{"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/deep-reinforcement-learning-for-sepsis","title":"Deep Reinforcement Learning for Sepsis Treatment","arxiv_id":"1711.09602","date":"2017-11-27","proceeding":null,"authors":["Aniruddh Raghu","Matthieu Komorowski","Imran Ahmed","Leo Celi","Peter Szolovits","Marzyeh Ghassemi"],"abstract":"Sepsis is a leading cause of mortality in intensive care units and costs\nhospitals billions annually. Treating a septic patient is highly challenging,\nbecause individual patients respond very differently to medical interventions\nand there is no universally agreed-upon treatment for sepsis. In this work, we\npropose an approach to deduce treatment policies for septic patients by using\ncontinuous state-space models and deep reinforcement learning. Our model learns\nclinically interpretable treatment policies, similar in important aspects to\nthe treatment policies of physicians. The learned policies could be used to aid\nintensive care clinicians in medical decision making and improve the likelihood\nof patient survival.","url_abs":"http://arxiv.org/abs/1711.09602v1","url_pdf":"http://arxiv.org/pdf/1711.09602v1.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":"deep-reinforcement-learning-for-sepsis","repo_url":"https://github.com/darkefyre/sepsisrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-for-sepsis","repo_url":"https://github.com/uribyul/py_ai_clinician","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.09602","atlas_url":"https://app.syntology.ai/?focus=1711.09602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.09602"}},"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/uribyul/py_ai_clinician","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/darkefyre/sepsisrl","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"1174e4664a2041f7","entry":"my_zscore","repo":"uribyul/py_ai_clinician","repo_kind":"listed","path":"Core.py","file_url":"https://github.com/uribyul/py_ai_clinician/blob/HEAD/Core.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1174e4664a2041f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}