Koninklijke Philips Corporation N.v.

Koninklljke Philips N.v.

Nicolas Wadih Chbat

Antonio Albanese

Francesco Vicario

Nikolaos Karamolegkos

Dong Wang

Adam Jacob Seiver

Caitlyn Marie Chiofolo

Balasundar Iyyavu Raju

Emil George Radulescu

Mark Simpson

Yasser Alsafadi

William Palmer Lord

Smita Garde

Nilanjana Banerjee

Fernando Jose Isaza

James David Schaffer

Roberto Buizza

Mahmoudreza Sharifi

Srinivasan Vairavan

Kees Van Zon

Limei Cheng

Syed Waseem Haider

Daniel Van Hise

A ventilation device includes a mechanical ventilator (), respiratory sensors () configured to acquire measurements of respiratory variables including at least measurements of airway pressure and airway flow, and an electronic processor () programmed to perform a ventilation method including: operating the mechanical ventilator to provide mechanical ventilation controlled using measurements acquired by the respiratory sensors; performing a pause maneuver comprising closing at least one of an inhalation valve () and an exhalation valve () for a pause interval and estimating a respiratory mechanics index from one or more respiratory system parameters estimated from measurements acquired by the respiratory sensors during or after the pause interval; and triggering a pause maneuver in response to detecting a change in the estimated respiratory mechanics index.

System and method for adaptive scheduling of pause maneuvers used for estimation of compliance and/or resistance during mechanical ventilation

A mechanical ventilation device () includes a mechanical ventilator. At least one airway sensor () is configured to measure at least one of airway pressure and airway air flow as a function of time for a patient on the mechanical ventilator. At least one microprocessor () is programmed to analyze at least one of airway pressure and airway air flow measured by the airway sensor to detect a spontaneous respiration anomaly in respiratory muscle pressure as a function of time generated by a patient on the mechanical ventilator. A display component () is configured to display an indication of a spontaneous respiration anomaly detected by the anomaly detection component.

Anomaly detection device and method for respiratory mechanics parameter estimation

A respiratory monitoring apparatus () includes a central venous pressure sensor () configured to measure a central venous pressure (CVP) signal of a patient. At least one processor () is programmed to process the CVP signal to generate respiratory information for the patient by operations including: segmenting the CVP signal based on detected breath intervals; calculating a surrogate muscle pressure signal from the segmented CVP signal; and filtering the surrogate muscle pressure signal to remove a cardiac activity component a cardiac activity component of the surrogate respiratory muscle pressure signal.

Enhancement of respiratory parameter estimation and asynchrony detection algorithms via the use of central venous pressure manometry

In respiratory monitoring, a breathing cycle detector () detects a breath interval in airway pressure and/or flow data. A respiratory parameters estimator and validator () asynchronously fits the airway pressure and airway flow data to an equation of motion of the lungs relating airway pressure and airway flow to generate asynchronously estimated respiratory parameters for the breath interval, using a sliding time window that is not synchronized with the breath interval. The asynchronously estimated respiratory parameters for the breath interval are validated using at least one physiological plausibility criterion defined with respect to the breath interval. Responsive to failure of the validation, the airway pressure and airway flow data are synchronously fitted to the equation of motion of the lungs to generate synchronously estimated respiratory parameters for the breath interval. The synchronous fitting is performed in a time window aligned with the breath interval.

Breath by breath reassessment of patient lung parameters to improve estimation performance

Respiratory variables are estimated on a per-breath basis from airway pressure and flow data acquired by airway pressure and flow sensors (). A breath detector () detects a breath interval. A per-breath respiratory variables estimator () fits the airway pressure and flow data over the detected breath interval to an equation of motion of the lungs relating airway pressure, airway flow, and a single-breath parameterized respiratory muscle pressure profile () to generate optimized parameter values for the single-breath parameterized respiratory muscle pressure profile. Respiratory muscle pressure is estimated as a function of time over the detected breath interval as the single-breath parameterized respiratory muscle pressure profile with the optimized parameter values, and may for example be displayed as a trend line on a display device () or integrated () to generate Work of Breathing (WoB) for use in adjusting settings of a ventilator ().

Simultaneous estimation of respiratory mechanics and patient effort via parametric optimization

A patient monitoring device includes at least one physiological sensor () configured to acquire at least one measured value for a patient of at least one monitored physiological variable. A cardiovascular (CV), pulmonary, or cardiopulmonary (CP) modeling component () includes a microprocessor pro-programmed to: receive the measured values of the at least one monitored physiological variable; receive a value for at least one patient-specific medical image parameter generated from at least one medical image of the patient; compute values for the patient of unmonitored physiological variables based on the measured values for the patient of the monitored physiological variables and the patient-specific medical image parameter; and at least one of (1) display the computed values and (2) control a therapy device delivering therapy to the patient based on the computed values.

Enhanced acute care management combining imaging and physiological monitoring

Disclosed herein are approaches for monitoring a patient in real-time for ARDS development and providing a biomarker-driven ventilation therapy recommendation tool based on the correlation of various therapy patterns and an ARDS biomarker score. When the ARDS biomarker indicates that a patient has a high ARDS risk, the recommendation tool suggests possible therapy routes based on clinical practice. In response to a high score output by the ARDS detection model, the tool outputs a recommendation to initiate a lung protective ventilation strategy (Low Tidal Volume, high Positive End-Expiratory Pressure (PEEP)). A high ARDS score is recognized to be predictive of the appropriateness of such therapy up to several hours before such intervention is typically initiated under current clinical practices.

Tool for recommendation of ventilation therapy guided by risk score for acute respirator distress syndrome (ARDS)

A mechanical ventilator () provides pressure support ventilation (PSV) to a patient (). A power of breathing (PoB) or work of breathing (WoB) estimator () generates a PoB or WoB signal () for the patient. An error calculator () computes an error signal as a difference between the PoB or WoB signal and a set point PoB or WoB value (). A controller () inputs a PSV control signal () equal to the product of the controller transfer function and the error signal to the mechanical ventilator. A patient adaptation component () fits parameters of a model of a controlled mechanical ventilation system comprising the mechanical ventilator and the patient to data comprising the PoB or WoB signal and the PSV control signal generated by the operating closed loop controller, and adjusts parameters of the controller transfer function to maintain stability of the operating closed loop controller.

Mechanical ventilation with automatic control of patient's work of breathing using classical feedback control

A method includes obtaining a first physiological parameter indicative of a non-invasively measured airway pressure of a subject, obtaining a second physiological parameter indicative of a non-invasively measured air flow into the lungs of the subject, and estimating a third physiological parameter indicative of an intra-pleural pressure of the subject based on the first and second physiological parameters and generating a signal indicative thereof. An other method includes obtaining a first physiological parameter indicative of a non-invasively estimated intra-pleural pressure of a subject, determining a second physiological parameter indicative of a lung volume of the subject that is based on a third physiological parameter indicative of a non-invasively measured air flow into the lungs of the subject, and determining a work of breathing based on the first and second physiological parameters and generating a signal indicative thereof.

Non-invasive estimation of intra-pleural pressure and/or computation of work of breathing based on a non-invasive estimation of intra-pleural pressure

A mechanical ventilator () is connected with a ventilated patient () to provide ventilation in accordance with ventilator settings of the mechanical ventilator. Physiological values (variables) are acquired for the ventilated patient using physiological sensors (). A ventilated patient cardiopulmonary (CP) model () is fitted to the acquired physiological variables values to generate a fitted ventilated patient CP model by fine-tuning its parameters (). Updated ventilator settings are determined by adjusting model ventilator settings of the fitted ventilated patient CP model to minimize a cost function (). The updated ventilator settings may be displayed on a display component () as recommended ventilator settings for the ventilated patient, or the ventilator settings of the mechanical ventilator may be automatically changed to the updated ventilator settings so as to automatically control the mechanical ventilator.

Systems and methods for model-based optimization of mechanical ventilation

A medical ventilator () performs a method including: receiving measurements of pressure of air inspired by or expired from a ventilated patient () operatively connected with the medical ventilator; receiving measurements of air flow into or out of the ventilated patient operatively connected with the medical ventilator; dividing a breath time interval into a plurality of fitting regions (); and simultaneously estimating respiratory system's resistance and compliance or elastance, and respiratory muscle pressure in each fitting region by fitting to a time series of pressure and air flow samples in that fitting region. In one approach, the fitting includes parameterizing the respiratory muscle pressure by a continuous differentiable function, such as a polynomial function, over the fitting region. In another approach, the fitting is to an equation of motion of the lungs in each fitting region, while monotonicity constraints and inequalities bounding at least the respiratory muscle pressure P(t) and respiratory system's resistence R and compliance C are applied to the respiratory muscle pressure in each region.

Simultaneous estimation of respiratory parameters by regional fitting of respiratory parameters

A Dynamic Bayesian Network provides models that provides emulation of patient data.

Method and apparatus for deriving probabilistic models from deterministic ones

When generating a model of physiological systems in a patient, differential equations representing parameters and variables in the systems are linked together to form one or more sub-models (e.g., one for each physiological system), which in turn are linked together to form the patient model. Simulations of hypothetical clinical situations are then run on the model to solve for the variables, and the solutions are output as decision support data for review by a clinician to facilitate a determination of a treatment of diagnosis for the patient. Additionally, model predictions can be compared to actual measurements, when available, and the model can be refined or optimized as a function of the comparison.

Integration of physiological models in medical decision support systems

A medical apparatus () assists clinicians, nurses or other users in choosing an intervention for the treatment of a patent suffering from an acute dynamic disease, e.g. sepsis. The medical apparatus is based on a method where a model of the disease is adapted or personalized to the patient. To ensure that the apparatus remains capable of predicting the health of the patient, the apparatus is continuously provided with new, more recent patient values and the model is continuously adapted to the new patient values. Since the medical apparatus is configured to be continuously adapted to current state of health, the apparatus is able to assist the user by generating disease management information, e.g. suggestions for medications, to an output device ().

Growing community of inventors

White Plains, NY, United States of America

Nicolas Wadih Chbat