Add ICU Mortality Prediction Task#963
Open
Jils-Patel wants to merge 1 commit intosunlabuiuc:masterfrom
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Contributors: Jils Patel (jilsp2), Jenish Patel (jenishp2), Chethan Kalvakuri (chethan5)
Type of Contribution: Standalone Task
Link to Original Paper:
Robust Real-Time Mortality Prediction in the Intensive Care Unit using Temporal Difference Learning
https://raw.githubusercontent.com/mlresearch/v259/main/assets/frost25a/frost25a.pdf
https://arxiv.org/pdf/2411.04285
High Level Description of Implementation: This PR adds a standalone task for ICU mortality prediction based on Frost et al. (2024), which uses Temporal Difference learning with Semi-Markov state representations. The task processes MIMIC-IV lab measurements into 5-tuple states {value, timepoint, feature_index, delta_value, delta_time} and generates binary mortality labels at 1, 3, 7, 14, and 28-day horizons. Includes full test coverage using synthetic data and an ablation example script.
Files to Review:
docs/api/tasks.rst
docs/api/tasks/pyhealth.tasks.TDICUMortalityPredictionMIMIC4.rst
examples/mimic4_td_icu_mortality_cnnlstm.py
pyhealth/tasks/init.py
pyhealth/tasks/td_icu_mortality_prediction.py
tests/test_td_icu_mortality_prediction.py