Nonlinear model for mechanical ventilation of human lungs

A Respiratory Motion Prediction Method Based on LSTM-AE with Attention Mechanism for Spine Surgery

Respiratory motion-induced vertebral movements can adversely impact intraoperative spine surgery, resulting in inaccurate positional information of the target region and unexpected damage during the operation. In this paper, we propose a novel deep learning architecture for respiratory motion prediction, which can adapt to different patients. The proposed method utilizes an LSTM-AE with attention mechanism network that can be trained using few-shot datasets during operation. To ensure real-time performance, a dimension reduction method based on the respiration-induced physical movement of spine vertebral bodies is introduced. The experiment collected data from prone-positioned patients under general anaesthesia to validate the prediction accuracy and time efficiency of the LSTM-AE-based motion prediction method. The experimental results demonstrate that the presented method (RMSE: 4.39%) outperforms other methods in terms of accuracy within a learning time of 2 min. The maximum predictive errors under the latency of 333 ms with respect to the x, y, and z axes of the optical camera system were 0.13, 0.07, and 0.10 mm, respectively, within a motion range of 2 mm.

Virtual patient framework for the testing of mechanical ventilation airway pressure and flow settings protocol

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.

Algebraic approximation of the distributed model for the pressure drop in the respiratory airways

The complexity of the human respiratory system causes that one of the main methods of analyzing the dynamic pulmonary phenomena and interpreting experimental results are simulations of its computational models. Among the most compound elements of these models, apart from the bronchial tree structure, is the phenomenon of flow limitation in flexible bronchi, which causes them to collapse with increasing flow, thus their properties, such as resistance, compliance and inertance, are highly nonlinear and time-varying. Commonly, this phenomenon is ignored, or a distributed model for the airway pressure drop is applied, simulated with a modified numerical solver of this differential equation (ODE). The disadvantages of this solution are the problems with taking into account the inherent singularity of the model and the long computation time due to iterative nature of the ODE procedure. The aim of the work was to derive an algebraic approximation of this distributed model, suitable for implementation in continuous dynamic models, to validate it by comparing the results of simulations with the respiratory system model including approximate and original (ODE solver) numerical procedures, as well as to evaluate possible acceleration of calculations. All simulations, including spontaneous breathing, mechanical ventilation with the optimal ventilatory waveform and forced expiration, proved that algebraic approximation yielded results negligibly differing from the ODE solution, and shortened the computation time by an order. The proposed approach is an attractive alternative in the case of computer implementations of pulmonary models, where simulations of flows and pressures in the complex respiratory system are of primary importance.

Numerical modeling and development of a dual lung simulator using partitioned fluid-structure interaction approach for ventilator testing

New designs of mechanical ventilators require extensive testing before utilizing the ventilator on a patient. Test lungs are commonly used to understand the behavior of new designs of ventilators and the lung mechanics. The current study aims to develop a numerical model of dual test lungs utilizing the partitioned fluid-structure interaction (FSI) approach and test it against the available experimental data of volume-controlled ventilation. Two breathing rates of 12 and 18 bpm were studied at two different tidal volumes of 500 and 600 ml for spontaneous breathing. It is found that with an increase in the compliance (tidal volume/pressure rise) of the lung, the peak pressure rise inside the test lung decreases irrespective of the breathing rate. The maximum average pressure of 44.73, 27.45, and 14 cm H₂ O is observed for static lung compliances of 10, 21 , and 39 ml/cm H₂ O, respectively at a tidal volume of 600 ml. Similarly, the maximum von-misses stress was higher (498 kPa) for the lung with lower compliance (10 ml/cm H₂ O) as compared to the lung with higher compliance (39 ml/cm H₂ O) at the end of inspiration. This study forms a basis for using computational methods to model simple lung simulators that can effectively investigate the lung mechanics for both spontaneous and ventilated breathing. Thus, it can be utilized as a reference to test novel designs of mechanical ventilators.

Stochastic Modelling of Respiratory System Elastance for Mechanically Ventilated Respiratory Failure Patients

While lung protective mechanical ventilation (MV) guidelines have been developed to avoid ventilator-induced lung injury (VILI), a one-size-fits-all approach cannot benefit every individual patient. Hence, there is significant need for the ability to provide patient-specific MV settings to ensure safety, and optimise patient care. Model-based approaches enable patient-specific care by identifying time-varying patient-specific parameters, such as respiratory elastance, Ers, to capture inter- and intra-patient variability. However, patient-specific parameters evolve with time, as a function of disease progression and patient condition, making predicting their future values crucial for recommending patient-specific MV settings. This study employs stochastic modelling to predict future Ers values using retrospective patient data to develop and validate a model indicating future intra-patient variability of Ers. Cross validation results show stochastic modelling can predict future elastance ranges with 92.59 and 68.56% of predicted values within the 5-95% and the 25-75% range, respectively. This range can be used to ensure patients receive adequate minute ventilation should elastance rise and minimise the risk of VILI should elastance fall. The results show the potential for model-based protocols using stochastic model prediction of future Ers values to provide safe and patient-specific MV. These results warrant further investigation to validate its clinical utility.

Non-Contact Respiratory Rate Estimation in Real-Time With Modified Joint Unscented Kalman Filter

It can be life-saving to monitor the respiratory rate (RR) even for healthy people in real-time. It is reported that the infected people with coronavirus disease 2019 (COVID-19), generally develop mild respiratory symptoms in the early stage. It will be more important to continuously monitor the RR of people in nursing homes and houses with a non-contact method. Conventional, contact-based, methods are not suitable for long-term health monitoring especially in-home care services. The potentials of wireless radio signals for health care applications, such as fall detection, etc., are examined in literature. In this paper, we focus on a device-free real-time RR monitoring system using wireless signals. In our recent study, we proposed a non-contact RR monitoring system with a batch processing (delayed) estimation method. In this paper, for real-time monitoring, we modify the standard joint unscented Kalman filter (JUKF) method for this new and time-critical problem. Due to the nonlinear structure of the RR estimation problem with respect to the measurements, a novel modification is proposed to transform measurement errors into parameter errors by using the hyperbolic tangent function. It is shown in the experiments conducted with the real measurements taken using healthy volunteers that the proposed modified joint unscented Kalman filter (ModJUKF) method achieves the highest accuracy according to the windowing-based methods in the time-varying RR scenario. It is also shown that the ModJUKF not only reduces the computational complexity approximately 8.54% but also improves the accuracy 36.7% with respect to the standard JUKF method.

Influence of bronchial diameter change on the airflow dynamics based on a pressure-controlled ventilation system

Bronchial diameter is a key parameter that affects the respiratory treatment of mechanically ventilated patients. In this paper, to reveal the influence of bronchial diameter on the airflow dynamics of pressure-controlled mechanically ventilated patients, a new respiratory system model is presented that combines multigeneration airways with lungs. Furthermore, experiments and simulation studies to verify the model are performed. Finally, through the simulation study, it can be determined that in airway generations 2 to 7, when the diameter is reduced to half of the original value, the maximum air pressure (maximum air pressure in lungs) decreases by nearly 16%, the maximum flow decreases by nearly 30%, and the total airway pressure loss (sum of each generation pressure drop) is more than 5 times the original value. Moreover, in airway generations 8 to 16, with increasing diameter, the maximum air pressure, maximum flow, and total airway pressure loss remain almost constant. When the diameter is reduced to half of the original value, the maximum air pressure decreases by 3%, the maximum flow decreases by nearly 5%, and the total airway pressure loss increases by 200%. The study creates a foundation for improvement in respiratory disease diagnosis and treatment.

Patient-specific optimization of mechanical ventilation for patients with acute respiratory distress syndrome using quasi-static pulmonary P-V data

Quasi-static, pulmonary pressure-volume (P-V) curves were combined with a respiratory system model to analyze tidal pressure cycles, simulating mechanical ventilation of patients with acute respiratory distress syndrome (ARDS). Two important quantities including 1) tidal recruited volume and 2) tidal hyperinflated volume were analytically computed by integrating the distribution of alveolar elements over the affected pop-open pressure range. We analytically predicted the tidal recruited volume of four canine subjects and compared our results with similar experimental measurements on canine models for the validation. We then applied our mathematical model to the P-V data of ARDS populations in four stages of Early ARDS, Deep Knee, Advanced ARDS and Baby Lung to quantify the tidal recruited volume and tidal hyperinflated volume as an indicator of ventilator-induced lung injury (VILI). These quantitative predictions based on patient-specific P-V data suggest that the optimum parameters of mechanical ventilation including PEEP and Tidal Pressure (Volume) are largely varying among ARDS population and are primarily influenced by the degree in the severity of ARDS.

Numerical simulation of volume-controlled mechanical ventilated respiratory system with 2 different lungs

Mechanical ventilation is a key therapy for patients who cannot breathe adequately by themselves, and dynamics of mechanical ventilation system is of great significance for life support of patients. Recently, models of mechanical ventilated respiratory system with 1 lung are used to simulate the respiratory system of patients. However, humans have 2 lungs. When the respiratory characteristics of 2 lungs are different, a single-lung model cannot reflect real respiratory system. In this paper, to illustrate dynamic characteristics of mechanical ventilated respiratory system with 2 different lungs, we propose a mathematical model of mechanical ventilated respiratory system with 2 different lungs and conduct experiments to verify the model. Furthermore, we study the dynamics of mechanical ventilated respiratory system with 2 different lungs. This research study can be used for improving the efficiency and safety of volume-controlled mechanical ventilation system.

Online Estimation Method for Respiratory Parameters Based on a Pneumatic Model

Mechanical ventilation is an important method to help people breathe. Respiratory parameters of ventilated patients are usually tracked for pulmonary diagnostics and respiratory treatment assessment. In this paper, to improve the estimation accuracy of respiratory parameters, a pneumatic model for mechanical ventilation was proposed. Furthermore, based on the mathematical model, a recursive least-squares algorithm was adopted to estimate the respiratory parameters. Finally, through experimental and numerical study, it was demonstrated that the proposed estimation method was effective and the method can be used in pulmonary diagnostics and treatment.

Dynamic Characteristics of Mechanical Ventilation System of Double Lungs with Bi-Level Positive Airway Pressure Model

In recent studies on the dynamic characteristics of ventilation system, it was considered that human had only one lung, and the coupling effect of double lungs on the air flow can not be illustrated, which has been in regard to be vital to life support of patients. In this article, to illustrate coupling effect of double lungs on flow dynamics of mechanical ventilation system, a mathematical model of a mechanical ventilation system, which consists of double lungs and a bi-level positive airway pressure (BIPAP) controlled ventilator, was proposed. To verify the mathematical model, a prototype of BIPAP system with a double-lung simulators and a BIPAP ventilator was set up for experimental study. Lastly, the study on the influences of key parameters of BIPAP system on dynamic characteristics was carried out. The study can be referred to in the development of research on BIPAP ventilation treatment and real respiratory diagnostics.

A RESPIRATORY MECHANICAL PARAMETERS ESTIMATION TECHNOLOGY BASED ON EXTENDED LEAST SQUARES

Respiratory mechanical parameters of ventilated patients are usually referred in the respiratory diagnosis and treatment. However, the effectiveness of the modern estimation methods is limited. To estimate the overall breathing resistance, overall respiratory compliance, and residual volume simultaneously, a new mathematical model of mechanical ventilation system was proposed. Furthermore, to improve the estimation accuracy, the noise model of mechanical ventilation system was taken into consideration. Based on the mathematical model, a respiratory mechanical parameters estimation method based on extended least squares (ELS) algorithm was derived. Finally, to test the respiratory mechanical parameters estimation method, it was studied experimentally and numerically, and it was approved that the proposed method is effective to estimate the three respiratory mechanical parameters simultaneously and precisely. The estimated values of the parameters can be adopted in the clinical practice. The study provides a new method to estimate respiratory mechanical parameters.

Pressure dynamic characteristics of pressure controlled ventilation system of a lung simulator

Mechanical ventilation is an important life support treatment of critically ill patients, and air pressure dynamics of human lung affect ventilation treatment effects. In this paper, in order to obtain the influences of seven key parameters of mechanical ventilation system on the pressure dynamics of human lung, firstly, mechanical ventilation system was considered as a pure pneumatic system, and then its mathematical model was set up. Furthermore, to verify the mathematical model, a prototype mechanical ventilation system of a lung simulator was proposed for experimental study. Last, simulation and experimental studies on the air flow dynamic of the mechanical ventilation system were done, and then the pressure dynamic characteristics of the mechanical system were obtained. The study can be referred to in the pulmonary diagnostics, treatment, and design of various medical devices or diagnostic systems.

Determination of respiratory gas flow by electrical impedance tomography in an animal model of mechanical ventilation

Background

A recent method determines regional gas flow of the lung by electrical impedance tomography (EIT). The aim of this study is to show the applicability of this method in a porcine model of mechanical ventilation in healthy and diseased lungs. Our primary hypothesis is that global gas flow measured by EIT can be correlated with spirometry. Our secondary hypothesis is that regional analysis of respiratory gas flow delivers physiologically meaningful results.

Methods

In two sets of experiments n = 7 healthy pigs and n = 6 pigs before and after induction of lavage lung injury were investigated. EIT of the lung and spirometry were registered synchronously during ongoing mechanical ventilation. In-vivo aeration of the lung was analysed in four regions-of-interest (ROI) by EIT: 1) global, 2) ventral (non-dependent), 3) middle and 4) dorsal (dependent) ROI. Respiratory gas flow was calculated by the first derivative of the regional aeration curve. Four phases of the respiratory cycle were discriminated. They delivered peak and late inspiratory and expiratory gas flow (PIF, LIF, PEF, LEF) characterizing early or late inspiration or expiration.

Results

Linear regression analysis of EIT and spirometry in healthy pigs revealed a very good correlation measuring peak flow and a good correlation detecting late flow. PIF_EIT = 0.702 · PIF_spiro + 117.4, r² = 0.809; PEF_EIT = 0.690 · PEF_spiro-124.2, r² = 0.760; LIF_EIT = 0.909 · LIF_spiro + 27.32, r² = 0.572 and LEF_EIT = 0.858 · LEF_spiro-10.94, r² = 0.647. EIT derived absolute gas flow was generally smaller than data from spirometry. Regional gas flow was distributed heterogeneously during different phases of the respiratory cycle. But, the regional distribution of gas flow stayed stable during different ventilator settings. Moderate lung injury changed the regional pattern of gas flow.

Conclusions

We conclude that the presented method is able to determine global respiratory gas flow of the lung in different phases of the respiratory cycle. Additionally, it delivers meaningful insight into regional pulmonary characteristics, i.e. the regional ability of the lung to take up and to release air.

Leakage estimation using Kalman filtering in noninvasive mechanical ventilation

Noninvasive mechanical ventilation is today often used to assist patient with chronic respiratory failure. One of the main reasons evoked to explain asynchrony events, discomfort, unwillingness to be treated, etc., is the occurrence of nonintentional leaks in the ventilation circuit, which are difficult to account for because they are not measured. This paper describes a solution to the problem of variable leakage estimation based on a Kalman filter driven by airflow and the pressure signals, both of which are available in the ventilation circuit. The filter was validated by showing that based on the attained leakage estimates, practically all the untriggered cycles can be explained.

Adaptive control of a pressure-controlled artificial ventilator: a simulator-based evaluation using real COPD patient data

The paper discusses the application of a direct adaptive controller to a pressure controlled artificial ventilation problem. In pressure controlled ventilators, the manipulated variable is the maximum flow applied to the patient during the active phase (inspiration), and the regulated variable is the peak pressure at end-inspiration. This simulation case study focuses on patients diagnosed with Chronic Obstructive Pulmonary Disease (COPD), which require artificial/mechanical ventilation. An adaptive PID controller ensures peak pressures below critical values, by manipulating the flow delivered by the ventilator. The simulation study is performed on fractional-order models of the respiratory impedance identified from lung function data obtained from 21 COPD patients. Additional simulation studies show the robustness of the controller in presence of varying model parameters from the respiratory impedance of the patient. Possibilities to implement the control strategy as an online adaptive algorithm are also explored. The results show that the design of the control is suitable for this kind of application and provides useful insight on realistic scenarios.

Analysis of multiple linear regression algorithms used for respiratory mechanics monitoring during artificial ventilation

Many patients undergo long-term artificial ventilation and their respiratory system mechanics should be monitored to detect changes in the patient's state and to optimize ventilator settings. In this work the most popular algorithms for tracking variations of respiratory resistance (R(rs)) and elastance (E(rs)) over a ventilatory cycle were analysed in terms of systematic and random errors. Additionally, a new approach was proposed and compared to the previous ones. It takes into account an exact description of flow integration by volume-dependent lung compliance. The results of analyses showed advantages of this new approach and enabled to form several suggestions. Algorithms including R(rs) and E(rs) dependencies on airflow and lung volume can be effectively applied only at low levels of noise present in measurement data, otherwise the use of the simplest model with constant parameters is preferable. Additionally, one should avoid including the resistance dependence on airflow alone, since this considerably destroys the retrieved trace of R(rs). Finally, the estimated cyclic trajectories of R(rs) and E(rs) are more sensitive to noise present in pressure than in the flow signal, and the elastance traces are estimated more accurately than the resistance ones.

Preliminary study on the accuracy of respiratory input impedance measurement using the interrupter technique

Respiratory input impedance contains information about the state of pulmonary mechanics in the frequency domain. In this paper the possibility of respiratory impedance measurement by interrupter technique as well as the accuracy of this approach are assessed. Transient states of flow and pressure recorded during expiratory flow interruption are simulated with a complex, linear model for the respiratory system and then used to calculate the impedance, including three states of respiratory mechanics and the influence of the measurement noise. The results of computations are compared to the known, theoretical impedance of the model. At 1 kHz sampling rate, the optimal time window lays between 100 and 200 ms and is centred around the pressure jump caused by the flow interruption. The proposed algorithm yields satisfactory accuracy in the range from 10 to 400 Hz, particularly to 150 Hz. Depending on the simulated respiratory system state, the error of calculated impedance (relative Euclidean distance between the vectors of computed and theoretical values), for the window of 190 ms, varies between 5.0% and 7.1%.

A computer model of the artificially ventilated human respiratory system in adult intensive care

A multi-technique approach to modelling artificially ventilated patients on the adult general intensive care unit (ICU) is proposed. Compartmental modelling techniques were used to describe the mechanical ventilator and the flexible hoses that connect it to the patient. 3D CFD techniques were used to model flow in the major airways and a Windkessel style balloon model was used to model the mechanical properties of the lungs. A multi-compartment model of the lung based on bifurcating tree structures representing the conducting airways and pulmonary circulation allowed lung disease to be modelled in terms of altered V/Q ratios within a lognormal distribution of values and it is from these that gas exchange was determined. A compartmental modelling tool, Bathfp, was used to integrate the different modelling techniques into a single model. The values of key parameters in the model could be obtained from measurements on patients in an ICU whilst a sensitivity analysis showed that the model was insensitive to the value of other parameters within it. Measured and modelled values for arterial blood gases and airflow parameters are compared for 46 ventilator settings obtained from 6 ventilator dependent patients. The results show correlation coefficients of 0.88 and 0.85 for the arterial partial pressures of the O(2) and CO(2), respectively (p<0.01) and of 0.99 and 0.96 for upper airway pressure and tidal volume, respectively (p<0.01). The difference between measured and modelled values was large in physiological terms, suggesting that some optimisation of the model is required.

Lung model parameter estimation by unscented Kalman filter

Dynamic nonlinear models are the best choice to analyze respiratory systems and to describe system mechanics. In this work, Unscented Kalman Filtering (UKF) was used to estimate the dynamic nonlinear model parameters of the lung model by using the measured airway flow, mask pressure and integrated lung volume. Artificially generated data and the data from Chronic Obstructive Pulmonary Diseased (COPD) patients were analyzed by the proposed model and the proposed UKF algorithm. Simulation results for both cases demonstrated that UKF is a promising estimation method for the respiratory system analysis.

A Simulation Study of Expiratory Flow Limitation in Obstructive Patients during Mechanical Ventilation

Although normal lungs may be represented satisfactorily by symmetrical architecture, pathological conditions generally require accounting for asymmetrical branching of the bronchial tree, since lung heterogeneity may be significant in respiratory diseases. In the present study, a recently proposed symmetrical dynamic morphometric model of the human lung, based on Weibel's regular dichotomy, was adapted to simulate different physiopathological scenarios of lung heterogeneity. The asymmetrical architecture was mimicked by modeling different conductive airway compartments below the main bronchi, each compartment being characterized by regular branching. The respiratory zone and chest wall were described by a Voigt body and a constant elastance, respectively. Simulation results allowed us to investigate the influence of the main mechanisms involved in expiratory flow limitation and dynamic hyperinflation in mechanically ventilated COPD patients. In brief, they showed that convective gas acceleration plays a key role in reproducing a negative relationship between driving pressure and expiratory flow. Moreover, reduced lung elastance due to emphysema resulted in a remarkable increase in dynamic hyperinflation, although it did not significantly modify expiratory flow limitation. Finally, the presence of a normal lung compartment masked pathological behaviors, preventing standard techniques from revealing expiratory flow limitation in affected compartments.