Daun Jeong, Minyoung Choi, Seung Jin Maeng, Hanbeom Yoon, Jong Eun Park, Gun Tak Lee, Sung Yeon Hwang, Tae Gun Shin, Sung Phil Chung, Tae Ho Lim, on behalf of the Korean Shock Society
In Press, Received October 15, 2025 Accepted December 29, 2025 Available online January 14, 2026
Objective Sepsis remains a major clinical challenge because of its complex, heterogeneous, and multidimensional clustering patterns. This study aimed to investigate the association between vasopressor administration and machine learning–derived clusters based on initial vital signs and lactate measurements obtained in emergency department (ED) and intensive care unit (ICU) settings.
Methods A retrospective cohort analysis was performed using data from the Korean Shock Society Septic Shock (KOSS) Registry (septic shock in the ED) and the Marketplace for Medical Information in Intensive Care (MIMIC)-IV database (ICU patients with suspected infection). To derive clusters, k-means clustering was applied to six initial vital signs and serum lactate measurements. The primary outcome was vasopressor administration. Secondary outcomes included second vasopressor administration and 28-day mortality.
Results A total of 17,500 patients were included in the analysis (KOSS cohort, n=7,130; MIMIC-IV cohort, n=10,370). K-means clustering identified three distinct clusters in each cohort. In the KOSS cohort, Cluster 3 was characterized by the lowest mean arterial pressure (MAP) (62 mmHg [IQR, 53–71]) and the highest diastolic shock index (DSI) (2.6 [2.3–3.0]). This cluster was associated with the highest rates of vasopressor administration (93.9%), second vasopressor administration (33.5%), and 28-day mortality (25.3%) (all p<0.001). Comparable physiological and clinical patterns were observed in the MIMIC-IV cohort, in which Cluster 3 likewise demonstrated the lowest MAP (68 mmHg [60–76]) and highest DSI (2.0 [1.8–2.3]). This group similarly exhibited the poorest outcomes, including vasopressor administration (41.0%), second vasopressor administration (16.7%), and 28-day mortality (29.0%).
Conclusion Machine learning–derived clusters based on initial vital signs and serum lactate levels demonstrated different patterns of vasopressor use and mortality. The clinical utility of this approach for guiding timely or targeted vasopressor therapy requires prospective validation.
Da Seul Kim, Jong Eun Park, Sung Yeon Hwang, Daun Jeong, Gun Tak Lee, Taerim Kim, Se Uk Lee, Hee Yoon, Won Chul Cha, Min Seob Sim, Ik Joon Jo, Tae Gun Shin
Clin Exp Emerg Med 2022;9(3):176-186. Published online September 30, 2022
Objective We evaluated the performance of diastolic shock index (DSI) and lactate in predicting vasopressor requirement among hypotensive patients with suspected infection in an emergency department.
Methods This was a single-center, retrospective observational study for adult patients with suspected infection and hypotension in the emergency department from 2018 to 2019. The study population was split into derivation and validation cohorts (70/30). We derived a simple risk score to predict vasopressor requirement using DSI and lactate cutoff values determined by Youden index. We tested the score by the area under the receiver operating characteristic curve (AUC). We performed a multivariable regression analysis to evaluate the association between the timing of vasopressor treatment and 28-day mortality.
Results A total of 1,917 patients were included. We developed a score, assigning 1 point each for the high DSI (≥2.0) and high lactate (≥2.5 mmol/L) criteria. The AUCs of the score were 0.741 (95% confidence interval [CI], 0.715–0.768) at hypotension and 0.736 (95% CI, 0.708–0.763) after initial fluid challenge in the derivation cohort and 0.676 (95% CI, 0.631–0.719) at hypotension and 0.688 (95% CI, 0.642–0.733) after initial fluid challenge in the validation cohort, respectively. In patients with scores of 2 points, early vasopressor therapy initiation was significantly associated with decreased 28-day mortality (adjusted odds ratio, 0.37; 95% CI, 0.14–0.94).
Conclusion A prediction model with DSI and lactate levels might be useful to identify patients who are more likely to need vasopressor administration among hypotensive patients with suspected infection.
Citations
Citations to this article as recorded by
Utility of Shock Index and Pediatric Age-Adjusted Shock Index in Predicting Severe Sepsis and Septic Shock Raziye Merve Yaradilmiş, Aytaç Göktuğ, İlknur Bodur, Betül Öztürk, Orkun Aydin, Muhammed M. Güneylioğlu, Bilge Akkaya, Fatma Şule Erdem, Ahmet S. Özcan, Ali Güngör, Can Demir Karacan, Nilden Tuygun Pediatric Emergency Care.2026; 42(1): e1. CrossRef
Predicting Cardiovascular Collapse in Critically Ill Patients During Intubation Induction: A Prospective Observational Study Ömer Emgin, Gamze Taşkan, Aytuğ Yıldız, İmren Taşkıran, Engin Haftacı, Adnan Ata, Mehmet Yılmaz Medicina.2026; 62(1): 177. CrossRef
Effect of norepinephrine initiation timing on mortality in septic shock: a multicenter cohort study Jung Won Choi, Tae Gun Shin, Seung Jin Maeng, Sung Yeon Hwang, Sang-Min Kim, Won Young Kim, Kyuseok Kim, Sung-Joon Park, Sung-Hyuk Choi, Sejoong Ahn, Woon Yong Kwon, Taeyoung Kong, Sung Phil Chung, Byuk Sung Ko, Tae Ho Lim BMC Anesthesiology.2026;[Epub] CrossRef
The Application of Scoring Systems in Pediatric Intensive Care Unit for Onco-Hematological Patients Who Have Not Undergone Stem Cell Transplantation: A Cross-Sectional Study Shereen Abdelmonem Mohamed Mohamed, Hanaa Ibrahim Abdel Fattah Rady, Eman Hany Ahmed Elsebaie, Rana Saber Bastawy Mahmoud Indian Journal of Medical and Paediatric Oncology.2026; 47(04): 263. CrossRef
Beyond the Mean: The Dynamic Fingerprint of Vasoplegia in Septic Shock Abhishek P Singh, Deepak Govil Indian Journal of Critical Care Medicine.2026; 30(2): 85. CrossRef
Temporal Analysis of Diastolic Shock Index in Patients with Septic Shock and Its Correlation with Clinical Outcomes in an Indian Setting: A Prospective Observational Study Soumya Sarkar, Ashish K Sharma, Afzal Azim, Jitendra S Chahar, Sangam Yadav, PV Sai Saran, Prabhakar Mishra, Mohan Gurjar, Banani Poddar Indian Journal of Critical Care Medicine.2026; 30(2): 99. CrossRef
From Static Risk Estimates to Dynamic Clinical Trajectories: A Conceptual Analysis of Perioperative Medicine Michele Danilo Pierri Health Care Analysis.2026;[Epub] CrossRef
Admission shock indices and lactate for mortality risk stratification in non-traumatic hypotensive patients Kadir Guzel, Senol Ardic, Ozgen Gonenc Cekic, Ramazan Ozel, Rahman Koseoglu, Tuncay Yazici Irish Journal of Medical Science (1971 -).2026;[Epub] CrossRef
Non‑invasive monitoring and prognostic indicators in critical conditions: from hemodynamics to metabolism (systematic review) E. Yu. Bersenev, T. A. Lapina, O. V. Kurilova, E. O. Sello, L. A. Davydova, S. V. Tsarenko, K. S. Gorbunov Extreme Medicine.2026;[Epub] CrossRef
The clinical utility of shock index in hospitalised patients requiring activation of the rapid response team Hasan M. Al-Dorzi, Yasser A. AlRumih, Mohammed Alqahtani, Mutaz H. Althobaiti, Thamer T. Alanazi, Kenana Owaidah, Saud N. Alotaibi, Monirah Alnasser, Abdulaziz M. Abdulaal, Turki Z. Al Harbi, Ahmad O. AlBalbisi, Saad Al-Qahtani, Yaseen M. Arabi Australian Critical Care.2025; 38(3): 101150. CrossRef
Diastolic shock index: Its importance and application in critically ill patients: A narrative review Natthida Owattanapanich, Natyada Boonchana Clinical Critical Care.2025;[Epub] CrossRef
Assessment of the Ability of Shock Index to Predict Early Hemodynamic Collapse in Hypotensive Sepsis Patient in Emergency Department Aiesha Baloch, Waqas Farooq Ali, Rafia Shoukat, Dania Asghar, Aqsa Baloch, Mars Christian Aragon Sta Ines Indus Journal of Bioscience Research.2025; 3(3): 696. CrossRef
Temporal Analysis of Diastolic Shock Index in Patients with Septic Shock and its Correlation with Clinical Outcomes in Indian Setting – A Prospective Observational Study Banani Poddar, Mohan Gurjar, Afzal Azim, Prabhakar Mishra, Jitendra Chahar, Soumya Sarkar Indian Journal of Critical Care Medicine.2025; 29(S1): S194. CrossRef
A Novel Approach to Early Personalized Hemodynamic Resuscitation: Non‐Invasive Peripheral Photoplethysmography for Identifying Predominant Vasodilatory Shock in Sepsis Sanne Ter Horst, Anna D. Schoonhoven, Raymond J. van Wijk, Rick Weitering, Sanne W. van Loon, Jan C. ter Maaten, Hjalmar R. Bouma Acta Anaesthesiologica Scandinavica.2025;[Epub] CrossRef
The usefulness of lactate/albumin ratio, C-reactive protein/albumin ratio, procalcitonin/albumin ratio, SOFA, and qSOFA in predicting the prognosis of patients with sepsis who presented to EDs Kyung Hun Yoo, Sung-Hyuk Choi, Gil Joon Suh, Sung Phil Chung, Han Sung Choi, Yoo Seok Park, You Hwan Jo, Tae Gun Shin, Tae Ho Lim, Won Young Kim, Juncheol Lee The American Journal of Emergency Medicine.2024; 78: 1. CrossRef
Predicting septic shock in patients with sepsis at emergency department triage using systolic and diastolic shock index Yumin Jeon, Sungjin Kim, Sejoong Ahn, Jong-Hak Park, Hanjin Cho, Sungwoo Moon, Sukyo Lee The American Journal of Emergency Medicine.2024; 78: 196. CrossRef
Comparison of Early and Late Norepinephrine Administration in Patients With Septic Shock Chiwon Ahn, Gina Yu, Tae Gun Shin, Youngsuk Cho, Sunghoon Park, Gee Young Suh CHEST.2024; 166(6): 1417. CrossRef
Early management of adult sepsis and septic shock: Korean clinical practice guidelines Chul Park, Nam Su Ku, Dae Won Park, Joo Hyun Park, Tae Sun Ha, Do Wan Kim, So Young Park, Youjin Chang, Kwang Wook Jo, Moon Seong Baek, Yijun Seo, Tae Gun Shin, Gina Yu, Jongmin Lee, Yong Jun Choi, Ji Young Jang, Yun Tae Jung, Inseok Jeong, Hwa Jin Cho, A Acute and Critical Care.2024; 39(4): 445. CrossRef
Which haemodynamic monitoring should we chose for critically ill patients with acute circulatory failure? Xavier Monnet, Christopher Lai Current Opinion in Critical Care.2023; 29(3): 275. CrossRef
DEVELOPMENT OF SCORE SYSTEM BASED ON POINT-OF-CARE ULTRASOUND TO PREDICT VASOPRESSOR REQUIREMENT FOR EMERGENCY PATIENTS WITH CARDIOPULMONARY SYMPTOMS Hayoung Kim, Ki Hong Kim, Yun Seong Park, Jin Hee Kim, Yun Ang Choi, Joong Wan Park, Yong Hee Lee, Jae Yun Jung Shock.2023; 60(1): 34. CrossRef
Development and derivation of bacteremia prediction model in patients with hepatobiliary infection Jung Won Choi, Sung-Bin Chon, Sung Yeon Hwang, Tae Gun Shin, Jong Eun Park, Kyuseok Kim The American Journal of Emergency Medicine.2023; 73: 102. CrossRef
Hemodynamic management of septic shock: beyond the Surviving Sepsis Campaign guidelines Gil Joon Suh, Tae Gun shin, Woon Yong Kwon, Kyuseok Kim, You Hwan Jo, Sung-Hyuk Choi, Sung Phil Chung, Won Young Kim Clinical and Experimental Emergency Medicine.2023; 10(3): 255. CrossRef
Prognostic accuracy of initial and 24-h maximum SOFA scores of septic shock patients in the emergency department Tae Han Kim, Daun Jeong, Jong Eun Park, Sung Yeon Hwang, Gil Joon Suh, Sung-Hyuk Choi, Sung Phil Chung, Won Young Kim, Gun Tak Lee, Tae Gun Shin Heliyon.2023; 9(9): e19480. CrossRef
Modified Cardiovascular Sequential Organ Failure Assessment Score in Sepsis: External Validation in Intensive Care Unit Patients Byuk Sung Ko, Seung Mok Ryoo, Eunah Han, Hyunglan Chang, Chang June Yune, Hui Jai Lee, Gil Joon Suh, Sung-Hyuk Choi, Sung Phil Chung, Tae Ho Lim, Won Young Kim, Jang Won Sohn, Mi Ae Jeong, Sung Yeon Hwang, Tae Gun Shin, Kyuseok Kim Journal of Korean Medical Science.2023;[Epub] CrossRef
A Simple Bacteremia Score for Predicting Bacteremia in Patients with Suspected Infection in the Emergency Department: A Cohort Study Hyelin Han, Da Seul Kim, Minha Kim, Sejin Heo, Hansol Chang, Gun Tak Lee, Se Uk Lee, Taerim Kim, Hee Yoon, Sung Yeon Hwang, Won Chul Cha, Min Sub Sim, Ik Joon Jo, Jong Eun Park, Tae Gun Shin Journal of Personalized Medicine.2023; 14(1): 57. CrossRef
Using the diastolic shock index to determine when to promptly administer vasopressors in patients with septic shock Gustavo A. Ospina-Tascón, Gustavo García-Gallardo, Nicolás Orozco Clinical and Experimental Emergency Medicine.2022; 9(4): 367. CrossRef
First
Prev
