| 39 | 0 | 40 |
| 下载次数 | 被引频次 | 阅读次数 |
急性呼吸窘迫综合征（ARDS）仍是重症医学领域亟待突破的关键难题，其高死亡率、显著的患者个体异质性，导致传统支持性治疗的临床效果难以进一步提升。本系统性综述围绕人工智能（AI）及机器学习（ML）技术在ARDS临床管理中的应用进展展开全面梳理，重点剖析此类技术在革新ARDS诊疗路径、改善临床结局中的变革性价值。系统探讨了AI/ML技术的多元应用场景：依托电子健康记录（EHR）和影像学检查等多模态数据，实现ARDS的早期预测与精准诊断；构建优于传统评分体系的预后评估模型，完成更精准的患者风险分层；通过精准识别ARDS不同亚型，为个体化治疗方案的制定提供科学指导。同时，详细阐述了AI技术在临床治疗优化中的具体作用，此外还涵盖其在ARDS相关药物研发领域的应用潜力。最后，分析了当前AI技术在ARDS应用中面临的主要瓶颈，包括数据质量参差不齐、模型泛化能力不足、可解释性欠佳及临床转化整合困难等，同时指出AI驱动的诊疗策略为ARDS精准医疗的落地、实时临床决策的优化，以及最终提升患者预后水平提供了前所未有的机遇，为后续相关研究的开展及临床转化应用提供了全面的参考依据。
Abstract：Acute respiratory distress syndrome (ARDS) remains a pivotal unsolved challenge in critical care medicine. Its high mortality rate and marked interindividual heterogeneity in patients render it difficult to further enhance the clinical efficacy of conventional supportive therapies. This systematic review comprehensively collates the research progress of artificial intelligence (AI) and machine learning (ML) technologies in the clinical management of ARDS， and focuses on analyzing their transformative value in innovating the diagnosis and treatment pathway of ARDS and improving clinical outcomes. The multimodal application scenarios of AI/ML technologies are systematically explored: early prediction and accurate diagnosis of ARDS are achieved based on multimodal data such as electronic health records (EHRs) and imaging examinations; prognostic assessment models superior to traditional scoring systems are constructed to implement accurate patient risk stratification; different ARDS subtypes are precisely identified to provide scientific guidance for formulating individualized treatment regimens. In addition， the specific roles of AI technologies in the optimization of clinical treatment are elaborated in detail， and their application potential in the field of ARDS-related drug research and development is also covered. Finally， the major current bottlenecks in the application of AI technologies for ARDS are analyzed， including inconsistent data quality， insufficient model generalization ability， poor interpretability， and difficulties in clinical translation and integration. Meanwhile， it is pointed out that AI-driven diagnosis and treatment strategies provide an unprecedented opportunity for the implementation of precision medicine for ARDS， the optimization of real-time clinical decision-making， and the ultimate improvement of patient prognosis， thus offering a comprehensive reference basis for subsequent relevant research and clinical translational applications.
[1] MATTHAY M A， ARABI Y， ARROLIGA A C， et al. A new global definition of acute respiratory distress syndrome[J]. American Journal of Respiratory and Critical Care Medicine， 2024， 209(1): 37-47.
[2] WANG M， YAN J J， HE X X， et al. Candidate genes and pathogenesis investigation for sepsis-related acute respiratory distress syndrome based on gene expression profile[J]. Biological Research， 2016， 49: 25.
[3] 钱桂生. 急性肺损伤和急性呼吸窘迫综合征研究现状与展望[J]. 解放军医学杂志， 2003， 28(2): 97-101.
[4] 唐敏， 李娜. 急性呼吸窘迫综合征发病机制及相关生物标志物的研究进展[J]. 中国现代医学杂志， 2022， 32(5): 1-6.
[5] BELLANI G， LAFFEY J G， PHAM T， et al. Epidemiology， patterns of care， and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries[J]. JAMA， 2016， 315(8): 788-800.
[6] SHAMOUT F， ZHU T， CLIFTON D A. Machine learning for clinical outcome prediction[J]. IEEE Reviews in Biomedical Engineering， 2021， 14: 116-126.
[7] RUSH B， CELI L A， STONE D J. Applying machine learning to continuously monitored physiological data[J]. Journal of Clinical Monitoring and Computing， 2019， 33(5): 887-893.
[8] LI S， YUE R， LU S， et al. Artificial intelligence and machine learning in acute respiratory distress syndrome management: recent advances[J]. Frontiers in Medicine， 2025， 12: 1604594.
[9] YANG J X， ZENG S Y， CUI S P， et al. Predictive modeling of acute respiratory distress syndrome using machine learning: systematic review and meta-analysis[J]. Journal of Medical Internet Research， 2025， 27: e66615.
[10] 张丽慧， 陈雪融. 急性呼吸窘迫综合征的危险因素预测及诊疗进展[J]. 华西医学， 2023， 38(1): 103-110.
[11] 黄丽丽， 刘玲， 邱海波. 急性呼吸窘迫综合征诊断的进步与发展[J]. 中国实用内科杂志， 2018， 38(11): 977-980.
[12] SILVERSIDES J A， FERGUSON N D. Clinical review: acute respiratory distress syndrome-clinical ventilator management and adjunct therapy[J]. Critical Care， 2013， 17(2): 225.
[13] LE S， PELLEGRINI E， GREEN-SAXENA A， et al. Supervised machine learning for the early prediction of acute respiratory distress syndrome (ARDS)[J]. Journal of Critical Care， 2020， 60: 96-102.
[14] SJODING M W， TAYLOR D， MOTYKA J， et al. Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation[J]. The Lancet Digital Health， 2021， 3(6): e340-e348.
[15] MADDALI M V， CHURPEK M， PHAM T， et al. Validation and utility of ARDS subphenotypes identified by machine-learning models using clinical data: an observational， multicohort， retrospective analysis[J]. The Lancet Respiratory Medicine， 2022， 10(4): 367-377.
[16] PENSIER J， FOSSET M， PASCHOLD B S， et al. Temporal stability of phenotypes of acute respiratory distress syndrome: clinical implications for early corticosteroid therapy and mortality[J]. Intensive Care Medicine， 2025， 51(10): 1784-1796.
[17] SINHA P， CHURPEK M M， CALFEE C S. Machine learning classifier models can identify acute respiratory distress syndrome phenotypes using readily available clinical data[J]. American Journal of Respiratory and Critical Care Medicine， 2020， 202(7): 996-1004.
[18] MEZA-FUENTES G， DELGADO I， BARBE M， et al. Machine learning-based identification of efficient and restrictive physiological subphenotypes in acute respiratory distress syndrome[J]. Intensive Care Medicine Experimental， 2025， 13: 29.
[19] TAN R M， GE C， LI Z， et al. Early prediction of mortality risk in acute respiratory distress syndrome: systematic review and meta-analysis[J]. Journal of Medical Internet Research， 2025， 27: e70537.
[20] BAI Y， XIA J G， HUANG X， et al. Using machine learning for the early prediction of sepsis-associated ARDS in the ICU and identification of clinical phenotypes with differential responses to treatment[J]. Frontiers in Physiology， 2022， 13: 1050849.
[21] HANNON D M， SYED J D A， MCNICHOLAS B， et al. The development of a C5.0 machine learning model in a limited data set to predict early mortality in patients with ARDS undergoing an initial session of prone positioning[J]. Intensive Care Medicine Experimental， 2024， 12: 103.
[22] LI W Y， ZHOU H Y， ZOU Y X. An interpretable machine learning model for predicting mortality risk in adult ICU patients with acute respiratory distress syndrome[J]. Frontiers in Medicine， 2025， 12: 1580345.
[23] SELLA N， PETTENUZZO T， ZARANTONELLO F， et al. Electrical impedance tomography: a compass for the safe route to optimal PEEP[J]. Respiratory Medicine， 2021， 187: 106555.
[24] HANDEL C， FRERICHS I， WEILER N， et al. Prediction and simulation of PEEP setting effects with machine learning models[J]. Medicina Intensiva， 2024， 48(4): 191-199.
[25] CHIEW Y S， CHASE J G， SHAW G M， et al. Model-based PEEP optimisation in mechanical ventilation[J]. BioMedical Engineering OnLine， 2011， 10: 111.
[26] GATTINONI L， TONETTI T， CRESSONI M， et al. Ventilator-related causes of lung injury: the mechanical power[J]. Intensive Care Medicine， 2016， 42(10): 1567-1575.
[27] CHANG K W， LEU S W， HU H C， et al. The mechanical power in patients with acute respiratory distress syndrome undergoing prone positioning can predict mortality[J]. Diagnostics， 2025， 15(2): 158.
[28] KAMYA P， OZEROV I V， PUN F W， et al. PandaOmics: an AI-driven platform for therapeutic target and biomarker discovery[J]. Journal of Chemical Information and Modeling， 2024， 64(10): 3961-3969.
[29] CHEN J， HOU R， XU X， et al. Integrative omics and multi-cohort identify IRF1 and biological targets related to sepsis-associated acute respiratory distress syndrome[J]. Journal of Biomedical Research， 2026， 40(1): 11-22.
[30] 陈加宝， 刘华. 急性肺损伤/急性呼吸窘迫综合征的药物治疗研究进展[J]. 广东药科大学学报， 2021， 37(3): 135-140.
[31] 俞正秋， 马春芳， 蔡宛如. 急性肺损伤/急性呼吸窘迫综合征治疗进展[J]. 中国现代医生， 2021， 59(13): 189-192.
[32] IGARASHI Y， OGAWA K， NISHIMURA K， et al. Machine learning for predicting successful extubation in patients receiving mechanical ventilation[J]. Frontiers in Medicine， 2022， 9: 961252.
[33] XU Y， XUE J J， DENG Y F， et al. Advances in machine learning for mechanically ventilated patients[J]. International Journal of General Medicine， 2025， 18: 3301-3311.
[34] HUANG K Y， HSU Y L， CHEN H C， et al. Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters[J]. Frontiers in Medicine， 2023， 10: 1167445.
[35] LIN Y H， CHANG T C， LIU C F， et al. The intervention of artificial intelligence to improve the weaning outcomes of patients with mechanical ventilation: practical applications in the medical intensive care unit and the COVID-19 intensive care unit: a retrospective study[J]. Medicine， 2024， 103(12): e37500.
[36] LIAO K M， KO S C， LIU C F， et al. Development of an interactive AI system for the optimal timing prediction of successful weaning from mechanical ventilation for patients in respiratory care centers[J]. Diagnostics， 2022， 12(4): 975.
[37] LU X， MILLER M， PEARCE A K， et al. Enhancing predictive modeling for respiratory support with LLM-driven guideline adherence[J]. Critical Care， 2025， 29(1): 491.
[38] CHEN X， HARHAY M O， TONG G， LI F. A Bayesian machine learning approach for estimating heterogeneous survivor causal effects: applications to a critical care trial[J]. The Annals of Applied Statistics， 2024， 18(1): 350-374.
基本信息:
中图分类号:R563.8;TP18
引用信息:
[1]孙翔宇,刘小株.人工智能在急性呼吸窘迫综合征中的应用进展[J].南通大学学报(自然科学版)().
2026-09-02
2026-09-02
2026-09-02