FHIR MCP Server implements a complete Model Context Protocol (MCP) server, designed to facilitate seamless interaction between LLM-based agents and a FHIR-compliant backend. It provides a standardized interface that enables full CRUD operations on FHIR resources through a comprehensive suite of tools - accessible from MCP-compatible clients such as Claude Desktop, allowing users to query and manipulate clinical data using natural-language prompts.
Practical 4-module course teaching how to implement AI solutions that actually work in regulated environments. Covers everything from HIPAA compliance to building clear diagnostic tools, with real frameworks and code examples, from team who ship healthcare AI.
Whether you're an executive feeling the pressure to demonstrate AI progress, or a tech leader who needs to cut through the AI hype and deliver healthcare solutions that actually work, this masterclass provides the strategic clarity to make confident decisions while your competitors are still figuring out where to start.
Get the strategic frameworks and practical tools to make confident AI investment decisions in healthcare.
In our latest Keep IT Healthy podcast episode, we talk with Ada Andruszkiewicz, Co-Founder and COO at Talkie.ai, about a different narrative around automation in healthcare—one where AI reduces pressure, restores empathy, and absorbs the chaos instead of creating it.
What they cover:
Why healthcare is the perfect use case for voice-based AI
How Talkie.ai makes AI-patient conversations actually feel human
Their bold pivot from a horizontal AI platform to a vertical healthcare solution
Whether automation can re-humanize healthcare
The future of proactive AI agents in preventive care
I'm working on Babla, an open-source tool that helps doctors spend less time on documentation. It transcribes and structures medical conversations automatically.
What's cool is the flexibility - you can deploy it with Docker and either run it completely locally with open models for HIPAA compliance or connect to external providers. It exports to multiple formats that work with existing systems.
We just launched it as free, open-source software. Now we are looking how to make it even better.
Just launched: Our open-source medical documentation tool!
Free yourself from documentation burden. Our tool automatically transcribes and structures medical interviews, so you can focus on patients, not paperwork. Record → Click → Review → Done!
HIPAA/GDPR compliant options with local models
Multiple output formats for EHR compatibility
Simple Docker deployment for technical teams
Most medical documentation tools rely on outdated architectures that can't leverage modern AI capabilities. Legacy EHR systems weren't designed for seamless AI integration, forcing physicians to choose between documentation completeness and patient interaction.
Babla takes a fundamentally different approach by offering a dockerized, modular solution with powerful technical capabilities:
1. ASR integration pipeline that transcribes ongoing or pre-recorded medical interviews with near-real-time performance
2. Configurable LLM processing layer supporting both local models and external APIs based on your security requirements
3. Flexible output formatting from plain text to structured formats (SOAP, HL7) for interoperability with existing systems
4. Full deployment control with Docker containerization allowing for easy integration via exposed API endpoints
5. Compliance-first architecture giving you exact control over where and how patient data is processed
What makes Babla technically superior is its modular design that respects healthcare's unique requirements. Unlike cloud-based alternatives that force you to share sensitive data with third parties, Babla can run entirely on-premises with local models or connect to trusted providers of your choice.
The tool reclaims an average of 30 minutes per hour of patient consultations by handling the documentation burden automatically – all while preserving the physician's control over the final content.
We are trying to make our new tool Babla better.
Has anyone here experimented with AI-powered notetaking tools for clinical documentation? I'm curious what features you've found most useful, and more importantly, what's still missing from current solutions. Are there specific pain points in your workflow that existing tools don't address, or integration challenges with your current EHR system?
