John Snow Labs

09/11/2026

Which medical AI models perform best when you measure what actually matters for deployment?

At Applied AI Summit 2026, David Talby, CEO of John Snow Labs, will present the keynote “The Medical AI Scorecard: Accuracy, Cost, and Responsible AI Across the Patient Journey.”

The keynote will compare medical language models with current frontier LLMs across three deployment criteria: clinical accuracy, cost at population scale, and responsible AI.

It will also look beyond individual models at the governed data foundation needed to support accurate, auditable AI agents across the patient journey.

Register now: https://hubs.li/Q04x0Js-0

Quick registration via LinkedIn: https://hubs.li/Q04x0Jrh0

Read the full speaker bio and abstract here: https://hubs.li/Q04x0Jqt0

09/10/2026

AI in lending has to make decisions in real time while meeting strict risk and regulatory requirements.

At Applied AI Summit 2026, Navneet Kumar Tyagi, Senior Software Engineer at Finance of America, will present “Designing AI-First Lending Platforms: Patterns for Real-Time Decisions, Risk, and Compliance.”

Drawing on production experience with mortgage and enterprise lending systems, the session will cover AI-enabled underwriting, automated decision workflows, explainability, model monitoring, governance, and compliance at scale.

A practical look at what it takes to architect AI for a highly regulated industry.

Register now: https://hubs.li/Q04x0HCd0

Quick registration via LinkedIn: https://hubs.li/Q04x0HGt0

Read the full speaker bio and abstract here: https://hubs.li/Q04x0HDP0

09/10/2026

Generative models become much more useful when they can operate as reliable components of a larger system.

At Applied AI Summit 2026, Nirmal Kumar Jingar, Sr. Engineering Manager at Wayfair, will present “Turning Generative Models into Reliable System Components.”

The session focuses on the engineering work required to move generative AI beyond demonstrations and into dependable production systems.

If you're working on the transition from AI prototypes to production architecture, this session will address the engineering questions that matter.

Register now: https://hubs.li/Q04x0GSZ0

Quick registration via LinkedIn: https://hubs.li/Q04x0GTF0

Read the full speaker bio and abstract here: https://hubs.li/Q04x0GQJ0

09/09/2026

What should determine whether a generative AI system is allowed to take action automatically?

At Applied AI Summit 2026, Divya Bharga, Sr. Applied Scientist, will join the conversation on practical AI reliability and governance.

The session will address questions that teams face when moving generative AI into production: when should a model act autonomously, which reliability metrics should become launch gates, and what is the minimum governance layer needed for an AI feature already in production?

These are practical questions for teams moving beyond experimentation.

Register now: https://hubs.li/Q04x0Fcs0
Quick registration via LinkedIn: https://hubs.li/Q04x0Fdp0
Read the full speaker bio and abstract here: https://hubs.li/Q04x0Fdq0

09/09/2026

How do you evaluate an AI agent when its job involves multiple turns, decisions, and actions?

At Applied AI Summit 2026, Eti Rastogi, Sr. Applied Scientist at Amazon, will tackle that question in “Beyond Vibes: Evaluation Strategies for Safe Multi-Turn AI Agents.”

The session looks at practical evaluation strategies for agents operating across multi-turn interactions, where traditional single-response metrics are no longer enough.

If you're building agentic systems, evaluation needs to account for the behavior of the entire interaction, not just the quality of one response.

Register now: https://hubs.li/Q04x0D5v0
Quick registration via LinkedIn: https://hubs.li/Q04x0D2q0

Read the full speaker bio and abstract here: https://hubs.li/Q04x0CYN0

09/08/2026

Clinical AI needs to be evaluated on more than whether an answer looks correct.

At Applied AI Summit 2026, Monica Munnangi, PhD Student at Northeastern University, will present “Towards Reliable Clinical AI: Evaluating Factuality, Robustness, and Real-World Performance of LLMs.”
Her session examines the practical challenges of evaluating LLMs for clinical use, including factuality, robustness, and performance under real-world conditions.

For anyone building or evaluating medical LLMs, these are the measures that determine whether a model is ready for practical deployment.

Register now: https://hubs.li/Q04wVzFT0

Quick registration via LinkedIn: https://hubs.li/Q04wVzJR0

Read the full speaker bio and abstract here: https://hubs.li/Q04wVzHB0

09/08/2026

At Applied AI Summit 2026, L. Raymond Guo, Assistant Professor at West Virginia University, will present “From Hallucinations to Humility: A Systematic Pipeline for Medical AI Red Teaming.”
The session focuses on systematic red teaming for medical AI, with an emphasis on identifying hallucinations and building evaluation pipelines that can expose failure modes before they reach real-world applications.
If you work on clinical AI evaluation, safety, or reliability, this is a session worth adding to your schedule.

Register now: https://hubs.li/Q04wVy0X0

Quick registration via LinkedIn: https://hubs.li/Q04wVy1y0

Read the full speaker bio and abstract here: https://hubs.li/Q04wVx_J0

09/03/2026

John Snow Labs’ AI Governance Framework conforms to 300+ laws, regulations, and industry standards worldwide, covering nine pillars including risk management, safety, privacy, transparency, fairness, and acceptable use.

The framework is built for regulated healthcare environments:
• Privacy: On-premises, private cloud, and air-gapped deployments keep data within your environment.
• Transparency: Published benchmarks and peer-reviewed research support independent evaluation.
• Fairness: LangTest provides 100+ test types for bias, fairness, robustness, toxicity, representation, and accuracy.

The result: regulatory-grade healthcare AI that is measurable, auditable, and designed for real-world deployment.

Learn more: https://hubs.ly/Q04wwmRz0

09/02/2026

EHR migrations break down at one specific point: translating medical codes across vocabularies.

You have ICD-10. The target system needs SNOMED. Or OMOP. Or UMLS. Someone has to map them - manually, at scale - error-prone and historically without a clean automated path.

The Code-to-Code Mapping feature in the Snow Labs Medical Terminology Server handles this automatically. Provide a source code. Select a target vocabulary - or let the system search across all 16+. Receive the mapped codes with their relationships in seconds.

Mappings are rule-based and curated, not inferred. The same code always maps to the same target. No hallucinated equivalences.

3-minute live UI demo in the comments.
https://hubs.li/Q04wd_FR0

Watch a live walkthrough of the Terminology Server's Concept Maps f...

09/01/2026

Before you route medical coding through a large language model, understand what you're actually getting.

An LLM generates responses. The same input can return different codes on different runs. It has no native access to ICD or SNOMED unless you explicitly provide it. Every API call incurs cost. In a regulated healthcare environment, sending clinical data to a cloud service creates compliance barriers that are hard to justify at scale.

A terminology server is a deterministic lookup engine. Enter "type 2 diabetes" today or next year: you get E11, every time - because it queries a validated, actively maintained vocabulary database. It runs on-premise, behind your firewall. One license. Unlimited lookups. No data leaving your environment.

The two tools complement each other. Use a terminology server for precise, auditable term-level mapping. Use an LLM for document-level inference on unstructured clinical notes. The strongest clinical NLP pipelines use both.

Full video breakdown in the comments.
https://hubs.li/Q04w3QWs0

ChatGPT can describe a disease — but it won't return the same ICD-1...