Extrapolation of a non-linear autoregressive model of pulmonary mechanics

Pulmonary response prediction through personalized basis functions in a virtual patient model

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.

Estimating the incidence of spontaneous breathing effort of mechanically ventilated patients using a non-linear auto regressive (NARX) model

BACKGROUND AND OBJECTIVE

Mechanical ventilation (MV) provides breathing support for acute respiratory distress syndrome (ARDS) patients in the intensive care unit, but is difficult to optimize. Too much, or too little of pressure or volume support can cause further ventilator-induced lung injury, increasing length of MV, cost and mortality. Patient-specific respiratory mechanics can help optimize MV settings. However, model-based estimation of respiratory mechanics is less accurate when patient exhibit un-modeled spontaneous breathing (SB) efforts on top of ventilator support. This study aims to estimate and quantify SB efforts by reconstructing the unaltered passive mechanics airway pressure using NARX model.

METHODS

Non-linear autoregressive (NARX) model is used to reconstruct missing airway pressure due to the presence of spontaneous breathing effort in mv patients. Then, the incidence of SB patients is estimated. The study uses a total of 10,000 breathing cycles collected from 10 ARDS patients from IIUM Hospital in Kuantan, Malaysia. In this study, there are 2 different ratios of training and validating methods. Firstly, the initial ratio used is 60:40 which indicates 600 breath cycles for training and remaining 400 breath cycles used for testing. Then, the ratio is varied using 70:30 ratio for training and testing data.

RESULTS AND DISCUSSION

The mean residual error between original airway pressure and reconstructed airway pressure is denoted as the magnitude of effort. The median and interquartile range of mean residual error for both ratio are 0.0557 [0.0230 - 0.0874] and 0.0534 [0.0219 - 0.0870] respectively for all patients. The results also show that Patient 2 has the highest percentage of SB incidence and Patient 10 with the lowest percentage of SB incidence which proved that NARX model is able to perform for both higher incidence of SB effort or when there is a lack of SB effort.

CONCLUSION

This model is able to produce the SB incidence rate based on 10% threshold. Hence, the proposed NARX model is potentially useful to estimate and identify patient-specific SB effort, which has the potential to further assist clinical decisions and optimize MV settings.

Quantifying neonatal patient effort using non-invasive model-based methods

Patient-specific spontaneous breathing effort (SB) is common in invasively mechanically ventilated (MV) adult patients, and especially common in preterm neonates who are not typically sedated. However, there is no proven, ethically feasible and non-invasive method to quantify SB effort in neonates, creating the potential for model-based measures. Lung mechanics and SB effort are segregated using a basis function model to identify passive lung mechanics, and an additional time-varying elastance model to identify patient-specific SB effort and asynchrony as negative and positive added elastances, respectively. Data from ten preterm neonates on standard MV care in the neonatal intensive care unit (NICU) are used to assess this model-based approach, using area under the curve (AUC) for positive (asynchrony) and negative (SB effort) time-varying elastance. Median [interquartile-range (IQR)] of passive pulmonary lung elastance was 3.82 [2.09-5.80] cmH₂O/ml. Median [IQR] AUC quantified SB effort was -0.32 [-0.43--0.12]cmH₂O/ml. AUC quantified asynchrony was 0.00 [0.00-0.01]cmH₂O/ml, and affected 28% of the 25,287 total breaths. This proof of concept model-based approach provides a non-invasive, computationally straightforward, and thus clinically feasible means to quantify patient-specific spontaneous breathing effort and asynchrony.

Over-distension prediction via hysteresis loop analysis and patient-specific basis functions in a virtual patient model

BACKGROUND AND OBJECTIVE

Recruitment maneuvers (RMs) with subsequent positive-end-expiratory-pressure (PEEP) have proven effective in recruiting lung volume and preventing alveolar collapse. However, a suboptimal PEEP could induce undesired injury in lungs by insufficient or excessive breath support. Thus, a predictive model for patient response under PEEP changes could improve clinical care and lower risks.

METHODS

This research adds novel elements to a virtual patient model to identify and predict patient-specific lung distension to optimise and personalise care. Model validity and accuracy are validated using data from 18 volume-controlled ventilation (VCV) patients at 7 different baseline PEEP levels (0-12cmH₂O), yielding 623 prediction cases. Predictions were made up to ΔPEEP = 12cmH₂O ahead covering 6x2cmH₂O PEEP steps.

RESULTS

Using the proposed lung distension model, 90% of absolute peak inspiratory pressure (PIP) prediction errors compared to clinical measurement are within 3.95cmH₂O, compared with 4.76cmH₂O without this distension term. Comparing model-predicted and clinically measured distension had high correlation increasing to R² = 0.93-0.95 if maximum ΔPEEP ≤ 6cmH₂O. Predicted dynamic functional residual capacity (V_frc) changes as PEEP rises yield 0.013L median prediction error for both prediction groups and overall R² of 0.84.

CONCLUSIONS

Overall results demonstrate nonlinear distension mechanics are accurately captured in virtual lung mechanics patients for mechanical ventilation, for the first time. This result can minimise the risk of lung injury by predicting its potential occurrence of distension before changing ventilator settings. The overall outcomes significantly extend and more fully validate this virtual mechanical ventilation patient model.

Model-based estimation of negative inspiratory driving pressure in patients receiving invasive NAVA mechanical ventilation

BACKGROUND

Optimisation of mechanical ventilation (MV) and weaning requires insight into underlying patient breathing effort. Current identifiable models effectively describe lung mechanics, such as elastance (E) and resistance (R) at the bedside in sedated patients, but are less effective when spontaneous breathing is present. This research derives and regularises a single compartment model to identify patient-specific inspiratory effort.

METHODS

Constrained second-order b-spline basis functions (knot width 0.05 s) are used to describe negative inspiratory drive (Pp, cmH₂O) as a function of time. Breath-breath Pp are identified with single E and R values over inspiration and expiration from n = 20 breaths for N = 22 patients on NAVA ventilation. Pp is compared to measured electrical activity of the diaphragm (Eadi) and published results.

RESULTS

Average per-patient root-mean-squared model fit error was (median [interquartile range, IQR]) 0.9 [0.6-1.3] cmH₂O, and average per-patient median Pp was -3.9 [-4.5- -3.0] cmH₂O, with range -7.9 - -1.9 cmH₂O. Per-patient E and R were 16.4 [13.6-21.8] cmH₂O/L and 9.2 [6.4-13.1] cmH₂O.s/L, respectively. Most patients showed an inspiratory volume threshold beyond which Pp started to return to baseline, and Pp at peak Eadi (end-inspiration) was often strongly correlated with peak Eadi (R²=0.25-0.86). Similarly, average transpulmonary pressure was consistent breath-breath in most patients, despite differences in peak Eadi and thus peak airway pressure.

CONCLUSIONS

The model-based inspiratory effort aligns with electrical muscle activity and published studies showing neuro-muscular decoupling as a function of pressure and/or volume. Consistency in coupling/dynamics were patient-specific. Quantification of patient and ventilator work of breathing contributions may aid optimisation of MV modes and weaning.

A Nonlinear Hysteretic Model for Automated Prediction of Lung Mechanics during Mechanical Ventilation

Mechanical ventilation (MV) is core intensive care unit (ICU) therapy during the Covid-19 pandemic. Optimising MV care to a specific patient with respiratory failure is difficult due to inter- and intra- patient variability in lung mechanics and condition. The ability to accurately predict patient-specific lung response to a change in MV settings would enable semi-automated care and significantly improve the efficiency of MV monitoring and care. It has particular emphasis when considering MV care required to treat Covid-19 patients, who require longer MV care, where patient-specific care can reduce the time on MV required. This study develops a nonlinear smooth hysteresis loop model (HLM) able to capture the essential lung dynamics in a patient-specific fashion from measured ventilator data, particularly for changes of compliance and infection points of the pressure-volume loop. The automated (no human input) hysteresis loop analysis (HLA) method is applied to identify HLM model parameters, enabling automated digital cloning to create a virtual patient model to accurately predict lung response at a specified positive end expiratory pressure (PEEP) level, as well as in response to the changes of PEEP. The performance of this automated digital cloning approach is assessed using clinical data from 4 patients and 8 recruitment maneuver (RM) arms. Validation results show the HLM-based hysteresis loops identified using HLA match clinical pressure-volume loops very well with root-mean-square (RMS) errors less than 2% for all 8 data sets over 4 patients, validating the accuracy of the developed HLM in capturing the essential lung physiology and respiratory behaviours at different patient conditions. More importantly, the patient-specific digital clones at lower PEEP levels accurately predict lung response at higher PEEP levels with predicted peak inspiratory pressure (PIP) errors less than 2% in average. In addition, the resulted additional lung volume Vfrc obtained with PEEP changes are predicted with average absolute difference of 0.025L. The overall results validate the versatility and potential of the developed HLM for delineating changes of nonlinear lung dynamics, and its capability to create a predictive virtual patient with use of HLA for future treatment personalization and optimisation in MV therapy.

Virtual patients for mechanical ventilation in the intensive care unit

BACKGROUND

Mechanical ventilation (MV) is a core intensive care unit (ICU) therapy. Significant inter- and intra- patient variability in lung mechanics and condition makes managing MV difficult. Accurate prediction of patient-specific response to changes in MV settings would enable optimised, personalised, and more productive care, improving outcomes and reducing cost. This study develops a generalised digital clone model, or in-silico virtual patient, to accurately predict lung mechanics in response to changes in MV.

METHODS

An identifiable, nonlinear hysteresis loop model (HLM) captures patient-specific lung dynamics identified from measured ventilator data. Identification and creation of the virtual patient model is fully automated using the hysteresis loop analysis (HLA) method to identify lung elastances from clinical data. Performance is evaluated using clinical data from 18 volume-control (VC) and 14 pressure-control (PC) ventilated patients who underwent step-wise recruitment maneuvers.

RESULTS

Patient-specific virtual patient models accurately predict lung response for changes in PEEP up to 12 cmH₂O for both volume and pressure control cohorts. R² values for predicting peak inspiration pressure (PIP) and additional retained lung volume, V_frc in VC, are R²=0.86 and R²=0.90 for 106 predictions over 18 patients. For 14 PC patients and 84 predictions, predicting peak inspiratory volume (PIV) and V_frc yield R²=0.86 and R²=0.83. Absolute PIP, PIV and V_frc errors are relatively small.

CONCLUSIONS

Overall results validate the accuracy and versatility of the virtual patient model for capturing and predicting nonlinear changes in patient-specific lung mechanics. Accurate response prediction enables mechanically and physiologically relevant virtual patients to guide personalised and optimised MV therapy.

The safety and efficacy of airway pressure release ventilation in acute respiratory distress syndrome patients: A PRISMA-compliant systematic review and meta-analysis

BACKGROUND

The acute respiratory distress syndrome (ARDS) is a critical illness with high mortality and a worse prognosis. Mechanical ventilation (MV) is currently considered to be one of the most effective methods of treating ARDS. In this meta-analysis, we discussed the efficacy of airway pressure release ventilation (APRV) in treating ARDS.

METHODS

Following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA), Ovid Medline, Embase, and PubMed were systematically searched with the keywords of "ARDS" and "APRV". The studies containing the treatment of APRV in ARDS were included. According to the MV protocol used in the studies, the comparison was undertaken between the APRV group vs low tidal volume (LTV) group and synchronized intermittent mandatory ventilation (SIMV) group. The relative risk (RR) and the standard mean difference with 95% confidence intervals (CI) were used for the comparison between groups.

RESULTS

Fourteen studies with 2096 patients were included in the meta-analysis. The average increasing rate of PaO2/FiO2 was 75.4% in the APRV group vs 44.1% in the non-APRV group. No significant differences were found in mortality and duration of ICU stay between APRV vs LTV (P = .073 and P = .404) and APRV vs SIMV (P = .370 and P = .894).

CONCLUSION

The APRV protocol would have a higher increase in the PaO2/FiO2 ratio, which was a safe protocol with a compatible effect comparing to LTV and SIMV.

Patient asynchrony modelling during controlled mechanical ventilation therapy

BACKGROUND AND OBJECTIVE

Mechanical ventilation therapy of respiratory failure patients can be guided by monitoring patient-specific respiratory mechanics. However, the patient's spontaneous breathing effort during controlled ventilation changes airway pressure waveform and thus affects the model-based identification of patient-specific respiratory mechanics parameters. This study develops a model to estimate respiratory mechanics in the presence of patient effort.

METHODS

Gaussian effort model (GEM) is a derivative of the single-compartment model with basis function. GEM model uses a linear combination of basis functions to model the nonlinear pressure waveform of spontaneous breathing patients. The GEM model estimates respiratory mechanics such as Elastance and Resistance along with the magnitudes of basis functions, which accounts for patient inspiratory effort.

RESULTS AND DISCUSSION

The GEM model was tested using both simulated data and a retrospective observational clinical trial patient data. GEM model fitting to the original airway pressure waveform is better than any existing models when reverse triggering asynchrony is present. The fitting error of GEM model was less than 10% for both simulated data and clinical trial patient data.

CONCLUSION

GEM can capture the respiratory mechanics in the presence of patient effect in volume control ventilation mode and also can be used to assess patient-ventilator interaction. This model determines basis functions magnitudes, which can be used to simulate any waveform of patient effort pressure for future studies. The estimation of parameter identification GEM model can further be improved by constraining the parameters within a physiologically plausible range during least-square nonlinear regression.

Optimising mechanical ventilation through model-based methods and automation

Mechanical ventilation (MV) is a core life-support therapy for patients suffering from respiratory failure or acute respiratory distress syndrome (ARDS). Respiratory failure is a secondary outcome of a range of injuries and diseases, and results in almost half of all intensive care unit (ICU) patients receiving some form of MV. Funding the increasing demand for ICU is a major issue and MV, in particular, can double the cost per day due to significant patient variability, over-sedation, and the large amount of clinician time required for patient management. Reducing cost in this area requires both a decrease in the average duration of MV by improving care, and a reduction in clinical workload. Both could be achieved by safely automating all or part of MV care via model-based dynamic systems modelling and control methods are ideally suited to address these problems. This paper presents common lung models, and provides a vision for a more automated future and explores predictive capacity of some current models. This vision includes the use of model-based methods to gain real-time insight to patient condition, improve safety through the forward prediction of outcomes to changes in MV, and develop virtual patients for in-silico design and testing of clinical protocols. Finally, the use of dynamic systems models and system identification to guide therapy for improved personalised control of oxygenation and MV therapy in the ICU will be considered. Such methods are a major part of the future of medicine, which includes greater personalisation and predictive capacity to both optimise care and reduce costs. This review thus presents the state of the art in how dynamic systems and control methods can be applied to transform this core area of ICU medicine.

A virtual patient model for mechanical ventilation

BACKGROUND AND OBJECTIVES

Mechanical ventilation (MV) is a primary therapy for patients with acute respiratory failure. However, poorly selected ventilator settings can cause further lung damage due to heterogeneity of healthy and damaged alveoli. Varying positive-end-expiratory-pressure (PEEP) to a point of minimum elastance is a lung protective ventilator strategy. However, even low levels of PEEP can lead to ventilator induced lung injury for individuals with highly inflamed pulmonary tissue. Hence, models that could accurately predict peak inspiratory pressures after changes to PEEP could improve clinician confidence in attempting potentially beneficial treatment strategies.

METHODS

This study develops and validates a physiologically relevant respiratory model that captures elastance and resistance via basis functions within a well-validated single compartment lung model. The model can be personalised using information available at a low PEEP to predict lung mechanics at a higher PEEP. Proof of concept validation is undertaken with data from four patients and eight recruitment manoeuvre arms.

RESULTS

Results show low error when predicting upwards over the clinically relevant pressure range, with the model able to predict peak inspiratory pressure with less than 10% error over 90% of the range of PEEP changes up to 12 cmH₂O.

CONCLUSIONS

The results provide an in-silico model-based means of predicting clinically relevant responses to changes in MV therapy, which is the foundation of a first virtual patient for MV.

Next-generation, personalised, model-based critical care medicine: a state-of-the art review of in silico virtual patient models, methods, and cohorts, and how to validation them

Critical care, like many healthcare areas, is under a dual assault from significantly increasing demographic and economic pressures. Intensive care unit (ICU) patients are highly variable in response to treatment, and increasingly aging populations mean ICUs are under increasing demand and their cohorts are increasingly ill. Equally, patient expectations are growing, while the economic ability to deliver care to all is declining. Better, more productive care is thus the big challenge. One means to that end is personalised care designed to manage the significant inter- and intra-patient variability that makes the ICU patient difficult. Thus, moving from current "one size fits all" protocolised care to adaptive, model-based "one method fits all" personalised care could deliver the required step change in the quality, and simultaneously the productivity and cost, of care. Computer models of human physiology are a unique tool to personalise care, as they can couple clinical data with mathematical methods to create subject-specific models and virtual patients to design new, personalised and more optimal protocols, as well as to guide care in real-time. They rely on identifying time varying patient-specific parameters in the model that capture inter- and intra-patient variability, the difference between patients and the evolution of patient condition. Properly validated, virtual patients represent the real patients, and can be used in silico to test different protocols or interventions, or in real-time to guide care. Hence, the underlying models and methods create the foundation for next generation care, as well as a tool for safely and rapidly developing personalised treatment protocols over large virtual cohorts using virtual trials. This review examines the models and methods used to create virtual patients. Specifically, it presents the models types and structures used and the data required. It then covers how to validate the resulting virtual patients and trials, and how these virtual trials can help design and optimise clinical trial. Links between these models and higher order, more complex physiome models are also discussed. In each section, it explores the progress reported up to date, especially on core ICU therapies in glycemic, circulatory and mechanical ventilation management, where high cost and frequency of occurrence provide a significant opportunity for model-based methods to have measurable clinical and economic impact. The outcomes are readily generalised to other areas of medical care.

Prediction of high airway pressure using a non-linear autoregressive model of pulmonary mechanics

Background

For mechanically ventilated patients with acute respiratory distress syndrome (ARDS), suboptimal PEEP levels can cause ventilator induced lung injury (VILI). In particular, high PEEP and high peak inspiratory pressures (PIP) can cause over distension of alveoli that is associated with VILI. However, PEEP must also be sufficient to maintain recruitment in ARDS lungs. A lung model that accurately and precisely predicts the outcome of an increase in PEEP may allow dangerous high PIP to be avoided, and reduce the incidence of VILI.

Methods and results

Sixteen pressure-flow data sets were collected from nine mechanically ventilated ARDs patients that underwent one or more recruitment manoeuvres. A nonlinear autoregressive (NARX) model was identified on one or more adjacent PEEP steps, and extrapolated to predict PIP at 2, 4, and 6 cmH₂O PEEP horizons. The analysis considered whether the predicted and measured PIP exceeded a threshold of 40 cmH₂O. A direct comparison of the method was made using the first order model of pulmonary mechanics (FOM(I)). Additionally, a further, more clinically appropriate method for the FOM was tested, in which the FOM was trained on a single PEEP prior to prediction (FOM(II)). The NARX model exhibited very high sensitivity (> 0.96) in all cases, and a high specificity (> 0.88). While both FOM methods had a high specificity (> 0.96), the sensitivity was much lower, with a mean of 0.68 for FOM(I), and 0.82 for FOM(II).

Conclusions

Clinically, false negatives are more harmful than false positives, as a high PIP may result in distension and VILI. Thus, the NARX model may be more effective than the FOM in allowing clinicians to reduce the risk of applying a PEEP that results in dangerously high airway pressures.