{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T11:40:11Z","timestamp":1759059611443,"version":"3.44.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061171","type":"print"},{"value":"9783032061188","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06118-8_18","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T11:22:50Z","timestamp":1759058570000},"page":"304-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Offline Reinforcement Learning for\u00a0Community-Acquired Pneumonia Management: A Feasibility Study"],"prefix":"10.1007","author":[{"given":"Alex","family":"Beeson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keith","family":"Couper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Montana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"18_CR1","unstructured":"An, G., Moon, S., Kim, J.H., Song, H.O.: Uncertainty-based offline reinforcement learning with diversified Q-ensemble. In: Advances in Neural Information Processing Systems, vol. 34, pp. 7436\u20137447 (2021)"},{"issue":"1","key":"18_CR2","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s10994-023-06458-y","volume":"113","author":"A Beeson","year":"2024","unstructured":"Beeson, A., Montana, G.: Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning. Mach. Learn. 113(1), 443\u2013488 (2024)","journal-title":"Mach. Learn."},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.jclinepi.2021.11.007","volume":"142","author":"T Bigirumurame","year":"2022","unstructured":"Bigirumurame, T., Uwimpuhwe, G., Wason, J.: Sequential multiple assignment randomized trial studies should report all key components: a systematic review. J. Clin. Epidemiol. 142, 152\u2013160 (2022)","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"18_CR4","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1146\/annurev-statistics-022513-115553","volume":"1","author":"B Chakraborty","year":"2014","unstructured":"Chakraborty, B., Murphy, S.A.: Dynamic treatment regimes. Ann. Rev. Stat. Appl. 1(1), 447\u2013464 (2014)","journal-title":"Ann. Rev. Stat. Appl."},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41479-017-0039-9","volume":"9","author":"J Chalmers","year":"2017","unstructured":"Chalmers, J., Campling, J., Ellsbury, G., Hawkey, P.M., Madhava, H., Slack, M.: Community-acquired pneumonia in the United Kingdom: a call to action. Pneumonia 9, 1\u20136 (2017)","journal-title":"Pneumonia"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, L.F., Prasad, N., Engelhardt, B.E.: An optimal policy for patient laboratory tests in intensive care units. In: BIOCOMPUTING 2019: Proceedings of the Pacific Symposium, pp. 320\u2013331. World Scientific (2018)","DOI":"10.1142\/9789813279827_0029"},{"key":"18_CR7","unstructured":"Fujimoto, S., Conti, E., Ghavamzadeh, M., Pineau, J.: Benchmarking batch deep reinforcement learning algorithms. arXiv preprint arXiv:1910.01708 (2019)"},{"key":"18_CR8","unstructured":"Fujimoto, S., Gu, S.S.: A minimalist approach to offline reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 20132\u201320145 (2021)"},{"key":"18_CR9","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062. PMLR (2019)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Hochreiter, S.: Long Short-Term Memory. Neural Computation. MIT-Press (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Hu, Q., Yue, W.: Markov Decision Processes with Their Applications, vol.\u00a014. Springer, New York (2007). https:\/\/doi.org\/10.1007\/978-0-387-36951-8","DOI":"10.1007\/978-0-387-36951-8"},{"issue":"1","key":"18_CR12","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3390\/make4010009","volume":"4","author":"M Hutsebaut-Buysse","year":"2022","unstructured":"Hutsebaut-Buysse, M., Mets, K., Latr\u00e9, S.: Hierarchical reinforcement learning: a survey and open research challenges. Mach. Learn. Knowl. Extr. 4(1), 172\u2013221 (2022)","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"18_CR13","unstructured":"Kaplan, W., Wirtz, V., Mantel-Teeuwisse, A., Stolk, P., Duthey, B.: Priority medicines for Europe and the world 2013 update. Technical report, World Health Organisation (2013)"},{"issue":"11","key":"18_CR14","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","volume":"24","author":"M Komorowski","year":"2018","unstructured":"Komorowski, M., Celi, L.A., Badawi, O., Gordon, A.C., Faisal, A.A.: The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat. Med. 24(11), 1716\u20131720 (2018)","journal-title":"Nat. Med."},{"key":"18_CR15","unstructured":"Kostrikov, I., Nair, A., Levine, S.: Offline reinforcement learning with implicit Q-learning. In: International Conference on Learning Representations (2021)"},{"key":"18_CR16","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1179\u20131191 (2020)"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Lange, S., Gabel, T., Riedmiller, M.: Batch Reinforcement Learning, vol. 12, pp. 45\u201373. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_2","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"18_CR18","unstructured":"Le, H., Voloshin, C., Yue, Y.: Batch policy learning under constraints. In: International Conference on Machine Learning, pp. 3703\u20133712. PMLR (2019)"},{"key":"18_CR19","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"issue":"5","key":"18_CR20","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1136\/thorax.58.5.377","volume":"58","author":"WS Lim","year":"2003","unstructured":"Lim, W.S., et al.: Defining community acquired pneumonia severity on presentation to hospital: an international derivation and validation study. Thorax 58(5), 377\u2013382 (2003)","journal-title":"Thorax"},{"key":"18_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102726","volume":"147","author":"J Liu","year":"2024","unstructured":"Liu, J., et al.: Value function assessment to different RL algorithms for heparin treatment policy of patients with sepsis in ICU. Artif. Intell. Med. 147, 102726 (2024)","journal-title":"Artif. Intell. Med."},{"issue":"7","key":"18_CR22","doi-asserted-by":"publisher","DOI":"10.2196\/18477","volume":"22","author":"S Liu","year":"2020","unstructured":"Liu, S., See, K.C., Ngiam, K.Y., Celi, L.A., Sun, X., Feng, M.: Reinforcement learning for clinical decision support in critical care: comprehensive review. J. Med. Internet Res. 22(7), e18477 (2020)","journal-title":"J. Med. Internet Res."},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lopez-Martinez, D., Eschenfeldt, P., Ostvar, S., Ingram, M., Hur, C., Picard, R.: Deep reinforcement learning for optimal critical care pain management with morphine using dueling double-deep Q networks. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3960\u20133963. IEEE (2019)","DOI":"10.1109\/EMBC.2019.8857295"},{"key":"18_CR24","unstructured":"Luo, J., Dong, P., Wu, J., Kumar, A., Geng, X., Levine, S.: Action-quantized offline reinforcement learning for robotic skill learning. In: 7th Annual Conference on Robot Learning (2023)"},{"issue":"9","key":"18_CR25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0075131","volume":"8","author":"ER Millett","year":"2013","unstructured":"Millett, E.R., Quint, J.K., Smeeth, L., Daniel, R.M., Thomas, S.L.: Incidence of community-acquired lower respiratory tract infections and pneumonia among older adults in the united kingdom: a population-based study. PLoS ONE 8(9), e75131 (2013)","journal-title":"PLoS ONE"},{"key":"18_CR26","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"10","key":"18_CR27","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1002\/sim.2022","volume":"24","author":"SA Murphy","year":"2005","unstructured":"Murphy, S.A.: An experimental design for the development of adaptive treatment strategies. Stat. Med. 24(10), 1455\u20131481 (2005)","journal-title":"Stat. Med."},{"key":"18_CR28","unstructured":"Prasad, N., Cheng, L.F., Chivers, C., Draugelis, M., Engelhardt, B.E.: A reinforcement learning approach to weaning of mechanical ventilation in intensive care units. arXiv preprint arXiv:1704.06300 (2017)"},{"key":"18_CR29","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"18_CR30","unstructured":"Thrun, S., Schwartz, A.: Issues in using function approximation for reinforcement learning. In: Proceedings of the Fourth Connectionist Models Summer School, Hillsdale, NJ, vol.\u00a0255, p.\u00a0263 (1993)"},{"issue":"2","key":"18_CR31","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s00134-019-05519-y","volume":"45","author":"A Torres","year":"2019","unstructured":"Torres, A., et al.: Challenges in severe community-acquired pneumonia: a point-of-view review. Intensive Care Med. 45(2), 159\u2013171 (2019). https:\/\/doi.org\/10.1007\/s00134-019-05519-y","journal-title":"Intensive Care Med."},{"key":"18_CR32","unstructured":"University Hospital Birmingham NHS Foundation Trust: Adult guidelines for antimicrobial prescribing. https:\/\/www.uhb.nhs.uk\/Downloads\/pdf\/controlled-documents\/AntimicrobialPrescribingGuidelines.pdf. Accessed 1 Sept 2023"},{"issue":"12","key":"18_CR33","doi-asserted-by":"publisher","first-page":"6690","DOI":"10.1002\/mp.12625","volume":"44","author":"HH Tseng","year":"2017","unstructured":"Tseng, H.H., Luo, Y., Cui, S., Chien, J.T., Ten Haken, R.K., Naqa, I.E.: Deep reinforcement learning for automated radiation adaptation in lung cancer. Med. Phys. 44(12), 6690\u20136705 (2017)","journal-title":"Med. Phys."},{"key":"18_CR34","unstructured":"Uehara, M., Shi, C., Kallus, N.: A review of off-policy evaluation in reinforcement learning. arXiv preprint arXiv:2212.06355 (2022)"},{"key":"18_CR35","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"18_CR36","unstructured":"Weng, W.H., Gao, M., He, Z., Yan, S., Szolovits, P.: Representation and reinforcement learning for personalized glycemic control in septic patients. arXiv preprint arXiv:1712.00654 (2017)"},{"issue":"3","key":"18_CR37","first-page":"10","volume":"1","author":"TL Wiemken","year":"2017","unstructured":"Wiemken, T.L., et al.: Predicting 30-day mortality in hospitalized patients with community-acquired pneumonia using statistical and machine learning approaches. Univ. Louisville J. Respir. Infect. 1(3), 10 (2017)","journal-title":"Univ. Louisville J. Respir. Infect."},{"issue":"3","key":"18_CR38","first-page":"729","volume":"12","author":"MA Wiering","year":"2012","unstructured":"Wiering, M.A., Van Otterlo, M.: Reinforcement learning. Adapt. Learn. Optim. 12(3), 729 (2012)","journal-title":"Adapt. Learn. Optim."},{"issue":"1","key":"18_CR39","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41746-023-00755-5","volume":"6","author":"X Wu","year":"2023","unstructured":"Wu, X., Li, R., He, Z., Yu, T., Cheng, C.: A value-based deep reinforcement learning model with human expertise in optimal treatment of sepsis. NPJ Digit. Med. 6(1), 15 (2023)","journal-title":"NPJ Digit. Med."},{"key":"18_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107280","volume":"229","author":"CY Yang","year":"2023","unstructured":"Yang, C.Y., Shiranthika, C., Wang, C.Y., Chen, K.W., Sumathipala, S.: Reinforcement learning strategies in cancer chemotherapy treatments: a review. Comput. Methods Programs Biomed. 229, 107280 (2023)","journal-title":"Comput. Methods Programs Biomed."},{"issue":"1","key":"18_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3477600","volume":"55","author":"C Yu","year":"2021","unstructured":"Yu, C., Liu, J., Nemati, S., Yin, G.: Reinforcement learning in healthcare: a survey. ACM Comput. Surv. (CSUR) 55(1), 1\u201336 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06118-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T11:22:59Z","timestamp":1759058579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06118-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032061171","9783032061188"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06118-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}