Acute and Critical Care

Original Articles

Neurology
Clinical variable-based decision-support model for rapid differentiation of hemorrhagic and ischemic stroke at emergency department presentation in South Korea: Jae-Woo Kim, Jin-Heon Jeong, Moon-Ku Han, Sang-Hoon Han, Ka Hyun Kim, Seung Park, Dong-Ick Shin, Kyu Sun Yum; Received October 21, 2025 Accepted February 10, 2026 Published online February 27, 2026; DOI: https://doi.org/10.4266/acc.004925 [Epub ahead of print]

369 View
8 Download

Abstract PDF Supplementary Material: Background
Prompt differentiation between ischemic stroke (IS) and hemorrhagic stroke (HS) is critical because their treatment strategies fundamentally differ. While neuroimaging is essential, clinical decision-making often begins before imaging is completed, and conventional clinical scores have shown inconsistent performance. The objective of this study was therefore to develop and externally validate a machine-learning model that supports HS vs. IS subtype suspicion at emergency department (ED) presentation using only clinical variables.
Methods
We conducted a retrospective multicenter cohort study of 2,998 adult patients with a final diagnosis of acute IS or HS treated at three comprehensive stroke centers (July 2020–January 2024). Patients from hospitals A and B comprised the development/internal validation cohort (n=2,418), while patients from hospital C served as an independent external validation cohort (n=580). An extreme gradient boosting (XGBoost) algorithm was trained using four-fold cross-validation, and feature contributions were assessed using Shapley additive explanation (SHAP) values.
Results
Internal validation showed an area under the receiver operating characteristic curve (AUROC) of 0.937 (95% CI, 0.922–0.950) with a sensitivity 0.828, specificity of 0.932, and accuracy of 0.905. Independent external validation yielded an AUROC of 0.841 (95% CI, 0.792–0.883) with a sensitivity 0.758, specificity of 0.789, and accuracy of 0.783. SHAP analysis identified headache and higher National Institutes of Health Stroke Scale item 1a (level of consciousness) as factors increasing the model output toward HS, whereas atrial fibrillation shifted predictions toward IS.
Conclusions
A clinical variable-only model can support early HS vs. IS subtype suspicion at ED presentation among patients managed in an acute-stroke pathway without requiring laboratory tests. Performance decreased on independent external validation, suggesting potential site-related differences and the need for prospective evaluation and calibration. Stroke mimics were not included and should be addressed in future studies.

CPR/Resuscitation
Initial arterial pH predicts survival of out-of-hospital cardiac arrest in South Korea: Daun Jeong, Sang Do Shin, Tae Gun Shin, Gun Tak Lee, Jong Eun Park, Sung Yeon Hwang, Jin-Ho Choi; Acute Crit Care. 2025;40(3):444-451. Published online August 29, 2025; DOI: https://doi.org/10.4266/acc.001050

2,870 View
64 Download

Abstract PDF Supplementary Material: Background
Arterial pH reflects both metabolic and respiratory distress in cardiac arrest and has prognostic implications. However, it was excluded from the 2024 update of the Utstein out-of-hospital cardiac arrest (OHCA) registry template. We investigated the rationale for including arterial pH into models predicting clinical outcomes. Methods: Data were sourced from the Korean Cardiac Arrest Research Consortium, a nationwide OHCA registry (NCT03222999). Prediction models were constructed using logistic regression, random forest, and eXtreme Gradient Boosting frameworks. Each framework included three model types: pH, low-flow time, and combined models. Then the area under the receiver operating characteristic curve (AUROC) of each predicting model was compared. The primary outcome was 30- day death or neurologically unfavorable status (cerebral performance category ≥3). Results: Among the 15,765 patients analyzed, 92.2% experienced death or unfavorable neurological outcomes. The predicting performance of the models including pH (AUROC, 0.92–0.94) were comparable to the models including low-flow time in all frameworks (0.93–0.94) (all P>0.05). Inclusion of pH into low-flow time models consistently showed higher AUROCs than individual models in all frameworks (AUROC, 0.93–0.95; all P<0.05). Conclusions: The predicting performance of models including arterial pH was comparable to models including low-flow time, and addition of arterial pH into low-flow time models could increase the performance of the models. Key Words: blood pH; hydrogen-ion con

Pulmonary
Using machine learning techniques for early prediction of tracheal intubation in patients with septic shock: a multi-center study in South Korea: Ji Han Heo, Taegyun Kim, Tae Gun Shin, Gil Joon Suh, Woon Yong Kwon, Hayoung Kim, Heesu Park, Heejun Kim, Sol Han; Acute Crit Care. 2025;40(2):221-234. Published online April 30, 2025; DOI: https://doi.org/10.4266/acc.004776

4,634 View
117 Download
1 Web of Science
2 Crossref

Abstract PDF Supplementary Material

Background
Patients with septic shock frequently require tracheal intubation in the emergency department (ED). However, the criteria for tracheal intubation are subjective, based on physician experience, or require serial evaluations over relatively long intervals to make accurate predictions, which might not be feasible in the ED. We used supervised learning approaches and features routinely available during the initial stages of evaluation and resuscitation to stratify the risks of tracheal intubation within a 24-hour time window.
Methods
We retrospectively analyzed the data of patients diagnosed with septic shock based on the SEPSIS-3 criteria across 21 university hospital EDs in the Republic of Korea. A principal component analysis revealed a complex, non-linear decision boundary with respect to the application of tracheal intubation within a 24-hour time window. Stratified five-fold cross validation and a grid search were used with extreme gradient boost. Shapley values were calculated to explain feature importance and preferences.
Results
In total, data for 4,762 patients were analyzed; within that population, 1,486 (31%) were intubated within a 24-hour window, and 3,276 (69%) were not. The area under the receiver operating characteristic curve and F1 scores for intubation within a 24-hour window were 0.829 (95% CI, 0.801–0.878) and 0.654 (95% CI, 0.627–0.681), respectively. The Shapley values identified lactate level after initial fluids, suspected lung infection, initial pH, Sequential Organ Failure Assessment score at enrollment, and respiratory rate at enrollment as important features for prediction.
Conclusions
An extreme gradient boosting machine can moderately discriminate whether intubation is warranted within 24 hours of the recognition of septic shock in the ED.

Citations

Citations to this article as recorded by

Early prediction of renal replacement therapy within 24 hours after septic shock recognition in the emergency department using machine learning: a retrospective analysis of a prospectively collected multicenter registry
Sangun Nah, Tae Ho Lim, Sung Phil Chung, Gil Joon Suh, Sung-Hyuk Choi, Woon Yong Kwon, Won Young Kim, Kyuseok Kim, Sangchun Choi, Je Sung You, Han Sung Choi, Tae Gun Shin, Sangsoo Han
BMC Emergency Medicine.2026;[Epub] CrossRef
Methodological development study: Dynamic mask attention graph neural network for mechanical ventilation in elderly intensive care unit patients
Yi Xie, Ni Xie, Jiao Guo
DIGITAL HEALTH.2025;[Epub] CrossRef

Pediatrics
A deep learning model for estimating sedation levels using heart rate variability and vital signs: a retrospective cross-sectional study at a center in South Korea: You Sun Kim, Bongjin Lee, Wonjin Jang, Yonghyuk Jeon, June Dong Park; Acute Crit Care. 2024;39(4):621-629. Published online November 25, 2024; DOI: https://doi.org/10.4266/acc.2024.01200; Retraction in: Acute Crit Care 2025;40(3):512

5,333 View
40 Download
3 Web of Science
2 Crossref

Pediatrics
Early detection of bloodstream infection in critically ill children using artificial intelligence: Hye-Ji Han, Kyunghoon Kim, June Dong Park; Acute Crit Care. 2024;39(4):611-620. Published online November 22, 2024; DOI: https://doi.org/10.4266/acc.2024.00752

3,367 View
79 Download
1 Web of Science
1 Crossref

Abstract PDF

Background
Despite the high mortality associated with bloodstream infection (BSI), early detection of this condition is challenging in critical settings. The objective of this study was to create a machine learning tool for rapid recognition of BSI in critically ill children.
Methods
Data were extracted from a derivative cohort comprising patients who underwent at least one blood culture during hospitalization in the pediatric intensive care unit (PICU) of a tertiary hospital from January 2020 to June 2023 for model development. Data from another tertiary hospital were utilized for external validation. Variables selected for model development were age, white blood cell count with segmented neutrophil count, C-reactive protein, bilirubin, liver enzymes, glucose, body temperature, heart rate, and respiratory rate. Algorithms compared were extra trees, random forest, light gradient boosting, extreme gradient boosting, and CatBoost.
Results
We gathered 1,806 measurements and recorded 290 hospitalizations from 263 patients in the derivative cohort. Median age on admission was 43 months, with an interquartile range of 10–118.75 months, and a male predominance was observed (n=160, 55.2%). Candida albicans was the most prevalent pathogen, and median duration to confirm BSI was 3 days (range, 3–4). Patients with BSI experienced significantly higher in-hospital mortality and prolonged stays in the PICU than patients without BSI. Random forest classifier achieved the highest area under the receiver operating characteristic curve of 0.874 (0.762 for the validation set).
Conclusions
We developed a machine learning model that predicts BSI with acceptable performance. Further research is necessary to validate its effectiveness.

Citations

Citations to this article as recorded by

Early diagnosis and prognostic prediction of secondary bloodstream infections caused by Acinetobacter baumannii in critically ill patients by machine-learning algorithms
Hengxin Chen, Wenjia Gan, Xianling Zhou, Pingjuan Liu, Tangdan Ding, Hongxu Xu, Peisong Chen, Yili Chen
Frontiers in Cellular and Infection Microbiology.2026;[Epub] CrossRef

Epidemiology
Pediatric septic shock estimation using deep learning and electronic medical records: Ji Weon Lee, Bongjin Lee, June Dong Park; Acute Crit Care. 2024;39(3):400-407. Published online August 1, 2024; DOI: https://doi.org/10.4266/acc.2024.00031

5,212 View
250 Download
2 Web of Science
2 Crossref

Abstract PDF

Background
Diagnosing pediatric septic shock is difficult due to the complex and often impractical traditional criteria, such as systemic inflammatory response syndrome (SIRS), which result in delays and higher risks. This study aims to develop a deep learning-based model using SIRS data for early diagnosis in pediatric septic shock cases.
Methods
The study analyzed data from pediatric patients (<18 years old) admitted to a tertiary hospital from January 2010 to July 2023. Vital signs, lab tests, and clinical information were collected. Septic shock cases were identified using SIRS criteria and inotrope use. A deep learning model was trained and evaluated using the area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). Variable contributions were analyzed using the Shapley additive explanation value.
Results
The analysis, involving 9,616,115 measurements, identified 34,696 septic shock cases (0.4%). Oxygen supply was crucial for 41.5% of the control group and 20.8% of the septic shock group. The final model showed strong performance, with an AUROC of 0.927 and AUPRC of 0.879. Key influencers were age, oxygen supply, sex, and partial pressure of carbon dioxide, while body temperature had minimal impact on estimation.
Conclusions
The proposed deep learning model simplifies early septic shock diagnosis in pediatric patients, reducing the diagnostic workload. Its high accuracy allows timely treatment, but external validation through prospective studies is needed.

Citations

Citations to this article as recorded by

Comparison of Pediatric Risk of Mortality-III, Phoenix Sepsis, and pediatric Sequential Organ Failure Assessment scores for predicting septic shock in Vietnamese children with sepsis
Khai Quang Tran, Ngan Tuong Thien Pham, Tri Duc Nguyen, Quan Minh Pham
The Brazilian Journal of Infectious Diseases.2026; 30(1): 104612. CrossRef
Aligning prediction models with clinical information needs: infant sepsis case study
Lusha Cao, Aaron J Masino, Mary Catherine Harris, Lyle H Ungar, Gerald Shaeffer, Alexander Fidel, Elease McLaurin, Lakshmi Srinivasan, Dean J Karavite, Robert W Grundmeier
JAMIA Open.2025;[Epub] CrossRef

Epidemiology
Development of a deep learning model for predicting critical events in a pediatric intensive care unit: In Kyung Lee, Bongjin Lee, June Dong Park; Acute Crit Care. 2024;39(1):186-191. Published online February 20, 2024; DOI: https://doi.org/10.4266/acc.2023.01424; Correction in: Acute Crit Care 2024;39(2):330

6,686 View
195 Download
2 Web of Science
4 Crossref

Abstract PDF

Background
Identifying critically ill patients at risk of cardiac arrest is important because it offers the opportunity for early intervention and increased survival. The aim of this study was to develop a deep learning model to predict critical events, such as cardiopulmonary resuscitation or mortality.
Methods
This retrospective observational study was conducted at a tertiary university hospital. All patients younger than 18 years who were admitted to the pediatric intensive care unit from January 2010 to May 2023 were included. The main outcome was prediction performance of the deep learning model at forecasting critical events. Long short-term memory was used as a deep learning algorithm. The five-fold cross validation method was employed for model learning and testing.
Results
Among the vital sign measurements collected during the study period, 11,660 measurements were used to develop the model after preprocessing; 1,060 of these data points were measurements that corresponded to critical events. The prediction performance of the model was the area under the receiver operating characteristic curve (95% confidence interval) of 0.988 (0.9751.000), and the area under the precision-recall curve was 0.862 (0.700–1.000).
Conclusions
The performance of the developed model at predicting critical events was excellent. However, follow-up research is needed for external validation.

Citations

Citations to this article as recorded by

Clinical Applications of Data Science and Machine Learning in the Pediatric Cardiac Intensive Care Unit
Fabio Savorgnan, Pranathi Pilla, Joshua Prabhu, Saul Flores, Rohit S. Loomba, Sebastian Acosta
Pediatric Cardiology.2026;[Epub] CrossRef
Prediction of Adverse Events in Single Ventricle Physiology Infants Using Artificial Intelligence Tools
Min Yu, Lucas Saenz Gaitan, Alejandro Lopez Magallon, Craig Futterman, Fang Jin, Marius George Linguraru, Syed Muhammad Anwar, Ricardo Munoz
Critical Care Explorations.2026; 8(2): e1381. CrossRef
Impacto de la inteligencia artificial en la predicción de eventos críticos en las unidades de cuidados intensivos: implicaciones para la práctica y la toma de decisiones en enfermería
Joao Andrés Cujilan Guamán, Nicole Elizabeth Chele Sudiaga, Víctor Alfonso Gavilanes Burnhan, Jenny Verónica Tacle Flores, Ruth Alexandra Boza Ruiz
Prohominum.2025; 7(2): 209. CrossRef
Impacto de la inteligencia artificial en la predicción de eventos críticos en las unidades de cuidados intensivos: Implicaciones para la práctica y la toma de decisiones en enfermería
Joao Andrés Cujilan Guamán, Nicole Elizabeth Chele Sudiaga, Víctor Alfonso Gavilanes Burnhan, Jenny Verónica Tacle Flores, Ruth Alexandra Boza Ruiz
Más Vita.2025; 7(2): 58. CrossRef

Neurosurgery
Comparison of intracranial pressure prediction in hydrocephalus patients among linear, non-linear, and machine learning regression models in Thailand: Avika Trakulpanitkit, Thara Tunthanathip; Acute Crit Care. 2023;38(3):362-370. Published online August 18, 2023; DOI: https://doi.org/10.4266/acc.2023.00094

4,426 View
80 Download
10 Web of Science
10 Crossref

Abstract PDF

Background
Hydrocephalus (HCP) is one of the most significant concerns in neurosurgical patients because it can cause increased intracranial pressure (ICP), resulting in mortality and morbidity. To date, machine learning (ML) has been helpful in predicting continuous outcomes. The primary objective of the present study was to identify the factors correlated with ICP, while the secondary objective was to compare the predictive performances among linear, non-linear, and ML regression models for ICP prediction.
Methods
A total of 412 patients with various types of HCP who had undergone ventriculostomy was retrospectively included in the present study, and intraoperative ICP was recorded following ventricular catheter insertion. Several clinical factors and imaging parameters were analyzed for the relationship with ICP by linear correlation. The predictive performance of ICP was compared among linear, non-linear, and ML regression models.
Results
Optic nerve sheath diameter (ONSD) had a moderately positive correlation with ICP (r=0.530, P<0.001), while several ventricular indexes were not statistically significant in correlation with ICP. For prediction of ICP, random forest (RF) and extreme gradient boosting (XGBoost) algorithms had low mean absolute error and root mean square error values and high R2 values compared to linear and non-linear regression when the predictive model included ONSD and ventricular indexes.
Conclusions
The XGBoost and RF algorithms are advantageous for predicting preoperative ICP and establishing prognoses for HCP patients. Furthermore, ML-based prediction could be used as a non-invasive method.

Citations

Citations to this article as recorded by

Impact of Preoperative Hair Removal on Self-Esteem after Brain Tumor Surgery
Thara Tunthanathip, Natthanee Pisitthaworakul
Asian Journal of Neurosurgery.2026; 21(01): 147. CrossRef
Cost-effectiveness of intracranial pressure monitoring in severe traumatic brain injury in Southern Thailand
Jidapa Jitchanvichai, Thara Tunthanathip
Acute and Critical Care.2025; 40(1): 69. CrossRef
Imaging biomarkers for detection and longitudinal monitoring of ventricular abnormalities from birth to childhood
Antonio Navarro-Ballester, Rosa Álvaro-Ballester, Miguel Á Lara-Martínez
World Journal of Radiology.2025;[Epub] CrossRef
Deep learning-based model for detection of intracranial waveforms with poor brain compliance in southern Thailand
Thara Tunthanathip, Avika Trakulpanitkit
Acute and Critical Care.2025; 40(3): 473. CrossRef
A nomogram for the prediction of traumatic intracranial abnormalities in the elderly: Development and validation
Apisorn Jongjit, Thara Tunthanathip
Chinese Journal of Traumatology.2025;[Epub] CrossRef
Feasibility comparison of deep learning image regressions to estimate intracranial pressure from cranial computed tomography in hydrocephalus
Thara Tunthanathip, Rakkrit Duangsoithong, Sakchai Sae-Heng
Journal of Neurosciences in Rural Practice.2025; 16: 606. CrossRef
Risk factors and dose-response relationship of catheter-associated urinary tract infection in neurosurgical patients
Thara Tunthanathip, Natthanee Pisitthaworakul
International Journal of Nutrition, Pharmacology, Neurological Diseases.2025; 15(4): 451. CrossRef
Prognosis of subarachnoid hemorrhage determined by intracranial pressure thresholds
Thara Tunthanathip, Rakkrit Duangsoithong, Sakchai Sae-Heng
Journal of Cerebrovascular and Endovascular Neurosurgery.2025; 27(4): 309. CrossRef
Assessing interpretability of data‐driven fuzzy models: Application in industrial regression problems
Jorge S. S. Júnior, Carlos Gaspar, Jérôme Mendes, Cristiano Premebida
Expert Systems.2024;[Epub] CrossRef
Progressive Optic Neuropathy in Hydrocephalic Ccdc13 Mutant Mice Caused by Impaired Axoplasmic Transport at the Optic Nerve Head
Mingjuan Wu, Xinyi Zhao, Shanzhen Peng, Xiaoyu Zhang, Jiali Ru, Lijing Xie, Tao Wen, Yingchun Su, Shujuan Xu, Dianlei Guo, Jianmin Hu, Haotian Lin, Tiansen Li, Chunqiao Liu
Investigative Ophthalmology & Visual Science.2024; 65(13): 5. CrossRef

First
Prev
Page of 1
Next
Last

Search