Hardware Podcasts

#459: The Purolea Warning Letter & Validating AI in Medical Devices - What FDA Actually Requires

Global Medical Device Podcast · 11 May 2026 · 24m · Episode 459

What this episode covers

Host Etienne Nichols analyzes the FDA's warning letter to Purolea Cosmetics Lab, arguing that the citation was not a crackdown on AI but a failure of quality system oversight and process validation. He explains that while Purolea used AI agents to draft specifications, the core violation was the lack of human review and accountability under 21 CFR 211.22. Nichols outlines a three-part validation framework for AI/ML-based Software as a Medical Device (SaMD), emphasizing the separation of training, validation, and holdout test data. He concludes by listing essential regulatory standards and five concrete questions to assess if a quality system is ready for FDA AI inspections.

Most relevant to

large enterprises

Topics

Mentioned

Companies
Purolea Cosmetics Lab, FDA, Greenlight Guru
Also
21 CFR 211.22, QMSR, IEC 62304, ISO 13485, ISO 14971, 21 CFR Part 11, IMDRF SaMD N41

Related episodes from other shows

Other shows on the same ground, closest first.

  • Let's Combinate · 31m

    206 - Will AI Decide Your Next Drug/Device Approval?

    Dominick Romano, founder of Drainpipe.io, explains how AI can be regulated in pharma and medtech by applying ICH guidelines and process validation to AI systems. He argues that pharmaceuticals are uniquely suited for AI because both deal with 'combinatorial problem sets' involving infinite inputs and outputs, requiring rigorous validation to prevent hallucinations in regulatory dossiers. Romano details how AI can accelerate dossier preparation by reducing millions of working hours in data acquisition and how regulators might use AI agents to speed up review processes, provided the technology is proven safe and accurate by the companies themselves.

    AI & machine learningCertification & compliance
    8 chapters

  • Let's Combinate · 22m

    210 - How AI Is Rewriting GMP: Smarter CAPA, PAT, DOE, and Continuous Yield

    Ben Locwin, a Healthcare Executive and Quality SME, joins host Subhi Saadeh to discuss integrating AI into Good Manufacturing Practices (GMP) within pharmaceutical and medical device manufacturing. They explore current applications like AI-assisted CAPA and deviation management, while highlighting the regulatory challenges of algorithmic opacity in Process Analytical Technology (PAT) and continuous manufacturing. The conversation emphasizes the critical role of Design of Experiments (DOE) in training AI models and using yield calculations as an early warning system for process discrepancies in combination products.

    Quality & yieldValidation & product-market fit
    6 chapters

  • Let's Combinate · 32m

    107 - Distilling Decades of MedTech Data, Generative AI, and Doing Without Tribal Knowledge with Michelle Wu

    Michelle Wu, CEO and Founder of NyquistData, explains how her company uses generative AI to distill decades of MedTech data, removing the 'tribal knowledge' barrier for quality and regulatory professionals. She details the distinction between pre-trained models and fine-tuned algorithms, emphasizing that Nyquist’s data is validated and specific to FDA and global medical device regulations, unlike generic models like OpenAI. Wu discusses the challenge of changing organizational culture and overcoming skepticism in life sciences, highlighting features like the 'Device Explorer' and 'Data Writer' that democratize access to complex regulatory insights.

    AI & machine learningQuality & yield
    10 chapters

  • Let's Combinate · 25m

    155 - FDA Compliance Programs, Program 7536.000: CDER vs. CDRH led Inspections, Mock PAI's, Supplier Management, and What is a Manufacturer? with Laurie Auerbach

    Laurie Auerbach, President of Compliance Prodigies, LLC, explains FDA Compliance Program 7356.000, clarifying that contract manufacturers (CMOs) and component suppliers selling bundled solutions are legally defined as combination product manufacturers. She highlights common failures in mock Pre-Approval Inspections (PAIs), particularly the misconception that drug GMPs (21 CFR 211) and ICH Q10 fully satisfy device requirements under 21 CFR Part 4. Auerbach emphasizes that sponsors often fail to audit suppliers for device-specific elements like design control, risk management, and specific supplier controls, leading to critical gaps in quality agreements and inspection readiness.

    Certification & complianceManufacturing partners & offshoring
    6 chapters

  • Being an Engineer · 51m

    S5E29 Steve Gompertz | Medical Device Quality Control & Regulatory Requirements

    Steve Gompertz, a partner at QRx Partners with prior leadership roles at Medtronic, Boston Scientific, St. Jude Medical, and Pelican Biothermal, explains how to build scalable quality management systems for medical device companies. He details the evolution of regulatory frameworks, noting the shift toward stricter EU standards and the integration of AI and cybersecurity into device compliance. Gompertz emphasizes tailoring quality systems to company size, using a case study of a client who reduced FDA findings from dozens to zero by implementing a holistic, process-connected system rather than a checklist approach. He also advocates for concurrent engineering and cross-functional teams to accelerate development while maintaining rigorous safety standards.

    Medical & health devicesQuality & yield
    10 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Global Medical Device Podcast. The episode itself belongs to its publisher.