{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:15:39Z","timestamp":1783703739794,"version":"3.55.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133464","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:54:28Z","timestamp":1783061668000},"page":"133464","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["CNA : An AI-oriented comprehensive normalized assessment for healthy status and application to optimize RRT strategies by reinforcement learning"],"prefix":"10.1016","volume":"332","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2800-448X","authenticated-orcid":false,"given":"Jiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-9202","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5840-2086","authenticated-orcid":false,"given":"Bin","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"11","key":"10.1016\/j.eswa.2026.133464_bib0001","first-page":"1817","article-title":"A framework for learning predictive structures from multiple tasks and unlabeled data","volume":"6","author":"Ando","year":"2005","journal-title":"Journal of Machine Learning Research"},{"issue":"12","key":"10.1016\/j.eswa.2026.133464_bib0002","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1093\/ajhp\/zxaf044","article-title":"Kdigo 2024 clinical practice guideline on evaluation and management of chronic kidney disease: A primer on what pharmacists need to know","volume":"82","author":"Awdishu","year":"2025","journal-title":"American Journal of Health-System Pharmacy"},{"issue":"2","key":"10.1016\/j.eswa.2026.133464_bib0003","doi-asserted-by":"crossref","first-page":"58","DOI":"10.3904\/kjim.2008.23.2.58","article-title":"Continuous renal replacement therapy for the treatment of acute kidney injury","volume":"23","author":"Bae","year":"2008","journal-title":"The Korean Journal of Internal Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102920","article-title":"End-to-end offline reinforcement learning for glycemia control","volume":"154","author":"Beolet","year":"2024","journal-title":"Artificial Intelligence in Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0005","series-title":"International conference on machine learning","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2019"},{"issue":"11S","key":"10.1016\/j.eswa.2026.133464_bib0006","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1681\/ASN.20223311S1354b","article-title":"Can augmented intelligence assist in delivering continuous renal replacement therapy? A scoping review: FR-PO102","volume":"33","author":"Hammouda","year":"2022","journal-title":"Journal of the American Society of Nephrology"},{"key":"10.1016\/j.eswa.2026.133464_bib0007","series-title":"Advances in neural information processing systems","article-title":"Double Q-learning","volume":"vol. 23","author":"Hasselt","year":"2010"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0008","first-page":"50","article-title":"Effects of continuous renal replacement therapy on apache-II score, creatinine, and urea nitrogen levels in patients with acute kidney injury","volume":"39","author":"Hou","year":"2023","journal-title":"Pakistan Journal of Medical Sciences"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"Mimic-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.133464_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcrc.2024.154964","article-title":"Optimal timing for renal replacement therapy in critically ill patients using reinforcement learning algorithms","volume":"86","author":"Kapral","year":"2025","journal-title":"Journal of Critical Care"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0011","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1186\/s13741-021-00219-y","article-title":"The potential for artificial intelligence to predict clinical outcomes in patients who have acquired acute kidney injury during the perioperative period","volume":"10","author":"Kelly","year":"2021","journal-title":"Perioperative Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0012","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.engappai.2014.01.007","article-title":"Adaptive multi-objective reinforcement learning with hybrid exploration for traffic signal control based on cooperative multi-agent framework","volume":"29","author":"Khamis","year":"2014","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"10","key":"10.1016\/j.eswa.2026.133464_bib0013","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1097\/00003246-198510000-00009","article-title":"Apache II: A severity of disease classification system","volume":"13","author":"Knaus","year":"1985","journal-title":"Critical Care Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0014","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.jcrc.2019.02.026","article-title":"Modification of sequential organ failure assessment score using acute kidney injury classification","volume":"51","author":"Kotani","year":"2019","journal-title":"Journal of Critical Care"},{"key":"10.1016\/j.eswa.2026.133464_bib0015","series-title":"2018\u202fIEEE First international conference on artificial intelligence and knowledge engineering (AIKE)","first-page":"129","article-title":"Performance dynamics and termination errors in reinforcement learning\u2013a unifying perspective","author":"Kuang","year":"2018"},{"issue":"3","key":"10.1016\/j.eswa.2026.133464_bib0016","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1007\/s10845-020-01612-y","article-title":"Designing an adaptive production control system using reinforcement learning","volume":"32","author":"Kuhnle","year":"2021","journal-title":"Journal of Intelligent Manufacturing"},{"key":"10.1016\/j.eswa.2026.133464_bib0017","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0018","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1186\/s13054-019-2663-7","article-title":"The SOFA score-development, utility and challenges of accurate assessment in clinical trials","volume":"23","author":"Lambden","year":"2019","journal-title":"Critical Care"},{"issue":"24","key":"10.1016\/j.eswa.2026.133464_bib0019","doi-asserted-by":"crossref","first-page":"2957","DOI":"10.1001\/jama.1993.03510240069035","article-title":"A new simplified acute physiology score (SAPS II) based on a European\/North American multicenter study","volume":"270","author":"Le Gall","year":"1993","journal-title":"Jama"},{"key":"10.1016\/j.eswa.2026.133464_bib0020","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.compchemeng.2017.10.008","article-title":"Machine learning: Overview of the recent progresses and implications for the process systems engineering field","volume":"114","author":"Lee","year":"2018","journal-title":"Computers & Chemical Engineering"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0021","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1186\/s12882-024-03538-6","article-title":"Deep learning algorithms for predicting renal replacement therapy initiation in CKD patients: A retrospective cohort study","volume":"25","author":"Leung","year":"2024","journal-title":"BMC Nephrology"},{"issue":"6","key":"10.1016\/j.eswa.2026.133464_bib0022","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"Lewis","year":"2012","journal-title":"IEEE Control Systems Magazine"},{"key":"10.1016\/j.eswa.2026.133464_bib0023","unstructured":"Li, L., Albert-Smet, I., & Faisal, A. A. (2020). Optimizing medical treatment for sepsis in intensive care: From reinforcement learning to pre-trial evaluation. arXiv preprint arXiv: 2003.06474,."},{"issue":"2","key":"10.1016\/j.eswa.2026.133464_bib0024","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1093\/ndt\/gfn560","article-title":"Intermittent versus continuous renal replacement therapy for acute kidney injury patients admitted to the intensive care unit: Results of a randomized clinical trial","volume":"24","author":"Lins","year":"2009","journal-title":"Nephrology Dialysis Transplantation"},{"key":"10.1016\/j.eswa.2026.133464_bib0025","unstructured":"Liu, J., Li, Y., Zhou, C., Xie, Y., Sun, Q., Shu, X., Li, P., Yang, C., Zhu, Y., Zhu, J. et al. (2025). TECM*: A data-driven assessment to reinforcement learning methods and application to heparin treatment strategy for surgical sepsis. arXiv preprint arXiv: 2512.10973,."},{"key":"10.1016\/j.eswa.2026.133464_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102726","article-title":"Value function assessment to different RL algorithms for heparin treatment policy of patients with sepsis in ICU","volume":"147","author":"Liu","year":"2024","journal-title":"Artificial Intelligence in Medicine"},{"issue":"2","key":"10.1016\/j.eswa.2026.133464_bib0027","doi-asserted-by":"crossref","DOI":"10.1186\/cc5713","article-title":"Acute kidney injury network: Report of an initiative to improve outcomes in acute kidney injury","volume":"11","author":"Mehta","year":"2007","journal-title":"Critical Care"},{"key":"10.1016\/j.eswa.2026.133464_bib0028","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv: 1312.5602,."},{"key":"10.1016\/j.eswa.2026.133464_bib0029","doi-asserted-by":"crossref","first-page":"94215","DOI":"10.1109\/ACCESS.2019.2928130","article-title":"Low-rank matrix completion: A contemporary survey","volume":"7","author":"Nguyen","year":"2019","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0030","doi-asserted-by":"crossref","first-page":"6920","DOI":"10.1038\/s41598-021-86419-4","article-title":"Optimal treatment recommendations for diabetes patients using the Markov decision process along with the South Korean electronic health records","volume":"11","author":"Oh","year":"2021","journal-title":"Scientific Reports"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0031","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1186\/s13054-016-1478-z","article-title":"Acute kidney injury 2016: Diagnosis and diagnostic workup","volume":"20","author":"Ostermann","year":"2016","journal-title":"Critical Care"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0032","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s41746-021-00388-6","article-title":"Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care","volume":"4","author":"Peine","year":"2021","journal-title":"NPJ Digital Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0033","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/RBME.2020.3013489","article-title":"Secure and robust machine learning for healthcare: A survey","volume":"14","author":"Qayyum","year":"2020","journal-title":"IEEE Reviews in Biomedical Engineering"},{"key":"10.1016\/j.eswa.2026.133464_bib0034","unstructured":"Raghu, A., Komorowski, M., Ahmed, I., Celi, L., Szolovits, P., & Ghassemi, M. (2017). Deep reinforcement learning for sepsis treatment. arXiv preprint arXiv: 1711.09602,."},{"issue":"5","key":"10.1016\/j.eswa.2026.133464_bib0035","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1038\/sj.ki.5002743","article-title":"The RIFLE criteria and mortality in acute kidney injury: A systematic review","volume":"73","author":"Ricci","year":"2008","journal-title":"Kidney International"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0036","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s10115-017-1038-0","article-title":"Effective sparse imputation of patient conditions in electronic medical records for emergency risk predictions","volume":"53","author":"Saha","year":"2017","journal-title":"Knowledge and Information Systems"},{"key":"10.1016\/j.eswa.2026.133464_bib0037","article-title":"Effects of continuous and intermittent renal replacement therapies among adult patients with acute kidney injury","volume":"13","author":"Schoenfelder","year":"2017","journal-title":"GMS Health Technology Assessment"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3278607","article-title":"Tensor completion algorithms in big data analytics","volume":"13","author":"Song","year":"2019","journal-title":"ACM Transactions on Knowledge Discovery From Data (TKDD)"},{"issue":"7","key":"10.1016\/j.eswa.2026.133464_bib0039","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (sepsis-related organ failure assessment) score to describe organ dysfunction\/failure: On behalf of the working group on sepsis-related problems of the european society of intensive care medicine (see contributors to the project in the appendix)","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Medicine"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0040","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1080\/0886022X.2020.1788581","article-title":"Sofa score is superior to apache-ii score in predicting the prognosis of critically ill patients with acute kidney injury undergoing continuous renal replacement therapy","volume":"42","author":"Wang","year":"2020","journal-title":"Renal Failure"},{"key":"10.1016\/j.eswa.2026.133464_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102811","article-title":"Clinical knowledge-guided deep reinforcement learning for sepsis antibiotic dosing recommendations","volume":"150","author":"Wang","year":"2024","journal-title":"Artificial Intelligence in Medicine"},{"key":"10.1016\/j.eswa.2026.133464_bib0042","series-title":"Ninth workshop on virtual intelligence\/dynamic neural networks","first-page":"510","article-title":"Stable adaptive control using new critic designs","volume":"vol. 3728","author":"Werbos","year":"1999"},{"issue":"7","key":"10.1016\/j.eswa.2026.133464_bib0043","doi-asserted-by":"crossref","first-page":"4285","DOI":"10.1109\/TSMC.2019.2931393","article-title":"A deep latent factor model for high-dimensional and sparse matrices in recommender systems","volume":"51","author":"Wu","year":"2019","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"10.1016\/j.eswa.2026.133464_bib0044","series-title":"2015 37th Annual international conference of the IEEE engineering in medicine and biology society (EMBC)","first-page":"6808","article-title":"Post-surgical complication prediction in the presence of low-rank missing data","author":"Wu","year":"2015"},{"key":"10.1016\/j.eswa.2026.133464_bib0045","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2023.1252630","article-title":"A narrative review on the application of artificial intelligence in renal ultrasound","volume":"13","author":"Xu","year":"2024","journal-title":"Frontiers in Oncology"},{"issue":"1","key":"10.1016\/j.eswa.2026.133464_bib0046","doi-asserted-by":"crossref","first-page":"4605","DOI":"10.1038\/s41598-023-30074-4","article-title":"Predicting outcomes of continuous renal replacement therapy using body composition monitoring: A deep-learning approach","volume":"13","author":"Yoo","year":"2023","journal-title":"Scientific Reports"},{"issue":"7","key":"10.1016\/j.eswa.2026.133464_bib0047","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1159\/000545988","article-title":"Long-term safety of \u201c4-hour\u201d hemoadsorption combined with hemodialysis in maintenance hemodialysis patients: A multicenter prospective cohort study","volume":"54","author":"Zhang","year":"2025","journal-title":"Blood Purification"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023730?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023730?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:46:34Z","timestamp":1783701994000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426023730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":47,"alternative-id":["S0957417426023730"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133464","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CNA : An AI-oriented comprehensive normalized assessment for healthy status and application to optimize RRT strategies by reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133464","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133464"}}