Artificial Intelligence-Driven Prognosis of Respiratory Mechanics: Forecasting Tissue Hysteresivity Using Long Short-Term Memory and Continuous Sensor Data.

Tissue hysteresivity is an important marker for determining the onset and progression of respiratory diseases, calculated from forced oscillation lung function test data. This study aims to reduce the number and duration of required measurements by combining multivariate data from various sensing devices. We propose using the Forced Oscillation Technique (FOT) lung function test in both a low-frequency prototype and the commercial RESMON device, combined with continuous monitoring from the Equivital (EQV) LifeMonitor and processed by artificial intelligence (AI) algorithms. While AI and deep learning have been employed in various aspects of respiratory system analysis, such as predicting lung tissue displacement and respiratory failure, the prediction or forecasting of tissue hysteresivity remains largely unexplored in the literature. In this work, the Long Short-Term Memory (LSTM) model is used in two ways: (1) to estimate the hysteresivity coefficient η using heart rate (HR) data collected continuously by the EQV sensor, and (2) to forecast η values by first predicting the heart rate from electrocardiogram (ECG) data. Our methodology involves a rigorous two-hour measurement protocol, with synchronized data collection from the EQV, FOT, and RESMON devices. Our results demonstrate that LSTM networks can accurately estimate the tissue hysteresivity parameter η, achieving an R2 of 0.851 and a mean squared error (MSE) of 0.296 for estimation, and forecast η with an R2 of 0.883 and an MSE of 0.528, while significantly reducing the number of required measurements by a factor of three (i.e., from ten to three) for the patient. We conclude that our novel approach minimizes patient effort by reducing the measurement time and the overall ambulatory time and costs while highlighting the potential of artificial intelligence methods in respiratory monitoring.

Development, Validation, and Comparison of a Novel Nociception/Anti-Nociception Monitor against Two Commercial Monitors in General Anesthesia.

In this paper, we present the development and the validation of a novel index of nociception/anti-nociception (N/AN) based on skin impedance measurement in time and frequency domain with our prototype AnspecPro device. The primary objective of the study was to compare the Anspec-PRO device with two other commercial devices (Medasense, Medstorm). This comparison was designed to be conducted under the same conditions for the three devices. This was carried out during total intravenous anesthesia (TIVA) by investigating its outcomes related to noxious stimulus. In a carefully designed clinical protocol during general anesthesia from induction until emergence, we extract data for estimating individualized causal dynamic models between drug infusion and their monitored effect variables. Specifically, these are Propofol hypnotic drug to Bispectral index of hypnosis level and Remifentanil opioid drug to each of the three aforementioned devices. When compared, statistical analysis of the regions before and during the standardized stimulus shows consistent difference between regions for all devices and for all indices. These results suggest that the proposed methodology for data extraction and processing for AnspecPro delivers the same information as the two commercial devices.

Parametric Modeling and Deep Learning for Enhancing Pain Assessment in Postanesthesia.

OBJECTIVE: The problem of reliable and widely accepted measures of pain is still open. It follows the objective of this work as pain estimation through post-surgical trauma modeling and classification, to increase the needed reliability compared to measurements only. METHODS: This article proposes (i) a recursive identification method to obtain the frequency response and parameterization using fractional-order impedance models (FOIM), and (ii) deep learning with convolutional neural networks (CNN) classification algorithms using time-frequency data and spectrograms. The skin impedance measurements were conducted on 12 patients throughout the postanesthesia care in a proof-of-concept clinical trial. Recursive least-squares system identification was performed using a genetic algorithm for initializing the parametric model. The online parameter estimates were compared to the self-reported level by the Numeric Rating Scale (NRS) for analysis and validation of the results. Alternatively, the inputs to CNNs were the spectrograms extracted from the time-frequency dataset, being pre-labeled in four intensities classes of pain during offline and online training with the NRS. RESULTS: The tendency of nociception could be predicted by monitoring the changes in the FOIM parameters' values or by retraining online the network. Moreover, the tissue heterogeneity, assumed during nociception, could follow the NRS trends. The online predictions of retrained CNN have more specific trends to NRS than pain predicted by the offline population-trained CNN. CONCLUSION: We propose tailored online identification and deep learning for artefact corrupted environment. The results indicate estimations with the potential to avoid over-dosing due to the objectivity of the information. SIGNIFICANCE: Models and artificial intelligence (AI) allow objective and personalized nociception-antinociception prediction in the patient safety era for the design and evaluation of closed-loop analgesia controllers.

Parameterisation of Respiratory Impedance in Lung Cancer Patients From Forced Oscillation Lung Function Test.

OBJECTIVE: This study aims to analyze the contribution and application of forced oscillation technique (FOT) devices in lung cancer assessment. Two devices and corresponding methods can be feasible to distinguish among various degrees of lung tissue heterogeneity. METHODS: The outcome respiratory impedance Zrs (in terms of resistance Rrs and reactance Xrs) is calculated for FOT and is interpreted in physiological terms by being fitted with a fractional-order impedance mathematical model (FOIM). The non-parametric data obtained from the measured signals of pressure and flow is correlated with an analogous electrical model to the respiratory system resistance, compliance, and elastance. The mechanical properties of the lung can be captured through Gr to define the damping properties and Hr to describe the elastance of the lung tissue, their ratio representing tissue heterogeneity ηr. RESULTS: We validated our hypotheses and methods in 17 lung cancer patients where we showed that FOT is suitable for non-invasively measuring their respiratory impedance. FOIM models are efficient in capturing frequency-dependent impedance value variations. Increased heterogeneity and structural changes in the lungs have been observed. The results present inter- and intra-patient variability for the performed measurements. CONCLUSION: The proposed methods and assessment of the respiratory impedance with FOT have been demonstrated useful for characterizing mechanical properties in lung cancer patients. SIGNIFICANCE: This correlation analysis between the measured clinical data motivates the use of the FOT devices in lung cancer patients for diagnosis of lung properties and follow-up of the respiratory function modified due to the applied radiotherapy treatment.

Lumped Parametric Model for Skin Impedance Data in Patients with Postoperative Pain.

The societal and economic burden of unassessed and unmodeled postoperative pain is high and predicted to rise over the next decade, leading to over-dosing as a result of subjective (NRS-based) over-estimation by the patient. This study identifies how post-surgical trauma alters the parameters of impedance models, to detect and examine acute pain variability. Model identification is performed on clinical data captured from post-anesthetized patients, using Anspec-PRO prototype apriori validated for clinical pain assessment. The multisine excitation of this in-house developed device enables utilizing the complex skin impedance frequency response in data-driven electrical models. The single-dispersion Cole model is proposed to fit the clinical curve in the given frequency range. Changes in identified parameters are analyzed for correlation with the patient's reported pain for the same time moment. The results suggest a significant correlation for the capacitor component. Clinical Relevance- Individual model parameters validated on patients in the post-anesthesia care unit extend the knowledge for objective pain detection to positively influence the outcome of clinical analgesia management.

Lung cancer dynamics using fractional order impedance modeling on a mimicked lung tumor setup.

Introduction: As pulmonary dysfunctions are prospective factors for developing cancer, efforts are needed to solve the limitations regarding applications in lung cancer. Fractional order respiratory impedance models can be indicative of lung cancer dynamics and tissue heterogeneity. Objective: The purpose of this study is to investigate how the existence of a tumorous tissue in the lung modifies the parameters of the proposed models. The first use of a prototype forced oscillations technique (FOT) device in a mimicked lung tumor setup is investigated by comparing and interpreting the experimental findings. Methods: The fractional order model parameters are determined for the mechanical properties of the healthy and tumorous lung. Two protocols have been performed for a mimicked lung tumor setup in a laboratory environment. A low frequency evaluation of respiratory impedance model and nonlinearity index were assessed using the forced oscillations technique. Results: The viscoelastic properties of the lung tissue change, results being mirrored in the respiratory impedance assessment via FOT. The results demonstrate significant differences among the mimicked healthy and tumor measurements, (p-values <0.05) for impedance values and also for heterogeneity index. However, there was no significant difference in lung function before and after immersing the mimicked lung in water or saline solution, denoting no structural changes. Conclusion: Simulation tests comparing the changes in impedance support the research hypothesis. The impedance frequency response is effective in non-invasive identification of respiratory tissue abnormalities in tumorous lung, analyzed with appropriate fractional models.

Bioimpedance Sensor and Methodology for Acute Pain Monitoring.

The paper aims to revive the interest in bioimpedance analysis for pain studies in communicating and non-communicating (anesthetized) individuals for monitoring purpose. The plea for exploitation of full potential offered by the complex (bio)impedance measurement is emphasized through theoretical and experimental analysis. A non-invasive, low-cost reliable sensor to measure skin impedance is designed with off-the-shelf components. This is a second generation prototype for pain detection, quantification, and modeling, with the objective to be used in fully anesthetized patients undergoing surgery. The 2D and 3D time-frequency, multi-frequency evaluation of impedance data is based on broadly available signal processing tools. Furthermore, fractional-order impedance models are implied to provide an indication of change in tissue dynamics correlated with absence/presence of nociceptor stimulation. The unique features of the proposed sensor enhancements are described and illustrated here based on mechanical and thermal tests and further reinforced with previous studies from our first generation prototype.

Pain Detection with Bioimpedance Methodology from 3-Dimensional Exploration of Nociception in a Postoperative Observational Trial.

Although the measurement of dielectric properties of the skin is a long-known tool for assessing the changes caused by nociception, the frequency modulated response has not been considered yet. However, for a rigorous characterization of the biological tissue during noxious stimulation, the bioimpedance needs to be analyzed over time as well as over frequency. The 3-dimensional analysis of nociception, including bioimpedance, time, and frequency changes, is provided by ANSPEC-PRO device. The objective of this observational trial is the validation of the new pain monitor, named as ANSPEC-PRO. After ethics committee approval and informed consent, 26 patients were monitored during the postoperative recovery period: 13 patients with the in-house developed prototype ANSPEC-PRO and 13 with the commercial device MEDSTORM. At every 7 min, the pain intensity was measured using the index of Anspec-pro or Medstorm and the 0-10 numeric rating scale (NRS), pre-surgery for 14 min and post-anesthesia for 140 min. Non-significant differences were reported for specificity-sensitivity analysis between ANSPEC-PRO (AUC = 0.49) and MEDSTORM (AUC = 0.52) measured indexes. A statistically significant positive linear relationship was observed between Anspec-pro index and NRS (r2 = 0.15, p < 0.01). Hence, we have obtained a validation of the prototype Anspec-pro which performs equally well as the commercial device under similar conditions.

Fractional-order PID design: Towards transition from state-of-art to state-of-use.

This paper presents a new tuning method for fractional-order (FO)PID controllers to simplify current tuning and make FOPID controllers more convenient for industry, i.e. facilitate transition from state-of-art to state-of-use. The number of tuning parameters is reduced from five to three based on popular specification settings for PID controllers without the need for reduced process models which introduce modeling errors. A test batch of 133 simulated processes and two real-life processes are used to test the presented method. A comparative study between the new method and the established CRONE controller, quantifies the performance. The conclusion states that the new method gives fractional controllers with similar performances as the current methods but with a significantly decreased tuning complexity making FOPID controllers more acceptable to industry.

An efficient algorithm for low-order direct discrete-time implementation of fractional order transfer functions.

Fractional order systems become increasingly popular due to their versatility in modelling and control applications across various disciplines. However, the bottleneck in deploying these tools in practice is related to their implementation on real-life systems. Numerical approximations are employed but their complexity no longer match the attractive simplicity of the original fractional order systems. This paper proposes a low-order, computationally stable and efficient method for direct approximation of general order (fractional order) systems in the form of discrete-time rational transfer functions, e.g. processes, controllers. A fair comparison to other direct discretization methods is presented, demonstrating its added value with respect to the state of art.

A novel auto-tuning method for fractional order PI/PD controllers.

Fractional order PID controllers benefit from an increasing amount of interest from the research community due to their proven advantages. The classical tuning approach for these controllers is based on specifying a certain gain crossover frequency, a phase margin and a robustness to gain variations. To tune the fractional order controllers, the modulus, phase and phase slope of the process at the imposed gain crossover frequency are required. Usually these values are obtained from a mathematical model of the process, e.g. a transfer function. In the absence of such model, an auto-tuning method that is able to estimate these values is a valuable alternative. Auto-tuning methods are among the least discussed design methods for fractional order PID controllers. This paper proposes a novel approach for the auto-tuning of fractional order controllers. The method is based on a simple experiment that is able to determine the modulus, phase and phase slope of the process required in the computation of the controller parameters. The proposed design technique is simple and efficient in ensuring the robustness of the closed loop system. Several simulation examples are presented, including the control of processes exhibiting integer and fractional order dynamics.

Lessons learned from closed loops in engineering: towards a multivariable approach regulating depth of anaesthesia.

In this paper is presented a brief state of art regarding the multivariable formulation for controlling the depth of anaesthesia by means of two intravenously administrated drugs, i.e. propofol and remifentanil. In a feasibility study of determining a suitable variable to quantify analgesia levels in patients undergoing cardiac surgery, the bispectral index and an electromyogram-based surrogate variable are proposed as the controlled variables. The study is carried on in the context of implementing a multivariable predictive control algorithm. The simulation results show that such a paradigm is feasible, although it does not guarantee perfect knowledge of the analgesia level-in other words, the variable is not validated against typical evaluations of the pain levels (e.g. clinical scores).

A recurrent parameter model to characterize the high-frequency range of respiratory impedance in healthy subjects.

In this work, a re-visited model of the respiratory system is proposed. Identification of a recurrent electrical ladder network model of the lungs, which incorporates their specific morphology and anatomical structure, is performed on 31 healthy subjects. The data for identification has been gathered using the forced oscillation lung function test, which delivers a non-parametric model of the impedance. On the measured frequency response, the ladder network parameters have been identified and a fractional order has been calculated from the recurrent ratios of the respiratory mechanics (resistance and compliance). The paper includes also a comparison of our recurrent parameter model with another parametric model for high frequency range. The results suggest that the two models can equally well characterize the respiratory impedance over a long range of frequencies. Additionally, we have shown that the fractional order resulting from the recurrent properties of resistance and compliance in the ladder network model is independent of frequency and is not biased by the nose clip wore by the patients during measurements. An illustrative example shows that our re-visited model is sensitive to changes in respiratory mechanics and the fractional order value is a reliable parameter to capture these changes.

Is multidimensional scaling suitable for mapping the input respiratory impedance in subjects and patients?

This paper presents the application of multidimensional scaling (MDS) analysis to data emerging from noninvasive lung function tests, namely the input respiratory impedance. The aim is to obtain a geometrical mapping of the diseases in a 3D space representation, allowing analysis of (dis)similarities between subjects within the same pathology groups, as well as between the various groups. The adult patient groups investigated were healthy, diagnosed chronic obstructive pulmonary disease (COPD) and diagnosed kyphoscoliosis, respectively. The children patient groups were healthy, asthma and cystic fibrosis. The results suggest that MDS can be successfully employed for mapping purposes of restrictive (kyphoscoliosis) and obstructive (COPD) pathologies. Hence, MDS tools can be further examined to define clear limits between pools of patients for clinical classification, and used as a training aid for medical traineeship.

Variable time-delay estimation for anesthesia control during intensive care.

The presence of artifacts plays a crucial role in automatic sedation systems and may introduce variable time delays (TDs) in the closed-loop-control structures. This paper presents a successful procedure to estimate the varying TD of the bispectral index (BIS) monitor used in closed-loop control during intensive care. The TD estimation (TDE) is based on the cross-correlation analysis technique and the method is validated with real measured signals of propofol and BIS. Extended prediction self-adaptive control is used in combination with a Smith predictor to reduce the computational burden imposed by the variable TD. The conclusion is that an online TDE of the BIS monitor improves the performance of the closed-loop system for reference tracking, disturbance rejection, and overall stability.

Mechanical properties of the respiratory system derived from morphologic insight.

This paper aims to provide the mechanical parameters of the respiratory airways (resistance, inertance, and compliance) from morphological insight, in order to facilitate the correlations of fractional-order models with pathologic changes. The approach consists of taking into account wall thickness, inner radius, tube length, and tissue structure for each airway level to combine them into a set of equations for modeling the pressure drop, flow, wall elasticity, and air velocity (axial and radial). Effects of pulmonary disease affecting the inner radius and elastic modulus of bronchial tree are discussed. A brief comparison with the circulatory system, which poses similarities with the respiratory system, is also given. The derived mechanical parameters can serve as elements in a transmission line equivalent, whose structure preserves the geometry of the human respiratory tree. The mechanical parameters derived in this paper offer the possibility to evaluate input impedance by altering the morphological parameters in relation to the pulmonary disease. In this way, we obtain a simple, yet accurate, model to simulate and understand specific effects in respiratory diseases; e.g., airway remodeling. The final scope of the research is to relate the variations in airway structure with disease to the values of fractional-order model parameters.

Relations between fractional-order model parameters and lung pathology in chronic obstructive pulmonary disease.

In this study, changes in respiratory mechanics from healthy and chronic obstructive pulmonary disease (COPD) diagnosed patients are observed from identified fractional-order (FO) model parameters. The noninvasive forced oscillation technique is employed for lung function testing. Parameters on tissue damping and elastance are analyzed with respect to lung pathology and additional indexes developed from the identified model. The observations show that the proposed model may be used to detect changes in respiratory mechanics and offers a clear-cut separation between the healthy and COPD subject groups. Our conclusion is that an FO model is able to capture changes in viscoelasticity of the soft tissue in lungs with disease. Apart from this, nonlinear effects present in the measured signals were observed and analyzed via signal processing techniques and led to supporting evidence in relation to the expected phenomena from lung pathology in healthy and COPD patients.

Robust predictive control strategy applied for propofol dosing using BIS as a controlled variable during anesthesia.

This paper presents the application of predictive control to drug dosing during anesthesia in patients undergoing surgery. The performance of a generic predictive control strategy in drug dosing control, with a previously reported anesthesia-specific control algorithm, has been evaluated. The robustness properties of the predictive controller are evaluated with respect to inter- and intrapatient variability. A single-input (propofol) single-output (bispectral index, BIS) model of the patient has been assumed for prediction as well as for simulation. A set of 12 patient models were studied and interpatient variability and disturbances are used to assess robustness of the controller. Furthermore, the controller guarantees the stability in a desired range. The applicability of the predictive controller in a real-life environment via simulation studies has been assessed.