Doctors Who Code

Clinical AI Should Help Us Find the Growth Restriction Cases We Miss

Chukwuma Onyeije, MD, FACOG — Sun, 07 Jun 2026 00:00:00 GMT

Fetal growth restriction is not just an ultrasound diagnosis. It is a longitudinal data problem. Clinical AI will not replace MFM judgment, but it can help surface the pregnancies whose risk is already visible in the record.

The Lemonade Machine Problem

Chukwuma Onyeije, MD, FACOG — Tue, 02 Jun 2026 00:00:00 GMT

Automation in medicine should not be judged against an ideal clinician. It should be judged against real human variance, machine variance, supervision, and the cost of failure.

The Moment a Clinical Tool Becomes Infrastructure

Chukwuma Onyeije, MD, FACOG — Thu, 28 May 2026 00:00:00 GMT

A short introduction to a DoctorsWhoCode series on spreadsheets, tests, and retrieval as the basic discipline of physician-built clinical software.

From Excel to Python: When Your Spreadsheet Becomes a Liability

Chukwuma Onyeije, MD, FACOG — Fri, 29 May 2026 00:00:00 GMT

Excel is often the right first move for a physician-builder. The problem begins when clinical logic stays trapped in a container that can no longer safely hold it.

Why Your Clinical Calculator Needs Tests

Chukwuma Onyeije, MD, FACOG — Sat, 30 May 2026 00:00:00 GMT

A clinical calculator is not safer because it is written in code. It becomes safer when its expected behavior is explicit, checked, and protected from silent drift.

RAG Is the Bridge Between Medical Knowledge and Medical Practice

Chukwuma Onyeije, MD, FACOG — Sun, 31 May 2026 00:00:00 GMT

Clinical AI earns workflow trust only when its answers are grounded in current, local, auditable knowledge. Retrieval is not a feature. It is infrastructure.

You Are Still Prompting. You Should Be Building Agents.

Chukwuma Onyeije, MD, FACOG — Tue, 26 May 2026 00:00:00 GMT

Prompting has a ceiling. Once you hit it, you are coordinating every step manually while the AI handles individual tasks. Here is the framework and three live workflows I use to cross that line.

Burnout Is Not From Working Too Hard. It Is From Working on the Wrong Things.

Chukwuma Onyeije, MD, FACOG — Fri, 22 May 2026 00:00:00 GMT

For physician-developers, burnout often comes from low-value technical friction. The answer is not more endurance. It is better delegation to systems, automation, and agents.

Hantavirus at Sea: What the MV Hondius Outbreak Teaches Physician-Developers

Chukwuma Onyeije, MD, FACOG — Tue, 19 May 2026 16:00:00 GMT

The MV Hondius outbreak was not only a rare infectious disease story. It exposed familiar failures in travel history, triage logic, outbreak data exchange, and emergency logistics.

I Gave an AI Agent 94 Skills and Let It Help Run My Clinical, Coding, and Theology Workflows

Chukwuma Onyeije, MD, FACOG — Sun, 17 May 2026 00:00:00 GMT

Three weeks into running Hermes Agent in production, I can say this: the real value is not the model. It is the workflow ecosystem wrapped around it. Here is what 94 specialized skills looks like in a real physician-developer stack.

The Architecture Behind My 24/7 AI Operations Partner

Chukwuma Onyeije, MD, FACOG — Sun, 17 May 2026 00:00:00 GMT

The model is not the product. The workflow is the product. Here is a technical look at the production stack behind a physician-built AI operations partner: Docker, Traefik, model failover, rate limits, logs, HIPAA boundaries, and the failure modes I watch for every week.

Dead Weight: What a 1970 Cardiology Textbook Taught Me About the Future of Clinical Evidence

Chukwuma Onyeije, MD, FACOG — Fri, 08 May 2026 00:00:00 GMT

A half-century-old textbook on congenital heart disease. A chapter on Ebstein's anomaly. A comparison that changed how I think about evidence, AI, and what we owe the next generation of physicians.

The Jetsons Problem in Clinical Medicine

Chukwuma Onyeije, MD, FACOG — Tue, 05 May 2026 10:50:00 GMT

Artificial intelligence in clinical medicine promises abundance. The real risk is not too little data, but too little agency, attention, and equity.

Fluent Answers Are Not Clinical Judgment

Chukwuma Onyeije, MD, FACOG — Mon, 01 Jun 2026 00:00:00 GMT

Language models can make uncertain medical information sound finished. The problem is not fluency. The problem is mistaking fluency for accountable clinical reasoning.

Journals Are Becoming Infrastructure

Chukwuma Onyeije, MD, FACOG — Mon, 01 Jun 2026 00:00:00 GMT

Medical journals are no longer only read by clinicians. They are becoming upstream inputs to AI systems. That makes provenance, evidence hierarchy, and distribution part of clinical infrastructure.

The Search Box Is Disappearing

Chukwuma Onyeije, MD, FACOG — Mon, 01 Jun 2026 00:00:00 GMT

Medicine is moving from retrieval to synthesis. That changes the physician's work from finding information to judging synthesized information under clinical pressure.

Fatigue, Failure, and the Data That Brought Me Back

Chukwuma Onyeije, MD, FACOG — Wed, 27 May 2026 00:00:00 GMT

After six weeks of missed training, my PGIS morning check-in revealed what a GPS watch alone never shows: glycemic and autonomic recovery run on entirely different clocks.

Building the Physician's Knowledge Flywheel

Chukwuma Onyeije, MD, FACOG — Mon, 25 May 2026 00:00:00 GMT

Why the vault gets exponentially more valuable the more you use it. The long-game thesis: this is the clinical infrastructure that vendors cannot build.

My Slides Became Code: Why I Use Marp for AI-Generated Presentations

Chukwuma Onyeije, MD, FACOG — Mon, 25 May 2026 00:00:00 GMT

Marp lets physician-builders turn reviewed knowledge into version-controlled, AI-assisted teaching decks without surrendering clinical responsibility.

AI Agents Do Not Replace Software Fundamentals. They Expose Whether You Have Any.

Chukwuma Onyeije, MD, FACOG — Fri, 22 May 2026 00:00:00 GMT

For physician-builders, agentic engineering is not prompt magic. It is bounded context, vertical slices, observability, and accountability.

The Thinking Partner Commands Every Physician Should Build

Chukwuma Onyeije, MD, FACOG — Mon, 18 May 2026 00:00:00 GMT

Slash commands that replace the morning literature review. /challenge, /emerge, /connect, /close-clinic, /graduate: clinical reasoning augmentation, not automation.

Codex on Mobile Solves the Async Doctor Problem

Chukwuma Onyeije, MD, FACOG — Fri, 15 May 2026 13:00:00 GMT

OpenAI bringing Codex into the ChatGPT mobile app is not about coding on a phone. It is about supervising agentic work when your clinical day refuses to give you uninterrupted time.

The Physician's Stack: Obsidian + Claude Code + Local LLM

Chukwuma Onyeije, MD, FACOG — Mon, 11 May 2026 00:00:00 GMT

How to build a clinical knowledge vault without sending patient data to anyone's server. The two-vaults architecture, ingestion workflows, and the HIPAA-first policy.

What Karpathy Actually Built (and Why It Matters for Medicine)

Chukwuma Onyeije, MD, FACOG — Mon, 04 May 2026 00:00:00 GMT

The compilation analogy, explained for clinicians. How LLM Wiki compiles clinical knowledge into synthesized entity pages instead of re-retrieving chunks on every query.

The Physician's Second Brain: A 5-Post Series

Chukwuma Onyeije, MD, FACOG — Mon, 27 Apr 2026 00:00:00 GMT

A complete guide to building an LLM-powered clinical knowledge vault. Why existing PKM failed physicians, how to build one that works, and why this is the infrastructure layer physicians must own.

The PKM System That Was Never Built for You

Chukwuma Onyeije, MD, FACOG — Mon, 27 Apr 2026 00:00:00 GMT

Why every personal knowledge management app failed physicians specifically, and why Karpathy's April 2026 LLM Wiki changes everything.

The Map Has Blind Spots

Chukwuma Onyeije, MD, FACOG — Sun, 26 Apr 2026 00:00:00 GMT

Move 37 was not a parlor trick. It was a warning. Physician-developers need to be ready for the moment AI starts finding medically important patterns our inherited maps never taught us to see.

AI Just Outperformed Physicians at Clinical Writing. This Should Not Surprise You.

Chukwuma Onyeije, MD, FACOG — Fri, 24 Apr 2026 00:00:00 GMT

HealthBench Professional shows AI has already crossed the threshold in clinical writing and documentation. The real lesson is not replacement. It is that physician-developers need to build the harness.

When AI Told a Dying Man What He Wanted to Hear

Chukwuma Onyeije, MD, FACOG — Thu, 23 Apr 2026 00:00:00 GMT

Joe Riley trusted AI over his oncologist and died of a treatable cancer. His tragedy wasn't naivety — it was earned distrust, amplified by a machine that had no way to know the difference.

The PDF Wall: Why Your Clinical RAG Keeps Hallucinating

Chukwuma Onyeije, MD, FACOG — Wed, 22 Apr 2026 00:00:00 GMT

Your clinical RAG system is not hallucinating because the model is bad. It is hallucinating because your document pipeline is broken. Here is what clinical PDF parsing actually requires, and why Docling is the fix.

Deployment: When Your Code Becomes Clinical Reality

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:09:00 GMT

An app on your laptop helps no one. Deployment is the step where physician-developer work finally becomes available to patients, colleagues, and clinics.

Postgres and Prisma: Where the Data Actually Lives

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:08:00 GMT

Clinical software becomes real when it remembers. This is the database layer that turns a one-off calculator into a longitudinal tool.

Tailwind CSS: Design Without Asking a Designer

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:07:00 GMT

Patients do not trust ugly calculators. Tailwind helps physician-developers build interfaces that feel clean, credible, and ready to use.

Astro: Building Fast, Clinical-Grade Websites Without the Bloat

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:06:00 GMT

Physician-developer projects are usually content-first. Astro fits that shape by shipping less JavaScript, faster pages, and cleaner performance by default.

MDX: Where Writing Meets Code

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:05:00 GMT

Most physician writing dies in static documents. MDX turns clinical education into living pages that can explain, calculate, and update in one file.

AI-Assisted Coding: Your Second Pair of Hands

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:04:00 GMT

Claude Code, Cursor, and Copilot do not replace judgment. They compress the feedback loop for physician-developers who still read every line before they ship.

Python: The Language of Clinical Data

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:03:00 GMT

JavaScript runs in the browser. Python runs behind the workflow, where lab values, CSV exports, data cleaning, and clinical models actually live.

TypeScript: Because a Misplaced Decimal Can Hurt a Patient

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:02:00 GMT

Clinical software cannot afford vague inputs. TypeScript gives physician-developers safer contracts, clearer data shapes, and fewer silent failures.

JavaScript: The Language Your Patients Already Run

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:01:00 GMT

Every patient portal, tablet consent form, and browser-based clinical tool already runs JavaScript. This is where physician-developers start changing what medicine feels like on a screen.

The Physician-Developer's Stack: Nine Tools. One Doctor. A Workflow That Actually Ships.

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 13:00:00 GMT

A practical 10-part Doctors Who Code series for physicians who want to build and ship clinical tools with the modern web stack, from JavaScript to deployment.

Deep Work for Physicians: Protecting the Cognitive Core of Medicine

Chukwuma Onyeije, MD, FACOG — Sun, 19 Apr 2026 00:00:00 GMT

Deep work is not a productivity hack for doctors. It is a clinical safety issue, a training issue, and a systems design issue. Physicians need to protect deep thinking and automate the shallows.

The Human Bottleneck: Why Medicine's Agentic Future Is Waiting on Us

Chukwuma Onyeije, MD, FACOG — Thu, 16 Apr 2026 00:00:00 GMT

AI agents are 50x faster than humans, but medicine only captures a fraction of that speed. The real bottleneck in agentic AI is not the technology — it is human capacity, clinical oversight, and workflows built for the wrong consumer. A physician-developer's perspective.

The Local Advantage: Why Physician-Developers Should Build on Local LLMs Instead of Consumer AI

Chukwuma Onyeije, MD, FACOG — Wed, 15 Apr 2026 00:00:00 GMT

Consumer AI tools like ChatGPT and Claude are useful. But a physician-developer who deploys a locally fine-tuned model on controlled infrastructure has something more powerful: a clinical tool that learns your practice, respects your data, and costs less at scale.

Clinical Documentation Automation Should Remove Friction, Not Replace the Doctor

Chukwuma Onyeije, MD, FACOG — Fri, 10 Apr 2026 00:00:00 GMT

Documentation automation is not a typing solution. It is a workflow design problem. For physicians and physician-developers, the real goal is protecting clinical judgment from administrative drag.

I Built PGIS Recipes Because Food Systems Need Architecture

Chukwuma Onyeije, MD, FACOG — Thu, 09 Apr 2026 00:00:00 GMT

PGIS Recipes started as a stack of Marp slide decks. I turned it into a GitHub Pages library because nutrition guidance only compounds when the delivery system is structured, durable, and easy to revisit.

Why Doctors Should Learn to Code

Chukwuma Onyeije, MD, FACOG — Tue, 07 Apr 2026 00:00:00 GMT

Not to become programmers. To become the kind of physician who can close the gap between a clinical insight and a working solution.

Doctors Who Code: Build Systems, Not Just Models

Chukwuma Onyeije, MD, FACOG — Thu, 02 Apr 2026 00:00:00 GMT

A TEDx pitch says physicians should build AI. I agree. But the work that matters is governance, validation, and delivery, not one-afternoon demos.

Inbox to Insight: Building the DoctorsWhoCode Engine

Chukwuma Onyeije, MD, FACOG — Wed, 01 Apr 2026 00:00:00 GMT

Physicians do not have an information problem. We have a conversion problem. Inside the Telegram-driven research engine I built to turn links, papers, transcripts, and videos into drafts, PDFs, and durable editorial records.

Doctors Who Code: From GitHub to Medical AI

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 14:10:00 GMT

A practical path for physicians who want to move from GitHub basics to building real medical AI projects.

Your First Medical AI Project on GitHub: How to Choose One You Will Actually Finish

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 14:00:00 GMT

Most physician-developers never ship their first AI project. The problem is not skill. It is scope. Here is a framework for choosing a project that lands.

Navigating Medical AI on GitHub: What Is Worth Your Time

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:50:00 GMT

There are thousands of medical AI repositories on GitHub. Most are abandoned, half-built, or unreproducible. Here is how to find the ones that actually work.

JSON for Physicians: The Structured Data Your Clinical AI Actually Needs

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:40:00 GMT

A physician's guide to JSON, FHIR JSON, and structured clinical data for APIs, interoperability, and medical AI.

Three GitHub Projects Physicians Can Actually Finish

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:30:00 GMT

Most physician-developer projects fail not because the ideas are bad but because the first build is too large. Here are three that are sized to finish.

Your First Week on GitHub as a Physician: A Practical Starter Plan

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:20:00 GMT

Not a tutorial on becoming a developer. A seven-day plan for a busy physician to go from zero to a real project in a repository they will actually return to.

GitHub for Physicians: Why Version Control Changes How You Build

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:10:00 GMT

Most physician-developers lose code the same way: no backups, no history, no way to recover. Here is why version control matters.

Stop Lurking: Why Physicians Should Start GitHub Before They Feel Ready

Chukwuma Onyeije, MD, FACOG — Tue, 31 Mar 2026 13:00:00 GMT

Most physicians assume GitHub is for real developers. That assumption is costing medicine. Here is why the barrier is not skill, and what to do instead.

The Referral System Is Broken for the Same Reason the Triage Line Is Broken

Chukwuma Onyeije, MD, FACOG — Sun, 29 Mar 2026 00:00:00 GMT

Nobody lost your fax. The system was designed to lose it. Referral failures are not clerical accidents. They are the predictable result of clinical infrastructure built for a different era.

When Medical Algorithms Code Racism Into Patient Care

Chukwuma Onyeije, MD, FACOG — Sun, 29 Mar 2026 00:00:00 GMT

Race-based clinical algorithms in kidney care and obstetrics did not just reflect bias. They operationalized it. Physicians now have a responsibility to challenge the software, logic, and architecture that turn racial fiction into patient harm.

I Built InboxDetox in Two Evenings — This Is What Disposable Software Looks Like

Chukwuma Onyeije, MD, FACOG — Fri, 27 Mar 2026 00:00:00 GMT

InboxDetox is an AI-powered email unsubscribe manager built in two evenings and deployed to Railway. It is on GitHub. Take it.

Demystifying Digital Medicine Coding -- A Physician-Developer's Guide to Sustainable Telehealth Workflows

Chukwuma Onyeije, MD, FACOG — Thu, 26 Mar 2026 00:00:00 GMT

A practical breakdown of 2025 CPT telehealth codes, RPM billing thresholds, and the workflow engineering required to make digital medicine financially sustainable.

Your Patients Are Already Using ChatGPT to Decide Whether to Call You

Chukwuma Onyeije, MD, FACOG — Tue, 24 Mar 2026 00:00:00 GMT

They are not asking it for fun. They are asking it because the triage line puts them on hold for 45 minutes. The threat is not the technology. The threat is the system that made the technology necessary.

The EHR Vendor Wants You to Stay a Consultant

Chukwuma Onyeije, MD, FACOG — Mon, 23 Mar 2026 00:00:00 GMT

Physician passivity in health tech is not an accident. It is a business model. Understanding the structural incentives is the first step to building outside of them.

Logs Before Intelligence: Why Data Discipline Must Precede AI Insight

Chukwuma Onyeije, MD, FACOG — Mon, 23 Mar 2026 00:00:00 GMT

Before you build any AI feature, you must first build the log. The principle every physician-developer needs to internalize before writing a single line of intelligence code.

Your First Build Does Not Have to Save Lives

Chukwuma Onyeije, MD, FACOG — Sun, 22 Mar 2026 00:00:00 GMT

Every physician who codes started somewhere that had nothing to do with clinical AI. The first build is about identity formation, not impact. Here is why that distinction matters, and where to actually start.

The Limits of Viability: What Patients Find Before They Find You

Chukwuma I. Onyeije, MD, FACOG — Sun, 22 Mar 2026 00:00:00 GMT

When families face periviability, they search before they call. What they find shapes everything. Here is why physician-developers have a responsibility to build better.

When the Algorithm Fails, Who Answers for It?

Chukwuma Onyeije, MD, FACOG — Fri, 20 Mar 2026 00:00:00 GMT

Every physician using an AI tool has heard the liability question. Most of us answer it wrong. The real answer is not about insurance. It is about who was in the room when the tool was designed.

Augmented Intelligence Is a Physician Problem. That Makes It a Physician-Developer Opportunity.

Chukwuma Onyeije, MD, FACOG — Thu, 19 Mar 2026 00:00:00 GMT

The AMA opened the door. Physicians must decide what to do with it. The survey data is not a comfort. It's a challenge. Here's what physician-developers do next.

Skill Loss Is the Wrong Fear. Here's the Right One.

Chukwuma Onyeije, MD, FACOG — Wed, 18 Mar 2026 00:00:00 GMT

88% of physicians fear AI will erode their clinical instincts. That fear is real but misdirected. The greater risk is intellectual dependency on systems we didn't build and cannot interrogate.

The AMA Is Right About Augmented Intelligence — They're Wrong About Who Should Build It

Chukwuma Onyeije, MD, FACOG — Tue, 17 Mar 2026 00:00:00 GMT

The AMA's 2026 survey shows 81% of physicians now use AI in practice. But read the fine print. Physicians want a seat at the table. The best way to earn that seat is to be the person who wrote the code.

I Ditched Headless WordPress for Astro — Here's Why a Physician-Developer Should Too

Chukwuma Onyeije, MD, FACOG — Mon, 16 Mar 2026 00:00:00 GMT

After spending a day fighting a WordPress plugin that wouldn't respect a domain change, I rebuilt DoctorsWhoCode.blog from scratch with Astro and MDX. The migration took one afternoon. The clarity was immediate.

From the ICU to the Marathon Course: What AI-Driven Glycemic Control Teaches Us About Athletic Performance

Dr. Chukwuma Onyeije — Mon, 16 Mar 2026 00:00:00 GMT

A physician-developer explores the powerful parallels between AI-driven glycemic control in the ICU and metabolic management for endurance athletes with Type 2 diabetes, introducing the Performance Glycemic Intelligence System (PGIS) as a real-world n-of-1 framework.

I Didn't Download an App. I Described My Problem to an AI and It Built One for Me.

Chukwuma Onyeije, MD, FACOG — Mon, 16 Mar 2026 00:00:00 GMT

A Maternal-Fetal Medicine specialist describes how his personal AI health system identified low HRV, recommended breathing exercises, and prompted him to build a custom evidence-based breathing app in a single afternoon. A case study in disposable software, physician agency, and the future of personal health technology.

The Protocol-to-Website Industrial Complex:

Chukwuma Onyeije, MD, FACOG — Sun, 15 Mar 2026 00:00:00 GMT

By Dr. Chukwuma Onyeije, MD, FACOG | Maternal-Fetal Medicine Specialist & Medical Director, Atlanta Perinatal Associates

PGIS — Performance Glycemic Intelligence System

Chukwuma Onyeije, MD, FACOG — Wed, 11 Mar 2026 00:00:00 GMT