ARTIFICIAL INTELLIGENCE IN IN-HOSPITAL EMERGENCY SYSTEM: FROM EARLY DETECTION TO OPTIMIZED TREATMENT AND CARE
DOI:
https://doi.org/10.59354/ydth175.2025.409Keywords:
Artificial Intelligence, Early Warning System, In-Hospital Cardiac Arrest, Sepsis, Machine Learning, Deep LearningAbstract
Background: Artificial intelligence (AI) has emerged as a groundbreaking tool in healthcare, particularly in enhancing the efficiency of in-hospital emergency systems. By improving early detection of clinical deterioration and optimizing treatment processes, AI contributes to reducing mortality rates and severe complications.
Objective: To systematically evaluate artificial-intelligence-based early warning systems (AI-EWS) for in-hospital emergencies, compare their performance with traditional scores, and discuss implementation prospects in Vietnam.
Methods: A systematic search of PubMed, Scopus and IEEE Xplore (2015 – 2024) used the terms “artificial intelligence”, “early warning”, “in-hospital”, “cardiac arrest”, and “sepsis”. Original studies with ≥ 500 subjects that reported AUROC/AUC and included MEWS/NEWS comparators were eligible. Eighteen studies met inclusion criteria; meta-analysis was precluded by heterogeneity of outcomes.
Results: Representative models – DeepCARS™, DEWS, AISE, Churpek’s Random-Forest model, and Deep EDICAS – achieved AUROC 0.80 – 0.94 (median 0.88), surpassing MEWS/NEWS (0.62 – 0.78). At matched specificity, AI reduced false alarms by 50 – 60 % and increased sensitivity up to 2.5-fold; predicted cardiac arrest or sepsis 4 – 24 hours earlier. Interpretable AI techniques are emerging, and most systems integrate seamlessly with electronic health records.
Conclusion: AI-enhanced warning systems markedly outperform conventional scores, offering earlier, more accurate detection and enabling proactive rapid-response activation. Multicenter trials on Vietnamese datasets, robust IT infrastructure, and a dedicated regulatory framework are essential for nationwide deployment.
References
1.Liu V. X., Lu Y., Carey K. A. et al. (2020). Comparison of Early Warning Scoring Systems for Hospitalized Patients With and Without Infection at Risk for In-Hospital Mortality and Transfer to the Intensive Care Unit. JAMA Netw Open. 3(5):e205191.
2.Mahmoodpoor A., Sanaie S., Saghaleini S. H. et al. (2022). Prognostic value of National Early Warning Score and Modified Early Warning Score on intensive care unit readmission and mortality: A prospective observational study. Front Med (Lausanne). 9938005.
3.McGaughey J., Fergusson D. A., Van Bogaert P. et al. (2021). Early warning systems and rapid response systems for the prevention of patient deterioration on acute adult hospital wards. Cochrane Database Syst Rev. 11(11):Cd005529.
4.Cho K. J., Kim J. S., Lee D. H. et al. (2023). Prospective, multicenter validation of the deep learning-based cardiac arrest risk management system for predicting in hospital cardiac arrest or unplanned intensive care unit transfer in patients admitted to general wards. Crit Care. 27(1):346.
5.Lee Y. J., Cho K. J., Kwon O. et al. (2021). A multicentre validation study of the deep learning-based early warning score for predicting in-hospital cardiac arrest in patients admitted to general wards. Resuscitation. 16378-85.
6.Kim Y. K., Koo J. H., Lee S. J. et al. (2023). Explainable Artificial Intelligence Warning Model Using an Ensemble Approach for In-Hospital Cardiac Arrest Prediction: Retrospective Cohort Study. J Med Internet Res. 25e48244.
7.Cho K. J., Kwon O., Kwon J. M. et al. (2020). Detecting Patient Deterioration Using Artificial Intelligence in a Rapid Response System. Crit Care Med. 48(4):e285-e289.
8.Churpek M. M., Yuen T. C., Winslow C. et al. (2016). Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards. Crit Care Med. 44(2):368-74.
9.Nemati S., Holder A., Razmi F. et al. (2018). An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU. Crit Care Med. 46(4):547- 553.
10.Deng Y. X., Wang J. Y., Ko C. H. et al. (2024). Deep learning-based Emergency Department In-hospital Cardiac Arrest Score (Deep EDICAS) for early prediction of cardiac arrest and cardiopulmonary resuscitation in the emergency department. BioData Min. 17(1):52.
11.Haas R., McGill S. C. (2022). CADTH Horizon Scans. Artificial Intelligence for the Prediction of Sepsis in Adults: CADTH Horizon Scan, Canadian Agency for Drugs and Technologies in Health, Ottawa (ON).
12.Abdullah Rana, Fakieh Bahjat (2020). Health Care Employees’ Perceptions of the Use of Artificial Intelligence Applications: Survey Study. J Med Internet Res. 22(5):e17620.
