{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T03:17:34Z","timestamp":1792466254786,"version":"4.5.0"},"reference-count":36,"publisher":"American Medical Association (AMA)","issue":"19","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA"],"published-print":{"date-parts":[[2025,5,20]]},"abstract":"\n Importance<\/jats:title>\n Norepinephrine is the first-line vasopressor for patients with septic shock. When and whether a second agent, such as vasopressin, should be added is unknown.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To derive and validate a reinforcement learning model to determine the optimal initiation rule for vasopressin in adult, critically ill patients receiving norepinephrine for septic shock.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n Reinforcement learning was used to generate the optimal rule for vasopressin initiation to improve short-term and hospital outcomes, using electronic health record data from 3608 patients who met the Sepsis-3 shock criteria at 5 California hospitals from 2012 to 2023. The rule was evaluated in 628 patients from the California dataset and 3 external datasets comprising 10\u202f217 patients from 227 US hospitals, using weighted importance sampling and pooled logistic regression with inverse probability weighting.<\/jats:p>\n <\/jats:sec>\n \n Exposures<\/jats:title>\n Clinical, laboratory, and treatment variables grouped hourly for 120 hours in the electronic health record.<\/jats:p>\n <\/jats:sec>\n \n Main Outcome and Measure<\/jats:title>\n The primary outcome was in-hospital mortality.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The derivation cohort (n\u2009=\u20093608) included 2075 men (57%) and had a median (IQR) age of 63 (56-70) years and Sequential Organ Failure Assessment (SOFA) score at shock onset of 5 (3-7 [range, 0-24, with higher scores associated with greater mortality]). The validation cohorts (n\u2009=\u200910\u202f217) were 56% male (n\u2009=\u20095743) with a median (IQR) age of 67 (57-75) years and a SOFA score of 6 (4-9). In validation data, the model suggested vasopressin initiation in more patients (87% vs 31%), earlier relative to shock onset (median [IQR], 4 [1-8] vs 5 [1-14] hours), and at lower norepinephrine doses (median [IQR], 0.20 [0.08-0.45] vs 0.37 [0.17-0.69] \u00b5g\/kg\/min) compared with clinicians\u2019 actions. The rule was associated with a larger expected reward in validation data compared with clinician actions (weighted importance sampling difference, 31 [95% CI, 15-52]). The adjusted odds of hospital mortality were lower if vasopressin initiation was similar to the rule compared with different (odds ratio, 0.81 [95% CI, 0.73-0.91]), a finding consistent across external validation sets.<\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In adult patients with septic shock receiving norepinephrine, the use of vasopressin was variable. A reinforcement learning model developed and validated in several observational datasets recommended more frequent and earlier use of vasopressin than average care patterns and was associated with reduced mortality.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jama.2025.3046","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T04:30:38Z","timestamp":1742272238000},"page":"1688","source":"Crossref","is-referenced-by-count":88,"title":["Optimal Vasopressin Initiation in Septic Shock"],"prefix":"10.1001","volume":"333","author":[{"given":"Alexandre","family":"Kalimouttou","sequence":"first","affiliation":[{"name":"Inserm UMR 1153, Centre for Research in Epidemiology and Statistics (CRESS), ECSTRRA Team, Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 Sorbonne Paris Nord, Paris, France"},{"name":"Department of Anesthesia & Perioperative Care, Zuckerberg San Francisco General Hospital and Trauma Center, University of California, San Francisco"},{"name":"Department of Anesthesiology and Intensive Care Medicine, Grenoble Alpes University Hospital, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason N.","family":"Kennedy","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"},{"name":"Center for Research, Investigation, and Systems Modeling of Acute Illness, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Epidemiology & Biostatistics, University of California, San Francisco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harvineet","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Epidemiology & Biostatistics, University of California, San Francisco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suchi","family":"Saria","sequence":"additional","affiliation":[{"name":"Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Maryland"},{"name":"Department of Computer Science, Johns Hopkins University, Baltimore, Maryland"},{"name":"Department of Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland"},{"name":"Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland"},{"name":"Bayesian Health, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek C.","family":"Angus","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"},{"name":"Center for Research, Investigation, and Systems Modeling of Acute Illness, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher W.","family":"Seymour","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"},{"name":"Center for Research, Investigation, and Systems Modeling of Acute Illness, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Pirracchio","sequence":"additional","affiliation":[{"name":"Inserm UMR 1153, Centre for Research in Epidemiology and Statistics (CRESS), ECSTRRA Team, Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 Sorbonne Paris Nord, Paris, France"},{"name":"Department of Anesthesia & Perioperative Care, Zuckerberg San Francisco General Hospital and Trauma Center, University of California, San Francisco"},{"name":"Department of Epidemiology & Biostatistics, University of California, San Francisco"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","reference":[{"issue":"8","key":"joi250012r1","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1007\/s00134-020-06151-x","article-title":"Incidence and mortality of hospital- and ICU-treated sepsis: results from an updated and expanded systematic review and meta-analysis.","volume":"46","author":"Fleischmann-Struzek","year":"2020","journal-title":"Intensive Care Med"},{"issue":"8","key":"joi250012r2","doi-asserted-by":"publisher","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"},{"issue":"11","key":"joi250012r3","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1097\/CCM.0000000000005357","article-title":"Executive summary: Surviving Sepsis Campaign: international guidelines for the management of sepsis and septic shock 2021.","volume":"49","author":"Evans","year":"2021","journal-title":"Crit Care Med"},{"issue":"10","key":"joi250012r4","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1513\/AnnalsATS.201604-259OC","article-title":"Epidemiology of vasopressin use for adults with septic shock.","volume":"13","author":"Vail","year":"2016","journal-title":"Ann Am Thorac Soc"},{"key":"joi250012r6","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods.","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"joi250012r9","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center database for critical care research.","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci Data"},{"issue":"20","key":"joi250012r10","doi-asserted-by":"publisher","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"},{"issue":"7","key":"joi250012r14","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction\/failure.","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med"},{"key":"joi250012r17","first-page":"2","article-title":"Model selection for offline reinforcement learning: practical considerations for healthcare settings.","volume":"149","author":"Tang","year":"2021","journal-title":"Proc Mach Learn Res"},{"issue":"1","key":"joi250012r18","doi-asserted-by":"publisher","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 Digit Med"},{"issue":"11","key":"joi250012r19","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1038\/s41591-018-0253-x","article-title":"Individualized sepsis treatment using reinforcement learning.","volume":"24","author":"Saria","year":"2018","journal-title":"Nat Med"},{"issue":"28","key":"joi250012r20","doi-asserted-by":"publisher","first-page":"3661","DOI":"10.1002\/sim.6607","article-title":"Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies.","volume":"34","author":"Austin","year":"2015","journal-title":"Stat Med"},{"issue":"4","key":"joi250012r21","doi-asserted-by":"publisher","first-page":"268","DOI":"10.7326\/M16-2607","article-title":"Sensitivity analysis in observational research: introducing the E-value.","volume":"167","author":"VanderWeele","year":"2017","journal-title":"Ann Intern Med"},{"issue":"2","key":"joi250012r22","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1097\/MLR.0000000000001040","article-title":"Falsification tests for instrumental variable designs with an application to tendency to operate.","volume":"57","author":"Keele","year":"2019","journal-title":"Med Care"},{"issue":"8","key":"joi250012r23","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1001\/jama.2010.1205","article-title":"Minimizing bias due to confounding by indication in comparative effectiveness research: the importance of restriction.","volume":"304","author":"Psaty","year":"2010","journal-title":"JAMA"},{"issue":"6","key":"joi250012r24","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1111\/j.1532-5415.1999.tb01603.x","article-title":"Assessment and control for confounding by indication in observational studies.","volume":"47","author":"Psaty","year":"1999","journal-title":"J Am Geriatr Soc"},{"issue":"10","key":"joi250012r25","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery.","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"joi250012r26","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102749","article-title":"Advanced decision support system for individuals with diabetes on multiple daily injections therapy using reinforcement learning and nearest-neighbors: in-silico and clinical results.","volume":"148","author":"Jafar","year":"2024","journal-title":"Artif Intell Med"},{"issue":"1","key":"joi250012r27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-024-01028-5","article-title":"The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial.","volume":"7","author":"Lauffenburger","year":"2024","journal-title":"Digit Med"},{"issue":"9","key":"joi250012r28","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1056\/NEJMoa067373","article-title":"Vasopressin versus norepinephrine infusion in patients with septic shock.","volume":"358","author":"Russell","year":"2008","journal-title":"N Engl J Med"},{"issue":"3","key":"joi250012r29","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1378\/chest.120.3.989","article-title":"Physiology of vasopressin relevant to management of septic shock.","volume":"120","author":"Holmes","year":"2001","journal-title":"Chest"},{"issue":"5","key":"joi250012r30","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1161\/01.CIR.95.5.1122","article-title":"Vasopressin deficiency contributes to the vasodilation of septic shock.","volume":"95","author":"Landry","year":"1997","journal-title":"Circulation"},{"issue":"3","key":"joi250012r31","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1097\/00003246-200203000-00001","article-title":"Depletion of neurohypophyseal content of vasopressin in septic shock.","volume":"30","author":"Sharshar","year":"2002","journal-title":"Crit Care Med"},{"issue":"6","key":"joi250012r32","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1097\/01.CCM.0000063046.82359.4A","article-title":"Circulating vasopressin levels in septic shock.","volume":"31","author":"Sharshar","year":"2003","journal-title":"Crit Care Med"},{"issue":"1","key":"joi250012r33","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1152\/physrev.1992.72.1.231","article-title":"Long-term control of arterial blood pressure.","volume":"72","author":"Cowley","year":"1992","journal-title":"Physiol Rev"},{"issue":"6464","key":"joi250012r34","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations.","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"joi250012r35","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.jcrc.2021.11.016","article-title":"An international survey of adherence to Surviving Sepsis Campaign guidelines 2016 regarding fluid resuscitation and vasopressors in the initial management of septic shock.","volume":"68","author":"Bitton","year":"2022","journal-title":"J Crit Care"},{"issue":"1","key":"joi250012r36","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/s41746-022-00708-4","article-title":"An interpretable RL framework for pre-deployment modeling in ICU hypotension management.","volume":"5","author":"Zhang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"joi250012r13","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316511","volume-title":"Simulation and the Monte Carlo Method","author":"Rubinstein","year":"1981"},{"key":"joi250012r5","unstructured":"Sutton? RS, Barto? AG. The reinforcement learning problem. 1998. Accessed July 3, 2023. http:\/\/incompleteideas.net\/book\/first\/Chap3PrePub.pdf"},{"key":"joi250012r7","unstructured":"UCSF Data. How to get de-identified clinical data for cohort studies, pattern recognition, and more. Accessed January 12, 2024. https:\/\/data.ucsf.edu\/research\/deid-data"},{"key":"joi250012r8","unstructured":"Johnson? A, Bulgarelli? L, Pollard? T, Horng? S, Celi? LA, Mark? R. MIMIC-IV. PhysioNet. March 16, 2021. Accessed March 3, 2025. https:\/\/physionet.org\/content\/mimiciv\/1.0\/"},{"key":"joi250012r11","unstructured":"Futoma? J, Hughes? M, Doshi-Velez? F. POPCORN: Partially Observed Prediction Constrained Reinforcement Learning. March 31, 2020. Accessed March 3, 2025. https:\/\/finale.seas.harvard.edu\/sites\/g\/files\/omnuum4281\/files\/finale\/files\/popcorn_partially_observed_prediction_constrained_reinforcement_learning.pdf"},{"key":"joi250012r12","unstructured":"Ernst? D, Geurts? P, Wehenkel? L. Tree-based batch mode reinforcement learning.? J Mach Learn Res. April 2005. Accessed March 3, 2025. https:\/\/www.jmlr.org\/papers\/volume6\/ernst05a\/ernst05a.pdf"},{"key":"joi250012r15","unstructured":"Voloshin? C, Le? HM, Jiang? N, Yue? Y. Empirical study of off-policy policy evaluation for reinforcement learning. arXiv. Revised November 27, 2021. Accessed March 3, 2025. http:\/\/arxiv.org\/abs\/1911.06854"},{"key":"joi250012r16","unstructured":"Precup? D, Sutton? RS, Singh? S. Eligibility traces for off-policy policy evaluation. Accessed April 23, 2023. https:\/\/scholarworks.umass.edu\/cgi\/viewcontent.cgi?article=1079&context=cs_faculty_pubs"}],"container-title":["JAMA"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jama\/articlepdf\/2831858\/jama_kalimouttou_2025_oi_250012_1746722703.30973.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T11:03:29Z","timestamp":1747739009000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jama\/fullarticle\/2831858"}},"subtitle":["The OVISS Reinforcement Learning Study"],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":36,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,5,20]]}},"URL":"https:\/\/doi.org\/10.1001\/jama.2025.3046","relation":{},"ISSN":["0098-7484"],"issn-type":[{"value":"0098-7484","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5,20]]}}}