{"id":26914521,"url":"https://github.com/kosuri-indu/plp-pipeline","last_synced_at":"2026-05-12T23:34:39.497Z","repository":{"id":279232756,"uuid":"937499220","full_name":"kosuri-indu/PLP-Pipeline","owner":"kosuri-indu","description":"PLP-Pipeline is a patient-level prediction pipeline using Julia and DrWatson. It predicts diabetes onset in hypertension patients by analyzing healthcare data with OMOP CDM. The pipeline includes cohort definition, feature extraction, preprocessing, and model training using L1 Logistic Regression, Random Forest, and XGBoost.","archived":false,"fork":false,"pushed_at":"2025-03-25T14:42:40.000Z","size":140,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-06T09:44:02.257Z","etag":null,"topics":["drwatson","duckdb","heathcare","julia","omop-cdm","patient-level-prediction","plp"],"latest_commit_sha":null,"homepage":"","language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kosuri-indu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-23T07:46:28.000Z","updated_at":"2025-03-25T14:42:44.000Z","dependencies_parsed_at":"2025-02-24T14:40:24.531Z","dependency_job_id":"ee88a739-e530-4b62-a347-69f8ab965cce","html_url":"https://github.com/kosuri-indu/PLP-Pipeline","commit_stats":null,"previous_names":["kosuri-indu/plp-pipeline"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kosuri-indu%2FPLP-Pipeline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kosuri-indu%2FPLP-Pipeline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kosuri-indu%2FPLP-Pipeline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kosuri-indu%2FPLP-Pipeline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kosuri-indu","download_url":"https://codeload.github.com/kosuri-indu/PLP-Pipeline/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kosuri-indu%2FPLP-Pipeline/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259159655,"owners_count":22814492,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["drwatson","duckdb","heathcare","julia","omop-cdm","patient-level-prediction","plp"],"created_at":"2025-04-01T17:28:36.802Z","updated_at":"2026-05-12T23:34:39.468Z","avatar_url":"https://github.com/kosuri-indu.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PLP-Pipeline\n\nThis code base is using the [Julia Language](https://julialang.org/) and [DrWatson](https://juliadynamics.github.io/DrWatson.jl/stable/) to make a reproducible scientific project named PLP-Pipeline. It is authored by *kosuri-indu*, demonstrates a pipeline for patient-level prediction. Special thanks to [@TheCedarPrince](https://github.com/TheCedarPrince) for guiding this project.\n\n## Research Question\n- Can we predict the onset of *diabetes* in patients diagnosed with *hypertension* using patient-level observational healthcare data?  \n- The goal is to build a predictive model that identifies patterns from historical healthcare data to determine which patients with hypertension are more likely to develop diabetes.\n\n## Getting Started\n\nTo (locally) reproduce this project, do the following:\n\n1. Download the Code Base \n   *Note:* Raw data are not included in the repository. You will need to download them separately.\n\n2. Set Up the Julia Environment\n   Open a Julia console and execute:\n   ```julia\n   using Pkg\n   Pkg.add(\"DrWatson\")        # Install DrWatson globally\n   Pkg.activate(\"path/to/this/project\")\n   Pkg.instantiate()          # Install all necessary packages\n\nThis will install all necessary packages for you to be able to run the scripts and everything should work out of the box, including correctly finding local paths.\n\nYou may notice that most scripts start with the commands:\n```julia\nusing DrWatson\n@quickactivate \"PLP-Pipeline\"\n```\nwhich auto-activate the project and enable local path handling from DrWatson.\n\n## Usage\n\n### Setting Up the Database\n\nSet up the DuckDB database with your data by running:\n```julia\njulia\u003e include(\"scripts/setup_db.jl\")\n```\n\n### Running the Pipeline\n\nTo run the machine learning pipeline, use the `run_plp.jl` script:\n```julia\njulia\u003e include(\"scripts/run_plp.jl\")\n```\n\n## TODO List\n\n- Documentation \u0026 Research\n  - [x] Add initial documentation in the `_research` folder\n  - [ ] Expand documentation with detailed research questions and hypotheses\n\n- Core Pipeline Implementation\n  - [x] Set up project structure with DrWatson\n  - [x] Database setup (`setup_db.jl`)\n  - [x] Data loading (`data_loader.jl`)\n  - [x] Cohort definition (`cohort_definition.jl`)\n  - [x] Feature extraction (`feature_extraction.jl`)\n  - [x] Distribution check (`distribution_check.jl`)\n  - [x] Outcome attachment (`outcome_attach.jl`)\n  - [x] Data preprocessing (`preprocessing.jl`)\n  - [x] Model training \u0026 evaluation (`train_model.jl`)\n\n- Future Enhancements\n  - [ ] Add robust error handling and logging\n  - [ ] Refine research questions and incorporate additional clinical variables\n  - [ ] Develop tests and expand documentation further\n\n## References\n\n- [OHDSI Patient-Level Prediction in R](https://ohdsi.github.io/PatientLevelPrediction/)\n- Reps, J. M., Schuemie, M. J., Suchard, M. A., Ryan, P. B., \u0026 Rijnbeek, P. R. (2018). Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data. *Journal of the American Medical Informatics Association, 25*(8), 969–975. https://doi.org/10.1093/jamia/ocy032\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkosuri-indu%2Fplp-pipeline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkosuri-indu%2Fplp-pipeline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkosuri-indu%2Fplp-pipeline/lists"}