RESUMEN
BACKGROUND AND OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.
Asunto(s)
Algoritmos , Aprendizaje Automático , Redes Neurales de la Computación , Respiración Artificial , Humanos , Estudios Retrospectivos , Masculino , Femenino , Persona de Mediana Edad , Anciano , Ventiladores Mecánicos , Asincronía Paciente-VentiladorRESUMEN
BACKGROUND AND OBJECTIVE: Healthcare datasets are plagued by issues of data scarcity and class imbalance. Clinically validated virtual patient (VP) models can provide accurate in-silico representations of real patients and thus a means for synthetic data generation in hospital critical care settings. This research presents a realistic, time-varying mechanically ventilated respiratory failure VP profile synthesised using a stochastic model. METHODS: A stochastic model was developed using respiratory elastance (Ers) data from two clinical cohorts and averaged over 30-minute time intervals. The stochastic model was used to generate future Ers data based on current Ers values with added normally distributed random noise. Self-validation of the VPs was performed via Monte Carlo simulation and retrospective Ers profile fitting. A stochastic VP cohort of temporal Ers evolution was synthesised and then compared to an independent retrospective patient cohort data in a virtual trial across several measured patient responses, where similarity of profiles validates the realism of stochastic model generated VP profiles. RESULTS: A total of 120,000 3-hour VPs for pressure control (PC) and volume control (VC) ventilation modes are generated using stochastic simulation. Optimisation of the stochastic simulation process yields an ideal noise percentage of 5-10% and simulation iteration of 200,000 iterations, allowing the simulation of a realistic and diverse set of Ers profiles. Results of self-validation show the retrospective Ers profiles were able to be recreated accurately with a mean squared error of only 0.099 [0.009-0.790]% for the PC cohort and 0.051 [0.030-0.126]% for the VC cohort. A virtual trial demonstrates the ability of the stochastic VP cohort to capture Ers trends within and beyond the retrospective patient cohort providing cohort-level validation. CONCLUSION: VPs capable of temporal evolution demonstrate feasibility for use in designing, developing, and optimising bedside MV guidance protocols through in-silico simulation and validation. Overall, the temporal VPs developed using stochastic simulation alleviate the need for lengthy, resource intensive, high cost clinical trials, while facilitating statistically robust virtual trials, ultimately leading to improved patient care and outcomes in mechanical ventilation.
Asunto(s)
Cuidados Críticos , Respiración Artificial , Humanos , Respiración Artificial/métodos , Estudios Retrospectivos , Simulación por Computador , Cuidados Críticos/métodos , Proyectos de InvestigaciónRESUMEN
BACKGROUND AND OBJECTIVE: Respiratory mechanics of mechanically ventilated patients evolve significantly with time, disease state and mechanical ventilation (MV) treatment. Existing deterministic data prediction methods fail to comprehensively describe the multiple sources of heterogeneity of biological systems. This research presents two respiratory mechanics stochastic models with increased prediction accuracy and range, offering improved clinical utility in MV treatment. METHODS: Two stochastic models (SM2 and SM3) were developed using retrospective patient respiratory elastance (Ers) from two clinical cohorts which were averaged over time intervals of 10 and 30 min respectively. A stochastic model from a previous study (SM1) was used to benchmark performance. The stochastic models were clinically validated on an independent retrospective clinical cohort of 14 patients. Differences in predictive ability were evaluated using the difference in percentile lines and cumulative distribution density (CDD) curves. RESULTS: Clinical validation shows all three models captured more than 98% (median) of future Ers data within the 5th - 95th percentile range. Comparisons of stochastic model percentile lines reported a maximum mean absolute percentage difference of 5.2%. The absolute differences of CDD curves were less than 0.25 in the ranges of 5 < Ers (cmH2O/L) < 85, suggesting similar predictive capabilities within this clinically relevant Ers range. CONCLUSION: The new stochastic models significantly improve prediction, clinical utility, and thus feasibility for synchronisation with clinical interventions. Paired with other MV protocols, the stochastic models developed can potentially form part of decision support systems, providing guided, personalised, and safe MV treatment.
Asunto(s)
Respiración con Presión Positiva , Respiración Artificial , Humanos , Respiración Artificial/métodos , Respiración con Presión Positiva/métodos , Estudios Retrospectivos , Mecánica Respiratoria , Sistema RespiratorioRESUMEN
BACKGROUND AND OBJECTIVE: Model-based and personalised decision support systems are emerging to guide mechanical ventilation (MV) treatment for respiratory failure patients. However, model-based treatments require resource-intensive clinical trials prior to implementation. This research presents a framework for generating virtual patients for testing model-based decision support, and direct use in MV treatment. METHODS: The virtual MV patient framework consists of 3 stages: 1) Virtual patient generation, 2) Patient-level validation, and 3) Virtual clinical trials. The virtual patients are generated from retrospective MV patient data using a clinically validated respiratory mechanics model whose respiratory parameters (respiratory elastance and resistance) capture patient-specific pulmonary conditions and responses to MV care over time. Patient-level validation compares the predicted responses from the virtual patient to their retrospective results for clinically implemented MV settings and changes to care. Patient-level validated virtual patients create a platform to conduct virtual trials, where the safety of closed-loop model-based protocols can be evaluated. RESULTS: This research creates and presents a virtual patient platform of 100 virtual patients generated from retrospective data. Patient-level validation reported median errors of 3.26% for volume-control and 6.80% for pressure-control ventilation mode. A virtual trial on a model-based protocol demonstrates the potential efficacy of using virtual patients for prospective evaluation and testing of the protocol. CONCLUSION: The virtual patient framework shows the potential to safely and rapidly design, develop, and optimise new model-based MV decision support systems and protocols using clinically validated models and computer simulation, which could ultimately improve patient care and outcomes in MV.
Asunto(s)
Respiración Artificial , Mecánica Respiratoria , Humanos , Simulación por Computador , Respiración Artificial/métodos , Mecánica Respiratoria/fisiología , Estudios Retrospectivos , Ensayos Clínicos como AsuntoRESUMEN
BACKGROUND: Spontaneous breathing (SB) effort during mechanical ventilation (MV) is an important metric of respiratory drive. However, SB effort varies due to a variety of factors, including evolving pathology and sedation levels. Therefore, assessment of SB efforts needs to be continuous and non-invasive. This is important to prevent both over- and under-assistance with MV. In this study, a machine learning model, Convolutional Autoencoder (CAE) is developed to quantify the magnitude of SB effort using only bedside MV airway pressure and flow waveform. METHOD: The CAE model was trained using 12,170,655 simulated SB flow and normal flow data (NB). The paired SB and NB flow data were simulated using a Gaussian Effort Model (GEM) with 5 basis functions. When the CAE model is given a SB flow input, it is capable of predicting a corresponding NB flow for the SB flow input. The magnitude of SB effort (SBEMag) is then quantified as the difference between the SB and NB flows. The CAE model was used to evaluate the SBEMag of 9 pressure control/ support datasets. Results were validated using a mean squared error (MSE) fitting between clinical and training SB flows. RESULTS: The CAE model was able to produce NB flows from the clinical SB flows with the median SBEMag of the 9 datasets being 25.39% [IQR: 21.87-25.57%]. The absolute error in SBEMag using MSE validation yields a median of 4.77% [IQR: 3.77-8.56%] amongst the cohort. This shows the ability of the GEM to capture the intrinsic details present in SB flow waveforms. Analysis also shows both intra-patient and inter-patient variability in SBEMag. CONCLUSION: A Convolutional Autoencoder model was developed with simulated SB and NB flow data and is capable of quantifying the magnitude of patient spontaneous breathing effort. This provides potential application for real-time monitoring of patient respiratory drive for better management of patient-ventilator interaction.