A Method to Combine Signals from Spontaneous Reporting Systems and Observational Healthcare Data to Detect Adverse Drug Reactions

A discovery and verification approach to pharmacovigilance using electronic healthcare data

Introduction

Pharmacovigilance is vital for drug safety. The process typically involves two key steps: initial signal generation from spontaneous reporting systems (SRSs) and subsequent expert review to assess the signals' (potential) causality and decide on the appropriate action.

Methods

We propose a novel discovery and verification approach to pharmacovigilance based on electronic healthcare data. We enhance the signal detection phase by introducing an ensemble of methods which generated signals are combined using Borda count ranking; a method designed to emphasize consensus. Ensemble methods tend to perform better when data is noisy and leverage the strengths of individual classifiers, while trying to mitigate some of their limitations. Additionally, we offer the committee of medical experts with the option to perform an in-depth investigation of selected signals through tailored pharmacoepidemiological studies to evaluate their plausibility or spuriousness. To illustrate our approach, we utilize data from the German Pharmacoepidemiological Research Database, focusing on drug reactions to the direct oral anticoagulant rivaroxaban.

Results

In this example, the ensemble method is built upon the Bayesian confidence propagation neural network, longitudinal Gamma Poisson shrinker, penalized regression and random forests. We also conduct a pharmacoepidemiological verification study in the form of a nested active comparator case-control study, involving patients diagnosed with atrial fibrillation who initiated anticoagulant treatment between 2011 and 2017.

Discussion

The case study reveals our ability to detect known adverse drug reactions and discover new signals. Importantly, the ensemble method is computationally efficient. Hasty false conclusions can be avoided by a verification study, which is, however, time-consuming to carry out. We provide an online tool for easy application: https://borda.bips.eu.

Detection of novel drug-adverse drug reaction signals in rheumatoid arthritis and ankylosing spondylitis: analysis of Korean real-world biologics registry data

This study aimed to detect signals of adverse drug reactions (ADRs) associated with biological disease-modifying antirheumatic drugs (DMARDs) and targeted therapies in rheumatoid arthritis (RA) and ankylosing spondylitis (AS) patients. Utilizing the KOrean College of Rheumatology BIOlogics & Targeted Therapy Registry (KOBIO) data, we calculated relative risks, excluded previously reported drug-ADR pairs, and externally validated remaining pairs using US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) and single centre's electronic health records (EHR) data. Analyzing data from 2279 RA and 1940 AS patients, we identified 35 significant drug-ADR pairs in RA and 26 in AS, previously unreported in drug labels. Among the novel drug-ADR pairs from KOBIO, 15 were also significant in the FAERS data. Additionally, 2 significant drug-laboratory abnormality pairs were found in RA using CDM MetaLAB analysis. Our findings contribute to the identification of 14 novel drug-ADR signals, expanding our understanding of potential adverse effects related to biological DMARDs and targeted therapies in RA and AS. These results emphasize the importance of ongoing pharmacovigilance for patient safety and optimal therapeutic interventions.

Enhancing antidepressant safety surveillance: comparative analysis of adverse drug reaction signals in spontaneous reporting and healthcare claims databases

Background/Objective: Spontaneous reporting systems (SRS) such as the Korea Adverse Event Reporting System (KAERS) are limited in their ability to detect adverse drug reaction (ADR) signals due to their limited data on drug use. Conversely, the national health insurance claim (NHIC) data include drug use information for all qualifying residents. This study aimed to compare ADR signal profiles for antidepressants between KAERS and NHIC, evaluating the extent to which detected signals belong to common ADRs and labeling information. Materials and Methods: ADR signal detection in KAERS and NHIC databases, spanning January to December 2017, employed disproportionality analysis. Signal classes were determined based on System Organ Class (SOC) of the Medical Dictionary for Regulatory Activities (MedDRA). Also, Common ADR Coverage (CAC), the proportion of detected signals deemed common ADRs, and labeling information coverage (LIC) represented by mean average precision (mAP) were calculated. Additionally, protopathic bias and relative risk (RR) evaluation were performed to check for signal robustness. Results: Signal detection revealed 51 and 62 signals in KAERS and NHIC databases, respectively. Both systems predominantly captured signals related to nervous system disorders, comprising 33.3% (N = 17) in KAERS and 50.8% (N = 31) in NHIC. Regarding the type of antidepressants, KAERS predominantly reported signals associated with tricyclic antidepressants (TCAs) (N = 21, 41.2%), while NHIC produced most signals linked to selective serotonin reuptake inhibitors (SSRIs) (N = 22, 35.5%). KAERS exhibited higher CAC (68.63% vs. 29.03%) than NHIC. LIC was also higher in KAERS than in NHIC (mAP for EB05: 1.00 vs. 0.983); i.e., NHIC identified 5 signals not documented in drug labeling information, while KAERS found none. Among the unlabeled signals, one (Duloxetine-Myelopathy) was from protopathic bias, and two (duloxetine-myelopathy and tianeptine-osteomalacia) were statistically significant in RR. Conclusion: NHIC exhibited greater capability in detecting ADR signals associated with antidepressant use, encompassing unlabeled ADR signals, compared to KAERS. NHIC also demonstrated greater potential for identifying less common ADRs. Further investigation is needed for signals detected exclusively in NHIC but not covered by labeling information. This study underscores the value of integrating different sources of data, offering substantial regulatory insights and enriching the scope of pharmacovigilance.

Serially Combining Epidemiological Designs Does Not Improve Overall Signal Detection in Vaccine Safety Surveillance

INTRODUCTION

Vaccine safety surveillance commonly includes a serial testing approach with a sensitive method for 'signal generation' and specific method for 'signal validation.' The extent to which serial testing in real-world studies improves or hinders overall performance in terms of sensitivity and specificity remains unknown.

METHODS

We assessed the overall performance of serial testing using three administrative claims and one electronic health record database. We compared type I and II errors before and after empirical calibration for historical comparator, self-controlled case series (SCCS), and the serial combination of those designs against six vaccine exposure groups with 93 negative control and 279 imputed positive control outcomes.

RESULTS

The historical comparator design mostly had fewer type II errors than SCCS. SCCS had fewer type I errors than the historical comparator. Before empirical calibration, the serial combination increased specificity and decreased sensitivity. Type II errors mostly exceeded 50%. After empirical calibration, type I errors returned to nominal; sensitivity was lowest when the methods were combined.

CONCLUSION

While serial combination produced fewer false-positive signals compared with the most specific method, it generated more false-negative signals compared with the most sensitive method. Using a historical comparator design followed by an SCCS analysis yielded decreased sensitivity in evaluating safety signals relative to a one-stage SCCS approach. While the current use of serial testing in vaccine surveillance may provide a practical paradigm for signal identification and triage, single epidemiological designs should be explored as valuable approaches to detecting signals.

Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review

INTRODUCTION

Pharmacovigilance programs protect patient health and safety by identifying adverse event signals through postmarketing surveillance of claims data and spontaneous reports. Electronic health records (EHRs) provide new opportunities to address limitations of traditional approaches and promote discovery-oriented pharmacovigilance.

METHODS

To evaluate the current state of EHR-based medication safety signal identification, we conducted a scoping literature review of studies aimed at identifying safety signals from routinely collected patient-level EHR data. We extracted information on study design, EHR data elements utilized, analytic methods employed, drugs and outcomes evaluated, and key statistical and data analysis choices.

RESULTS

We identified 81 eligible studies. Disproportionality methods were the predominant analytic approach, followed by data mining and regression. Variability in study design makes direct comparisons difficult. Studies varied widely in terms of data, confounding adjustment, and statistical considerations.

CONCLUSION

Despite broad interest in utilizing EHRs for safety signal identification, current efforts fail to leverage the full breadth and depth of available data or to rigorously control for confounding. The development of best practices and application of common data models would promote the expansion of EHR-based pharmacovigilance.

Early Detection of Adverse Drug Reaction Signals by Association Rule Mining Using Large-Scale Administrative Claims Data

INTRODUCTION

Adverse drug reactions (ADRs) are a leading cause of mortality worldwide and should be detected promptly to reduce health risks to patients. A data-mining approach using large-scale medical records might be a useful method for the early detection of ADRs. Many studies have analyzed medical records to detect ADRs; however, most of them have focused on a narrow range of ADRs, limiting their usefulness.

OBJECTIVE

This study aimed to identify methods for the early detection of a wide range of ADR signals.

METHODS

First, to evaluate the performance in signal detection of ADRs by data-mining, we attempted to create a gold standard based on clinical evidence. Second, association rule mining (ARM) was applied to patient symptoms and medications registered in claims data, followed by evaluating ADR signal detection performance.

RESULTS

We created a new gold standard consisting of 92 positive and 88 negative controls. In the assessment of ARM using claims data, the areas under the receiver-operating characteristic curve and the precision-recall curve were 0.80 and 0.83, respectively. If the detection criteria were defined as lift > 1, conviction > 1, and p-value < 0.05, ARM could identify 156 signals, of which 90 were true positive controls (sensitivity: 0.98, specificity: 0.25). Evaluation of the capability of ARM with short periods of data revealed that ARM could detect a greater number of positive controls than the conventional analysis method.

CONCLUSIONS

ARM of claims data may be effective in the early detection of a wide range of ADR signals.

A New Drug Safety Signal Detection and Triage System Integrating Sequence Symmetry Analysis and Tree-Based Scan Statistics with Longitudinal Data

Purpose

Development and evaluation of a drug-safety signal detection system integrating data-mining tools in longitudinal data is essential. This study aimed to construct a new triage system using longitudinal data for drug-safety signal detection, integrating data-mining tools, and evaluate adaptability of such system.

Patients and Methods

Based on relevant guidelines and structural frameworks in Taiwan's pharmacovigilance system, we constructed a triage system integrating sequence symmetry analysis (SSA) and tree-based scan statistics (TreeScan) as data-mining tools for detecting safety signals. We conducted an exploratory analysis utilizing Taiwan's National Health Insurance Database and selecting two drug classes (sodium-glucose co-transporter-2 inhibitors (SGLT2i) and non-fluorinated quinolones (NFQ)) as chronic and episodic treatment respectively, as examples to test feasibility of the system.

Results

Under the proposed system, either cohort-based or self-controlled mining with SSA and TreeScan was selected, based on whether the screened drug had an appropriate comparator. All detected alerts were further classified as known adverse drug reactions (ADRs), events related to other causes or potential signals from the triage algorithm, building on existing drug labels and clinical judgement. Exploratory analysis revealed greater numbers of signals for NFQ with a relatively low proportion of known ADRs; most were related to indication, patient characteristics or bias. No safety signals were found. By contrast, most SGLT2i signals were known ADRs or events related to patient characteristics. Four were potential signals warranting further investigation.

Conclusion

The proposed system facilitated active and systematic screening to detect and classify potential safety signals. Countries with real-world longitudinal data could adopt it to streamline drug-safety surveillance.

Identifying Antidepressants Less Likely to Cause Hyponatremia: Triangulation of Retrospective Cohort, Disproportionality, and Pharmacodynamic Studies

Antidepressants are known to cause hyponatremia, but conflicting evidence exists regarding specific antidepressants. To identify antidepressants less likely to cause hyponatremia, we conducted a triangulation study integrating retrospective cohort, disproportionality, and pharmacodynamic studies. In the retrospective cohort study of patients (≥ 60 years) in Nihon University School of Medicine's Clinical Data Warehouse (2004-2020), a significant decrease in serum sodium levels was observed within 30 days after initiation of a selective serotonin reuptake inhibitor (SSRI; mean change -1.00 ± 0.23 mmol/L, P < 0.001) or serotonin-noradrenaline reuptake inhibitor (SNRI; -1.01 ± 0.31 mmol/L, P = 0.0013), whereas no decrease was found for a noradrenergic and specific serotonergic antidepressant (mirtazapine; +0.55 ± 0.47 mmol/L, P = 0.24). Within-class comparison revealed no decrease in serum sodium levels for fluvoxamine (+0.74 ± 0.75 mmol/L, P = 0.33) among SSRIs and milnacipran (+0.08 ± 0.87 mmol/L, P = 0.93) among SNRIs. In the disproportionality analysis of patients (≥ 60 years) in the Japanese Adverse Drug Event Report database (2004-2020), a significant increase in hyponatremia reports was observed for SSRIs (reporting odds ratio 4.41, 95% confidence interval 3.58-5.45) and SNRIs (5.66, 4.38-7.31), but not for mirtazapine (1.08, 0.74-1.58), fluvoxamine (1.48, 0.94-2.32), and milnacipran (0.85, 0.45-1.62). Finally, pharmacoepidemiological-pharmacodynamic analysis revealed a significant correlation between the decrease in serum sodium levels and binding affinity for serotonin transporter (SERT; r = -0.84, P = 0.02), suggesting that lower binding affinity of mirtazapine, fluvoxamine, and milnacipran against SERT is responsible for the above difference. Although further research is needed, our data suggest that mirtazapine, fluvoxamine, and milnacipran are less likely to cause hyponatremia.

Improving Pharmacovigilance Signal Detection from Clinical Notes with Locality Sensitive Neural Concept Embeddings

Although pharmaceutical products undergo clinical trials to profile efficacy and safety, some adverse drug reactions (ADRs) are only discovered after release to market. Post-market drug safety surveillance - pharmacovigilance - leverages information from various sources to proactively identify such ADRs. Clinical notes are one source of observational data that could assist this process, but their inherent complexity can obfuscate possible ADR signals. In previous research, embeddings trained on observational reports have improved detection of such signals over commonly used statistical measures. Moreover, neural embedding methods which further encode juxtapositional information have shown promise on analogical retrieval tasks, suggesting proximity-based alternatives to document-level modeling for signal detection. This work uses natural language processing and locality sensitive neural embeddings to increase ADR signal recovery from clinical notes, with AUCs of ~0.63-0.71. Constituting a ~50% increase over baselines, our method sets the state-of-the-art for these reference standards when solely leveraging clinical notes.

A smart hospital-driven approach to precision pharmacovigilance

Researchers, regulatory agencies, and the pharmaceutical industry are moving towards precision pharmacovigilance as a comprehensive framework for drug safety assessment, at the service of the individual patient, by clustering specific risk groups in different databases. This article explores its implementation by focusing on: (i) designing a new data collection infrastructure, (ii) exploring new computational methods suitable for drug safety data, and (iii) providing a computer-aided framework for distributed clinical decisions with the aim of compiling a personalized information leaflet with specific reference to a drug's risks and adverse drug reactions. These goals can be achieved by using 'smart hospitals' as the principal data sources and by employing methods of precision medicine and medical statistics to supplement current public health decisions.

A reference set of clinically relevant adverse drug-drug interactions

The accurate and timely detection of adverse drug-drug interactions (DDIs) during the postmarketing phase is an important yet complex task with potentially major clinical implications. The development of data mining methodologies that scan healthcare databases for drug safety signals requires appropriate reference sets for performance evaluation. Methodologies for establishing DDI reference sets are limited in the literature, while there is no publicly available resource simultaneously focusing on clinical relevance of DDIs and individual behaviour of interacting drugs. By automatically extracting and aggregating information from multiple clinical resources, we provide a scalable approach for generating a reference set for DDIs that could support research in postmarketing safety surveillance. CRESCENDDI contains 10,286 positive and 4,544 negative controls, covering 454 drugs and 179 adverse events mapped to RxNorm and MedDRA concepts, respectively. It also includes single drug information for the included drugs (i.e., adverse drug reactions, indications, and negative drug-event associations). We demonstrate usability of the resource by scanning a spontaneous reporting system database for signals of DDIs using traditional signal detection algorithms.

Measurement(s)	Adverse Event
Technology Type(s)	digital curation
Sample Characteristic - Organism	Homo sapiens

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.16681933

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

Introduction: Improving adverse drug event (ADE) detection is important for post-marketing drug safety surveillance. Existing statistical approaches can be further optimized owing to their high efficiency and low cost.

Objective: The objective of this study was to evaluate the proposed approach for use in pharmacovigilance, the early detection of potential ADEs, and the improvement of drug safety.

Methods: We developed a novel integrated approach, the Bayesian signal detection algorithm, based on the pharmacological network model (IC_PNM) using the FDA Adverse Event Reporting System (FAERS) data published from 2004 to 2009 and from 2014 to 2019Q2, PubChem, and DrugBank database. First, we used a pharmacological network model to generate the probabilities for drug-ADE associations, which comprised the proper prior information component (IC). We then defined the probability of the propensity score adjustment based on a logistic regression model to control for the confounding bias. Finally, we chose the Side Effect Resource (SIDER) and the Observational Medical Outcomes Partnership (OMOP) data to evaluate the detection performance and robustness of the IC_PNM compared with the statistical approaches [disproportionality analysis (DPA)] by using the area under the receiver operator characteristics curve (AUC) and Youden’s index.

Results: Of the statistical approaches implemented, the IC_PNM showed the best performance (AUC, 0.8291; Youden’s index, 0.5836). Meanwhile, the AUCs of the IC, EBGM, ROR, and PRR were 0.7343, 0.7231, 0.6828, and 0.6721, respectively.

Conclusion: The proposed IC_PNM combined the strengths of the pharmacological network model and the Bayesian signal detection algorithm and performed better in detecting true drug-ADE associations. It also detected newer ADE signals than a DPA and may be complementary to the existing statistical approaches.

Intelligent Telehealth in Pharmacovigilance: A Future Perspective

Pharmacovigilance improves patient safety by detecting and preventing adverse drug events. However, challenges exist that limit adverse drug event detection, resulting in many adverse drug events being underreported or inaccurately reported. One challenge includes having access to large data sets from various sources including electronic health records and wearable medical devices. Artificial intelligence, including machine learning methods, such as natural language processing and deep learning, can detect and extract information about adverse drug events, thus automating the pharmacovigilance process and improving the surveillance of known and documented adverse drug events. In addition, with the increased demand for telehealth services, for managing both acute and chronic diseases, artificial intelligence methods can play a role in detecting and preventing adverse drug events. In this review, we discuss two use cases of how artificial intelligence methods may be useful to improve the quality of pharmacovigilance and the role of artificial intelligence in telehealth practices.

Random control selection for conducting high-throughput adverse drug events screening using large-scale longitudinal health data

Case-control design based high-throughput pharmacoinformatics study using large-scale longitudinal health data is able to detect new adverse drug event (ADEs) signals. Existing control selection approaches for case-control design included the dynamic/super control selection approach. The dynamic/super control selection approach requires all individuals to be evaluated at all ADE case index dates, as the individuals' eligibilities as control depend on ADE/enrollment history. Thus, using large-scale longitudinal health data, the dynamic/super control selection approach requires extraordinarily high computational time. We proposed a random control selection approach in which ADE case index dates were matched by randomly generated control index dates. The random control selection approach does not depend on ADE/enrollment history. It is able to significantly reduce computational time to prepare case-control data sets, as it requires all individuals to be evaluated only once. We compared the performance metrics of all control selection approaches using two large-scale longitudinal health data and a drug-ADE gold standard including 399 drug-ADE pairs. The F-scores for the random control selection approach were between 0.586 and 0.600 compared to between 0.545 and 0.562 for dynamic/super control selection approaches. The random control selection approach was ~ 1000 times faster than dynamic/super control selection approach on preparing case-control data sets. With large-scale longitudinal health data, a case-control design-based pharmacoinformatics study using random control selection is able to generate comparable ADE signals than the existing control selection approaches. The random control selection approach also significantly reduces computational time to prepare the case-control data sets.

Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

INTRODUCTION

Drug safety research asks causal questions but relies on observational data. Confounding bias threatens the reliability of studies using such data. The successful control of confounding requires knowledge of variables called confounders affecting both the exposure and outcome of interest. However, causal knowledge of dynamic biological systems is complex and challenging. Fortunately, computable knowledge mined from the literature may hold clues about confounders. In this paper, we tested the hypothesis that incorporating literature-derived confounders can improve causal inference from observational data.

METHODS

We introduce two methods (semantic vector-based and string-based confounder search) that query literature-derived information for confounder candidates to control, using SemMedDB, a database of computable knowledge mined from the biomedical literature. These methods search SemMedDB for confounders by applying semantic constraint search for indications treated by the drug (exposure) and that are also known to cause the adverse event (outcome). We then include the literature-derived confounder candidates in statistical and causal models derived from free-text clinical notes. For evaluation, we use a reference dataset widely used in drug safety containing labeled pairwise relationships between drugs and adverse events and attempt to rediscover these relationships from a corpus of 2.2 M NLP-processed free-text clinical notes. We employ standard adjustment and causal inference procedures to predict and estimate causal effects by informing the models with varying numbers of literature-derived confounders and instantiating the exposure, outcome, and confounder variables in the models with dichotomous EHR-derived data. Finally, we compare the results from applying these procedures with naive measures of association (χ2 and reporting odds ratio) and with each other.

RESULTS AND CONCLUSIONS

We found semantic vector-based search to be superior to string-based search at reducing confounding bias. However, the effect of including more rather than fewer literature-derived confounders was inconclusive. We recommend using targeted learning estimation methods that can address treatment-confounder feedback, where confounders also behave as intermediate variables, and engaging subject-matter experts to adjudicate the handling of problematic covariates.

Dermatologic Research Potential of the Observational Health Data Sciences and Informatics (OHDSI) Network

BACKGROUND

The Observational Health Data Sciences and Informatics (OHDSI) network enables access to billions of deidentified, standardized health records and built-in analytics software for observational health research, with numerous potential applications to dermatology. While the use of the OHDSI has increased steadily over the past several years, review of the literature reveals few studies utilizing OHDSI in dermatology. To our knowledge, the University of Colorado School of Medicine is unique in its use of OHDSI for dermatology big data research.

SUMMARY

A PubMed search was conducted in August 2020, followed by a literature review, with 24 of the 72 screened articles selected for inclusion. In this review, we discuss the ways OHDSI has been used to compile and analyze data, improve prediction and estimation capabilities, and inform treatment guidelines across specialties. We also discuss the potential for OHDSI in dermatology - specifically, ways that it could reveal adherence to available guidelines, establish standardized protocols, and ensure health equity. Key Messages: OHDSI has demonstrated broad utility in medicine. Adoption of OHDSI by the field of dermatology would facilitate big data research, allow for examination of current prescribing and treatment patterns without clear best practice guidelines, improve the dermatologic knowledge base and, by extension, improve patient outcomes.

Combining Social Media and FDA Adverse Event Reporting System to Detect Adverse Drug Reactions

INTRODUCTION

Adverse drug reactions (ADRs) are unintended reactions caused by a drug or combination of drugs taken by a patient. The current safety surveillance system relies on spontaneous reporting systems (SRSs) and more recently on observational health data; however, ADR detection may be delayed and lack geographic diversity. The broad scope of social media conversations, such as those on Twitter, can include health-related topics. Consequently, these data could be used to detect potentially novel ADRs with less latency. Although research regarding ADR detection using social media has made progress, findings are based on single information sources, and no study has yet integrated drug safety evidence from both an SRS and Twitter.

OBJECTIVE

The aim of this study was to combine signals from an SRS and Twitter to facilitate the detection of safety signals and compare the performance of the combined system with signals generated by individual data sources.

METHODS

We extracted potential drug-ADR posts from Twitter, used Monte Carlo expectation maximization to generate drug safety signals from both the US FDA Adverse Event Reporting System and posts from Twitter, and then integrated these signals using a Bayesian hierarchical model. The results from the integrated system and two individual sources were evaluated using a reference standard derived from drug labels. Area under the receiver operating characteristics curve (AUC) was computed to measure performance.

RESULTS

We observed a significant improvement in the AUC of the combined system when comparing it with Twitter alone, and no improvement when comparing with the SRS alone. The AUCs ranged from 0.587 to 0.637 for the combined SRS and Twitter, from 0.525 to 0.534 for Twitter alone, and from 0.612 to 0.642 for the SRS alone. The results varied because different preprocessing procedures were applied to Twitter.

CONCLUSION

The accuracy of signal detection using social media can be improved by combining signals with those from SRSs. However, the combined system cannot achieve better AUC performance than data from FAERS alone, which may indicate that Twitter data are not ready to be integrated into a purely data-driven combination system.

Mining and visualizing high-order directional drug interaction effects using the FAERS database

Background

Adverse drug events (ADEs) often occur as a result of drug-drug interactions (DDIs). The use of data mining for detecting effects of drug combinations on ADE has attracted growing attention and interest, however, most studies focused on analyzing pairwise DDIs. Recent efforts have been made to explore the directional relationships among high-dimensional drug combinations and have shown effectiveness on prediction of ADE risk. However, the existing approaches become inefficient from both computational and illustrative perspectives when considering more than three drugs.

Methods

We proposed an efficient approach to estimate the directional effects of high-order DDIs through frequent itemset mining, and further developed a novel visualization method to organize and present the high-order directional DDI effects involving more than three drugs in an interactive, concise and comprehensive manner. We demonstrated its performance by mining the directional DDIs associated with myopathy using a publicly available FAERS dataset.

Results

Directional effects of DDIs involving up to seven drugs were reported. Our analysis confirmed previously reported myopathy associated DDIs including interactions between fusidic acid with simvastatin and atorvastatin. Furthermore, we uncovered a number of novel DDIs leading to increased risk for myopathy, such as the co-administration of zoledronate with different types of drugs including antibiotics (ciprofloxacin, levofloxacin) and analgesics (acetaminophen, fentanyl, gabapentin, oxycodone). Finally, we visualized directional DDI findings via the proposed tool, which allows one to interactively select any drug combination as the baseline and zoom in/out to obtain both detailed and overall picture of interested drugs.

Conclusions

We developed a more efficient data mining strategy to identify high-order directional DDIs, and designed a scalable tool to visualize high-order DDI findings. The proposed method and tool have the potential to contribute to the drug interaction research and ultimately impact patient health care.

Availability and implementation

http://lishenlab.com/d3i/explorer.html

Analysis of antiseizure drug-related adverse reactions from the electronic health record using the common data model

OBJECTIVE

Antiseizure drugs (ASDs) are known to cause a wide range of adverse drug reactions (ADRs). Recently, electronic health care data using the common data model (CDM) have been introduced and commonly adopted in pharmacovigilance research. We aimed to analyze ASD-related ADRs using CDM and to assess the feasibility of CDM analysis in monitoring ADR in a single tertiary hospital.

METHODS

We selected five ASDs: oxcarbazepine (OXC), lamotrigine (LTG), levetiracetam (LEV), valproic acid (VPA), and topiramate (TPM). Patients diagnosed with epilepsy and exposed to monotherapy with one of the ASDs before age 18 years were included. We measured four ADR outcomes: (1) hematologic abnormality, (2) hyponatremia, (3) elevation of liver enzymes, and (4) subclinical hypothyroidism. We performed a subgroup analysis to exclude the effects of concomitant medications.

RESULTS

From the database, 1344 patients were included for the study. Of the 1344 patients, 436 were receiving OXC, 293 were receiving LTG, 275 were receiving LEV, 180 were receiving VPA, and 160 were receiving TPM. Thrombocytopenia developed in 14.1% of patients taking VPA. Hyponatremia occurred in 10.5% of patients taking OXC. Variable ranges of liver enzyme elevation were detected in 19.3% of patients taking VPA. Subclinical hypothyroidism occurred in approximately 21.5% to 28% of patients with ASD monotherapy, which did not significantly differ according to the type of ASD. In a subgroup analysis, we observed similar ADR tendencies, but with less thrombocytopenia in the TPM group.

SIGNIFICANCE

The incidence and trends of ADRs that were evaluated by CDM were similar to the previous literature. CDM can be a useful tool for analyzing ASD-related ADRs in a multicenter study. The strengths and limitations of CDM should be carefully addressed.

aer2vec: Distributed Representations of Adverse Event Reporting System Data as a Means to Identify Drug/Side-Effect Associations

Adverse event report (AER) data are a key source of signal for post marketing drug surveillance. The standard methodology to analyze AER data applies disproportionality metrics, which estimate the strength of drug/side-effect associations from discrete counts of their occurrence at report level. However, in other domains, improvements in predictive modeling accuracy have been obtained through representation learning, where discrete features are replaced by distributed representations learned from unlabeled data. This paper describes aer2vec, a novel representational approach for AER data in which concept embeddings emerge from neural networks trained to predict drug/side-effect co-occurrence. Trained models are evaluated for their utility in identifying drug/side-effect relationships, with improvements over disproportionality metrics in most cases. In addition, we evaluate the utility of an otherwise-untapped resource in the Food and Drug Administration (FDA) AER system - reporter designations of suspected causality - and find that incorporating this information enhances performance of all models evaluated.

Towards early detection of adverse drug reactions: combining pre-clinical drug structures and post-market safety reports

Background

Adverse drug reaction (ADR) is a major burden for patients and healthcare industry. Early and accurate detection of potential ADRs can help to improve drug safety and reduce financial costs. Post-market spontaneous reports of ADRs remain a cornerstone of pharmacovigilance and a series of drug safety signal detection methods play an important role in providing drug safety insights. However, existing methods require sufficient case reports to generate signals, limiting their usages for newly approved drugs with few (or even no) reports.

Methods

In this study, we propose a label propagation framework to enhance drug safety signals by combining drug chemical structures with FDA Adverse Event Reporting System (FAERS). First, we compute original drug safety signals via common signal detection algorithms. Then, we construct a drug similarity network based on chemical structures. Finally, we generate enhanced drug safety signals by propagating original signals on the drug similarity network. Our proposed framework enriches post-market safety reports with pre-clinical drug similarity network, effectively alleviating issues of insufficient cases for newly approved drugs.

Results

We apply the label propagation framework to four popular signal detection algorithms (PRR, ROR, MGPS, BCPNN) and find that our proposed framework generates more accurate drug safety signals than the corresponding baselines. In addition, our framework identifies potential ADRs for newly approved drugs, thus paving the way for early detection of ADRs.

Conclusions

The proposed label propagation framework combines pre-clinical drug structures with post-market safety reports, generates enhanced drug safety signals, and can potentially help to accurately detect ADRs ahead of time.

Availability

The source code for this paper is available at: https://github.com/ruoqi-liu/LP-SDA.

Complementing Observational Signals with Literature-Derived Distributed Representations for Post-Marketing Drug Surveillance

INTRODUCTION

As a result of the well documented limitations of data collected by spontaneous reporting systems (SRS), such as bias and under-reporting, a number of authors have evaluated the utility of other data sources for the purpose of pharmacovigilance, including the biomedical literature. Previous work has demonstrated the utility of literature-derived distributed representations (concept embeddings) with machine learning for the purpose of drug side-effect prediction. In terms of data sources, these methods are complementary, observing drug safety from two different perspectives (knowledge extracted from the literature and statistics from SRS data). However, the combined utility of these pharmacovigilance methods has yet to be evaluated.

OBJECTIVE

This research investigates the utility of directly or indirectly combining an observational signal from SRS with literature-derived distributed representations into a single feature vector or in an ensemble approach for downstream machine learning (logistic regression).

METHODS

Leveraging a recently developed representation scheme, concept embeddings were generated from relational connections extracted from the literature and composed to represent drug and associated adverse reactions, as defined by two reference standards of positive (likely causal) and negative (no causal evidence) pairs. Embeddings were presented with and without common measures of observational signal from SRS sources to logistic regressors, and performance was evaluated with the receiver operating characteristic (ROC) area under the curve (AUC) metric.

RESULTS

ROC AUC performance with these composite models improves up to ≈ 20% over SRS-based disproportionality metrics alone and exceeds the best prior results reported in the literature when models leverage both sources of information.

CONCLUSIONS

Results from this study support the hypothesis that knowledge extracted from the literature can enhance the performance of SRS-based methods (and vice versa). Across reference sets, using literature and SRS information together performed better than using either source alone, providing strong support for the complementary nature of these approaches to post-marketing drug surveillance.

What Could the Future of Safety Monitoring Look Like?

Like much of the clinical research and health care provider enterprise, the data capture and archiving for harm, probability of harm, and impact of intervention-related events is fragmented, inconsistent, and lacks standards to perform the types of operations that could inform researchers, practitioners, and patients in a timely way of actions and policies. The entire system of assessments, terminology, data formats and structure, analyses, and dissemination would benefit from changes based on adherence to a process framework of detect, describe, analyze, and react in the context of recognizing the multiple pathways and factors that lead to any specific outcome or series of outcomes. Existing tools, if properly applied, can form the basis for the next generation of data systems, processes, analyses, and sharing to address most of the current challenges.

On the evidence consistency of pharmacovigilance outcomes between Food and Drug Administration Adverse Event Reporting System and electronic medical record data for acute mania patients

Evaluation of premarketing drug safety in clinical trials is often limited, due to the relatively small sample size and short follow-up time. The data collected in the postmarketing spontaneous reporting systems such as Food and Drug Administration Adverse Event Reporting System as well as electronic medical record systems provide crucial information to evaluate postmarketing drug safety. In this article, we assess the strengths and limitations of Food and Drug Administration Adverse Event Reporting System and electronic medical record data in studying the postmarketing pharmacovigilance outcomes for 12 selected antidepressant drugs. In addition, we evaluate the consistency of the results obtained from these two data sources, and provide potential directions for evidence integration.

ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model

OBJECTIVE

Supplementing the Spontaneous Reporting System (SRS) with Electronic Health Record (EHR) data for adverse drug reaction detection could augment sample size, increase population heterogeneity and cross-validate results for pharmacovigilance research. The difference in the underlying data structures and terminologies between SRS and EHR data presents challenges when attempting to integrate the two into a single database. The Observational Health Data Sciences and Informatics (OHDSI) collaboration provides a Common Data Model (CDM) for organizing and standardizing EHR data to support large-scale observational studies. The objective of the study is to develop and evaluate an informatics platform known as ADEpedia-on-OHDSI, where spontaneous reporting data from FDA's Adverse Event Reporting System (FAERS) is converted into the OHDSI CDM format towards building a next generation pharmacovigilance signal detection platform.

METHODS

An extraction, transformation and loading (ETL) tool was designed, developed, and implemented to convert FAERS data into the OHDSI CDM format. A comprehensive evaluation, including overall ETL evaluation, mapping quality evaluation of drug names to RxNorm, and an evaluation of transformation and imputation quality, was then performed to assess the mapping accuracy and information loss using the FAERS data collected between 2012 and 2017. Previously published findings related to vascular safety profile of triptans were validated using ADEpedia-on-OHDSI in pharmacovigilance research. For the triptan-related vascular event detection, signals were detected by Reporting Odds Ratio (ROR) in high-level group terms (HLGT) level, high-level terms (HLT) level and preferred term (PT) level using the original FAERS data and CDM-based FAERS respectively. In addition, six standardized MedDRA queries (SMQs) related to vascular events were applied.

RESULTS

A total of 4,619,362 adverse event cases were loaded into 8 tables in the OHDSI CDM. For drug name mapping, 93.9% records and 47.0% unique names were matched with RxNorm codes. Mapping accuracy of drug names was 96% based on a manual verification of randomly sampled 500 unique mappings. Information loss evaluation showed that more than 93% of the data is loaded into the OHDSI CDM for most fields, with the exception of drug route data (66%). The replication study detected 5, 18, 47 and 6, 18, 50 triptan-related vascular event signals in MedDRA HLGT level, HLT level, and PT level for the original FAERS data and CDM-based FAERS respectively. The signal detection scores of six standardized MedDRA queries (SMQs) of vascular events in the raw data study were found to be lower than those scores in the CDM study.

CONCLUSION

The outcome of this work would facilitate seamless integration and combined analyses of both SRS and EHR data for pharmacovigilance in ADEpedia-on-OHDSI, our platform for next generation pharmacovigilance.

Authenticity and credibility aware detection of adverse drug events from social media

OBJECTIVES

Adverse drug events (ADEs) are among the top causes of hospitalization and death. Social media is a promising open data source for the timely detection of potential ADEs. In this paper, we study the problem of detecting signals of ADEs from social media.

METHODS

Detecting ADEs whose drug and AE may be reported in different posts of a user leads to major concerns regarding the content authenticity and user credibility, which have not been addressed in previous studies. Content authenticity concerns whether a post mentions drugs or adverse events that are actually consumed or experienced by the writer. User credibility indicates the degree to which chronological evidence from a user's sequence of posts should be trusted in the ADE detection. We propose AC-SPASM, a Bayesian model for the authenticity and credibility aware detection of ADEs from social media. The model exploits the interaction between content authenticity, user credibility and ADE signal quality. In particular, we argue that the credibility of a user correlates with the user's consistency in reporting authentic content.

RESULTS

We conduct experiments on a real-world Twitter dataset containing 1.2 million posts from 13,178 users. Our benchmark set contains 22 drugs and 8089 AEs. AC-SPASM recognizes authentic posts with F₁ - the harmonic mean of precision and recall of 80%, and estimates user credibility with precision@10 = 90% and NDCG@10 - a measure for top-10 ranking quality of 96%. Upon validation against known ADEs, AC-SPASM achieves F₁ = 91%, outperforming state-of-the-art baseline models by 32% (p < 0.05). Also, AC-SPASM obtains precision@456 = 73% and NDCG@456 = 94% in detecting and prioritizing unknown potential ADE signals for further investigation. Furthermore, the results show that AC-SPASM is scalable to large datasets.

CONCLUSIONS

Our study demonstrates that taking into account the content authenticity and user credibility improves the detection of ADEs from social media. Our work generates hypotheses to reduce experts' guesswork in identifying unknown potential ADEs.

Authenticity and credibility aware detection of adverse drug events from social media

OBJECTIVES

Adverse drug events (ADEs) are among the top causes of hospitalization and death. Social media is a promising open data source for the timely detection of potential ADEs. In this paper, we study the problem of detecting signals of ADEs from social media.

METHODS

Detecting ADEs whose drug and AE may be reported in different posts of a user leads to major concerns regarding the content authenticity and user credibility, which have not been addressed in previous studies. Content authenticity concerns whether a post mentions drugs or adverse events that are actually consumed or experienced by the writer. User credibility indicates the degree to which chronological evidence from a user's sequence of posts should be trusted in the ADE detection. We propose AC-SPASM, a Bayesian model for the authenticity and credibility aware detection of ADEs from social media. The model exploits the interaction between content authenticity, user credibility and ADE signal quality. In particular, we argue that the credibility of a user correlates with the user's consistency in reporting authentic content.

RESULTS

We conduct experiments on a real-world Twitter dataset containing 1.2 million posts from 13,178 users. Our benchmark set contains 22 drugs and 8089 AEs. AC-SPASM recognizes authentic posts with F₁ - the harmonic mean of precision and recall of 80%, and estimates user credibility with precision@10 = 90% and NDCG@10 - a measure for top-10 ranking quality of 96%. Upon validation against known ADEs, AC-SPASM achieves F₁ = 91%, outperforming state-of-the-art baseline models by 32% (p < 0.05). Also, AC-SPASM obtains precision@456 = 73% and NDCG@456 = 94% in detecting and prioritizing unknown potential ADE signals for further investigation. Furthermore, the results show that AC-SPASM is scalable to large datasets.

CONCLUSIONS

Our study demonstrates that taking into account the content authenticity and user credibility improves the detection of ADEs from social media. Our work generates hypotheses to reduce experts' guesswork in identifying unknown potential ADEs.

Learning predictive models of drug side-effect relationships from distributed representations of literature-derived semantic predications

Objective

The aim of this work is to leverage relational information extracted from biomedical literature using a novel synthesis of unsupervised pretraining, representational composition, and supervised machine learning for drug safety monitoring.

Methods

Using ≈80 million concept-relationship-concept triples extracted from the literature using the SemRep Natural Language Processing system, distributed vector representations (embeddings) were generated for concepts as functions of their relationships utilizing two unsupervised representational approaches. Embeddings for drugs and side effects of interest from two widely used reference standards were then composed to generate embeddings of drug/side-effect pairs, which were used as input for supervised machine learning. This methodology was developed and evaluated using cross-validation strategies and compared to contemporary approaches. To qualitatively assess generalization, models trained on the Observational Medical Outcomes Partnership (OMOP) drug/side-effect reference set were evaluated against a list of ≈1100 drugs from an online database.

Results

The employed method improved performance over previous approaches. Cross-validation results advance the state of the art (AUC 0.96; F1 0.90 and AUC 0.95; F1 0.84 across the two sets), outperforming methods utilizing literature and/or spontaneous reporting system data. Examination of predictions for unseen drug/side-effect pairs indicates the ability of these methods to generalize, with over tenfold label support enrichment in the top 100 predictions versus the bottom 100 predictions.

Discussion and Conclusion

Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples.

An MCEM Framework for Drug Safety Signal Detection and Combination from Heterogeneous Real World Evidence

Delayed drug safety insights can impact patients, pharmaceutical companies, and the whole society. Post-market drug safety surveillance plays a critical role in providing drug safety insights, where real world evidence such as spontaneous reporting systems (SRS) and a series of disproportional analysis serve as a cornerstone of proactive and predictive drug safety surveillance. However, they still face several challenges including concomitant drugs confounders, rare adverse drug reaction (ADR) detection, data bias, and the under-reporting issue. In this paper, we are developing a new framework that detects improved drug safety signals from multiple data sources via Monte Carlo Expectation-Maximization (MCEM) and signal combination. In MCEM procedure, we propose a new sampling approach to generate more accurate SRS signals for each ADR through iteratively down-weighting their associations with irrelevant drugs in case reports. While in signal combination step, we adopt Bayesian hierarchical model and propose a new summary statistic such that SRS signals can be combined with signals derived from other observational health data allowing for related signals to borrow statistical support with adjustment of data reliability. They combined effectively alleviate the concomitant confounders, data bias, rare ADR and under-reporting issues. Experimental results demonstrated the effectiveness and usefulness of the proposed framework.

The Patient's Voice in Pharmacovigilance: Pragmatic Approaches to Building a Patient-Centric Drug Safety Organization

Patient-centeredness has become an acknowledged hallmark of not only high-quality health care but also high-quality drug development. Biopharmaceutical companies are actively seeking to be more patient-centric in drug research and development by involving patients in identifying target disease conditions, participating in the design of, and recruitment for, clinical trials, and disseminating study results. Drug safety departments within the biopharmaceutical industry are at a similar inflection point. Rising rates of per capita prescription drug use underscore the importance of having robust pharmacovigilance systems in place to detect and assess adverse drug reactions (ADRs). At the same time, the practice of pharmacovigilance is being transformed by a host of recent regulatory guidances and related initiatives which emphasize the importance of the patient’s perspective in drug safety. Collectively, these initiatives impact the full range of activities that fall within the remit of pharmacovigilance, including ADR reporting, signal detection and evaluation, risk management, medication error assessment, benefit–risk assessment and risk communication. Examples include the fact that manufacturing authorization holders are now expected to monitor all digital sources under their control for potential reports of ADRs, and the emergence of new methods for collecting, analysing and reporting patient-generated ADR reports for signal detection and evaluation purposes. A drug safety department’s ability to transition successfully into a more patient-centric organization will depend on three defining attributes: (1) a patient-centered culture; (2) deployment of a framework to guide patient engagement activities; and (3) demonstrated proficiency in patient-centered competencies, including patient engagement, risk communication and patient preference assessment. Whether, and to what extent, drug safety departments embrace the new patient-centric imperative, and the methods and processes they implement to achieve this end effectively and efficiently, promise to become distinguishing factors in the highly competitive biopharmaceutical industry landscape.

Innovative Digital Tools and Surveillance Systems for the Timely Detection of Adverse Events at the Point of Care: A Proof-of-Concept Study

INTRODUCTION AND OBJECTIVE

Regulatory authorities often receive poorly structured safety reports requiring considerable effort to investigate potential adverse events post hoc. Automated question-and-answer systems may help to improve the overall quality of safety information transmitted to pharmacovigilance agencies. This paper explores the use of the VACC-Tool (ViVI Automated Case Classification Tool) 2.0, a mobile application enabling physicians to classify clinical cases according to 14 pre-defined case definitions for neuroinflammatory adverse events (NIAE) and in full compliance with data standards issued by the Clinical Data Interchange Standards Consortium.

METHODS

The validation of the VACC-Tool 2.0 (beta-version) was conducted in the context of a unique quality management program for children with suspected NIAE in collaboration with the Robert Koch Institute in Berlin, Germany. The VACC-Tool was used for instant case classification and for longitudinal follow-up throughout the course of hospitalization. Results were compared to International Classification of Diseases , Tenth Revision (ICD-10) codes assigned in the emergency department (ED).

RESULTS

From 07/2013 to 10/2014, a total of 34,368 patients were seen in the ED, and 5243 patients were hospitalized; 243 of these were admitted for suspected NIAE (mean age: 8.5 years), thus participating in the quality management program. Using the VACC-Tool in the ED, 209 cases were classified successfully, 69 % of which had been missed or miscoded in the ED reports. Longitudinal follow-up with the VACC-Tool identified additional NIAE.

CONCLUSION

Mobile applications are taking data standards to the point of care, enabling clinicians to ascertain potential adverse events in the ED setting and during inpatient follow-up. Compliance with Clinical Data Interchange Standards Consortium (CDISC) data standards facilitates data interoperability according to regulatory requirements.

Representing Knowledge Consistently Across Health Systems

Objectives: Electronic health records (EHRs) have increasingly emerged as a powerful source of clinical data that can be leveraged for reuse in research and in modular health apps that integrate into diverse health information technologies. A key challenge to these use cases is representing the knowledge contained within data from different EHR systems in a uniform fashion. Method: We reviewed several recent studies covering the knowledge representation in the common data models for the Observational Medical Outcomes Partnership (OMOP) and its Observational Health Data Sciences and Informatics program, and the United States Patient Centered Outcomes Research Network (PCORNet). We also reviewed the Health Level 7 Fast Healthcare Interoperability Resource standard supporting app-like programs that can be used across multiple EHR and research systems. Results: There has been a recent growth in high-impact efforts to support quality-assured and standardized clinical data sharing across different institutions and EHR systems. We focused on three major efforts as part of a larger landscape moving towards shareable, transportable, and computable clinical data. Conclusion: The growth in approaches to developing common data models to support interoperable knowledge representation portends an increasing availability of high-quality clinical data in support of research. Building on these efforts will allow a future whereby significant portions of the populations in the world may be able to share their data for research.

Large-scale adverse effects related to treatment evidence standardization (LAERTES): an open scalable system for linking pharmacovigilance evidence sources with clinical data

BACKGROUND

Integrating multiple sources of pharmacovigilance evidence has the potential to advance the science of safety signal detection and evaluation. In this regard, there is a need for more research on how to integrate multiple disparate evidence sources while making the evidence computable from a knowledge representation perspective (i.e., semantic enrichment). Existing frameworks suggest well-promising outcomes for such integration but employ a rather limited number of sources. In particular, none have been specifically designed to support both regulatory and clinical use cases, nor have any been designed to add new resources and use cases through an open architecture. This paper discusses the architecture and functionality of a system called Large-scale Adverse Effects Related to Treatment Evidence Standardization (LAERTES) that aims to address these shortcomings.

RESULTS

LAERTES provides a standardized, open, and scalable architecture for linking evidence sources relevant to the association of drugs with health outcomes of interest (HOIs). Standard terminologies are used to represent different entities. For example, drugs and HOIs are represented in RxNorm and Systematized Nomenclature of Medicine -- Clinical Terms respectively. At the time of this writing, six evidence sources have been loaded into the LAERTES evidence base and are accessible through prototype evidence exploration user interface and a set of Web application programming interface services. This system operates within a larger software stack provided by the Observational Health Data Sciences and Informatics clinical research framework, including the relational Common Data Model for observational patient data created by the Observational Medical Outcomes Partnership. Elements of the Linked Data paradigm facilitate the systematic and scalable integration of relevant evidence sources.

CONCLUSIONS

The prototype LAERTES system provides useful functionality while creating opportunities for further research. Future work will involve improving the method for normalizing drug and HOI concepts across the integrated sources, aggregated evidence at different levels of a hierarchy of HOI concepts, and developing more advanced user interface for drug-HOI investigations.

Literature-Based Discovery of Confounding in Observational Clinical Data

Observational data recorded in the Electronic Health Record (EHR) can help us better understand the effects of therapeutic agents in routine clinical practice. As such data were not collected for research purposes, their reuse for research must compensate for additional information that may bias analyses and lead to faulty conclusions. Confounding is present when factors aside from the given predictor(s) affect the response of interest. However, these additional factors may not be known at the outset. In this paper, we present a scalable literature-based confounding variable discovery method for biomedical research applications with pharmacovigilance as our use case. We hypothesized that statistical models, adjusted with literature-derived confounders, will more accurately identify causative drug-adverse drug event (ADE) relationships. We evaluated our method with a curated reference standard, and found a pattern of improved performance ~ 5% in two out of three models for gastrointestinal bleeding (pre-adjusted Area Under Curve ≥ 0.6).

Pharmacovigilance and Biomedical Informatics: A Model for Future Development

PURPOSE

The discipline of pharmacovigilance is rooted in the aftermath of the thalidomide tragedy of 1961. It has evolved as a result of collaborative efforts by many individuals and organizations, including physicians, patients, Health Authorities, universities, industry, the World Health Organization, the Council for International Organizations of Medical Sciences, and the International Conference on Harmonisation. Biomedical informatics is rooted in technologically based methodologies and has evolved at the speed of computer technology. The purpose of this review is to bring a novel lens to pharmacovigilance, looking at the evolution and development of the field of pharmacovigilance from the perspective of biomedical informatics, with the explicit goal of providing a foundation for discussion of the future direction of pharmacovigilance as a discipline.

METHODS

For this review, we searched [publication trend for the log₁₀ value of the numbers of publications identified in PubMed] using the key words [informatics (INF), pharmacovigilance (PV), phar-macovigilance þ informatics (PV þ INF)], for [study types] articles published between [1994-2015]. We manually searched the reference lists of identified articles for additional information.

IMPLICATIONS

Biomedical informatics has made significant contributions to the infrastructural development of pharmacovigilance. However, there has not otherwise been a systematic assessment of the role of biomedical informatics in enhancing the field of pharmacovigilance, and there has been little cross-discipline scholarship. Rapidly developing innovations in biomedical informatics pose a challenge to pharmacovigilance in finding ways to include new sources of safety information, including social media, massively linked databases, and mobile and wearable wellness applications and sensors. With biomedical informatics as a lens, it is evident that certain aspects of pharmacovigilance are evolving more slowly. However, the high levels of mutual interest in both fields and intense global and economic external pressures offer opportunities for a future of closer collaboration.

Using Rich Data on Comorbidities in Case-Control Study Design with Electronic Health Record Data Improves Control of Confounding in the Detection of Adverse Drug Reactions

Recent research has suggested that the case-control study design, unlike the self-controlled study design, performs poorly in controlling confounding in the detection of adverse drug reactions (ADRs) from administrative claims and electronic health record (EHR) data, resulting in biased estimates of the causal effects of drugs on health outcomes of interest (HOI) and inaccurate confidence intervals. Here we show that using rich data on comorbidities and automatic variable selection strategies for selecting confounders can better control confounding within a case-control study design and provide a more solid basis for inference regarding the causal effects of drugs on HOIs. Four HOIs are examined: acute kidney injury, acute liver injury, acute myocardial infarction and gastrointestinal ulcer hospitalization. For each of these HOIs we use a previously published reference set of positive and negative control drugs to evaluate the performance of our methods. Our methods have AUCs that are often substantially higher than the AUCs of a baseline method that only uses demographic characteristics for confounding control. Our methods also give confidence intervals for causal effect parameters that cover the expected no effect value substantially more often than this baseline method. The case-control study design, unlike the self-controlled study design, can be used in the fairly typical setting of EHR databases without longitudinal information on patients. With our variable selection method, these databases can be more effectively used for the detection of ADRs.

Detecting signals of detrimental prescribing cascades from social media

MOTIVATION

Prescribing cascade (PC) occurs when an adverse drug reaction (ADR) is misinterpreted as a new medical condition, leading to further prescriptions for treatment. Additional prescriptions, however, may worsen the existing condition or introduce additional adverse effects (AEs). Timely detection and prevention of detrimental PCs is essential as drug AEs are among the leading causes of hospitalization and deaths. Identifying detrimental PCs would enable warnings and contraindications to be disseminated and assist the detection of unknown drug AEs. Nonetheless, the detection is difficult and has been limited to case reports or case assessment using administrative health claims data. Social media is a promising source for detecting signals of detrimental PCs due to the public availability of many discussions regarding treatments and drug AEs.

OBJECTIVE

In this paper, we investigate the feasibility of detecting detrimental PCs from social media.

METHODS

The detection, however, is challenging due to the data uncertainty and data rarity in social media. We propose a framework to mine sequences of drugs and AEs that signal detrimental PCs, taking into account the data uncertainty and data rarity.

RESULTS

We conduct experiments on two real-world datasets collected from Twitter and Patient health forum. Our framework achieves encouraging results in the validation against known detrimental PCs (F1=78% for Twitter and 68% for Patient) and the detection of unknown potential detrimental PCs (Precision@50=72% and NDCG@50=95% for Twitter, Precision@50=86% and NDCG@50=98% for Patient). In addition, the framework is efficient and scalable to large datasets.

CONCLUSION

Our study demonstrates the feasibility of generating hypotheses of detrimental PCs from social media to reduce pharmacists' guesswork.

Using Literature-Based Discovery to Explain Adverse Drug Effects

We report on our research in using literature-based discovery (LBD) to provide pharmacological and/or pharmacogenomic explanations for reported adverse drug effects. The goal of LBD is to generate novel and potentially useful hypotheses by analyzing the scientific literature and optionally some additional resources. Our assumption is that drugs have effects on some genes or proteins and that these genes or proteins are associated with the observed adverse effects. Therefore, by using LBD we try to find genes or proteins that link the drugs with the reported adverse effects. These genes or proteins can be used to provide insight into the processes causing the adverse effects. Initial results show that our method has the potential to assist in explaining reported adverse drug effects.