1
|
Ang CYS, Chiew YS, Wang X, Ooi EH, Cove ME, Chen Y, Zhou C, Chase JG. Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method? COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 255:108323. [PMID: 39029417 DOI: 10.1016/j.cmpb.2024.108323] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/01/2024] [Revised: 06/27/2024] [Accepted: 07/10/2024] [Indexed: 07/21/2024]
Abstract
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.
Collapse
Affiliation(s)
| | - Yeong Shiong Chiew
- School of Engineering, Monash University Malaysia, Selangor, Malaysia; Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand.
| | - Xin Wang
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Ean Hin Ooi
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Matthew E Cove
- Division of Respiratory & Critical Care Medicine, Department of Medicine, National University Health System, Singapore
| | - Yuhong Chen
- Intensive Care Unit, the Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei Province, China
| | - Cong Zhou
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - J Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
2
|
Ang CYS, Chiew YS, Wang X, Ooi EH, Nor MBM, Cove ME, Chase JG. Virtual patient with temporal evolution for mechanical ventilation trial studies: A stochastic model approach. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 240:107728. [PMID: 37531693 DOI: 10.1016/j.cmpb.2023.107728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 06/27/2023] [Accepted: 07/19/2023] [Indexed: 08/04/2023]
Abstract
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.
Collapse
Affiliation(s)
| | | | - Xin Wang
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Ean Hin Ooi
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Mohd Basri Mat Nor
- Kulliyah of Medicine, International Islamic University Malaysia, Pahang, Malaysia
| | - Matthew E Cove
- Division of Respiratory & Critical Care Medicine, Department of Medicine, National University Hospital, Singapore
| | - J Geoffrey Chase
- Center of Bioengineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
3
|
Ang CYS, Chiew YS, Wang X, Mat Nor MB, Cove ME, Chase JG. Predicting mechanically ventilated patients future respiratory system elastance - A stochastic modelling approach. Comput Biol Med 2022; 151:106275. [PMID: 36375413 DOI: 10.1016/j.compbiomed.2022.106275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Revised: 10/26/2022] [Accepted: 10/30/2022] [Indexed: 11/13/2022]
Abstract
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.
Collapse
Affiliation(s)
| | | | - Xin Wang
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Mohd Basri Mat Nor
- Kulliyah of Medicine, International Islamic University Malaysia, Kuantan, 25200, Malaysia
| | - Matthew E Cove
- Division of Respiratory & Critical Care Medicine, Department of Medicine, National University Health System, Singapore
| | - J Geoffrey Chase
- Center of Bioengineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
4
|
Ang CYS, Lee JWW, Chiew YS, Wang X, Tan CP, Cove ME, Nor MBM, Zhou C, Desaive T, Chase JG. Virtual patient framework for the testing of mechanical ventilation airway pressure and flow settings protocol. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 226:107146. [PMID: 36191352 DOI: 10.1016/j.cmpb.2022.107146] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Revised: 09/17/2022] [Accepted: 09/17/2022] [Indexed: 06/16/2023]
Abstract
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.
Collapse
Affiliation(s)
| | - Jay Wing Wai Lee
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | | | - Xin Wang
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Chee Pin Tan
- School of Engineering, Monash University Malaysia, Selangor, Malaysia
| | - Matthew E Cove
- Division of Respiratory & Critical Care Medicine, Department of Medicine, National University Health System, Singapore
| | - Mohd Basri Mat Nor
- Kulliyah of Medicine, International Islamic University Malaysia, Kuantan, 25200, Malaysia
| | - Cong Zhou
- Center of Bioengineering, University of Canterbury, Christchurch, New Zealand
| | - Thomas Desaive
- GIGA In-Silico Medicine, University of Liege, Liege, Belgium
| | - J Geoffrey Chase
- Center of Bioengineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
5
|
Arn Ng Q, Yew Shuen Ang C, Shiong Chiew Y, Wang X, Pin Tan C, Basri Mat Nor M, Salwa Damanhuri N, Geoffrey Chase J. CAREDAQ: Data acquisition device for mechanical ventilation waveform monitoring. HARDWAREX 2022; 12:e00358. [PMID: 36117541 PMCID: PMC9474567 DOI: 10.1016/j.ohx.2022.e00358] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/25/2022] [Revised: 09/01/2022] [Accepted: 09/05/2022] [Indexed: 06/15/2023]
Abstract
Mechanical ventilation (MV) provides respiratory support for critically ill patients in the intensive care unit (ICU). Waveform data output by the ventilator provides valuable physiological and diagnostic information. However, existing systems do not provide full access to this information nor allow for real-time, non-invasive data collection. Therefore, large amounts of data are lost and analysis is limited to short samples of breathing cycles. This study presents a data acquisition device for acquiring and monitoring patient ventilation waveform data. Acquired data can be exported to other systems, allowing users to further analyse data and develop further clinically useful parameters. These parameters, together with other ventilatory information, can help personalise and guide MV treatment. The device is designed to be easily replicable, low-cost, and scalable according to the number of patient beds. Validation was carried out by assessing system performance and stability over prolonged periods of 7 days of continuous use. The device provides a platform for future integration of machine-learning or model-based modules, potentially allowing real-time, proactive, patient-specific MV guidance and decision support to improve the quality and productivity of care and outcomes.
Collapse
Affiliation(s)
- Qing Arn Ng
- School of Engineering, Monash University Malaysia, Subang Jaya, Selangor 47500, Malaysia
| | | | - Yeong Shiong Chiew
- School of Engineering, Monash University Malaysia, Subang Jaya, Selangor 47500, Malaysia
| | - Xin Wang
- School of Engineering, Monash University Malaysia, Subang Jaya, Selangor 47500, Malaysia
| | - Chee Pin Tan
- School of Engineering, Monash University Malaysia, Subang Jaya, Selangor 47500, Malaysia
| | - Mohd Basri Mat Nor
- Kulliyah of Medicine, International Islamic University Malaysia, Kuantan, Pahang 25200, Malaysia
| | - Nor Salwa Damanhuri
- Faculty of Electrical Engineering, Universiti Teknologi MARA, Cawangan Pulau Pinang, 13500, Permatang Pauh, Pulau Pinang, Malaysia
| | - J. Geoffrey Chase
- Center of Bioengineering, University of Canterbury, Christchurch 8041, New Zealand
| |
Collapse
|