<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Po-Wei Chen, MD — Physiatrist &amp; Builder</title><link>https://drpwchen.com/en/</link><description>Recent content on Po-Wei Chen, MD — Physiatrist &amp; Builder</description><image><title>Po-Wei Chen, MD — Physiatrist &amp; Builder</title><url>https://drpwchen.com/og-default.png</url><link>https://drpwchen.com/og-default.png</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 25 Jul 2026 06:45:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/en/index.xml" rel="self" type="application/rss+xml"/><item><title>AI running out of gas halfway through a midnight task? I built it a fuel gauge and automatic brakes</title><link>https://drpwchen.com/en/posts/claude-pacer/</link><pubDate>Sat, 25 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/claude-pacer/</guid><description>The most common way for AI to die running tasks autonomously at night isn&amp;#39;t bad code, it&amp;#39;s hitting the usage limit and getting cut off. claude-pacer solves this with a three-layer design: a status line for humans, a budget alert for AI, and a GO/PACE/STOP verdict for agents to run. Open source MIT.</description></item><item><title>Getting started with AI agents from scratch: installing, understanding GitHub, and running your first tool</title><link>https://drpwchen.com/en/posts/getting-started/</link><pubDate>Fri, 24 Jul 2026 07:15:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/getting-started/</guid><description>You can follow along even if you&amp;#39;ve never used the command line: install Claude Code with one command, understand GitHub pages, and get your first open-source tool running and producing results.</description></item><item><title>AI Content Map</title><link>https://drpwchen.com/en/map/</link><pubDate>Fri, 24 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/map/</guid><description>The articles on this site about AI workflows aren&amp;#39;t just scattered pieces; they form a path. This map illustrates the connections between four levels and two tool pipelines (papers: discover → fetch → read; notes: produce → update → search). Hover over any node to highlight connected articles.</description></item><item><title>How I talk to AI agents: three mindsets, four meta-skills, and a rules file that shouldn't keep growing</title><link>https://drpwchen.com/en/posts/talking-to-agents/</link><pubDate>Fri, 24 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/talking-to-agents/</guid><description>Getting the tools installed is just the beginning. Three mindsets, four meta-skills you can use right away, how to write prompts now, and what belongs in each of the three layers of constraints for AI.</description></item><item><title>Too Many Notes is No Notes: The Design of note-supplement</title><link>https://drpwchen.com/en/posts/note-supplement/</link><pubDate>Thu, 23 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/note-supplement/</guid><description>My note vault has only one rule: one note per topic. If the same thing is covered in five different places, it&amp;#39;s the same as having no notes. The hard part is holding this line as sources pile up. note-supplement handles merging outside materials back into existing notes, without breaking the things you already got right.</description></item><item><title>My Complete AI Toolbox: Find the Tool for Whatever You Want to Do</title><link>https://drpwchen.com/en/posts/my-ai-toolbox/</link><pubDate>Mon, 20 Jul 2026 13:15:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/my-ai-toolbox/</guid><description>A complete list of the tools I actually use, categorized by need: AI assistants, speech-to-text, OCR, notes and knowledge base, paper tools, free website hosting, home servers and backup systems, plus the open-source scripts I wrote myself.</description></item><item><title>Cross-Textbook Automated Note-Generation Workflow: A Product of the Board Examination</title><link>https://drpwchen.com/en/posts/textbook-to-note/</link><pubDate>Sun, 19 Jul 2026 15:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/textbook-to-note/</guid><description>With over forty designated reference books for the board examination, and the same concepts scattered across multiple books, how could anyone possibly finish reading them? I tuned AI to my note-taking workflow, letting it organize textbooks structurally and with evidence. Today I open-sourced the whole setup, and this post covers the five hurdles I cleared along the way.</description></item><item><title>Do you still need to exercise at 80? An older adult stumped me, so I actually checked the textbooks</title><link>https://drpwchen.com/en/posts/talking-elders-exercise/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/talking-elders-exercise/</guid><description>After being stumped when talking about exercise with an 80-year-old adult, I broke the answer into five layers and checked textbooks and papers: walking isn&amp;#39;t enough, multicomponent exercise is needed; telling people to exercise doesn&amp;#39;t work because it uses the wrong stage of behavior change; motivational interviewing is the right tool; older adults have the right not to exercise; and gerotranscendence reminds us that living comfortably is sometimes more important than living long.</description></item><item><title>Gerotranscendence: The Body Declines, But the Mind Can Grow Richer</title><link>https://drpwchen.com/en/notes/gerotranscendence/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/notes/gerotranscendence/</guid><description>Gerotranscendence is a gerontological theory proposing that healthy aging isn&amp;#39;t just about maintaining physical function, but also involves a mindset shift: decreased fear of death and a greater focus on a few meaningful relationships. This post summarizes its three dimensions, the strength of the evidence, and its clinical boundaries.</description></item><item><title>Impaired Insight in Dementia: When the Patient Says "I'm Fine"</title><link>https://drpwchen.com/en/notes/anosognosia-dementia/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/notes/anosognosia-dementia/</guid><description>Older adults with dementia often say &amp;#34;I&amp;#39;m fine, no problem,&amp;#34; while their families are already exhausted from caring for them. This is often not stubbornness, but a neurological impairment of insight called anosognosia. This post summarizes its difference from psychological denial, its mechanisms, evaluation, and why we must always ask an extra family member during history taking.</description></item><item><title>Late-Life Depression: The Disease Easily Mistaken for "Normal Aging"</title><link>https://drpwchen.com/en/notes/geriatric-depression/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/notes/geriatric-depression/</guid><description>Late-life depression often presents as physical discomfort, lack of energy, and memory decline, making it easy to miss as normal aging or dementia. This post summarizes its atypical presentation, differentiation from dementia, specific screening tools, and the evidence for exercise as a treatment—which works just as well as medication.</description></item><item><title>Motivational Interviewing: How to Talk to People Who Don't Want to Change</title><link>https://drpwchen.com/en/notes/motivational-interviewing/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/notes/motivational-interviewing/</guid><description>The core of motivational interviewing isn&amp;#39;t persuasion, but drawing out the person&amp;#39;s own reasons for wanting to change. This post uses six steps of an interview to string together the right attitude, four tasks, listening skills, and signals of change, plus a verbatim transcript of a demonstration.</description></item><item><title>The Five Stages of Behavior Change: Why "Telling People to Exercise" Rarely Works</title><link>https://drpwchen.com/en/notes/stages-of-change/</link><pubDate>Fri, 17 Jul 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/notes/stages-of-change/</guid><description>The Transtheoretical Model divides behavior change into five stages, and the patient education required at each stage is entirely different. Throwing exercise routines at someone who hasn&amp;#39;t even thought about changing is bound to fail. This post covers the five stages, the intervention strategies for each, and the three underlying mechanisms.</description></item><item><title>The last piece of The Paper Trilogy: paper-fetch. Give it a DOI, and it fetches the full text itself</title><link>https://drpwchen.com/en/posts/paper-fetch/</link><pubDate>Tue, 14 Jul 2026 08:15:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/paper-fetch/</guid><description>To let AI read papers for you, you first need the full text. And what usually gets you stuck isn&amp;#39;t the AI—it&amp;#39;s permissions, publishers, and the library. paper-fetch uses a step-by-step route from open access, to official publisher APIs, to your own hospital library to turn a DOI into a full-text PDF, without taking any piracy routes.</description></item><item><title>My data, my benchmark: Swapping the speech recognition (ASR) engine for my lecture note system</title><link>https://drpwchen.com/en/posts/my-data-my-benchmark/</link><pubDate>Mon, 13 Jul 2026 16:31:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/my-data-my-benchmark/</guid><description>MediaTek&amp;#39;s official benchmark already proves Breeze-ASR-25 beats Whisper, but it isn&amp;#39;t testing your task. Using a 180,000-word glossary built from hundreds of textbooks as a yardstick, I found it captures 49% more real vocabulary and runs faster. Another finding not in any model card: the time alignment of the Taiwanese version, Breeze-ASR-26, has regressed. Default decoding only segments once every 30 seconds, which outright breaks when making subtitles or aligning with slides, but enabling word-level timestamps saves it. The testing method is open-sourced.</description></item><item><title>My Open-Source Tool Was Targeted by a Bot Marketer!</title><link>https://drpwchen.com/en/posts/github-bot-marketing/</link><pubDate>Thu, 09 Jul 2026 10:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/github-bot-marketing/</guid><description>My open-source paper tool received a GitHub issue full of sincere praise. After checking, I found it was automated marketing spammed by a bot to 26 repos within two minutes. This post breaks down its tactics, the paid marketplace model behind it, and why running it with your own subscription is a better deal.</description></item><item><title>I turned my journal club "paper-reading brain" into an AI skill, and forced it not to bullshit from impressions</title><link>https://drpwchen.com/en/posts/paper-tools/</link><pubDate>Tue, 07 Jul 2026 09:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/paper-tools/</guid><description>I took the entire workflow of a journal club critical appraisal and wrote it into two Claude Code skills. I even wrote two deterministic little scripts to hand over the calculation of evidence certainty and logical flaws to code, stopping the AI from bullshitting based on overall impressions. It&amp;#39;s already open-sourced on GitHub.</description></item><item><title>Exam Practice Platform: Spaced Repetition, Wrong Bank, and Score Projection</title><link>https://drpwchen.com/en/posts/exam-practice-platform/</link><pubDate>Thu, 02 Jul 2026 22:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/exam-practice-platform/</guid><description>While prepping for the PM&amp;amp;R board examination, I used an engineer&amp;#39;s approach to solve an old problem: how to practice past exam questions without forgetting them right after. I built a small tool called &amp;#34;Exam Navigator&amp;#34;, which uses FSRS to schedule spaced repetition reviews, categorizes wrong questions by failure type into a wrong bank, and can even project your score on exam day. It&amp;#39;s now open source for anyone who needs it.</description></item><item><title>I Open-Sourced My Paper Reading Radar</title><link>https://drpwchen.com/en/posts/paper-radar/</link><pubDate>Wed, 01 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/paper-radar/</guid><description>I took my clunky paper RSS setup and turned it into an online site that automatically fetches papers daily, ranks them by my interest, and learns my tastes over time. Selected papers are then automatically fetched, digested, and critically appraised. Now I&amp;#39;ve organized it into an open-source version on GitHub. Not just for medicine—any field with RSS feeds can fork it to build their own radar.</description></item><item><title>I installed a money-saving dashboard for my AI</title><link>https://drpwchen.com/en/posts/ai-token-4-budget-dashboard/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/ai-token-4-budget-dashboard/</guid><description>The final part of the saving tokens series: not everything needs the smartest brain, and even for reading images, the cheapest model is often enough. Toss noisy chores to a clone to keep your desk clean, then install a dashboard, or even let the AI watch its own usage and pace the budget just right.</description></item><item><title>If an abacus works, don't boot up the supercomputer: When to actually make AI think?</title><link>https://drpwchen.com/en/posts/ai-token-2-script-vs-llm/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/ai-token-2-script-vs-llm/</guid><description>Some jobs simply shouldn&amp;#39;t be given to AI. Clear-cut, repetitive tasks belong to hardcoded scripts—they&amp;#39;re fast, accurate, and practically free. Vague, judgment-heavy tasks are what you boot up AI for. Here&amp;#39;s how I read my medical textbook PDFs as an example of making this tradeoff.</description></item><item><title>Organizing a clean desk for the AI</title><link>https://drpwchen.com/en/posts/ai-token-3-clean-desk/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/ai-token-3-clean-desk/</guid><description>There&amp;#39;s a cost you pay with every sentence: the config file residing right in front of the AI. Keep it lean, layer the memory, make good use of prompt caching to bill repeated content at one-tenth the price, and throw away the noise of successful commands directly. A clean desk doesn&amp;#39;t just save money; the AI answers more accurately, too.</description></item><item><title>Why Does Your AI Get Slower and Dumber the Longer You Chat?</title><link>https://drpwchen.com/en/posts/ai-token-1-chat-gets-dumber/</link><pubDate>Mon, 29 Jun 2026 06:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/ai-token-1-chat-gets-dumber/</guid><description>AI has no memory. With every reply, it rereads the entire conversation from the beginning, which is why longer chats get slower, more expensive, and dumber. This post explains the mechanism using a taxi meter analogy, and gives everyone who chats with AI three ways to save that you can use today.</description></item><item><title>When AI Can Do It All, I Double-Check My Keys at Home</title><link>https://drpwchen.com/en/posts/ai-agent-secrets-audit/</link><pubDate>Sun, 28 Jun 2026 01:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/ai-agent-secrets-audit/</guid><description>After handing over permissions to read files, execute commands, and connect to the internet to an AI assistant, I went back to inventory, lock, and revoke my scattered keys and tokens, putting together a few security habits for using AI.</description></item><item><title>"Neurodynamic Solutions: Turns out my nerve exams have never been standard enough"</title><link>https://drpwchen.com/en/posts/neurodynamic-solutions/</link><pubDate>Wed, 24 Jun 2026 21:40:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/neurodynamic-solutions/</guid><description>&amp;#34;After taking Michael Shacklock&amp;#39;s two-level Neurodynamic Solutions course in Taiwan, I&amp;#39;ve put on a new pair of glasses for looking at nerve pain: standardizing nerve exams, reasoning from mechanics and anatomy, and putting evidence-based home exercises back into the hands of patients.&amp;#34;</description></item><item><title>Built a PM&amp;R Continuing Education Radar</title><link>https://drpwchen.com/en/posts/rehab-course-radar/</link><pubDate>Wed, 24 Jun 2026 07:30:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/rehab-course-radar/</guid><description>I built a website, courses.drpwchen.com, that automatically aggregates courses and announcements from 17 rehabilitation-related societies and institutions. It updates every 3 hours, supports RSS or ntfy notifications, and is free with no login required.</description></item><item><title>I turned Obsidian into a second brain that "searches notes by meaning" (and open-sourced it)</title><link>https://drpwchen.com/en/posts/obsidian-vault-search/</link><pubDate>Tue, 23 Jun 2026 17:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/obsidian-vault-search/</guid><description>Obsidian&amp;#39;s built-in search only looks for the exact words you type, but you rarely remember the words you used months ago. I cleaned up and open-sourced the &amp;#34;semantic search trio&amp;#34; I&amp;#39;ve been using for the past half-year. It&amp;#39;s completely local and MIT-licensed.</description></item><item><title>Adding graph retrieval to my medical LLM Wiki, and it actually works this time</title><link>https://drpwchen.com/en/posts/vault-graph-rag/</link><pubDate>Mon, 22 Jun 2026 15:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/vault-graph-rag/</guid><description>I threw a new paper on SQL-RAG at Claude to verify it myself: useless for a redundant textbook library, but a great fit for finding &amp;#34;related notes&amp;#34; in a sparse Obsidian medical note vault. After swapping the ranking to personalized PageRank, the proportion of correctly finding related notes jumped from 34% to 84%, and I put it straight into production.</description></item><item><title>Completing PM&amp;R Residency</title><link>https://drpwchen.com/en/posts/rehab-specialist-board-2026/</link><pubDate>Sat, 20 Jun 2026 18:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/rehab-specialist-board-2026/</guid><description>I finished the board examination last weekend and officially became a PM&amp;amp;R attending physician. Looking back at my four years of training at Hualien Tzu Chi Hospital, from Prof. Cifu&amp;#39;s reminder to &amp;#34;not be limited&amp;#34;, to getting exposure to pediatric rehab, neuro, orthopedics, musculoskeletal ultrasound, and manual therapy, and then jumping into vibe coding with Claude Code this February to redesign my study methods. Documenting this milestone, and previewing the AI learning tools I want to share next.</description></item><item><title>A Physiatrist's Learning of the DAI Osteopathy Course</title><link>https://drpwchen.com/en/posts/dai-osteopathy-course-review/</link><pubDate>Thu, 11 Apr 2024 13:23:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/dai-osteopathy-course-review/</guid><description>DAI Osteopathy is a manual therapy system developed by Dr. Kerry D&amp;#39;Ambrogio, integrating osteopathy, physical therapy, and acupuncture. Centered on systemic evaluation, gentle techniques, and &amp;#34;repeated reassessment,&amp;#34; it&amp;#39;s completely different from typical courses that only teach maneuvers. After six days of class, I actually helped a friend resolve their long-standing finger stiffness. The takeaways far exceeded my expectations.</description></item><item><title>First Time in the US, First International PM&amp;R Conference at AAP Physiatry '23</title><link>https://drpwchen.com/en/posts/aap-physiatry-23-first-trip-usa/</link><pubDate>Sun, 30 Apr 2023 13:53:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/aap-physiatry-23-first-trip-usa/</guid><description>My first time in the US and my first AAP Physiatry &amp;#39;23. The biggest shock wasn&amp;#39;t the academic content, but the energetic, complimentary culture of American physicians, alongside the diverse developments in PM&amp;amp;R like pelvic rehabilitation, AI gait analysis, and lifestyle medicine. The bar for a resident to submit a poster is much lower than you&amp;#39;d think. I highly recommend taking the plunge and attending.</description></item><item><title>[EBM] Should I calculate study power when results are not significant? Misleading post-hoc power</title><link>https://drpwchen.com/en/posts/ebm-post-hoc-power-analysis/</link><pubDate>Fri, 11 Nov 2022 09:26:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/ebm-post-hoc-power-analysis/</guid><description>Calculating post-hoc power when statistics are non-significant is actually a misleading practice: it&amp;#39;s inherently tied to the p-value. When p &amp;gt; 0.05, post-hoc power will inevitably be low—the two are basically circular reasoning. A more practical alternative is to interpret the 95% confidence interval alongside MCID, which aligns with the latest 2022 Cochrane GRADE guidelines.</description></item><item><title>ACSM-CPT Prep (Part 1): Introduction</title><link>https://drpwchen.com/en/posts/acsm-cpt-prep-1-introduction/</link><pubDate>Fri, 03 Jun 2022 12:00:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/acsm-cpt-prep-1-introduction/</guid><description>I passed the ACSM-CPT, a personal trainer certification with only a 53% pass rate in the US. As a PM&amp;amp;R resident, I took this exam to build a solid foundation in sports medicine and to force myself to study. There&amp;#39;s not much shared online about this exam, so I hope this series can serve as a reference for anyone interested.</description></item><item><title>ACSM-CPT Prep (2): Resources</title><link>https://drpwchen.com/en/posts/acsm-cpt-prep-2-resources/</link><pubDate>Fri, 03 Jun 2022 11:00:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/acsm-cpt-prep-2-resources/</guid><description>The core resources for preparing for the ACSM-CPT are the three-day course by Dr. Chia-Chih Lin, along with the CPT textbook and GETP 11th edition. For practice questions, the case studies in the official Certification Review are enough; Pocket Prep and commercially available practice exams each have their trade-offs. This post summarizes the pros, cons, and my recommendations for each resource.</description></item><item><title>ACSM-CPT Prep (Part 3): Question Trends</title><link>https://drpwchen.com/en/posts/acsm-cpt-prep-3-exam-topics/</link><pubDate>Fri, 03 Jun 2022 10:00:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/acsm-cpt-prep-3-exam-topics/</guid><description>The 135 questions on the ACSM-CPT involve almost no rote memorization. They are nearly all flexible &amp;#34;best answer&amp;#34; questions. The exam covers four domains, ranging from the details of exercise prescription to US laws like negligence and HIPAA. Being off by a single number means picking the wrong answer. In this post, I break down the question trends and things to watch out for, domain by domain, based on what I encountered.</description></item><item><title>ACSM-CPT Prep (Part 4): The Prep Process and Test Day</title><link>https://drpwchen.com/en/posts/acsm-cpt-prep-4-exam-day/</link><pubDate>Fri, 03 Jun 2022 09:00:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/acsm-cpt-prep-4-exam-day/</guid><description>It took me just 25 days from the course to the exam, with about 10 days of actual studying. This post shares a 9-step recommended prep sequence, plus the test day check-in process, whiteboard tricks, and time management, so you know exactly what to expect before you walk into the ACSM-CPT exam.</description></item><item><title>Technology Helping People with Disabilities Bridge the Gap to the World</title><link>https://drpwchen.com/en/posts/assistive-technology-disability/</link><pubDate>Wed, 31 Mar 2021 09:22:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/assistive-technology-disability/</guid><description>A patient with a high-level spinal cord injury used an eye-tracking computer to open the door to connecting with the world, all while staying humorous and cheerful. In Taiwan, we have the Icebreaker Association and MUVE using technology to help people with disabilities bridge the gap to the world, showing that disability doesn&amp;#39;t mean losing out on life.</description></item><item><title>&lt;Systematic Review Workshop&gt; Takeaway 1: Do we use PICO for diagnostic, prognostic, and harmfulness studies?</title><link>https://drpwchen.com/en/posts/systematic-review-workshop-1-pico/</link><pubDate>Thu, 13 Dec 2018 06:43:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/systematic-review-workshop-1-pico/</guid><description>PICO is actually only suitable for therapeutic studies. For diagnostic studies, change it to PIGO (adding Gold standard); for harmfulness studies, use PEO (random assignment is impossible due to ethical concerns); for prognostic studies, just PO is needed. This was the most rewarding lesson from Prof. Edwin Chan of Cochrane Singapore&amp;#39;s workshop. You need to figure out the study type before setting your keywords so your search can be precise.</description></item><item><title>Systematic Review Workshop Takeaway 2: Are Few Search Results a Sign of a Good Search Strategy?</title><link>https://drpwchen.com/en/posts/systematic-review-workshop-2-search/</link><pubDate>Wed, 12 Dec 2018 11:55:00 +0000</pubDate><guid>https://drpwchen.com/en/posts/systematic-review-workshop-2-search/</guid><description>Getting only 5 papers in your search results doesn&amp;#39;t mean your search was highly accurate—you might have missed a lot of important articles instead. When you get too many results, use title search, filter, and NOT to narrow things down; when there are too few, use MeSH terms, similar articles, or free text to broaden your criteria. Mastering the trade-off between sensitivity and specificity is the only way to find the literature you actually need.</description></item><item><title>About Me</title><link>https://drpwchen.com/en/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://drpwchen.com/en/about/</guid><description>Po-Wei Chen, MD — A physiatrist who loves manual therapy, sports medicine, self-hosted services, coding, and AI workflows. Education, publications, and course records.</description></item><item><title>Tools I Built</title><link>https://drpwchen.com/en/tools/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://drpwchen.com/en/tools/</guid><description>I took the recurring annoyances in clinical practice and studying, and wrote tools to solve them one by one. This page collects my self-built, public open-source projects: PM&amp;amp;R course radar, paper learning radar, critical appraisal and content digestion skill, question bank navigator, Obsidian semantic search plugin and MCP, and a pipeline to turn textbooks into cited notes. All source code is on GitHub.</description></item></channel></rss>