Traditional methods and artificial intelligence: current status, challenges, and future directions of risk assessment models for patients undergoing extracorporeal membrane oxygenation.
10.3760/cma.j.cn121430-20250604-00543
- Author:
Zhaojie LIN
1
;
Lu LU
;
Menghao FANG
;
Yanqing LIU
;
Jifeng XING
;
Haojun FAN
Author Information
1. School of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China. Corresponding author: Fan Haojun, Email: fanhj@tju.edu.cn.
- Publication Type:English Abstract
- MeSH:
Extracorporeal Membrane Oxygenation;
Humans;
Artificial Intelligence;
Risk Assessment;
Respiratory Insufficiency/therapy*;
Heart Failure/therapy*
- From:
Chinese Critical Care Medicine
2025;37(10):893-900
- CountryChina
- Language:Chinese
-
Abstract:
Extracorporeal membrane oxygenation (ECMO) is primarily used in clinical practice to provide continuous extracorporeal respiratory and circulatory support for patients with severe heart and lung failure, thereby sustaining life. It is a key technology for managing severe heart failure and respiratory failure that are difficult to control. With the accumulation of clinical experience in ECMO for circulatory and/or respiratory support, as well as advancements in biomedical engineering technology, more portable and stable ECMO devices have been introduced into clinical use, benefiting an increasing number of critically ill patients. Although ECMO technology has become relatively mature, the timing of ECMO initiation, management of sudden complications, and monitoring and early warning of physiological indicators are critical factors that greatly affect the therapeutic outcomes of ECMO. This article reviews traditional methods and artificial intelligence techniques used in risk assessment related to ECMO, including the latest achievements and research hotspots. Additionally, it discusses future trends in ECMO risk management, focusing on six key areas: multi-center and prospective studies, external validation and standardization of model performance, long-term prognosis considerations, integration of innovative technologies, enhancing model interpretability, and economic cost-effectiveness analysis. This provides a reference for future researchers to build models and explore new research directions.
