Ventilator dyssynchrony (VD) can worsen lung injury and is challenging to detect and quantify due to the complex variability in the dyssynchronous breaths. While machine learning (ML) approaches are ...useful for automating VD detection from the ventilator waveform data, scalable severity quantification and its association with pathogenesis and ventilator mechanics remain challenging.
We develop a systematic framework to quantify pathophysiological features observed in ventilator waveform signals such that they can be used to create feature-based severity stratification of VD breaths.
A mathematical model was developed to represent the pressure and volume waveforms of individual breaths in a feature-based parametric form. Model estimates of respiratory effort strength were used to assess the severity of flow-limited (FL)-VD breaths compared to normal breaths. A total of 93,007 breath waveforms from 13 patients were analyzed.
A novel model-defined continuous severity marker was developed and used to estimate breath phenotypes of FL-VD breaths. The phenotypes had a predictive accuracy of over 97% with respect to the previously developed ML-VD identification algorithm. To understand the incidence of FL-VD breaths and their association with the patient state, these phenotypes were further successfully correlated with ventilator-measured parameters and electronic health records.
This work provides a computational pipeline to identify and quantify the severity of FL-VD breaths and paves the way for a large-scale study of VD causes and effects. This approach has direct application to clinical practice and in meaningful knowledge extraction from the ventilator waveform data.
Display omitted
•Ventilator dyssynchrony may instigate and exacerbate ventilator-induced lung injury.•Identifying and quantifying patient-ventilator dyssynchrony is necessary.•Quantifiable breath phenotypes of flow-limited dyssynchronous breaths are created.•An efficient pipeline is developed to extract knowledge from the waveform data.
Acute respiratory distress syndrome (ARDS) and acute lung injury have a diverse spectrum of causative factors including sepsis, aspiration of gastric contents, and near drowning. Clinical management ...of severe lung injury typically includes mechanical ventilation to maintain gas exchange which can lead to ventilator-induced lung injury (VILI). The cause of respiratory failure is acknowledged to affect the degree of lung inflammation, changes in lung structure, and the mechanical function of the injured lung. However, these differential effects of injury and the role of etiology in the structure-function relationship are not fully understood. To address this knowledge gap we caused lung injury with intratracheal hydrochloric acid (HCL) or endotoxin (LPS) 2 days prior to ventilation or with an injurious lavage (LAV) immediately prior to ventilation. These injury groups were then ventilated with high inspiratory pressures and positive end expiratory pressure (PEEP) = 0 cmH
O to cause VILI and model the clinical course of ARDS followed by supportive ventilation. The effects of injury were quantified using invasive lung function measurements recorded during PEEP ladders where the end-expiratory pressure was increased from 0 to 15 cm H
O and decreased back to 0 cmH
O in steps of 3 cmH
O. Design-based stereology was used to quantify the parenchymal structure of lungs air-inflated to 2, 5, and 10 cmH
O. Pro-inflammatory gene expression was measured with real-time quantitative polymerase chain reaction and alveolocapillary leak was estimated by measuring bronchoalveolar lavage protein content. The LAV group had small, stiff lungs that were recruitable at higher pressures, but did not demonstrate substantial inflammation. The LPS group showed septal swelling and high pro-inflammatory gene expression that was exacerbated by VILI. Despite widespread alveolar collapse, elastance in LPS was only modestly elevated above healthy mice (CTL) and there was no evidence of recruitability. The HCL group showed increased elastance and some recruitability, although to a lesser degree than LAV. Pro-inflammatory gene expression was elevated, but less than LPS, and the airspace dimensions were reduced. Taken together, those data highlight how different modes of injury, in combination with a 2
hit of VILI, yield markedly different effects.
Mechanical ventilation is an essential tool in the management of Acute Respiratory Distress Syndrome (ARDS), but it exposes patients to the risk of ventilator-induced lung injury (VILI). The human ...lung–ventilator system (LVS) involves the interaction of complex anatomy with a mechanical apparatus, which limits the ability of process-based models to provide individualized clinical support. This work proposes a hypothesis-driven strategy for LVS modeling in which robust personalization is achieved using a pre-defined parameter basis in a non-physiological model. Model inversion, here via windowed data assimilation, forges observed waveforms into interpretable parameter values that characterize the data rather than quantifying physiological processes. Accurate, model-based inference on human–ventilator data indicates model flexibility and utility over a variety of breath types, including those from dyssynchronous LVSs. Estimated parameters generate static characterizations of the data that are 50%–70% more accurate than breath-wise single-compartment model estimates. They also retain sufficient information to distinguish between the types of breath they represent. However, the fidelity and interpretability of model characterizations are tied to parameter definitions and model resolution. These additional factors must be considered in conjunction with the objectives of specific applications, such as identifying and tracking the development of human VILI.
Display omitted
•Patients under mechanical ventilation risk injury but are difficult to model or infer.•Informed-model data assimilation avoids many shortcomings of existing methods.•Interpretable parameters describe the system even in more complex cases.•Data characterization of ventilator dyssynchrony outperforms the traditional model.•Clinical informatics applications include lung injury progression for improved care.
Objective
Seizures have been implicated as a cause of secondary brain injury, but the systemic and cerebral physiologic effects of seizures after acute brain injury are poorly understood.
Methods
We ...analyzed intracortical electroencephalographic (EEG) and multimodality physiological recordings in 48 comatose subarachnoid hemorrhage patients to better characterize the physiological response to seizures after acute brain injury.
Results
Intracortical seizures were seen in 38% of patients, and 8% had surface seizures. Intracortical seizures were accompanied by elevated heart rate (p = 0.001), blood pressure (p < 0.001), and respiratory rate (p < 0.001). There were trends for rising cerebral perfusion pressure (p = 0.03) and intracranial pressure (p = 0.06) seen after seizure onset. Intracortical seizure–associated increases in global brain metabolism, partial brain tissue oxygenation, and regional cerebral blood flow (rCBF) did not reach significance, but a trend for a pronounced delayed rCBF rise was seen for surface seizures (p = 0.08). Functional outcome was very poor for patients with severe background attenuation without seizures and best for those without severe attenuation or seizures (77% vs 0% dead or severely disabled, respectively). Outcome was intermediate for those with seizures independent of the background EEG and worse for those with intracortical only seizures when compared to those with intracortical and scalp seizures (50% and 25% death or severe disability, respectively).
Interpretation
We replicated in humans complex physiologic processes associated with seizures after acute brain injury previously described in laboratory experiments and illustrated differences such as the delayed increase in rCBF. These real world physiologic observations may permit more successful translation of laboratory research to the bedside. Ann Neurol 2013;74:53–64
Diabetes is caused by the inability of electrically coupled, functionally heterogeneous β-cells within the pancreatic islet to provide adequate insulin secretion. Functional networks have been used ...to represent synchronized oscillatory Ca
dynamics and to study β-cell subpopulations, which play an important role in driving islet function. The mechanism by which highly synchronized β-cell subpopulations drive islet function is unclear. We used experimental and computational techniques to investigate the relationship between functional networks, structural (gap junction) networks, and intrinsic β-cell dynamics in slow and fast oscillating islets. Highly synchronized subpopulations in the functional network were differentiated by intrinsic dynamics, including metabolic activity and K
channel conductance, more than structural coupling. Consistent with this, intrinsic dynamics were more predictive of high synchronization in the islet functional network as compared to high levels of structural coupling. Finally, dysfunction of gap junctions, which can occur in diabetes, caused decreases in the efficiency and clustering of the functional network. These results indicate that intrinsic dynamics rather than structure drive connections in the functional network and highly synchronized subpopulations, but gap junctions are still essential for overall network efficiency. These findings deepen our interpretation of functional networks and the formation of functional subpopulations in dynamic tissues such as the islet.
Motivated by a desire to understand pulmonary physiology, scientists have developed physiological lung models of varying complexity. However, pathophysiology and interactions between human lungs and ...ventilators, e.g., ventilator-induced lung injury (VILI), present challenges for modeling efforts. This is because the real-world pressure and volume signals may be too complex for simple models to capture, and while complex models tend not to be estimable with clinical data, limiting clinical utility. To address this gap, in this manuscript we developed a new damaged-informed lung ventilator (DILV) model. This approach relies on mathematizing ventilator pressure and volume waveforms, including lung physiology, mechanical ventilation, and their interaction. The model begins with nominal waveforms and adds limited, clinically relevant, hypothesis-driven features to the waveform corresponding to pulmonary pathophysiology, patient-ventilator interaction, and ventilator settings. The DILV model parameters uniquely and reliably recapitulate these features while having enough flexibility to reproduce commonly observed variability in clinical (human) and laboratory (mouse) waveform data. We evaluate the proof-in-principle capabilities of our modeling approach by estimating 399 breaths collected for differently damaged lungs for tightly controlled measurements in mice and uncontrolled human intensive care unit data in the absence and presence of ventilator dyssynchrony. The cumulative value of mean squares error for the DILV model is, on average, ≈12 times less than the single compartment lung model for all the waveforms considered. Moreover, changes in the estimated parameters correctly correlate with known measures of lung physiology, including lung compliance as a baseline evaluation. Our long-term goal is to use the DILV model for clinical monitoring and research studies by providing high fidelity estimates of lung state and sources of VILI with an end goal of improving management of VILI and acute respiratory distress syndrome.
Neuromuscular blockade (NMB) is a therapy for acute respiratory distress syndrome (ARDS). However, the mechanism by which NMB may improve outcome for ARDS patients remains unclear. We sought to ...determine whether NMB attenuates biomarkers of epithelial and endothelial lung injury and systemic inflammation in ARDS patients, and whether the association is dependent on tidal volume size and the initial degree of hypoxemia.
We performed a secondary analysis of patients enrolled in the ARDS network low tidal volume ventilation (ARMA) study. Our primary predictor variable was the number of days receiving NMB between study enrollment and day 3. Our primary outcome variables were the change in concentration of biomarkers of epithelial injury (serum surfactant protein-D (SP-D)), endothelial injury (von Willebrand factor (VWF)), and systemic inflammation (interleukin (IL)-8). Multivariable regression analysis was used to compare the change in biomarker concentration controlling for multiple covariates. Patients were stratified by treatment arm (12 versus 6 cm
/kg) and by an initial arterial oxygen tension (PaO
) to fractional inspired oxygen (FiO
) (P/F) ratio of 120.
A total of 446 (49%) patients had complete SP-D, VWF, and IL-8 measurements on study enrollment and day 3. After adjusting for baseline differences, each day of NMB was associated with a decrease in SP-D (-23.7 ng/ml/day, p = 0.029), VWF (-33.5% of control/day, p = 0.015), and IL-8 (-362.6 pg/ml/day, p = 0.030) in patients with an initial P/F less than or equal to 120 and receiving low tidal volume ventilation. However, patients with a P/F ratio of greater than 120 or receiving high tidal volume ventilation had either no change or an increase in SP-D, WVF, or IL-8 concentrations.
NBM is associated with decreased biomarkers of epithelial and endothelial lung injury and systemic inflammation in ARDS patients receiving low tidal volume ventilation and those with a P/F ratio less than or equal to 120.
•Data assimilation using sparse data and complex models with many parameters can lead to non-unique or non-convergent parameter estimates.•When identifiability failure arises it can be difficult to ...decide which parameters to estimate from among the 10s to 100s of potential parameters.•The parameter Houlihan is a framework for selecting which parameters to estimate using data assimilation in the context of sparse data and identifiability failure to minimize non-uniqueness of parameter estimates and error.
One way to interject knowledge into clinically impactful forecasting is to use data assimilation, a nonlinear regression that projects data onto a mechanistic physiologic model, instead of a set of functions, such as neural networks. Such regressions have an advantage of being useful with particularly sparse, non-stationary clinical data. However, physiological models are often nonlinear and can have many parameters, leading to potential problems with parameter identifiability, or the ability to find a unique set of parameters that minimize forecasting error. The identifiability problems can be minimized or eliminated by reducing the number of parameters estimated, but reducing the number of estimated parameters also reduces the flexibility of the model and hence increases forecasting error. We propose a method, the parameter Houlihan, that combines traditional machine learning techniques with data assimilation, to select the right set of model parameters to minimize forecasting error while reducing identifiability problems. The method worked well: the data assimilation-based glucose forecasts and estimates for our cohort using the Houlihan-selected parameter sets generally also minimize forecasting errors compared to other parameter selection methods such as by-hand parameter selection. Nevertheless, the forecast with the lowest forecast error does not always accurately represent physiology, but further advancements of the algorithm provide a path for improving physiologic fidelity as well. Our hope is that this methodology represents a first step toward combining machine learning with data assimilation and provides a lower-threshold entry point for using data assimilation with clinical data by helping select the right parameters to estimate.
Nurses alter their monitoring behavior as a patient's clinical condition deteriorates, often detecting and documenting subtle changes before physiological trends are apparent. It was hypothesized ...that a nurse's behavior of recording optional documentation (beyond what is required) reflects concern about a patient's status and that mining data from patients' electronic health records for the presence of these features could help predict patients' mortality.
Data-mining methods were used to analyze electronic nursing documentation from a 15-month period at a large, urban academic medical center. Mortality rates and the frequency of vital sign measurements (beyond required) and optional nursing comment documentation were analyzed for a random set of patients and patients who experienced a cardiac arrest during their hospitalization. Patients were stratified by age-adjusted Charlson comorbidity index.
A total of 15,000 acute care patients and 145 cardiac arrest patients were studied. Patients who died had a mean of 0.9 to 1.5 more optional comments and 6.1 to 10 more vital signs documented within 48 hours than did patients who survived. A higher frequency of comment and vital sign documentation was also associated with a higher likelihood of cardiac arrest. Of patients who had a cardiac arrest, those with more documented comments were more likely to die.
For the first time, nursing documentation patterns have been linked to patients' mortality. Findings were consistent with the hypothesis that some features of nursing documentation within electronic health records can be used to predict mortality. With future work, these associations could be used in real time to establish a threshold of concern indicating a risk for deterioration in a patient's condition.