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
|
Guy EF, Flett IL, Clifton JA, Calje-van der Klei T, Chen R, Knopp JL, Möller K, Chase JG. Pulmonary function testing dataset of pressure and flow, dynamic circumference, heart rate, and aeration monitoring. Data Brief 2024; 54:110386. [PMID: 38646196 PMCID: PMC11033070 DOI: 10.1016/j.dib.2024.110386] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2024] [Revised: 03/27/2024] [Accepted: 03/29/2024] [Indexed: 04/23/2024] Open
Abstract
Respiratory data was collected from 20 subjects, with an even sex distribution, in the low-risk clinical unit at the University of Canterbury. Ethical consent for this trial was granted by the University of Canterbury Human Research Ethics Committee (Ref: HREC 2023/30/LR-PS). Respiratory data were collected, for each subject, over three tests consisting of: 1) increasing set PEEP from a starting point of ZEEP using a CPAP machine; 2) test 1 repeated with two simulated apnoea's (breath holds) at each set PEEP; and 3) three forced expiratory manoeuvres at ZEEP. Data were collected using a custom pressure and flow sensor device, ECG, PPG, Garmin HRM Dual heartrate belt, and a Dräeger PulmoVista 500 Electrical Impedance Tomography (EIT) machine. Subject demographic data was also collected prior to the trial, in a questionnaire, with measurement equipment available. These data aim to inform the development of pulmonary mechanics models and titration algorithms.
Collapse
Affiliation(s)
- Ella F.S. Guy
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Isaac L. Flett
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Jaimey A. Clifton
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | | | - Rongqing Chen
- Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - Jennifer L. Knopp
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Knut Möller
- Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - J. Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
3
|
Guy EF, Clifton JA, Calje-Van Der Klei T, Chen R, Knopp JL, Möller K, Chase JG. Respiratory monitoring dataset, with rapid expiratory occlusions, over increasing positive airway pressure ventilation. Data Brief 2024; 52:109874. [PMID: 38146285 PMCID: PMC10749260 DOI: 10.1016/j.dib.2023.109874] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2023] [Revised: 11/22/2023] [Accepted: 11/23/2023] [Indexed: 12/27/2023] Open
Abstract
Resting breathing data was collected from 80 smokers, vapers, asthmatics, and otherwise healthy people in the low-risk clinical unit at the University of Canterbury. Subjects were asked to breathe normally through a full-face mask connected to a Fisher and Paykel Healthcare SleepStyle SPSCAA CPAP device. PEEP (Positive End-Expiratory Pressure) support was increased from 4 to 12 cmH2O in 0.5 cmH2O increments. Data was also collected during resting breathing at ZEEP (0 cmH2O) before and after the PEEP trial. The trial was conducted under University of Canterbury Human Research Ethics Committee consent (Ref: HREC 2023/04/LR-PS). Data was collected by and Dräeger PulmoVista 500 EIT machine and a custom Venturi-based pressure and flow sensor device connected in series with the CPAP and full-face mask. The outlined dataset includes pressure, flow, volume, dynamic circumference (thoracic and abdominal, and cross-sectional aeration. Subject demographic data was self-reported using a questionnaire given prior to the trial.
Collapse
Affiliation(s)
- Ella F.S. Guy
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Jaimey A. Clifton
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | | | - Rongqing Chen
- Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - Jennifer L. Knopp
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Knut Möller
- Institute of Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - J. Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
4
|
Clifton JA, Guy EF, Caljé-van der Klei T, Knopp JL, Chase JG. Simulated obstructive respiratory disease dataset over increasing positive end-expiratory pressure. Data Brief 2024; 52:109903. [PMID: 38161653 PMCID: PMC10754699 DOI: 10.1016/j.dib.2023.109903] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 11/27/2023] [Accepted: 11/28/2023] [Indexed: 01/03/2024] Open
Abstract
The breathing dataset presented is collected from 20 healthy individuals at the University of Canterbury using a device to simulate the pressure and flow profiles of obstructive pulmonary disease. Specifically, the expiratory non-linear resistance, which generates the characteristic expiratory pressure-flow loop lobe seen in obstructive disease. Ethical consent for the trial was granted by the University of Canterbury Human Research Ethics Committee (Ref: HREC 2022/26/LR). Data was collected using an open-source data collection device connected to a Fisher and Paykel Healthcare SleepStyle SPSCAA CPAP. The trial was conducted at CPAP PEEP levels of 4 and 8 cmH2O, as well as at ZEEP (0 cmH2O) with no CPAP attached. The simulation device was a modular device connected to the expiratory pathway, consisting of a free volume diversion and fixed high resistance outlet. Three simulation levels were selected for testing, achieved by changing the size of the elastic free volume. The intended use of this dataset is for the initial validation and development of respiratory pulmonary mechanics models, using data collected from healthy people with simulated disease prior to clinical testing.
Collapse
Affiliation(s)
- Jaimey A. Clifton
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Ella F.S. Guy
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | | | - Jennifer L. Knopp
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - J. Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
5
|
Caljé-van der Klei T, Sun Q, Chase JG, Zhou C, Tawhai MH, Knopp JL, Möller K, Heines SJ, Bergmans DC, Shaw GM. Pulmonary response prediction through personalized basis functions in a virtual patient model. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 244:107988. [PMID: 38171168 DOI: 10.1016/j.cmpb.2023.107988] [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: 06/21/2023] [Revised: 11/16/2023] [Accepted: 12/17/2023] [Indexed: 01/05/2024]
Abstract
BACKGROUND AND OBJECTIVE Recruitment maneuvers with subsequent positive-end-expiratory-pressure (PEEP) have proven effective in recruiting lung volume and preventing alveoli collapse. However, determining a safe, effective, and patient-specific PEEP is not standardized, and this more optimal PEEP level evolves with patient condition, requiring personalised monitoring and care approaches to maintain optimal ventilation settings. METHODS This research examines 3 physiologically relevant basis function sets (exponential, parabolic, cumulative) to enable better prediction of elastance evolution for a virtual patient or digital twin model of MV lung mechanics, including novel elements to model and predict distension elastance. Prediction accuracy and robustness are validated against recruitment maneuver data from 18 volume-controlled ventilation (VCV) patients at 7 different baseline PEEP levels (0 to 12 cmH2O) and 14 pressure-controlled ventilation (PCV) patients at 4 different baseline PEEP levels (6 to 12 cmH2O), yielding 623 and 294 prediction cases, respectively. Predictions were made up to 12 cmH2O of added PEEP ahead, covering 6 × 2 cmH2O PEEP steps. RESULTS The 3 basis function sets yield median absolute peak inspiratory pressure (PIP) prediction error of 1.63 cmH2O for VCV patients, and median peak inspiratory volume (PIV) prediction error of 0.028 L for PCV patients. The exponential basis function set yields a better trade-off of overall performance across VCV and PCV prediction than parabolic and cumulative basis function sets from other studies. Comparing predicted and clinically measured distension prediction in VCV demonstrated consistent, robust high accuracy with R2 = 0.90-0.95. CONCLUSIONS The results demonstrate recruitment mechanics are best captured by an exponential basis function across different mechanical ventilation modes, matching physiological expectations, and accurately capture, for the first time, distension mechanics to within 5-10 % accuracy. Enabling the risk of lung injury to be predicted before changing ventilator settings. The overall outcomes significantly extend and more fully validate this digital twin or virtual mechanical ventilation patient model.
Collapse
Affiliation(s)
- Trudy Caljé-van der Klei
- Department of Mechanical Engineering, Centre for Bio-Engineering, University of Canterbury, Christchurch, New Zealand.
| | - Qianhui Sun
- Department of Mechanical Engineering, Centre for Bio-Engineering, University of Canterbury, Christchurch, New Zealand; University of Liége, Liége, Belgium
| | - J Geoffrey Chase
- Department of Mechanical Engineering, Centre for Bio-Engineering, University of Canterbury, Christchurch, New Zealand
| | - Cong Zhou
- Department of Mechanical Engineering, Centre for Bio-Engineering, University of Canterbury, Christchurch, New Zealand
| | - Merryn H Tawhai
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Jennifer L Knopp
- Department of Mechanical Engineering, Centre for Bio-Engineering, University of Canterbury, Christchurch, New Zealand
| | - Knut Möller
- Institute for Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
| | - Serge J Heines
- Department of Intensive Care, School of Medicine, Maastricht University, Maastricht, Netherlands
| | - Dennis C Bergmans
- Department of Intensive Care, School of Medicine, Maastricht University, Maastricht, Netherlands
| | - Geoffrey M Shaw
- Department of Intensive Care, Christchurch Hospital, Christchurch, New Zealand
| |
Collapse
|
6
|
Arshad M, Mehmood K, Lazoglu I. Development of a non-invasive ventilator for emergency and beyond. Comput Biol Med 2023; 167:107670. [PMID: 37939406 DOI: 10.1016/j.compbiomed.2023.107670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 10/22/2023] [Accepted: 10/31/2023] [Indexed: 11/10/2023]
Abstract
The SARS-CoV-2 pandemic led to the development and implementation of emergency ventilators owing to the shortage of ventilators globally. Using invasive ventilators for patient intubation has medical experts concerned about increasing mortality. Early intervention with oxygen and respiratory therapy reduces the need for intubation, increases survival rates, and reduces the stress of critical care ventilators in hospitals. This study explores the capabilities of an easy-to-build and accessible non-invasive ventilator during an emergency and the practical implementation of the ventilator beyond the scope of the emergency. The proposed system consists of a high-pressure turbine integrated with a microcontroller and pressure and flow sensors assembled in a portable design. The non-invasive pressure support system is tested with a single-chamber high-precision lung simulator capable of simulating multiple lung diseases. The system is operated in a spontaneous pressure support mode as a Bi-level Ventilator for varying degrees of pressure level and lung conditions. The proposed study implements two most commonly adapted non-invasive patient circuits, i.e., single passive limb leak circuit and single limb active circuit. Both circuits are tested with and without leakage compensation. Two clinically accepted ventilation modes, i.e., pressure support and volume-assured pressure support ventilation, are presented. The results demonstrate the feasibility of using this type of device for non-invasive respiratory support and highlight the need for further testing to assess its safety and effectiveness in various clinical settings.
Collapse
Affiliation(s)
- Munam Arshad
- Manufacturing and Automation Research Center, Koc University, Istanbul, 34450, Turkey
| | - Khunsha Mehmood
- Manufacturing and Automation Research Center, Koc University, Istanbul, 34450, Turkey
| | - Ismail Lazoglu
- Manufacturing and Automation Research Center, Koc University, Istanbul, 34450, Turkey.
| |
Collapse
|
7
|
Guy EF, Clifton JA, Knopp JL, Holder-Pearson LR, Chase JG. Respiratory pressure and split flow data collection device with rapid occlusion attachment. HARDWAREX 2023; 16:e00489. [PMID: 38058767 PMCID: PMC10696101 DOI: 10.1016/j.ohx.2023.e00489] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/03/2023] [Accepted: 11/10/2023] [Indexed: 12/08/2023]
Abstract
Respiratory model-based methods require datasets containing enough dynamics to ensure model identifiability for development and validation. Rapid expiratory occlusion has been used to identify elastance and resistance within a single breath. Currently accepted practice for rapid expiratory occlusion involves a 100 ms occlusion of the expiratory pathway. This article presents a low-cost modular rapid shutter attachment to enable identification of passive respiratory mechanics. Shuttering faster than 100 ms creates rapid expiratory occlusion without the added dynamics of muscular response to shutter closure, by eliminating perceived expiratory blockage via high shutter speed. The shutter attachment fits onto a non-invasive venturi-based flow meter with separated inspiratory and expiratory pathways, established using one-way valves. Overall, these elements allow comprehensive collection of respiratory pressure and flow datasets with relatively very rapid expiratory occlusion.
Collapse
Affiliation(s)
- Ella F.S. Guy
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Jaimey A. Clifton
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Jennifer L. Knopp
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Lui R. Holder-Pearson
- Department of Electrical Engineering, University of Canterbury, Christchurch, New Zealand
| | - J. Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
8
|
Guy EFS, Knopp JL, Lerios T, Chase JG. Airflow and dynamic circumference of abdomen and thorax for adults at varied continuous positive airway pressure ventilation settings and breath rates. Sci Data 2023; 10:481. [PMID: 37481681 PMCID: PMC10363111 DOI: 10.1038/s41597-023-02326-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Accepted: 06/22/2023] [Indexed: 07/24/2023] Open
Abstract
Continuous positive airway pressure (CPAP) ventilation is a commonly prescribed respiratory therapy providing positive end-expiratory pressure (PEEP) to assist breathing and prevent airway collapse. Setting PEEP is highly debated and it is thus primarily titrated based on symptoms of excessive or insufficient support. However, titration periods are clinician intensive and can result in barotrauma or under-oxygenation during the process. Developing model-based methods to more efficiently personalise CPAP therapy based on patient-specific response requires clinical data of lung/CPAP interactions. To this end, a trial was conducted to establish a dataset of healthy subjects lung/CPAP interaction. Pressure, flow, and tidal volume were recorded alongside secondary measures of dynamic chest and abdominal circumference, to better validate model outcomes and assess breathing modes, muscular recruitment, and effort. N = 30 subjects (15 male; 15 female) were included. Self-reported asthmatics and smokers/vapers were included, offering a preliminary assessment of any potential differences in response to CPAP from lung stiffness changes in these scenarios. Additional demographics associated with lung function (sex, age, height, and weight) were also recorded.
Collapse
Affiliation(s)
- Ella F S Guy
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand.
| | - Jennifer L Knopp
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - Theodore Lerios
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| | - J Geoffrey Chase
- Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|
9
|
An identifiable model of lung mechanics to diagnose and monitor COPD. Comput Biol Med 2023; 152:106430. [PMID: 36543001 DOI: 10.1016/j.compbiomed.2022.106430] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Revised: 11/23/2022] [Accepted: 12/13/2022] [Indexed: 12/23/2022]
Abstract
BACKGROUND Current methods to diagnose and monitor COPD employ spirometry as the gold standard to identify lung function reduction with reduced forced expiratory volume (FEV1)/vital capacity (VC) ratio. Current methods utilise linear assumptions regarding airway resistance, where nonlinear resistance modelling may provide rapid insight into patient specific condition and disease progression. This study examines model-based expiratory resistance in healthy lungs and those with progressively more severe COPD. METHODS Healthy and COPD pressure (P)[cmH2O] and flow (Q)[L/s] data is obtained from the literature, and 5 intermediate levels of COPD and responses are created to simulate COPD progression and assess model-based metric resolution. Linear and nonlinear single compartment models are used to identify changes in inspiratory (R1,insp) and linear (R1,exp)/nonlinear (R2Φ) expiratory resistance with disease severity and over the course of expiration. RESULTS R1,insp increases from 2.1 to 7.3 cmH2O/L/s, R1,exp increases from 2.4 to 10.0 cmH2O/L/s with COPD severity. Nonlinear R2Φ increases (mean R2Φ: 2.5 cmH2O/L/s (healthy) to 24.4 cmH2O/L/s (COPD)), with increasing end-expiratory nonlinearity as COPD severity increases. CONCLUSION Expiratory resistance is increasingly highly nonlinear with COPD severity. These results show a simple, nonlinear model can capture fundamental COPD dynamics and progression from regular breathing data, and such an approach may be useful for patient-specific diagnosis and monitoring.
Collapse
|
10
|
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
|
11
|
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
|
12
|
Guy EFS, Knopp JL, Gilbertson O, Blue S, Holder-Pearson L, Chase JG. CPAP pressure and flow data at 2 positive pressure levels and multiple controlled breathing rates from a trial of 30 adults. BMC Res Notes 2022; 15:257. [PMID: 35842701 PMCID: PMC9288698 DOI: 10.1186/s13104-022-06133-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Accepted: 06/21/2022] [Indexed: 11/10/2022] Open
Abstract
OBJECTIVES A unique dataset of airway flow/pressure from healthy subjects on Continuous Positive Airway Pressure (CPAP) ventilation was collected. This data can be used to develop or validate models of pulmonary mechanics, and/or to develop methods to identify patient-specific parameters which cannot be measured non-invasively, during CPAP therapy. These models and values, particularly if available breath-to-breath in real-time, could assist clinicians in the prescription or optimisation of CPAP therapy, including optimising PEEP settings. DATA DESCRIPTION Data was obtained from 30 subjects for model-based identification of patient-specific lung mechanics using a specially designed venturi sensor system comprising an array of differential and gauge pressure sensors. Relevant medical information was collected using a questionnaire, including: sex; age; weight; height; smoking history; and history of asthma. Subjects were tasked with breathing at five different rates (including passive), matched to an online pacing sound and video, at two different levels of PEEP (4 and 7 cmH2O) for between 50 and 180 s. Each data set comprises ~ 17 breaths of data, including rest periods between breathing rates and CPAP levels.
Collapse
Affiliation(s)
- Ella F S Guy
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand.
| | - Jennifer L Knopp
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand
| | - Oliver Gilbertson
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand
| | - Simon Blue
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand
| | - Lui Holder-Pearson
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand
| | - J Geoffrey Chase
- Department of Mechanical Engineering, Centre for Bioengineering, University of Canterbury, Christchurch, New Zealand
| |
Collapse
|