Non-invasive over-distension measurements: data driven vs model-based.

Clinical measurements offer bedside monitoring aiming to minimise unintended over-distension, but have limitations and cannot be predicted for changes in mechanical ventilation (MV) settings and are only available in certain MV modes. This study introduces a non-invasive, real-time over-distension measurement, which is robust, predictable, and more intuitive than current methods. The proposed over-distension measurement, denoted as OD, is compared with the clinically proven stress index (SI). Correlation is analysed via R2 and Spearman rs. The OD safe range corresponding to the unit-less SI safe range (0.95-1.05) is calibrated by sensitivity and specificity test. Validation is fulfilled with 19 acute respiratory distress syndrome (ARDS) patients data (196 cases), including assessment across ARDS severity. Overall correlation between OD and SI yielded R2 = 0.76 and Spearman rs = 0.89. Correlation is higher considering only moderate and severe ARDS patients. Calibration of OD to SI yields a safe range defined: 0 ≤ OD ≤ 0.8 cmH2O. The proposed OD offers an efficient, general, real-time measurement of patient-specific lung mechanics, which is more intuitive and robust than SI. OD eliminates the limitations of SI in MV mode and its less intuitive lung status value. Finally, OD can be accurately predicted for new ventilator settings via its foundation in a validated predictive personalized lung mechanics model. Therefore, OD offers potential clinical value over current clinical methods.

Reconstructing asynchrony for mechanical ventilation using a hysteresis loop virtual patient model.

BACKGROUND: Patient-specific lung mechanics during mechanical ventilation (MV) can be identified from measured waveforms of fully ventilated, sedated patients. However, asynchrony due to spontaneous breathing (SB) effort can be common, altering these waveforms and reducing the accuracy of identified, model-based, and patient-specific lung mechanics. METHODS: Changes in patient-specific lung elastance over a pressure-volume (PV) loop, identified using hysteresis loop analysis (HLA), are used to detect the occurrence of asynchrony and identify its type and pattern. The identified HLA parameters are then combined with a nonlinear mechanics hysteresis loop model (HLM) to extract and reconstruct ventilated waveforms unaffected by asynchronous breaths. Asynchrony magnitude can then be quantified using an energy-dissipation metric, Easyn, comparing PV loop area between model-reconstructed and original, altered asynchronous breathing cycles. Performance is evaluated using both test-lung experimental data with a known ground truth and clinical data from four patients with varying levels of asynchrony. RESULTS: Root mean square errors for reconstructed PV loops are within 5% for test-lung experimental data, and 10% for over 90% of clinical data. Easyn clearly matches known asynchrony magnitude for experimental data with RMS errors < 4.1%. Clinical data performance shows 57% breaths having Easyn > 50% for Patient 1 and 13% for Patient 2. Patient 3 only presents 20% breaths with Easyn > 10%. Patient 4 has Easyn = 0 for 96% breaths showing accuracy in a case without asynchrony. CONCLUSIONS: Experimental test-lung validation demonstrates the method's reconstruction accuracy and generality in controlled scenarios. Clinical validation matches direct observations of asynchrony in incidence and quantifies magnitude, including cases without asynchrony, validating its robustness and potential efficacy as a clinical real-time asynchrony monitoring tool.

Ventilation/Perfusion Matching: Of Myths, Mice, and Men.

Despite a huge range in lung size between species, there is little measured difference in the ability of the lung to provide a well-matched air flow (ventilation) to blood flow (perfusion) at the gas exchange tissue. Here, we consider the remarkable similarities in ventilation/perfusion matching between species through a biophysical lens and consider evidence that matching in large animals is dominated by gravity but in small animals by structure.

High-Frequency Oscillatory Ventilation and Ventilator-Induced Lung Injury: Size Does Matter.

OBJECTIVES: The theoretical basis for minimizing tidal volume during high-frequency oscillatory ventilation may not be appropriate when lung tissue stretch occurs heterogeneously and/or rapidly. The objective of this study was to assess the extent to which increased ventilation heterogeneity may contribute to ventilator-induced lung injury during high-frequency oscillatory ventilation in adults compared with neonates on the basis of lung size, using a computational model of human lungs. DESIGN: Computational modeling study. SETTING: Research laboratory. SUBJECTS: High-fidelity, 3D computational models of human lungs, scaled to various sizes representative of neonates, children, and adults, with varying injury severity. All models were generated from one thoracic CT image of a healthy adult male. INTERVENTIONS: Oscillatory ventilation was simulated in each lung model at frequencies ranging from 0.2 to 40 Hz. Sinusoidal flow oscillations were delivered at the airway opening of each model and distributed through the lungs according to regional parenchymal mechanics. MEASUREMENTS AND MAIN RESULTS: Acinar flow heterogeneity was assessed by the coefficient of variation in flow magnitudes across all acini in each model. High-frequency oscillatory ventilation simulations demonstrated increasing heterogeneity of regional parenchymal flow with increasing lung size, with decreasing ratio of deadspace to total acinar volume, and with increasing frequency above lung corner frequency and resonant frequency. Potential for resonant amplification was greatest in injured adult-sized lungs with higher regional quality factors indicating the presence of underdamped lung regions. CONCLUSIONS: The potential for ventilator-induced lung injury during high-frequency oscillatory ventilation is enhanced at frequencies above lung corner frequency or resonant frequency despite reduced tidal volumes, especially in adults, due to regional amplification of heterogeneous flow. Measurements of corner frequency and resonant frequency should be considered during high-frequency oscillatory ventilation management.

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.

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.

Association of Placental Jets and Mega-Jets With Reduced Villous Density.

Spiral arteries (SAs) lie at the interface between the uterus and placenta, and supply nutrients to the placental surface. Maternal blood circulation is separated from the fetal circulation by structures called villous trees. SAs are transformed in early pregnancy from tightly coiled vessels to large high-capacity channels, which is believed to facilitate an increased maternal blood flow throughout pregnancy with minimal increase in velocity, preventing damage to delicate villous trees. Significant maternal blood flow velocities have been theorized in the space surrounding the villi (the intervillous space, IVS), particularly when SA conversion is inadequate, but have only recently been visualized reliably using pulsed wave Doppler ultrasonography. Here, we present a computational model of blood flow from SA openings, allowing prediction of IVS properties based on jet length. We show that jets of flow observed by ultrasound are likely correlated with increased IVS porosity near the SA mouth and propose that observed mega-jets (flow penetrating more than half the placental thickness) are only possible when SAs open to regions of the placenta with very sparse villous structures. We postulate that IVS tissue density must decrease at the SA mouth through gestation, supporting the hypothesis that blood flow from SAs influences villous tree development.

A multiscale model of placental oxygen exchange: The effect of villous tree structure on exchange efficiency.

The placenta is critical to fetal health during pregnancy as it supplies oxygen and nutrients to maintain life. It has a complex structure, and alterations to this structure across spatial scales are associated with several pregnancy complications, including intrauterine growth restriction (IUGR). The relationship between placental structure and its efficiency as an oxygen exchanger is not well understood in normal or pathological pregnancies. Here we present a computational framework that predicts oxygen transport in the placenta which accounts for blood and oxygen transport in the space around a placental functional unit (the villous tree). The model includes the well-defined branching structure of the largest villous tree branches, as well as a smoothed representation of the small terminal villi that comprise the placenta's gas exchange interfaces. The model demonstrates that oxygen exchange is sensitive to villous tree geometry, including the villous branch length and volume, which are seen to change in IUGR. This is because, to be an efficient exchanger, the architecture of the villous tree must provide a balance between maximising the surface area available for exchange, and the opposing condition of allowing sufficient maternal blood flow to penetrate into the space surrounding the tree. The model also predicts an optimum oxygen exchange when the branch angle is 24 °, as villous branches and TBs are spread out sufficiently to channel maternal blood flow deep into the placental tissue for oxygen exchange without being shunted directly into the DVs. Without concurrent change in the branch length and angles, the model predicts that the number of branching generations has a small influence on oxygen exchange. The modelling framework is presented in 2D for simplicity but is extendible to 3D or to incorporate the high-resolution imaging data that is currently evolving to better quantify placental structure.

Simulation of Forced Expiration in a Biophysical Model, With Homogeneous and Clustered Bronchoconstriction.

One limitation of forced spirometry is that it integrates the contribution of the complex and dynamic behavior of all of the airways and tissue of the lung into a single exhaling unit, hence, it is not clear how spirometric measures are affected by local changes to the airways or tissue such as the presence of "ventilation defects." Here, we adapt a wave-speed limitation model to a spatially distributed and anatomically based airway tree that is embedded within a deformable parenchyma, to simulate forced expiration in 1 s (FEV1). This provides a model that can be used to assess the consequence of imposed constrictions on FEV1. We first show how the model can be parameterized to represent imaging and forced spirometry data from nonasthmatic healthy young adults. We then compare the effect of homogeneous and clustered bronchoconstriction on FEV1 in six subject-specific models (three male and three female). The model highlights potential sources of normal subject variability in response to agonist challenge, including the interaction between sites of airway constriction and sites of flow limitation at baseline. The results support earlier studies which proposed that the significant constriction of nondefect airways must be present in order to match to clinical measurements of lung function.

Quantifying normal geometric variation in human pulmonary lobar geometry from high resolution computed tomography.

Previous studies of the ex vivo lung have suggested significant intersubject variability in lung lobe geometry. A quantitative description of normal lung lobe shape would therefore have value in improving the discrimination between normal population variability in shape and pathology. To quantify normal human lobe shape variability, a principal component analysis (PCA) was performed on high resolution computed tomography (HRCT) imaging of the lung at full inspiration. Volumetric imaging from 22 never-smoking subjects (10 female and 12 male) with normal lung function was included in the analysis. For each subject, an initial finite element mesh geometry was generated from a group of manually selected nodes that were placed at distinct anatomical locations on the lung surface. Each mesh used cubic shape functions to describe the surface curvilinearity, and the mesh was fitted to surface data for each lobe. A PCA was performed on the surface meshes for each lobe. Nine principal components (PCs) were sufficient to capture >90% of the normal variation in each of the five lobes. The analysis shows that lobe size can explain between 20% and 50% of intersubject variability, depending on the lobe considered. Diaphragm shape was the next most significant intersubject difference. When the influence of lung size difference is removed, the angle of the fissures becomes the most significant shape difference, and the variability in relative lobe size becomes important. We also show how a lobe from an independent subject can be projected onto the study population's PCs, demonstrating potential for abnormalities in lobar geometry to be defined in a quantitative manner.

Phenotype, endotype and patient-specific computational modelling for optimal treatment design in asthma.

Understanding and treatment of asthma is significantly complicated by the heterogeneous spectrum of phenotypes associated with the disease. Recent advances in phenotype classification promise more targeted therapies, but these categories are based on constellations of largely external measurements and are not necessarily indicative of underlying pathophysiology. We propose that computational modelling is a valuable tool that allows the disease spectrum to be decomposed not into phenotypes but rather into groups organized by underlying dysfunction, referred to by some authors as endotypes. By breaking down the asthmatic spectrum in this way, therapies can be targeted more directly to the underlying defects. This would be not only an important improvement in its own right, but also an important step toward the ultimate goal of patient-specific modelling.

A novel two-dimensional phantom for electrical impedance tomography using 3D printing.

Electrical impedance tomography (EIT) is an imaging method that can be used to image electrical impedance contrasts within various tissues of the body. To support development of EIT measurement systems, a phantom is required that represents the electrical characteristics of the imaging domain. No existing type of EIT phantom combines good performance in all three characteristics of resistivity resolution, spatial resolution, and stability. Here, a novel EIT phantom concept is proposed that uses 3D printed conductive material. Resistivity is controlled using the 3D printing infill percentage parameter, allowing arbitrary resistivity contrasts within the domain to be manufactured automatically. The concept of controlling resistivity through infill percentage is validated, and the manufacturing accuracy is quantified. A method for making electrical connections to the 3D printed material is developed. Finally, a prototype phantom is printed, and a sample EIT analysis is performed. The resulting phantom, printed with an Ultimaker S3, has high reported spatial resolution of 6.9 µm, 6.9 µm, and 2.5 µm for X, Y, and Z axis directions, respectively (X and Y being the horizontal axes, and Z the vertical). The number of resistivity levels that are manufacturable by varying infill percentage is 15 (calculated by dividing the available range of resistivities by two times the standard deviation of the manufacturing accuracy). This phantom construction technique will allow assessment of the performance of EIT devices under realistic physiological scenarios.

A Wearable Open-Source electrical impedance tomography device.

Electrical impedance tomography (EIT) is medical imaging technique in which small electrical signals are used to map the electrical impedance distribution within the body. It is safe and non-invasive, which make it attractive for use in continuous monitoring or outpatient applications, but the high cost of commercial devices is an impediment to its adoption. Over the last 10 years, many research groups have developed their own EIT devices, but few designs for open-source EIT hardware are available. In this work, we present a complete open-source EIT system that is designed to be suitable for monitoring the lungs of free breathing subjects. The device is low-cost, wearable, and is designed to comply with the industry accepted safety standard for EIT. The device has been tested in two regimes: Firstly in terms of measurement uncertainty as a voltage measurement system, and secondly against a set of measures that have been proposed specifically for EIT hardware. The voltage measurement uncertainty of the device was measured to be - 0.7 % ± 0.36 mV. The EIT specific performance was measured in a phantom test designed to be as physiologically representative as practicable, and the device performed similarly to other published devices. This work will contribute to increased accessibility of EIT for study and will contribute to consensus on testing methodology for EIT devices.

Evaluating Tissue Heterogeneity in the Radiologically Normal-Appearing Tissue in IPF Compared to Healthy Controls.

RATIONALE AND OBJECTIVES: Idiopathic Pulmonary Fibrosis (IPF) is a progressive interstitial lung disease characterised by heterogeneously distributed fibrotic lesions. The inter- and intra-patient heterogeneity of the disease has meant that useful biomarkers of severity and progression have been elusive. Previous quantitative computed tomography (CT) based studies have focussed on characterising the pathological tissue. However, we hypothesised that the remaining lung tissue, which appears radiologically normal, may show important differences from controls in tissue characteristics. MATERIALS AND METHODS: Quantitative metrics were derived from CT scans in IPF patients (N = 20) and healthy controls with a similar age (N = 59). An automated quantitative software (CALIPER, Computer-Aided Lung Informatics for Pathology Evaluation and Rating) was used to classify tissue as normal-appearing, fibrosis, or low attenuation area. Densitometry metrics were calculated for all lung tissue and for only the normal-appearing tissue. Heterogeneity of lung tissue density was quantified as coefficient of variation and by quadtree. Associations between measured lung function and quantitative metrics were assessed and compared between the two cohorts. RESULTS: All metrics were significantly different between controls and IPF (p < 0.05), including when only the normal tissue was evaluated (p < 0.04). Density in the normal tissue was 14% higher in the IPF participants than controls (p < 0.001). The normal-appearing tissue in IPF had heterogeneity metrics that exhibited significant positive relationships with the percent predicted diffusion capacity for carbon monoxide. CONCLUSION: We provide quantitative assessment of IPF lung tissue characteristics compared to a healthy control group of similar age. Tissue that appears visually normal in IPF exhibits subtle but quantifiable differences that are associated with lung function and gas exchange.

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.

Quantitative Analysis of Lung Shape in Idiopathic Pulmonary Fibrosis: Insights Into Disease- and Age-Associated Patterns.

RATIONALE AND OBJECTIVES: Fibrotic scarring in idiopathic pulmonary fibrosis (IPF) typically develops first in the posterior-basal lung tissue before advancing to involve more of the lung. The complexity of lung shape in the costo-diaphragmatic region has been proposed as a potential factor in this regional development. Intrinsic and disease-related shape could therefore be important for understanding IPF risk and its staging. We hypothesized that lung and lobe shape in IPF would have important differences from controls. MATERIALS AND METHODS: A principal component (PC) analysis was used to derive a statistical shape model (SSM) of the lung for a control cohort aged > 50 years (N = 39), using segmented lung and fissure surface data from CT imaging. Individual patient shape models derived for baseline (N = 18) and follow-up (N = 16) CT scans in patients with IPF were projected to the SSM to describe shape as the sum of the SSM average and weighted PC modes. Associations between the first four PC shape modes, lung function, percentage of fibrosis (fibrosis%) and pulmonary vessel-related structures (PVRS%), and other tissue metrics were assessed and compared between the two cohorts. RESULTS: Shape was different between IPF and controls (P < 0.05 for all shape modes), with IPF shape forming a distinct shape cluster. Shape had a negative relationship with age in controls (P = 0.013), but a positive relationship with age in IPF (P = 0.026). Some features of shape changed on follow-up. Shape in IPF was associated with fibrosis% (P < 0.05) and PVRS% (P < 0.05). CONCLUSION: Quantitative comparison of lung and lobe shape in IPF with controls of a similar age reveals shape differences that are strongly associated with age and percent fibrosis. The clustering of IPF cohort shape suggests that it could be an important feature to describe disease.

Blood flow in capillaries of the human lung.

A novel model for the blood system is postulated focusing on the flow rate and pressure distribution inside the arterioles and venules of the pulmonary acinus. Based upon physiological data it is devoid of any ad hoc constants. The model comprises nine generations of arterioles, venules, and capillaries in the acinus, the gas exchange unit of the lung. Blood is assumed incompressible and Newtonian and the blood vessels are assumed inextensible. Unlike previous models of the blood system, the venules and arterioles open up to the capillary network in numerous locations along each generation. The large number of interconnected capillaries is perceived as a porous medium in which the flow is macroscopically unidirectional from arterioles to venules openings. In addition, the large number of capillaries extending from each arteriole and venule allows introduction of a continuum theory and formulation of a novel system of ordinary, nonlinear differential equations which governs the blood flow and pressure fields along the arterioles, venules, and capillaries. The solution of the differential equations is semianalytical and requires the inversion of three diagonal, 9 × 9 matrices only. The results for the total flow rate of blood through the acinus are within the ballpark of physiological observations despite the simplifying assumptions used in our model. The results also manifest that the contribution of the nonlinear convection term of the Navier-Stokes equations has little effect (less than 2%) on the total blood flow entering/leaving the acinus despite the fact that the Reynolds number is not much smaller than unity at the proximal generations. The model makes it possible to examine some pathological cases. Here, centri-acinar and distal emphysema were investigated yielding a reduction in inlet blood flow rate.

In silico prediction of e-cigarette aerosol particle transport and deposition within the airways.

Electronic cigarettes (ECs) generate aerosols by heating up a liquid ('e-liquid') that typically consists of propylene glycol (PG), vegetable glycerol (VG), nicotine and flavouring agents. These aerosols transport through the airway tree, and lung and deposit non-uniformly in the bronchi and alveoli. Studying the transport of aerosols through lung airways is necessary because it provides information about the concentration and deposition of particles in the upper and lower airways. Here, particle transport and deposition were simulated within an anatomically-realistic airway model, which was constructed from computed tomography imaging. Particle transport was simulated using the advection-diffusion equations. Particle deposition was estimated using three different mechanisms; including sedimentation, impaction and Brownian diffusion. Results show that by increasing the particle size (PS) from 50 nm to 500 nm, the total deposition efficiency decreased from 50% to 10%, and then by increasing the PS to 3 µm, it increased to 60%. In addition, Brownian deposition was the dominant mechanism for nanoparticles (PS≪0.5µm), while the sedimentation deposition mechanism was the dominant one for microparticles (PS≫0.5µm).Clinical relevance-There is an urgent need to understand the risk that ECs pose to human health and to determine the safest methods for using these devices to support smoking cessation whilst also minimising harm. The results of this study will be used to simulate the conditions such as aerosol concentration and flow rate in airways and alveoli to use in in vitro studies.

Improved Electrical Impedance Tomography Reconstruction via a Bayesian Approach With an Anatomical Statistical Shape Model.

OBJECTIVE: electrical impedance tomography (EIT) is a promising technique for rapid and continuous bedside monitoring of lung function. Accurate and reliable EIT reconstruction of ventilation requires patient-specific shape information. However, this shape information is often not available and current EIT reconstruction methods typically have limited spatial fidelity. This study sought to develop a statistical shape model (SSM) of the torso and lungs and evaluate whether patient-specific predictions of torso and lung shape could enhance EIT reconstructions in a Bayesian framework. METHODS: torso and lung finite element surface meshes were fitted to computed tomography data from 81 participants, and a SSM was generated using principal component analysis and regression analyses. Predicted shapes were implemented in a Bayesian EIT framework and were quantitatively compared to generic reconstruction methods. RESULTS: Five principal shape modes explained 38% of the cohort variance in lung and torso geometry, and regression analysis yielded nine total anthropometrics and pulmonary function metrics that significantly predicted these shape modes. Incorporation of SSM-derived structural information enhanced the accuracy and reliability of the EIT reconstruction as compared to generic reconstructions, demonstrated by reduced relative error, total variation, and Mahalanobis distance. CONCLUSION: As compared to deterministic approaches, Bayesian EIT afforded more reliable quantitative and visual interpretation of the reconstructed ventilation distribution. However, no conclusive improvement of reconstruction performance using patient specific structural information was observed as compared to the mean shape of the SSM. SIGNIFICANCE: The presented Bayesian framework builds towards a more accurate and reliable method for ventilation monitoring via EIT.