A Population-Informed Particle Filter for Robust Physiological Monitoring Using Low-Information Time-Series Measurements.

OBJECTIVE: To present the population-informed particle filter (PIPF), a novel filtering approach that incorporates past experiences with patients into the filtering process to provide reliable beliefs about a new patient's physiological state. METHODS: To derive the PIPF, we formulate the filtering problem as recursive inference on a probabilistic graphical model, which includes representations for the pertinent physiological dynamics and the hierarchical relationship between past and present patient characteristics. Then, we provide an algorithmic solution to the filtering problem using Sequential Monte-Carlo techniques. To demonstrate the merits of the PIPF approach, we apply it to a case study of physiological monitoring for hemodynamic management. RESULTS: The PIPF approach could provide reliable beliefs about the likely values and uncertainties associated with a patient's unmeasured physiological variables (e.g., hematocrit and cardiac output), characteristics (e.g., tendency for atypical behavior), and events (e.g., hemorrhage) given low-information measurements. CONCLUSION: The PIPF shows promise in the presented case study, and may have applications to a wider range of real-time monitoring problems with limited measurements. SIGNIFICANCE: Forming reliable beliefs about a patient's physiological state is an essential aspect of algorithmic decision-making in medical care settings. Hence, the PIPF may serve as a solid basis for designing interpretable and context-aware physiological monitoring, medical decision-support, and closed-loop control algorithms.

A Mathematical Model for Simulation of Vasoplegic Shock and Vasopressor Therapy.

OBJECTIVE: To develop a high-fidelity mathematical model intended to replicate the cardiovascular (CV) responses of a critically ill patient to vasoplegic shock-induced hypotension and vasopressor therapy. METHODS: The mathematical model consists of a lumped-parameter CV physiology model with baroreflex modulation feedback and a phenomenological dynamic dose-response model of a vasopressor. The adequacy of the proposed mathematical model was investigated using an experimental dataset acquired from 10 pigs receiving phenylephrine (PHP) therapy after vasoplegic shock induced via sodium nitroprusside (SNP). RESULTS: Upon calibration, the mathematical model could (i) faithfully replicate the effects of PHP on dynamic changes in blood pressure (BP), cardiac output (CO), and systemic vascular resistance (SVR) (root-mean-squared errors between measured and calibrated mathematical responses: mean arterial BP 2.5+/-1.0 mmHg, CO 0.2+/-0.1 lpm, SVR 2.4+/-1.5 mmHg/lpm; r value: mean arterial BP 0.96+/-0.01, CO 0.65+/-0.45, TPR 0.92+/-0.10) and (ii) predict physiologically plausible behaviors of unmeasured internal CV variables as well as secondary baroreflex modulation effects. CONCLUSION: This mathematical model is perhaps the first of its kind that can comprehensively replicate both primary (i.e., direct) and secondary (i.e., baroreflex modulation) effects of a vasopressor drug on an array of CV variables, rendering it ideally suited to pre-clinical virtual evaluation of the safety and efficacy of closed-loop control algorithms for autonomous vasopressor administration once it is extensively validated. SIGNIFICANCE: This mathematical model architecture incorporating both direct and baroreflex modulation effects may generalize to serve as part of an effective platform for high-fidelity in silico simulation of CV responses to vasopressors during vasoplegic shock.

Collective Variational Inference for Personalized and Generative Physiological Modeling: A Case Study on Hemorrhage Resuscitation.

OBJECTIVE: Individual physiological experiments typically provide useful but incomplete information about a studied physiological process. As a result, inferring the unknown parameters of a physiological model from experimental data is often challenging. The objective of this paper is to propose and illustrate the efficacy of a collective variational inference (C-VI) method, intended to reconcile low-information and heterogeneous data from a collection of experiments to produce robust personalized and generative physiological models. METHODS: To derive the C-VI method, we utilize a probabilistic graphical model to impose structure on the available physiological data, and algorithmically characterize the graphical model using variational Bayesian inference techniques. To illustrate the efficacy of the C-VI method, we apply it to a case study on the mathematical modeling of hemorrhage resuscitation. RESULTS: In the context of hemorrhage resuscitation modeling, the C-VI method could reconcile heterogeneous combinations of hematocrit, cardiac output, and blood pressure data across multiple experiments to obtain (i) robust personalized models along with associated measures of uncertainty and signal quality, and (ii) a generative model capable of reproducing the physiological behavior of the population. CONCLUSION: The C-VI method facilitates the personalized and generative modeling of physiological processes in the presence of low-information and heterogeneous data. SIGNIFICANCE: The resulting models provide a solid basis for the development and testing of interpretable physiological monitoring, decision-support, and closed-loop control algorithms.

Mathematical Modeling, In-Human Evaluation and Analysis of Volume Kinetics and Kidney Function After Burn Injury and Resuscitation.

OBJECTIVE: Existing burn resuscitation protocols exhibit a large variability in treatment efficacy. Hence, they must be further optimized based on comprehensive knowledge of burn pathophysiology. A physics-based mathematical model that can replicate physiological responses in diverse burn patients can serve as an attractive basis to perform non-clinical testing of burn resuscitation protocols and to expand knowledge on burn pathophysiology. We intend to develop, optimize, validate, and analyze a mathematical model to replicate physiological responses in burn patients. METHODS: Using clinical datasets collected from 233 burn patients receiving burn resuscitation, we developed and validated a mathematical model applicable to computer-aided in-human burn resuscitation trial and knowledge expansion. Using the validated mathematical model, we examined possible physiological mechanisms responsible for the cohort-dependent differences in burn pathophysiology between younger versus older patients, female versus male patients, and patients with versus without inhalational injury. RESULTS: We demonstrated that the mathematical model can replicate physiological responses in burn patients associated with wide demographic characteristics and injury severity, and that an increased inflammatory response to injury may be a key contributing factor in increasing the mortality risk of older patients and patients with inhalation injury via an increase in the fluid retention. CONCLUSION: We developed and validated a physiologically plausible mathematical model of volume kinetic and kidney function after burn injury and resuscitation suited to in-human application. SIGNIFICANCE: The mathematical model may provide an attractive platform to conduct non-clinical testing of burn resuscitation protocols and test new hypotheses on burn pathophysiology.

Mathematical model of volume kinetics and renal function after burn injury and resuscitation.

This paper presents a mathematical model of blood volume kinetics and renal function in response to burn injury and resuscitation, which is applicable to the development and non-clinical testing of burn resuscitation protocols and algorithms. Prior mathematical models of burn injury and resuscitation are not ideally suited to such applications due to their limited credibility in predicting blood volume and urinary output observed in wide-ranging burn patients as well as in incorporating contemporary knowledge of burn pathophysiology. Our mathematical model consists of an established multi-compartmental model of blood volume kinetics, a hybrid mechanistic-phenomenological model of renal function, and novel lumped-parameter models of burn-induced perturbations in volume kinetics and renal function equipped with contemporary knowledge on burn-related physiology and pathophysiology. Using the dataset collected from 16 sheep, we showed that our mathematical model can be characterized with physiologically plausible parameter values to accurately predict blood volume kinetic and renal function responses to burn injury and resuscitation on an individual basis against a wide range of pathophysiological variability. Pending validation in humans, our mathematical model may serve as an effective basis for in-depth understanding of complex burn-induced volume kinetic and renal function responses as well as development and non-clinical testing of burn resuscitation protocols and algorithms.

The First Inherited Retinal Disease Registry in Iran: Research Protocol and Results of a Pilot Study.

BACKGROUND: To describe the protocol for developing a national inherited retinal disease (IRD) registry in Iran and present its initial report. METHODS: This community-based participatory research was approved by the Ministry of Health and Medical Education of Iran in 2016. To provide the minimum data set (MDS), several focus group meetings were held. The final MDS was handed over to an engineering team to develop a web-based software. In the pilot phase, the software was set up in two referral centers in Iran. Final IRD diagnosis was made based on clinical manifestations and genetic findings. Ultimately, patient registration was done based on all clinical and non-clinical manifestations. RESULTS: Initially, a total of 151 data elements were approved with Delphi technique. The registry software went live at www. IRDReg.org based on DHIS2 open source license agreement since February 2016. So far, a total of 1001 patients have been registered with a mean age of 32.41±15.60 years (range, 3 months to 74 years). The majority of the registered patients had retinitis pigmentosa (42%, 95% CI: 38.9% to 45%). Genetic testing was done for approximately 20% of the registered individuals. CONCLUSION: Our study shows successful web-based software design and data collection as a proof of concept for the first IRD registry in Iran. Multicenter integration of the IRD registry in medical centers throughout the country is well underway as planned. These data will assist researchers to rapidly access information about the distribution and genetic patterns of this disease.

Practical Use of Regularization in Individualizing a Mathematical Model of Cardiovascular Hemodynamics Using Scarce Data.

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.

Tapered vs. Uniform Tube-Load Modeling of Blood Pressure Wave Propagation in Human Aorta.

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.

Modeling a Telemedicine Screening Program for Diabetic Retinopathy in Iran and Implementing a Pilot Project in Tehran Suburb.

PURPOSE: To model a community-based telescreening program for diabetic retinopathy (DR) in Iran and to implement a pilot project at the Iranian Diabetes Society (IDS) branch in a Tehran suburb. METHODS: In this mixed model study, a web application called the "Iranian Retinopathy Teleophthalmology Screening (IRTOS)" was launched. The educational course for DR screening was established for general practitioners (GPs). Registered patients in IDS branch were recalled for fundus photography; images were transferred to the reading center via IRTOS to be graded by GPs, and patients were informed about the results via mobile messaging. All images were independently reviewed by a retina specialist as the gold standard. Patients who required further assessment were referred to an eye hospital. RESULTS: Overall, 604 subjects with diabetes were screened; of these, 50% required referral. The sensitivity and specificity for diagnosis of any stage of DR by trained GPs were 82.8% and 86.2%, respectively, in comparison to the gold standard. The corresponding values for detecting any stage of diabetic macular edema (DME) were 63.5% and 96.6%, respectively. CONCLUSIONS: Telescreening was an effective method for detecting DR in a Tehran suburb. This screening model demonstrated its capacity for promoting diabetic eye care services at the national level. However, the sensitivity for detecting DME needs to be improved by modifying the referral pathway and promoting the skill of GPs.

Leakage fault detection in Electro-Hydraulic Servo Systems using a nonlinear representation learning approach.

Electro-Hydraulic Servo Systems (EHSS) are employed as actuators to track the desired trajectory and exert force in heavy-duty industrial applications. The EHSS is often prone to problems such as leakage and actuator seal damage during the course of its utilization. These faults which cannot be directly detected from current sensor values, can eventually result in complications and degrade control performance. The goal of this research is to use representation learning concepts to detect these faults with decreased complexity. The objective is to find a nonlinear mapping to transform raw data into another space in which classification becomes easier. The data are driven from the hydraulic supply pressure signal. To find the mapping, a custom-built optimization algorithm is proposed along with a suitable cost function to carry out the search for the new representation. The performance of the resulting transformation is tested in an experimental setting to show the merits of the proposed method.

A switched energy saving position controller for variable-pressure electro-hydraulic servo systems.

The electro-hydraulic servo system (EHSS) demonstrates a relatively low level of efficiency compared to other available actuation methods. The objective of this paper is to increase this efficiency by introducing a variable supply pressure into the system and controlling this pressure during the task of position tracking. For this purpose, an EHSS structure with controllable supply pressure is proposed and its dynamic model is derived from the basic laws of physics. A switching control structure is then proposed to control both the supply pressure and the cylinder position at the same time, in a way that reduces the overall energy consumption of the system. The stability of the proposed switching control system is guaranteed by proof, and its performance is verified by experimental testing.