Scholarlink

Background <p>Pharmacovigilance is vital for monitoring adverse drug reactions (ADRs) and ensuring drug safety. Traditional methods are slow and inconsistent, but artificial intelligence (AI), through automation and advanced analytics, improves efficiency and accuracy in managing increasing data complexity.</p> Aim <p>To explore AI’s practical applications in pharmacovigilance, focusing on efficiency, process acceleration, and task automation. It also examines the use of an expert-defined Bayesian network for causality assessment in a Pharmacovigilance Centre, demonstrating its impact on decision-making.</p> Method <p>A comprehensive literature narrative review was conducted in MEDLINE (via PubMed), Scopus, and Web of Science using a set of targeted keywords, including but not limited to “pharmacovigilance”, “artificial intelligence”, “adverse drug reactions” and “drug safety”. Relevant studies were analysed without restrictions on publication year or language. The search was carried out in January 2025.</p> Results <p>AI has greatly improved pharmacovigilance by streamlining signal detection, surveillance, and ADR reporting automation. Techniques like data mining and automated signal detection have expedited safety signal identification, while duplicate detection has enhanced data precision in safety evaluations. AI has also refined real-world evidence analysis, deepening drug safety and efficacy insights. Predictive models now anticipate ADRs and drug-drug interactions, enabling proactive patient care. At a regional pharmacovigilance center, the implementation of an expert-defined Bayesian network has optimized causality assessment, reducing processing times from days to hours, minimizing subjectivity, and improving the reliability of drug safety evaluations.</p> Conclusion <p>AI holds significant promise for enhancing pharmacovigilance practices, yet its practical application remains primarily confined to academic research, with integration hindered by data quality issues, regulatory barriers, and the need for more transparent algorithms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial intelligence in pharmacovigilance: a narrative review and practical experience with an expert-defined Bayesian network tool

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月30日

查看全文
  • Rogério Caixinha Algarvio,
  • Jaime Conceição,
  • Pedro Pereira Rodrigues,
  • Inês Ribeiro,
  • Renato Ferreira-da-Silva

摘要

Background

Pharmacovigilance is vital for monitoring adverse drug reactions (ADRs) and ensuring drug safety. Traditional methods are slow and inconsistent, but artificial intelligence (AI), through automation and advanced analytics, improves efficiency and accuracy in managing increasing data complexity.

Aim

To explore AI’s practical applications in pharmacovigilance, focusing on efficiency, process acceleration, and task automation. It also examines the use of an expert-defined Bayesian network for causality assessment in a Pharmacovigilance Centre, demonstrating its impact on decision-making.

Method

A comprehensive literature narrative review was conducted in MEDLINE (via PubMed), Scopus, and Web of Science using a set of targeted keywords, including but not limited to “pharmacovigilance”, “artificial intelligence”, “adverse drug reactions” and “drug safety”. Relevant studies were analysed without restrictions on publication year or language. The search was carried out in January 2025.

Results

AI has greatly improved pharmacovigilance by streamlining signal detection, surveillance, and ADR reporting automation. Techniques like data mining and automated signal detection have expedited safety signal identification, while duplicate detection has enhanced data precision in safety evaluations. AI has also refined real-world evidence analysis, deepening drug safety and efficacy insights. Predictive models now anticipate ADRs and drug-drug interactions, enabling proactive patient care. At a regional pharmacovigilance center, the implementation of an expert-defined Bayesian network has optimized causality assessment, reducing processing times from days to hours, minimizing subjectivity, and improving the reliability of drug safety evaluations.

Conclusion

AI holds significant promise for enhancing pharmacovigilance practices, yet its practical application remains primarily confined to academic research, with integration hindered by data quality issues, regulatory barriers, and the need for more transparent algorithms.