Semantic distance-based creation of clusters of pharmacovigilance terms and their evaluation

Biases associated with epidermal necrolysis reporting in pharmacovigilance: An exploratory analysis using World Health Organization VigiBase

BACKGROUND

Possible biases in pharmacovigilance reporting may impact epidermal necrolysis (EN) and drugs associations.

OBJECTIVES

To assess biases associated with EN-reporting.

METHODS

Using VigiBase, the World Health Organization-pharmacovigilance database, among drugs associated with EN between 2016 and 2020, we used an unsupervised clustering including reports characteristics, that is, reporter quality, time from drug intake to EN onset, and only one suspected drug in the report.

RESULTS

Among 152 drugs, three clusters were identified. Cluster 1 (n = 41) exhibited drugs frequently reported within a time from intake to onset longer than 4 days, in 57 ± 13% of reports. It corresponded to well-reported drugs and was composed mainly of antivirals and antiepileptics. Cluster 2 (n = 42) exhibited drugs frequently reported within a time from drug intake to onset shorter than 4 days, in 31 ± 12% of reports. It corresponded to drugs with a high risk of protopathic bias and was composed of nonsteroidal anti-inflammatory drugs (NSAIDs), analgesics, and antibiotics. Cluster 3 (n = 69) exhibited drugs frequently reported with an unavailable time from drug intake to reaction, in 66 ± 11% of reports, and reported by a high frequency of consumers (9 ± 9%). It corresponded to drugs reported with a high risk of classification bias, and was composed of anticancer therapies and cardiovascular drugs.

CONCLUSION

Protopathic and classification biases impact EN-reporting and should be considered regarding associations with antibiotics, NSAIDs, analgesics, anticancer therapies, and cardiovascular drugs.

Consensus clustering for case series identification and adverse event profiles in pharmacovigilance

OBJECTIVE

To describe and evaluate vigiGroup - a consensus clustering algorithm which can identify groups of individual case reports referring to similar suspected adverse drug reactions and describe associated adverse event profiles, accounting for co-reported adverse event terms.

MATERIALS AND METHODS

Consensus clustering is achieved by grouping pairs of reports that are repeatedly placed together in the same clusters across a set of mixture model-based cluster analyses. The latter use empirical Bayes statistical shrinkage for improved performance. As baseline comparison, we considered a regular mixture model-based cluster analysis. Three randomly selected drugs in VigiBase, the World Health Organization's global database of Individual Case Safety Reports were analyzed: sumatriptan, ambroxol and tacrolimus. Clustering stability was assessed using the adjusted Rand index, ranging between -1 and +1, and clinical coherence was assessed through an intruder detection analysis.

RESULTS

For the three drugs considered, vigiGroup achieved stable and coherent results with adjusted Rand indices between +0.80 and +0.92, and intruder detection rates between 86% and 94%. Consensus clustering improved both stability and clinical coherence compared to mixture model-based clustering alone. Statistical shrinkage improved the stability of clusters compared to the baseline mixture model, as well as the cross-validated log-likelihood.

CONCLUSIONS

The proposed algorithm can achieve adequate stability and clinical coherence in clustering individual case reports, thereby enabling better identification of case series and associated adverse event profiles in pharmacovigilance. The use of empirical Bayes shrinkage and consensus clustering each led to meaningful improvements in performance.

The 2011–2020 Trends of Data-Driven Approaches in Medical Informatics for Active Pharmacovigilance

Pharmacovigilance, the scientific discipline pertaining to drug safety, has been studied extensively and is progressing continuously. In this field, medical informatics techniques and interpretation play important roles, and appropriate approaches are required. In this study, we investigated and analyzed the trends of pharmacovigilance systems, especially the data collection, detection, assessment, and monitoring processes. We used PubMed to collect papers on pharmacovigilance published over the past 10 years, and analyzed a total of 40 significant papers to determine the characteristics of the databases and data analysis methods used to identify drug safety indicators. Through systematic reviews, we identified the difficulty of standardizing data and terminology and establishing an adverse drug reactions (ADR) evaluation system in pharmacovigilance, and their corresponding implications. We found that appropriate methods and guidelines for active pharmacovigilance using medical big data are still required and should continue to be developed.

Clustering-Based Hybrid Approach for Identifying Quantitative Multidimensional Associations Between Patient Attributes, Drugs and Adverse Drug Reactions

The activity of post-marketing surveillance results in a collection of large amount of data. The analysis of data is very useful for raising early warnings on possible adverse reactions of drugs. Association rule mining techniques have been heavily explored by the research community for identifying binary association between drugs and their adverse effects. But these techniques perform poorly and miss out several interesting associations when it comes to analysis of multidimensional data which may include multiple patient attributes, drugs and adverse drug reactions. In the present work, a clustering-based hybrid approach has been presented for finding quantitative multidimensional association from the large amount of data. Firstly, it employs clustering technique for segmentation of data into semantically coherent clusters. Furthermore, disproportionality method called proportional reporting ratio is applied on clustered data for generating statistically strong associations. The performance of the proposed methodology has been examined on the data taken from the U.S. Food and Drug Administration Adverse Event Reporting System database corresponding to Aspirin and nine other drugs which are prescribed along with Aspirin. The experimental results show that the proposed approach discovered a number of association rules which are very comprehensive and informative regarding relationship of patient traits and drugs with adverse drug reactions. On comparing experimental results with LPMiner, it is observed that the quantitative association rules discovered by LPMiner are just 8.3% of what have been discovered by the proposed methodology.

Computational Advances in Drug Safety: Systematic and Mapping Review of Knowledge Engineering Based Approaches

Drug Safety (DS) is a domain with significant public health and social impact. Knowledge Engineering (KE) is the Computer Science discipline elaborating on methods and tools for developing “knowledge-intensive” systems, depending on a conceptual “knowledge” schema and some kind of “reasoning” process. The present systematic and mapping review aims to investigate KE-based approaches employed for DS and highlight the introduced added value as well as trends and possible gaps in the domain. Journal articles published between 2006 and 2017 were retrieved from PubMed/MEDLINE and Web of Science® (873 in total) and filtered based on a comprehensive set of inclusion/exclusion criteria. The 80 finally selected articles were reviewed on full-text, while the mapping process relied on a set of concrete criteria (concerning specific KE and DS core activities, special DS topics, employed data sources, reference ontologies/terminologies, and computational methods, etc.). The analysis results are publicly available as online interactive analytics graphs. The review clearly depicted increased use of KE approaches for DS. The collected data illustrate the use of KE for various DS aspects, such as Adverse Drug Event (ADE) information collection, detection, and assessment. Moreover, the quantified analysis of using KE for the respective DS core activities highlighted room for intensifying research on KE for ADE monitoring, prevention and reporting. Finally, the assessed use of the various data sources for DS special topics demonstrated extensive use of dominant data sources for DS surveillance, i.e., Spontaneous Reporting Systems, but also increasing interest in the use of emerging data sources, e.g., observational healthcare databases, biochemical/genetic databases, and social media. Various exemplar applications were identified with promising results, e.g., improvement in Adverse Drug Reaction (ADR) prediction, detection of drug interactions, and novel ADE profiles related with specific mechanisms of action, etc. Nevertheless, since the reviewed studies mostly concerned proof-of-concept implementations, more intense research is required to increase the maturity level that is necessary for KE approaches to reach routine DS practice. In conclusion, we argue that efficiently addressing DS data analytics and management challenges requires the introduction of high-throughput KE-based methods for effective knowledge discovery and management, resulting ultimately, in the establishment of a continuous learning DS system.

Concept embedding to measure semantic relatedness for biomedical information ontologies

There have been many attempts to identify relationships among concepts corresponding to terms from biomedical information ontologies such as the Unified Medical Language System (UMLS). In particular, vector representation of such concepts using information from UMLS definition texts is widely used to measure the relatedness between two biological concepts. However, conventional relatedness measures have a limited range of applicable word coverage, which limits the performance of these models. In this paper, we propose a concept-embedding model of a UMLS semantic relatedness measure to overcome the limitations of earlier models. We obtained context texts of biological concepts that are not defined in UMLS by utilizing Wikipedia as an external knowledgebase. Concept vector representations were then derived from the context texts of the biological concepts. The degree of relatedness between two concepts was defined as the cosine similarity between corresponding concept vectors. As a result, we validated that our method provides higher coverage and better performance than the conventional method.

An unsupervised machine learning model for discovering latent infectious diseases using social media data

INTRODUCTION

The authors of this work propose an unsupervised machine learning model that has the ability to identify real-world latent infectious diseases by mining social media data. In this study, a latent infectious disease is defined as a communicable disease that has not yet been formalized by national public health institutes and explicitly communicated to the general public. Most existing approaches to modeling infectious-disease-related knowledge discovery through social media networks are top-down approaches that are based on already known information, such as the names of diseases and their symptoms. In existing top-down approaches, necessary but unknown information, such as disease names and symptoms, is mostly unidentified in social media data until national public health institutes have formalized that disease. Most of the formalizing processes for latent infectious diseases are time consuming. Therefore, this study presents a bottom-up approach for latent infectious disease discovery in a given location without prior information, such as disease names and related symptoms.

METHODS

Social media messages with user and temporal information are extracted during the data preprocessing stage. An unsupervised sentiment analysis model is then presented. Users' expressions about symptoms, body parts, and pain locations are also identified from social media data. Then, symptom weighting vectors for each individual and time period are created, based on their sentiment and social media expressions. Finally, latent-infectious-disease-related information is retrieved from individuals' symptom weighting vectors.

DATASETS AND RESULTS

Twitter data from August 2012 to May 2013 are used to validate this study. Real electronic medical records for 104 individuals, who were diagnosed with influenza in the same period, are used to serve as ground truth validation. The results are promising, with the highest precision, recall, and F₁ score values of 0.773, 0.680, and 0.724, respectively.

CONCLUSION

This work uses individuals' social media messages to identify latent infectious diseases, without prior information, quicker than when the disease(s) is formalized by national public health institutes. In particular, the unsupervised machine learning model using user, textual, and temporal information in social media data, along with sentiment analysis, identifies latent infectious diseases in a given location.