Skip to content

Conversation

@aasalaz2
Copy link

@aasalaz2 aasalaz2 commented Dec 2, 2025

1. UIUC NetIDs

  • Andrew Salazar (aas15)
  • Sharon Lin (xinyiyl2)
  • Soumya Mazumder (soumyam4)

2. Contribution Type

Task

3. High-Level Description

This PR adds a new PyHealth task that enables sleep stage classification using inter-beat interval (IBI) sequences extracted from the DREAMT wearable dataset.

4. Files to Look At

New Task Implementation

  • pyhealth/tasks/dreamt_ibi_sleep_staging.py
    • Implements the DREAMT IBI sleep staging task
    • Windows the IBI signals, normalizes it, and aligns with stage labels

New Unit Test

  • tests/test_dreamt_ibi_sleep_staging.py
    • Creates dummy DREAMT-like data
    • Validates task output formats, windowing, and sample generation

How to Run Unit Tests

From the project root:

pytest tests/test_dreamt_ibi_sleep_staging.py

The test does not depend on external data and runs self-contained.

Additional Note

  • This task does not modify any existing datasets/models, so it should not affect existing PyHealth behavior.

@jhnwu3
Copy link
Collaborator

jhnwu3 commented Dec 3, 2025

Nevermind, read through deeply. Nice task submission. Will look through this later lol

@jhnwu3 jhnwu3 closed this Dec 3, 2025
@jhnwu3 jhnwu3 reopened this Dec 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants