Conceptual models of drug-drug interactions: A summary of recent efforts
Introduction
Knowledge representation is an essential activity in knowledge engineering. Particular knowledge about a domain (e.g., the patient presents a sudden rise in temperature (39 °C) and neck stiffness and is a suspected case of meningitis) requires prior general knowledge of how concrete objects are related in the world (e.g., A disease presents signs and symptoms. The identification of signs and symptoms is used to diagnose the disease. A suspected case of meningococcal meningitis is defined as any person with sudden onset of fever ( > 38.5 °C) and at least one of the following signs: neck stiffness, altered consciousness or other meningeal signs). Conceptual modeling elicits and describes the general knowledge of a particular domain. The sets of objects and facts in a particular domain constitute its conceptualization, and its formal description, which sometimes includes a graphical notation, is the conceptual model (CM) [1]. Usually, the design of a CM relies on the perspectives of experts in that specific domain. However, different CMs can represent the same domain because they result from human intellectual activity with different objectives. These CMs are abstract models that can be translated into different description languages and interpretable schemata such as ontologies, relational databases or XML schemata.
Because of the growing success of the Semantic Web, ontologies have become one of the most popular formalisms for knowledge representation. Indeed, the most comprehensive repository of biomedical ontologies, BioPortal,1 doubled the number of collected ontologies from ∼200 to more than 400 in the last six years [2]. The enormous complexity of the biological, medical and pharmaceutical domains compels authors to create individual ontologies with more exhaustive descriptions of specific areas within a broader domain. Further, various applications such as the coding and indexing of medical records [3], semantic annotation of biomedical documents [4], data integration from the Semantic Web and Linked Data [5] or data analysis and discovery applications [6] may require different conceptualizations of the same domain.
Thus, some research groups initially develop their own independent conceptualizations de novo, which can lead to multiple isolated CMs that represent different or even overlapping aspects of the same domain. To avoid such duplication, the OBO Foundry,2 a collaborative effort to develop and maintain biomedical ontologies, recommends collaboration to 1) avoid duplication of work, 2) increase interoperability and 3) ensure that ontology content is both scientifically sound and meets community needs [7].
The medical and pharmacological domains are active areas of knowledge-based systems research [8]. Representation of drug-drug interactions (DDIs), a serious type of adverse drug reaction (ADR) that occurs when one drug affects the levels or effects of another drug [9], is an important effort in these domains. DDIs pose serious risks to patients’ safety and increase healthcare costs [10], [11], so their early apprehension is vital in clinical settings [12]. Various research groups have proposed diverse computational approaches that rely on CMs or other formal representations of the domain to improve prediction or management of DDIs. Here, we review the aspects of DDIs that have been conceptualized, characterize how this information has been modeled by different research groups, describe how the different CMs have been finally implemented and illustrate the applications generated from the final CMs.
Section snippets
Literature search
We have searched the bibliographic databases for the medical (MedLine through the PubMed search engine3), computational (IEEE Xplore4 and ACM Digital5) and general (Web of knowledge,6 Scopus7 and Google scholar8) domains, considering only documents
3. Modeling approaches in the DDI domain
The conceptualizations identified here have addressed representation of the DDI domain in very different ways depending on their final purposes. The simplest representation merely indicates an interaction between two drugs, but does not provide any additional information, as in the Pharmaceutical Product Ontology (PPO), an ontology for the integration of pharmaceutical knowledge [15] that combines an OWL-implemented model (Fig. S1) with a SWRL (Semantic Web Rule Language) inference rule to
Comparison of DDI knowledge modeling approaches
Next, we compare the different conceptualizations and analyze the representation of the most relevant concepts in the DDI domain. Table S2 summarizes and compares the contents included in the 15 models.
Description languages and applications
The scope and content of the different CMs were compared above, and we now describe their final formal representations and applications. Most of the CMs discussed here are implemented as OWL ontologies (PPO, Rubrichi et al., DIO, DEI, PKO, DIDEO and DINTO). Moitra et al. build their CM using SADL [35] and translated it into OWL. Khan et al. use RDF, while the DIKB represents the CM as a set of rules in FOL and the evidence taxonomy as an OWL–DL ontology. The CM of Mille et al. is used to build
Discussion and future trends
We have identified, analyzed and compared 15 conceptualization efforts in the DDI domain. To the best of our knowledge, such a comprehensive study of former conceptualizations has not yet been performed or published, although it is an essential step for reusing previous efforts, avoiding duplicated models, and gaining scientific agreement, as recommended by the OBO Foundry. As we have not conducted a systematic review, some related works might have not been included here. However, we have
Acknowledgements
María Herrero-Zazo holds a C. W. Maplethorpe Postdoctoral Fellowship for Pharmaceutical Education and Research at King's College London. This work was partially supported by eGovernAbility-Access project [TIN2014-52665-C2-2-R].
References (66)
- et al.
Bio2RDF: towards a mashup to build bioinformatics knowledge systems
J. Biomed. Inform
(2008) - et al.
Practitioners ’ views on computerized drug – drug interaction alerts in the VA system
J. Am. Med. Inf. Assoc
(2007) - et al.
Summary of Product Characteristics content extraction for a safe drugs usage
J. Biomed. Inform.
(2012) - et al.
A system for the extraction and representation of summary of product characteristics content
Artif. Intell. Med
(2013) - et al.
Computing with evidence Part I: a drug-mechanism evidence taxonomy oriented toward confidence assignment
J. Biomed. Inf.
(2009) - et al.
Extracting drug-enzyme relation from literature as evidence for drug drug interaction
J. Biomed. Semantics
(2016) - et al.
A formal framework of knowledge to support rational psychoactive drug selection
Artif. Intell. Med.
(2001) - et al.
Lessons learnt from the DDIExtraction-2013 shared task
J. Biomed. Inform.
(2014) - et al.
Pharmacovigilance through the development of text mining and natural language processing techniques
J. Biomed. Inform.
(2015) - et al.
Leveraging MEDLINE indexing for pharmacovigilance – Inherent limitations and mitigation strategies
J. Biomed. Inf.
(2015)
Filtering big data from social media – Building an early warning system for adverse drug reactions
J. Biomed. Inf.
Turning user generated health-related content into actionable knowledge through text analytics services
Comput. Ind.
Conceptual Modeling of Information Systems
BioPortal: ontologies and integrated data resources at the click of a mouse
Nucl. Acids Res.
SNOMED clinical terms: overview of the development process and project status
Medical subject headings (MeSH)
Bull. Med. Libr. Assoc
Biomedical ontologies in action: role in knowledge management, data integration and decision support
Yearb. Med. Inform.
The OBO Foundry: coordinated evolution of ontologies to support biomedical data integration
Nat. Biotechnol.
Foundations of Biomedical Knowledge Representation
S.D. Interactions
Communicating information about drug interactions
Br. J. Clin. Pharmacol.
Adverse drug reactions as cause of admission to hospital: prospective analysis of 18820 patients
Br. Med. J.
Proposal for a new tool to evaluate drug interaction cases
Ann. Pharmacother.
Semantic Resources in Pharmacovigilance: A Corpus and an Ontology for Drug-Drug Interactions
Selecting and customizing a mereology ontology for its reuse in a pharmaceutical product ontology
Front. Artif. Intell. Appl
Integrating machine learning into a medical decision support system to address the problem of missing patient data
Initializing the VA medication reference terminology using UMLS metathesaurus co-ocurrences
Evaluating drug-drug interaction information in NDF-RT and DrugBank
Comparison of critical drug-drug interaction listings: the Department of Veterans Affairs medical system and standard reference compendia.
Clin. Pharmacol. Ther.
An ontological knowledge and multiple abstraction level decision support system in healthcare
Decis. Anal.
Modeling and acquisition of drug-drug interaction knowledge
Cited by (15)
MTMA: Multi-task multi-attribute learning for the prediction of adverse drug–drug interaction
2020, Knowledge-Based SystemsCitation Excerpt :The success of these methods primarily lies on the importance of pharmacovigilance in an increasing attention and the accumulation of healthcare data in a massive scale [26]. However, due to that knowledge-based methods are highly dependent on the sufficient clinical evidences, their predictive results can only be regarded as a post-marketing surveillance, serving as post-marketing warnings, but are inadequate in exploring potential ADDIs before drugs hit markets, serving as pre-marketing alerts [10,18]. Based on the assumption that ADDIs are essentially caused by the attribute conflicts between two drugs [19,27], similarity-based methods are proposed to provide such alerts for predicting potential ADDIs.
A novel integrated action crossing method for drug-drug interaction prediction in non-communicable diseases
2018, Computer Methods and Programs in BiomedicineCitation Excerpt :Although the IAC method provides the suitable dataset for prediction modeling that is associated with DDIs PK mechanism, a more information about drugs such as chemical, structure, pharmacological information could be included to improve the prediction models performance. The various applications of conceptual models for DDIs make the prediction modeling through knowledge-based systems and semantic rules to become a very attractive research area [45]. In addition, the enormous complexity of the drug information domains that are obtained from the linked open data can be used for further investigation and the various applications, except for the MLs, may be required for NCDs DDI prediction.
A Minimal Information Model for Potential Drug-Drug Interactions
2021, Frontiers in PharmacologyUsing UML class diagrams for content ontology design patterns engineering
2021, Journal of Physics: Conference SeriesImplementation of clinical decision support services to detect potential drug-drug interaction using clinical quality language
2019, Studies in Health Technology and Informatics