Artificial Intelligence in Pharmacovigilance: An Introduction to Terms, Concepts, Applications, and Limitations

Analysis of Duloxetine-Related Adverse Events Using the Food and Drug Administration Adverse Event Reporting System: Implications for Monitoring and Management

BACKGROUND

The objective of this study was to examine the characteristics of adverse drug reactions of duloxetine and investigate the potential precautions that may exist beyond the drug label.

METHODS

This study used data from the Food and Drug Administration Adverse Event Reporting System database 2004-2023 and the linked information of duloxetine. Four algorithms used to evaluate the correlation between duloxetine and adverse events include reporting odds ratio, proportional reporting ratio, Bayesian confidence propagation neural network, and multi-item gamma Poisson shrinker.

RESULTS

Adverse reactions involving duloxetine were associated with 24 System Organ Classes. Among them, the three most frequent systems affected were psychiatric disorders (reporting odds ratio [ROR] 5.05), nervous system disorders (ROR 2.27), and general medical conditions and administration site conditions (ROR 0.83). Of particular note, the number of reported cases and the risk of occurrence of adverse events of drug withdrawal syndrome (n = 7498), nausea (n = 7942), and headache (n = 5732) were the highest, increasing each year and reached a peak submission in 2017. More importantly, the occurrence of reproductive system and breast disorders (chisq 317.85) was not mentioned in the drug leaflet.

CONCLUSIONS

Psychiatric and nervous system disorders are the most frequently reported adverse events associated with duloxetine, with drug withdrawal syndrome, nausea, and headache being especially common. The emergence of mood-related symptoms, such as agitation and irritability, underscores the need for vigilant monitoring of mental health. Additionally, potential risks affecting the reproductive system suggest areas for further attention. These findings highlight the importance of proactive monitoring to improve patient safety during duloxetine treatment.

Application of a Language Model Tool for COVID-19 Vaccine Adverse Event Monitoring Using Web and Social Media Content: Algorithm Development and Validation Study

BACKGROUND

Spontaneous pharmacovigilance reporting systems are the main data source for signal detection for vaccines. However, there is a large time lag between the occurrence of an adverse event (AE) and the availability for analysis. With global mass COVID-19 vaccination campaigns, social media, and web content, there is an opportunity for real-time, faster monitoring of AEs potentially related to COVID-19 vaccine use. Our work aims to detect AEs from social media to augment those from spontaneous reporting systems.

OBJECTIVE

This study aims to monitor AEs shared in social media and online support groups using medical context-aware natural language processing language models.

METHODS

We developed a language model-based web app to analyze social media, patient blogs, and forums (from 190 countries in 61 languages) around COVID-19 vaccine-related keywords. Following machine translation to English, lay language safety terms (ie, AEs) were observed using the PubmedBERT-based named-entity recognition model (precision=0.76 and recall=0.82) and mapped to Medical Dictionary for Regulatory Activities (MedDRA) terms using knowledge graphs (MedDRA terminology is an internationally used set of terms relating to medical conditions, medicines, and medical devices that are developed and registered under the auspices of the International Council for Harmonization of Technical Requirements for Pharmaceuticals for Human Use). Weekly and cumulative aggregated AE counts, proportions, and ratios were displayed via visual analytics, such as word clouds.

RESULTS

Most AEs were identified in 2021, with fewer in 2022. AEs observed using the web app were consistent with AEs communicated by health authorities shortly before or within the same period.

CONCLUSIONS

Monitoring the web and social media provides opportunities to observe AEs that may be related to the use of COVID-19 vaccines. The presented analysis demonstrates the ability to use web content and social media as a data source that could contribute to the early observation of AEs and enhance postmarketing surveillance. It could help to adjust signal detection strategies and communication with external stakeholders, contributing to increased confidence in vaccine safety monitoring.

The impact of artificial intelligence on the knowledge, attitude, and practice of pharmacists across diverse settings: A cross-sectional study

The pharmacy practice landscape is undergoing a significant transformation with the increasing integration of artificial intelligence (AI). As essential members of the healthcare team, pharmacists' readiness and willingness to adopt AI technologies is critical. This cross-sectional study explores pharmacists' knowledge, attitudes, and practices (KAP) regarding AI in various practice settings. Utilizing a descriptive survey methodology, we collected data through a structured questionnaire targeting pharmacists across diverse working environments. Statistical analyses were conducted to calculate KAP scores. Results revealed that 44.8 % of participants possessed a moderate level of knowledge about AI, while 49.1 % expressed positive attitudes toward its potential applications in pharmacy. However, their current practices related to AI were rated as adequate (57.3 %). Notably, a significant association was found between knowledge, attitudes, and practices (p < 0.001). This study provides valuable insights into pharmacists' readiness to incorporate AI into their practice, emphasizing the need for targeted educational interventions to enhance knowledge and promote positive attitudes. Furthermore, efforts must be directed towards facilitating the integration of AI into pharmacy workflows to fully leverage this transformative technology and improve patient care outcomes.

Artificial intelligence in pharmacovigilance - Opportunities and challenges

Pharmacovigilance (PV) is a data-driven process to identify medicine safety issues at the earliest by processing suspected adverse event (AE) reports and extraction of health data. The PV case processing cycle starts with data collection, data entry, initial checking completeness and validity, coding, medical assessment for causality, expectedness, severity, and seriousness, subsequently submitting report, quality checking followed by data storage and maintenance. This requires a workforce and technical expertise and therefore, is expensive and time-consuming. There has been exponential growth in the number of suspected AE reports in the PV database due to smart collection and reporting of individual case safety reports, widening the base by increased awareness and participation by health-care professionals and patients. Processing of the enormous volume and variety of data, making its sensible use and separating "needles from haystack," is a challenge for key stakeholders such as pharmaceutical firms, regulatory authorities, medical and PV experts, and National Pharmacovigilance Program managers. Artificial intelligence (AI) in health care has been very impressive in specialties that rely heavily on the interpretation of medical images. Similarly, there has been a growing interest to adopt AI tools to complement and automate the PV process. The advanced technology can certainly complement the routine, repetitive, manual task of case processing, and boost efficiency; however, its implementation across the PV lifecycle and practical impact raises several questions and challenges. Full automation of PV system is a double-edged sword and needs to consider two aspects - people and processes. The focus should be a collaborative approach of technical expertise (people) combined with intelligent technology (processes) to augment human talent that meets the objective of the PV system and benefit all stakeholders. AI technology should enhance human intelligence rather than substitute human experts. What is important is to emphasize and ensure that AI brings more benefits to PV rather than challenges. This review describes the benefits and the outstanding scientific, technological, and policy issues, and the maturity of AI tools for full automation in the context to the Indian health-care system.

Innovative applications of artificial intelligence during the COVID-19 pandemic

The COVID-19 pandemic has created unprecedented challenges worldwide. Artificial intelligence (AI) technologies hold tremendous potential for tackling key aspects of pandemic management and response. In the present review, we discuss the tremendous possibilities of AI technology in addressing the global challenges posed by the COVID-19 pandemic. First, we outline the multiple impacts of the current pandemic on public health, the economy, and society. Next, we focus on the innovative applications of advanced AI technologies in key areas such as COVID-19 prediction, detection, control, and drug discovery for treatment. Specifically, AI-based predictive analytics models can use clinical, epidemiological, and omics data to forecast disease spread and patient outcomes. Additionally, deep neural networks enable rapid diagnosis through medical imaging. Intelligent systems can support risk assessment, decision-making, and social sensing, thereby improving epidemic control and public health policies. Furthermore, high-throughput virtual screening enables AI to accelerate the identification of therapeutic drug candidates and opportunities for drug repurposing. Finally, we discuss future research directions for AI technology in combating COVID-19, emphasizing the importance of interdisciplinary collaboration. Though promising, barriers related to model generalization, data quality, infrastructure readiness, and ethical risks must be addressed to fully translate these innovations into real-world impacts. Multidisciplinary collaboration engaging diverse expertise and stakeholders is imperative for developing robust, responsible, and human-centered AI solutions against COVID-19 and future public health emergencies.

Closed-Loop Medication Management with an Electronic Health Record System in U.S. and Finnish Hospitals

Many medication errors in the hospital setting are due to manual, error-prone processes in the medication management system. Closed-loop Electronic Medication Management Systems (EMMSs) use technology to prevent medication errors by replacing manual steps with automated, electronic ones. As Finnish Helsinki University Hospital (HUS) establishes its first closed-loop EMMS with the new Epic-based Electronic Health Record system (APOTTI), it is helpful to consider the history of a more mature system: that of the United States. The U.S. approach evolved over time under unique policy, economic, and legal circumstances. Closed-loop EMMSs have arrived in many U.S. hospital locations, with myriad market-by-market manifestations typical of the U.S. healthcare system. This review describes and compares U.S. and Finnish hospitals' EMMS approaches and their impact on medication workflows and safety. Specifically, commonalities and nuanced differences in closed-loop EMMSs are explored from the perspectives of the care/nursing unit and hospital pharmacy operations perspectives. As the technologies are now fully implemented and destined for evolution in both countries, perhaps closed-loop EMMSs can be a topic of continued collaboration between the two countries. This review can also be used for benchmarking in other countries developing closed-loop EMMSs.

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

As the only blood vessels that can directly be seen in the whole body, pathological changes in retinal vessels are related to the metabolic state of the whole body and many systems, which seriously affect the vision and quality of life of patients. Timely diagnosis and treatment are key to improving vision prognosis. In recent years, with the rapid development of artificial intelligence, the application of artificial intelligence in ophthalmology has become increasingly extensive and in-depth, especially in the field of retinal vascular diseases. Research study results based on artificial intelligence and fundus images are remarkable and provides a great possibility for early diagnosis and treatment. This paper reviews the recent research progress on artificial intelligence in retinal vascular diseases (including diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, retinopathy of prematurity, and age-related macular degeneration). The limitations and challenges of the research process are also discussed.

Patient-centered pharmacovigilance: priority actions from the inherited bleeding disorders community

Pharmacovigilance, the science and practice of monitoring the effects of medicinals and their safety, is the responsibility of all stakeholders involved in the development, manufacture, regulation, distribution, prescription, and use of drugs and devices. The patient is the stakeholder most impacted by and the greatest source of information on safety issues. It is rare, however, for the patient to take a central role and exert leadership in the design and execution of pharmacovigilance. Patient organizations in the inherited bleeding disorders community are among the most established and empowered, particularly in the rare disorders. In this review, two of the largest bleeding disorders patient organizations, Hemophilia Federation of America (HFA) and National Hemophilia Foundation (NHF), offer insights into the priority actions required of all stakeholders to improve pharmacovigilance. The recent and ongoing increase in incidents raising safety concerns and a therapeutic landscape on the cusp of unprecedented expansion heighten the urgency of a recommitment to the primacy of patient safety and well-being in drug development and distribution.

Plain Language Summary

Patients at the center of product safety Every medical device and therapeutic product has potential benefits and harms. The pharmaceutical and biomedical companies that develop them must demonstrate that they are effective, and the safety risks are limited or manageable, for regulators to approve them for use and sale. After the product has been approved and people are using it in their daily lives, it is important to continue to collect information about any negative side effects or adverse events; this is called pharmacovigilance. Regulators, like the United States (US) Food and Drug Administration, the companies that sell and distribute the products, and healthcare professionals who prescribe them are all required to participate in collecting, reporting, analyzing, and communicating this information. The people with the most firsthand knowledge of the benefits and harms of the drug or device are the patients who use them. They have an important responsibility to learn how to recognize adverse events, how to report them, and to stay informed of any news about the product from the other partners in the pharmacovigilance network. Those partners have a crucial responsibility to provide clear, easy-to-understand information to patients about any new safety concerns that come to light. The community of people with inherited bleeding disorders has recently encountered problems with poor communication of product safety issues, prompting two large US patient organizations, National Hemophilia Foundation and Hemophilia Federation of America, to hold a Safety Summit with all the pharmacovigilance network partners. Together they developed recommendations to improve the collection and communication of information about product safety so that patients can make well-informed, timely decisions about their use of drugs and devices. This article presents these recommendations in the context of how pharmacovigilance is supposed to work and some of the challenges encountered by the community.

Lost in Translation: A Multilingual Survey of Interlinguistic Variations in Terms Used in Pharmacovigilance

INTRODUCTION

Although English is the universal language of science, it is nevertheless the first language of only about 6% of the world's population, and 75% of people do not speak English at all. It is therefore important that accurate translations of scientific information should be available, not only for professionals but also for the general public. This applies to pharmacovigilance as much as to any other discipline.

OBJECTIVE

The aim of this study was to determine how pharmacovigilance terms are translated into other languages, in order to judge the extent to which differences between languages might impair communication in pharmacovigilance.

METHODS

I surveyed the translation of 26 pharmacovigilance terms into 26 languages via a panel of 83 pharmacovigilance experts.

RESULTS

Three types of terms emerged: Type 1-those that are similar in form across all, or almost all, of the languages surveyed (e.g. 'signal' and 'risk'); Type 2-terms that are similar in form across some languages but not all (e.g. 'pharmacovigilance' and 'surveillance'); Type 3-terms for which there are major differences across languages (e.g. 'hazard').

CONCLUSION

Misconceptions in the communication of pharmacovigilance information may arise through difficulties in translation. Metaphorical expressions are best avoided in serious scientific publications, in order to reduce the difficulties of translation. A multilingual glossary of terms and definitions, which could be used to program a dedicated machine translator, would be of value. Published guidelines offer guidance to methods of translation, but they are complex and time-consuming and are mostly used in translating instruments for eliciting patient-reported outcomes.

Integration of Privacy Protection and Blockchain-Based Food Safety Traceability: Potential and Challenges

Concern about food safety has become a hot topic, and numerous researchers have come up with various effective solutions. To ensure the safety of food and avoid financial loss, it is important to improve the safety of food information in addition to the quality of food. Additionally, protecting the privacy and security of food can increase food harvests from a technological perspective, reduce industrial pollution, mitigate environmental impacts, and obtain healthier and safer food. Therefore, food traceability is one of the most effective methods available. Collecting and analyzing key information on food traceability, as well as related technology needs, can improve the efficiency of the traceability chain and provide important insights for managers. Technology solutions, such as the Internet of Things (IoT), Artificial Intelligence (AI), Privacy Preservation (PP), and Blockchain (BC), are proposed for food monitoring, traceability, and analysis of collected data, as well as intelligent decision-making, to support the selection of the best solution. However, research on the integration of these technologies is still lacking, especially in the integration of PP with food traceability. To this end, the study provides a systematic review of the use of PP technology in food traceability and identifies the security needs at each stage of food traceability in terms of data flow and technology. Then, the work related to food safety traceability is fully discussed, particularly with regard to the benefits of PP integration. Finally, current developments in the limitations of food traceability are discussed, and some possible suggestions for the adoption of integrated technologies are made.