Category: Medical Informatics
-
Darth Vecdor Update: Toward a Shareable Knowledge Base Library
by Jonathan A. Handler, MD, FACEP, FAMIA Recently, I announced the free, open-source, public availability of Darth Vecdor (DV), a tool I wrote for creating graph databases (“knowledge bases” or “knowledge graphs“) using LLMs. For more info about DV, see either or both of: Or… visit the GitHub site to see more information and download…
-
Introducing Darth Vecdor: A Free, Open-Source Platform to Create Knowledge Graphs Using LLMs (such as ChatGPT)
by Jonathan A. Handler, MD, FACEP, FAMIA I Wanted a Comprehensive Medical Knowledge Graph For decades, I have hypothesized that a comprehensive medical knowledge database (aka, “knowledge base” or “knowledge graph”) would enable radical positive transformation in healthcare. I wanted a database containing relationships between concepts, like: With such a database, I imagined we could…
-
The WXP: My “Secret Weapon” Metric in Process Performance Analysis
by Jonathan A. Handler, MD, FACEP, FAMIA Introduction Throughout my professional life, I have performed analyses to assess performance related to some process or function. Whether it’s the performance of people processes, machine processes, or something else, I have found a simple metric (or set of similar metrics) that seems very often to tell me…
-
Migrating a Postgres.app database to a new major database version on MacOS
by Jonathan A. Handler, MD, FACEP, FAMIA WARNINGS AND CAVEATS This post was mostly just for me, to remember what I did when it’s time for the next major version upgrade or server move. I’m just sharing my experiences here. However, if it ends up helping someone else, great! My Requirements I took the approach…
-
Predicting Correctly Seems More Often Luck Than Skill. I’m Making Some Healthcare Predictions Anyway.
by Jonathan A. Handler, MD, FACEP, FAMIA As of this writing (2025), there are about 8 billion people in the world. Let’s say that every person guesses the likelihood that “the stock market” (let’s say the S&P 500) will be up or down from one quarter to the next. And let’s say that this is…
-
The Patient Hierarchy of Needs
by Jonathan A. Handler, MD, FACEP, FAMIA Introduction Back in 1943, a seminal work by Dr. Abraham Maslow was published describing the human hierarchy of needs. In this hierarchy, once lower level needs were adequately satisfied (i.e., basic physiologic needs like food and shelter), then higher level needs arise. In other words, people typically don’t…
-
Some ChatGPT Prompts for Exploration & Practice
by Jonathan A. Handler, MD Go to: chat.openai.com Prompt: I need to give a presentation on key issues in the quality of care for pneumonia patients. Please give me 5 options for a catchy title. Prompt:Give me 5 BRIEF bullet points for why quality of pneumonia care is important, putting the heading part in bold and…
-
Many say AI, including ChatGPT, isn’t good enough to be your doctor. We need a moonshot to change that.
Access to healthcare is a longstanding and worsening problem in the US for many. They say AI isn’t good enough to replace doctors, and if that’s right, then how will we address the supply/demand mismatch? We need a government-sponsored “moonshot” program to make great and empathetic AI doctors a reality.
-
Cali: A ChatGPT-like Clinical Baloney Detector Prototype
#ChatGPT, #PokerFace, #Columbo, #DigitalAssistants, #MedicalError, and #MedicalInformatics, all in one blog post. Plus sample code and links to a demonstration video!
-
Grimoire Entry: Importing UMLS content into PostgreSQL
by Jonathan A. Handler, MD, FACEP, FAMIA This is my first “grimoire”-type post. A grimoire is a book of magic spells. In the real world, very often I have to search all over or create a solution to complete some task, typically when doing something on a computer. Installing software under certain conditions is a…
-
The “Hard Dollar Delusion”: losing touch with the reality of “soft” dollars
Primarily because they are easier to measure, some consider “hard dollars” more “real” and therefore more likely to drive their business decisions than “soft dollars,” even when soft dollars have a greater impact on the business. As a result, business and clinical outcomes can be adversely affected.
-
A contradiction in terms: AI interoperability in healthcare
Most AI models can and will only ever be used at the institution(s) at which they were developed. The concept that an AI model is “shareable” — that a model developed at one place can be used at another — is generally a myth. This post explains why, and how the situation can be improved.
-
The Patient Empowerment Paradox… and Solution
This post describes the “Patient Empowerment Paradox,” identifies its root cause, and offers a potential solution.
-
Avoiding False Alerts: Snoozing ≠ Laziness
A simple approach can dramatically reduce false positives and annoying, redundant true negatives. Unfortunately, classic count-based metrics usually lead to the false conclusion that the approach wasn’t helpful! Our simple, novel approach solves that problem, enabling implementations with dramatically fewer false and useless alarms.
-
Shocking new discovery: Recall and Sensitivity are not the same!
Classic statistics like sensitivity and specificity make assumptions that are usually false. That leads to serious problems. Our simple, novel approach provides the solution. Imagine this: My personal library contains 100 books, 50 with red bindings and 50 with blue bindings. I hide coins inside 20 of the books. 10 of the red books each…
Zero Effectors 