Skip to content
View drpwchen's full-sized avatar

Block or report drpwchen

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
drpwchen/README.md

嗨,我是陳柏威 👋 Po-Wei (Paul) Chen, MD

Physiatrist (PM&R) in Hualien, Taiwan — rebuilding medicine, learning, and life with evidence + engineering.

I'm a rehabilitation physician who codes. My favorite problems live at the intersection of clinical medicine × evidence-based practice × AI knowledge workflows × self-hosting — and I share the whole process in public, failed experiments included.

  • 🏥 By day — physiatrist at Hualien Tzu Chi Hospital: musculoskeletal ultrasound, manual therapy, sports medicine
  • 🔬 By training — evidence-based medicine: meta-analysis, critical appraisal, national health-insurance database research
  • 🤖 By night — building AI-powered study & research pipelines with Claude Code, Obsidian, and a homelab

🚀 What I build

Everything here is exhaust from my real daily workflow — I build tools to use them, then open-source what survives.

Project What it does
📡 paper-radar Personal literature radar — journal/PubMed feeds → interest-scored triage site → straight into your notes. Discovery end of my paper pipeline.
⬇️ paper-fetch Publisher-aware full-text fetcher — DOI in, PDF out, via open access → publisher TDM APIs → your own institutional proxy. Download end of the pipeline.
📖 paper-review-and-digest Claude Code skills for journal-club-grade paper appraisal (deterministic GRADE + CrossRef gate) and fast content digest. Reading end of the pipeline.
🎙️ asr-benchmark Score speech-recognition models on your own audio with no ground-truth transcript — build a lexicon from your field's literature, then measure real terms captured vs hallucinated.
🔍 vault-search Local-first semantic search, related notes & RAG chat for Obsidian — plugin + MCP server over one LanceDB + Ollama index.
📝 exam-practice Self-hostable past-exam practice platform driven by FSRS spaced repetition, built for medical board prep.

✍️ Writing

I write (mostly in Traditional Chinese) about rehab medicine, AI knowledge workflows, and self-hosting at drpwchen.com — how each tool above was built, what broke along the way, and what I'd do differently.

📫 Find me

Blog Facebook LinkedIn ResearchGate

If any of these tools saved you some time, you can buy me a boba 🧋 — it keeps the homelab humming.

boba icon BUY ME A BOBA

Pinned Loading

  1. paper-radar paper-radar Public

    論文學習雷達 — a personal literature-tracking & learning radar: dozens of journal/PubMed feeds → interest-scored → private web triage → flows into your notes. Discovery end of a pipeline: pair with paper…

    Python 89 28

  2. paper-review-and-digest paper-review-and-digest Public

    Two Claude Code skills for reading one academic paper: /paper-review (journal-club appraisal, deterministic GRADE + CrossRef gate) and /paper-digest (fast content absorption). Reading end of a pipe…

    Python 29 5

  3. vault-search vault-search Public

    Local-first semantic search, Related Notes & RAG chat for your Obsidian vault — an Obsidian plugin (vault-search-obsidian) and an MCP server (vault-search-mcp) over one LanceDB + Ollama index, with…

    Python 1

  4. exam-practice exam-practice Public

    A source-available, self-hostable past-exam practice platform driven by the FSRS algorithm. Designed for medical residents and professionals to streamline board exam preparation through collaborati…

    Python 1