Now with the full set of nearly a thousand comments on the CMS RFI: joshuamandel.com/regulations....

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...

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...

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!)

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

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...

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...

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...

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

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

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!)

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...

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!

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

TFW you open the hotel stairwell door expecting dingy utility vibes and are greeted with a brilliant wall of sunlight.

Interested in using large language models to help create knowledge content? https://youtu.be/_Pk-9Hlrs0o gives a quick introduction to playgrounds, chat interfaces, notebook environments, and libraries. I use "quiz generation" as a sample task. #GPT #LLM @OpenAI

Quick demo from this week's ChatGPT-4 plugin experiment. A very simple approach to imbue with health interoperability skills via #FHIR Validator + Terminology + iterative refinement. https://youtu.be/FpT-FO41PD4 Or https://github.com/jmandel/fhir-examples-ai-plugin if you want to run it yourself!

"Cancel my cancel!" -- there is room to improve this UX :-) See https://ux.stackexchange.com/a/35756 for suggestions @support.bsky.team

For all the good vibes + acceptance here in the skeetiverse, what's with the casual ageism? Scrolling my feed this morning I stumbled over multiple replies tossing age based prejudice into conversations that weren't about age at all. From folks who surely know the ills of discrimination.

Currently do the various (not-yet-federated, independent) personal data servers each maintain their own did:plc endpoint+db? @atproto.com @atproto.bsky.social

@atproto.bsky.social I'm new here! Reading through the guides, I'm thinking the identity resolution guide might be out of date and could be updated to something like https://github.com/bluesky-social/atproto-website/compare/main...jmandel:atproto-website:patch-1 but repo permissions prevent a PR.

Goodness yes! Looking at my 10 most recently updated repo at https://github.com/jmandel?tab=repositories, ChatGPT-4 helped me with 8 of them. And probably provided critical activation energy for 5. Not to mention general knowledge, explanations, idea generation. ChatGPT-4 is *very* capable.

Hello world! Twitter has been my health tech policy place. Instagram my bread baking place. Zulip my FHIR place. What will this be? If nothing else, my first use for a decentralized identifier :-)