jiarui_li/DeepHealth

Go to file

Jiarui Li 34d8d8ce9d Add evaluation and utility functions for time-dependent metrics

- Introduced `evaluate.py` for time-dependent evaluation of models, including data loading and model inference.
- Added `evaluation_time_dependent.py` to compute various evaluation metrics such as AUC, average precision, and precision/recall at specified thresholds.
- Implemented CIF calculation methods in `losses.py` for different loss types, including exponential and piecewise exponential models.
- Created utility functions in `utils.py` for context selection and multi-hot encoding of events within specified horizons.

2026-01-16 14:55:09 +08:00

age_encoder.py

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

backbones.py

Enhance DataLoader configuration and improve tensor transfer efficiency in Trainer class

2026-01-08 13:20:32 +08:00

dataset.py

Enhance DataLoader configuration and improve tensor transfer efficiency in Trainer class

2026-01-08 13:20:32 +08:00

embed_icd10.py

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

evaluate.py

Add evaluation and utility functions for time-dependent metrics

2026-01-16 14:55:09 +08:00

evaluation_time_dependent.py

Add evaluation and utility functions for time-dependent metrics

2026-01-16 14:55:09 +08:00

experiments.txt

Update experiments configuration: replace PiecewiseExponentialLoss with DiscreteTimeCIFNLLLoss for delphi_fork and sap_delphi models

2026-01-09 18:44:16 +08:00

field_id.txt

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

field_ids_enriched.csv

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

icd10_codes_mod.tsv

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

labels.csv

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

LICENSE

Initial commit

2026-01-07 21:27:38 +08:00

losses.py

Add evaluation and utility functions for time-dependent metrics

2026-01-16 14:55:09 +08:00

model.py

Refactor loss functions and model architecture: replace PiecewiseExponentialLoss with DiscreteTimeCIFNLLLoss, update Trainer to use SimpleHead, and modify argument parsing for new loss type.

2026-01-09 18:31:38 +08:00

prepare_data.py

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

prepare_data.R

Add loss functions and model architecture for time-to-event prediction

2026-01-07 21:32:00 +08:00

README.md

Initial commit

2026-01-07 21:27:38 +08:00

run_experiments_multi_gpu.sh

Enhance multi-GPU experiment runner: add log directory option, improve logging with sanitized filenames, and capture command output in log files.

2026-01-09 18:46:59 +08:00

train.py

Add Piecewise Exponential CIF Loss and update model evaluation for PWE

2026-01-15 11:36:24 +08:00

utils.py

Add evaluation and utility functions for time-dependent metrics

2026-01-16 14:55:09 +08:00

README.md

DeepHealth