Search

Abstract We investigated the potential of the transmission line model as a digital twin of aneurysmal aorta by comparatively analyzing how a uniform lossless tube-load model were fitted to the carotid and femoral artery tonometry waveforms pertaining to (i) 79 abdominal aortic aneurysm (AAA) patients vs their matched controls (CON) and (ii) 35 AAA patients before vs after endovascular aneurysm repair (EVAR). The uniform lossless tube-load model fitted the tonometry waveforms pertaining to AAA as well as CON and EVAR. In addition, the parameters in the tube-load model exhibited physiologically explainable changes: when normalized, both pulse transit time and reflection coefficient increased with AAA and decreased after EVAR, which can be explained by the increase in arterial compliance and the decrease in arterial inertance due to the aortic expansion associated with AAA. In sum, the tube-load model may have the potential as a digital twin to enable personalized AAA monitoring.

IntroductionTreating extensive burn injury requires an individually tailored resuscitation protocol that includes hourly-titrated intravenous fluid infusion to avert both hypovolemic shock and edema. Due to the complexity of burn pathophysiology and significant variability in treatment protocols, there is an ongoing effort to optimize burn resuscitation. The goal of this work is to contribute to this effort by developing a mathematical model of burn pathophysiology and resuscitation for in silico testing of burn resuscitation protocols and decision-support systems.MethodsIn our previous work, we developed and validated a mathematical model consisting of volume kinetics, burn-induced perturbations, and kidney function. In this work, we expanded our previous mathematical model to incorporate novel mathematical models of cardiovascular system and hormonal system (renin-angiotensin-aldosterone (RAAS) system and antidiuretic hormone) which affect blood volume and pressure regulation. We also developed a detailed mathematical model of kidney function to regulate blood volume, pressure, and sodium levels, including components for glomerular filtration rate, reabsorption rates in nephron tubules, Tubuglomerular feedback, and myogenic mechanisms. We trained and validated the expanded mathematical model using experimental data from 15 pigs and 9 sheep with extensive burns to quantitatively evaluate its prediction accuracy for hematocrit, cardiac output, mean arterial pressure, central venous pressure, serum sodium levels, and urinary output. We then trained and tested the mathematical model using a clinical dataset of 233 human burn patients with demographic data and urinary output measurements.ResultsThe mathematical model could predict all tested variables very well, while internal variables and estimated parameters were consistent with the literature.DiscussionTo the best of our knowledge, this is the first mathematical model of burn injury and resuscitation which is extensively validated to replicate actual burn patients. Hence, this in silico platform may complement large animal pre-clinical testing of burn resuscitation protocols. Beyond its primary purpose, the mathematical model can be used as a training tool for healthcare providers delivering insight into the pathophysiology of burn shock, and offering novel mathematical models of human physiology which can be independently used for other purposes and contexts.

The past several decades have seen rapid advances in diagnosis and treatment of cardiovascular diseases and stroke, enabled by technological breakthroughs in imaging, genomics, and physiological monitoring, coupled with therapeutic interventions. We now face the challenge of how to (1) rapidly process large, complex multimodal and multiscale medical measurements; (2) map all available data streams to the trajectories of disease states over the patient's lifetime; and (3) apply this information for optimal clinical interventions and outcomes. Here we review new advances that may address these challenges using digital twin technology to fulfill the promise of personalized cardiovascular medical practice. Rooted in engineering mechanics and manufacturing, the digital twin is a virtual representation engineered to model and simulate its physical counterpart. Recent breakthroughs in scientific computation, artificial intelligence, and sensor technology have enabled rapid bidirectional interactions between the virtual‐physical counterparts with measurements of the physical twin that inform and improve its virtual twin, which in turn provide updated virtual projections of disease trajectories and anticipated clinical outcomes. Verification, validation, and uncertainty quantification builds confidence and trust by clinicians and patients in the digital twin and establishes boundaries for the use of simulations in cardiovascular medicine. Mechanistic physiological models form the fundamental building blocks of the personalized digital twin that continuously forecast optimal management of cardiovascular health using individualized data streams. We present exemplars from the existing body of literature pertaining to mechanistic model development for cardiovascular dynamics and summarize existing technical challenges and opportunities pertaining to the foundation of a digital twin.

Physiological closed-loop controlled (PCLC) medical devices, such as those designed for blood pressure regulation, can be tested for safety and efficacy in real-world clinical settings. However, relying solely on limited animal and clinical studies may not capture the diverse range of physiological conditions. Credible mathematical models can complement these studies by allowing the testing of the device against simulated patient scenarios. This research involves the development and validation of a low-order lumped-parameter mathematical model of the cardiovascular system’s response to fluid perturbation. The model takes rates of hemorrhage and fluid infusion as inputs and provides hematocrit and blood volume, heart rate, stroke volume, cardiac output and mean arterial blood pressure as outputs. The model was calibrated using data from 27 sheep subjects, and its predictive capability was evaluated through a leave-one-out cross-validation procedure, followed by independent validation using 12 swine subjects. Our findings showed small model calibration error against the training dataset, with the normalized root-mean-square error (NRMSE) less than 10% across all variables. The mathematical model and virtual patient cohort generation tool demonstrated a high level of predictive capability and successfully generated a sufficient number of subjects that closely resembled the test dataset. The average NRMSE for the best virtual subject, across two distinct samples of virtual subjects, was below 12.7% and 11.9% for the leave-one-out cross-validation and independent validation dataset. These findings suggest that the model and virtual cohort generator are suitable for simulating patient populations under fluid perturbation, indicating their potential value in PCLC medical device evaluation.

This paper investigates the feasibility of detecting and estimating the rate of internal hemorrhage based on continuous noninvasive hematocrit measurement. A unique challenge in hematocrit-based hemorrhage detection is that hematocrit decreases in response to hemorrhage and resuscitation with fluids, which makes hemorrhage detection during resuscitation challenging. We developed two sequential inference algorithms for detection of internal hemorrhage based on the Luenberger observer and the extended Kalman filter. The sequential inference algorithms use fluid resuscitation dose and hematocrit measurement as inputs to generate signatures to enable detection of internal hemorrhage. In the case of the extended Kalman filter, the signature is nothing but inferred hemorrhage rate, which allows it to also estimate internal hemorrhage rate. We evaluated the proof-of-concept of these algorithms based on in silico evaluation in 100 virtual patients subject to diverse hemorrhage and resuscitation rates. The results showed that the sequential inference algorithms outperformed naïve internal hemorrhage detection based on the decrease in hematocrit when hematocrit noise level was 1% (average F1 score: Luenberger observer 0.80; extended Kalman filter 0.76; hematocrit 0.59). Relative to the Luenberger observer, the extended Kalman filter demonstrated comparable internal hemorrhage detection performance and superior accuracy in estimating the hemorrhage rate. The analysis of the dependence of the sequential inference algorithms on measurement noise and plant parametric uncertainty showed that small (≤1%) hematocrit noise level and personalization of sequential inference algorithms may enable continuous noninvasive detection of internal hemorrhage and estimation of its rate.

Abstract Physiological closed-loop controlled (PCLC) medical devices monitor and automatically adjust the patient’s condition by using physiological variables as feedback, ideally with minimal human intervention to achieve the target levels set by a clinician. PCLC devices present a challenge when it comes to evaluating their performance, where conducting large clinical trials can be expensive. Virtual physiological patients simulated by validated mathematical models can be utilized to obtain pre-clinical evidence of safety and assess the performance of the PCLC medical device during normal and worst-case conditions that are unlikely to happen in a limited clinical trial. A physiological variable that plays a major role during fluid resuscitation is heart rate (HR). For in silico assessment of PCLC medical devices regarding fluid perturbation, there is currently no mathematical model of HR validated in terms of its predictive capability performance. This paper develops and validates a mathematical model of HR response using data collected from sheep subjects undergoing hemorrhage and fluid infusion. The model proved to be accurate in estimating the HR response to fluid perturbation, where averaged between 21 calibration datasets, the fitting performance showed a normalized root mean square error (NRMSE) of $$7.41 \pm 2.8 \%$$ 7.41 ± 2.8 % . The model was also evaluated in terms of model predictive capability performance via a leave-one-out procedure (21 subjects) and an independent validation dataset (6 subjects). Two different virtual cohort generation tools were used in each validation analysis. The generated envelope of virtual subjects robustly met the defined acceptance criteria, in which $$95\%$$ 95 % of the testing datasets presented simulated HR patterns that were within a deviation of 50% from the observed data. In addition, out of 16000 and 18522 simulated subjects for the leave-one-out and independent datasets, the model was able to generate at least one virtual subject that was close to the real subject within an error margin of $$9.56 \pm 3.15\%$$ 9.56 ± 3.15 % and $$11.1 \pm 1.22\%$$ 11.1 ± 1.22 % NRMSE, respectively. In conclusion, the model can generate valid virtual HR physiological responses to fluid perturbation and be incorporated into future non-clinical simulated testing setups for assessing PCLC devices intended for fluid resuscitation.

Abstract Abdominal aortic aneurysms (AAAs) are lethal but treatable yet substantially under-diagnosed and under-monitored. Hence, new AAA monitoring devices that are convenient in use and cost are needed. Our hypothesis is that analysis of arterial waveforms, which could be obtained with such a device, can provide information about AAA size. We aim to initially test this hypothesis via tonometric waveforms. We study noninvasive carotid and femoral blood pressure (BP) waveforms and reference image-based maximal aortic diameter measurements from 50 AAA patients as well as the two noninvasive BP waveforms from these patients after endovascular repair (EVAR) and from 50 comparable control patients. We develop linear regression models for predicting the maximal aortic diameter from waveform or non-waveform features. We evaluate the models in out-of-training data in terms of predicting the maximal aortic diameter value and changes induced by EVAR. The best model includes the carotid area ratio (diastolic area divided by systolic area) and normalized carotid-femoral pulse transit time ((age·diastolic BP)/(height/PTT)) as input features with positive model coefficients. This model is explainable based on the early, negative wave reflection in AAA and the Moens-Korteweg equation for relating PTT to vessel diameter. The predicted maximal aortic diameters yield receiver operating characteristic area under the curves of 0.83 ± 0.04 in classifying AAA versus control patients and 0.72 ± 0.04 in classifying AAA patients before versus after EVAR. These results are significantly better than a baseline model excluding waveform features as input. Our findings could potentially translate to convenient devices that serve as an adjunct to imaging.

Stress is a major determinant of health and wellbeing. Conventional stress management approaches do not account for the daily-living acute changes in stress that affect quality of life. The combination of physiological monitoring and non-invasive Peripheral Nerve Stimulation (PNS) represents a promising technological approach to quantify stress-induced physiological manifestations and reduce stress during everyday life. This study aimed to evaluate the effectiveness of three well-established transcutaneous PNS modalities in reducing physiological manifestations of stress compared to a sham: auricular and cervical Vagus Nerve Stimulation (taVNS and tcVNS), and Median Nerve Stimulation (tMNS). Using a single-blind sham-controlled crossover study with four visits, we compared the stress mitigation effectiveness of taVNS, tcVNS, and tMNS, quantified through physiological markers derived from five physiological signals peripherally measured on 19 young healthy volunteers. Participants underwent three acute mental and physiological stressors while receiving stimulation. Blinding effectiveness was assessed via subjective survey. taVNS and tMNS relative to sham resulted in significant changes that suggest a reduction in sympathetic outflow following the acute stressors: Left Ventricular Ejection Time Index (LVETI) shortening (tMNS: p = 0.007, taVNS: p = 0.015) and Pre-Ejection Period (PEP)-to-LVET ratio (PEP/LVET) increase (tMNS: p = 0.044, taVNS: p = 0.029). tMNS relative to sham also reduced Pulse Pressure (PP; p = 0.032) and tonic EDA activity (tonicMean; p = 0.025). The nonsignificant blinding survey results suggest these effects were not influenced by placebo. taVNS and tMNS effectively reduced stress-induced sympathetic arousal in wearable-compatible physiological signals, motivating their future use in novel personalized stress therapies to improve quality of life.

Hypovolemic shock is one of the leading causes of death in the military. The current methods of assessing hypovolemia in field settings rely on a clinician assessment of vital signs, which is an unreliable assessment of hypovolemia severity. These methods often detect hypovolemia when interventional methods are ineffective. Therefore, there is a need to develop real-time sensing methods for the early detection of hypovolemia. Previously, our group developed a random-forest model that successfully estimated absolute blood-volume status (ABVS) from noninvasive wearable sensor data for a porcine model (n = 6). However, this model required normalizing ABVS data using individual baseline data, which may not be present in crisis situations where a wearable sensor might be placed on a patient by the attending clinician. We address this barrier by examining seven individual baseline-free normalization techniques. Using a feature-specific global mean from the ABVS and an external dataset for normalization demonstrated similar performance metrics compared to no normalization (normalization: R2 = 0.82 ± 0.025|0.80 ± 0.032, AUC = 0.86 ± 5.5 × 10−3|0.86 ± 0.013, RMSE = 28.30 ± 0.63%|27.68 ± 0.80%; no normalization: R2 = 0.81 ± 0.045, AUC = 0.86 ± 8.9 × 10−3, RMSE = 28.89 ± 0.84%). This demonstrates that normalization may not be required and develops a foundation for individual baseline-free ABVS prediction.

This paper describes a signal quality classification method for arm ballistocardiogram (BCG), which has the potential for non-invasive and continuous blood pressure measurement. An advantage of the BCG signal for wearable devices is that it can easily be measured using accelerometers. However, the BCG signal is also susceptible to noise caused by motion artifacts. This distortion leads to errors in blood pressure estimation, thereby lowering the performance of blood pressure measurement based on BCG. In this study, to prevent such performance degradation, a binary classification model was created to distinguish between high-quality versus low-quality BCG signals. To estimate the most accurate model, four time-series imaging methods (recurrence plot, the Gramain angular summation field, the Gramain angular difference field, and the Markov transition field) were studied to convert the temporal BCG signal associated with each heartbeat into a 448 × 448 pixel image, and the image was classified using CNN models such as ResNet, SqueezeNet, DenseNet, and LeNet. A total of 9626 BCG beats were used for training, validation, and testing. The experimental results showed that the ResNet and SqueezeNet models with the Gramain angular difference field method achieved a binary classification accuracy of up to 87.5%.

OBJECTIVES/GOALS: Patients suffering from respiratory failure have few options to support oxygenation and carbon dioxide removal aside from mechanical ventilation. Our objective was to test a novel extrapulmonary mechanism of gas exchange via peritoneal oxygenated perfluorocarbon (PFC) in a large animal model. METHODS/STUDY POPULATION: Using two 50 kg swine, hypoxia was modeled with subatmospheric oxygen and hypercarbia induced with acute hypoventilation. Through a midline laparotomy, cannulas were placed into the peritoneal space to allow for PFC infusion and circulation. After abdominal closure, these cannulas were connected to a device capable of draining, oxygenating, and infusing PFC. One animal was subjected to acute hypoxia (12% FiO2) and another animal to acute hypoventilation (4 breaths per minute). Primary outcomes were times for SpO2 to reach 75 mmHg, respectively. Trials were performed without PFC and with PFC dwelling or circulating through the peritoneal space, during which abdominal and bladder pressures were monitored and maintained under 20 mmHg by regulation of the PFC volume contained in the animal. RESULTS/ANTICIPATED RESULTS: In the animal subjected to acute hypoxia (12% FiO2), survival time improved from 5:55 to 20:00 (min:sec) after 2.5 liters of oxygenated PFC was instilled in the peritoneal space. Oxygen percent saturation of PFC before and after dwelling in the peritoneal space was measured at 100% before and 70% after dwelling in the animal during this hypoxic period corresponding with a gas transfer of 300 mL of oxygen over the 20-minute trial (i.e., 15 mL/min). Continual PFC circulation did not further extend the survival time during hypoxic conditions over PFC dwelling in the abdomen. In the animal that was acutely hypoventilated, there were no detectable differences in the rate of CO2 accumulation as measured by EtCO2 or direct blood pCO2 measurements with PFC dwelling or circulating through the peritoneal space. DISCUSSION/SIGNIFICANCE: Oxygenated PFC dwelling in the peritoneal space increased the duration of systemic arterial blood saturation remaining greater than 50% during normobaric hypoxic (12% FiO2) conditions but did not appreciably clear blood carbon dioxide during hypoventilation. Future experiments will focus on maximizing the rate of systemic oxygen uptake.

This paper presents a novel deep learning-based arterial pulse wave analysis (PWA) approach to diagnosis of peripheral artery occlusive disease (PAD). Naïve application of deep learning to PAD diagnosis can be hampered by the fact that securing a large amount of longitudinal dataset encompassing diverse PAD severity as well as anatomical and physiological variability presents formidable challenge. Training of a deep neural network (DNN) to a small training dataset raises the risk of overfitting the PAD diagnosis algorithm only to the individuals in the training dataset while deteriorating its ability to generalize also to other individuals who may exhibit a large variability in anatomical and physiological characteristics beyond the training dataset. To overcome these obstacles, we propose a continuous property-adversarial regularization (CPAR) approach to robust generalization of a DNN against scarce datasets. Our approach fosters the exploitation of latent features that can facilitate the intended task independently of confounding property-induced disturbances. by regularizing the extraction of disturbance-dependent latent features in the network’s feature extraction layer. By training and testing a deep convolutional neural network (CNN) for PAD diagnosis using scarce virtual datasets, we illustrated that the CNN trained by our approach was superior to a conventionally trained CNN in detecting and assessing the severity of PAD against disturbances originating from diversity in the patients’ height and arterial stiffness: when trained with one-time pulse wave signal measurement at ankle and brachial arteries in a small number of patients, our approach achieved detection accuracy of >90% and severity assessment of 0.83 in r2 value, which were >15% and >40% improvement over conventional approach without CPAR. In addition, we ascertained the advantage of our approach in efficient training and robust generalization of DNN by contrasting it to multi-task learning which promotes the exploitation (as opposed to regularization in CPAR) of disturbance-dependent latent features in fulfilling the intended tasks.

The objective of this study was to investigate the efficacy of pulse transit time (PTT)-pulse wave analysis (PWA) fusion in cuff-less blood pressure (BP) trend tracking based on the wearable wrist ballistocardiogram (BCG). We constructed PTT and 36 candidate BCG PWA features based on the BCG and photoplethysmogram (PPG) signals acquired at the wrist. We performed a model-based analysis to select 6 candidate BCG PWA features most sensitive to BP. We aggregated the 6 BCG PWA features into novel predictors of diastolic, systolic, and pulse BP (DP, SP, and PP) orthogonal to PTT by covariance-maximizing dimensionality reduction. Then, we evaluated and compared the efficacy of BCG PTT and BCG PTT-PWA fusion in tracking the trend of DP, SP, and PP. Unique innovations of this study, generalizable to a range of physiological signals beyond the BCG, are (i) the systematic selection of PWA features based on model-based analysis and (ii) the development of PWA-based BP predictors orthogonal to PTT. Using the experimental wrist BCG and PPG signals collected from 23 human subjects, we demonstrated that (i) BCG PTT-PWA fusion may significantly outperform BCG PTT; (ii) PTT may play the primary role in tracking BP while BCG PWA features may still have an independent and complementary value (especially in tracking PP); and (iii) model-based selection of BCG PWA features can enhance the robustness of BP trend tracking based on BCG PTT-PWA fusion.

Subject-specific mathematical models for prediction of physiological parameters such as blood volume, cardiac output, and blood pressure in response to hemorrhage have been developed. In silico studies using these models may provide an effective tool to generate pre-clinical safety evidence for medical devices and help reduce the size and scope of animal studies that are performed prior to initiation of human trials. To achieve such a goal, the credibility of the mathematical model must be established for the purpose of pre-clinical in silico testing. In this work, the credibility of a subject-specific mathematical model of blood volume kinetics intended to predict blood volume response to hemorrhage and fluid resuscitation during fluid therapy was evaluated. A workflow was used in which: (i) the foundational properties of the mathematical model such as structural identifiability were evaluated; (ii) practical identifiability was evaluated both pre- and post-calibration, with the pre-calibration results used to determine an optimal splitting of experimental data into calibration and validation datasets; (iii) uncertainty in model parameters and the experimental uncertainty were quantified for each subject; and (iv) the uncertainty was propagated through the blood volume kinetics model and its predictive capability was evaluated via validation tests. The mathematical model was found to be structurally identifiable. Pre-calibration identifiability analysis led to splitting the 180 min of time series data per subject into 50 and 130 min calibration and validation windows, respectively. The average root mean squared error of the mathematical model was 12.6% using the calibration window of (0 min, 50 min). Practical identifiability was established post-calibration after fixing one of the parameters to a nominal value. In the validation tests, 82 and 75% of the subject-specific mathematical models were able to correctly predict blood volume response when predictive capability was evaluated at 180 min and at the time when amount of infused fluid equals fluid loss.

Hypercortisolism or Cushing's disease, which corresponds to the excessive levels of cortisol hormone, is associated with tiredness and fatigue during the day and disturbed sleep at night. Our goal is to employ a wearable brain machine interface architecture to regulate one's energy levels in hypercortisolism. In the present simulation study, we generate multi-day cortisol profile data for ten subjects both in healthy and disease conditions. To relate an internal hidden cognitive energy state to one's cortisol secretion patterns, we employ a state-space model. Particularly, we consider circadian upper and lower bound envelopes on cortisol levels, and timings of hypothalamic pulsatile activity underlying cortisol secretions as continuous and binary observations, respectively. To estimate the hidden cognitive energy-related state, we use Bayesian filtering. In our proposed architecture, we infer one's cognitive energy-related state using wearable devices rather than monitoring the brain activity directly and close the loop utilizing fuzzy control. To model actuation in the real-time closed-loop architecture, we simulate two types of medications that result in increasing and decreasing the energy levels in the body. Finally, we close the loop using a knowledge-based control approach. The results on ten simulated profiles verify how the proposed architecture is able to track the energy state and regulate it using hypothetical medications. In a simulation study based on experimental data, we illustrate the feasibility of designing a wearable brain machine interface architecture for energy regulation in hypercortisolism. This simulation study is a first step toward the ultimate goal of managing hypercortisolism in real-world situations.

Physiological closed-loop controlled (PCLC) medical devices are complex systems integrating one or more medical devices with a patient's physiology through closed-loop control algorithms; introducing many failure modes and parameters that impact performance. These control algorithms should be tested through safety and efficacy trials to compare their performance to the standard of care and determine whether there is sufficient evidence of safety for their use in real care setting. With this aim, credible mathematical models have been constructed and used throughout the development and evaluation phases of a PCLC medical device to support the engineering design and improve safety aspects. Uncertainties about the fidelity of these models and ambiguities about the choice of measures for modeling performance need to be addressed before a reliable PCLC evaluation can be achieved. This research develops tools for evaluating the accuracy of physiological models and establishes fundamental measures for predictive capability assessment across different physiological models. As a case study, we built a refined physiological model of blood volume (BV) response by expanding an original model we developed in our prior work. Using experimental data collected from 16 sheep undergoing hemorrhage and fluid resuscitation, first, we compared the calibration performance of the two candidate physiological models, i.e., original and refined, using root-mean-squared error (RMSE), Akiake information criterion (AIC), and a new multi-dimensional approach utilizing normalized features extracted from the fitting error. Compared to the original model, the refined model demonstrated a significant improvement in calibration performance in terms of RMSE (9%, P = 0.03) and multi-dimensional measure (48%, P = 0.02), while a comparable AIC between the two models verified that the enhanced calibration performance in the refined model is not due to data over-fitting. Second, we compared the physiological predictive capability of the two models under three different scenarios: prediction of subject-specific steady-state BV response, subject-specific transient BV response to hemorrhage perturbation, and leave-one-out inter-subject BV response. Results indicated enhanced accuracy and predictive capability for the refined physiological model with significantly larger proportion of measurements that were within the prediction envelope in the transient and leave-one-out prediction scenarios (P < 0.02). All together, this study helps to identify and merge new methods for credibility assessment and physiological model selection, leading to a more efficient process for PCLC medical device evaluation.

OBJECTIVES/GOALS: For patients suffering from respiratory failure there are limited options to support gas exchange aside from mechanical ventilation. Our goal is to design, investigate, and refine a novel device for extrapulmonary gas exchange via peritoneal perfusion with perfluorocarbons (PFC) in an animal model. METHODS/STUDY POPULATION: Hypoxic respiratory failure will be modeled using 50 kg swine mechanically ventilated with subatmospheric (10-12%) oxygen. Through a midline laparotomy, two cannulas, one for inflow and one for outflow, will be placed into the peritoneal space. After abdominal closure, the cannulas will be connected to a device capable of draining, oxygenating, regulating temperature, filtering, and pumping perfluorodecalin at a rate of 3-4 liters per minute. During induced hypoxia, the physiologic response to PFC circulation through the peritoneal space will be monitored with invasive (e.g. arterial and venous blood gases) and non-invasive measurements (e.g. pulse oximetry). RESULTS/ANTICIPATED RESULTS: We anticipate that the initiation of oxygenated perfluorocarbons perfusion through the peritoneal space during induced hypoxia will create an increase in hemoglobin oxygen saturation and partial pressure of oxygen in arterial blood. As we expect gas exchange to be occurring in the microvascular beds of the peritoneal membrane, we expect to observe an increase in the venous blood oxygen content sampled from the inferior vena cava. Using other invasive hemodynamic measures (e.g. cardiac output) and blood samples taken from multiple venous sites, a quantifiable rate of oxygen delivery will be calculable. DISCUSSION/SIGNIFICANCE: Peritoneal perfluorocarbon perfusion, if able to deliver significant amounts of oxygen, would provide a potentially lifesaving therapy for patients in respiratory failure who are unable to be supported with mechanical ventilation alone, and are not candidates for extracorporeal membrane oxygenation.

Toward the ultimate goal of affordable and non-invasive screening of peripheral occlusive artery disease (PAD), the objective of this work is to investigate the potential of deep learning-based arterial pulse waveform analysis in detecting and assessing the severity of PAD. Using an established transmission line model of arterial hemodynamics, a large number of virtual patients associated with PAD of a wide range of severity and the corresponding arterial pulse waveform data were created. A deep convolutional neural network capable of detecting and assessing the severity of PAD based on the analysis of brachial and ankle arterial pulse waveforms was constructed, evaluated for efficacy, and compared with the state-of-the-art ankle-brachial index (ABI) using the virtual patients. The results suggested that deep learning may diagnose PAD more accurately and robustly than ABI. In sum, this work demonstrates the initial proof-of-concept of deep learning-based arterial pulse waveform analysis for affordable and convenient PAD screening as well as presents challenges that must be addressed for real-world clinical applications.

Individualizing physiological models to a patient can enable patient-specific monitoring and treatment in critical care environments. However, this task often presents a unique “practical identifiability” challenge due to the conflict between model complexity and data scarcity. Regularization provides an established framework to cope with this conflict by compensating for data scarcity with prior knowledge. However, regularization has not been widely pursued in individualizing physiological models to facilitate patient-specific critical care. Thus, the goal of this work is to garner potentially generalizable insight into the practical use of regularization in individualizing a complex physiological model using scarce data by investigating its effect in a clinically significant critical care case study of blood volume kinetics and cardiovascular hemodynamics in hemorrhage and circulatory resuscitation. We construct a population-average model as prior knowledge and individualize the physiological model via regularization to illustrate that regularization can be effective in individualizing a physiological model to learn salient individual-specific characteristics (resulting in the goodness of fit to individual-specific data) while restricting unnecessary deviations from the population-average model (achieving practical identifiability). We also illustrate that regularization yields parsimonious individualization of only sensitive parameters as well as adequate physiological plausibility and relevance in predicting internal physiological states.

This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.

Abstract Vasopressor infusion (VPI) is used to treat hypotension in an ICU. We studied compliance with blood pressure (BP) goals during VPI and whether a statistical model might be efficacious for advance warning of impending hypotension, compared with a basic hypotension threshold alert. Retrospective data were obtained from a public database. Studying adult ICU patients receiving VPI at submaximal dosages, we analyzed characteristics of sustained hypotension episodes (>15 min) and then developed a logistic regression model to predict hypotension episodes using input features related to BP trends. The model was then validated with prospective data. In the retrospective dataset, 102-of-215 ICU stays experienced >1 hypotension episode (median of 2.5 episodes per day in this subgroup). When trained with 75% of retrospective dataset, testing with the remaining 25% of the dataset showed that the model and the threshold alert detected 99.6% and 100% of the episodes, respectively, with median advance forecast times (AFT) of 12 and 0 min. In a second, prospective dataset, the model detected 100% of 26 episodes with a median AFT of 22 min. In conclusion, episodes of hypotension were common during VPI in the ICU. A logistic regression model using BP temporal trend features predicted the episodes before their onset.

Oscillometric devices are widely used for automatic cuff blood pressure (BP) measurement. These devices estimate BP from the oscillometric cuff pressure waveform using population average methods. Hence, the devices may only be accurate over a limited BP range. The objective was to evaluate a new patient-specific method, which estimates BP by fitting a physiologic model to the same waveform. One-hundred and forty-five cardiac catheterization patients and normal adults were included for study. The oscillometric cuff pressure waveform was obtained with an office device, while reference BP was measured via brachial artery catheterization or auscultation, during baseline and/or nitroglycerin administration. Fifty-seven of the subject records were utilized for refining the patient-specific method, while the remaining 88 subject records were employed for evaluation. The precision errors for all BP levels of the patient-specific method ranged from 6.3 to 7.6 mmHg. These errors were significantly lower than those of the office device (by 29% on average) in subjects with high pulse pressure (>50 mmHg) while being comparable to those of the device in subjects with normal pulse pressure (

A correction has been published and is appended to both the HTML and PDF versions of this paper. The error has not been fixed in the paper.

Oscillometry is the blood pressure (BP) measurement principle of most automatic cuff devices. The oscillogram (which is approximately the blood volume oscillation amplitude-external pressure function) is measured, and BP is then estimated via an empirical algorithm. The objective was to establish formulas to explain three popular empirical algorithms in the literature—the maximum amplitude, derivative, and fixed ratio algorithms. A mathematical model of the oscillogram was developed and analyzed to derive parametric formulas for explaining each algorithm. Exemplary parameter values were obtained by fitting the model to measured oscillograms. The model and formulas were validated by showing that their predictions correspond to measurements. The formula for the maximum amplitude algorithm indicates that it yields a weighted average of systolic and diastolic BP (0.45 and 0.55 weighting) instead of commonly assumed mean BP. The formulas for the derivative algorithm indicate that it can accurately estimate systolic and diastolic BP (40). The established formulas allow for easy and complete interpretation of perhaps the three most popular oscillometric BP estimation algorithms in the literature while providing new insights. The model and formulas may also be of some value toward improving the accuracy of automatic cuff BP measurement devices.

In this paper, tapered vs. uniform tube-load models are comparatively investigated as mathematical representation for blood pressure (BP) wave propagation in human aorta. The relationship between the aortic inlet and outlet BP waves was formulated based on the exponentially tapered and uniform tube-load models. Then, the validity of the two tube-load models was comparatively investigated by fitting them to the experimental aortic and femoral BP waveform signals collected from 13 coronary artery bypass graft surgery patients. The two tube-load models showed comparable goodness of fit: (i) the root-mean-squared error (RMSE) was 3.3+/−1.1 mmHg in the tapered tube-load model and 3.4+/−1.1 mmHg in the uniform tube-load model; and (ii) the correlation was r = 0.98+/−0.02 in the tapered tube-load model and r = 0.98+/−0.01 mmHg in the uniform tube-load model. They also exhibited frequency responses comparable to the non-parametric frequency response derived from the aortic and femoral BP waveforms in most patients. Hence, the uniform tube-load model was superior to its tapered counterpart in terms of the Akaike Information Criterion (AIC). In general, the tapered tube-load model yielded the degree of tapering smaller than what is physiologically relevant: the aortic inlet-outlet radius ratio was estimated as 1.5 on the average, which was smaller than the anatomically plausible typical radius ratio of 3.5 between the ascending aorta and femoral artery. When the tapering ratio was restricted to the vicinity of the anatomically plausible typical value, the exponentially tapered tube-load model tended to underperform the uniform tube-load model (RMSE: 3.9+/−1.1 mmHg; r = 0.97+/−0.02). It was concluded that the uniform tube-load model may be more robust and thus preferred as the representation for BP wave propagation in human aorta; compared to the uniform tube-load model, the exponentially tapered tube-load model may not provide valid physiological insight on the aortic tapering, and its efficacy on the goodness of fit may be only marginal.

This study investigates the potential of the limb ballistocardiogram (BCG) for unobtrusive estimation of cardiovascular (CV) parameters. In conjunction with the reference CV parameters (including diastolic, pulse, and systolic pressures, stroke volume, cardiac output, and total peripheral resistance), an upper-limb BCG based on an accelerometer embedded in a wearable armband and a lower-limb BCG based on a strain gauge embedded in a weighing scale were instrumented simultaneously with a finger photoplethysmogram (PPG). To standardize the analysis, the more convenient yet unconventional armband BCG was transformed into the more conventional weighing scale BCG (called the synthetic weighing scale BCG) using a signal processing procedure. The characteristic features were extracted from these BCG and PPG waveforms in the form of wave-to-wave time intervals, wave amplitudes, and wave-to-wave amplitudes. Then, the relationship between the characteristic features associated with (i) the weighing scale BCG-PPG pair and (ii) the synthetic weighing scale BCG-PPG pair versus the CV parameters, was analyzed using the multivariate linear regression analysis. The results indicated that each of the CV parameters of interest may be accurately estimated by a combination of as few as two characteristic features in the upper-limb or lower-limb BCG, and also that the characteristic features recruited for the CV parameters were to a large extent relevant according to the physiological mechanism underlying the BCG.

This paper presents a lumped-parameter model that can reproduce blood volume response to fluid infusion. The model represents the fluid shift between the intravascular and interstitial compartments as the output of a hypothetical feedback controller that regulates the ratio between the volume changes in the intravascular and interstitial fluid at a target value (called target volume ratio). The model is characterized by only three parameters: the target volume ratio, feedback gain (specifying the speed of fluid shift), and initial blood volume. This model can obviate the need to incorporate complex mechanisms involved in the fluid shift in reproducing blood volume response to fluid infusion. The ability of the model to reproduce real-world blood volume response to fluid infusion was evaluated by fitting it to a series of data reported in the literature. The model reproduced the data accurately with average error and root-mean-squared error (RMSE) of 0.6 % and 9.5 % across crystalloid and colloid fluids when normalized by the underlying responses. Further, the parameters derived for the model showed physiologically plausible behaviors. It was concluded that this simple model may accurately reproduce a variety of blood volume responses to fluid infusion throughout different physiological states by fitting three parameters to a given dataset. This offers a tool that can quantify the fluid shift in a dataset given the measured fractional blood volumes.