In this episode of The Healthcare AI Pod, we unpack the impact of LLM-based medical agents on modern medicine – from architecture and multi-agent design to regulation and real-world risks.

Healthcare is facing a perfect storm: ageing populations, staff shortages, and rising costs. Can AI agents be the solution?

We discuss insights from over 60 studies on medical LLMs, including key areas such as:

• Multi-agent architectures and clinical decision support
• The security dilemma: protecting patient data when your API is just text
• Prompt injection attacks and HIPAA compliance challenges
• Liability concerns in AI-powered healthcare

From Baymax dreams to real-world implementation: how close are we?

Timestamps

0:00 Introduction – Baymax as inspiration for medical AI
2:20 What are LLM-based medical agents and how they differ from models
10:00 Healthcare security – regulation, compliance, and patient data
14:50 Patient reliance on AI, prompt-hacking, and global access challenges
18:00 Agent architectures – functional, role-based, and departmental approaches
25:10 Task decomposition and subject-matter expert input
28:00 Reward functions, accuracy vs user-pleasing bias, and physician training
33:00 User experience – agent personalities and conversational design
45:20 Liability, insurance, and evaluation of medical AI systems
54:20 Future outlook – Baymax revisited, challenges, and opportunities ahead

Mentioned Materials

• A Survey of LLM-based Agents in Medicine: How far are we from Baymax? https://arxiv.org/abs/2502.11211
• MAGDA: Multi-agent guideline-driven diagnostic assistance https://arxiv.org/abs/2409.06351

Listen On

• YouTube – https://youtu.be/R9h_Whj6sB0
• Apple Podcasts – https://podcasts.apple.com/us/podcast/the-healthcare-ai-podcast/id1827098175
• Spotify – https://open.spotify.com/show/2XNrQBeCY7OGql2jVhcP7t
• Amazon Music – https://music.amazon.com/podcasts/5b1f49a6-dba8-479e-acdf-9deac2f8f60e/the-healthcare-ai-podcast

Connect With Us

• Our Website – https://www.johnsnowlabs.com/
• LinkedIn – https://www.linkedin.com/company/johnsnowlabs/
• Facebook – https://www.facebook.com/JohnSnowLabsInc/
• X (Twitter) – https://x.com/JohnSnowLabs

• 
  

#HealthcareInnovation #AIAgents #HealthTech #MedicalAI #AIEthics #Baymax #MedicalLLM #HealthcareAI #ClinicalAI #MedicalTechnology #AIResearch #DigitalHealth #FutureOfMedicine #AIinMedicine #HealthcareAutomation #MedicalChatbots #PatientCare #HealthcareSolutions #MedicalInnovation

Can AI make healthcare feedback fairer and smarter? In Episode 4 of The Healthcare AI Podcast, Ben Webster (VP of AI Solutions at NLP Logix) and David Talby (CEO of John Snow Labs) dive into a game-changing approach to AI governance. Discover how LangTest tackles bias in processing 1.5M hospital feedback audio files annually, ensuring fair sentiment analysis and actionable insights. From eliminating gender bias in nurse vs. doctor feedback to building robust, ethical AI models, this episode is a must-watch for healthcare and AI innovators!

Join the Conversation: What’s the biggest challenge in healthcare AI today? Comment below!

Timestamps

06:18 – Bias in patient-feedback NLP

07:13 – LangTest & synthetic debiasing

12:30 – Data contamination & custom benchmarks

15:19 – Robustness testing & augmentation

20:18 – Medical red-teaming & safety checks

23:44 – Clinical cognitive biases in LLMs

Listen on your favourite platform:

• ⁠YouTube⁠: https://www.youtube.com/playlist?list=PL5zieHHAlvApZKkwtu746ivthRc5zyTiU

• ⁠⁠Apple Podcast⁠⁠: https://podcasts.apple.com/us/podcast/the-healthcare-ai-podcast/id1827098175

• ⁠⁠Spotify⁠⁠: https://open.spotify.com/show/2XNrQBeCY7OGql2jVhcP7t

• Amazon Music⁠⁠: https://music.amazon.com/podcasts/5b1f49a6-dba8-479e-acdf-9deac2f8f60e/the-healthcare-ai-podcast

Connect with us:

Our website: https://www.johnsnowlabs.com/

LinkedIn: https://www.linkedin.com/company/johnsnowlabs/

Facebook: https://www.facebook.com/JohnSnowLabsInc/

X: https://x.com/JohnSnowLabs

#AIinHealthcare #AIBias #EthicalAI #AIGovernance #NLP #HealthTech #PatientFeedback #HealthcareAI

Dive into Episode 3 of the Healthcare AI Podcast, where Vishnu Vettrivel and Alex Thomas explore the growing world of Model Context Protocol (MCP) with a focus on Healthcare MCP (HMCP) from Innovaccer. This episode breaks down the essentials of MCP, from converting papers to N-Triples to deploying on Claude Desktop. Learn about resources, prompts, and tools that empower AI models, plus key security considerations. Stick around for a call to action to spark your thoughts on agentic frameworks!

Tune in to discover why MCP could be the next big leap for AI in Healthcare.

Timestamps

01:01 – Introducing the Model Context Protocol (MCP): Purpose & Core Concepts

05:44 – Healthcare MCP (HMCP) by Innovaccer

06:50 – Basics of MCP: Resources, Prompts, Tools

10:50 – Demo: Deploying to Claude Desktop (Example MCP Project)

22:24 – Healthcare Relevance & HMCP

23:46 – Security & Limitations

27:30 – Future Directions

Listen on your favourite platform:

• YouTube: https://www.youtube.com/playlist?list=PL5zieHHAlvApZKkwtu746ivthRc5zyTiU

• ⁠⁠Apple Podcast⁠⁠: https://podcasts.apple.com/us/podcast/the-healthcare-ai-podcast/id1827098175

• ⁠⁠Spotify⁠⁠: https://open.spotify.com/show/2XNrQBeCY7OGql2jVhcP7t

• Amazon Music⁠⁠: https://music.amazon.com/podcasts/5b1f49a6-dba8-479e-acdf-9deac2f8f60e/the-healthcare-ai-podcast

Resources:

- Model Context Protocol: https://modelcontextprotocol.io/overview

- Introducing HMCP: A Universal, Open Standard for AI in Healthcare: https://innovaccer.com/resources/blogs/introducing-hmcp-a-universal-open-standard-for-ai-in-healthcare

- We built the security layer MCP always needed: https://blog.trailofbits.com/2025/07/28/we-built-the-security-layer-mcp-always-needed/

Connect with us:

Our website: https://www.johnsnowlabs.com/

LinkedIn: https://www.linkedin.com/company/johnsnowlabs/

Facebook: https://www.facebook.com/JohnSnowLabsInc/

X: https://x.com/JohnSnowLabs

#MCP #ModelContextProtocol #HealthcareAI #MedicalData #AgenticAI #ClinicalAI #DataScience #HealthTech

Explore regulatory‑grade multimodal data de‑identification and tokenisation with Youssef Mellah, PhD, Senior Data Scientist at John Snow Labs and Srikanth Kumar Rana, Solutions Architect at Databricks.

Learn how to remove, mask or transform PHI across clinical notes, tables, PDFs and DICOMs at scale, while meeting HIPAA, GDPR and CCPA standards — all without sacrificing analytical value.

Timestamps

00:00 – Welcome & Episode Overview

02:43 – How Databricks supports secure De‑identification workflows

03:50 – Built-in techniques: masking, encryption, hashing

05:26 – Introduction to Multimodal Data De-Identification

07:15 – OCR + NLP pipeline for visual & text data – PHI Extraction

08:35 – Notebook demo: PHI identification in clinical notes

12:00 – PDF de-identification

12:56 – DICOM file de-identification

14:18 – Output: consistent masking across all modalities

Listen on your favourite platform:

• YouTube: https://www.youtube.com/playlist?list=PL5zieHHAlvApZKkwtu746ivthRc5zyTiU

• ⁠⁠Apple Podcast⁠⁠: https://podcasts.apple.com/us/podcast/the-healthcare-ai-podcast/id1827098175

• ⁠⁠Spotify⁠⁠: https://open.spotify.com/show/2XNrQBeCY7OGql2jVhcP7t

• Amazon Music⁠⁠: https://music.amazon.com/podcasts/5b1f49a6-dba8-479e-acdf-9deac2f8f60e/the-healthcare-ai-podcast

Resources:

• John Snow Labs Models Hub: https://nlp.johnsnowlabs.com/models

• Spark NLP Workshop Repo: https://github.com/JohnSnowLabs/spark-nlp-workshop

• Visual NLP Workshop Repo: https://github.com/JohnSnowLabs/visual-nlp-workshop

• JSL Docs: https://nlp.johnsnowlabs.com/docs

• JSL Live Demos: https://nlp.johnsnowlabs.com/demos

• JSL Learning Hub: https://nlp.johnsnowlabs.com/learn

Connect with us:

Our website: https://www.johnsnowlabs.com/

LinkedIn: https://www.linkedin.com/company/johnsnowlabs/

Facebook: https://www.facebook.com/JohnSnowLabsInc/

X: https://x.com/JohnSnowLabs

#HealthcareAI #DataPrivacy #HIPAA #PHI #DeIdentification #MedicalAI #GDPR #HealthTech #MultimodalAI

Welcome to the first episode of The Healthcare AI Podcast, presented by John Snow Labs!

Join John Snow Labs CEO David Talby and CTO Veysel Kocaman, as they crack open the future of medicine.

They’ll reveal how state-of-the-art Healthcare AI is transforming the industry, directly comparing leading Frontier LLMs like OpenAI's GPT-4.5, Anthropic's Claude 3.7 Sonnet, and John Snow Labs’ Medical LLM.

Dive deep into critical clinical tasks, from summarization and information extraction to de-identification and clinical coding. You'll get expert insights from practicing doctors evaluating these models for factuality, relevance, and conciseness, demonstrating which AI truly delivers.

Bonus, understand the significant cost differences and learn why private, on-premise deployment is a game-changer for data privacy and compliance. You'll walk away with a deeper knowledge of the models poised to revolutionize healthcare, ensuring accuracy and compliance in your AI initiatives.

Episode Highlights & Timestamps:

0:00 - Welcome & Episode Overview

0:48 - Benchmarking Frontier LLMs & Clinical NLP

2:00 - The Competitors: OpenAI, Anthropic, AWS, Azure, Google

3:15 - Introducing John Snow Labs Medical LLMs

6:42 - Why AI Evaluation is Critical in Healthcare

9:48 - Blind Evaluation by Medical Doctors: Methodology

15:12 - Overall Preference: John Snow Labs vs. GPT-4.5 & Claude Sonnet 3.7

22:56 - Clinical Information Extraction Benchmarks

27:08 - Advanced NLP: Named Entity Recognition (NER) Deep Dive

29:53 - Assertion Status Detection: the crucial role of context (e.g., patient denies pain vs. father with Alzheimer's) and how different solutions compare in accuracy.

35:37 - Medical Coding with RxNorm: the way of mapping clinical entities to standardized terminologies and the performance metrics for RxNorm.

39:18 - The Clinical De-identification of PHI Data: the most critical privacy use case in healthcare

Connect with us:

Our website: https://www.johnsnowlabs.com/

LinkedIn: https://www.linkedin.com/company/johnsnowlabs/

Facebook: https://www.facebook.com/JohnSnowLabsInc/

Twitter: https://x.com/JohnSnowLabs