Detection Of Adverse Events Research Articles

Comparative Safety Surveillance of Triple (IDA) Versus Dual Therapy (DA) in Mass Drug Administration for Elimination of Lymphatic Filariasis in Kenya: A Cohort Event Monitoring Study.

Dual diethylcarbamazine and albendazole (DA) therapy is the standard mass drug administration (MDA) regimen for lymphatic filariasis in Kenya. Following the recent World Health Organization recommendation, Kenya piloted triple therapy with ivermectin, diethylcarbamazine, and albendazole (IDA) in MDA. We conducted a community-based, observational, cohort event monitoring study to compare the types, frequency, severity, and predictors of adverse events following dual versus triple therapy in 20,421 eligible residents. Residents in Kilifi (n = 10,010) and Mombasa counties (n = 10,411) received DA and IDA through MDA campaigns, respectively. Adverse events were actively monitored through house-to-house visits on days 1, 2, and 7 after MDA. Any clinical events reported before and after MDA were cross-checked and verified to differentiate pre-existing events from MDA-associated adverse events. Overall, 5807 and 3102 adverse events were reported by 2839 and 1621 individuals in the IDA and DA groups, respectively. The incidence of experiencing one or more adverse events was significantly higher (p < 0.0001) in the IDA group (27.3%; 95% confidence interval [CI] 26.4-28.2) than in the DA group (16.2%; 95% CI 15.5-16.9). Dizziness (15.9% vs 5.9%) and drowsiness (10.1% vs 2.6%) were the most common adverse events and significantly higher in the IDA group compared with the DA group (p < 0.0001). Most adverse events were mild or moderate with a few severe cases (IDA = 0.05%; 95% CI 0.35-0.78, DA = 0.03%; 95% CI 0.14-0.60). Female sex, obesity, taking three or more diethylcarbamazine or ivermectin tablets, and having pre-existing clinical symptoms were significant predictors of adverse events following IDA treatment. Ivermectin, diethylcarbamazine, and albendazole as a combination is as safe and well tolerated as DA to use in MDA campaigns with no serious life-threatening adverse events. Systemic mild-to-moderate adverse events with a few severe cases and transient adverse events are more common with IDA treatment than with DA treatment. Hence, integrating pharmacovigilance into a MDA program is recommended for the timely detection and management of adverse events.

Empowering Pharmacovigilance: Unleashing the Potential of Generative AI in Drug Safety Monitoring

Pharmacovigilance plays a crucial role in ensuring drug safety and promoting patient well-being throughout the life cycle of medicinal products. However, this field faces several challenges, including underreporting of adverse events, data quality issues, and the complexity of signal detection in large datasets. To address these challenges and enhance drug safety monitoring, there is a growing interest in harnessing the potential of generative artificial intelligence (AI) techniques. This article explores the applications and implications of generative AI in pharmacovigilance. It provides an overview of popular generative models and their working principles, highlighting their ability to analyse drug databases, medical literature, and real-world data sources to identify drug-drug interactions, adverse events, and potential safety signals. Moreover, it emphasizes the importance of human validation and expert oversight in interpreting and acting on the insights generated by generative AI algorithms. The integration of generative AI with traditional pharmacovigilance methods creates a synergistic approach, combining the computational power of AI with human expertise. This integration can lead to improved signal detection, efficient case report generation, proactive risk assessment, and optimized resource allocation. Additionally, the article addresses challenges related to data quality, interpretability, and model validation in generative AI applications, emphasizing the need for standardized protocols and collaborative efforts among stakeholders. Overall, the potential of generative AI in pharmacovigilance is vast. By leveraging its capabilities, we can enhance drug safety monitoring, facilitate early detection of adverse events, and improve patient outcomes. However, it is crucial to address ethical considerations, ensure data privacy, and maintain human oversight to foster responsible and effective implementation of generative AI in pharmacovigilance practices.

Signal Detection of Adverse Event of Metoclopramide in Korea Adverse Event Reporting System (KAERS)

Signal Detection of Adverse Event of Metoclopramide in Korea Adverse Event Reporting System (KAERS)

Cardiopulmonary complications following COVID-19 vaccinations: a systematic review and meta-analysis

Clinical trials of COVID-19 vaccines were insufficient to detect uncommon adverse outcomes that are crucial for risk-benefit analyses and informing clinical practice post-vaccination. As a result, the detection of infrequent adverse events has become a global research priority. The current study aims to estimate the rate of cardiopulmonary complications associated with COVID-19 vaccination.Two databases and one search engine were explored to identify English language-related studies published up to January 2023.The literature search turned up a total of 3974 relevant studies. Of them, 37 articles matched the inclusion criteria. The mean age of patients was 26.4 years, and about 77% of them were male. The most common reported consequence was inflammatory heart disease (myo-peri-cariditis) (77%), followed by pulmonary embolism (17%), and myocardial infarction (5%). The majority of complications were reported following mRNA COVID-19 vaccinations, particularly following the administration of the second dose. Pfizer has a slightly higher risk of cardiac complications following vaccination (4.1 per 100000 persons) than Moderna (3.7 per 100,000 persons). Although cardiopulmonary complications associated with COVID-19 vaccinations are uncommon, they can be life-threatening. Therefore, more large-scale observational studies and review articles of those studies are strongly recommended.

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

Detection of Vaccine Adverse Events Before Package Insert Revisions Using a Japanese Spontaneous Reporting System.

The usefulness of disproportionality analysis for the pharmacovigilance of vaccines in the Japanese Adverse Drug Event Report (JADER) database is yet to be proven. This study aimed to verify whether significant disproportionality could be detected before adding new vaccine adverse event information to package inserts. Information on package insert revisions related to vaccine adverse drug events from January 2013 to March 2023 was extracted from the Pharmaceuticals and Medical Devices Agency website. This period was set as the maximum period for which early disproportionalities could be detected by the latest JADER database (April 2004 to December 2022). From JADER data, 15 revision histories (10 types of vaccines) of package inserts were identified, and 823,662 cases were obtained. Of the 15, 12 (80%) adverse events were identified as significant disproportionalities before package insert revisions were made. Nine of the 15 (60%) events were identified as significant disproportionalities earlier than at least 12 months. These findings suggest that the JADER database may detect vaccine adverse events earlier than package insert revisions, indicating its usefulness for the safety surveillance of vaccines.

Time Elapsed Between Cells, Tissues, and Organs Donation and Transplantation and Adverse Events Detection

This study was designed to discuss the time elapsed between cell, tissue, and organ donation and transplantation and detection of adverse events notified in São Paulo, Brazil. This is a descriptive study with a quantitative approach. Data were provided by the Transplant Center of the state of São Paulo from the "Individual notification form of adverse reactions in Biovigilance" between 2016 and 2019. Analysis was performed using descriptive statistics. Fifty-two notifications were analyzed, and 3 categories were formed: (1) adverse events detected on the same day of the transplant, 8; (2) adverse events detected between 1 week and 1.5 years after transplant, 40; and (3) adverse events detected 2 years after transplant, 4. The discussion on the topic is beginning; however, it is important. Clinical management of transplant recipients and comprehending what is considered an adverse event and the natural course of a patient's life can impact clinical decision-making, public policies, and patient safety research. This study highlights the need to investigate related factors to adverse events, especially the time between the transplant procedure and adverse event detection, to establish clinical guidelines.

Data mining for signal detection of adverse events for taxanes based on the food and drug administration adverse drug events reporting system database

ABSTRACT Background This study aimed to mine and compare the positive signals of adverse drug events (ADE) in paclitaxel, docetaxel, and nab-paclitaxel to evaluate the accuracy of current drug package information inserts and enable clinicians to select the appropriate treatment. Research design and methods ADE data reported from January 2006 to December 2020 were extracted from the Food and Drug Adverse Drug Events Reporting System (FAERS) database, and the reporting odds ratio (ROR) was used to detect the risk signals of the 3 taxanes. The definition relied on system organ class (SOCs) and preferred terms (PTs) by the Medical Dictionary for Regulatory Activities (MedDRA). Results A total of 39,163 case reports on paclitaxel, docetaxel and nab-paclitaxel involving 25 different system organ classes (SOCs) were retrieved from the database. The ADE paclitaxel and nab-paclitaxel reports mainly focused on ‘general disorders and administration site conditions’ and the docetaxel ADE reports focused on ‘skin and subcutaneous tissue diseases.’ Among the three taxanes, nab-paclitaxel had the highest positive signal for serious adverse events. Conclusions Overall, the most common ADE signals and ADE mapping systems obtained in this study were consistent with the package inserts. However, some inconsistencies were noted. Further research is recommended to confirm some of the strong risk signals for ADEs for taxanes before updating the drug package information inserts.

Signal detection of COVID-19 vaccines adverse events using spontaneous reports from South Korea.

Studies on the detection of COVID-19 vaccine signals in South Korea are insufficient. Therefore, to investigate adverse events (AEs) that might be associated with COVID-19 vaccines, signals were detected using spontaneous reports from South Korea. We compared the signals with the vaccine insert lists of the regulators in the four countries. Spontaneous reports from 62 sites were collected by the National Medical Center between January 2013 and May 2022. A descriptive analysis of AEs associated with COVID-19 vaccines (Pfizer, Moderna, AstraZeneca, and Janssen) was performed, and the proportional reporting ratio, reporting odds ratio, and information component were calculated. We performed five analyses, with five cases and one control group. During the study period, 68,355 cases were reported, of which 12,485 were COVID-19 vaccine AEs. Injection site pain (2,198 cases, 17.6%), myalgia (1,552 cases, 12.4%), headache (1,145 cases, 9.2%), pyrexia (1,003 cases, 8.0%), and fatigue (735 cases, 5.9%) were frequently reported. When comparing all COVID-19 vaccines with other viral vaccines, 20 signals were detected, of which cachexia, dyspepsia, abdominal discomfort, and mood swings were not listed on the vaccine inserts in all four countries. Overall, 20, 17, 29, and 9 signals were detected in vaccines developed by Pfizer, Moderna, AstraZeneca, and Janssen, respectively. Based on a disproportionate analysis of COVID-19 vaccine AEs using spontaneous reports from South Korea, different signals were detected for each vaccine manufacturer.

Active Pharmacovigilance Study: A Follow-Up Model of Oral Anti-Cancer Drugs under Additional Monitoring.

Adverse drug reactions (ADRs) are responsible for almost 5% of hospital admissions, making it necessary to implement different pharmacovigilance strategies. The additional monitoring (AM) concept has been highlighted and intended to increase the number of suspected ADRs reported, namely in medicines with limited safety data. A prospective, descriptive study of active pharmacovigilance (AP) was conducted between 2019 and 2021 in the Local Health Unit of Matosinhos (LHUM) (Porto, Portugal). A model of AP for medicines under AM, namely oral antineoplastic agents, was designed. Follow-up consultations were performed, and adverse events (AEs) data were collected. The overall response to the treatment was evaluated through the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 criteria. A total of 52 patients were included in the study, and 14 antineoplastic drugs under AM were analyzed. Of the total number of patients included, only 29 developed at least one type of toxicity. Hematological disorders were the most reported suspected ADR. However, only four patients interrupted their treatment due to toxicity. After 12 months of treatment, most patients had disease progression, which was the main reason for therapy discontinuation. This AP model played an important role in the early detection of AEs and, consequently, contributed to better management of them. Increasing the number of suspected ADR reports is crucial for drugs with limited safety data.

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.

Development of a Periprocedure Trigger for Outpatient Interventional Radiology Procedures in the Veterans Health Administration.

Interventional radiology (IR) is the newest medical specialty. However, it lacks robust quality assurance metrics, including adverse event (AE) surveillance tools. Considering the high frequency of outpatient care provided by IR, automated electronic triggers offer a potential catalyst to support accurate retrospective AE detection. We programmed previously validated AE triggers (admission, emergency visit, or death up to 14 days after procedure) for elective, outpatient IR procedures performed in Veterans Health Administration surgical facilities between fiscal years 2017 and 2019. We then developed a text-based algorithm to detect AEs that explicitly occurred in the periprocedure time frame: before, during, and shortly after the IR procedure. Guided by the literature and clinical expertise, we generated clinical note keywords and text strings to flag cases with high potential for periprocedure AEs. Flagged cases underwent targeted chart review to measure criterion validity (i.e., the positive predictive value), to confirm AE occurrence, and to characterize the event. Among 135,285 elective outpatient IR procedures, the periprocedure algorithm flagged 245 cases (0.18%); 138 of these had ≥1 AE, yielding a positive predictive value of 56% (95% confidence interval, 50%-62%). The previously developed triggers for admission, emergency visit, or death in 14 days flagged 119 of the 138 procedures with AEs (73%). Among the 43 AEs detected exclusively by the periprocedure trigger were allergic reactions, adverse drug events, ischemic events, bleeding events requiring blood transfusions, and cardiac arrest requiring cardiopulmonary resuscitation. The periprocedure trigger performed well on IR outpatient procedures and offers a complement to other electronic triggers developed for outpatient AE surveillance.

Use of Structured Electronic Health Records Data Elements for the Development of Computable Phenotypes to Identify Potential Adverse Events Associated with Intravenous Immunoglobulin Infusion.

Detection of adverse reactions to drugs and biologic agents is an important component of regulatory approval and post-market safety evaluation. Real-world data, including insurance claims and electronic health records data, are increasingly used for the evaluation of potential safety outcomes; however, there are different types of data elements available within these data resources, impacting the development and performance of computable phenotypes for the identification of adverse events (AEs) associated with a given therapy. To evaluate the utility of different types of data elements to the performance of computable phenotypes for AEs. We used intravenous immunoglobulin (IVIG) as a model therapeutic agent and conducted a single-center, retrospective study of 3897 individuals who had at least one IVIG administration between 1 January 2014 and 31 December 2019. We identified the potential occurrence of four different AEs, including two proximal AEs (anaphylaxis and heart rate alterations) and two distal AEs (thrombosis and hemolysis). We considered three different computable phenotypes: (1) an International Classification of Disease (ICD)-based phenotype; (2) a phenotype-based on EHR-derived contextual information based on structured data elements, including laboratory values, medication administrations, or vital signs; and (3) a compound phenotype that required both an ICD code for the AE in combination with additional EHR-derived structured data elements. We evaluated the performance of each of these computable phenotypes compared with chart review-based identification of AEs, assessing the positive predictive value (PPV), specificity, and estimated sensitivity of each computable phenotype method. Compound computable phenotypes had a high positive predictive value for acute AEs such as anaphylaxis and bradycardia or tachycardia; however, few patients had both ICD codes and the relevant contextual data, which decreased the sensitivity of these computable phenotypes. In contrast, computable phenotypes for distal AEs (i.e., thrombotic events or hemolysis) frequently had ICD codes for these conditions in the absence of an AE due to a prior history of such events, suggesting that patient medical history of AEs negatively impacted the PPV of computable phenotypes based on ICD codes. These data provide evidence for the utility of different structured data elements in computable phenotypes for AEs. Such computable phenotypes can be used across different data sources for the detection of infusion-related adverse events.

Analysis of medication-related triggers to determine adverse drug events

PurposeVoluntary event reporting systems continue to be the most common method used to identify adverse events in most US hospitals; however, this method fails to capture more than 90% of...

Knowledge, Perception, and Reporting Practices of Healthcare Providers about Adverse Events Following the COVID-19 Vaccination in Iraq(Conference Paper )#

Routine vaccination activities, such as detection, reporting, and management of adverse events following immunization (AEFIs), are generally handled by healthcare providers (HCPs). Safe vaccines against severe acute respiratory syndrome coronavirus (SARS-CoV-2) were introduced to control the Coronavirus Disease-19 (COVID-19) pandemic. The study aimed to assess the knowledge, perceptions, and practice of HCPs in Iraq about reporting adverse events following COVID-19 vaccination, and their association with sociodemographic variables. The study was a cross-sectional study that was carried out between August and September 2021 at the COVID-19 vaccination centers in Iraq. This study used an online and paper-based questionnaire, which was distributed among HCPs (physicians and pharmacists) in COVID-19 vaccination centers. A total of 117 pharmacists and physicians responded to the survey. Two-thirds of respondents were pharmacists. The majority of the respondents (49.6%) had fair knowledge levels on AEFIs. The perception of 43% of the participants was very good, whereas the perception of 28%, 23%, and 6% of the participants was fair, good, and poor, respectively. The reporting practice of HCPs was inadequate in 53% of respondents. The number of pharmacists who had good knowledge of AEFIs was significantly higher than that of the physicians. The age group (30-39) years of HCPs was significantly associated with more positive perception towards AEFIs. The number of pharmacists that had good perception was significantly higher than that of the physicians. Furthermore, HCPs aged 30 to 39 years had significantly higher reporting practices than other age groups. The study highlighted that the HCPs working at the COVID-19 vaccination centers have low knowledge of AEFIs. On the other hand, HCPs had more positive perception towards reporting AEFIs. Education programs and reference materials are needed to increase their awareness about AEFIs.

Medical errors and patient safety: Strategies for reducing errors using artificial intelligence

Background: Medical errors remain a significant challenge in healthcare, contributing to adverse patient outcomes, increased costs, and extended hospitalizations. These errors encompass diagnostic inaccuracies, medication mistakes, surgical errors, and communication breakdowns. The global prevalence of medical errors underscores the urgent need for effective strategies to enhance patient safety. Aim: This article explores the role of Artificial Intelligence (AI) in reducing medical errors and improving patient safety. It aims to evaluate how AI technologies can mitigate various types of medical errors, and the challenges associated with their implementation. Methods: The study reviews current literature on AI applications in healthcare, focusing on diagnostic support, medication safety, surgical precision, and patient monitoring. It analyzes the effectiveness of AI-driven systems in reducing errors across different medical disciplines and examines the integration challenges, including ethical and regulatory concerns. Results: AI technologies, including machine learning algorithms and decision support systems, have demonstrated significant potential in enhancing diagnostic accuracy, preventing medication errors, and improving surgical outcomes. AI-driven systems have shown promising results in real-time patient monitoring, early detection of adverse events, and optimizing healthcare management. However, challenges related to data privacy, algorithm transparency, and integration into clinical workflows persist.

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.

PHARMACOKINETICS AND PHARMACODYNAMICS OF PROPOFOL AND DEXMEDETOMIDINE DURING ELECTIVE PROCEDURAL SEDATIONS AND CHARACTERISTICS OF THEIR COMBINATION (LITERATURE REVIEW)

In the previous publication, we outlined the general principles of procedural sedation (PS), the depth of suppression of consciousness and spontaneous motor activity, the minimum quantity of patients' pre-procedural examinations and the aspects of informed consent obtaining. The principles of vital signs monitoring, patients' immobilisation, and the detection and treatment of adverse events have been described. A key aspect of the PS is the readiness to ensure patency of the airways and oxygenation at least one level deeper than the existing level of the PS.&#x0D; In this publication, attention is focused on the pharmacokinetics and pharmacodynamics of propofol and dexmedetomidine - the main drugs for elective PS and on the combination between them. In a future publication, we plan to characterize other key medications for PS, such as midazolam, ketamine, thiopental, and fentanyl.&#x0D; Propofol is a short-track anaesthesia drug, and it was the most widely distributed in the 21st century because after its use patients quickly and fully regain consciousness. At the same time, to achieve the necessary deep level of sedation and prevent unintended movements of the patient, it is often required to use high doses of propofol that can cause clinically significant suppression of the patency of the upper respiratory airways, depth of breathing, and hemodynamic. Therefore, in this publication, we promote the implementation of multimodal sedation and analgesia with the use of moderate doses of several drugs, which allows a significant reduction in the dose of propofol and thus increase the safety of PS. Dexmedetomidine has both sedative and analgesic properties with a minimal effect on the patency of the upper airways and the depth of breathing, thus is the best drug to combine with propofol in PS.&#x0D; In children, intranasal administration of dexmedetomidine and midazolam is an important alternative method of premedication, which provides a gentle entry into sedation and prevents the child's stress reactions to the placement of a venous catheter. Although the use of dexmedetomidine in children's practice is still "off-label" and outside the indications approved by the FDA in this publication we provide evidence to justify its safety and effectiveness of its usage in paediatrics PS.

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.