Detection Of Adverse Drug Events Research Articles

Using Multiple Drug Similarity Networks to Promote Adverse Drug Event Detection

The occurrence of an adverse drug event (ADE) has become a serious social concern of public health. Early detection of ADEs can lower the risk of drug safety as well as the expense of the drug. While post-market spontaneous reports of ADEs remain a cornerstone of pharmacovigilance, most existing signal detection algorithms rely on substantial accumulated data, limiting their applicability to early ADE detection when reports are scarce. To address this issue, we propose a label propagation model for generating enhanced drug safety signals using multiple drug features. We first construct multiple drug similarity networks using a range of drug features. We then calculate initial drug safety signals using conventional signal detection algorithms. These original signals are subsequently propagated across each drug similarity network to obtain enhanced drug safety signals. We evaluate our proposed model using two common signal detection algorithms on data from the FDA Adverse Event Reporting System (FAERS). Results demonstrate that enhanced drug safety signals with pre-clinical information outperform the standard safety signal detection algorithms on early ADE detection. In addition, we systematically evaluate the performance of different drug similarities against different types of ADEs. Furthermore, we have developed a web interface (http://drug-drug-sim.aimedlab.net/) to display our multiple drug similarity scores, facilitating access to this valuable resource for drug safety monitoring.

Developing large language models to detect adverse drug events in posts on X

ABSTRACT Adverse drug events (ADEs) are one of the major causes of hospital admissions and are associated with increased morbidity and mortality. Post-marketing ADE identification is one of the most important phases of drug safety surveillance. Traditionally, data sources for post-marketing surveillance mainly come from spontaneous reporting system such as the Food and Drug Administration Adverse Event Reporting System (FAERS). Social media data such as posts on X (formerly Twitter) contain rich patient and medication information and could potentially accelerate drug surveillance research. However, ADE information in social media data is usually locked in the text, making it difficult to be employed by traditional statistical approaches. In recent years, large language models (LLMs) have shown promise in many natural language processing tasks. In this study, we developed several LLMs to perform ADE classification on X data. We fine-tuned various LLMs including BERT-base, Bio_ClinicalBERT, RoBERTa, and RoBERTa-large. We also experimented ChatGPT few-shot prompting and ChatGPT fine-tuned on the whole training data. We then evaluated the model performance based on sensitivity, specificity, negative predictive value, positive predictive value, accuracy, F1-measure, and area under the ROC curve. Our results showed that RoBERTa-large achieved the best F1-measure (0.8) among all models followed by ChatGPT fine-tuned model with F1-measure of 0.75. Our feature importance analysis based on 1200 random samples and RoBERTa-Large showed the most important features are as follows: “withdrawals”/”withdrawal”, “dry”, “dealing”, “mouth”, and “paralysis”. The good model performance and clinically relevant features show the potential of LLMs in augmenting ADE detection for post-marketing drug safety surveillance.

A Precision Mixture Risk Model to Identify Adverse Drug Events in Subpopulations Using a Case‐Crossover Design

ABSTRACTDespite the success of pharmacovigilance studies in detecting signals of adverse drug events (ADEs) from real‐world data, the risks of ADEs in subpopulations warrant increased scrutiny to prevent them in vulnerable individuals. Recently, the case‐crossover design has been implemented to leverage large‐scale administrative claims data for ADE detection, while controlling both observed confounding effects and short‐term fixed unobserved confounding effects. Additionally, as the case‐crossover design only includes cases, subpopulations can be conveniently derived. In this manuscript, we propose a precision mixture risk model (PMRM) to identify ADE signals from subpopulations under the case‐crossover design. The proposed model is able to identify signals from all ADE‐subpopulation‐drug combinations, while controlling for false discovery rate (FDR) and confounding effects. We applied the PMRM to an administrative claims data. We identified ADE signals in subpopulations defined by demographic variables, comorbidities, and detailed diagnosis codes. Interestingly, certain drugs were associated with a higher risk of ADE only in subpopulations, while these drugs had a neutral association with ADE in the general population. Additionally, the PMRM could control FDR at a desired level and had a higher probability to detect true ADE signals than the widely used McNemar's test. In conclusion, the PMRM is able to identify subpopulation‐specific ADE signals from a tremendous number of ADE‐subpopulation‐drug combinations, while controlling for both FDR and confounding effects.

Protocol for the development and validation of a trigger tool for antiretroviral ADE detection among adult HIV/AIDS patients: A short communication

Antiretroviral therapy (ART) is a lifelong combination therapy which has been very promising in managing HIV/AIDs but reported to have several adverse events on the recipients, affecting the desired antiretroviral therapeutic goals. Adverse drug event detection and prevention therefore become very important safety culture maintenance tools among patients living with HIV/AIDS. The designed protocol provided step by step approaches to develop and validate a trigger tool for detection of adverse drug events (ADE) among adult HIV/AIDS patients. The approaches involved include a baseline (Pre-trigger tool development) retrospective clinical record review to establish a baseline ADE detection capacity of a conventional non-trigger tool method; the Delphi panel process to develop the trigger tool in question; Face and content validity approach for validation of the developed trigger tool; Pilot test of the trigger tool using small clinical record sample; determining the effectiveness of the developed trigger tool through the retrospective clinical record review of same samples reviewed at the baseline. Finally, the protocol described the process of determining the feasibility of the developed trigger tool through the survey of the clinical record review team members.

Natural language processing for detecting adverse drug events: A systematic review protocol

Background Detecting Adverse Drug Events (ADEs) is an emerging research area, attracting great interest in the research community. Better anticipatory management of predisposing factors has considerable potential to improve outcomes. Automatic extraction of ADEs using Natural Language Processing (NLP) has a great potential to significantly facilitate efficient and effective distillation of such knowledge, to better understand and predict risk of adverse events. Methods This systematic review follows the six-stage including the literature from 6 databases (Embase, Medline, Web Of Science Core Collection, ACM Guide to Computing Literature, IEEE Digital Library and Scopus). Following the title, abstract and full-text screenings, characteristics and main findings of the included studies and resources will be tabulated and summarized. The risk of bias and reporting quality was assessed using the PROBAST tool. Results We developed our search strategy and collected all relevant publications. As of July 2024, we have completed all the stages of the systematic review. We identified 178 studies for inclusion through the academic literature search (where data was extracted from all of the papers). Right now, we are writing up the systematic review paper where we are synthesising the different findings. Further refinement of the eligibility criteria and data extraction has been ongoing since August 2022. Conclusion In this systematic review, we will identify and consolidate information and evidence related to the use and effectiveness of existing NLP approaches and tools for automatically detecting ADEs from free text (discharge summaries, General Practitioner notes, social media, etc.). Our findings will improve the understanding of the current landscape of the use of NLP for extracting ADEs. It will lead to better anticipatory management of predisposing factors with the potential to improve outcomes considerably. Our results will also be valuable both to NLP researchers developing methods to extract ADEs and to translational/clinical researchers who use NLP for this purpose and in healthcare in general. For example, from our initial analysis of the studies, we can conclude that the majority of the proposed works are about the detection (extraction) of ADEs from text. An important portion of studies also focus on the binary classification of text (for highlighting if it includes or not ADEs). Different challenges related to the unbalanced dataset, abbreviations and acronyms but also to the lower results with rare ADEs were also mentioned by the studied papers.

Establishing a trigger tool based on global trigger tools to identify adverse drug events in obstetric inpatients in China

BackgroundPregnant women belong to the special population of drug therapy, and their physiological state, pharmacokinetics and pharmacodynamics are significantly different from the general population. Drug safety during pregnancy involves two generations, which is a hot issue widely concerned in the whole society. Global Trigger Tool (GTT) of the Institute for Healthcare Improvement (IHI) has been wildly used as a patient safety measurement strategy by several institutions and national programs, and the effectiveness had been demonstrated. But only one study reports the use of GTT in obstetric delivery until now. The aim of the study is to establish triggers detecting adverse drug events (ADEs) suitable for obstetric inpatients on the basis of the GTT, to examine the performance of the obstetric triggers in detecting ADEs experienced by obstetric units compared with the spontaneous reporting system and GTT, and to assess the utility and value of the obstetric trigger tool in identifying ADEs of obstetric inpatients.MethodsBased on a literature review searched in PubMed and CNKI from January of 1997 to October of 2023, retrospective local obstetric ADEs investigations, relevant obstetric guidelines and the common adverse reactions of obstetric therapeutic drugs were involved to establish the initial obstetric triggers. According to the Delphi method, two rounds of expert questionnaire survey were conducted among 16 obstetric and neonatological physicians and pharmacists until an agreement was reached. A retrospective study was conducted to identity ADEs in 300 obstetric inpatient records at the Sichuan Academy of Medical Sciences & Sichuan Provincial People’s Hospital from June 1 to September 30, 2018. Two trained junior pharmacists analyzed the first eligible records independently, and the included records reviewed by trained pharmacist and physician to identify ADEs. Sensitivity and specificity of the established obstetric triggers were assessed by the number of ADEs/100 patients and positive predictive value with the spontaneous reporting system (SRS) and GTT. Excel 2010 and SPSS22 were used for data analysis.ResultsThrough two rounds of expert investigation, 39 preliminary triggers were established that comprised four modules (12 laboratory tests, 9 medications, 14 symptoms, and 4 outcomes). A total of 300 medical records were reviewed through the obstetric triggers, of which 48 cases of ADEs were detected, with an incidence of ADEs of 16%. Among the 39 obstetric triggers, 22 (56.41%) were positive and 11 of them detected ADEs. The positive predictive value (PPV) was 36.36%, and the number of ADEs/100 patients was 16.33 (95% CI, 4.19–17.81). The ADE detection rate, positive trigger rate, and PPV for the obstetric triggers were significantly augmented, confirming that the obstetric triggers were more specific and sensitive than SRS and GTT.ConclusionThe obstetric triggers were proven to be sensitive and specific in the active monitoring of ADE for obstetric inpatients, which might serve as a reference for ADE detection of obstetric inpatients at medical institutions.

Active monitoring of antifungal adverse events in hospitalized patients based on Global Trigger Tool method.

The increasing prevalence of fungal infections necessitates broader use of antifungal medications. However, the prevalence of adverse drug events (ADEs) restricts their clinical application. This study aimed to develop a reliable ADEs trigger for antifungals to enable proactive ADEs monitoring, serving as a reference for ADEs prevention and control. This investigation comprises two phases. Initially, the trigger was established via a literature review, extraction of relevant items, and refinement through Delphi expert consultation. Subsequently, the validity of the trigger was assessed by analyzing hospital records of antifungal drug users from 1 January 2019 to 31 December 2020. The correlation between each trigger signal and ADEs occurrence was examined, and the sensitivity and specificity of the trigger were evaluated through the spontaneous reporting system (SRS) and Global Trigger Tool (GTT). Additionally, risk factors contributing to adverse drug events (ADEs) resulting from antifungal use were analyzed. Results: Twenty-one preliminary triggers were refined into 21 final triggers after one expert round. In the retrospective analysis, the positive trigger rate was 65.83%, with a positive predictive value (PPV) of 28.75%. The incidence of ADEs in inpatients was 28.75%, equating to 44.58 ADEs per 100 admissions and 33.04 ADEs per 1,000 patient days. Predominant ADEs categories included metabolic disturbances, gastrointestinal damage, and skin rashes. ADEs severity was classified into 36 cases at grade 1, 160 at grade 2, and 18 at grade 3. The likelihood of ADEs increased with longer stays, more positive triggers, and greater comorbidity counts. This study underscores the effectiveness of the GTT in enhancing ADEs detection during antifungal medication use, thereby confirming its value as a monitoring tool.

Impact of the COVID-19 pandemic on the spontaneous reporting and signal detection of adverse drug events

AbstractExternal factors severely affecting in a short period of time the spontaneous reporting of adverse events (AEs) can significantly impact drug safety signal detection. Coronavirus disease 2019 (COVID-19) represented an enormous challenge for health systems, with over 767 million cases and massive vaccination campaigns involving over 70% of the worldwide population. This study investigates the potential masking effect on certain AEs caused by the substantial increase in reports solely related to COVID-19 vaccines within various spontaneous reporting systems (SRSs). Three SRSs were used to monitor AEs reporting before and during the pandemic, namely, the World Health Organisation (WHO) global individual case safety reports database (VigiBase®), the United States Food and Drug Administration Adverse Event Reporting System (FAERS) and the Japanese Adverse Drug Event Report database (JADER). Findings revealed a sudden over-reporting of 35 AEs (≥ 200%) during the pandemic, with an increment of the RRF value in 2021 of at least double the RRF reported in 2020. This translates into a substantial reduction in signals of disproportionate reporting (SDR) due to the massive inclusion of COVID-19 vaccine reports. To mitigate the masking effect of COVID-19 vaccines in post-marketing SRS analyses, we recommend utilizing COVID-19-corrected versions for a more accurate assessment.

Adverse drug events in Chinese elder inpatients: a retrospective review for evaluating the efficiency of the Global Trigger Tool.

Elderly patients frequently experience a high incidence of adverse drug events (ADEs) due to the coexistence of multiple diseases, the combination of various medications, poor medication compliance, and other factors. Global Trigger Tool (GTT) is a new method for identifying ADEs, introducing the concept of a trigger, that is, clues including abnormal laboratory values, reversal drugs, and clinical symptoms that may suggest ADEs, and specifically locating information related to ADEs in the medical record to identify ADEs. The aim of this study was to establish a GTT-based trigger tool for adverse medication events in elderly patients and to investigate the risk variables associated with such events. The triggers were identified by reviewing the frequency of ADEs in elderly patients in Sichuan, China, retrieving relevant literature, and consulting experts. A retrospective analysis was carried out to identify adverse medication occurrences among 480 elderly inpatients in Sichuan People's Hospital. A total of 56 ADEs were detected in 51 patients (10.62%), 13.04 per 1,000 patient days, and 11.67 per 100 admissions. The overall positive predictive value (PPV) of the triggers was 23.84, and 94.64% of ADEs caused temporary injury. Gastrointestinal system injury (27.87%) and metabolic and nutritional disorders (24.53%) were the primary organ-systems affected by ADEs. The majority of ADEs were caused by drugs used to treat cardiovascular diseases. 71.43% of ADE occurred within 2 days of administration and the risk factor analysis of ADE revealed that the number of medicines had a significant correlation. This study demonstrated GTT's value as a tool for ADEs detection in elderly inpatients in China. It enhances the level of medication management and comprehensively reflects the situation of ADE of the elderly.

A holistic AI-based approach for pharmacovigilance optimization from patients behavior on social media

In this paper, we propose a holistic AI-based pharmacovigilance optimization approach using patient’s social media data. Instead of focusing on the detection and identification of Adverse Drug Events (ADE) in social media posts in single time points, we propose a holistic approach that looks at the evolution of different user behavior indicators in time. We examine various NLP-based indicators such as word frequency, semantic similarity, Adverse Drug Reactions mentions, and sentiment analysis. We introduce a classification approach to identify normal vs. abnormal time periods based on patient comments. This approach, along with user behavior indicators, can optimize the pharmacovigilance process by flagging the need for immediate attention and further investigation. We specifically focus on the Levothyrox® case in France, which sparked media attention due to changes in the medication formula and affected patient behavior on medical forums. For classification, we propose a deep learning architecture called Word Cloud Convolutional Neural Network (WC-CNN), trained on word clouds from patient comments. We evaluate different temporal resolutions and NLP pre-processing techniques, finding that monthly resolution and the proposed indicators can effectively detect new safety signals, with an accuracy of 75%. We have made the code open source, available via github.

The Role of Social Media for Identifying Adverse Drug Events Data in Pharmacovigilance: Protocol for a Scoping Review.

Adverse drug events (ADEs) are a considerable public health burden resulting in disability, hospitalization, and death. Even those ADEs deemed nonserious can severely impact a patient's quality of life and adherence to intervention. Monitoring medication safety, however, is challenging. Social media may be a useful adjunct for obtaining real-world data on ADEs. While many studies have been undertaken to detect adverse events on social media, a consensus has not yet been reached as to the value of social media in pharmacovigilance or its role in pharmacovigilance in relation to more traditional data sources. The aim of the study is to evaluate and characterize the use of social media in ADE detection and pharmacovigilance as compared to other data sources. A scoping review will be undertaken. We will search 11 bibliographical databases as well as Google Scholar, hand-searching, and forward and backward citation searching. Records will be screened in Covidence by 2 independent reviewers at both title and abstract stage as well as full text. Studies will be included if they used any type of social media (such as Twitter or patient forums) to detect any type of adverse event associated with any type of medication and then compared the results from social media to any other data source (such as spontaneous reporting systems or clinical literature). Data will be extracted using a data extraction sheet piloted by the authors. Important data on the types of methods used (such as machine learning), any limitations of the methods used, types of adverse events and drugs searched for and included, availability of data and code, details of the comparison data source, and the results and conclusions will be extracted. We will present descriptive summary statistics as well as identify any patterns in the types and timing of ADEs detected, including but not limited to the similarities and differences in what is reported, gaps in the evidence, and the methods used to extract ADEs from social media data. We will also summarize how the data from social media compares to conventional data sources. The literature will be organized by the data source for comparison. Where possible, we will analyze the impact of the types of adverse events, the social media platform used, and the methods used. This scoping review will provide a valuable summary of a large body of research and important information for pharmacovigilance as well as suggest future directions of further research in this area. Through the comparisons with other data sources, we will be able to conclude the added value of social media in monitoring adverse events of medications, in terms of type of adverse events and timing. PRR1-10.2196/47068.

DKADE: a novel framework based on deep learning and knowledge graph for identifying adverse drug events and related medications.

Adverse drug events (ADEs) are common in clinical practice and can cause significant harm to patients and increase resource use. Natural language processing (NLP) has been applied to automate ADE detection, but NLP systems become less adaptable when drug entities are missing or multiple medications are specified in clinical narratives. Additionally, no Chinese-language NLP system has been developed for ADE detection due to the complexity of Chinese semantics, despite ˃10 million cases of drug-related adverse events occurring annually in China. To address these challenges, we propose DKADE, a deep learning and knowledge graph-based framework for identifying ADEs. DKADE infers missing drug entities and evaluates their correlations with ADEs by combining medication orders and existing drug knowledge. Moreover, DKADE can automatically screen for new adverse drug reactions. Experimental results show that DKADE achieves an overall F1-score value of 91.13%. Furthermore, the adaptability of DKADE is validated using real-world external clinical data. In summary, DKADE is a powerful tool for studying drug safety and automating adverse event monitoring.

Application of an Integrative Drug Safety Model for Detection of Adverse Drug Events Associated With Inhibition of Glutathione Peroxidase 1 in Chronic Obstructive Pulmonary Disease

BackgroundChronic Obstructive Pulmonary Disease is characterised by declining lung function and a greater oxidative stress burden due to reduced activity of antioxidant enzymes such as Glutathione Peroxidase 1.ObjectivesThe extent to which drugs may contribute to this compromised activity is largely unknown. An integrative drug safety model explores inhibition of Glutathione Peroxidase 1 by drugs and their association with chronic obstructive pulmonary disease adverse drug events.MethodsIn silico molecular modelling approaches were utilised to predict the interactions that drugs have within the active site of Glutathione Peroxidase 1 in both human and bovine models. Similarities of chemical features between approved drugs and the known inhibitor tiopronin were also investigated. Subsequently the Food and Drug Administration Adverse Event System was searched to uncover adverse drug event signals associated with chronic obstructive pulmonary disease.ResultsStatistical and molecular modelling analyses confirmed that the use of several registered drugs, including acetylsalicylic acid and atenolol may be associated with inhibition of Glutathione Peroxidase 1 and chronic obstructive pulmonary disease.ConclusionThe integration of molecular modelling and pharmacoepidemological data has the potential to advance drug safety science. Ongoing review of medication use and further pharmacoepidemiological and biological analyses are warranted to ensure appropriate use is recommended.Graphical

Evaluation of Global trigger tool as a medication safety tool for adverse drug event detection—a cross-sectional study in a tertiary hospital

The objective of this study is to describe and analyze adverse drug events (ADE) identified using the Global trigger tool (GTT) in a Finnish tertiary hospital during a 5-year period and also to evaluate whether the medication module of the GTT is a useful tool for ADE detection and management or if modification of the medication module is needed. A cross-sectional study of retrospective record review in a 450-bed tertiary hospital in Finland. Ten randomly selected patients from electronic medical records were reviewed bimonthly from 2017 to 2021. The GTT team reviewed a total of 834 records with modified GTT method, which includes the evaluation of possible polypharmacy, National Early Warning Score (NEWS), highest nursing intensity raw score (NI), and pain triggers. The data set contained 366 records with triggers in medication module and 601 records with the polypharmacy trigger that were analyzed in this study. With the GTT, a total of 53 ADEs were detected in the 834 medical records, which corresponds to 13 ADEs/1000 patient-days and 6% of the patients. Altogether, 44% of the patients had at least one trigger found with the GTT medication module. As the number of medication module triggers increased per patient, it was more likely that the patient had also experienced an ADE. The number of triggers found with the GTT medication module in patients’ records seems to correlate with the risk of ADEs. Modification of the GTT could provide even more reliable data for ADE prevention.

Involvement of Pharmacists in the Emergency Department to Correct Errors in the Medication History and the Impact on Adverse Drug Event Detection.

(1) Incomplete or wrong medication histories can lead to missed diagnoses of Adverse Drug Effects (ADEs). We aimed to evaluate pharmacist-identified ED errors in the medication histories obtained by physicians, and their consequences for ADE detection. (2) This prospective monocentric study was carried out in an ED of a university hospital. We included adult patients presenting with an ADE detected in the ED. The best possible medication histories collected by pharmacists were used to identify errors in the medication histories obtained by physicians. We described these errors, and identified those related to medications involved in ADEs. We also identified the ADEs that could not have been detected without the pharmacists' interventions. (3) Of 735 patients presenting with an ADE, 93.1% had at least one error on the medication list obtained by physicians. Of the 1047 medications involved in ADEs, 51.3% were associated with an error in the medication history. In total, 23.1% of the medications involved in ADEs were missing in the physicians' medication histories and were corrected by the pharmacists. (4) Medication histories obtained by ED physicians were often incomplete, and half the medications involved in ADEs were not identified, or were incorrectly characterized in the physicians' medication histories.

Update of triggers for detection of adverse drug events in hematologic patients

The use of triggers for the active search and detection of adverse drug events (ADEs) has been gaining ground within pharmacovigilance services. Thus, the main objective of the study was to propose a new list of triggers to be used in a center specialized in hematology in Rio de Janeiro, Brazil. The update of the list of triggers consisted of revising the current list, with the exclusion and inclusion of new triggers. To verify the performance of the new list of triggers, a cross-sectional study was conducted in which the new triggers were used to investigate the occurrence of ADEs in patients attended in the emergency unit or hospitalized from January to March 2022. For each suspected ADEs, the patient's profile and adverse drug reactions (ADRs) were characterized regarding causality and severity. The performance of the triggers and their ability to capture ADEs were estimated using the following indicators: frequency of the trigger per 100 medical records, frequency of ADEs per 100 records, and positive predictive value (PPV). To evaluate the overall performance of the proposed new list, the PPV was estimated. A total of 374 prescriptions for triggers were identified in 186 medical records. The most efficient in the detection of possible ADEs were: lidocaine, loperamide, bisacodyl, filgrastim and glycerin clyster. The overall PPV of the new suggested list was 48% versus 10% of the previous list. This study demonstrated the importance of an updated list of triggers for the monitoring of ADEs and improvement of the care provided.

LiSA: an assisted literature search pipeline for detecting serious adverse drug events with deep learning

IntroductionDetecting safety signals attributed to a drug in scientific literature is a fundamental issue in pharmacovigilance. The constant increase in the volume of publications requires the automation of this tedious task, in order to find and extract relevant articles from the pack. This task is critical, as serious Adverse Drug Reactions (ADRs) still account for a large number of hospital admissions each year.ObjectivesThe aim of this study is to develop an augmented intelligence methodology for automatically identifying relevant publications mentioning an established link between a Drug and a Serious Adverse Event, according to the European Medicines Agency (EMA) definition of seriousness.MethodsThe proposed pipeline, called LiSA (for Literature Search Application), is based on three independent deep learning models supporting a precise detection of safety signals in the biomedical literature. By combining a Bidirectional Encoder Representations from Transformers (BERT) algorithms and a modular architecture, the pipeline achieves a precision of 0.81 and a recall of 0.89 at sentences level in articles extracted from PubMed (either abstract or full-text). We also measured that by using LiSA, a medical reviewer increases by a factor of 2.5 the number of relevant documents it can collect and evaluate compared to a simple keyword search. In the interest of re-usability, emphasis was placed on building a modular pipeline allowing the insertion of other NLP modules to enrich the results provided by the system, and extend it to other use cases. In addition, a lightweight visualization tool was developed to analyze and monitor safety signal results.ConclusionsOverall, the generic pipeline and the visualization tool proposed in this article allows for efficient and accurate monitoring of serious adverse drug reactions from the literature and can easily be adapted to similar pharmacovigilance use cases. To facilitate reproducibility and benefit other research studies, we also shared a first benchmark dataset for Serious Adverse Drug Events detection.

Automatic Detection of Adverse Drug Events in Geriatric Care: Study Proposal.

One-third of older inpatients experience adverse drug events (ADEs), which increase their mortality, morbidity, and health care use and costs. In particular, antithrombotic drugs are among the most at-risk medications for this population. Reporting systems have been implemented at the national, regional, and provider levels to monitor ADEs and design prevention strategies. Owing to their well-known limitations, automated detection technologies based on electronic medical records (EMRs) are being developed to routinely detect or predict ADEs. This study aims to develop and validate an automated detection tool for monitoring antithrombotic-related ADEs using EMRs from 4 large Swiss hospitals. We aim to assess cumulative incidences of hemorrhages and thromboses in older inpatients associated with the prescription of antithrombotic drugs, identify triggering factors, and propose improvements for clinical practice. This project is a multicenter, cross-sectional study based on 2015 to 2016 EMR data from 4 large hospitals in Switzerland: Lausanne, Geneva, and Zürich university hospitals, and Baden Cantonal Hospital. We have included inpatients aged ≥65 years who stayed at 1 of the 4 hospitals during 2015 or 2016, received at least one antithrombotic drug during their stay, and signed or were not opposed to a general consent for participation in research. First, clinical experts selected a list of relevant antithrombotic drugs along with their side effects, risks, and confounding factors. Second, administrative, clinical, prescription, and laboratory data available in the form of free text and structured data were extracted from study participants' EMRs. Third, several automated rule-based and machine learning-based algorithms are being developed, allowing for the identification of hemorrhage and thromboembolic events and their triggering factors from the extracted information. Finally, we plan to validate the developed detection tools (one per ADE type) through manual medical record review. Performance metrics for assessing internal validity will comprise the area under the receiver operating characteristic curve, F1-score, sensitivity, specificity, and positive and negative predictive values. After accounting for the inclusion and exclusion criteria, we will include 34,522 residents aged ≥65 years. The data will be analyzed in 2022, and the research project will run until the end of 2022 to mid-2023. This project will allow for the introduction of measures to improve safety in prescribing antithrombotic drugs, which today remain among the drugs most involved in ADEs. The findings will be implemented in clinical practice using indicators of adverse events for risk management and training for health care professionals; the tools and methodologies developed will be disseminated for new research in this field. The increased performance of natural language processing as an important complement to structured data will bring existing tools to another level of efficiency in the detection of ADEs. Currently, such systems are unavailable in Switzerland. DERR1-10.2196/40456.

Increasing adverse drug events extraction robustness on social media: Case study on negation and speculation.

In the last decade, an increasing number of users have started reporting adverse drug events (ADEs) on social media platforms, blogs, and health forums. Given the large volume of reports, pharmacovigilance has focused on ways to use natural language processing (NLP) techniques to rapidly examine these large collections of text, detecting mentions of drug-related adverse reactions to trigger medical investigations. However, despite the growing interest in the task and the advances in NLP, the robustness of these models in face of linguistic phenomena such as negations and speculations is an open research question. Negations and speculations are pervasive phenomena in natural language and can severely hamper the ability of an automated system to discriminate between factual and non-factual statements in text. In this article, we take into consideration four state-of-the-art systems for ADE detection on social media texts. We introduce SNAX, a benchmark to test their performance against samples containing negated and speculated ADEs, showing their fragility against these phenomena. We then introduce two possible strategies to increase the robustness of these models, showing that both of them bring significant increases in performance, lowering the number of spurious entities predicted by the models by 60% for negation and 80% for speculations.

Adverse drug event trigger tool: construction and application of a readyto-use tool at Hue University of Medicine and Pharmacy Hospital

Background: Adverse drug event (ADE) is one of the most common causes of injury to patients, accounting for 19% of adverse events (AEs), particularly among the elderly due to their sensitivity to ADE. Thus, taking ADE detection is the first vital step in improving medication safety. Objective: This study aimed to develop an appropriate modified triggers tool based on Institute for Healthcare Improvement (IHI) Global Trigger tool for Adverse Events detecting potential ADEs in patients at Hue University Hospital. Materials and methods: Using a retrospective study on the medical records of inpatients treated in Hue University of Medicine and Pharmacy Hospital in 2020. Results: The modified ADE trigger tool encompassed 13 triggers. In the screening stage, the ADEs were found in 18 medical records (1.9% of total screening records), and 22 ADEs were identified, in which 19 ADEs were determined as adverse drug reactions (ADRs). The study also found that 17/19 ADRs had not been reported via a spontaneous reporting system (89.5%). The modified ADE Trigger tool’s positive predictive value (PPV) was 0.06. Conclusion: A modified ADE Trigger tool for detecting ADE has been constructed and applied at Hue University of Medicine and Pharmacy Hospital. This study would be the first motivation for further studies that attempt to apply this tool into daily clinical pharmacy activities and emphasize the role of Clinical Pharmacists at the hospital. Key words: Adverse Drug Event, adverse event, geriatrics, clinical pharmacy.