Now with the full set of nearly a thousand comments on the CMS RFI: joshuamandel.com/regulations....
Comment Analysis Dashboard
joshuamandel.com
Josh Mandel, MD
@josh.mandel.md
Physician, programmer, and would-be pâtissier/poet. Chief Architect for Microsoft and SMART Health IT. Health tech policy, interoperability, FHIR, AI, web.
Now with the full set of nearly a thousand comments on the CMS RFI: joshuamandel.com/regulations....
Comment Analysis Dashboard
joshuamandel.com
New live demo+deep dive! "What's next for sharing SMART Health Cards & FHIR bundles?" We explore W3C Digital Credentials API, browser-mediated presentation, & path beyond "show me your QR". Demo+Deep Dive: youtu.be/pgoaZjYMGJY Article: linkedin.com/pulse/better... Source: github/jmandell/shl...
W3C Digital Credentials Demo: SMART Health Wallet!
YouTube video by Josh Mandel
youtu.be
FHIR is evolving! I prototyped an LLM-driven analysis to diff R4 vs. R6 resources and study downstream effects on IGs like US Core. The goal: explore automated methods for spec insight. Article: linkedin.com/pulse/evalua... Output and code: github.com/jmandel/fhir...
GitHub - jmandel/fhir-diff
Contribute to jmandel/fhir-diff development by creating an account on GitHub.
github.com
Great discussion with Farzad Mostashari and the Aledade, Inc. team on applying Model Context Protocols (MCPs) for LLM-EHR interaction! We touc on data access, authorization & the future of AI in healthcare. Write-up: linkedin.com/pulse/mcp-pr... Video: youtu.be/AMPuz56qhx4 (sorry for poor audio!)
MCP for EHR: Discussion with Aledade Team
YouTube video by Josh Mandel
youtu.be
New Proposal: "MCP postMessage transport" using browser sandbox for security, privacy + zero-install MCPs. See my EHR data demo & read the proposal. Article: www.linkedin.com/pulse/mcp-yo... Video with Demo: youtu.be/_VuMRotKbV8
MCP postMessage Transport: Secure, Local AI Tools In Your Browser (Demo)
YouTube video by Josh Mandel
youtu.be
I used 50 leftover o3 credits to test ChatGPT’s vision capabilities on cryptic crossword grids. Pure vision failed; combining vision with code got there. Web app: chatgpt.com/canvas/share... Blog post: www.linkedin.com/pulse/o3-mee...
New Perspective: The EHR Association's push to remove foundational data access is misguided & harmful for health innovation. www.linkedin.com/pulse/ehr-as...
What if, instead of pre-specifying every data field and every possible workflow step, we could enable conversations between capable systems? Prior auth and beyond! youtu.be/BRX7HUBlEqw?... www.linkedin.com/pulse/conver...
Live Demo: Conversational Interop for Prior Auth (LLMs, A2A, and MCP)
YouTube video by Josh Mandel
youtu.be
Day 4: ⭐ ⭐ (*) claude.site/artifacts/f5... On Part 2, Claude took 4 code analyzer blocks to fully debug its algorithm. (It's rare in my experience that broken code gets fixed after three failed attempts, so this was a pretty impressive feat.)
New Challenge: "Advent of Claude"! Write a Claude(dot ai) custom style to solve Advent of Code puzzles within Claude's UI. Score: # adventofcode(dot com) stars earned in 2 daily conversation turns.
turkeydown: a markdown-shaped, LLM-powered prompt flow for meal prep and more 🦃 🎉 My Thanksgiving 2024 template, defining processing logic: github.com/jmandel/turk... Output including prep plan, shopping list, & full recipe set for everything we're cooking this Thursday: github.com/jmandel/turk...
Thanksgiving prep with LLMs. Here's my recipe: 0. Decide what to cook 1. Put all recipes (or dish ideas) in project context 2. Request * 4 day prep plan * All recipes with consistent formatting * All ingredients in a combined shopping list
❤️ CDC's NVSS: It's *amazing* that anyone can download 200MB .zip with ~all 3.6M USA births in 2023, including dozens of row-level attributes to answer questions like "when and how did women deliver, given specific assumptions for age, educational status, BMI?" joshuamandel.com/birth-analysis
@bsky.app feature request: include a "following back" button inline in the "New user followed you" notification screen. (Right now, new follows are grouped into a drop-down, but as you click each one to review — and follow back — the drop-down group is re-filtered and needs to be re-expanded.)
Healthcare data access vs. privacy tensions aren't zero-sum. Better-designed Health Information Networks can bend the tradeoff curve, enabling convenience AND control. No silver bullets, but real progress is possible. User stories & principles: hackmd.io/@jmandel/hin...
Princinpled (Q)HIN Design: Convenience AND Control - HackMD
All stories feature Elena, a 42-year-old marketing executive whose healthcare providers participate in AcmeConnect, a Health Information Network (HIN).
hackmd.io
ChatGPT, act as physical therapy consultant && web developer to design neck exercises, write a web app to track daily progress, & ramp up difficulty. Quick enough to complete btw boarding + takeoff to #FHIR #DevDays Output: joshuamandel.com/nexercise Chat: chatgpt.com/share/7fac01...
Whiplash Recovery Exercise Tracker
joshuamandel.com
EHI Export insight: >100 individual users (i.e., provider org staff) contributed to some aspect of my EHI in the past 6 years of ambulatory care. This diagram shows only users & tasks mentioned at least 10 times. (Task labels generated by GPT-4, based on Epic's EHI schema.)
Just out: www.nature.com/articles/s41... Health AI integration requires workflow & data access. @SMARTHealthIT experience: it takes products, pragmatics, open standards... and regulations. Better alignment & precision on "jobs to be done" => (much) faster timeframes! @mandl @gotdan
Integration of AI in healthcare requires an interoperable digital data ecosystem - Nature Medicine
Electronic health information, including from electronic health records, is needed to develop AI tools for health, but the seamless flow of data will require standards and interoperability.
nature.com
Beyond Split Pea Soup: #ChatGPT 1) assembles order sets on-the-fly from primary source 2) controls my web browser through a focused API 3) applies common sense + quantitative reasoning. A strained analogy between online grocery shopping & clinician-facing order entry. youtu.be/447C-f9MJw8
Automating EHR Order Entry, or Shopping for Split Pea Soup with ChatGPT
Beyond Split Pea Soup: #ChatGPT 1) assembles order sets on-the-fly from a primary source; 2) controls my local browser through a focused API; 3) applies sens...
youtu.be
Preview "lightning talk" I'm giving this Thursday re: hopes for AI in health interop & the role of government in getting us there. I'd love your feedback to hone this 3-minute presentation. youtu.be/umn2bPbD8SA
It was very cool to see how widely supported #JSON-LD is for recipe content. I wrote a 10 line proxy to extract this content for LLMs. For example... Source kingarthurbaking.com/recipes/mult... Extraction ld.fly.dev?url=https://...
Recipes: when I find a keeper, I condense & transcribe (in ink) on a 3x5 card. Which made me wonder... can a custom GPT come close? After 30m fiddling with prompts and proxies: yes, but you be the judge! chat.openai.com/g/g-bdnABvG9... (But you'll have to wrestle the fountain pen from my grip!)
Recipes: when I find a keeper, I condense & transcribe (in ink) on a 3x5 card. Which made me wonder... can a custom GPT come close? After 30m fiddling with prompts and proxies: yes, but you be the judge! chat.openai.com/g/g-bdnABvG9... (But you'll have to wrestle the fountain pen from my grip!)
ChatGPT - Reci-pop!
Recipe as wall of text → •🤏 short •🍬sweet (Inputs: free-text, URL from NYT/King Arthur/etc)
chat.openai.com
Deciphering Health IT regulations is like spelunking through a C codebase — federal register publishes a giant patch to the CFR; comments can be cryptic; and internally everything is pointers. Navigate wisely :-) www.healthit.gov/topic/laws-r...
Fun with #GPT-4 in hierarchical summary of US Regulations: joshuamandel.com/regview/#ful... summarizes every (sub(sub(sub)))section of ONC's "HTI-1 Final Rule" for Health Tech Interoperability (parts I-VI). It's a rough prototype but already helping me make sense of the 900+ page rule. Enjoy!
A CMS mandate went into effect in 2021 to ensure that many health plans publish their network details (Provider lists, etc) with a #FHIR API for interoperability. In 2023, things are messy and could use CMS attention. Summary in🧵 Details at hackmd.io/@jmandel/ins...
Insurance Plan Interop: A Cautionary Tale - HackMD
A CMS mandate went into effect in 2021 to ensure that health plans offer #FHIR APIs for their Provider Directory. Let’s explore how things are going.
hackmd.io
I've been pondering how #Interoperability will change as AI advances. Video: youtu.be/32a7WWMhXd0 Key Points: 1. #chatgpt4 Advanced Analysis Mode is impressive with @HL7 #FHIR data inputs... but 2. Free text can work just as well, using #GPT4 to guide on-the-fly abstraction!
Automating clinical data analysis with on-the-fly data abstraction
In this video, I explore automated capabilities for analyzing clinical data. We begin by running ChatGPT's Advanced Data Analysis tool against a FHIR Bundle,...
youtu.be
Fun with custom feeds: https://bsky.app/profile/did:plc:gr52g3xuvvdzezou433awxpw/feed/gptfeed reads your BlueSky profile, generates a list of relevant topics via GPT, and filters posts by these topics. Your feed starts empty + gains new messages as they happen. Just testing; needs a home
Test message about healthcare standards, to see if it shows up in my personal custom feed :-)
For @atproto.com team: how likely is it that high quality custom feeds can be developed / optimized without access to "client-internal" stats like dwell time, link clicks / engagements, etc?
Has someone already written a feed generator that matches user profiles to posts, using a language model to generate scores? It'd work like this... Example input: @jay.bsky.team Transcript: https://chat.openai.com/share/53e040b9-5b83-410e-8c46-3f55c990c553 Example output: Relevance 9, Quality 8