This guide walks you through installing reprodICU, configuring paths to your ICU datasets, and building your first harmonized database.

Installation

Prerequisites

• python 3.10 or later
• Access to at least one ICU dataset (eICU, HiRID, MIMIC-III, MIMIC-IV, NWICU, SICdb, or AmsterdamUMCdb)
• OMOP Vocabularies (you can download the OMOP vocabularies from https://athena.ohdsi.org/search-terms/start, the OHDSI vocabularies repository for free (after creating a free account))

Then install the package including dependencies:

pip install git+https://github.com/CUB-CORR/reprodICU

1. Downloading the raw data

• https://amsterdammedicaldatascience.nl/#amsterdamumcdb
• [Faltys, M., Zimmermann, M., Lyu, X., Hüser, M., Hyland, S., Rätsch, G., & Merz, T. (2021). HiRID, a high time-resolution ICU dataset (version 1.1.1). PhysioNet. https://doi.org/10.13026/nkwc-js72.](https://reprodicu.notion.site/Faltys-M-Zimmermann-M-Lyu-X-H-ser-M-Hyland-S-R-tsch-G-Merz-T-2021-HiRID-a--175f41411fe780589c03d1cfae521791)
• [Rodemund, N., Kokoefer, A., Wernly, B., & Cozowicz, C. (2024). Salzburg Intensive Care database (SICdb), a freely accessible intensive care database (version 1.0.8). PhysioNet. https://doi.org/10.13026/8m72-6j83.](https://reprodicu.notion.site/Rodemund-N-Kokoefer-A-Wernly-B-Cozowicz-C-2024-Salzburg-Intensive-Care-database-SIC-175f41411fe7809bbda7cde3cf0f6a2c)
• [Pollard, T., Johnson, A., Raffa, J., Celi, L. A., Badawi, O., & Mark, R. (2019). eICU Collaborative Research Database (version 2.0). PhysioNet. https://doi.org/10.13026/C2WM1R.](https://reprodicu.notion.site/Pollard-T-Johnson-A-Raffa-J-Celi-L-A-Badawi-O-Mark-R-2019-eICU-Collaborative--175f41411fe78011ad4cfffb24dcc267)
• [Johnson, A., Pollard, T., & Mark, R. (2016). MIMIC-III Clinical Database (version 1.4). PhysioNet. https://doi.org/10.13026/C2XW26.](https://reprodicu.notion.site/Johnson-A-Pollard-T-Mark-R-2016-MIMIC-III-Clinical-Database-version-1-4-PhysioNet-h-175f41411fe780ef8499f5342b2021f7)
• [Johnson, A., Bulgarelli, L., Pollard, T., Gow, B., Moody, B., Horng, S., Celi, L. A., & Mark, R. (2024). MIMIC-IV (version 3.1). PhysioNet. https://doi.org/10.13026/kpb9-mt58.](https://reprodicu.notion.site/Johnson-A-Bulgarelli-L-Pollard-T-Gow-B-Moody-B-Horng-S-Celi-L-A-Mark-R-20-175f41411fe780999d95e295430c1e4f)
• [Moukheiber, D., Temps, W., Molgi, B., Li, Y., Lu, A., Nannapaneni, P., Chahin, A., Hao, S., Torres Fabregas, F., Celi, L. A., Wong, A., Lloyd, M., Borrat Frigola, X., Lee, H., Schneider, D., Pollard, T., Luo, Y., Kho, A., & Mark, R. (2024). Northwestern ICU (NWICU) database (version 0.1.0). PhysioNet. https://doi.org/10.13026/s84w-1829.](https://reprodicu.notion.site/Moukheiber-D-Temps-W-Molgi-B-Li-Y-Lu-A-Nannapaneni-P-Chahin-A-Hao-S-Torres-F-175f41411fe7807dacfbdf6971fee951)

1.1. preparing the raw data

2. Downloading the OMOP vocabularies