Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

• Published in: Computer methods and programs in biomedicine Vol. 255; p. 108323
• Main Authors: Ang, Christopher Yew Shuen, Chiew, Yeong Shiong, Wang, Xin, Ooi, Ean Hin, Cove, Matthew E, Chen, Yuhong, Zhou, Cong, Chase, J. Geoffrey
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.10.2024
• Subjects: Aged; Algorithms; Convolution neural network; Female; Humans; Hysteresis loop analysis; Machine Learning; Male; Mechanical ventilation; Middle Aged; Neural Networks, Computer; Patient-Ventilator Asynchrony; Respiration, Artificial; Retrospective Studies; Rule based methods; Ventilators, Mechanical; Hysteresis loop analysis; Rule based methods; Convolution neural network; Mechanical ventilation; Patient–ventilator asynchrony; Machine learning
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2024.108323

•Patient-ventilator asynchrony (PVA) detection methods have variable performance.•A rule-based and machine learning (ML) method is used to classify 7 types of PVA.•Class activation mapping heatmaps improve ML result explicability.•Rule-based approach achieves better PVA classification performance and robustness.•Potential for real-time continuous monitoring of PVA with improved transparency. Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort. Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison. Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN. The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.