

Liu-Wei

Barnawi

et al. 2020

Preprint

View full text Add to dashboard Cite

Motivation: Drug-drug interactions (DDIs) are complex processes which may depend on many clinical and non-clinical factors. Identifying and distinguishing ways in which drugs interact remains a challenge. To minimize DDIs and to personalize treatment based on accurate stratification of patients, it is crucial that mechanisms of interaction can be identified. Most DDIs are a consequence of metabolic mechanisms of interaction, but DDIs with different mechanisms occur less frequently and are therefore more difficult to identify. Results: We developed a method (D4) for computationally identifying potential DDIs and determining whether they interact based on one of eleven mechanisms of interaction. D4 predicts DDIs and their mechanisms through features that are generated through a deep learning approach from phenotypic and functional knowledge about drugs, their side-effects and targets. Our findings indicate that our method is able to identify known DDIs with high accuracy and that D4 can determine mechanisms of interaction. We also identify numerous novel and potential DDIs for each mechanism of interaction and evaluate our predictions using DDIs from adverse event reporting systems.

show abstract

Section: Discussionmentioning

confidence: 99%

D4: Deep Drug-drug interaction Discovery and Demystification

Noor

Liu-Wei

Barnawi

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The Signal Generator module adapts MARAS [QKW∗17], a drug interaction signal extraction and scoring technique. Other machine learning techniques [SFG16,ADK∗03,HCF10,ISAE16,CLH∗17] are also candidates for producing signals that serve as input to DIVA. These generated signals model the association between drugs and ADRs, depicted in Fig.…”

Section: Diva System Overviewmentioning

confidence: 99%

“…Automated approaches to drug reaction analysis are also insufficient. Machine learning techniques proposed to mine drug reaction reports for signal hypotheses tend to generate a large number of candidate signals [SFG16,ADK∗03,HCF10,ISAE16,CLH∗17]. For example, n distinct drugs and m unique adverse reactions across a set of reports result in up to O (2 n+m ) signals in the worst case.…”

Section: Introductionmentioning

confidence: 99%

DIVA: Exploration and Validation of Hypothesized Drug‐Drug Interactions

Kakar

Qin

Rundensteiner

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Adverse reactions caused by drug‐drug interactions are a major public health concern. Currently, adverse reaction signals are detected through a tedious manual process in which drug safety analysts review a large number of reports collected through post‐marketing drug surveillance. While computational techniques in support of this signal analysis are necessary, alone they are not sufficient. In particular, when machine learning techniques are applied to extract candidate signals from reports, the resulting set is (1) too large in size, i.e., exponential to the number of unique drugs and reactions in reports, (2) disconnected from the underlying reports that serve as evidence and context, and (3) ultimately requires human intervention to be validated in the domain context as a true signal warranting action. In this work, we address these challenges though a visual analytics system, DIVA, designed to align with the drug safety analysis workflow by supporting the detection, screening, and verification of candidate drug interaction signals. DTVA's abstractions and encodings are informed by formative interviews with drug safety analysts. DIVA's coordinated visualizations realize a proposed novel augmented interaction data model (AIM) which links signals generated by machine learning techniques with domain‐specific metadata critical for signal analysis. DIVA's alignment with the drug review process allows an analyst to interactively screen for important signals, triage signals for in‐depth investigation, and validate signals by reviewing the underlying reports that serve as evidence. The evaluation of DIVA encompasses case‐studies and interviews by drug analysts at the US Food and Drug Administration ‐ both of which confirm that DIVA indeed is effective in supporting analysts in the critical task of exploring and verifying dangerous drug‐drug interactions.

show abstract

“…Pharmacovigilance (PhV) has been defined by the World Health Organization (WHO,2004) as activities are done to monitor detection, assessment, understanding, and prevention of any obnoxious adverse reactions to drugs at a therapeutic concentration in animals and humans (Ibrahim et al, 2016). As part of Good Manufacturing Practices (GMP), the United States Pharmacopoeia (USP) Microbial Limits Test provides methods for determining the safety of a product through the absence of indicator microorganisms, which can be considered a hazard to consumers and indicative of contamination.…”

Section: Introductionmentioning

confidence: 99%

Detection and Identification of Clostridium Perfringens in Some Locally Oral Pharmaceutical Samples

Sharaf

2018

Al-Azhar Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

Contamination of oral pharmaceuticals with microorganisms may lead to deleterious effects on the therapeutic properties of the drug, and may potentially cause injuries to intended recipients. Thirty contaminated samples were detected representing 2% out of 1500 total collected samples. Out of 30 contaminated samples, only six samples (20%) revealed the presence of Clostridium perfringens. The biofilm assay was performed using the Microtiter Plate Method (MTP) for the six of the detected C. perfringens were three isolates biofilm forming. PCR multiplex was done for C. perfringens showed the presence of alpha toxin gene among all species. In spite of the current recommendation for a conventional detection method for Closterium spp., the application of multiplex PCR showed to be more, effective and able to detect Clostridium toxins genes.

show abstract

Mining association patterns of drug-interactions using post marketing FDA’s spontaneous reporting data

Abstract: The proposed method could efficiently detect DIAE signals from SRS data as well as, identifying rare adverse drug reactions (ADRs).

Cited by 73 publications

References 43 publications

D4: Deep Drug-drug interaction Discovery and Demystification

D4: Deep Drug-drug interaction Discovery and Demystification

DIVA: Exploration and Validation of Hypothesized Drug‐Drug Interactions

Detection and Identification of Clostridium Perfringens in Some Locally Oral Pharmaceutical Samples

Contact Info

Product

Resources

About