{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-extensive-data-processing-pipeline-for","title":"An Extensive Data Processing Pipeline for MIMIC-IV","arxiv_id":"2204.13841","date":"2022-04-29","proceeding":null,"authors":["Mehak Gupta","Brennan Gallamoza","Nicolas Cutrona","Pranjal Dhakal","Raphael Poulain","Rahmatollah Beheshti"],"abstract":"An increasing amount of research is being devoted to applying machine learning methods to electronic health record (EHR) data for various clinical purposes. This growing area of research has exposed the challenges of the accessibility of EHRs. MIMIC is a popular, public, and free EHR dataset in a raw format that has been used in numerous studies. The absence of standardized pre-processing steps can be, however, a significant barrier to the wider adoption of this rare resource. Additionally, this absence can reduce the reproducibility of the developed tools and limit the ability to compare the results among similar studies. In this work, we provide a greatly customizable pipeline to extract, clean, and pre-process the data available in the fourth version of the MIMIC dataset (MIMIC-IV). The pipeline also presents an end-to-end wizard-like package supporting predictive model creations and evaluations. The pipeline covers a range of clinical prediction tasks which can be broadly classified into four categories - readmission, length of stay, mortality, and phenotype prediction. The tool is publicly available at https://github.com/healthylaife/MIMIC-IV-Data-Pipeline.","url_abs":"https://arxiv.org/abs/2204.13841v5","url_pdf":"https://arxiv.org/pdf/2204.13841v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-extensive-data-processing-pipeline-for","repo_url":"https://github.com/anonymousblind/mimic-iv-data-pipeline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-extensive-data-processing-pipeline-for","repo_url":"https://github.com/healthylaife/mimic-iv-data-pipeline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-prediction","task_name":"Time Series Prediction"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.13841","atlas_url":"https://app.syntology.ai/?focus=2204.13841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13841"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anonymousblind/mimic-iv-data-pipeline","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/healthylaife/mimic-iv-data-pipeline","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"497f7fe7aad7540a","entry":"create_vocab","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"497f7fe7aad7540a"}},{"code_sha256_prefix":"6745ad831637cf59","entry":"dataframe_from_csv","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"mimic4_preprocess_util.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/mimic4_preprocess_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6745ad831637cf59"}},{"code_sha256_prefix":"eea810915b1e8ce5","entry":"index_seg","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/behrt_model.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/behrt_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eea810915b1e8ce5"}},{"code_sha256_prefix":"7cedea7a54f72fb3","entry":"init","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7cedea7a54f72fb3"}},{"code_sha256_prefix":"d912f9f7048d6d88","entry":"position_idx","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/behrt_model.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/behrt_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d912f9f7048d6d88"}},{"code_sha256_prefix":"4f9de57bd1bf493b","entry":"read_admissions_table","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"mimic4_preprocess_util.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/mimic4_preprocess_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f9de57bd1bf493b"}},{"code_sha256_prefix":"dfb09c753068d63c","entry":"seq_padding","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/behrt_model.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/behrt_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfb09c753068d63c"}},{"code_sha256_prefix":"e33b3ffeb2767d35","entry":"create_batches","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e33b3ffeb2767d35"}},{"code_sha256_prefix":"1bad43858a0e09f5","entry":"fairness_evaluation","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"model/fairness.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/fairness.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1bad43858a0e09f5"}},{"code_sha256_prefix":"eb6717b0bd21e273","entry":"read_patients_table","repo":"healthylaife/mimic-iv-data-pipeline","repo_kind":"official","path":"mimic4_preprocess_util.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/mimic4_preprocess_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb6717b0bd21e273"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}