clinicians.dev

A community of clinical experts super-powered with skills in agentic engineering. Our roots are in coding and clinical medicine. We know how to create and supervise LLMs writing Python, SQL, R, JS, HTML. We love startups, regs, policy, UI/UX, data viz, project management, informatics. We want to create the medicine of the next 100 years.

✉ Email for Slack invite → Slack → Substack ↓ Next event

today · the wire

The Wire

What you'll be asked today — and what to say back. A couple that caught my eye this morning; the rest are on the wire.

Every landmark ambient-scribe study ran at an academic medical center. Zero ran at a health center like mine.

Gigi Magan, MD · Aug 4

A safety-net physician went looking for ambient-scribe evidence from federally qualified health centers and community clinics and found none — zero studies, zero peer-reviewed accuracy data stratified by race, language, or accent. Every published trial sits at UCLA, Mass General Brigham, Emory, UCSF, Yale, UC Davis, Kaiser NorCal, Penn, or Stanford. That matters because commercial speech recognition has a documented failure gradient — a 2020 study found error rates roughly twice as high for Black speakers, with over 20% of their audio degraded past usability versus under 2% for white speakers. Measured time savings run about a minute a visit at scale; the real benefit is attention, not minutes. The patients most exposed to the failure modes are the ones missing from the evidence.

BuilderThis is a procurement clause, not an op-ed. Ask your vendor for accuracy stratified by language and accent before you sign — what contracts require, roadmaps deliver.

A Bayesian model beat the standard cardiac risk calculator 0.89 to 0.68 — using data your EHR already has

Nature · Eric Topol, Ground Truths · Aug 4

ALADYNOULLI, built on longitudinal EHR data plus polygenic risk scores across more than 683,000 patients, beat the Pooled Cohort Equation 0.89 to 0.68 on one-year coronary risk, and beat GAIL 0.783 to 0.54 on breast cancer. It spans UK Biobank, Mass General Brigham, and All of Us — 348 diseases, up to 52 years of follow-up — and models risk as signatures that update over time instead of a single static score, outperforming the code-level foundation model everyone was benchmarking against six months ago. Nothing has been validated prospectively yet, and it needs genetic data most systems don't have.

80/20The one thing that matters is the shift from "will this happen" to "when." A score you recalculate annually is a different product from a trajectory that re-routes like GPS — and your CDS layer was built for the first one.

Your patients' records leave through two doors. Only one of them is regulated.

Sam Ashoo, MD · Aug 2

Back door: health systems sell de-identified records to brokers. Front door: patients upload fully identifiable records to consumer AI products themselves — and only the back door has rules. ChatGPT Health went nationwide July 23, connecting Apple Health, Epic, and Oracle Health records, while stating it isn't intended for covered-entity use and offering no BAA — meaning uploaded records lose HIPAA protection at the door. Meanwhile Truveta aggregates 130 million-plus de-identified patients across 900-plus hospitals. The uncomfortable math: a 2019 study put correct re-identification of Americans at 99.98% from just 15 demographic attributes, and every state privacy law that matters exempts de-identified data.

SkepticWe spent fifteen years building consent workflows, then handed patients a chat box that does an end run around every one of them.

Four federal courts have now rejected insurers' attempt to relitigate arbitration losses as fraud

Wendell Potter, HEALTH CARE un-covered · Aug 4

A Georgia federal judge dismissed Elevance's RICO suit against HaloMD with prejudice — the fourth court after California, Texas, and Florida to reject insurers recasting No Surprises Act arbitration losses as fraud and racketeering. The court held it lacks jurisdiction over outcomes Congress deliberately shielded from broad review, and called a pattern of lowball offers far more plausible than a provider-arbitrator conspiracy. One case is still live in Ohio, and AHIP is arguing the roughly 85% provider win rate proves the process is broken rather than working. For revenue cycle, IDR awards are durable enough now to forecast against — a different planning assumption than a year ago.

The most credentialed founder in AI drug discovery says there's no magic wand

Daphne Koller, insitro · a16z · Aug 4

Koller's point isn't that AI is useless in drug discovery — it's that biology isn't understood well enough yet for models to shortcut it, so the compression everyone is promising doesn't have a substrate underneath it. Coming from insitro's own CEO, in the same week frontier labs are claiming mathematics breakthroughs, it's about the most useful calibration available on timelines right now.

Read the full wire ↗

learn by doing

Interactives

Companion experiences for the newsletter — don't just read about it, try it.

The Underwater Line

August 6, 2026 · Source: CMS FY 2027 IPPS/LTCH final rule (CMS‑1849‑F), Federal Register, Aug 4, 2026 · MIMI Labs · CMS Medicare Inpatient Hospitals by Geography & Service, 2023 vintage, 773 MS‑DRGs / 6,926,093 discharges / $104.1B

CMS just repealed the pathway that let an FDA Breakthrough Device designation stand in for proof of substantial clinical improvement when applying for a New Technology Add-on Payment. That reads like paperwork; it is a pricing constraint. Medicare pays one fixed amount per inpatient stay regardless of what the hospital spent — so here is every one of those 773 prices on one scatter, average payment against annual discharges, with a slider for the cost of the new thing you want to put inside the stay. At $25,000 with no add-on payment the technology costs more than the entire average Medicare payment in 620 of 773 DRGs — 88% of all fee-for-service inpatient volume; turn NTAP on at 65% and it falls to 220 DRGs and 32%. That gap is the add-on payment. Stress test: flip the axis to Charges and the red mostly vanishes — 196 DRGs below a $50,000 line by charges against 729 by payments, because the median DRG's submitted charge is 6.0× its payment. Critical lens: NTAP is computed off the hospital's cost and this file has no cost column, so the red-dot test is a ceiling test, not a margin test.

773 Prices

August 6, 2026 · Source: Mario Aguilar, STAT, “Federal regulators invite industry to closed-door meetings on clinical AI” (Aug 5, 2026) · MIMI Labs · CMS Medicare Inpatient Hospitals, 2023 vintage · CMS FY 2027 IPPS final rule

Ten companies got an unannounced demo day with FDA and CMS at White Oak on July 8, and part of the agenda was how Medicare should pay for clinical AI. This is that question, drawn. One animated field, no click-through: all 773 national MS‑DRGs arrive as a cloud, settle into a dot histogram sorted by what Medicare actually pays, the median lands at $12,714, and a technology-cost line sweeps in from $300,000 down to $25,000 while the prices that can't hold it turn red and a counter runs — 620 of 773 with no add-on payment, 220 with NTAP at 65%. Then the last act: an empty box where autonomous clinical AI would sit. No DRG, no code, no rate, 0 of 773 rungs — because when no clinician performs the service, no existing category contains it, and whoever writes the definition of “a unit of service” sets the business model for everything that follows. Critical lens: payments are not costs, fee-for-service excludes the half of Medicare in Advantage plans, and 263 of the 773 DRGs carry under 1,000 discharges a year between them — a dot is a row, not a population.

Browse all interactives →

from the substack

Builder's Briefing

The newsletter — what shipped this week, what it means, and what to build next. A couple of recent issues.

Fetal AI lifts 22 points 🤰, Your devices already run AI 🕵️, Part D comes off the drip 💧

⚡ Around the Wards

Read on Substack →

Duke built its own chart reader 🔦, ~80 AnMed sites go dark 🕳️, Being safe vs feeling safe 🤔

⚡ Around the Wards

Read on Substack →

What the Vibe

Saturday, May 30, 2026 · 12p–2p ET

Vibe coding changed everything. The barrier to building just disappeared. So what's the vibe? Is clinicians.dev dead? Does knowing how to code still matter when anyone can build? Four clinician-builders. Twelve minutes each. Show us what you made — vibe-coded, hand-coded, or somewhere in between.

Tentative speakers

Joe Izzo

First, Do No Harm — Especially With Your MVP: A CMIO's Advice in the Clinician-Builder Era

Patrick Damaso

Trajectories, Not Targets: Catching Reward-Hacked Diagnostic Reasoning One ICD Branch at a Time

Sam Wang

Silent Denials, Loud Insights: Visibility into the Payors Who Won't Show Their Work

Matt Segar

From Bedside to Buyout: An EP Fellow Path to Acquisition

4 talks (12 min each)
1:1 breakouts after each
Group discussion
Open community talk: "What the Vibe?"

RSVP on Luma →

01 · Learn

AI & agentic engineering

The foundational reads, the tools clinicians-who-code are actually using, and the loop that ships.

Context engineering — the foundation

Effective Context Engineering for AI Agents

Anthropic's foundational guide.

Building Effective Agents

When to use workflows vs. agents, and how to structure both.

2026 Agentic Coding Trends Report

How teams are actually shipping with agents.

Learn `CLAUDE.md` / `AGENTS.md`

The spec files that make agentic coding repeatable.

🔁 The Ralph Wiggum Pattern — the loop that ships. Tight spec → agent implements → you verify → adjust spec → repeat. Just keep going.

Tools of the trade

Tool	Best for	Notes
Claude Code	Complex multi-file work, architecture	Terminal-native, large context. The power tool. Good for non-code tasks too.
Cursor	Daily coding with autocomplete + inline edits	AI IDE, huge user base.
Windsurf	Budget entry, Cascade collaboration	AI-native editor.
Copilot / Codex CLI	Repo-native GitHub workflows	Tight GitHub integration.

Agentic frameworks & orchestration

CrewAI— multi-agent orchestration, clinical workflow pipelines
LangGraph— graph-based agent workflows with state
AutoGen— Microsoft's multi-agent conversation framework
MS Agent Framework 1.0— production .NET + Python
DSPy— programmatic LLM pipelines, good for clinical NLP

02 · Communities

Communities, courses, substacks

Where clinician innovators and clinician builders are hanging out.

EHRs, FHIR, fake patients

The pipes you'll need when you're actually building.

EHRs & FHIR

🔑 SMART-on-FHIR / OAuth flow — fhir.epic.com/Documentation?docId=oauth2

Clinical datasets worth knowing

From CXRs to genomes to ICU waveforms. Filter by name, modality, or license.

Name	Relevance	License
ReXGradient-160K	160k multi-site CXR + reports — vision-language radiology sandbox.	Harvard DUA, non-commercial
CheXpert Plus	Large paired CXR–report set; benchmarked in many papers.	Stanford DUA, free research
Endoscapes 2023	Open laparoscopic chole frames — segmentation / CVS detection.	CC BY-NC-SA 4.0
Surg-3M	3M surgical frames powering "SurgFM" foundation model.	TBA, expect research-only
AFRICAI Repository	Imaging sets from African centres — fairness & domain shift.	Mixed open licenses
OpenOximetry	Waveforms + skin-tone data for pulse-ox bias work.	PhysioNet credentialed
DeepLesion	32k CT slices with bounding-box lesions; detection / tracking.	NIH DUA, research-only
BioASQ Synergy 2024	Biomedical Q-A pairs — LLM eval set.	CC BY 2.5
CliniFact	Clinical-trial fact-checking corpus — fine-tune retrieval / RAG.	MIT
Hallucination Annotations	Doctor- & LLM-written discharge summaries with token-level labels.	PhysioNet credentialed
Clinical-Trial Eligibility QA	QA pairs linking MIMIC-IV to apixaban RCT criteria.	PhysioNet credentialed
PIFIR	Wearable PPG/ECG for arrhythmia-free interval prediction.	PhysioNet restricted
GREGoR R02	Rare-disease genomic + phenotypic harmonised data.	dbGaP controlled
Synthetic Rare-Disease EHRs	Benchmark synthetic EHRs for low-prevalence conditions.	CC BY
Korea4K	4k Korean genomes — ancestry diversity for variant calling.	EGA controlled
OpenNeuro	20k+ public neuro-imaging sessions; BIDS-ready.	CC0 / CC BY-SA
Bridge2AI-Voice	Multimodal speech (voice, vitals) for health AI.	PhysioNet restricted
PMDB Pain Monitoring	Wearable IMU + self-report pain diary.	CC BY 4.0
DREAMT Wearable Sleep	Apple Watch PSG pairs for sleep-staging models.	PhysioNet restricted
MC-MED	Multi-condition medical dialogue (GPT / human).	PhysioNet credentialed
Wearable Stress Dataset	Smartwatch vitals + stress labels — mental health ML.	PhysioNet restricted
MIMIC-IV v3.1	Flagship 380k-patient de-id EHR; ED + ICU tables.	PhysioNet credentialed + CITI
MIETIC	Italian clinical-notes corpus with entity spans.	PhysioNet credentialed
ODD (Opioid Behavior)	Annotated notes for opioid-related behaviour NLP.	PhysioNet credentialed
UK Biobank	500k UK adult cohort — EHR, surveys, genetics.	Controlled access
All of Us (NIH)	1M-goal US cohort — EHR, surveys, genomics, wearables.	Registered + Controlled tiers
TCGA	~11k patients across 33 cancer types — multi-omics + clinical.	Partially open
AmsterdamUMCdb	First open European ICU DB — 23k admissions.	DUA required
ADNI	Longitudinal Alzheimer's — serial MRI/PET, clinical, biomarkers.	Free non-commercial
ABCD Study	10k youths — neuroimaging, cognitive, mental health, genetic.	NIMH controlled access
NHANES (CDC)	US national survey — health, nutrition, lab data.	Public domain
CheXpert (original)	224k chest X-rays, 65k patients — labeled findings.	Free non-commercial
EchoNet-Dynamic	10k+ cardiac ultrasound videos with EF + ventricle volumes.	Non-commercial
Synthea	Realistic synthetic patient records — full EHR.	MIT
1000 Genomes	WGS from ~2,500 diverse individuals — human variation reference.	Open access
DementiaBank (Pitt)	Speech recordings + transcripts from Alzheimer's patients + controls.	Consortium access
VitalDB	6,300+ surgeries with continuous high-freq vital sign waveforms.	Open, registration + DUA
Medical Segmentation Decathlon	10 open datasets for 3D medical image segmentation.	CC BY-SA 4.0
PANDA	10k+ prostate biopsy WSIs with Gleason grades.	CC BY 4.0

05 · Conferences

AI & health conferences

Borrowed from Raihan Faroqui's healthcare AI resource guide. Filter to find your tribe.

06 · Jobs

Job boards that don't suck (as much)

What they are. Not endorsements — just the lay of the land.

jobs.heyhealthtech.com
Rock Health Capital
MDisrupt
PharmDs in IT
AMIA
General Catalyst— surprisingly good for startups
Matchday Health
Wellfound
Look for Zebras
Fractional Jobs
HealthTech Nerds Jobs

07 · Startup

So you want to build a startup

But don't know anything about tech/stack, marketing/sales, finances, management.

Life hacking / survival

Because clinician-builders need to not burn out.

09 · Experiments

LLM matrix tests (alpha)

Testing out LLMs with fake patient scenarios generated by GPTs.

Past events

Where we've been.

Fall 2025 Conference

Time	Speaker	Talk
1:00p	TBD	Welcome
1:10–1:22p	Josh Mandel, MD	Conversational Interoperability for Prior Auth and Beyond — MCP, A2A, and the Unreasonable Effectiveness of Making Data Accessible
1:35–1:47p	Jung Hoon Son, MD	Data CPR: How LLMs Revive Buried Clinical Insights
2:00–2:12p	Jason Theobald, MD	Contain Multitudes: A Docker Intro
2:25–2:37p	Calvin Johnston, MD	Software Design and Family Medicine: Overlapping skill sets
2:50p	TBD	Wrap-up

Summer 2025 Conference

Time	Speaker	Talk
1:00p	Kevin Maloy, MD	Welcome
1:10–1:22p	Vishnu Ravi, MD	Digital Health that Ships: An Open Framework You Can Use Today
1:35–1:47p	Alex Dummet, MD	Topic TBD
2:00–2:12p	Pawan Jindal, MD	Startup Survival 101: A Clinician's Guide
2:25–2:37p	Omar Usman, MD	Change Data Capture (CDC): A Defiant Approach
2:50p	Kevin Maloy, MD	Wrap-up

Fall 2024 Conference (Nov 9, 2024)

Time	Speaker	Talk
1:00p	Kevin Maloy, MD	Welcome
1:10–1:22p	Paulius Mui, MD	From 0 to 1: Becoming a Clinician Who Codes
1:30–1:42p	Brian Fung, PharmD	Path of the Clinician Engineer
1:50–2:02p	Joe Izzo, MD	The Coding CMIO — it's okay to get your hands dirty
2:10–2:22p	Karambir Khangoora, MD	Learning to Code as a Clinician: Building Medagogy
2:30–2:42p	Joey LeGrand, PharmD	One Brain Can Be Better Than Two
2:50p	Kevin Maloy, MD	Wrap-up

Podchat — Should Hospitals Mandate GenAI Training? (Aug 29, 2024)

Listen to a short podcast, then talk about whether it's right or wrong. Original from Bill Russell at This Week Health. → Meetup event

clinicians.dev

The Wire

Interactives

Builder's Briefing

What the Vibe

AI & agentic engineering

Context engineering — the foundation

Learn CLAUDE.md / AGENTS.md

Tools of the trade

Skills marketplaces

Healthcare MCPs

Agentic frameworks & orchestration

Communities, courses, substacks

EHRs, FHIR, fake patients

EHRs & FHIR

Generate fake patients

Clinical datasets worth knowing

AI & health conferences

Job boards that don't suck (as much)

So you want to build a startup

Life hacking / survival

LLM matrix tests (alpha)

Past events

Learn `CLAUDE.md` / `AGENTS.md`