How Predictive Modeling and Risk-Based Strategy Are Changing What “Defensible” Means

ISO 10993-18 expectations are evolving faster than most extractables and leachables (E&L) programs. The approach that was defensible when you started may not hold up by the time it reaches a reviewer. Programs that meet the minimums but lack scientific rigor are encountering new questions about identification confidence, quantification accuracy, and documentation rationale.¹ 

This guide is built on patterns observed across hundreds of E&L studies annually at Jordi Labs, an RQM+ company. It shows where programs are most likely to be challenged and how to close those gaps before they become delays. 

What You’ll Learn

  • What changed in ISO 10993-18:2020 and why regulatory interpretation continues to evolve beyond what the standard captures (e.g., shifting USP chapter expectations²˒³ and FDA interpretations based on submission patterns4)
  • How predictive response factor modeling, including Lumo™, uses neural network models to identify unknowns faster5
  • When predicted response factors can replace empirical standards, and when they cannot
  • How to build documentation that answers regulatory questions on AET calculation, identification confidence, and method selection
  • A self-assessment framework to identify misalignment with current expectations

Who This Is For

QA/RA leaders, biocompatibility specialists, and toxicologists responsible for ISO 10993 compliance and E&L program strategy. 

References 

  1. International Organization for Standardization. (2020). ISO 10993-18:2020 Biological evaluation of medical devices — Part 18: Chemical characterization of medical device materials within a risk management process. https://www.iso.org/standard/64750.html 
  1. United States Pharmacopeia. (2023). USP <1663> Assessment of Extractables Associated with Pharmaceutical Packaging/Delivery Systems. https://doi.usp.org/USPNF/USPNF_M7126_03_01.html 
  1. United States Pharmacopeia. (2023). USP <1664> Assessment of Drug Product Leachables Associated with Pharmaceutical Packaging/Delivery Systems. https://doi.usp.org/USPNF/USPNF_M7127_03_01.html 
  1. U.S. Food and Drug Administration. (2023). Use of International Standard ISO 10993-1. https://www.fda.gov/regulatory-information/search-fda-guidance-documents/use-international-standard-iso-10993-1-biological-evaluation-medical-devices-part-1-evaluation-and 
  1. Deng, Y., Grice, A., Louis, M., et al. (2026). Neural Network Prediction of Response Factors for Extractables and Leachables in Pharmaceuticals and Medical Devices. PDA Journal of Pharmaceutical Science and Technology. https://journal.pda.org/content/early/2026/01/30/pdajpst.2025-000061.1 

Back to Resources

Get Your Copy Now

Fields marked with * are required.

Your ideas make an impact. Our expertise brings them to life.

Choose RQM+ as your partner and let’s make MedTech happen together.

Contact Us Today