from dataclasses import dataclass
from enum import Enum
@dataclass
class Task:
benchmark: str
metric: str
col_name: str
# Select your tasks here
# ---------------------------------------------------
class Tasks(Enum):
# task_key in the json file, metric_key in the json file, name to display in the leaderboard
task0 = Task("Appendicitis", "acc", "Appendicits")
task1 = Task("Cholecystitis", "acc", "Cholecystitis")
task2 = Task("Diverticulitis", "acc", "Diverticulitis")
task3 = Task("Pancreatitis", "acc", "Pancreatitis")
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------
# Your leaderboard name
TITLE = """
MIMIC Clinical Decision Making
"""
# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
This leaderboard shows current scores of models on the MIMIC Clinical Decision Making (MIMIC-CDM) and MIMIC Clinical Decision Making Full Information (MIMIC-CDM-FI) datasets. The dataset can be found [here](https://physionet.org/content/mimic-iv-ext-cdm/). The code used to run the models can be found [here](https://github.com/paulhager/MIMIC-Clinical-Decision-Making-Framework).
"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works
## Reproducibility
To reproduce our results, here is the commands you can run:
For MIMIC-CDM, navigate to the MIMIC-Clinical-Decision-Making-Framework repository and execute:
```
python run.py pathology=appendicitis model=
python run.py pathology=cholecystitis model=
python run.py pathology=pancreatitis model=
python run.py pathology=diverticulitis model=
```
For MIMIC-CDM-FI, navigate to the MIMIC-Clinical-Decision-Making-Framework repository and execute:
```
python run_full_info.py pathology=appendicitis model=
python run_full_info.py pathology=cholecystitis model=
python run_full_info.py pathology=pancreatitis model=
python run_full_info.py pathology=diverticulitis model=
```
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@article{hager_evaluation_2024,
title = {Evaluation and mitigation of the limitations of large language models in clinical decision-making},
issn = {1546-170X},
url = {https://doi.org/10.1038/s41591-024-03097-1},
doi = {10.1038/s41591-024-03097-1},,
journaltitle = {Nature Medicine},
shortjournal = {Nature Medicine},
author = {Hager, Paul and Jungmann, Friederike and Holland, Robbie and Bhagat, Kunal and Hubrecht, Inga and Knauer, Manuel and Vielhauer, Jakob and Makowski, Marcus and Braren, Rickmer and Kaissis, Georgios and Rueckert, Daniel},
date = {2024-07-04},
}
@misc{hager_mimic-iv-ext_nodate,
title = {{MIMIC}-{IV}-Ext Clinical Decision Making: A {MIMIC}-{IV} Derived Dataset for Evaluation of Large Language Models on the Task of Clinical Decision Making for Abdominal Pathologies},
url = {https://physionet.org/content/mimic-iv-ext-cdm/1.0/},
shorttitle = {{MIMIC}-{IV}-Ext Clinical Decision Making},
publisher = {{PhysioNet}},
author = {Hager, Paul and Jungmann, Friederike and Rueckert, Daniel},
urldate = {2024-07-04},
doi = {10.13026/2PFQ-5B68},
note = {Version Number: 1.0
Type: dataset},
}
"""