Jul 2026· Real-World Data & Evidence· Vol 6, pp. 56-67· 0 citations· 3 references
TL;DR
A critical analysis of the potential of NLP systems to optimize routine PV tasks, taking into account data protection requirements is provided, and AI can become a robust tool for increasing the efficiency of PV processes.
Abstract
Introduction
. Artificial intelligence (AI) has undergone rapid development in pharmacovigilance (PV), evolving from experimental application to being considered a key tool in daily practice. Relatively simple AI models, including statistical signal detection methods, have been used in PV for decades, while recent advances in Natural Language Processing (NLP) have significantly expanded the scope of potential applications.
Objective
. This article provides a critical analysis of the potential of NLP systems to optimize routine PV tasks, taking into account data protection requirements. The application of semantic search AI models based on alternative architectural approaches, specifically embedding models and retrieval-augmented generation (RAG), is examined separately.
Main points
. The authors distinguish between processes that do not involve personal data and allow the use of open AI solutions (searching and systematizing scientific literature, generating publication summaries), and processes involving the handling of confidential information (e. g., data extraction from Individual Case Safety Reports (ICSRs), automated generation of clinical case descriptions, benefit-risk analysis, and compliance with regulatory requirements and reporting standards), which require the use of corporate AI systems deployed within a secure infrastructure. The article also discusses limitations, risks, practical implementation aspects, as well as issues of ensuring the reliability, reproducibility, and transparency of the solutions used.
Conclusion
. AI models, particularly NLP models, have significant potential for integration into routine PV processes. However, successful integration of AI models is impossible without a systematic approach to managing associated risks. Subject to these conditions, AI can become a robust tool for increasing the efficiency of PV processes.
This perspective examines recent developments in AI for PV and introduces a conceptual framework of “computable PV,” in which tasks are evaluated based on their computational tractability and suitability for automation.
Leihong Wu, Joshua Xu, Oanh Dang et al.· Frontiers in Drug Safety and...· 0 citations
The progress of artificial intelligence (AI) has rapidly increased its use in clinical laboratories, making it easier to diagnose patients and run the laboratories more efficiently. Nonetheless, difficulties remain regarding the ethical aspects, uniformity, and reliability of algorithmic decision-making. This study seeks to delineate the evolution of AI applications in clinical laboratories over the preceding five years through a bibliometric analysis. We obtained original articles from the Scopus database published between 2021 and 2025 in the fields of medicine, computer science, and health professions. A systematic identification and screening process resulted in 1,891 documents, followed by filtering, duplicate removal, and eligibility assessment, giving in the inclusion of 994 studies in the final analysis. We conducted a bibliometric analysis to examine publication trends, changes in themes over time, co-occurrence of keywords, networks of international collaboration, and highly cited core studies. The results show that research output is growing quickly, and the focus is shifting from developing new methods to putting them into practice in the real world. Keyword mapping indicates that automation, diagnostic accuracy, and decision-support systems are becoming increasingly important. International collaboration is growing, but it is still unevenly distributed across regions. In conclusion, this study offers a thorough examination of the evolving research landscape of AI in clinical laboratories and underscores the need for enhanced global collaboration and the ethical, clinically reliable, and sustainable incorporation of AI in clinical laboratories.
Tika Adilistya, Firman Pribadi· Indonesian Journal of Global...· 0 citations
These results are the first to demonstrate an intelligent automation platform that may streamline signal management workflows using a machine‐first, human‐verified operational workflow while maintaining regulatory compliance.
Jeffrey B. Warner, Luis Henrique De Souza Teodoro, Anaclara Prada Jardim et al.· Clinical pharmacology and th...· 0 citations
An overview of the CIOMS XIV guidance on Artificial Intelligence in Pharmacovigilance presents seven guiding principles and illustrates how these principles may be applied in practice through selected use cases.
G. N. Norén, Julie Durand, V. Kara et al.· Drug Safety· 0 citations
Artificial intelligence [AI] has become an indispensable part of scientific and medical research, however, the exponential growth in model complexity and computational requirements has made AI adoption challenging for resource-limited settings. The concept of Frugal AI has emerged to address this gap by designing efficient, accessible, and sustainable AI systems that achieve comparable accuracy with reduced computational, financial, and environmental costs. In the context of medical research, Frugal AI enables data-driven discovery, diagnostics, and decision-making through low-cost, scalable, and adaptable methodologies. This review explores the evolution and influence of Frugal AI on research methodology in biomedical sciences over the past decade. It discusses its principles, technological innovations, and integration into experimental design, data management, and analytical frameworks. Furthermore, the paper critically evaluates the benefits and limitations of Frugal AI in medical research, highlighting its transformative role in improving accessibility, reducing bias, and fostering innovation in low-resource environments. Finally, it underscores the future perspectives of Frugal AI in achieving equitable, reproducible, and sustainable medical research worldwide.
Sharique Ahmad, Subuhi Anwar, Saeeda Wasim et al.· Saudi Journal of Biomedical...· 0 citations
