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