Closed justin13601 closed 3 weeks ago
[!WARNING]
Review failed
The pull request is closed.
The recent updates enhance the clarity, functionality, and flexibility of the ACES system. Notable changes include clarifications on the index_timestamp
field, expanded support for arbitrary dataset schemas, updated installation and usage instructions, and refined task configurations. Additionally, new examples and detailed explanations for mortality prediction tasks have been added, along with improvements to predicates and window definitions in configuration files.
File(s) | Change Summary |
---|---|
README.md |
Clarified usage of index_timestamp and expanded support for arbitrary dataset schemas. |
docs/source/index.md |
Reordered information for better clarity. |
docs/source/notebooks/examples.ipynb |
Renamed sections, updated descriptions, added new examples and configurations for mortality prediction tasks. |
docs/source/usage.md |
Updated installation instructions, task configuration examples, CLI usage, results output, and Hydra configuration details. |
sample_configs/abnormal_lab.yaml |
Updated predicates section to use lab_name instead of lab for SpO2 values. |
sample_configs/imminent_mortality.yaml |
Split target window into gap and target windows with adjusted inclusivity. |
sample_configs/inhospital_mortality.yaml |
Modified gap section timing logic. |
sample_configs/long-term-incidence.yaml |
Renamed diagnosis fields and updated myocardial_infarction expression. Adjusted windows section start field. |
sample_configs/long_term_recurrence.yaml |
Introduced configuration for Long-term MI Recurrence Prediction. |
src/aces/query.py |
Modified query function to dynamically construct columns based on configuration. |
tests/test_e2e.py |
Updated task identifiers from inhospital-mortality to inhospital_mortality . |
sequenceDiagram
participant User
participant CLI
participant ACES
participant Dataset
User->>CLI: Run ACES command
CLI->>ACES: Parse task configuration
ACES->>Dataset: Extract data based on predicates
Dataset-->>ACES: Return extracted data
ACES->>ACES: Dynamically construct columns
ACES-->>CLI: Return results
CLI-->>User: Display results
In fields of code where data streams flow,
A rabbit hops with knowledge to bestow.
With timestamps set and schemas wide,
Predictions clear, no need to hide.
Mortality tasks now well-defined,
In ACES' realm, new insights you'll find.
🐇✨
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?
Summary by CodeRabbit
Documentation
index_timestamp
field in the task configuration file.examples.ipynb
with new sections and detailed configurations for mortality prediction tasks.usage.md
with enhanced installation instructions, CLI usage examples, and Hydra configuration details.Configuration Updates
abnormal_lab.yaml
to uselab_name
for SpO2 value ranges.imminent_mortality.yaml
to split thetarget
window intogap
andtarget
.inhospital_mortality.yaml
timing logic.long-term-incidence.yaml
.long_term_recurrence.yaml
for Long-term MI Recurrence Prediction.Code Enhancements
query
function to dynamically construct columns based on the configuration.Tests