{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T13:36:57Z","timestamp":1794317817155,"version":"4.9.0"},"reference-count":32,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T00:00:00Z","timestamp":1675036800000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T00:00:00Z","timestamp":1675036800000},"content-version":"tdm","delay-in-days":29,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61771261"],"award-info":[{"award-number":["61771261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Sepsis seriously threatens human life. Early identification of a patient\u2019s risk status and appropriate treatment can reduce septic shock risk and mortality. Our purpose is to design and validate an adjunctive therapy system based on deep reinforcement learning (DRL), which can provide treatment recommendations with providence and assess the patient\u2019s risk status and treatment options in the early stages.\n                    <jats:italic>Approach.<\/jats:italic>\n                    Data is from the Beth Israel Deaconess Medical Center. The raw data included 53 423 patients from MIMIC-III. Of these, 19 620 eligible samples were screened to form the final cohort. First, the patient\u2019s physiological parameters were fed into the DRL therapy strategy recommendation module (TSRM), which provides a forward-looking recommendation for treatment strategy. The recommended strategies were then fed into the reinforcement learning risk assessment module (RAM), which predicts the patient\u2019s risk status and treatment strategy from a long-term perspective. The DRL model designed in this paper assists in formulating treatment plans and evaluating treatment risks and patient status through continuous interaction with patient trajectory; this model therefore has the foresight that a supervising deep learning model does not.\n                    <jats:italic>Main results.<\/jats:italic>\n                    The experiment shows that, in the test set for the TSRM, mortality is the lowest when the treatment strategy that is actually implemented is the same as the AI-recommended strategy. Regarding the RAM, it can accurately grasp a patient\u2019s deterioration trend, and can reasonably assess a patient\u2019s risk status and treatment plans at an early stage. The assessment results of the model were matched with the actual clinical records.\n                    <jats:italic>Significance.<\/jats:italic>\n                    A DRL-based sepsis adjunctive therapy model is proposed. It can prospectively assist physicians in proposing treatment strategies, assess the patient\u2019s risk status and treatment methods early on, and detect deterioration trends in advance.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/acb03b","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T17:42:35Z","timestamp":1672854155000},"page":"015003","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Artificial intelligence can use physiological parameters to optimize treatment strategies and predict clinical deterioration of sepsis in ICU"],"prefix":"10.1088","volume":"44","author":[{"given":"Quan","family":"Zhang","sequence":"first","affiliation":[{"name":"Nankai University"},{"name":"Nankai University"},{"name":"Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6664-2650","authenticated-orcid":false,"given":"Jianqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University"},{"name":"Nankai University"},{"name":"Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohua","family":"Liu","sequence":"additional","affiliation":[{"name":"Nankai University"},{"name":"Nankai University"},{"name":"Nankai University"},{"name":"Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin Research Institute for Water Transport Engineering, M.O.T., Tianjin 300456,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,1,30]]},"reference":[{"key":"pmeaacb03bbib1","doi-asserted-by":"publisher","first-page":"105816","DOI":"10.1016\/j.cmpb.2020.105816","type":"journal-article","article-title":"A deep learning approach for sepsis monitoring via severity score estimation","volume":"198","author":"A\u015furo\u011flu","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmeaacb03bbib2","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1097\/CCM.0000000000004224","type":"journal-article","article-title":"MMSc6 sepsis among medicare beneficiaries: 1. The burdens of sepsis, 2012\u20132018*","volume":"48","author":"Buchman Timothy","year":"2020","journal-title":"Critical Care Medicine"},{"key":"pmeaacb03bbib3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13613-016-0231-8","type":"journal-article","article-title":"Fluid resuscitation in human sepsis: time to rewrite history?","volume":"7","author":"Byrne","year":"2017","journal-title":"Ann Intensive Care"},{"key":"pmeaacb03bbib4","doi-asserted-by":"publisher","first-page":"115014","DOI":"10.1088\/1361-6560\/ac6fad","type":"journal-article","article-title":"Machine learning-based detection of aberrant deep learning segmentations of target and organs at risk for prostate radiotherapy using a secondary segmentation algorithm","volume":"67","author":"Claessens","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmeaacb03bbib5","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1182\/blood.V118.21.1233.1233","type":"journal-article","article-title":"Haemostasis change in intensive care patients with severe sepsis and patients with organ failure without sepsis","volume":"118","author":"Dreden","year":"2011","journal-title":"Blood"},{"key":"pmeaacb03bbib6","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s00134-021-06506-y","type":"journal-article","article-title":"Surviving sepsis campaign: international guidelines for management of sepsis and septic shock","volume":"47","author":"Evans","year":"2021","journal-title":"Intensive Care Med."},{"key":"pmeaacb03bbib7","article-title":"Medical dead-ends and learning to identify high-risk states and treatments","author":"Fatemi","year":"2021","type":"preprint"},{"key":"pmeaacb03bbib8","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.annemergmed.2021.02.029","type":"journal-article","article-title":"Development and validation of machine learning models to predict admission from emergency department to inpatient and intensive care units","volume":"78","author":"Fenn","year":"2021","journal-title":"Annals of Emergency Medicine"},{"key":"pmeaacb03bbib9","doi-asserted-by":"publisher","first-page":"104165","DOI":"10.1016\/j.jobe.2022.104165","type":"journal-article","article-title":"Applications of reinforcement learning for building energy efficiency control: a review","volume":"50","author":"Fu","year":"2022","journal-title":"J. Building Eng."},{"key":"pmeaacb03bbib10","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1016\/j.jebo.2022.06.021","type":"journal-article","article-title":"Reinforcement learning with foregone payoff information in normal form games","volume":"200","author":"Funai","year":"2022","journal-title":"J. Economic Behavior & Organization"},{"key":"pmeaacb03bbib11","doi-asserted-by":"publisher","first-page":"115008","DOI":"10.1088\/1361-6579\/ab5154","type":"journal-article","article-title":"Imputation of partial pressures of arterial oxygen using oximetry and its impact on sepsis diagnosis","volume":"40","author":"Gadrey","year":"2019","journal-title":"Physiol. Meas."},{"key":"pmeaacb03bbib12","doi-asserted-by":"publisher","first-page":"024001","DOI":"10.1088\/1361-6560\/ac4000","type":"journal-article","article-title":"Prospectively-validated deep learning model for segmenting swallowing and chewing structures in CT","volume":"67","author":"Iyer","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmeaacb03bbib13","doi-asserted-by":"publisher","first-page":"103762","DOI":"10.1016\/j.jbi.2021.103762","type":"journal-article","article-title":"Safety-driven design of machine learning for sepsis treatment","volume":"117","author":"Jia","year":"2021","journal-title":"J. Biomedical Informatics"},{"key":"pmeaacb03bbib14","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","type":"journal-article","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"pmeaacb03bbib15","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1016\/j.ophtha.2021.12.017","type":"journal-article","article-title":"DeepLensNet: deep learning automated diagnosis and quantitative classification of cataract type and severity","volume":"129","author":"Keenan","year":"2022","journal-title":"Ophthalmology"},{"key":"pmeaacb03bbib16","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","type":"journal-article","article-title":"The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care","volume":"24","author":"Komorowski","year":"2018","journal-title":"Nat. Med."},{"key":"pmeaacb03bbib17","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1097\/CCM.0000000000005294","type":"journal-article","article-title":"Criteria for pediatric sepsis\u2014a systematic review and meta-analysis by the pediatric sepsis definition taskforce*","volume":"50","author":"Kusum","year":"2022","journal-title":"Critical Care Medicine"},{"key":"pmeaacb03bbib18","doi-asserted-by":"publisher","first-page":"145014","DOI":"10.1088\/1361-6560\/ac783d","type":"journal-article","article-title":"A personalized deep learning denoising strategy for low-count PET images","volume":"67","author":"Liu","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmeaacb03bbib19","doi-asserted-by":"publisher","first-page":"679","DOI":"10.2147\/DMSO.S242585","type":"journal-article","article-title":"Deep learning-based method of diagnosing hyperlipidemia and providing diagnostic markers automatically","volume":"13","author":"Liu","year":"2020","journal-title":"Diabetes Metab Syndr Obes"},{"key":"pmeaacb03bbib20","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1016\/S0140-6736(19)32501-2","type":"journal-article","article-title":"Deep learning and medical diagnosis","volume":"394","author":"Liu","year":"2019","journal-title":"Lancet"},{"key":"pmeaacb03bbib21","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1093\/bja\/aev349","type":"journal-article","article-title":"A rational approach to fluid therapy in sepsis","volume":"116","author":"Marik","year":"2016","journal-title":"British Journal of Anaesthesia"},{"key":"pmeaacb03bbib21a","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.1093\/bja\/aev349","type":"journal-article","article-title":"Epidemiology and burden of sepsis acquired in hospitals and intensive care units: a systematic review and meta-analysis","volume":"46","author":"Markwart","year":"2020","journal-title":"Intensive Care Med"},{"key":"pmeaacb03bbib22","article-title":"Deep reinforcement learning for sepsis treatment","author":"Raghu","year":"2017","type":"preprint"},{"key":"pmeaacb03bbib23","doi-asserted-by":"publisher","first-page":"144003","DOI":"10.1088\/1361-6560\/ac79f8","type":"journal-article","article-title":"A deep learning and Monte Carlo based framework for bioluminescence imaging center of mass-guided glioblastoma targeting","volume":"67","author":"Rezaeifar","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmeaacb03bbib24","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","type":"journal-article","article-title":"Global, regional, and national sepsis incidence and mortality, 1990\u20132017: analysis for the Global Burden of Disease Study","volume":"395","author":"Rudd","year":"2020","journal-title":"Lancet"},{"key":"pmeaacb03bbib25","doi-asserted-by":"publisher","first-page":"104445","DOI":"10.1016\/j.autcon.2022.104445","type":"journal-article","article-title":"Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning","volume":"141","author":"Sanzana","year":"2022","journal-title":"Autom. Constr."},{"key":"pmeaacb03bbib26","author":"Schaul","year":"2016","type":"preprint"},{"key":"pmeaacb03bbib27","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1088\/1361-6579\/aa9772","type":"journal-article","article-title":"Multiscale network representation of physiological time series for early prediction of sepsis","volume":"38","author":"Shashikumar","year":"2017","journal-title":"Physiol. Meas."},{"key":"pmeaacb03bbib28","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","type":"journal-article","article-title":"The third international consensus definitions for sepsis and septic shock (Sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA"},{"key":"pmeaacb03bbib29","doi-asserted-by":"publisher","first-page":"100094","DOI":"10.1016\/j.jjimei.2022.100094","type":"journal-article","article-title":"How are reinforcement learning and deep learning algorithms used for big data based decision making in financial industries\u2013a review and research agenda","volume":"2","author":"Singh","year":"2022","journal-title":"Int. J. Information Management Data Insights"},{"key":"pmeaacb03bbib30","doi-asserted-by":"publisher","first-page":"066032","DOI":"10.1088\/1741-2552\/ac37cc","type":"journal-article","article-title":"A whole-process interpretable and multi-modal deep reinforcement learning for diagnosis and analysis of Alzheimer\u2019s disease","volume":"18","author":"Zhang","year":"2021","journal-title":"J. Neural Eng."},{"key":"pmeaacb03bbib31","doi-asserted-by":"publisher","first-page":"145012","DOI":"10.1088\/1361-6560\/ac7b09","type":"journal-article","article-title":"Feasibility study of three-material decomposition in dual-energy cone-beam CT imaging with deep learning","volume":"67","author":"Zhu","year":"2022","journal-title":"Phys. Med. Biol."}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:40:40Z","timestamp":1778776840000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/acb03b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1,30]]},"published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/acb03b","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]},"assertion":[{"value":"Artificial intelligence can use physiological parameters to optimize treatment strategies and predict clinical deterioration of sepsis in ICU","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2022-11-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}