mims-harvard/Raindrop

Graph Neural Networks for Irregular Time Series

48
/ 100
Emerging

This tool helps healthcare professionals and researchers analyze health data, especially from ICU patients, or sensor data from human activity monitoring. It takes in irregularly recorded patient sensor data or activity monitor readings and outputs classifications, such as predicting sepsis, mortality, or specific physical activities. Medical and human activity researchers who work with time-series sensor data would find this useful.

219 stars. No commits in the last 6 months.

Use this if you need to classify patient conditions (like sepsis risk or mortality) or physical activities based on sensor data that is collected at inconsistent times or has missing sensor readings.

Not ideal if your data is perfectly regularly sampled or if you are not dealing with a classification task on multivariate time series.

healthcare-analytics clinical-prediction patient-monitoring human-activity-recognition irregular-time-series
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

219

Forks

47

Language

Python

License

MIT

Last pushed

Oct 04, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/Raindrop"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.