Contextual Intelligence for Healthcare Solutions

Rethinking Epic's AI Future: A Call for Protocol-Level Innovation Bill Russell has long been a thoughtful voice in healthcare technology. A leader I respect and continue to learn from. His recent piece raises critical questions that every healthcare executive should be considering. At the heart of Bill’s argument is the Model Context Protocol (#MCP), a rapidly emerging open standard introduced by Anthropic in late 2024. MCP enables structured, secure sharing of organizational context between AI models and enterprise systems. It’s been called the USB-C of AI: a unified interface that simplifies integration across platforms. In practical terms, this means instead of building dozens of custom APIs to connect AI with data sources, organizations can connect once and scale widely. Bill rightly notes that Epic has been highly responsive to customer demand over the years, from Meaningful Use to #TEFCA to interoperability frameworks like #FHIR. But the next wave, context-aware AI, requires more than feature upgrades. It demands an architectural shift. I’m aligned with many of Bill’s observations: • MCP adoption is moving swiftly in other sectors. Financial services and software development are leveraging it to build agentic, context-rich applications. • AI-native platforms in healthcare are emerging, with built-in MCP support, that allow clinicians and analysts to create tools directly tied to real-world workflows. • Most importantly, CIOs are ready. Many are piloting AI solutions today but are held back by integration complexity, security concerns, or vendor constraints. That said, there are key tensions that must be navigated: • Security and governance cannot be compromised. Healthcare data is deeply sensitive, and any new protocol must align with the trust and safety expectations our patients and regulators demand. • Epic’s current closed-loop model was designed with auditability, traceability, and operational control in mind. Reimagining this through the lens of open context exchange requires rigorous oversight, not just technical feasibility. • And while the idea of mass customization is powerful, we must avoid fragmentation. Enabling bottom-up innovation should not come at the cost of standards or shared best practices. I believe Bill’s central thesis is directionally correct: if we want to accelerate safe, meaningful innovation in healthcare, context needs to be a first-class citizen in our AI strategies, and MCP, or something like it, could be the enabler. Epic has the data, the reach, and the infrastructure. What’s needed now is a willingness, from customers and vendor alike; to step into the next layer of interoperability: not just data exchange, but contextual intelligence at scale. As Bill points out, Epic moves when customers move. It’s time we collectively start that conversation. #HealthIT #AIinHealthcare #EpicSystems #MCP #DigitalStrategy #HealthcareLeadership #ClinicalInnovation #CxOInsights

🔗 Building the Internet of AI Agents in Healthcare Using the Model Context Protocol (MCP) 🧠 From diagnostic chatbots to standalone imaging models, traditional AI systems have lacked the interoperability and contextual awareness needed to deliver coordinated care. But a new architecture is emerging—one that mirrors how real medical teams collaborate. Enter the MCP—an open standard from Anthropic that acts like a universal adapter, connecting AI agents with tools like EHRs, genomics databases, PACS, and trial registries using standardized JSON-RPC. 🔌 MCP makes it possible to build the Internet of AI Agents in Healthcare (IoAIA): a decentralized, modular ecosystem where intelligent agents—each trained for a specific clinical role—communicate, coordinate, and act in real time. 🏗️ System Architecture: 4-Layer Agent Stack Cognitive Layer — LLM-powered agents specialized in domains like oncology, genomics, radiology Tool Layer — MCP-standardized access to clinical tools and APIs Orchestration Layer — A Care Navigator Agent manages workflows and state Execution Layer — Deployed in Colab, the cloud, or edge devices 🧬 Use Case: Multidisciplinary Cancer Care For a patient with triple-negative breast cancer, we simulate collaboration across: 🧪 Pathology → parses HER2/ER/PR/Ki-67 🖼️ Radiology → extracts tumor size via MCP-linked PACS 💊 Oncology → recommends NCCN-based treatment 🧬 Genomics → flags BRCA+ via genomics.labs.fetch 🏥 Surgery & Radiation → plan interventions 🧭 Clinical Trials → matches BRCA+ TNBC to open studies ❤️ Palliative Care → identifies behavioral and fatigue needs Each agent shares findings with the Care Navigator, which generates: ✅ A clinician-ready report ✅ A plain-language patient roadmap 💻 Google Colab Prototype: Simulating the IoAIA in Action 🔧 We’ve implemented a working prototype in Google Colab: Each agent is a Python class MCP functions are mocked (e.g., ehr.read_file, ctgov.search_trials) Agents coordinate in real-time, with explainable logs and dual reports This simulation enables: ⚡ Rapid prototyping 🧪 Safe experimentation 📚 Educational demos 📦 Foundation for real deployment #AIAgents #AIinHealthcare #MCP #Anthropic #AgenticAI #DigitalHealth 

The difference between useful AI and expensive noise in healthcare? Context. While most organizations wait for vendor roadmaps, small teams at CHOP and Stanford are solving AI's fundamental challenge: giving LLMs the clinical context they need to actually help patients. CHOP's CHIPPER - A single informaticist used Model Context Protocol to orchestrate 17 clinical tools, creating an AI assistant that understands patient history, current medications, lab trends, and clinical guidelines simultaneously. Development time? Months, not years. Stanford's ChatEHR - Embedded directly in Epic, reducing emergency physician chart review time by 40% during critical handoffs. Built by a small multidisciplinary team focused on workflow integration over feature lists. What makes this significant: → Open frameworks (MCP, SMART-on-FHIR) enable rapid innovation → Small teams with hybrid expertise move faster than large vendor projects → Context matters more than AI model capabilities → Workflow integration beats standalone AI applications The organizations building clinical context infrastructure today will have significant advantages as AI capabilities mature. #HealthcareIT #ArtificialIntelligence #ClinicalInformatics #HealthTech This non-AI-generated image is a real scene from my life. Visited with family last week and welcomed our first grandchild. Not the dog, a real grandchild, but I'm not at liberty to share pictures just yet.

Heard of Andrej Karpathy? If not, I bet you've at least heard of "𝘃𝗶𝗯𝗲 𝗰𝗼𝗱𝗶𝗻𝗴." He's the brilliant mind who coined the term! Well, he's just dropped another one, and expect to hear it a lot everywhere now: "𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴." As always, he has nailed it. So, what does this new term mean, especially for us in healthcare? Context Engineering is the meticulous art and science of ensuring the Large Language Model (LLM) gets access to the data it needs to correctly answer the question or take action. In the last few weeks, there's been a lot of buzz around "chatting" with healthcare data, especially EHRs, using LLMs. For LLMs to truly thrive and deliver reliable, safe, and effective solutions in healthcare, it's ALL about context. Without it, these powerful tools can stumble and fail where accuracy is paramount. How is it different from Prompt Engineering? As Andrej described it: "People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. In every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step." It's not just about what you ask, but what you surround that question with. Think patient history, real-time vitals, relevant clinical guidelines, and even the user's specific workflow. This can be complex, but it's the difference between an AI that "knows" and an AI that understands and acts appropriately. This is precisely why the "C" in Model Context Protocol (MCP) is so critical. MCP is designed to drive the core of robust chatbots and copilots in healthcare, providing a structured way to deliver context. Understanding Context Engineering is non-negotiable for chatbots or Copilots in healthcare. If you are wondering the difference between "chatbots" and "Copilots," check out my recent post. I shared a video demonstrating how we're building to combine context into chat-like interfaces to enable truly intelligent and actionable copilots within healthcare workflows with Epic. https://lnkd.in/g-S5H4H5 If you're navigating the complexities of making LLMs reliable partners with the right context in clinical settings,  I'd love to discuss! #AIinHealthcare