Knowledge Graphs in Pharmacovigilance: A Scoping Review.

PURPOSE: To critically assess the role and added value of knowledge graphs in pharmacovigilance, focusing on their ability to predict adverse drug reactions. METHODS: A systematic scoping review was conducted in which detailed information, including objectives, technology, data sources, methodology, and performance metrics, were extracted from a set of peer-reviewed publications reporting the use of knowledge graphs to support pharmacovigilance signal detection. FINDINGS: The review, which included 47 peer-reviewed articles, found knowledge graphs were utilized for detecting/predicting single-drug adverse reactions and drug-drug interactions, with variable reported performance and sparse comparisons to legacy methods. IMPLICATIONS: Research to date suggests that knowledge graphs have the potential to augment predictive signal detection in pharmacovigilance, but further research using more reliable reference sets of adverse drug reactions and comparison with legacy pharmacovigilance methods are needed to more clearly define best practices and to establish their place in holistic pharmacovigilance systems.

The evolving role of disproportionality analysis in pharmacovigilance.

INTRODUCTION: From 2009 to 2015, the IMI PROTECT conducted rigorous studies addressing questions about optimal implementation and significance of disproportionality analyses, leading to the development of Good Signal Detection Practices. The ensuing period witnessed the independent exploration of research paths proposed by IMI PROTECT, accumulating valuable experience and insights that have yet to be seamlessly integrated. AREAS COVERED: This state-of-the-art review integrates IMI PROTECT recommendations with recent acquisitions and evolving challenges. It deals with defining the object of study, disproportionality methods, subgrouping, masking, drug-drug interaction, duplication, expectedness, the debated use of disproportionality results as risk measures, integration with other types of data. EXPERT OPINION: Despite the ongoing skepticism regarding the usefulness of disproportionality analyses and individual case safety reports, their ability to timely detect safety signals regarding rare and unpredictable adverse reactions remains unparalleled. Moreover, recent exploration into their potential for characterizing safety signals revealed valuable insights concerning potential risk factors and the patient's perspective. To fully realize their potential beyond hypothesis generation and achieve a comprehensive evidence synthesis with other kinds of data and studies, each with their unique limitations and contributions, we need to investigate methods for more transparently communicating disproportionality results and mapping and addressing pharmacovigilance biases.

The Reporting of a Disproportionality Analysis for Drug Safety Signal Detection Using Individual Case Safety Reports in PharmacoVigilance (READUS-PV): Development and Statement.

BACKGROUND AND AIM: Disproportionality analyses using reports of suspected adverse drug reactions are the most commonly used quantitative methods for detecting safety signals in pharmacovigilance. However, their methods and results are generally poorly reported in published articles and existing guidelines do not capture the specific features of disproportionality analyses. We here describe the development of a guideline (REporting of A Disproportionality analysis for drUg Safety signal detection using individual case safety reports in PharmacoVigilance [READUS-PV]) for reporting the results of disproportionality analyses in articles and abstracts. METHODS: We established a group of 34 international experts from universities, the pharmaceutical industry, and regulatory agencies, with expertise in pharmacovigilance, disproportionality analyses, and assessment of safety signals. We followed a three-step process to develop the checklist: (1) an open-text survey to generate a first list of items; (2) an online Delphi method to select and rephrase the most important items; (3) a final online consensus meeting. RESULTS: Among the panel members, 33 experts responded to round 1 and 30 to round 2 of the Delphi and 25 participated to the consensus meeting. Overall, 60 recommendations for the main body of the manuscript and 13 recommendations for the abstracts were retained by participants after the Delphi method. After merging of some items together and the online consensus meeting, the READUS-PV guidelines comprise a checklist of 32 recommendations, in 14 items, for the reporting of disproportionality analyses in the main body text and four items, comprising 12 recommendations, for abstracts. CONCLUSIONS: The READUS-PV guidelines will support authors, editors, peer-reviewers, and users of disproportionality analyses using individual case safety report databases. Adopting these guidelines will lead to more transparent, comprehensive, and accurate reporting and interpretation of disproportionality analyses, facilitating the integration with other sources of evidence.

The REporting of A Disproportionality Analysis for DrUg Safety Signal Detection Using Individual Case Safety Reports in PharmacoVigilance (READUS-PV): Explanation and Elaboration.

In pharmacovigilance, disproportionality analyses based on individual case safety reports are widely used to detect safety signals. Unfortunately, publishing disproportionality analyses lacks specific guidelines, often leading to incomplete and ambiguous reporting, and carries the risk of incorrect conclusions when data are not placed in the correct context. The REporting of A Disproportionality analysis for drUg Safety signal detection using individual case safety reports in PharmacoVigilance (READUS-PV) statement was developed to address this issue by promoting transparent and comprehensive reporting of disproportionality studies. While the statement paper explains in greater detail the procedure followed to develop these guidelines, with this explanation paper we present the 14 items retained for READUS-PV guidelines, together with an in-depth explanation of their rationale and bullet points to illustrate their practical implementation. Our primary objective is to foster the adoption of the READUS-PV guidelines among authors, editors, peer reviewers, and readers of disproportionality analyses. Enhancing transparency, completeness, and accuracy of reporting, as well as proper interpretation of their results, READUS-PV guidelines will ultimately facilitate evidence-based decision making in pharmacovigilance.

Knowledge Graphs in Pharmacovigilance: A Step-By-Step Guide.

PURPOSE: This work aims to demystify Knowledge Graphs (KGs) in pharmacovigilance (PV). It complements the scoping review within this issue. By bridging knowledge gaps and stimulating interest, further engagement with this topic by pharmacovigilance professionals will be facilitated. METHODS: We elucidate fundamental KGs concepts and terminology, followed by delineating a sequence of implementation steps: use case definition, data type selection, data sourcing, KG construction, KG embedding, and deriving actionable insights. Information technology options and limitations are also explored. FINDINGS: KGs in pharmacovigilance is a multi-disciplinary field involving information technology, machine learning, biology, and PV. We were able to synthesize the relevant core concepts to create an intuitive exposition of KGs in PV. IMPLICATIONS: This work demystifies KGs with a pharmacovigilance focus, preparing readers for the accompanying in-depth scoping review. that follows. It lays the groundwork for advancing PV research and practice by emphasizing the importance of engaging with vigilance experts. This approach enhances knowledge sharing and collaboration, contributing to more effective and informed pharmacovigilance efforts and optimal assessment and deployment of KGs in PV.

Potential Signals of COVID-19 as an Effect Modifier of Adverse Drug Reactions.

PURPOSE: COVID-19 infection may interact with patients' medical conditions or medications. The objective of this study was to identify potential signals of effect modification of adverse drug reactions by statistical reporting interactions with COVID-19 infection (SRIsCOVID-19) in a large spontaneous reporting database. METHODS: Data from the US Food and Drug Administration Adverse Event Reporting System through the second quarter of 2020 were used. Three-dimensional disproportionality analyses were conducted to identify drug-event-event (DEE) combinations, for which 1 of the events was COVID-19 infection, that were disproportionately reported. Effect size was quantified by an interaction signal score (INTSS) when COVID-19 was coreported as an adverse event or an indication (INTSSCOVID-19). An SRICOVID-19 exists when the calculated INTSSCOVID-19 is >2. The analyses focused on pandemic-emergent SRIsCOVID-19. Screening for extreme duplication of cases was applied. To assess possible reporting artifacts during the early pandemic as an alternative explanation for pandemic-emergent SRICOVID-19, we repeated the analyses with an additional year of data to gauge temporal stability of our findings. FINDINGS: When examining DEE interactions, 193 emergent SRIsCOVID-19 were identified, involving 44 drugs and 88 events, in addition to COVID-19 infection. Of the 44 drugs recorded, most were immunosuppressant or modulatory drugs, followed by antivirals. Seven drugs (eg, azithromycin) were identified in emergent SRIsCOVID-19 with preferred terms representing off-label use for prevention or treatment of COVID-19 infection. These drugs were in fact repurposed for COVID-19 treatment, supporting assay sensitivity of our procedure. Infections and infestations were the most frequently observed system organ class, followed by the general disorders and respiratory disorders. The psychiatric system organ class had only a few emergent SRIsCOVID-19 but contained the largest INTSSs. Less commonly reported manifestations of COVID-19 (e.g., skin events) were also identified. After excluding DEE combinations that were highly suggestive of extreme duplication, there remained a more robust set of emergent SRIsCOVID-19, which were supported by biological plausibility considerations. Our findings indicate a relative temporal stability, with >90% of SRIsCOVID-19 persisting after updating the analysis with an additional year of data. IMPLICATIONS: The signals identified in the analyses could be critical in refining our understanding of the causality of spontaneously reported adverse drug events and thus informing the ongoing care of patients with COVID-19. Our findings also underscore the importance of undetected report duplication as a distorting influence on disproportionality analysis.

Artificial Intelligence and Data Mining for the Pharmacovigilance of Drug-Drug Interactions.

Despite increasing mechanistic understanding, undetected and underrecognized drug-drug interactions (DDIs) persist. This elusiveness relates to an interwoven complexity of increasing polypharmacy, multiplex mechanistic pathways, and human biological individuality. This persistent elusiveness motivates development of artificial intelligence (AI)-based approaches to enhancing DDI detection and prediction capabilities. The literature is vast and roughly divided into "prediction" and "detection." The former relatively emphasizes biological and chemical knowledge bases, drug development, new drugs, and beneficial interactions, whereas the latter utilizes more traditional sources such as spontaneous reports, claims data, and electronic health records to detect novel adverse DDIs with authorized drugs. However, it is not a bright line, either nominally or in practice, and both are in scope for pharmacovigilance supporting signal detection but also signal refinement and evaluation, by providing data-based mechanistic arguments for/against DDI signals. The wide array of intricate and elegant methods has expanded the pharmacovigilance tool kit. How much they add to real prospective pharmacovigilance, reduce the public health impact of DDIs, and at what cost in terms of false alarms amplified by automation bias and its sequelae are open questions.

More extreme duplication in FDA Adverse Event Reporting System detected by literature reference normalization and fuzzy string matching.

PURPOSE: Literature reports of adverse drug events can be replicated across multiple companies, resulting in extreme duplication (defined as a majority of reports being duplicates) in the FDA Adverse Event Reporting System (FAERS) database because they can escape legacy duplicate detection algorithms routinely deployed on that data source. Literature reference field, added to in 2014, could potentially be utilized to identify replicated reports. FAERS does not enforce adherence to the Vancouver referencing convention, thus the same article may be referenced differently leading to duplication. The objective of this analysis is to determine if variations of the same literature references observed in FAERS can be resolved with text normalization and fuzzy string matching. METHODS: We normalized the literature references recorded in the FAERS database through the first quarter of 2021 with a rule-based algorithm so that they better conform to the Vancouver convention. Levenshtein distance was then utilized to merge sufficiently similar normalized literature references together. RESULTS: Normalization of literature references increases the percentage that can be parsed into author, title, and journal from 61.74% to 93.93%. We observe that about 98% of pairs within groups do have a Levenshtein similarity of the title above the threshold. The extreme duplication ranged from 66% to 87% with a median of 72% of reports being duplicates and often involved addictovigilance scenarios. CONCLUSIONS: We have shown that these normalized references can be merged via fuzzy string matching to improve enumeration of all the individual case safety reports that refer to the same article. Inclusion of the PubMed ID and adherence to the Vancouver convention could facilitate identification of duplicates in the FAERS dataset. Awareness of this phenomenon may improve disproportionality analysis, especially in areas such as addictovigilance.

Individual Case Safety Report Replication: An Analysis of Case Reporting Transmission Networks.

INTRODUCTION: The basis of pharmacovigilance is provided by the exchange of Individual Case Safety Reports (ICSRs) between the recipient of the original report and other interested parties, which include Marketing Authorization Holders (MAHs) and Health Authorities (HAs). Different regulators have different reporting requirements for report transmission. This results in replication of each ICSR that will exist in multiple locations. Adding in the fact that each case will go through multiple versions, different recipients may receive different case versions at different times, potentially influencing patient safety decisions and potentially amplifying or obscuring safety signals inappropriately. OBJECTIVE: The present study aimed to investigate the magnitude of replication, the variability among recipients, and the subsequent divergence across recipients of ICSRs. METHODS: Seven participating TransCelerate Member Companies (MCs) queried their respective safety databases covering a 3-year period and provided aggregate ICSR submission statistics for expedited safety reports to an independent project manager. As measured in the US Food and Drug Administration (FDA)'s Adverse Event Reporting System (FAERS), ICSR volume for these seven MCs makes up approximately 20% of the total case volume. Aggregate metrics were calculated from the company data, specifically: (i) number of ICSR transmissions, (ii) average number of recipients (ANR) per case version transmitted, (iii) a submission selectivity metric, which measures the percentage of recipients not having received all sequential case version numbers, and (iv) percent of common ISCRs residing in two or more MAH databases. RESULTS: The analysis reflects 2,539,802 case versions, distributed through 7,602,678 submissions. The overall mean replication rate is 3.0 submissions per case version. The distribution of the ANR replication measure was observed to be very long-tailed, with a significant fraction of case versions (~ 12.4% of all transmissions) being sent to ten or more HA recipients. Replication is higher than average for serious, unlisted, and literature cases, ranging from 3.5 to 6.1 submissions per version. Within the subset of ICSR versions sent to three recipients, a significant degree of variability in the actual recipients (i.e., HAs) was observed, indicating that there is not one single combination of the same three HAs predominantly receiving an ICSR. Submission selectivity increases with the case version. For case version 6, the range of the submission selectivity for the MAHs ranges from ~ 10% to over 50%, with a median of 30.2%. Within the participating MAHs, the percentage of cases that reside within at least two safety databases is approximately 2% across five databases. Further analysis of the data from three MAHs showed percentages of 13.4%, 15.6%, and 27.9% of ICSRs originating from HAs and any other partners such as other MAHs and other institutions. CONCLUSION: Replication of ICSRs and the variation of available safety information in recipient databases were quantified and shown to be substantial. Our work shows that multiple processors and medical reviewers will likely handle the same original ICSR as a result of replication. Aside from the obvious duplicate work, this phenomenon could conceivably lead to differing clinical assessments and decisions. If replication could be reduced or even eliminated, this would enable more focus on activities with a benefit for patient safety.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation.

BACKGROUND: Inflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time. METHODS: On May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure ("machine learning" OR "artificial intelligence") AND ("Crohn* Disease" OR "Ulcerative Colitis" OR "Inflammatory Bowel Disease"). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research. RESULTS: Seventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation. DISCUSSION: Availability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.