cehrgpt 0.0.1__tar.gz

cehrgpt-0.0.1/.github/workflows/build-python.yaml

@@ -0,0 +1,93 @@
+name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
+
+on: push
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.x"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/cehrgpt  # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: >-
+      Sign the Python 🐍 distribution 📦 with Sigstore
+      and upload them to GitHub Release
+    needs:
+    - publish-to-pypi
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write  # IMPORTANT: mandatory for making GitHub Releases
+      id-token: write  # IMPORTANT: mandatory for sigstore
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Sign the dists with Sigstore
+      uses: sigstore/gh-action-sigstore-python@v3.0.0
+      with:
+        inputs: >-
+          ./dist/*.tar.gz
+          ./dist/*.whl
+    - name: Create GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      run: >-
+        gh release create
+        '${{ github.ref_name }}'
+        --repo '${{ github.repository }}'
+        --notes ""
+    - name: Upload artifact signatures to GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      # Upload to GitHub Release using the `gh` CLI.
+      # `dist/` contains the built packages, and the
+      # sigstore-produced signatures and certificates.
+      run: >-
+        gh release upload
+        '${{ github.ref_name }}' dist/**
+        --repo '${{ github.repository }}'

cehrgpt-0.0.1/.github/workflows/tests.yaml

@@ -0,0 +1,39 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Tests
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.10.0
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest
+        pip install -e .
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        PYTHONPATH=./: pytest

cehrgpt-0.0.1/.gitignore

@@ -0,0 +1,38 @@
+.DS_Store
+.idea/
+.vscode/
+venv*
+dist/*
+
+*ipynb_checkpoints/
+*h5
+*logs
+*nohup.out
+*ipynb
+
+*__pycache__/
+.eggs/
+*.dat
+.metastore_db/
+
+src/cehr-bert/evaluations/hospitalization_baseline.py
+src/cehr-bert/evaluations/hospitalization_prediction-new-data-generator.py
+hospitalization_baseline.py
+hospitalization_prediction-new-data-generator.py
+build/
+concept_embeddings.egg-info/
+
+src/cehr-bert/runner/*yaml
+
+*.out
+*.egg-info/
+
+cehr_transformers.egg-info/dependency_links.txt
+cehr_transformers.egg-info/PKG-INFO
+cehr_transformers.egg-info/requires.txt
+cehr_transformers.egg-info/SOURCES.txt
+cehr_transformers.egg-info/top_level.txt
+
+test_data
+test_dataset_prepared
+test*results

cehrgpt-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,83 @@
+# For documentation on pre-commit usage, see https://pre-commit.com/
+# This file should be updated quarterly by a developer running `pre-commit autoupdate`
+# with changes added and committed.
+# This will run all defined formatters prior to adding a commit.
+default_language_version:
+  python: python3  # or python3.10 to set a specific default version
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+
+  - repo: https://github.com/DanielNoord/pydocstringformatter
+    rev: 'v0.7.3'
+    hooks:
+      - id: pydocstringformatter
+
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.2.0
+    hooks:
+      - id: autoflake
+
+  - repo: https://github.com/psf/black
+    rev: '24.1.1'
+    hooks:
+      - id: black
+        # It is recommended to specify the latest version of Python
+        # supported by your project here, or alternatively use
+        # pre-commit's default_language_version, see
+        # https://pre-commit.com/#top_level-default_language_version
+        # Pre-commit hook info from: https://black.readthedocs.io/en/stable/integrations/source_version_control.html
+        # Editor integration here:  https://black.readthedocs.io/en/stable/integrations/editors.html
+
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: "v1.12.1"  # replace with latest tag on GitHub
+    hooks:
+      - id: blacken-docs
+        additional_dependencies:
+          - black>=22.12.0
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: 'v4.5.0'
+    hooks:
+      - id: trailing-whitespace
+        exclude: .git/COMMIT_EDITMSG
+      - id: end-of-file-fixer
+        exclude: .git/COMMIT_EDITMSG
+      - id: detect-private-key
+      - id: debug-statements
+      - id: check-json
+      - id: pretty-format-json
+      - id: check-yaml
+      - id: name-tests-test
+      - id: requirements-txt-fixer
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: 'v1.10.0'
+    hooks:
+      # - id: python-no-eval
+      - id: python-no-log-warn
+      - id: python-use-type-annotations
+
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.4
+    hooks:
+      - id: remove-crlf
+      - id: remove-tabs  # defaults to: 4
+        exclude: .git/COMMIT_EDITMSG
+
+  - repo: https://github.com/PyCQA/isort.git
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: [ "--profile", "black" ]
+
+  - repo: https://github.com/PyCQA/bandit
+    rev: '1.7.7'
+    hooks:
+      - id: bandit
+        args: ["--skip", "B101,B106,B107,B301,B311,B105,B608,B403"]

cehrgpt-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Department of Biomedical Informatics
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cehrgpt-0.0.1/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.2
+Name: cehrgpt
+Version: 0.0.1
+Summary: CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines
+Author-email: Chao Pang <chaopang229@gmail.com>, Xinzhuo Jiang <xj2193@cumc.columbia.edu>, Krishna Kalluri <kk3326@cumc.columbia.edu>, Elise Minto <em3697@cumc.columbia.edu>, Jason Patterson <jp3477@cumc.columbia.edu>, Nishanth Parameshwar Pavinkurve <np2689@cumc.columbia.edu>, Karthik Natarajan <kn2174@cumc.columbia.edu>
+License: MIT License
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cehrbert==1.3.3
+Requires-Dist: openai==1.54.3
+Requires-Dist: optuna==4.0.0
+Requires-Dist: transformers==4.40.0
+Requires-Dist: tokenizers==0.19
+Requires-Dist: trl==0.11.4
+Provides-Extra: dev
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-subtests; extra == "dev"
+Requires-Dist: rootutils; extra == "dev"
+Requires-Dist: hypothesis; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Provides-Extra: flash-attn
+Requires-Dist: flash_attn; extra == "flash-attn"
+
+# CEHRGPT
+
+[![PyPI - Version](https://img.shields.io/pypi/v/cehrgpt)](https://pypi.org/project/cehrgpt/)
+![Python](https://img.shields.io/badge/-Python_3.11-blue?logo=python&logoColor=white)
+[![tests](https://github.com/knatarajan-lab/cehrgpt-public/actions/workflows/tests.yaml/badge.svg)](https://github.com/knatarajan-lab/cehrgpt-public/actions/workflows/tests.yml)
+[![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)](https://github.com/knatarajan-lab/cehrgpt-public/blob/main/LICENSE)
+[![contributors](https://img.shields.io/github/contributors/knatarajan-lab/cehrgpt-public.svg)](https://github.com/knatarajan-lab/cehrgpt-public/graphs/contributors)
+
+## Description
+CEHRGPT is a synthetic data generation model developed to handle structured electronic health records (EHR) with enhanced privacy and reliability. It leverages state-of-the-art natural language processing techniques to create realistic, anonymized patient data that can be used for research and development without compromising patient privacy.
+
+## Features
+- **Synthetic Patient Data Generation**: Generates comprehensive patient profiles including demographics, medical history, treatment courses, and outcomes.
+- **Privacy-Preserving**: Implements techniques to ensure the generated data does not reveal identifiable information.
+- **Compatibility with OMOP**: Fully compatible with the OMOP common data model, allowing seamless integration with existing healthcare data systems.
+- **Extensible**: Designed to be adaptable to new datasets and different EHR systems.
+
+## Installation
+To install CEHRGPT, clone this repository and install the required dependencies.
+
+```bash
+git clone https://github.com/knatarajan-lab/cehrgpt-public.git
+cd cehrgpt-public
+pip install .
+```
+
+## Citation
+```
+@article{cehrgpt2024,
+  title={CEHRGPT: Synthetic Data Generation for Electronic Health Records},
+  author={Natarajan, K and others},
+  journal={arXiv preprint arXiv:2402.04400},
+  year={2024}
+}
+```

cehrgpt-0.0.1/README.md

@@ -0,0 +1,35 @@
+# CEHRGPT
+
+[![PyPI - Version](https://img.shields.io/pypi/v/cehrgpt)](https://pypi.org/project/cehrgpt/)
+![Python](https://img.shields.io/badge/-Python_3.11-blue?logo=python&logoColor=white)
+[![tests](https://github.com/knatarajan-lab/cehrgpt-public/actions/workflows/tests.yaml/badge.svg)](https://github.com/knatarajan-lab/cehrgpt-public/actions/workflows/tests.yml)
+[![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)](https://github.com/knatarajan-lab/cehrgpt-public/blob/main/LICENSE)
+[![contributors](https://img.shields.io/github/contributors/knatarajan-lab/cehrgpt-public.svg)](https://github.com/knatarajan-lab/cehrgpt-public/graphs/contributors)
+
+## Description
+CEHRGPT is a synthetic data generation model developed to handle structured electronic health records (EHR) with enhanced privacy and reliability. It leverages state-of-the-art natural language processing techniques to create realistic, anonymized patient data that can be used for research and development without compromising patient privacy.
+
+## Features
+- **Synthetic Patient Data Generation**: Generates comprehensive patient profiles including demographics, medical history, treatment courses, and outcomes.
+- **Privacy-Preserving**: Implements techniques to ensure the generated data does not reveal identifiable information.
+- **Compatibility with OMOP**: Fully compatible with the OMOP common data model, allowing seamless integration with existing healthcare data systems.
+- **Extensible**: Designed to be adaptable to new datasets and different EHR systems.
+
+## Installation
+To install CEHRGPT, clone this repository and install the required dependencies.
+
+```bash
+git clone https://github.com/knatarajan-lab/cehrgpt-public.git
+cd cehrgpt-public
+pip install .
+```
+
+## Citation
+```
+@article{cehrgpt2024,
+  title={CEHRGPT: Synthetic Data Generation for Electronic Health Records},
+  author={Natarajan, K and others},
+  journal={arXiv preprint arXiv:2402.04400},
+  year={2024}
+}
+```

cehrgpt-0.0.1/pyproject.toml

@@ -0,0 +1,47 @@
+[build-system]
+requires = ["setuptools", "wheel", "setuptools_scm"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cehrgpt"
+dynamic = ["version"]
+authors = [
+    { name = "Chao Pang", email = "chaopang229@gmail.com" },
+    { name = "Xinzhuo Jiang", email = "xj2193@cumc.columbia.edu" },
+    { name = "Krishna Kalluri", email = "kk3326@cumc.columbia.edu" },
+    { name = "Elise Minto", email = "em3697@cumc.columbia.edu" },
+    { name = "Jason Patterson", email = "jp3477@cumc.columbia.edu" },
+    { name = "Nishanth Parameshwar Pavinkurve", email = "np2689@cumc.columbia.edu" },
+    { name = "Karthik Natarajan", email = "kn2174@cumc.columbia.edu" }
+]
+description = "CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines"
+readme = "README.md"
+license = { text = "MIT License" }
+requires-python = ">=3.10.0"
+
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3"
+]
+
+dependencies = [
+    "cehrbert==1.3.3",
+    "openai==1.54.3",
+    "optuna==4.0.0",
+    "transformers==4.40.0",
+    "tokenizers==0.19",
+    "trl==0.11.4",
+]
+
+[tool.setuptools_scm]
+
+[project.optional-dependencies]
+dev = [
+    "pre-commit", "pytest", "pytest-cov", "pytest-subtests", "rootutils", "hypothesis", "black"
+]
+flash_attn = [
+    "flash_attn"
+]

cehrgpt-0.0.1/scripts/level_three_evaluation.sh

@@ -0,0 +1,165 @@
+#!/bin/bash
+
+# Export environment variables
+export OMOP_FOLDER=$1
+export PATIENT_SPLITS_FOLDER=$2
+
+# Echo input variables
+echo "OMOP_FOLDER=$OMOP_FOLDER"
+echo "PATIENT_SPLITS_FOLDER=$PATIENT_SPLITS_FOLDER"
+
+# Helper function to check and create directories
+create_directory_if_not_exists() {
+    if [ ! -d "$1" ]; then
+        echo "Creating $1"
+        mkdir -p "$1"
+    fi
+}
+
+#!/bin/bash
+
+# Generate CAD CABG Cohort
+echo "Generating cad_cabg"
+create_directory_if_not_exists "$OMOP_FOLDER/cohorts/cad_cabg"
+
+python -u -m cehrbert_data.prediction_cohorts.cad_cabg_cohort \
+    -c cad_cabg_bow \
+    -i "$OMOP_FOLDER" \
+    -o "$OMOP_FOLDER/cohorts/cad_cabg/" \
+    -dl 1985-01-01 -du 2023-12-31 \
+    -l 18 -u 100 -ow 360 -ps 0 -pw 360 -f \
+    --att_type cehr_bert \
+    --ehr_table_list condition_occurrence procedure_occurrence drug_exposure -iv
+
+# Run Predictions on CAD CABG
+echo "Run predictions on cad_cabg"
+create_directory_if_not_exists "$OMOP_FOLDER/evaluation_gpt/cad_cabg"
+
+if [ -n "$PATIENT_SPLITS_FOLDER" ]; then
+    python -m cehrbert.evaluations.evaluation \
+        -a baseline_model \
+        -d "$OMOP_FOLDER/cohorts/cad_cabg/cad_cabg_bow/" \
+        -ef "$OMOP_FOLDER/evaluation_gpt/cad_cabg/" \
+        --patient_splits_folder "$PATIENT_SPLITS_FOLDER"
+else
+    python -m cehrbert.evaluations.evaluation \
+        -a baseline_model \
+        -d "$OMOP_FOLDER/cohorts/cad_cabg/cad_cabg_bow/" \
+        -ef "$OMOP_FOLDER/evaluation_gpt/cad_cabg/"
+fi
+
+# Generate HF Readmission
+echo "Generating hf_readmission"
+create_directory_if_not_exists "$OMOP_FOLDER/cohorts/hf_readmission"
+
+python -u -m cehrbert_data.prediction_cohorts.hf_readmission \
+  -c hf_readmission_bow \
+  -i "$OMOP_FOLDER" \
+  -o "$OMOP_FOLDER/cohorts/hf_readmission" \
+  -dl 1985-01-01 -du 2023-12-31 -l 18 -u 100 -ow 360 -ps 0 -pw 30 -f \
+  --att_type cehr_bert \
+  --ehr_table_list condition_occurrence procedure_occurrence drug_exposure -iv
+
+# Run predictions on HF Readmission
+echo "Run predictions on hf_readmission"
+create_directory_if_not_exists "$OMOP_FOLDER/evaluation_gpt/hf_readmission"
+
+if [ -n "$PATIENT_SPLITS_FOLDER" ]; then
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/hf_readmission/hf_readmission_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/hf_readmission/" \
+      --patient_splits_folder "$PATIENT_SPLITS_FOLDER"
+else
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/hf_readmission/hf_readmission_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/hf_readmission/"
+fi
+
+# Generate COPD Readmission
+echo "Generating copd_readmission"
+create_directory_if_not_exists "$OMOP_FOLDER/cohorts/copd_readmission"
+
+python -u -m cehrbert_data.prediction_cohorts.copd_readmission \
+  -c copd_readmission_bow \
+  -i "$OMOP_FOLDER" \
+  -o "$OMOP_FOLDER/cohorts/copd_readmission" \
+  -dl 1985-01-01 -du 2023-12-31 -l 18 -u 100 -ow 720 -ps 0 -pw 360 -f \
+  --att_type cehr_bert \
+  --ehr_table_list condition_occurrence procedure_occurrence drug_exposure -iv
+
+# Run predictions on COPD Readmission
+echo "Run predictions on copd_readmission"
+create_directory_if_not_exists "$OMOP_FOLDER/evaluation_gpt/copd_readmission"
+
+if [ -n "$PATIENT_SPLITS_FOLDER" ]; then
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/copd_readmission/copd_readmission_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/copd_readmission/" \
+      --patient_splits_folder "$PATIENT_SPLITS_FOLDER"
+else
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/copd_readmission/copd_readmission_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/copd_readmission/"
+fi
+
+# Generate Hospitalization
+echo "Generating hospitalization"
+create_directory_if_not_exists "$OMOP_FOLDER/cohorts/hospitalization"
+
+python -u -m cehrbert_data.prediction_cohorts.hospitalization \
+  -c hospitalization_bow \
+  -i "$OMOP_FOLDER" \
+  -o "$OMOP_FOLDER/cohorts/hospitalization" \
+  -dl 1985-01-01 -du 2023-12-31 -l 18 -u 100 -ow 540 -hw 180 -ps 0 -pw 360 -f -iw \
+  --att_type cehr_bert \
+  --ehr_table_list condition_occurrence procedure_occurrence drug_exposure -iv
+
+# Run predictions on Hospitalization
+echo "Run predictions on hospitalization"
+create_directory_if_not_exists "$OMOP_FOLDER/evaluation_gpt/hospitalization"
+
+if [ -n "$PATIENT_SPLITS_FOLDER" ]; then
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/hospitalization/hospitalization_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/hospitalization/" \
+      --patient_splits_folder "$PATIENT_SPLITS_FOLDER"
+else
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/hospitalization/hospitalization_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/hospitalization/"
+fi
+
+# Generate AFIB Ischemic Stroke
+echo "Generating afib_ischemic_stroke"
+create_directory_if_not_exists "$OMOP_FOLDER/cohorts/afib_ischemic_stroke"
+
+python -u -m cehrbert_data.prediction_cohorts.afib_ischemic_stroke \
+  -c afib_ischemic_stroke_bow \
+  -i "$OMOP_FOLDER" \
+  -o "$OMOP_FOLDER/cohorts/afib_ischemic_stroke" \
+  -dl 1985-01-01 -du 2023-12-31 -l 18 -u 100 -ow 720 -ps 0 -pw 360 -f \
+  --att_type cehr_bert \
+  --ehr_table_list condition_occurrence procedure_occurrence drug_exposure -iv
+
+# Run predictions on AFIB Ischemic Stroke
+echo "Run predictions on afib_ischemic_stroke"
+create_directory_if_not_exists "$OMOP_FOLDER/evaluation_gpt/afib_ischemic_stroke"
+
+if [ -n "$PATIENT_SPLITS_FOLDER" ]; then
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/afib_ischemic_stroke/afib_ischemic_stroke_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/afib_ischemic_stroke/" \
+      --patient_splits_folder "$PATIENT_SPLITS_FOLDER"
+else
+    python -m cehrbert.evaluations.evaluation \
+      -a baseline_model \
+      -d "$OMOP_FOLDER/cohorts/afib_ischemic_stroke/afib_ischemic_stroke_bow/" \
+      -ef "$OMOP_FOLDER/evaluation_gpt/afib_ischemic_stroke/"
+fi

cehrgpt-0.0.1/scripts/omop_pipeline.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+
+# Exporting input arguments as environment variables
+export PATIENT_SEQUENCE_FOLDER=$1
+export OMOP_FOLDER=$2
+export SOURCE_OMOP_FOLDER=$3
+export PATIENT_SPLITS_FOLDER=$SOURCE_OMOP_FOLDER/patient_splits
+
+# Echoing the values of the environment variables
+echo "PATIENT_SEQUENCE_FOLDER=$PATIENT_SEQUENCE_FOLDER"
+echo "OMOP_FOLDER=$OMOP_FOLDER"
+echo "SOURCE_OMOP_FOLDER=$SOURCE_OMOP_FOLDER"
+
+# Ensure OMOP_FOLDER exists
+if [ ! -d "$OMOP_FOLDER" ]; then
+    echo "Creating $OMOP_FOLDER"
+    mkdir -p "$OMOP_FOLDER"
+fi
+
+# Removing existing OMOP tables
+rm -rf $OMOP_FOLDER/person/
+rm -rf $OMOP_FOLDER/visit_occurrence/
+rm -rf $OMOP_FOLDER/condition_occurrence/
+rm -rf $OMOP_FOLDER/procedure_occurrence/
+rm -rf $OMOP_FOLDER/drug_exposure/
+rm -rf $OMOP_FOLDER/death/
+rm -rf $OMOP_FOLDER/measurement/
+rm -rf $OMOP_FOLDER/observation_period/
+rm -rf $OMOP_FOLDER/condition_era/
+
+# Removing existing OMOP concept tables
+rm -rf $OMOP_FOLDER/concept
+rm -rf $OMOP_FOLDER/concept_ancestor
+rm -rf $OMOP_FOLDER/concept_relationship
+
+# Copying OMOP concept tables if they don't already exist
+if [ ! -d $OMOP_FOLDER/concept ]; then
+    echo "Creating $OMOP_FOLDER/concept"
+    cp -r $SOURCE_OMOP_FOLDER/concept $OMOP_FOLDER/concept
+fi
+
+if [ ! -d $OMOP_FOLDER/concept_relationship ]; then
+    echo "Creating $OMOP_FOLDER/concept_relationship"
+    cp -r $SOURCE_OMOP_FOLDER/concept_relationship $OMOP_FOLDER/concept_relationship
+fi
+
+if [ ! -d $OMOP_FOLDER/concept_ancestor ]; then
+    echo "Creating $OMOP_FOLDER/concept_ancestor"
+    cp -r $SOURCE_OMOP_FOLDER/concept_ancestor $OMOP_FOLDER/concept_ancestor
+fi
+
+# Reconstructing the OMOP instance from patient sequences
+echo "Reconstructing the OMOP instance from patient sequences in $OMOP_FOLDER"
+python -m cehrgpt.generation.omop_converter_batch \
+  --patient_sequence_path $PATIENT_SEQUENCE_FOLDER \
+  --output_folder $OMOP_FOLDER \
+  --concept_path $OMOP_FOLDER/concept \
+  --buffer_size 1280 \
+  --cpu_cores 10
+
+# Create observation_period
+echo "Reconstructing observation_period in $OMOP_FOLDER"
+python -u -m cehrgpt.omop.observation_period \
+  --input_folder $OMOP_FOLDER \
+  --output_folder $OMOP_FOLDER \
+  --domain_table_list condition_occurrence drug_exposure procedure_occurrence measurement
+
+# Create condition_era
+echo "Reconstructing condition_era in $OMOP_FOLDER"
+python -u -m cehrgpt.omop.condition_era \
+  --input_folder $OMOP_FOLDER \
+  --output_folder $OMOP_FOLDER \
+  --domain_table_list condition_occurrence