jiarui_li/DeepHealth
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
46 Commits 1 Branch 0 Tags
8316326d7e4b031b38166fc271fc1718a30d908b
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
Jiarui Li 8316326d7e Add R script to plot 1-year AUC comparisons with ggplot2 (256 vs Delphi and 120 vs Delphi)
2025-10-22 15:25:58 +08:00
.gitattributes
feat: Add training and validation data via Git LFS
2025-10-16 14:24:56 +08:00
.gitignore
feat: Add multi-GPU training and improve config/ignore
2025-10-17 14:09:34 +08:00
best_model_n_embd_120_n_layer_12_n_head_12.pt
feat: Add model checkpoints and configurations
2025-10-20 09:38:24 +08:00
best_model_n_embd_256_n_layer_16_n_head_16.pt
feat: Add model checkpoints and configurations
2025-10-20 09:38:24 +08:00
config_n_embd_120_n_layer_12_n_head_12.json
feat: Add model checkpoints and configurations
2025-10-20 09:38:24 +08:00
config_n_embd_256_n_layer_16_n_head_16.json
feat: Add model checkpoints and configurations
2025-10-20 09:38:24 +08:00
delphi_labels_chapters_colours_icd.csv
add evaluation scripts.
2025-10-18 13:26:56 +08:00
evaluate_auc.py
evaluate_auc: adapt to new utils.load_model signature (infer checkpoint from config)
2025-10-22 11:40:46 +08:00
evaluate_models.ipynb
evaluate_models.ipynb: update load_model usage to new signature (infer checkpoint from config)
2025-10-22 13:27:28 +08:00
GEMINI.md
feat: Implement time-aware GPT-2 for patient event prediction
2025-10-16 14:21:36 +08:00
LICENSE
Initial commit
2025-10-15 13:54:52 +08:00
models.py
update models and training scripts
2025-10-22 08:36:55 +08:00
plot_model_comparison_1year.R
Add R script to plot 1-year AUC comparisons with ggplot2 (256 vs Delphi and 120 vs Delphi)
2025-10-22 15:25:58 +08:00
prepare_data.py
feat: Implement time-aware GPT-2 for patient event prediction
2025-10-16 14:21:36 +08:00
README.md
Initial commit
2025-10-15 13:54:52 +08:00
requirements.txt
feat: Optimize AUC evaluation with parallel processing
2025-10-20 16:16:50 +08:00
train_ddp.py
Add train_ddp.py: DistributedDataParallel multi-GPU training with distributed samplers, rank-0 checkpointing, and aggregated metrics
2025-10-22 11:54:48 +08:00
train_iter.py
feat: Add load_model function and update training script
2025-10-18 11:07:59 +08:00
train.py
update models and training scripts
2025-10-22 08:36:55 +08:00
ukb_real_train.bin
feat: Add training and validation data via Git LFS
2025-10-16 14:24:56 +08:00
ukb_real_val.bin
feat: Add training and validation data via Git LFS
2025-10-16 14:24:56 +08:00
utils.py
utils.load_model: take only config; infer checkpoint name from config (with legacy fallback) and vocab from checkpoint
2025-10-22 11:39:10 +08:00

README.md

DeepHealth

Description
No description provided
Readme BSD-3-Clause 146 MiB
Languages
Jupyter Notebook 84.4%
Python 12.3%
R 3.3%