ICH GCP R3 is now in English & EU languages. Book Now
  • Clinical PracticeClinical PracticeRight Arrow
  • PharmacovigilancePharmacovigilanceRight Arrow
  • ManufacturingManufacturingRight Arrow
  • Laboratory PracticeLaboratory PracticeRight Arrow
  • DistributionDistributionRight Arrow
  • Medical DevicesMedical DevicesRight Arrow
  • AI ClinicalAI ClinicalRight Arrow

About

An introduction to the application of Artificial Intelligence in pharmacovigilance. Covers how AI supports case processing, signal detection, literature screening, and automation of safety workflows. Highlights global regulatory perspectives (ICH, FDA, EMA) and key concepts such as machine learning, natural language processing (NLP), data quality, and human oversight.

This course explains how AI technologies are integrated into end-to-end pharmacovigilance activities, including automated case intake, duplicate detection, triage, MedDRA coding, and narrative generation. It covers AI-driven signal detection, risk management, and real-world data utilization. Includes validation of AI systems, regulatory expectations, ethical considerations, bias mitigation, and human-in-the-loop models. Also addresses implementation challenges, quality assurance, and future trends in AI-enabled pharmacovigilance.

Course Syllabus

  1. Module Learning Objectives
  2. What is Pharmacovigilance?
  3. The PV Lifecycle
  4. ICSR Processing Workflow
  5. The Scale Challenge in Pharmacovigilance
  6. Why the Volume Challenge Demands AI
  7. Signal Management: The Full Process
  8. What is Artificial Intelligence?
  9. AI Technology Landscape
  10. Natural Language Processing (NLP) in Pharmacovigilance
  11. Large Language Models (LLMs) and GenAI in PV
  12. Traditional vs. AI-Enhanced PV Methods
  13. The AI in PV Landscape (CIOMS WG XIV, 2025)
  14. Examples of Deployed AI Solutions in PV (CIOMS WG XIV, Table 1)
  15. CIOMS Working Group XIV – Overview
  16. CIOMS WG XIV – The 7 Guiding Principles
  17. EMA Multi-Annual AI Workplan 2023–2028
  18. EMA Digital Innovation Lab (DigiLab)
  19. AI in PV – Why Now? The Drivers
  20. Benefits of AI in Pharmacovigilance
  21. Risks and Challenges of AI in PV
  22. Caution: The Pharmacovigilance Hype Cycle
  23. The Rapid Evolution of AI Technologies
  24. AI Technology Readiness in PV
  25. Key Terminology You Must Know
  26. PV Data Sources and AI Applicability
  27. The Role of Human Expertise in AI-Enabled PV
  28. Stakeholders in AI-Enabled Pharmacovigilance
  29. Global Regulatory Interest in AI for PV
  30. The EU AI Act — Relevance to PV
  31. Benefits vs. Risks: Balanced Assessment
  32. Module 1 – Connecting to the Guiding Principles
  33. Module 1 – Key Takeaways

  1. Module Learning Objectives
  2. Section 1 - AI in ICSR Processing & Case Management
  3. The ICSR Processing Challenge
  4. ICSR Lifecycle — AI Integration Points
  5. AI in Case Triage
  6. NLP for ICSR Narrative Processing
  7. Automated MedDRA Coding with AI
  8. Duplicate Detection — ML in Practice
  9. AI Translation in Pharmacovigilance
  10. LLMs for Causality Assessment Support
  11. AI in Case Deduplication — Technical Deep Dive
  12. Generative AI for Case Narrative Writing
  13. ICSR Processing: Before vs. After AI
  14. AI Performance Benchmarks in ICSR Processing
  15. Section 2 - AI in Signal Detection & Signal Management
  16. Signal Detection: Foundations
  17. Limitations of Traditional Signal Detection Methods
  18. Machine Learning in Signal Detection
  19. AI Signal Detection Opportunities at EMA
  20. Conditional Inference Tree for False Positive Signal Dismissal
  21. Unsupervised ML for Signal Detection
  22. Predictive Safety Analytics
  23. Section 3 - AI in Literature Screening & Automation
  24. Literature Screening: The Challenge
  25. Semi-Automated Literature Screening Workflow
  26. NLP for Literature Relevance Classification
  27. AI for Extracting Product Information Safety Data
  28. Real-World Data (RWD) and AI in PV
  29. Comparison: AI Applications in PV Workflows
  30. Key Performance Indicators for AI in ICSR Processing
  31. Vendor Evaluation Framework for AI PV Tools
  32. Change Management for AI Implementation
  33. Module 2 – Key Takeaways

  1. Module Learning Objectives
  2. Section 1 - Regulatory Frameworks for AI in PV
  3. The Regulatory Landscape for AI in PV
  4. EMA Reflection Paper on AI in the Medicinal Product Lifecycle (Sept 2024)
  5. FDA Draft Guidance: AI for Regulatory Decision-Making (Jan 2025)
  6. FDA Emerging Drug Safety Technology Program (EDSTP)
  7. Comparison: CIOMS WG XIV Guiding Principles vs. Regulatory Bodies
  8. Section 2 - Risk-Based Approach
  9. The Risk-Based Approach — Core Principle
  10. Risk Assessment Components for AI in PV
  11. Risk-Based Approach: PV Application Examples
  12. Issue Detection and Risk Mitigation
  13. Section 3 - Human Oversight
  14. Human Oversight — Why It Matters in PV
  15. Human-in-the-Loop (HITL) in PV
  16. Human-on-the-Loop (HOTL) in PV
  17. Transformation of Traditional PV Roles
  18. Section 4 - Validity, Robustness & GxP Validation
  19. Validity and Robustness — Core Requirements
  20. AI Validation Requirements in a GxP Environment
  21. AI Model Specification and Design
  22. Performance Evaluation Best Practices
  23. Continuous Integration and Post-Deployment Monitoring
  24. Section 5 - Transparency & Explainability
  25. Transparency — What and To Whom
  26. Transparency Regarding Performance (Table 4 — CIOMS)
  27. Explainability (XAI) in PV
  28. XAI Methods: LIME and SHAP in PV
  29. Section 6 - Governance & Accountability Framework
  30. Governance & Accountability — The CIOMS Framework
  31. The CIOMS Governance Framework Grid
  32. Traceability and Version Control for AI in PV
  33. AI Roles and Responsibilities in a PV Organisation
  34. PSMF and AI System Documentation
  35. Regulatory Inspection Readiness for AI
  36. Module 3 – Key Takeaways

  1. Module Learning Objectives
  2. Section 1 - Fairness & Equity in AI-Enabled PV
  3. Fairness & Equity — Why It Matters in PV
  4. Sources of Bias in PV AI Systems
  5. Bias in Signal Detection: Specific Risks
  6. Mitigation Strategies for Fairness & Equity
  7. Risk, Impact and Mitigation: Fairness in AI PV
  8. Section 2 - Data Privacy in AI-Enabled PV
  9. Data Privacy — The Ethical Foundation
  10. GDPR Principles Relevant to AI in PV
  11. Data Privacy Considerations by Country
  12. GenAI and Privacy — Special Risks
  13. Practical Privacy Protection Measures for AI in PV
  14. Section 3 - Ethics of AI in Pharmacovigilance
  15. Ethical Principles for AI in PV
  16. 'What Went Wrong' — AI Failure Modes in PV Context
  17. 'What Went Wrong' — Additional Scenarios
  18. Section 4 - The Future of AI in Pharmacovigilance
  19. Future Considerations: The CIOMS Vision (Chapter 10)
  20. Future: Predictive Safety Analytics
  21. Future: GenAI Transformation of PV Workflows
  22. Future: Multi-Modal AI in PV
  23. Future: The Long-Term Vision — From PV to Prevention
  24. Preparing Your Organisation for the AI-Enabled PV Future
  25. Module 4 – Key Takeaways

  1. Module Learning Objectives
  2. Case Studies Overview - Eight real-world AI use cases from CIOMS WG XIV Appendix 3
  3. CIOMS WG XIV Use Cases Overview (Appendix 3)
  4. Case Study A: LLMs for Data Extraction in Case Processing
  5. Case Study B: Case Deduplication
  6. Case Study C: AI Translation Assistant
  7. Case Study D: LLMs for Context-Aware Structured Query Language (SQL)
  8. Case Study E: Causality Assessment of Adverse Drug Reactions
  9. Case Study F: Process Efficiencies Supporting Signal Detection
  10. Case Study G: GenAI for PV Document Synthesis
  11. Case Study H: AI for Hydroxychloroquine Retinopathy Detection
  12. What Went Wrong - Learning from AI PV Failures
  13. What Went Wrong: Scenario 1 — The Missed Signal
  14. What Went Wrong: Scenario 2 — The Hallucinated Rechallenge
  15. What Went Wrong: Scenario 3 — The Privacy Breach
  16. What Went Wrong: Scenario 4 — The Unvalidated Model
  17. Course Summary – Key Takeaways
  18. About Whitehall Pharmacovigilance Training
  19. Primary Sources & References
  20. Advanced Topics - Deep dives into NLP, GenAI validation and AI governance implementation
  21. Advanced NLP: Transformer Architecture in PV
  22. Prompt Engineering for PV Applications
  23. AI in Aggregate Safety Reporting (PSURs/PBRERs)
  24. AI and Risk Management Plans (RMPs)
  25. NLP for Social Media and Digital Health Data
  26. Integrating AI into the Pharmacovigilance QMS
  27. AI in PV: Implementation Roadmap
  28. AI Technology Landscape: Key Vendors and Tools
  29. Robotic Process Automation (RPA) in PV — AI or Not?
  30. AI in Clinical Trial Safety Monitoring
  31. AI in Benefit-Risk Assessment
  32. Data Standards Enabling AI in PV
  33. AI in PV: Global Equity Considerations
  34. AI Readiness Self-Assessment Checklist
  35. Regulatory Q&A: Common AI in PV Questions
  36. AI Impact on Signal Detection Efficiency
  37. AI in PV: Adoption Timeline Outlook
  38. In Practice: Questions to Ask Your AI Vendor
  39. Ethics in Action: Scenario Discussion
  40. Lessons Learned: Industry AI PV Deployments
  41. How the CIOMS Principles Connect Across Modules
  42. Governance Framework for GenAI in PV
  43. AI Guiding Principles: CIOMS vs. Regulatory Bodies — Detailed
  44. A Final Thought from CIOMS WG XIV
  45. Extended Topics - AI maturity, model lifecycle, QPPV perspective, digital biomarkers and AI procurement
  46. AI Maturity Model for Pharmacovigilance
  47. Detecting and Managing Model Performance Drift
  48. AI Model Cards: Standardised Transparency in PV
  49. Data Annotation and Labelling for PV AI Training
  50. Transfer Learning: Accelerating PV AI Development
  51. The QPPV's Role in AI-Enabled Pharmacovigilance
  52. AI in Expedited Safety Reporting (15/7-Day Reports)
  53. Cross-Border Data Sharing for AI Model Training in PV
  54. AI for Case Narrative Quality Enhancement
  55. Digital Biomarkers and Wearable Data in AI PV
  56. AI Procurement: Essential Contract & Due Diligence Checklist
  57. AI in Biosimilar Pharmacovigilance
  58. ICH E9(R1) Estimands Framework — Implications for AI in Clinical Safety
  59. AI Governance Committee: Recommended Structure for PV
  60. Lessons from COVID-19: AI as PV Capacity Multiplier
  61. Module Extended Topics: Key Takeaways – Key Takeaways
  62. Appendix - Glossary of Key AI and PV Terms
  63. Glossary of Key AI Terms for PV Professionals
  64. Glossary of Key AI Terms for PV Professionals (continued)
  65. Completion slide

Course Benefits

Benefits fully_compliant icon
Fully compliant

This course describes the compliance requirements for the reporting of adverse events relating to medical devices. Learners also receive 4 Continual Professional Development (CPD) Points, accredited by The Faculty of Pharmaceutical Medicine of the Royal College of Physicians of the United Kingdom. These can be used to count towards the distance learning element of any scheme that comes under the umbrella of The Academy of Medical Royal Colleges or any other scheme for which there is mutual recognition.

Benefits certification icon
Certified

All learners who pass the final exam receive a uniquely numbered, personal certificate to demonstrate their subject knowledge. Since the questions are picked randomly from a database, re-sitting the exam doesn’t mean taking the same questions again and again.

Benefits affordable icon
Affordable

Our cost-effective prices represent excellent value. You can easily pay up to ten-times more for face-to-face training. We can also offer generous group discounts on larger purchases.

Benefits time_saving icon
Time-saving

Our new administration system makes it incredibly quick and simple to allocate licences to multiple learners. Learners save time too by choosing when and where they complete the training. Our reporting tools make it easy for administrators to check the progress of learners and identify areas for future training.

Benefits reliable_and_trustworthy icon
Reliable and trustworthy

This course was written by Steve Jolley, a recognised expert in International drug and device vigilance. You will stay up to date with any international legislative changes in device vigilance as our training courses are constantly monitored, reviewed and updated (last updated in May 2018). Steve Jolley is a Cambridge University graduate with 25 years’ experience in drug & device safety & vigilance, who specializes in global safety compliance, business process improvement and signal detection. He is the Chairperson of the DIA Clinical Safety and Pharmacovigilance steering committee for North America and has worked with over 80 clients in the US, Europe and Japan. He is a featured speaker with the FDA and MHRA at DIA conferences and webinars on drug safety topics including auditing and signaling.)


Our Certified Customers

novartis
NHS
takeda
roche
dhl

Learner Rating & Reviews

4.7
★★★★★★
Average Rating
536 global ratings
★★★★★
87.0%
★★★★★
5.0%
★★★★★
3.0%
★★★★★
3.0%
★★★★★
2.0%
RC

Working with Whitehall training for the last two years of partnership has been a very successful experience – I have fast access to all the GCP course...

SM

I have finalised the demo for the ICH-GCP E6 R3 refresher course. Overall, I liked the content and the interface. I also want to thank Whitehall Train...