Skip to content
View danielchang-0's full-sized avatar
  • 18:57 (UTC -07:00)

Block or report danielchang-0

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
danielchang-0/README.md

Daniel Chang

High school student in Las Vegas. I build AI for real-world problems: medicine and education.

πŸ”¬ Research

WoundWise A small CNN that stages pressure ulcers (I-IV) from a photo. It runs on a phone, hits 92% accuracy, and beats DenseNet121, MobileNetV1, and MobileNetV2 despite being a fraction of their size.

Co-first author. Accepted for oral presentation at ICIBM 2026. πŸ† Nevada State Champion, Presidential AI Challenge 2026. Done at the Nevada Institute of Personalized Medicine, UNLV.

torchxrayvision Contributor to the open source chest X-ray deep learning library.

πŸ“± Projects

Flexeon Physical therapy app that watches you do your exercises and tells you when your form is off. Real-time pose estimation, rep counting, all on device. πŸ† Winner of the 2025 Congressional App Challenge (NV-04).

Flexeon demo

πŸ“š Other

CTO of ReadUp Youth, a literacy nonprofit. I built the reading app. We've donated $45K in books and reached 23K students.

πŸ“« Contact

danieltchang7@gmail.com

Pinned Loading

  1. mlmed/torchxrayvision mlmed/torchxrayvision Public

    TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

    Jupyter Notebook 1.2k 254

  2. flexeon flexeon Public

    AI-powered home physical therapy. Real-time pose estimation gives live form feedback, rep counting, and a skeleton overlay β€” fully on-device. πŸ† 2025 Congressional App Challenge winner.

    TypeScript

  3. WoundWise WoundWise Public

    Lightweight CNN for pressure ulcer staging (Stages I-IV) that runs on-device. 92% accuracy, outperforms DenseNet121 & MobileNetV2. Presidential AI Challenge state champion; ICIBM 2026.

    TypeScript