{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:50:59Z","timestamp":1787028659117,"version":"build-2736575974"},"reference-count":32,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Septic shock is a heterogeneous syndrome with diverse clinical presentations and pathophysiology, yet current management guidelines largely treat it as a homogenous entity. Early risk stratification relies on lactate and different predictive scoring systems, which may not capture the underlying heterogeneity in host responses. Aim: To identify discrete subphenotypes of septic shock using admission demographics and laboratory parameters, and to evaluate their relationship with in-hospital outcomes. Methods: We conducted a retrospective multicenter cohort study of 10,462 adult patients with ICD-10-defined septic shock admitted to intensive care units between 2014 and 2015. We used Two-Step Cluster Analysis using log-likelihood distance and the Bayesian Information Criterion to identify two distinct phenotypes. We compared clusters on baseline characteristics, in-hospital outcomes including mortality, days on mechanical ventilation, vasopressor use, acute kidney injury (AKI), AKI requiring renal replacement therapy (RRT), and ICU and hospital lengths of stay. Results: We identified two clusters (Cluster 1, n = 5355 and Cluster 2, n = 5107) in our study. Cluster 1 showed greater biochemical severity at presentation, including higher median lactate (2.40 vs. 2.20 mmol L\u22121; p &lt; 0.001), serum creatinine (1.39 vs. 1.20 mg dL\u22121; p &lt; 0.001), blood urea nitrogen (28 vs. 25 mg dL\u22121; p &lt; 0.001), and neutrophil-to-lymphocyte ratio (11.12 vs. 10.38; p &lt; 0.001), and a higher mean SOFA score (7.05 \u00b1 3.85 vs. 6.76 \u00b1 3.87; p &lt; 0.001). Despite this, Cluster 1 required mechanical ventilation more frequently (46.1% vs. 42.2%; p &lt; 0.001) and had a higher incidence of AKI (58.1% vs. 55.6%; p = 0.009), including more stage 3 AKI (17.2% vs. 15.2%; p &lt; 0.001) and dialysis (6.6% vs. 5.2%; p = 0.005), yet experienced similar in-hospital mortality (15.4% vs. 15.8%; p = 0.615) and comparable ICU (2.18 vs. 2.26 days; p = 0.254) and hospital lengths of stay (6.63 vs. 6.80 days; p = 0.251). Conclusions: Two septic shock phenotypes were identified, one with marked early organ dysfunction (Cluster 1) and another with milder initial derangements (Cluster 2), yet both showed convergent short-term mortality and lengths of stay despite divergent support needs. These results challenge reliance on single-parameter severity markers and underscore the need for phenotype-guided risk stratification and personalized management strategies in septic shock.<\/jats:p>","DOI":"10.3390\/jcm14134450","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T07:42:34Z","timestamp":1750664554000},"page":"4450","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised Machine Learning in Identification of Septic Shock Phenotypes and Their In-Hospital Outcomes: A Multicenter Cohort Study"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8557-9880","authenticated-orcid":false,"given":"Song Peng","family":"Ang","sequence":"first","affiliation":[{"name":"Department of Medicine, Division of Cardiology, Sarver Heart Center, University of Arizona College of Medicine, Tucson, AZ 85724, USA"},{"name":"Department of Medicine, Rutgers Health\/Community Medical Center, Toms River, NJ 08755, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia Ee","family":"Chia","sequence":"additional","affiliation":[{"name":"Department of Medicine, Texas Tech University Health Science Center, El Paso, TX 79905, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunseuk","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Medicine, Rutgers Health\/Community Medical Center, Toms River, NJ 08755, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Jose","family":"Lorenzo-Capps","sequence":"additional","affiliation":[{"name":"Department of Medicine, Rutgers Health\/Community Medical Center, Toms River, NJ 08755, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madison","family":"Laezzo","sequence":"additional","affiliation":[{"name":"Department of Medicine, Hackensack Meridian School of Medicine, Nutley, NJ 07110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7851-0498","authenticated-orcid":false,"given":"Jose","family":"Iglesias","sequence":"additional","affiliation":[{"name":"Department of Medicine, Hackensack Meridian School of Medicine, Nutley, NJ 07110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Komorowski, M., Green, A., Tatham, K.C., Seymour, C., and Antcliffe, D. (2022). Sepsis biomarkers and diagnostic tools with a focus on machine learning. EBioMedicine, 86.","DOI":"10.1016\/j.ebiom.2022.104394"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"864","DOI":"10.15585\/mmwr.mm6533e1","article-title":"Vital Signs: Epidemiology of Sepsis: Prevalence of Health Care Factors and Opportunities for Prevention","volume":"65","author":"Novosad","year":"2016","journal-title":"MMWR Morb. Mortal. Wkly. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ang, S.P., Chia, J.E., Gregory, B., and Iglesias, J. (2025). Sex differences in trends and outcomes among patients with septic shock in the United States. Am. J. Med. Sci., online ahead of print.","DOI":"10.1016\/j.amjms.2025.05.010"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Espinal, C., Cort\u00e9s, E., P\u00e9rez-Madrigal, A., Saludes, P., Gil, A., Caballer, A., Nogales, S., Gruartmoner, G., and Mesquida, J. (2024). Evaluating tissue hypoxia and the response to fluid administration in septic shock patients: A metabolic cluster analysis. BMC Anesthesiol., 24.","DOI":"10.1186\/s12871-024-02662-y"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e1063","DOI":"10.1097\/CCM.0000000000005337","article-title":"Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock 2021","volume":"49","author":"Evans","year":"2021","journal-title":"Crit. Care Med."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Peng, W., and Zheng, X. (2024). The prognostic value of the combined neutrophil-to-lymphocyte ratio (NLR) and neutrophil-to-platelet ratio (NPR) in sepsis. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-64469-8"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ang, S.P., Chia, J.E., Jaiswal, V., Hanif, M., and Iglesias, J. (2024). Prognostic Value of Neutrophil-to-Lymphocyte Ratio in Patients with Acute Decompensated Heart Failure: A Meta-Analysis. J. Clin. Med., 13.","DOI":"10.3390\/jcm13051212"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Iglesias, J., Vassallo, A., Ilagan, J., Ang, S.P., Udongwo, N., Mararenko, A., Alshami, A., Patel, D., Elbaga, Y., and Levine, J.S. (2023). Acute Kidney Injury Associated with Severe SARS-CoV-2 Infection: Risk Factors for Morbidity and Mortality and a Potential Benefit of Combined Therapy with Tocilizumab and Corticosteroids. Biomedicines, 11.","DOI":"10.3390\/biomedicines11030845"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Iglesias, J., Okoh, N., Ang, S.P., Rodriguez, C.A., Chia, J.E., and Levine, J.S. (2024). Short-Term Mortality in Hospitalized Patients with Congestive Heart Failure: Markers of Thrombo-Inflammation Are Independent Risk Factors and Only Weakly Associated with Renal Insufficiency and Co-Morbidity Burden. J. Cardiovasc. Dev. Dis., 11.","DOI":"10.3390\/jcdd11030093"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1016\/S2213-2600(23)00237-0","article-title":"Identifying molecular phenotypes in sepsis: An analysis of two prospective observational cohorts and secondary analysis of two randomised controlled trials","volume":"11","author":"Sinha","year":"2023","journal-title":"Lancet Respir. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1097\/HCO.0000000000001215","article-title":"Elevated C-reactive protein and cardiovascular risk","volume":"40","author":"Chia","year":"2025","journal-title":"Curr. Opin. Cardiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1056\/NEJMoa1202290","article-title":"Drotrecogin alfa (activated) in adults with septic shock","volume":"366","author":"Ranieri","year":"2012","journal-title":"N. Engl. J. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e2023062967","DOI":"10.1542\/peds.2023-062967","article-title":"Pediatric Sepsis Diagnosis, Management, and Sub-phenotypes","volume":"153","author":"Weiss","year":"2024","journal-title":"Pediatrics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1164\/rccm.201607-1535LE","article-title":"Simplification of a Septic Shock Endotyping Strategy for Clinical Application","volume":"195","author":"Wong","year":"2017","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.1007\/s40121-022-00684-y","article-title":"Application of Machine Learning for Clinical Subphenotype Identification in Sepsis","volume":"11","author":"Hu","year":"2022","journal-title":"Infect. Dis. Ther."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Miller, R.J.H., Bednarski, B.P., Pieszko, K., Kwiecinski, J., Williams, M.C., Shanbhag, A., Liang, J.X., Huang, C., Sharir, T., and Hauser, M.T. (2024). Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: A retrospective observational study. EBioMedicine, 99.","DOI":"10.1016\/j.ebiom.2023.104930"},{"key":"ref_17","doi-asserted-by":"crossref","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":"Scientific Data"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"c179","DOI":"10.1159\/000339789","article-title":"KDIGO clinical practice guidelines for acute kidney injury","volume":"120","author":"Khwaja","year":"2012","journal-title":"Nephron Clin. Pract."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Benassi, M., Garofalo, S., Ambrosini, F., Sant\u2019Angelo, R.P., Raggini, R., De Paoli, G., Ravani, C., Giovagnoli, S., Orsoni, M., and Piraccini, G. (2020). Using Two-Step Cluster Analysis and Latent Class Cluster Analysis to Classify the Cognitive Heterogeneity of Cross-Diagnostic Psychiatric Inpatients. Front. Psychol., 11.","DOI":"10.3389\/fpsyg.2020.01085"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Papathanakos, G., Andrianopoulos, I., Xenikakis, M., Papathanasiou, A., Koulenti, D., Blot, S., and Koulouras, V. (2023). Clinical Sepsis Phenotypes in Critically Ill Patients. Microorganisms, 11.","DOI":"10.3390\/microorganisms11092165"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1007\/s00134-015-3764-7","article-title":"Phenotypic clusters within sepsis-associated multiple organ dysfunction syndrome","volume":"41","author":"Knox","year":"2015","journal-title":"Intensive Care Med."},{"key":"ref_22","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":"ref_23","doi-asserted-by":"crossref","first-page":"e98","DOI":"10.1097\/CCM.0000000000004709","article-title":"External Corroboration That Corticosteroids May Be Harmful to Septic Shock Endotype A Patients","volume":"49","author":"Wong","year":"2021","journal-title":"Crit. Care Med."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Garduno, A., Cusack, R., Leone, M., Einav, S., and Martin-Loeches, I. (2023). Multi-Omics Endotypes in ICU Sepsis-Induced Immunosuppression. Microorganisms, 11.","DOI":"10.3390\/microorganisms11051119"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Baghela, A., Pena, O.M., Lee, A.H., Baquir, B., Falsafi, R., An, A., Farmer, S.W., Hurlburt, A., Mondragon-Cardona, A., and Rivera, J.D. (2022). Predicting sepsis severity at first clinical presentation: The role of endotypes and mechanistic signatures. EBioMedicine, 75.","DOI":"10.1016\/j.ebiom.2021.103776"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/s43856-024-00542-7","article-title":"Sepsis endotypes identified by host gene expression across global cohorts","volume":"4","author":"Chenoweth","year":"2024","journal-title":"Commun. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Papin, G., Bailly, S., Dupuis, C., Ruckly, S., Gainnier, M., Argaud, L., Azoulay, E., Adrie, C., Souweine, B., and Goldgran-Toledano, D. (2021). Clinical and biological clusters of sepsis patients using hierarchical clustering. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0252793"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1186\/s13054-025-05256-3","article-title":"Clinical subtypes in critically ill patients with sepsis: Validation and parsimonious classifier model development","volume":"29","author":"Rademaker","year":"2025","journal-title":"Crit. Care"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1097\/MCC.0000000000001178","article-title":"Sepsis phenotypes, subphenotypes, and endotypes: Are they ready for bedside care?","volume":"30","author":"Scherger","year":"2024","journal-title":"Curr. Opin. Crit. Care"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, W., Zhang, H., and Liao, X. (2025). Sepsis subphenotypes: Bridging the gaps in sepsis treatment strategies. Front. Immunol., 16.","DOI":"10.3389\/fimmu.2025.1546474"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1038\/mp.2011.173","article-title":"Machine learning and data mining: Strategies for hypothesis generation","volume":"17","author":"Oquendo","year":"2012","journal-title":"Mol. Psychiatry"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Loftus, T.J., Shickel, B., Balch, J.A., Tighe, P.J., Abbott, K.L., Fazzone, B., Anderson, E.M., Rozowsky, J., Ozrazgat-Baslanti, T., and Ren, Y. (2022). Phenotype clustering in health care: A narrative review for clinicians. Front. Artif. Intell., 5.","DOI":"10.3389\/frai.2022.842306"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/13\/4450\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:57:01Z","timestamp":1760032621000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/13\/4450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":32,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["jcm14134450"],"URL":"https:\/\/doi.org\/10.3390\/jcm14134450","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,23]]}}}