Uploading README
Browse files
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- tabular-regression
|
5 |
+
- ehr
|
6 |
+
- transformer
|
7 |
+
- medical
|
8 |
+
model_name: audit-icu-gpt2-25_3M
|
9 |
+
---
|
10 |
+
# audit-icu-gpt2-131_6M
|
11 |
+
|
12 |
+
This repo contains the model weights for audit-icu-gpt2-131_6M, a tabular language model built on the gpt2 architecture
|
13 |
+
for evaluating the cross-entropy of Epic EHR audit log event sequences. This model was originally designed to
|
14 |
+
calculate cross-entropies but can also be used for generation.
|
15 |
+
|
16 |
+
The code to train and perform inference this model is available [here](https://github.com/bcwarner/audit-log-lm).
|
17 |
+
More details about how to use this model can be found there.
|
18 |
+
|
19 |
+
# Model Details
|
20 |
+
|
21 |
+
More details can be found in the model card of our paper in Appendix B [here](https://arxiv.org/abs/2311.06401).
|
22 |
+
|
23 |
+
Please cite our paper if you use this model in your work:
|
24 |
+
```
|
25 |
+
|
26 |
+
@misc{warner2023autoregressive,
|
27 |
+
title={Autoregressive Language Models For Estimating the Entropy of Epic EHR Audit Logs},
|
28 |
+
author={Benjamin C. Warner and Thomas Kannampallil and Seunghwan Kim},
|
29 |
+
year={2023},
|
30 |
+
eprint={2311.06401},
|
31 |
+
archivePrefix={arXiv},
|
32 |
+
primaryClass={cs.CL}
|
33 |
+
}
|
34 |
+
|
35 |
+
```
|