{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:42:08Z","timestamp":1762522928943},"reference-count":59,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:p>Large randomized trials in sepsis have generally failed to find effective novel treatments. This is increasingly attributed to patient heterogeneity, including heterogeneous cardiovascular changes in septic shock. We discuss the potential for machine learning systems to personalize cardiovascular resuscitation in sepsis. While the literature is replete with proofs of concept, the technological readiness of current systems is low, with a paucity of clinical trials and proven patient benefit. Systems may be vulnerable to confounding and poor generalization to new patient populations or contemporary patterns of care. Typical electronic health records do not capture rich enough data, at sufficient temporal resolution, to produce systems that make actionable treatment suggestions. To resolve these issues, we recommend a simultaneous focus on technical challenges and removing barriers to translation. This will involve improving data quality, adopting causally grounded models, prioritizing safety assessment and integration into healthcare workflows, conducting randomized clinical trials and aligning with regulatory requirements.<\/jats:p>","DOI":"10.1097\/cce.0000000000001087","type":"journal-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T14:02:41Z","timestamp":1715004161000},"page":"e1087","update-policy":"http:\/\/dx.doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Can Machine Learning Personalize Cardiovascular Therapy in Sepsis?"],"prefix":"10.1097","volume":"6","author":[{"given":"Finneas J. R.","family":"Catling","sequence":"first","affiliation":[{"name":"Institute of Healthcare Engineering, University College London, London, United Kingdom."},{"name":"Division of Anaesthetics, Pain Medicine, and Intensive Care, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myura","family":"Nagendran","sequence":"additional","affiliation":[{"name":"Division of Anaesthetics, Pain Medicine, and Intensive Care, Imperial College London, London, United Kingdom."},{"name":"UKRI Centre for Doctoral Training in AI for Healthcare, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Festor","sequence":"additional","affiliation":[{"name":"UKRI Centre for Doctoral Training in AI for Healthcare, Imperial College London, London, United Kingdom."},{"name":"Department of Computing, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuzanna","family":"Bien","sequence":"additional","affiliation":[{"name":"School of Life Course & Population Sciences, King\u2019s College London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Harris","sequence":"additional","affiliation":[{"name":"Department of Critical Care, University College London Hospital, London, United Kingdom."},{"name":"Institute of Health Informatics, University College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Aldo","family":"Faisal","sequence":"additional","affiliation":[{"name":"UKRI Centre for Doctoral Training in AI for Healthcare, Imperial College London, London, United Kingdom."},{"name":"Department of Computing, Imperial College London, London, United Kingdom."},{"name":"Institute of Artificial and Human Intelligence, Universit\u00e4t Bayreuth, Bayreuth, Germany"},{"name":"Department of Bioengineering, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony C.","family":"Gordon","sequence":"additional","affiliation":[{"name":"Division of Anaesthetics, Pain Medicine, and Intensive Care, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthieu","family":"Komorowski","sequence":"additional","affiliation":[{"name":"Division of Anaesthetics, Pain Medicine, and Intensive Care, Imperial College London, London, United Kingdom."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2024,5,6]]},"reference":[{"key":"R1-20240806","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (Sepsis-3).","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA"},{"key":"R2-20240806","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","article-title":"Global, regional, and national sepsis incidence and mortality, 1990-2017: Analysis for the Global Burden of Disease Study.","volume":"395","author":"Rudd","year":"2020","journal-title":"Lancet"},{"key":"R3-20240806","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.molmed.2014.01.007","article-title":"Why have clinical trials in sepsis failed?","volume":"20","author":"Marshall","year":"2014","journal-title":"Trends Mol Med"},{"key":"R4-20240806","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1056\/NEJMoa1701380","article-title":"Early, goal-directed therapy for septic shock\u2014a patient-level meta-analysis.","volume":"376","author":"Rowan","year":"2017","journal-title":"N Engl J Med"},{"key":"R5-20240806","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1056\/NEJMoa2212663","article-title":"Early restrictive or liberal fluid management for sepsis-induced hypotension.","volume":"388","author":"Shapiro","year":"2023","journal-title":"N Engl J Med"},{"key":"R6-20240806","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s13613-018-0379-5","article-title":"Predictors of response to fixed-dose vasopressin in adult patients with septic shock.","volume":"8","author":"Sacha","year":"2018","journal-title":"Ann Intensive Care"},{"key":"R7-20240806","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1007\/s00134-019-05596-z","article-title":"Cardiovascular clusters in septic shock combining clinical and echocardiographic parameters: A post hoc analysis.","volume":"45","author":"Geri","year":"2019","journal-title":"Intensive Care Med"},{"key":"R8-20240806","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1186\/s13054-020-2779-9","article-title":"Heterogeneity of cardiovascular response to standardized sepsis resuscitation.","volume":"24","author":"Guarracino","year":"2020","journal-title":"Crit Care"},{"key":"R9-20240806","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1007\/s00134-021-06506-y","article-title":"Surviving sepsis campaign: International guidelines for management of sepsis and septic shock 2021.","volume":"47","author":"Evans","year":"2021","journal-title":"Intensive Care Med"},{"key":"R10-20240806","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/s41581-019-0199-3","article-title":"Prognostic and predictive enrichment in sepsis.","volume":"16","author":"Stanski","year":"2020","journal-title":"Nat Rev Nephrol"},{"key":"R11-20240806","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/S2213-2600(16)00046-1","article-title":"Genomic landscape of the individual host response and outcomes in sepsis: A prospective cohort study.","volume":"4","author":"Davenport","year":"2016","journal-title":"Lancet Respir Med"},{"key":"R12-20240806","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1164\/rccm.201807-1419OC","article-title":"Transcriptomic signatures in sepsis and a differential response to steroids. From the VANISH randomized trial.","volume":"199","author":"Antcliffe","year":"2019","journal-title":"Am J Respir Crit Care Med"},{"key":"R13-20240806","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1186\/s13054-019-2375-z","article-title":"Subjective right ventricle assessment by echo qualified intensive care specialists: Assessing agreement with objective measures.","volume":"23","author":"Orde","year":"2019","journal-title":"Crit Care"},{"key":"R14-20240806","doi-asserted-by":"crossref","first-page":"e000234","DOI":"10.1136\/bmjresp-2017-000234","article-title":"Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: A randomised clinical trial.","volume":"4","author":"Shimabukuro","year":"2017","journal-title":"BMJ Open Respir Res"},{"key":"R15-20240806","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1038\/s41591-022-01894-0","article-title":"Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis.","volume":"28","author":"Adams","year":"2022","journal-title":"Nat Med"},{"key":"R16-20240806","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1038\/s41746-023-00986-6","article-title":"Impact of a deep learning sepsis prediction model on quality of care and survival.","volume":"7","author":"Boussina","year":"2024","journal-title":"NPJ Digit Med"},{"author":"Catling","journal-title":"medRxiv","article-title":"Data-driven decision support for individualised cardiovascular resuscitation in sepsis: A scoping review and primer for clinicians.","key":"R17-20240806"},{"key":"R18-20240806","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.cmpb.2019.05.009","article-title":"A machine learning approach for predicting urine output after fluid administration.","volume":"177","author":"Lin","year":"2019","journal-title":"Comput Methods Programs Biomed"},{"key":"R19-20240806","doi-asserted-by":"crossref","first-page":"4100209","DOI":"10.1109\/JTEHM.2019.2919020","article-title":"Reduced rank least squares for real-time short term estimation of mean arterial blood pressure in septic patients receiving norepinephrine.","volume":"7","author":"Tang","year":"2019","journal-title":"IEEE J Transl Eng Health Med"},{"key":"R20-20240806","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1097\/CCM.0000000000004842","article-title":"Sepsis subclasses: A framework for development and interpretation.","volume":"49","author":"DeMerle","year":"2021","journal-title":"Crit Care Med"},{"key":"R21-20240806","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1186\/s13054-018-2279-3","article-title":"Identification of subclasses of sepsis that showed different clinical outcomes and responses to amount of fluid resuscitation: A latent profile analysis.","volume":"22","author":"Zhang","year":"2018","journal-title":"Crit Care"},{"key":"R22-20240806","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1007\/s00134-022-06890-z","article-title":"Development and validation of novel sepsis subphenotypes using trajectories of vital signs.","volume":"48","author":"Bhavani","year":"2022","journal-title":"Intensive Care Med"},{"key":"R23-20240806","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1001\/jama.2019.5791","article-title":"Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis.","volume":"321","author":"Seymour","year":"2019","journal-title":"JAMA"},{"key":"R24-20240806","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","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":"R25-20240806","doi-asserted-by":"crossref","first-page":"102003","DOI":"10.1016\/j.artmed.2020.102003","article-title":"Transatlantic transferability of a new reinforcement learning model for optimizing haemodynamic treatment for critically ill patients with sepsis.","volume":"112","author":"Roggeveen","year":"2021","journal-title":"Artif Intell Med"},{"key":"R26-20240806","doi-asserted-by":"crossref","first-page":"e0275358","DOI":"10.1371\/journal.pone.0275358","article-title":"Superhuman performance on sepsis MIMIC-III data by distributional reinforcement learning.","volume":"17","author":"B\u00f6ck","year":"2022","journal-title":"PLoS One"},{"key":"R27-20240806","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/s41746-023-00755-5","article-title":"A value-based deep reinforcement learning model with human expertise in optimal treatment of sepsis.","volume":"6","author":"Wu","year":"2023","journal-title":"NPJ Digit Med"},{"author":"Joshi","journal-title":"arXiv","article-title":"Learning-to-defer for sequential medical decision-making under uncertainty.","key":"R28-20240806"},{"key":"R29-20240806","doi-asserted-by":"crossref","first-page":"R155","DOI":"10.1186\/cc7149","article-title":"Norepinephrine weaning in septic shock patients by closed loop control based on fuzzy logic.","volume":"12","author":"Merouani","year":"2008","journal-title":"Crit Care"},{"key":"R30-20240806","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.jbi.2016.12.010","article-title":"Septic shock prediction for ICU patients via coupled HMM walking on sequential contrast patterns.","volume":"66","author":"Ghosh","year":"2017","journal-title":"J Biomed Inform"},{"author":"Killian","journal-title":"arXiv [cs.LG]","article-title":"An empirical study of representation learning for reinforcement learning in healthcare.","key":"R31-20240806"},{"key":"R32-20240806","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1007\/s10994-021-05984-x","article-title":"Inverse reinforcement learning in contextual MDPs.","volume":"110","author":"Belogolovsky","year":"2021","journal-title":"Mach Learn"},{"key":"R33-20240806","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1001\/jama.2016.0288","article-title":"Assessment of clinical criteria for sepsis: For the third international consensus definitions for sepsis and septic shock (Sepsis-3).","volume":"315","author":"Seymour","year":"2016","journal-title":"JAMA"},{"key":"R34-20240806","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300032","article-title":"Evaluation of sepsis prediction models before onset of treatment.","volume":"1","author":"Kamran","year":"2024","journal-title":"NEJM AI"},{"key":"R35-20240806","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database.","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"year":"2020","article-title":"Global Report on the Epidemiology and Burden of Sepsis: Current Evidence, Identifying Gaps and Future Directions.","key":"R36-20240806"},{"key":"R37-20240806","first-page":"72","article-title":"Pragmatic recommendations for the management of COVID-19 patients with shock in low- and middle-income countries.","volume":"104","author":"Maximous","year":"2020","journal-title":"Am J Trop Med Hyg"},{"key":"R38-20240806","doi-asserted-by":"crossref","first-page":"12598","DOI":"10.1038\/s41598-020-69250-1","article-title":"Federated learning in medicine: Facilitating multi-institutional collaborations without sharing patient data.","volume":"10","author":"Sheller","year":"2020","journal-title":"Sci Rep"},{"author":"Gottesman","journal-title":"arXiv","article-title":"Evaluating reinforcement learning algorithms in observational health settings.","key":"R39-20240806"},{"key":"R40-20240806","doi-asserted-by":"crossref","first-page":"114476","DOI":"10.1016\/j.eswa.2020.114476","article-title":"Optimal sepsis patient treatment using human-in-the-loop artificial intelligence.","volume":"169","author":"Gupta","year":"2021","journal-title":"Expert Syst Appl"},{"author":"Xu","journal-title":"arXiv","article-title":"DeepRite: Deep recurrent inverse treatment weighting for adjusting time-varying confounding in modern longitudinal observational data.","key":"R41-20240806"},{"author":"Jeter","journal-title":"medRxiv","article-title":"Learning to treat hypotensive episodes in sepsis patients using a counterfactual reasoning framework.","key":"R42-20240806"},{"author":"Kausik","journal-title":"arXiv","article-title":"Offline policy evaluation and optimization under confounding.","key":"R43-20240806"},{"key":"R44-20240806","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1177\/09622802221122397","article-title":"Penalized Spline-Involved Tree-based (PenSIT) Learning for estimating an optimal dynamic treatment regime using observational data.","volume":"31","author":"Speth","year":"2022","journal-title":"Stat Methods Med Res"},{"key":"R45-20240806","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s12938-018-0455-y","article-title":"Next-generation, personalised, model-based critical care medicine: A state-of-the art review of in silico virtual patient models, methods, and cohorts, and how to validation them.","volume":"17","author":"Chase","year":"2018","journal-title":"Biomed Eng Online"},{"author":"Raghu","journal-title":"arXiv","article-title":"Deep reinforcement learning for sepsis treatment.","key":"R46-20240806"},{"key":"R47-20240806","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.3390\/jcm12041513","article-title":"Development of a reinforcement learning algorithm to optimize corticosteroid therapy in critically ill patients with sepsis.","volume":"12","author":"Bologheanu","year":"2023","journal-title":"J Clin Med"},{"key":"R48-20240806","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI.","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat Med"},{"author":"Madras","journal-title":"arXiv","article-title":"Predict responsibly: Improving fairness and accuracy by learning to defer.","key":"R49-20240806"},{"key":"R50-20240806","doi-asserted-by":"crossref","first-page":"m4786","DOI":"10.1136\/bmj.m4786","article-title":"Electronic health record alerts for acute kidney injury: Multicenter, randomized clinical trial.","volume":"372","author":"Wilson","year":"2021","journal-title":"BMJ"},{"key":"R51-20240806","doi-asserted-by":"crossref","first-page":"e100549","DOI":"10.1136\/bmjhci-2022-100549","article-title":"Assuring the safety of AI-based clinical decision support systems: A case study of the AI clinician for sepsis treatment.","volume":"29","author":"Festor","year":"2022","journal-title":"BMJ Health Care Inform"},{"key":"R52-20240806","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4496127","article-title":"Clinical Evaluation Framework Using Behavioural & Visual Attention Read-Outs for Explainable AI (XAI).","author":"Nagendran","year":"2023"},{"key":"R54-20240806","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients.","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern Med"},{"key":"R55-20240806","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1038\/s41746-022-00611-y","article-title":"Clinical artificial intelligence quality improvement: Towards continual monitoring and updating of AI algorithms in healthcare.","volume":"5","author":"Feng","year":"2022","journal-title":"NPJ Digit Med"},{"key":"R56-20240806","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1038\/s41591-022-01895-z","article-title":"Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing.","volume":"28","author":"Henry","year":"2022","journal-title":"Nat Med"},{"key":"R57-20240806","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1038\/s41591-023-02552-9","article-title":"Optimized glycemic control of type 2 diabetes with reinforcement learning: A proof-of-concept trial.","volume":"29","author":"Wang","year":"2023","journal-title":"Nat Med"},{"key":"R58-20240806","doi-asserted-by":"crossref","first-page":"e489","DOI":"10.1016\/S2589-7500(20)30186-2","article-title":"The myth of generalisability in clinical research and machine learning in health care.","volume":"2","author":"Futoma","year":"2020","journal-title":"Lancet Digit Health"},{"key":"R59-20240806","doi-asserted-by":"crossref","first-page":"2686","DOI":"10.1038\/s41591-023-02540-z","article-title":"External validation of AI models in health should be replaced with recurring local validation.","volume":"29","author":"Youssef","year":"2023","journal-title":"Nat Med"},{"key":"R63-20240806","doi-asserted-by":"crossref","first-page":"101","DOI":"10.36469\/jheor.2022.33951","article-title":"The potential cost and cost-effectiveness impact of using a machine learning algorithm for early detection of sepsis in intensive care units in Sweden.","volume":"9","author":"Ericson","year":"2022","journal-title":"J Health Econ Outcomes Res"}],"container-title":["Critical Care Explorations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/CCE.0000000000001087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T22:07:25Z","timestamp":1722982045000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/CCE.0000000000001087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":59,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1097\/cce.0000000000001087","relation":{},"ISSN":["2639-8028"],"issn-type":[{"type":"electronic","value":"2639-8028"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}