Hardware Podcasts

#345: Using AI In MedTech

Global Medical Device Podcast · 22 Nov 2023 · 24m · Episode 345

AI in practice: 2 real uses of AI described

What this episode covers

Wade Schroeder, Medical Device Guru at Greenlight Guru, discusses the state of AI in MedTech, highlighting that 65% of professionals distrust AI data accuracy due to unknown sources. He explains how Greenlight Guru’s Risk Intelligence tool uses Bayesian statistics and natural language processing to pull data from the FDA’s MAUDE database, helping engineers address the 'cold start' problem in risk management. Schroeder also introduces the 'Digital Guru,' an AI bot trained specifically on FDA regulations to ensure compliance and trust, contrasting it with general models like ChatGPT.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationGreenlight Guru Risk Intelligence

The AI tool uses Bayesian statistics to analyze the FDA's MAUDE database and provide probabilistic estimates of harm frequency and severity for specific product codes, helping engineers identify and mitigate risks early in the design phase.

“Greenlight actually has what we call risk intelligence. … you can actually take your product code, put it into this risk intelligence tool, and it's going to pull all of the data from the mod database for you … using Basian statistics, is going to give you estimates for how often those things are occurring.”

Speaker 1 · Hear it at 10:15

Engineering & simulationGreenlight Guru (Semantic Search)

The platform employs natural language processing and semantic search to map user-inputted harm descriptions to standardized IMDRF codes, allowing engineers to build risk matrices without memorizing specific regulatory annexes.

“We use that semantic search capabilities, that natural language processing that's built into AI tools such as chat GPT, built our own semantic search then for the IMDRF codes. So you can type in something like one of the examples I've used with a customer's sniffles. … And it comes up with all of these IMDRF codes related to that.”

Speaker 1 · Hear it at 15:08

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Greenlight Guru
Products
ChatGPT, SolidWorks, Greenlight Guru Risk Intelligence, Digital Guru
Also
Wade Schroeder, Etienne Nichols, FDA, IMDRF, MAUDE

Related episodes from other shows

Other shows on the same ground, closest first.

  • 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 · 34m

    172 - Regulatory AI Innovations, Drugs@FDA Database, Regulatory Intelligence Strategies, Human Factors Insights, and Smarter Submission Approaches with Doug Mead

    Doug Mead, founder of CP Pathways and Rhizome AI, explains how his company uses AI to search the FDA's Drugs@FDA database, enabling faster regulatory intelligence for combination products. He details the transition from manual Google searches to a specialized tool that handles OCR and semantic search to interpret review memos, human factors data, and Type C meeting minutes. Mead highlights the value of understanding FDA precedents for products like auto-injectors and on-body injectors, while noting limitations such as redacted data and unpublished supplement reviews.

    Connected products & IoTCertification & compliance
    7 chapters

  • Being an Engineer · 37m

    S1E12 Simplifying Quality Management | Jon Speer

    Jon Speer, founder of Greenlight Guru, explains how his frustration with managing medical device quality via Excel spreadsheets led to the creation of a dedicated QMS software platform. He details the transition from chemical engineering to medical device systems, highlighting the specific pain points of manual data merging and the high validation burden for electronic records. The episode covers Greenlight Guru’s development, its focus on design controls and traceability matrices, and the regulatory challenges of FDA submissions and ISO 13485 certification for startups.

    Quality & yieldStarting a product company
    8 chapters

  • Being an Engineer · 51m

    S6E19 Stuart Grant | MedTech Innovation

    Dr. Stuart Grant, founder of Archetype MedTech, discusses his 25-year career at Johnson & Johnson and DePuy Synthes before launching his consultancy to help startups navigate medical device development. He details the challenges of securing funding, managing regulatory differences between the EU's MDR and the US FDA, and the strategic importance of narrow clinical indications. Grant also explores future trends in surgical robotics and AI, emphasizing the need for modular platforms and the value of accumulated engineering knowledge.

    Starting a product companyMedical & health devices
    11 chapters

  • 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

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.