{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T01:15:57Z","timestamp":1793495757868,"version":"4.5.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early hemodynamic stabilization after vasopressor initiation in septic shock is heterogeneous and difficult to predict. We aimed to develop and externally validate interpretable machine learning models for predicting early hemodynamic stabilization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study used MIMIC-IV for model development and internal validation and eICU for external validation. Adult ICU patients with septic shock receiving vasopressors were included. Dynamic clinical features during the first 6\u2005h after vasopressor initiation were used to predict stabilization during 6\u201324\u2005h, defined by sustained mean arterial pressure (MAP) control without vasopressor escalation or increased norepinephrine-equivalent dose. Seven machine learning models were compared. Performance was assessed using discrimination, calibration, Brier score, decision curve analysis, external validation, and SHAP.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The MIMIC-IV and eICU cohorts included 3,445 and 453 patients, with stabilization rates of 41.77% and 32.67%, respectively. Gradient boosting machine (GBM) showed the best overall performance, with an AUC of 0.720 and Brier score of 0.209 in internal validation and an AUC of 0.730 and Brier score of 0.192 in external validation. At the training-derived threshold, external sensitivity and specificity were 0.466 and 0.797. SHAP identified early MAP stability, lactate clearance, platelet count, renal function, inflammatory burden, and vasopressor intensity as major predictors. The stabilization endpoint was associated with ICU and hospital mortality and remained robust to alternative MAP definitions. However, predictive performance was substantially driven by proximal hemodynamic features, particularly MAP trajectories, and the full GBM did not consistently outperform simpler hemodynamic benchmarks externally.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Early dynamic clinical features provided moderate discrimination for predicting hemodynamic stabilization after vasopressor initiation, with similar external performance. The model should be interpreted as a structured risk-stratification tool rather than a measure of pharmacological vasopressor responsiveness. Prospective validation is required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1920329","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:20:26Z","timestamp":1789539626000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable machine learning models using early dynamic clinical features to predict early hemodynamic stabilization after vasopressor initiation in patients with septic shock: development in MIMIC-IV and external validation in eICU"],"prefix":"10.3389","volume":"13","author":[{"given":"Shu-jiao","family":"Lu","sequence":"first","affiliation":[{"name":"Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze-kun","family":"Wei","sequence":"additional","affiliation":[{"name":"Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo-chen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Emergency Center, Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian-yu","family":"Bi","sequence":"additional","affiliation":[{"name":"Department of Emergency Center, Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le-run","family":"Zong","sequence":"additional","affiliation":[{"name":"Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Kong","sequence":"additional","affiliation":[{"name":"Department of Emergency Center, Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei-hu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Emergency Center, Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","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":"J Am Med Assoc"},{"key":"B2","doi-asserted-by":"publisher","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":"B3","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1056\/NEJMoa1312173","article-title":"High versus low blood-pressure target in patients with septic shock","volume":"370","author":"Asfar","year":"2014","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1097\/01.CCM.0000132904.35713.A7","article-title":"Early lactate clearance is associated with improved outcome in severe sepsis and septic shock","volume":"32","author":"Nguyen","year":"2004","journal-title":"Crit Care Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.jcrc.2020.11.002","article-title":"Vasopressor dose equivalence: a scoping review and suggested formula","volume":"61","author":"Goradia","year":"2021","journal-title":"J Crit Care"},{"key":"B6","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1002\/phar.2683","article-title":"Machine learning to predict vasopressin responsiveness in patients with septic shock","volume":"42","author":"Scheibner","year":"2022","journal-title":"Pharmacotherapy"},{"key":"B7","doi-asserted-by":"publisher","first-page":"105257","DOI":"10.1016\/j.ebiom.2024.105257","article-title":"Blood pressure response index and clinical outcomes in patients with septic shock: a multicenter cohort study","volume":"106","author":"Chen","year":"2024","journal-title":"EBioMedicine"},{"key":"B8","doi-asserted-by":"publisher","first-page":"850532","DOI":"10.3389\/fmed.2022.850532","article-title":"Interpretable machine learning for early prediction of in-hospital mortality in ICU patients with sepsis","volume":"9","author":"Hu","year":"2022","journal-title":"Front Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"155269","DOI":"10.1016\/j.jcrc.2025.155269","article-title":"Septic shock: past, present, and perspectives","volume":"91","author":"Plata-Menchaca","year":"2026","journal-title":"J Crit Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e078378","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":"Br Med J"},{"key":"B11","doi-asserted-by":"publisher","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":"Sci Data"},{"key":"B12","doi-asserted-by":"publisher","first-page":"180178","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"},{"key":"B13","first-page":"546","article-title":"Predicting sepsis onset in ICU patients using machine learning and feature section: a case study of MIMIC-IV data","author":"Shan","year":"2024"},{"key":"B14","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Making"},{"key":"B15","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B16","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1056\/NEJMoa010307","article-title":"Early goal-directed therapy in the treatment of severe sepsis and septic shock","volume":"345","author":"Rivers","year":"2001","journal-title":"N Engl J Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1001\/jama.2010.158","article-title":"Lactate clearance vs central venous oxygen saturation as goals of early sepsis therapy: a randomized clinical trial","volume":"303","author":"Jones","year":"2010","journal-title":"J Am Med Assoc"},{"key":"B19","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1007\/s00134-018-5085-0","article-title":"The surviving sepsis campaign bundle: 2018 update","volume":"44","author":"Levy","year":"2018","journal-title":"Intensive Care Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1056\/NEJMoa1703058","article-title":"Time to treatment and mortality during mandated emergency care for sepsis","volume":"376","author":"Seymour","year":"2017","journal-title":"N Engl J Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1001\/jama.2019.0071","article-title":"Effect of a resuscitation strategy targeting peripheral perfusion status vs serum lactate levels on 28-day mortality among patients with septic shock: the ANDROMEDA-SHOCK randomized clinical trial","volume":"321","author":"Hern\u00e1ndez","year":"2019","journal-title":"J Am Med Assoc"},{"key":"B22","doi-asserted-by":"publisher","first-page":"5658","DOI":"10.3390\/jcm12175658","article-title":"Machine learning-based early prediction of sepsis using electronic health records: a systematic review","volume":"12","author":"Islam","year":"2023","journal-title":"J Clin Med"},{"key":"B23","doi-asserted-by":"publisher","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":"B24","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","article-title":"An interpretable machine learning model for accurate prediction of sepsis in the ICU","volume":"46","author":"Nemati","year":"2018","journal-title":"Crit Care Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1016\/j.jelectrocard.2017.08.013","article-title":"Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics","volume":"50","author":"Shashikumar","year":"2017","journal-title":"J Electrocardiol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1056\/NEJMoa1401602","article-title":"A randomized trial of protocol-based care for early septic shock","volume":"370","author":"Yealy","year":"2014","journal-title":"N Engl J Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1056\/NEJMoa1404380","article-title":"Goal-directed resuscitation for patients with early septic shock","volume":"371","author":"Peake","year":"2014","journal-title":"N Engl J Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e074820","DOI":"10.1136\/bmj-2023-074820","article-title":"Evaluation of clinical prediction models (part 2): how to undertake an external validation study","volume":"384","author":"Riley","year":"2024","journal-title":"Br Med J"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1056\/NEJMoa1500896","article-title":"Trial of early, goal-directed resuscitation for septic shock","volume":"372","author":"Mouncey","year":"2015","journal-title":"N Engl J Med"},{"key":"B30","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"},{"key":"B31","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1001\/jama.2016.10485","article-title":"Effect of early vasopressin vs norepinephrine on kidney failure in patients with septic shock: the VANISH randomized clinical trial","volume":"316","author":"Gordon","year":"2016","journal-title":"J Am Med Assoc"},{"key":"B32","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1056\/NEJMoa0907118","article-title":"Comparison of dopamine and norepinephrine in the treatment of shock","volume":"362","author":"De Backer","year":"2010","journal-title":"N Engl J Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1164\/rccm.201806-1034OC","article-title":"Early use of norepinephrine in septic shock resuscitation (CENSER): a randomized trial","volume":"199","author":"Permpikul","year":"2019","journal-title":"Am J Respir Crit Care Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1795","DOI":"10.1007\/s00134-014-3525-z","article-title":"Consensus on circulatory shock and hemodynamic monitoring","volume":"40","author":"Cecconi","year":"2014","journal-title":"Intensive Care Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1164\/rccm.200912-1918OC","article-title":"Early lactate-guided therapy in intensive care unit patients: a multicenter, open-label, randomized controlled trial","volume":"182","author":"Jansen","year":"2010","journal-title":"Am J Respir Crit Care Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"B37","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"B38","doi-asserted-by":"publisher","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"Probast: a tool to assess the risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann Intern Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e074821","DOI":"10.1136\/bmj-2023-074821","article-title":"Evaluation of clinical prediction models (part 3): calculating the sample size required for an external validation study","volume":"384","author":"Riley","year":"2024","journal-title":"Br Med J"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1920329\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:20:27Z","timestamp":1789539627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1920329\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":39,"alternative-id":["10.3389\/fmed.2026.1920329"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1920329","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1920329"}}