Acute and Critical Care

Original Article

Rapid response system
Prospective external validation of a deep-learning-based early-warning system for major adverse events in general wards in South Korea: Taeyong Sim, Eun Young Cho, Ji-hyun Kim, Kyung Hyun Lee, Kwang Joon Kim, Sangchul Hahn, Eun Yeong Ha, Eunkyeong Yun, In-Cheol Kim, Sun Hyo Park, Chi-Heum Cho, Gyeong Im Yu, Byung Eun Ahn, Yeeun Jeong, Joo-Yun Won, Hochan Cho, Ki-Byung Lee; Acute Crit Care. 2025;40(2):197-208. Published online May 30, 2025; DOI: https://doi.org/10.4266/acc.000525

6,173 View
172 Download
2 Web of Science
2 Crossref

Background
Acute deterioration of patients in general wards often leads to major adverse events (MAEs), including unplanned intensive care unit transfers, cardiac arrest, or death. Traditional early warning scores (EWSs) have shown limited predictive accuracy, with frequent false positives. We conducted a prospective observational external validation study of an artificial intelligence (AI)-based EWS, the VitalCare - Major Adverse Event Score (VC-MAES), at a tertiary medical center in the Republic of Korea.
Methods
Adult patients from general wards, including internal medicine (IM) and obstetrics and gynecology (OBGYN)—the latter were rarely investigated in prior AI-based EWS studies—were included. The VC-MAES predictions were compared with National Early Warning Score (NEWS) and Modified Early Warning Score (MEWS) predictions using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and logistic regression for baseline EWS values. False-positives per true positive (FPpTP) were assessed based on the power threshold.
Results
Of 6,039 encounters, 217 (3.6%) had MAEs (IM: 9.5%, OBGYN: 0.26%). Six hours prior to MAEs, the VC-MAES achieved an AUROC of 0.918 and an AUPRC of 0.352, including the OBGYN subgroup (AUROC, 0.964; AUPRC, 0.388), outperforming the NEWS (0.797 and 0.124) and MEWS (0.722 and 0.079). The FPpTP was reduced by up to 71%. Baseline VC-MAES was strongly associated with MAEs (P<0.001).
Conclusions
The VC-MAES significantly outperformed traditional EWSs in predicting adverse events in general ward patients. The robust performance and lower FPpTP suggest that broader adoption of the VC-MAES may improve clinical efficiency and resource allocation in general wards.

Citations

Citations to this article as recorded by

Clinical Context Is More Important than Data Quantity to the Performance of an Artificial Intelligence-Based Early Warning System
Taeyong Sim, Eunyoung Cho, Jihyun Kim, Ho Gwan Kim, Soo-Jeong Kim
Journal of Clinical Medicine.2025; 14(13): 4444. CrossRef
Artificial intelligence and machine learning approaches for patient safety in complex surgery: a review
Mohamed Mustaf Ahmed, Zhinya Kawa Othman, Uthman Okikiola Adebayo, Omar Kasimieh, Olalekan John Okesanya, Shuaibu Saidu Musa, Francesco Branda, Victor C. Cañezo , Edgar G. Cue, Don Eliseo Lucero Prisno III
Patient Safety in Surgery.2025;[Epub] CrossRef

Guideline

Meta-analysis
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, Ala Woo, Sua Kim, Dae-Hwan Bae, Sung Wook Kang, Sun Hyo Park, Gee Young Suh, Sunghoon Park; Acute Crit Care. 2024;39(4):445-472. Published online November 18, 2024; DOI: https://doi.org/10.4266/acc.2024.00920

36,510 View
1,605 Download
4 Web of Science
8 Crossref

Abstract PDF Supplementary Material

Background
Despite recent advances and global improvements in sepsis recognition and supportive care, mortality rates remain high, and adherence to sepsis bundle components in Korea is low. To address this, the Korean Sepsis Alliance, affiliated with the Korean Society of Critical Care Medicine, developed the first sepsis treatment guidelines for Korea based on a comprehensive systematic review and meta-analysis.
Methods
A de novo method was used to develop the guidelines. Methodologies included determining key questions, conducting a literature search and selection, assessing the risk of bias, synthesizing evidence, and developing recommendations. The certainty of evidence and the strength of recommendations were determined using the Grading of Recommendations, Assessment, Development, and Evaluations approach. Draft recommendations underwent internal and external review processes and public hearings. The development of these guidelines was supported by a research grant from the Korean Disease Control and Prevention Agency.
Results
In these guidelines, we focused on early treatments for adult patients with sepsis and septic shock. Through the guideline development process, 12 key questions and their respective recommendations were formulated. These include lactate measurement, fluid therapies, target blood pressure, antibiotic administration, use of vasopressors and dobutamine, extracorporeal membrane oxygenation, and echocardiography.
Conclusions
These guidelines aim to support medical professionals in making appropriate decisions about treating adult sepsis and septic shock. We hope these guidelines will increase awareness of sepsis and reduce its mortality rate.

Citations

Citations to this article as recorded by

Comparison between norepinephrine plus epinephrine and norepinephrine plus vasopressin after return of spontaneous circulation in patients with out-of-hospital cardiac arrest
Sejoong Ahn, Bo-Yeong Jin, Sukyo Lee, Jong-Hak Park, Hanjin Cho, Sungwoo Moon, Sang Kuk Han, Phil Cho Choi, Young Hwan Lee, Sang O. Park, Jong Seok Lee, Ki Young Jeong, Sung Hyuk Choi, Young Hoon Yoon, Su Jin Kim, Kap Su Han, Min Seob Sim, Gun Tak Lee, Yo
Scientific Reports.2025;[Epub] CrossRef
Recommendations for the use of biomarkers for the management of adults with sepsis: a scoping review and critical appraisal
Miriam Mateos-Haro, Ana Garcia-Santa-Vinuela, Daniel Molano-Franco, Ivan Solà, Federico Gordo-Vidal, María Cruz Martín-Delgado, Jesus Lopez-Alcalde, Javier Zamora
BMJ Open.2025; 15(7): e090922. CrossRef
Regional Adherence to Early Sepsis Management Bundle and Associated Mortality in Hong Kong Between 2009–2018
Jack Zhenhe Zhang, Chun Hei Chan, Lok Ching Chang, Lok Ching Sandra Chiu, Pauline Yeung Ng, Manimala Dharmangadan, Eunise Ho, Steven Ling, Man Yee Man, Ka Man Fong, Ting Liong, Alwin Wai Tak Yeung, Ka Fai Au, Jacky Ka Hing Chan, Michele Tang, Katy Hoi Ki
Open Forum Infectious Diseases.2025;[Epub] CrossRef
Outcomes of septic shock from urinary and non-urinary sources in nonagenarians and centenarians admitted to intensive care units
Je Min Suh, Laurence Weinberg, Nattaya Raykateeraroj, Jerry Lim, Angelina Yoon, David Pilcher, Dong-Kyu Lee
Scientific Reports.2025;[Epub] CrossRef
Association between emergency department–to–intensive care unit transfer time and mortality in patients with septic shock: a target trial emulation with septic shock in South Korea
Ji Hyun Cha, Danbee Kang, Ryoung-Eun Ko, Won Young Kim, Dong-gon Hyun, Yeon Joo Lee, Woo Hyun Cho, Sunghoon Park, Juhee Cho, Gee Young Suh
Acute and Critical Care.2025; 40(4): 548. CrossRef
Early Versus Delayed Norepinephrine Initiation in Septic Shock: A Systematic Review and Meta-Analysis of Randomized and Observational Studies
Chibuzo C Manafa, Oluwayemisi E Ekor, Akintunde C Akinboboye, Okelue E Okobi, Gift Ojukwu, Osemwegie O Ugbo, Michael U Mochu, Emasenyie Isikwei, Sergio Hernandez Borges, Miguel Diaz-Miret
Cureus.2025;[Epub] CrossRef
Quality assessment of clinical practice guidelines for sepsis and variations in recommendations
Hong-Yan Li, Shan-Ling Jiang, Jing Wang, Hai-Shan Wang, Li-Hong Wang
BMC Infectious Diseases.2025;[Epub] CrossRef
Evidence-Based Interventions for Sepsis Management in Critically Ill Adults: A Systematic Review
Elsa Jardim Sousa, Michelle de Soresa Virissimo, Abel Mendonça Viveiros, Ana Alves, Valter Gonçalves
European Journal of Medical and Health Research.2025; 3(6): 232. CrossRef

First
Prev
Page of 1
Next
Last

Search