Comparative analysis of pharmacovigilance methods in the detection of adverse drug reactions using electronic medical records

A Comparison of Active Pharmacovigilance Strategies Used to Monitor Adverse Events to Antiviral Agents: A Systematic Review

INTRODUCTION

The safety of antiviral agents in real-world clinical settings is crucial, as pre-marketing studies often do not capture all adverse events (AE). Active pharmacovigilance strategies are essential for detecting and characterising these AE comprehensively.

OBJECTIVE

The aim of this study was to identify and characterise active pharmacovigilance strategies used in real-world clinical settings for patients under systemic antiviral agents, focusing on the frequency of AE and the clinical data sources used.

METHODS

We conducted a systematic review by searching three electronic bibliographic databases targeting observational prospective active pharmacovigilance studies, phase IV clinical trials for post-marketing safety surveillance, and interventional studies assessing active pharmacovigilance strategies, focusing on individuals exposed to systemic antiviral agents.

RESULTS

We included 36 primary studies, predominantly using Drug Event Monitoring (DEM), with a minority employing sentinel sites and registries. Human immunodeficiency virus (HIV) was the most common condition, with the majority using DEM. Within the DEM, there was a wide range of incidences of patients experiencing at least one AE, and most of these studies used one or two data sources. Sentinel site studies were less common, with two on hepatitis C virus (HCV) and one on HIV, each relying on one or two data sources. The single study using a registry focusing on HIV therapy reported using just one data source. Patient interviews were the most common data source, followed by medical records and laboratory tests. The quality of the studies was considered 'good' in 18/36, 'fair' in 1/36, and 'poor' in 17/36 studies.

CONCLUSION

DEM was the predominant pharmacovigilance strategy, employing multiple data sources, and appears to increase the likelihood of detecting higher AE incidence. Establishing such a framework would facilitate a more detailed and consistent approach across different studies and settings.

Adverse event reporting of the IGF-1R monoclonal antibody teprotumumab: a real-world study based on the US food and drug administration adverse event reporting system

Background

Teprotumumab, an IGF-1R monoclonal antibody, has shown significant efficacy in treating thyroid eye disease (TED). However, since teprotumumab was launched in 2020 and first approved in the United States, there were limited reports of post-marketing adverse events (AEs). In this study, we aimed to mine and analyze the AEs signals with teprotumumab on the basis of the United States Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) to provide instructions in clinical practice concerning adverse reactions and assistance in drug development and import/export into other countries.

Methods

All AE reports were obtained from the FAERS database from the first quarter of 2020 to the fourth quarter of 2023. To comprehensively analyze the AEs, we applied four disproportionality analysis algorithms, including the reporting odds ratio (ROR), the proportional reporting ratio (PRR), the Bayesian confidence propagation neural network (BCPNN), and the multi-item gamma Poisson shrinker (MGPS) algorithms.

Results

A total of 687 reports from 200 patients related to administration of teprotumumab were obtained, and 78% of the cases was female. Signal detection of teprotumumab at the system organ class (SOC) level included gastrointestinal disorders, ear and labyrinth disorders, general disorders and administration site conditions, nervous system disorders, and musculoskeletal and connective tissue disorders. AEs that ranked top five at the preferred terms (PTs) level were muscle spasms, fatigue, tinnitus, headache, and deafness. The median time to those AEs onsets was 48 days (interquartile range 19.0-92.0 days) after administering drugs. Additionally, our results indicated the AEs in reproductive system and breast disorders because the prevalence of TED was more common in women.

Conclusion

This study identified many AEs associated with teprotumumab and unveiled potential new AE signals. These results can provide valuable evidence for further clinical application of teprotumumab and are important in enhancing clinical medication safety.

Exploring Health Informatics in the Battle against Drug Addiction: Digital Solutions for the Rising Concern

Drug addiction is a rising concern globally that has deeply attracted the attention of the healthcare sector. The United States is not an exception, and the drug addiction crisis there is even more serious, with 10% of adults having faced substance use disorder, while around 75% of this number has been reported as not having received any treatment. Surprisingly, there are annually over 70,000 deaths reported as being due to drug overdose. Researchers are continually searching for solutions, as the current strategies have been ineffective. Health informatics platforms like electronic health records, telemedicine, and the clinical decision support system have great potential in tracking the healthcare data of patients on an individual basis and provide precise medical support in a private space. Such technologies have been found to be useful in identifying the risk factors of drug addiction among people and mitigating them. Moreover, the platforms can be used to check prescriptions of addictive drugs such as opioids and caution healthcare providers. Programs such as the Prescription Drug Monitoring Program (PDMP) and the Drug and Alcohol Services Information Systems (DASIS) are already in action in the US, but the situation demands more in-depth studies in order to mitigate substance use disorders. Artificial intelligence (AI), when combined with health informatics, can aid in the analysis of large amounts of patient data and aid in classifying nature of addiction to assist in the provision of personalized care.

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.

Current Scenario and Future Prospects of Adverse Drug Reactions (ADRs) Monitoring and Reporting Mechanisms in the Rural Areas of India

BACKGROUND

Pharmacovigilance (PV) deals with the detection, collection, assessment, understanding, and prevention of adverse effects associated with drugs. The objective of PV is to ensure the safety of the medicines and patients by monitoring and reporting all adverse drug reactions (ADRs) associated with prescribed medicine usage. Findings have indicated that about 0.2- 24% of hospitalization cases are due to ADRs, of which 3.7% of patients have lethal ADRs. The reasons include the number of prescribed drugs, an increased number of new medicines in the market, an inadequate PV system for ADR monitoring, and a need for more awareness and knowledge about ADR reporting. Severe ADRs lead to enhanced hospital stays, increased treatment costs, risk of death, and many medical and economic consequences. Therefore, ADR reporting at its first instance is essential to avoid further harmful effects of the prescribed drugs. In India, the rate of ADR reporting is less than 1%, whereas worldwide, it is 5% due to a need for more awareness about PV and ADR monitoring among healthcare providers and patients. The main objective of this review is to highlight the current scenario and possible futuristic ways of ADR reporting methods in rural areas of India. We have searched the literature using PubMed, Google scholar, Indian citation index to retrieve the resources related to ADR monitoring and reporting in India's urban and rural areas. Spontaneous reporting is the most commonly used PV method to report ADRs in India's urban and rural areas. Evidence revealed that no effective ADR reporting mechanisms developed in rural areas causing underreporting of ADR, thus increasing the threat to the rural population. Hence, PV and ADR reporting awareness among healthcare professionals and patients, telecommunication, telemedicine, use of social media and electronic medical records, and artificial intelligence are the potential approaches for prevention, monitoring, and reporting of ADRs in rural areas.

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.

Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources

With the rapid development of artificial intelligence (AI) technologies, and the large amount of pharmacovigilance-related data stored in an electronic manner, data-driven automatic methods need to be urgently applied to all aspects of pharmacovigilance to assist healthcare professionals. However, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings. Analyzing challenges and solutions for AI-based pharmacovigilance in resource-limited settings can improve pharmacovigilance frameworks and capabilities in these settings. In this review, we summarize the challenges into four categories: establishing a database for an AI-based pharmacovigilance system, lack of human resources, weak AI technology and insufficient government support. This study also discusses possible solutions and future perspectives on AI-based pharmacovigilance in resource-limited settings.

A weakly supervised model for the automated detection of adverse events using clinical notes

With clinical trials unable to detect all potential adverse reactions to drugs and medical devices prior to their release into the market, accurate post-market surveillance is critical to ensure their safety and efficacy. Electronic health records (EHR) contain rich observational patient data, making them a valuable source to actively monitor the safety of drugs and devices. While structured EHR data and spontaneous reporting systems often underreport the complexities of patient encounters and outcomes, free-text clinical notes offer greater detail about a patient's status. Previous studies have proposed machine learning methods to detect adverse events from clinical notes, but suffer from manually extracted features, reliance on costly hand-labeled data, and lack of validation on external datasets. To address these challenges, we develop a weakly-supervised machine learning framework for adverse event detection from unstructured clinical notes and evaluate it on insulin pump failure as a test case. Our model accurately detected cases of pump failure with 0.842 PR AUC on the holdout test set and 0.815 PR AUC when validated on an external dataset. Our approach allowed us to leverage a large dataset with far less hand-labeled data and can be easily transferred to additional adverse events for scalable post-market surveillance.

A statistical quality assessment method for longitudinal observations in electronic health record data with an application to the VA million veteran program

Background

To describe an automated method for assessment of the plausibility of continuous variables collected in the electronic health record (EHR) data for real world evidence research use.

Methods

The most widely used approach in quality assessment (QA) for continuous variables is to detect the implausible numbers using prespecified thresholds. In augmentation to the thresholding method, we developed a score-based method that leverages the longitudinal characteristics of EHR data for detection of the observations inconsistent with the history of a patient. The method was applied to the height and weight data in the EHR from the Million Veteran Program Data from the Veteran’s Healthcare Administration (VHA). A validation study was also conducted.

Results

The receiver operating characteristic (ROC) metrics of the developed method outperforms the widely used thresholding method. It is also demonstrated that different quality assessment methods have a non-ignorable impact on the body mass index (BMI) classification calculated from height and weight data in the VHA’s database.

Conclusions

The score-based method enables automated and scaled detection of the problematic data points in health care big data while allowing the investigators to select the high-quality data based on their need. Leveraging the longitudinal characteristics in EHR will significantly improve the QA performance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01643-2.

Real-world data-based adverse drug reactions detection from the Korea Adverse Event Reporting System databases with electronic health records-based detection algorithm

Pharmacovigilance involves monitoring of drugs and their adverse drug reactions (ADRs) and is essential for their safety post-marketing. Because of the different types and structures of medical databases, several previous surveillance studies have analyzed only one database. In the present study, we extracted potential drug-ADR pairs from electronic health record (EHR) data using the MetaNurse algorithm and analyzed them using the Korean Adverse Event Reporting System (KAERS) database for systematic validation. The Medical Dictionary for Regulatory Activities (MedDRA) and World Health Organization (WHO) Adverse Reactions Terminology (WHO-ART) were mapped for signal detection. We used the Side Effect Resource (SIDER) database to select 2663 drug-ADR pairs to investigate unknown drug-induced ADRs. The reporting odds ratio (ROR) value was calculated for the drug-exposed and non-exposed groups of drug-ADR pairs, and 19 potential pairs showed significant signals. Appropriate terminology systems and criteria are needed to handle diverse medical databases.

Association of Breast Implants with Nonspecific Symptoms, Connective Tissue Diseases, and Allergic Reactions: A Retrospective Cohort Analysis

BACKGROUND

Given the rising media attention regarding various adverse conditions attributed to breast implants, the authors examined the association between breast implantation and the risk of being diagnosed with connective tissue diseases, allergic reactions, and nonspecific constitutional complaints in a cohort study with longitudinal follow-up.

METHODS

Women enrolled in a regional military health care system between 2003 and 2012 were evaluated in this retrospective cohort study. A propensity score was generated to match women who underwent breast implantation with women who did not undergo breast implantation. The propensity score included age, social history, health care use, comorbidities, and medication use. Outcomes assessed included International Classification of Diseases, Ninth Revision, diagnoses codes for (1) nonspecific constitutional symptoms, (2) nonspecific cardiac conditions, (3) rheumatoid arthritis and systemic lupus erythematosus, (4) other connective tissue diseases, and (5) allergic reactions.

RESULTS

Of 22,063 women included in the study (513 breast implants and 21,550 controls), we propensity score-matched 452 breast implant recipients with 452 nonrecipients. Odds ratios and 95 percent confidence intervals in breast implant recipients compared to nonrecipients were similar, including nonspecific constitutional symptoms (OR, 0.77; 95 percent CI, 0.53 to 1.13), nonspecific cardiac conditions (OR, 0.97; 95 percent CI, 0.69 to 1.37), rheumatoid arthritis and systemic lupus erythematosus (OR, 0.66; 95 percent CI, 0.33 to 1.31), other connective tissue diseases (OR, 1.02; 95 percent CI, 0.78 to 1.32), and allergic reactions (OR, 1.18; 95 percent CI, 0.84 to 1.66).

CONCLUSIONS

Women with breast implants did not have an increased likelihood of being diagnosed with nonspecific constitutional symptoms, connective tissue disorders, and/or allergic reaction conditions.

CLINICAL QUESTION/LEVEL OF EVIDENCE

Therapeutic, III.

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.

SGLT-2 inhibitors and atrial fibrillation in the Food and Drug Administration adverse event reporting system

Background

Sodium glucose cotransporter-2 inhibitors (SGLT2i) reduce the risk of heart failure and new data show they can prevent atrial fibrillation (AF). We examined the association between SGLT2i and AF in the Food and Drug Administration adverse event reporting system (FAERS).

Methods

We mined the FAERS from 2014q1 to 2019q4 to compare AF reporting for SGLT-2 i versus reports for other glucose lowering medications (ATC10 class). Several exclusions were sequentially applied for: concomitant medications; diabetes, cardiovascular or renal disease indication; reports for competing adverse events (genitourinary tract infections, ketoacidosis, Fournier’s gangrene, amputation). We provide descriptive statistics and calculated proportional reporting ratios (PRR).

Results

There were 62,098 adverse event reports for SGLT2i and 642,031 reports for other ATC10 drugs. The reporting of AF was significantly lower with SGLT2i than with other ATC10 drugs (4.8 versus 8.7/1000; p < 0.001) with a PRR of 0.55 (0.49–0.62). Results did not change substantially after excluding reports listing insulin (PRR 0.49) or anti-arrhythmics (PRR 0.59) as suspect or concomitant drugs, excluding reports with indications for cardiovascular disease (PRR 0.49) or renal disease (PRR 0.55), and those filed for competing adverse events (PRR 0.63). Results were always statistically significant whether the diabetes indication was specified. Negative and positive controls confirmed internal validity of the database.

Conclusions

In a large pharmacovigilance database, AF was robustly and consistently reported more frequently for diabetes medications other than SGLT2i. This finding complements available evidence from trials supporting a protective role of SGLT2i against the occurrence of AF.

Is Statin Use Associated With Risk of Thyroid Diseases? Results of a Retrospective Cohort Study

BACKGROUND

Given the ubiquity of statin use and prevalence of thyroid diseases, such as thyroid cancer, hyperthyroidism, and thyroiditis, understanding their association deserves further attention.

OBJECTIVE

To examine the association between statin use and thyroid cancer, thyrotoxicosis, goiter, and thyroiditis.

METHODS

Using Tricare data, 2 propensity score (PS)-matched cohorts of statin users and nonusers were formed: (1) a PS-matched general cohort (all patients aged 30-85 years) and (2) a PS-matched healthy cohort (excluded patients with cardiovascular diseases or severe comorbidities). Outcomes were thyroid cancer, thyrotoxicosis, goiter, and thyroiditis. Odds ratios (ORs) and 95% CIs of outcomes were estimated using conditional regression analysis.

RESULTS

Of 43 438 patients, the PS-matched general cohort matched 6342 statin users to 6342 nonusers. The OR of thyroid cancer was 0.62 (95% CI = 0.39-0.996). There was no significant difference between statin users and nonusers in risk of thyrotoxicosis (OR = 0.88; 95% CI = 0.71-1.09), goiter (OR = 0.9; 95% CI = 0.77-1.03), or thyroiditis (OR = 0.78; 95% CI = 0.53-1.15). In the PS-matched healthy cohort (3351 statin users to 3351 nonusers), there was no difference between statin users and nonusers in any outcome. Limitations of the study include its retrospective observational design and use of administrative codes in outcomes ascertainment.

CONCLUSION AND RELEVANCE

This study did not demonstrate any association of statins with harmful effects on thyroid diseases, which offers assurance to clinicians and patients. Furthermore, statin use appears to be associated with a decreased risk of thyroid cancer, but more studies are needed.

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

Biobanks linked to electronic health records provide rich resources for health-related research. With improvements in administrative and informatics infrastructure, the availability and utility of data from biobanks have dramatically increased. In this paper, we first aim to characterize the current landscape of available biobanks and to describe specific biobanks, including their place of origin, size, and data types. The development and accessibility of large-scale biorepositories provide the opportunity to accelerate agnostic searches, expedite discoveries, and conduct hypothesis-generating studies of disease-treatment, disease-exposure, and disease-gene associations. Rather than designing and implementing a single study focused on a few targeted hypotheses, researchers can potentially use biobanks' existing resources to answer an expanded selection of exploratory questions as quickly as they can analyze them. However, there are many obvious and subtle challenges with the design and analysis of biobank-based studies. Our second aim is to discuss statistical issues related to biobank research such as study design, sampling strategy, phenotype identification, and missing data. We focus our discussion on biobanks that are linked to electronic health records. Some of the analytic issues are illustrated using data from the Michigan Genomics Initiative and UK Biobank, two biobanks with two different recruitment mechanisms. We summarize the current body of literature for addressing these challenges and discuss some standing open problems. This work complements and extends recent reviews about biobank-based research and serves as a resource catalog with analytical and practical guidance for statisticians, epidemiologists, and other medical researchers pursuing research using biobanks.

Key Elements in Adverse Drug Reactions Safety Signals: Application of Legal Strategies

Adverse drug reactions, or unintended and harmful outcomes related to the administration of a pharmaceutical product, are a major public health concern, particularly for cancer patients. If counted as a separate cause of death, adverse drug reactions would represent the fourth leading cause of death in the United States. Several legal strategies are available to help mitigate their occurrences and to compensate victims for the harm that results from adverse events. Prior to FDA approval of a drug, the limited size and duration of clinical trials often fail to detect adverse drug reactions. However, after FDA approval, pharmacovigilance efforts are bolstered by recent expansions of FDA post-marketing regulatory powers codified in the 2007 Food and Drug Administration Amendments Act, as well as advances in big data analytics that improve adverse signal detection through data mining of large electronic health records. For victims of adverse drug reactions, tort lawsuits filed in the courts help compensate for the harm suffered and may also serve as warnings to manufacturers to improve drug safety to avoid future legal liability. While encouraging developments have occurred, new and existing legal structures to mitigate and compensate for adverse drug reactions must continue to be refined given increasingly complex pharmaceutical agents.

Machine learning model combining features from algorithms with different analytical methodologies to detect laboratory-event-related adverse drug reaction signals

Background

The importance of identifying and evaluating adverse drug reactions (ADRs) has been widely recognized. Many studies have developed algorithms for ADR signal detection using electronic health record (EHR) data. In this study, we propose a machine learning (ML) model that enables accurate ADR signal detection by integrating features from existing algorithms based on inpatient EHR laboratory results.

Materials and methods

To construct an ADR reference dataset, we extracted known drug–laboratory event pairs represented by a laboratory test from the EU-SPC and SIDER databases. All possible drug–laboratory event pairs, except known ones, are considered unknown. To detect a known drug–laboratory event pair, three existing algorithms—CERT, CLEAR, and PACE—were applied to 21-year inpatient EHR data. We also constructed ML models (based on random forest, L1 regularized logistic regression, support vector machine, and a neural network) that use the intermediate products of the CERT, CLEAR, and PACE algorithms as inputs and determine whether a drug–laboratory event pair is associated. For performance comparison, we evaluated the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1-measure, and area under receiver operating characteristic (AUROC).

Results

All measures of ML models outperformed those of existing algorithms with sensitivity of 0.593–0.793, specificity of 0.619–0.796, NPV of 0.645–0.727, PPV of 0.680–0.777, F1-measure of 0.629–0.709, and AUROC of 0.737–0.816. Features related to change or distribution of shape were considered important for detecting ADR signals.

Conclusions

Improved performance of ML models indicated that applying our model to EHR data is feasible and promising for detecting more accurate and comprehensive ADR signals.

PregOMICS-Leveraging systems biology and bioinformatics for drug repurposing in maternal-child health

Obstetric diseases remain underserved and understudied. Drug repurposing-utilization of a drug whose use is accepted in one condition for a different condition-could represent a rapid and low-cost way to identify new therapies that are known to be safe. In diseases of pregnancy, the known safety profile is a strong additional incentive. We describe the techniques and steps used in the use of 'omics data for drug repurposing. We illustrate these techniques using case studies of published drug repurposing projects. We provide a set of available databases with low barriers to entry which investigators can use to perform their own projects. The promise of 'omics techniques is unbiased screening, either of all drug targets or of all patients using particular drugs to find which are likely to alter disease risk or progression. However, we caution that reproducibility across the underlying studies, and thus the drugs suggested for repurposing, can be poor. We suggest that improved nosology, for example correlating patient clinical conditions with placental pathology, could yield more robust associations. We conclude that 'omics-driven drug repurposing represents a potential fruitful path to discover new, safe treatments of obstetric diseases.

Clinical Relation Extraction Toward Drug Safety Surveillance Using Electronic Health Record Narratives: Classical Learning Versus Deep Learning

BACKGROUND

Medication and adverse drug event (ADE) information extracted from electronic health record (EHR) notes can be a rich resource for drug safety surveillance. Existing observational studies have mainly relied on structured EHR data to obtain ADE information; however, ADEs are often buried in the EHR narratives and not recorded in structured data.

OBJECTIVE

To unlock ADE-related information from EHR narratives, there is a need to extract relevant entities and identify relations among them. In this study, we focus on relation identification. This study aimed to evaluate natural language processing and machine learning approaches using the expert-annotated medical entities and relations in the context of drug safety surveillance, and investigate how different learning approaches perform under different configurations.

METHODS

We have manually annotated 791 EHR notes with 9 named entities (eg, medication, indication, severity, and ADEs) and 7 different types of relations (eg, medication-dosage, medication-ADE, and severity-ADE). Then, we explored 3 supervised machine learning systems for relation identification: (1) a support vector machines (SVM) system, (2) an end-to-end deep neural network system, and (3) a supervised descriptive rule induction baseline system. For the neural network system, we exploited the state-of-the-art recurrent neural network (RNN) and attention models. We report the performance by macro-averaged precision, recall, and F1-score across the relation types.

RESULTS

Our results show that the SVM model achieved the best average F1-score of 89.1% on test data, outperforming the long short-term memory (LSTM) model with attention (F1-score of 65.72%) as well as the rule induction baseline system (F1-score of 7.47%) by a large margin. The bidirectional LSTM model with attention achieved the best performance among different RNN models. With the inclusion of additional features in the LSTM model, its performance can be boosted to an average F1-score of 77.35%.

CONCLUSIONS

It shows that classical learning models (SVM) remains advantageous over deep learning models (RNN variants) for clinical relation identification, especially for long-distance intersentential relations. However, RNNs demonstrate a great potential of significant improvement if more training data become available. Our work is an important step toward mining EHRs to improve the efficacy of drug safety surveillance. Most importantly, the annotated data used in this study will be made publicly available, which will further promote drug safety research in the community.

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.

Clinical Informatics Researcher's Desiderata for the Data Content of the Next Generation Electronic Health Record

OBJECTIVE

Clinical informatics researchers depend on the availability of high-quality data from the electronic health record (EHR) to design and implement new methods and systems for clinical practice and research. However, these data are frequently unavailable or present in a format that requires substantial revision. This article reports the results of a review of informatics literature published from 2010 to 2016 that addresses these issues by identifying categories of data content that might be included or revised in the EHR.

MATERIALS AND METHODS

We used an iterative review process on 1,215 biomedical informatics research articles. We placed them into generic categories, reviewed and refined the categories, and then assigned additional articles, for a total of three iterations.

RESULTS

Our process identified eight categories of data content issues: Adverse Events, Clinician Cognitive Processes, Data Standards Creation and Data Communication, Genomics, Medication List Data Capture, Patient Preferences, Patient-reported Data, and Phenotyping.

DISCUSSION

These categories summarize discussions in biomedical informatics literature that concern data content issues restricting clinical informatics research. These barriers to research result from data that are either absent from the EHR or are inadequate (e.g., in narrative text form) for the downstream applications of the data. In light of these categories, we discuss changes to EHR data storage that should be considered in the redesign of EHRs, to promote continued innovation in clinical informatics.

CONCLUSION

Based on published literature of clinical informaticians' reuse of EHR data, we characterize eight types of data content that, if included in the next generation of EHRs, would find immediate application in advanced informatics tools and techniques.

Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records

Unknown adverse reactions to drugs available on the market present a significant health risk and limit accurate judgement of the cost/benefit trade-off for medications. Machine learning has the potential to predict unknown adverse reactions from current knowledge. We constructed a knowledge graph containing four types of node: drugs, protein targets, indications and adverse reactions. Using this graph, we developed a machine learning algorithm based on a simple enrichment test and first demonstrated this method performs extremely well at classifying known causes of adverse reactions (AUC 0.92). A cross validation scheme in which 10% of drug-adverse reaction edges were systematically deleted per fold showed that the method correctly predicts 68% of the deleted edges on average. Next, a subset of adverse reactions that could be reliably detected in anonymised electronic health records from South London and Maudsley NHS Foundation Trust were used to validate predictions from the model that are not currently known in public databases. High-confidence predictions were validated in electronic records significantly more frequently than random models, and outperformed standard methods (logistic regression, decision trees and support vector machines). This approach has the potential to improve patient safety by predicting adverse reactions that were not observed during randomised trials.

Application and optimisation of the Comparison on Extreme Laboratory Tests (CERT) algorithm for detection of adverse drug reactions: Transferability across national boundaries

PURPOSE

The Singapore regulatory agency for health products (Health Sciences Authority), in performing active surveillance of medicines and their potential harms, is open to new methods to achieve this goal. Laboratory tests are a potential source of data for this purpose. We have examined the performance of the Comparison on Extreme Laboratory Tests (CERT) algorithm, developed by Ajou University, Korea, as a potential tool for adverse drug reaction detection based on the electronic medical records of the Singapore health care system.

METHODS

We implemented the original CERT algorithm, comparing extreme laboratory results pre- and post-drug exposure, and 5 variations thereof using 4.5 years of National University Hospital (NUH) electronic medical record data (31 869 588 laboratory tests, 6 699 591 drug dispensings from 272 328 hospitalizations). We investigated 6 drugs from the original CERT paper and an additional 47 drugs. We benchmarked results against a reference standard that we created from UpToDate 2015.

RESULTS

The original CERT algorithm applied to all 53 drugs and 44 laboratory abnormalities yielded a positive predictive value (PPV) and sensitivity of 50.3% and 54.1%, respectively. By raising the minimum number of cases for each drug-laboratory abnormality pair from 2 to 400, the PPV and sensitivity increased to 53.9% and 67.2%, respectively. This post hoc variation, named CERT400, performed particularly well for drug-induced hepatic and renal toxicities.

DISCUSSION

We have demonstrated that the CERT algorithm can be applied across national boundaries. One modification (CERT400) was able to identify adverse drug reaction signals from laboratory data with reasonable PPV and sensitivity, which indicates potential utility as a supplementary pharmacovigilance tool.

Data Mining Approach to Estimate the Duration of Drug Therapy from Longitudinal Electronic Medical Records

Background:

Electronic Medical Records (EMRs) from primary/ ambulatory care systems present a new and promising source of information for conducting clinical and translational research.

Objectives:

To address the methodological and computational challenges in order to extract reliable medication information from raw data which is often complex, incomplete and erroneous. To assess whether the use of specific chaining fields of medication information may additionally improve the data quality.

Methods:

Guided by a range of challenges associated with missing and internally inconsistent data, we introduce two methods for the robust extraction of patient-level medication data. First method relies on chaining fields to estimate duration of treatment (“chaining”), while second disregards chaining fields and relies on the chronology of records (“continuous”). Centricity EMR database was used to estimate treatment duration with both methods for two widely prescribed drugs among type 2 diabetes patients: insulin and glucagon-like peptide-1 receptor agonists.

Results:

At individual patient level the “chaining” approach could identify the treatment alterations longitudinally and produced more robust estimates of treatment duration for individual drugs, while the “continuous” method was unable to capture that dynamics. At population level, both methods produced similar estimates of average treatment duration, however, notable differences were observed at individual-patient level.

Conclusion:

The proposed algorithms explicitly identify and handle longitudinal erroneous or missing entries and estimate treatment duration with specific drug(s) of interest, which makes them a valuable tool for future EMR based clinical and pharmaco-epidemiological studies. To improve accuracy of real-world based studies, implementing chaining fields of medication information is recommended.

Leveraging Food and Drug Administration Adverse Event Reports for the Automated Monitoring of Electronic Health Records in a Pediatric Hospital

The objective of this study was to determine whether the Food and Drug Administration’s Adverse Event Reporting System (FAERS) data set could serve as the basis of automated electronic health record (EHR) monitoring for the adverse drug reaction (ADR) subset of adverse drug events. We retrospectively collected EHR entries for 71 909 pediatric inpatient visits at Cincinnati Children’s Hospital Medical Center. Natural language processing (NLP) techniques were used to identify positive diseases/disorders and signs/symptoms (DDSSs) from the patients’ clinical narratives. We downloaded all FAERS reports submitted by medical providers and extracted the reported drug-DDSS pairs. For each patient, we aligned the drug-DDSS pairs extracted from their clinical notes with the corresponding drug-DDSS pairs from the FAERS data set to identify Drug-Reaction Pair Sentences (DRPSs). The DRPSs were processed by NLP techniques to identify ADR-related DRPSs. We used clinician annotated, real-world EHR data as reference standard to evaluate the proposed algorithm. During evaluation, the algorithm achieved promising performance and showed great potential in identifying ADRs accurately for pediatric patients.

Development of a novel algorithm for detecting glucocorticoid-induced diabetes mellitus using a medical information database

WHAT IS KNOWN AND OBJECTIVE

Glucocorticoid-induced diabetes mellitus (GIDM) increases the risk of diabetes mellitus (DM)-related complications but is generally difficult to detect in clinical settings. The criteria for diagnosing GIDM have not been established. Recently, medical information databases (MIDs) have been used in post-marketing surveillance (PMS) studies. We conducted a pharmacoepidemiological study to develop an algorithm for detecting GIDM using MID.

METHODS

We selected 1214 inpatients who were newly prescribed with a typical glucocorticoid, prednisolone, during hospitalization from 2008 to 2014 from an MID of Hamamatsu University Hospital in Japan. GIDM was screened based on fasting blood glucose (FBG) and haemoglobin A1c (HbA1c) levels according to the current Japan Diabetes Society (JDS) DM criteria, and its predictability was evaluated by an expert's review of medical records. We investigated further candidate screening factors using receiver operating characteristics analysis.

RESULTS

Sixty-three inpatients were identified by the JDS DM criteria. Of these, 33 patients were definitely diagnosed as having GIDM by expert's review (positive predictive value = 52·4%). To develop a highly predictive algorithm, we compared the characteristics of inpatients diagnosed with definite GIDM and those diagnosed as non-GIDM. The maximum levels of HbA1c in patients with GIDM were significantly higher than those of patients with non-GIDM (66·9 mmol/mol vs. 58·7 mmol/mol, P < 0·001). The patients with GIDM had significantly higher relative increase in maximum level of HbA1c (RIM-HbA1c) than those with non-GIDM (0·3 vs. 0·03, P < 0·001). However, we did not observe a significant difference in those of fasting blood glucose (FBG) levels. We applied the RIM-HbA1c as a second screening factor to improve the detection of GIDM. It showed that a 13% increase in RIM-HbA1c separated patients with from patients without GIDM.

WHAT IS NEW AND CONCLUSIONS

Patients with GIDM had significantly higher RIM-HbA1c than patients with non-GIDM. There was a 13% increase in RIM-HbA1c in patients with GIDM compared to the others. Our detection algorithm for GIDM using an MID achieved high sensitivity and specificity, and was superior to one based only on the current JDS DM criteria. Our results suggest that monitoring changes in HbA1c levels is important for detecting GIDM and adds to current diagnostic criteria for type 2 DM.

Feasibility of Prioritizing Drug-Drug-Event Associations Found in Electronic Health Records

Background and Objective

Several studies have demonstrated the ability to detect adverse events potentially related to multiple drug exposure via data mining. However, the number of putative associations produced by such computational approaches is typically large, making experimental validation difficult. We theorized that those potential associations for which there is evidence from multiple complementary sources are more likely to be true, and explored this idea using a published database of drug–drug-adverse event associations derived from electronic health records (EHRs).

Methods

We prioritized drug–drug-event associations derived from EHRs using four sources of information: (1) public databases, (2) sources of spontaneous reports, (3) literature, and (4) non-EHR drug–drug interaction (DDI) prediction methods. After pre-filtering the associations by removing those found in public databases, we devised a ranking for associations based on the support from the remaining sources, and evaluated the results of this rank-based prioritization.

Results

We collected information for 5983 putative EHR-derived drug–drug-event associations involving 345 drugs and ten adverse events from four data sources and four prediction methods. Only seven drug–drug-event associations (<0.5 %) had support from the majority of evidence sources, and about one third (1777) had support from at least one of the evidence sources.

Conclusions

Our proof-of-concept method for scoring putative drug–drug-event associations from EHRs offers a systematic and reproducible way of prioritizing associations for further study. Our findings also quantify the agreement (or lack thereof) among complementary sources of evidence for drug–drug-event associations and highlight the challenges of developing a robust approach for prioritizing signals of these associations.

Electronic supplementary material

The online version of this article (doi:10.1007/s40264-015-0352-2) contains supplementary material, which is available to authorized users.

Complex temporal topic evolution modelling using the Kullback-Leibler divergence and the Bhattacharyya distance

The rapidly expanding corpus of medical research literature presents major challenges in the understanding of previous work, the extraction of maximum information from collected data, and the identification of promising research directions. We present a case for the use of advanced machine learning techniques as an aide in this task and introduce a novel methodology that is shown to be capable of extracting meaningful information from large longitudinal corpora and of tracking complex temporal changes within it. Our framework is based on (i) the discretization of time into epochs, (ii) epoch-wise topic discovery using a hierarchical Dirichlet process-based model, and (iii) a temporal similarity graph which allows for the modelling of complex topic changes. More specifically, this is the first work that discusses and distinguishes between two groups of particularly challenging topic evolution phenomena: topic splitting and speciation and topic convergence and merging, in addition to the more widely recognized emergence and disappearance and gradual evolution. The proposed framework is evaluated on a public medical literature corpus.

Leveraging graph topology and semantic context for pharmacovigilance through twitter-streams

Background

Adverse drug events (ADEs) constitute one of the leading causes of post-therapeutic death and their identification constitutes an important challenge of modern precision medicine. Unfortunately, the onset and effects of ADEs are often underreported complicating timely intervention. At over 500 million posts per day, Twitter is a commonly used social media platform. The ubiquity of day-to-day personal information exchange on Twitter makes it a promising target for data mining for ADE identification and intervention. Three technical challenges are central to this problem: (1) identification of salient medical keywords in (noisy) tweets, (2) mapping drug-effect relationships, and (3) classification of such relationships as adverse or non-adverse.

Methods

We use a bipartite graph-theoretic representation called a drug-effect graph (DEG) for modeling drug and side effect relationships by representing the drugs and side effects as vertices. We construct individual DEGs on two data sources. The first DEG is constructed from the drug-effect relationships found in FDA package inserts as recorded in the SIDER database. The second DEG is constructed by mining the history of Twitter users. We use dictionary-based information extraction to identify medically-relevant concepts in tweets. Drugs, along with co-occurring symptoms are connected with edges weighted by temporal distance and frequency. Finally, information from the SIDER DEG is integrate with the Twitter DEG and edges are classified as either adverse or non-adverse using supervised machine learning.

Results

We examine both graph-theoretic and semantic features for the classification task. The proposed approach can identify adverse drug effects with high accuracy with precision exceeding 85 % and F1 exceeding 81 %. When compared with leading methods at the state-of-the-art, which employ un-enriched graph-theoretic analysis alone, our method leads to improvements ranging between 5 and 8 % in terms of the aforementioned measures. Additionally, we employ our method to discover several ADEs which, though present in medical literature and Twitter-streams, are not represented in the SIDER databases.

Conclusions

We present a DEG integration model as a powerful formalism for the analysis of drug-effect relationships that is general enough to accommodate diverse data sources, yet rigorous enough to provide a strong mechanism for ADE identification.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1220-5) contains supplementary material, which is available to authorized users.

Incidence of adverse drug events in public and private hospitals in Riyadh, Saudi Arabia: the (ADESA) prospective cohort study

OBJECTIVES

To determine the incidence of adverse drug events (ADEs) and assess their severity and preventability in four Saudi hospitals.

DESIGN

Prospective cohort study.

SETTING

The study included patients admitted to medical, surgical and intensive care units (ICUs) of four hospitals in Saudi Arabia. These hospitals include a 900-bed tertiary teaching hospital, a 400-bed private hospital, a 1400-bed large government hospital and a 350-bed small government hospital.

PARTICIPANTS

All patients (≥12 years) admitted to the study units over 4 months.

PRIMARY AND SECONDARY OUTCOME MEASURES

Incidents were collected by pharmacists and reviewed by independent clinicians. Reviewers classified the identified incidents as ADEs, potential ADEs (PADEs) or medication errors and then determined their severity and preventability.

RESULTS

We followed 4041 patients from admission to discharge. Of these, 3985 patients had complete data for analysis. The mean±SD age of patients in the analysed cohort was 43.4±19.0 years. A total of 1676 ADEs were identified by pharmacists during the medical chart review. Clinician reviewers accepted 1531 (91.4%) of the incidents identified by the pharmacists (245 ADEs, 677 PADEs and 609 medication errors with low risk of causing harm). The incidence of ADEs was 6.1 (95% CI 5.4 to 6.9) per 100 admissions and 7.9 (95% CI 6.9 to 8.9) per 1000 patient-days. The occurrence of ADEs was most common in ICUs (149 (60.8%)) followed by medical (67 (27.3%)) and surgical (29 (11.8%)) units. In terms of severity, 129 (52.7%) of the ADEs were significant, 91 (37.1%) were serious, 22 (9%) were life-threatening and three (1.2%) were fatal.

CONCLUSIONS

We found that ADEs were common in Saudi hospitals, especially in ICUs, causing significant morbidity and mortality. Future studies should focus on investigating the root causes of ADEs at the prescribing stage, and development and testing of interventions to minimise harm from medications.

Inference for correlated effect sizes using multiple univariate meta-analyses

Multivariate meta-analysis, which involves jointly analyzing multiple and correlated outcomes from separate studies, has received a great deal of attention. One reason to prefer the multivariate approach is its ability to account for the dependence between multiple estimates from the same study. However, nearly all the existing methods for analyzing multivariate meta-analytic data require the knowledge of the within-study correlations, which are usually unavailable in practice. We propose a simple non-iterative method that can be used for the analysis of multivariate meta-analysis datasets, that has no convergence problems, and does not require the use of within-study correlations. Our approach uses standard univariate methods for the marginal effects but also provides valid joint inference for multiple parameters. The proposed method can directly handle missing outcomes under missing completely at random assumption. Simulation studies show that the proposed method provides unbiased estimates, well-estimated standard errors, and confidence intervals with good coverage probability. Furthermore, the proposed method is found to maintain high relative efficiency compared with conventional multivariate meta-analyses where the within-study correlations are known. We illustrate the proposed method through two real meta-analyses where functions of the estimated effects are of interest.

Electronic medical record phenotyping using the anchor and learn framework

Background Electronic medical records (EMRs) hold a tremendous amount of information about patients that is relevant to determining the optimal approach to patient care. As medicine becomes increasingly precise, a patient’s electronic medical record phenotype will play an important role in triggering clinical decision support systems that can deliver personalized recommendations in real time. Learning with anchors presents a method of efficiently learning statistically driven phenotypes with minimal manual intervention.

Materials and Methods We developed a phenotype library that uses both structured and unstructured data from the EMR to represent patients for real-time clinical decision support. Eight of the phenotypes were evaluated using retrospective EMR data on emergency department patients using a set of prospectively gathered gold standard labels.

Results We built a phenotype library with 42 publicly available phenotype definitions. Using information from triage time, the phenotype classifiers have an area under the ROC curve (AUC) of infection 0.89, cancer 0.88, immunosuppressed 0.85, septic shock 0.93, nursing home 0.87, anticoagulated 0.83, cardiac etiology 0.89, and pneumonia 0.90. Using information available at the time of disposition from the emergency department, the AUC values are infection 0.91, cancer 0.95, immunosuppressed 0.90, septic shock 0.97, nursing home 0.91, anticoagulated 0.94, cardiac etiology 0.92, and pneumonia 0.97.

Discussion The resulting phenotypes are interpretable and fast to build, and perform comparably to statistically learned phenotypes developed with 5000 manually labeled patients.

Conclusion Learning with anchors is an attractive option for building a large public repository of phenotype definitions that can be used for a range of health IT applications, including real-time decision support.

Statin Use and the Risk of Kidney Disease With Long-Term Follow-Up (8.4-Year Study)

Few studies have examined long-term effects of statin therapy on kidney diseases. The objective of this study was to determine the association of statin use with incidence of acute and chronic kidney diseases after prolonged follow-up. In this retrospective cohort study, we analyzed data from the San Antonio area military health care system from October 2003 through March 2012. Statin users were propensity score matched to nonusers using 82 baseline characteristics including demographics, co-morbidities, medications, and health care utilization. Study outcomes were acute kidney injury, chronic kidney disease (CKD), and nephritis/nephrosis/renal sclerosis. Of the 43,438 subjects included, we propensity score matched 6,342 statin users with 6,342 nonusers. Statin users had greater odds of acute kidney injury (odds ratio [OR] 1.30, 95% confidence interval [CI] 1.14 to 1.48), CKD (OR 1.36, 95% CI 1.22 to 1.52), and nephritis/nephrosis/renal sclerosis (OR 1.35, 95% CI 1.05 to 1.73). In a subset of patients without co-morbidities, the association of statin use with CKD remained significant (OR 1.53, 95% CI 1.27 to 1.85). In a secondary analysis, adjusting for diseases/conditions that developed during follow-up weakened this association. In conclusion, statin use is associated with increased incidence of acute and chronic kidney disease. These findings are cautionary and suggest that long-term effects of statins in real-life patients may differ from shorter term effects in selected clinical trial populations.

Statins and New-Onset Diabetes Mellitus and Diabetic Complications: A Retrospective Cohort Study of US Healthy Adults

BACKGROUND

Statin use is associated with increased incidence of diabetes and possibly with increased body weight and reduced exercise capacity. Data on the long-term effects of these associations in healthy adults, however, are very limited. In addition, the relationship between these effects and diabetic complications has not been adequately studied.

OBJECTIVE

To examine the association between statin use and new-onset diabetes, diabetic complications, and overweight/obesity in a cohort of healthy adults.

RESEARCH DESIGN

This was a retrospective cohort study.

PARTICIPANTS

Subjects were Tricare beneficiaries who were evaluated between October 1, 2003 and March 1, 2012. Patients were divided into statin users and nonusers.

INTERVENTION

We excluded patients who, at baseline, had a preexisting disease indicative of cardiovascular diseases, any positive element of the Charlson comorbidity index (including diabetes mellitus), or life-limiting chronic diseases. Using 42 baseline characteristics, we generated a propensity score to match statin users and nonusers.

MAIN MEASURES

Outcomes assessed included new-onset diabetes, diabetic complications, and overweight/obesity.

KEY RESULTS

A total of 25,970 patients (3982 statin users and 21,988 nonusers) were identified as healthy adults at baseline. Of these, 3351 statins users and 3351 nonusers were propensity score-matched. Statin users had higher odds of new-onset diabetes (odds ratio [OR] 1.87; 95 % confidence interval [95 % CI] 1.67-2.01), diabetes with complications (OR 2.50; 95 % CI 1.88-3.32), and overweight/obesity (OR 1.14; 95 % CI 1.04-1.25). Secondary and sensitivity analyses demonstrated similar findings.

CONCLUSIONS

Diabetes, diabetic complications, and overweight/obesity were more commonly diagnosed among statin-users than similar nonusers in a healthy cohort of adults. This study demonstrates that short-term clinical trials might not fully describe the risk/benefit of long-term statin use for primary prevention.

Detecting drug-herbal interaction using a spontaneous reporting system database: an example with benzylpenicillin and qingkailing injection

PURPOSE

The study aims to quantify anaphylaxis signal for combined exposure of benzylpenicilin and qingkailing injection (QI) compared with individual exposure of the two drugs and the background risk based on all other exposures in SRS database.

METHODS

Data used in this study were collected during 2003-2014 from China Guangdong Provincial Center of ADR Monitoring. We studied the suspected ADR reports using a case/non-case design. The cases were defined as the reactions coded by WHO-preferred terms of anaphylactic shock or anaphylactoid reaction. Reporting odds ratios (RORs) were used as a measure of disproportionality and were adjusted for age and gender to reduce confounding effects. An observed-to-expected ratio Ω was also used for interaction detection.

RESULTS

The crude RORs (95 % CIs) for anaphylaxis in patients who used only benzylpenicillin or QI and those who used the two drugs concomitantly compared with patients who used neither of the two drugs were 2.50 (2.34-2.68), 1.59 (1.46-1.73), and 6.22 (3.34-11.58), respectively. The adjusted RORs (95 % CIs) were 2.48 (2.31-2.65), 1.54 (1.41-1.67), and 6.01 (3.22-11.20), respectively, after being adjusted for age and gender. The measured Ω, Ω0, Ω025, and Ω975 was 1.03, 1.09, 0.14, and 1.71, respectively.

CONCLUSIONS

Case reports in the database are suggestive of a safety signal which indicates that an interaction between benzylpenicillin and QI resulting in excess risk of anaphylaxis may occur. SRS databases have a potential for signaling unknown drug-herbal interactions. More effort is needed to expand this potential.

Role of text mining in early identification of potential drug safety issues

Drugs are an important part of today's medicine, designed to treat, control, and prevent diseases; however, besides their therapeutic effects, drugs may also cause adverse effects that range from cosmetic to severe morbidity and mortality. To identify these potential drug safety issues early, surveillance must be conducted for each drug throughout its life cycle, from drug development to different phases of clinical trials, and continued after market approval. A major aim of pharmacovigilance is to identify the potential drug-event associations that may be novel in nature, severity, and/or frequency. Currently, the state-of-the-art approach for signal detection is through automated procedures by analyzing vast quantities of data for clinical knowledge. There exists a variety of resources for the task, and many of them are textual data that require text analytics and natural language processing to derive high-quality information. This chapter focuses on the utilization of text mining techniques in identifying potential safety issues of drugs from textual sources such as biomedical literature, consumer posts in social media, and narrative electronic medical records.

Computational approaches for pharmacovigilance signal detection: toward integrated and semantically-enriched frameworks

Computational signal detection constitutes a key element of postmarketing drug monitoring and surveillance. Diverse data sources are considered within the 'search space' of pharmacovigilance scientists, and respective data analysis methods are employed, all with their qualities and shortcomings, towards more timely and accurate signal detection. Recent systematic comparative studies highlighted not only event-based and data-source-based differential performance across methods but also their complementarity. These findings reinforce the arguments for exploiting all possible information sources for drug safety and the parallel use of multiple signal detection methods. Combinatorial signal detection has been pursued in few studies up to now, employing a rather limited number of methods and data sources but illustrating well-promising outcomes. However, the large-scale realization of this approach requires systematic frameworks to address the challenges of the concurrent analysis setting. In this paper, we argue that semantic technologies provide the means to address some of these challenges, and we particularly highlight their contribution in (a) annotating data sources and analysis methods with quality attributes to facilitate their selection given the analysis scope; (b) consistently defining study parameters such as health outcomes and drugs of interest, and providing guidance for study setup; (c) expressing analysis outcomes in a common format enabling data sharing and systematic comparisons; and (d) assessing/supporting the novelty of the aggregated outcomes through access to reference knowledge sources related to drug safety. A semantically-enriched framework can facilitate seamless access and use of different data sources and computational methods in an integrated fashion, bringing a new perspective for large-scale, knowledge-intensive signal detection.

Mining adverse drug reactions from online healthcare forums using hidden Markov model

BACKGROUND

Adverse Drug Reactions are one of the leading causes of injury or death among patients undergoing medical treatments. Not all Adverse Drug Reactions are identified before a drug is made available in the market. Current post-marketing drug surveillance methods, which are based purely on voluntary spontaneous reports, are unable to provide the early indications necessary to prevent the occurrence of such injuries or fatalities. The objective of this research is to extract reports of adverse drug side-effects from messages in online healthcare forums and use them as early indicators to assist in post-marketing drug surveillance.

METHODS

We treat the task of extracting adverse side-effects of drugs from healthcare forum messages as a sequence labeling problem and present a Hidden Markov Model(HMM) based Text Mining system that can be used to classify a message as containing drug side-effect information and then extract the adverse side-effect mentions from it. A manually annotated dataset from http://www.medications.com is used in the training and validation of the HMM based Text Mining system.

RESULTS

A 10-fold cross-validation on the manually annotated dataset yielded on average an F-Score of 0.76 from the HMM Classifier, in comparison to 0.575 from the Baseline classifier. Without the Plain Text Filter component as a part of the Text Processing module, the F-Score of the HMM Classifier was reduced to 0.378 on average, while absence of the HTML Filter component was found to have no impact. Reducing the Drug names dictionary size by half, on average reduced the F-Score of the HMM Classifier to 0.359, while a similar reduction to the side-effects dictionary yielded an F-Score of 0.651 on average. Adverse side-effects mined from http://www.medications.com and http://www.steadyhealth.com were found to match the Adverse Drug Reactions on the Drug Package Labels of several drugs. In addition, some novel adverse side-effects, which can be potential Adverse Drug Reactions, were also identified.

CONCLUSIONS

The results from the HMM based Text Miner are encouraging to pursue further enhancements to this approach. The mined novel side-effects can act as early indicators for health authorities to help focus their efforts in post-marketing drug surveillance.

Functional evaluation of out-of-the-box text-mining tools for data-mining tasks

Objective The trade-off between the speed and simplicity of dictionary-based term recognition and the richer linguistic information provided by more advanced natural language processing (NLP) is an area of active discussion in clinical informatics. In this paper, we quantify this trade-off among text processing systems that make different trade-offs between speed and linguistic understanding. We tested both types of systems in three clinical research tasks: phase IV safety profiling of a drug, learning adverse drug–drug interactions, and learning used-to-treat relationships between drugs and indications.

Materials We first benchmarked the accuracy of the NCBO Annotator and REVEAL in a manually annotated, publically available dataset from the 2008 i2b2 Obesity Challenge. We then applied the NCBO Annotator and REVEAL to 9 million clinical notes from the Stanford Translational Research Integrated Database Environment (STRIDE) and used the resulting data for three research tasks.

Results There is no significant difference between using the NCBO Annotator and REVEAL in the results of the three research tasks when using large datasets. In one subtask, REVEAL achieved higher sensitivity with smaller datasets.

Conclusions For a variety of tasks, employing simple term recognition methods instead of advanced NLP methods results in little or no impact on accuracy when using large datasets. Simpler dictionary-based methods have the advantage of scaling well to very large datasets. Promoting the use of simple, dictionary-based methods for population level analyses can advance adoption of NLP in practice.

Large-scale combining signals from both biomedical literature and the FDA Adverse Event Reporting System (FAERS) to improve post-marketing drug safety signal detection

BACKGROUND

Independent data sources can be used to augment post-marketing drug safety signal detection. The vast amount of publicly available biomedical literature contains rich side effect information for drugs at all clinical stages. In this study, we present a large-scale signal boosting approach that combines over 4 million records in the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) and over 21 million biomedical articles.

RESULTS

The datasets are comprised of 4,285,097 records from FAERS and 21,354,075 MEDLINE articles. We first extracted all drug-side effect (SE) pairs from FAERS. Our study implemented a total of seven signal ranking algorithms. We then compared these different ranking algorithms before and after they were boosted with signals from MEDLINE sentences or abstracts. Finally, we manually curated all drug-cardiovascular (CV) pairs that appeared in both data sources and investigated whether our approach can detect many true signals that have not been included in FDA drug labels. We extracted a total of 2,787,797 drug-SE pairs from FAERS with a low initial precision of 0.025. The ranking algorithm combined signals from both FAERS and MEDLINE, significantly improving the precision from 0.025 to 0.371 for top-ranked pairs, representing a 13.8 fold elevation in precision. We showed by manual curation that drug-SE pairs that appeared in both data sources were highly enriched with true signals, many of which have not yet been included in FDA drug labels.

CONCLUSIONS

We have developed an efficient and effective drug safety signal ranking and strengthening approach We demonstrate that large-scale combining information from FAERS and biomedical literature can significantly contribute to drug safety surveillance.

Mining clinical text for signals of adverse drug-drug interactions

BACKGROUND AND OBJECTIVE

Electronic health records (EHRs) are increasingly being used to complement the FDA Adverse Event Reporting System (FAERS) and to enable active pharmacovigilance. Over 30% of all adverse drug reactions are caused by drug-drug interactions (DDIs) and result in significant morbidity every year, making their early identification vital. We present an approach for identifying DDI signals directly from the textual portion of EHRs.

METHODS

We recognize mentions of drug and event concepts from over 50 million clinical notes from two sites to create a timeline of concept mentions for each patient. We then use adjusted disproportionality ratios to identify significant drug-drug-event associations among 1165 drugs and 14 adverse events. To validate our results, we evaluate our performance on a gold standard of 1698 DDIs curated from existing knowledge bases, as well as with signaling DDI associations directly from FAERS using established methods.

RESULTS

Our method achieves good performance, as measured by our gold standard (area under the receiver operator characteristic (ROC) curve >80%), on two independent EHR datasets and the performance is comparable to that of signaling DDIs from FAERS. We demonstrate the utility of our method for early detection of DDIs and for identifying alternatives for risky drug combinations. Finally, we publish a first of its kind database of population event rates among patients on drug combinations based on an EHR corpus.

CONCLUSIONS

It is feasible to identify DDI signals and estimate the rate of adverse events among patients on drug combinations, directly from clinical text; this could have utility in prioritizing drug interaction surveillance as well as in clinical decision support.