Hierarchical adaptive closed-loop fluid resuscitation and cardiovascular drug administration system

Inventors

Gholami, Behnood

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Assignees

Autonomous Healthcare Inc

Member
Autonomous Healthcare
Autonomous Healthcare

Autonomous Healthcare develops autonomous systems for critical care, applying advanced algorithms and modeling to automate and support processes such as mechanical ventilation and hemodynamic management in intensive care units. The company leverages expertise from aerospace engineering and artificial intelligence to provide continuous clinical vigilance, validated through rigorous research and regulatory milestones.

Publication Number

US-11338087-B2

Patent

Publication Date

2022-05-24

Expiration Date


Abstract

The present disclosure describes a closed-loop fluid resuscitation and/or cardiovascular drug administration system that uses continuous measurements and adaptive control architecture. The adaptive control architecture uses a function approximator to identify unknown dynamics and physiological parameters of a patient to compute appropriate infusion rates and to regulate the endpoint of resuscitation.

Core Innovation

The invention provides a closed loop system for fluid resuscitation or drug administration that uses sensor-obtained hemodynamic measurements of a subject from a hemodynamic monitoring device. The system includes a processing module with computer-executable instructions that receive the hemodynamic measurements and coordinate control actions to compute infusion rates.

A lower-level controller computes infusion rates based on the sensor-obtained hemodynamic measurements and a set of adaptive parameters. The lower-level controller includes a dynamic observer with dynamic observer states to estimate a current value of one or more physiological parameters, and a dynamical system that uses a function approximator with basis functions and weights to approximate an unknown function describing distribution of a fluid and/or drug in the body of the subject.

A higher-level logic-based controller is communicatively coupled to the lower-level controller and governs operation using verification and timing logic. The higher-level controller verifies whether infusion rates meet infusion rate requirements, determines timing for engaging the lower-level controller, and determines timing for disengaging the lower-level controller based on violation of a performance criterion, while a user interface displays computed infusion rates, receives an initial infusion rate from an end-user, and notifies the end-user if the performance criterion is violated.

Claims Coverage

The independent claim covers a hierarchical adaptive closed-loop architecture with sensor-based processing, a lower-level dynamic observer and function approximator that compute infusion rates, and a higher-level logic-based controller that verifies infusion-rate requirements and manages engagement and disengagement based on performance-criterion violation. It includes a user interface for end-user interaction and notifications.

Dynamic observer and physiological parameter estimation

A lower-level controller comprises a dynamic observer comprising a set of dynamic observer states for estimating a current value of one or more physiological parameters of the subject.

Function approximator for unknown fluid/drug distribution

A lower-level controller comprises a dynamical system using a function approximator comprising a set of basis functions and a set of weights to approximate at least one unknown function describing distribution of a fluid and/or drug in the body of the subject.

Infusion rate computation from hemodynamic measurements and weights

The at least one lower-level controller is configured to compute infusion rates based at least upon the sensor-obtained hemodynamic measurements of the subject and the set of weights.

Verification of infusion rate requirements

A higher-level logic-based controller is configured to verify whether infusion rates of the at least one lower-level controller meet infusion rate requirements.

Timing of engaging the lower-level controller

A higher-level logic-based controller is configured to determine timing of engaging with the at least one lower-level controller.

Timing of disengaging based on performance-criterion violation

A higher-level logic-based controller is configured to determine timing of disengaging the at least one lower-level controller based on violation of a performance criterion.

User interface for infusion rate display and end-user control

A user interface is configured to display computed infusion rates, receive an initial infusion rate from an end-user, communicate the initial infusion rate by the end-user to the at least one higher-level logic-based controller, and notify the end-user if the performance criterion is violated.

Overall, the claim coverage centers on a hierarchical adaptive closed-loop system where a lower-level controller uses a dynamic observer and a function approximator with basis functions and weights to estimate physiological parameters and approximate unknown fluid/drug distribution in the body, while a higher-level logic-based controller verifies infusion-rate requirements and controls engagement and disengagement based on performance-criterion violation, supported by a user interface for end-user input, display, and notifications.

Stated Advantages

Maintains and/or restores target hemodynamic endpoints such as SVV in example simulations and canine study scenarios.

Provides controlled operation with safety verification through infusion rate requirements and performance-criterion based disengagement.

Supports partial automation via end-user provision of an initial infusion rate and user notification when the performance criterion is violated.

Documented Applications

Fluid resuscitation and cardiovascular drug administration using a closed-loop system with continuous hemodynamic monitoring and hierarchical adaptive control.

Example simulations including restoration/maintenance of SVV targets with controlled and uncontrolled hemorrhage scenarios.

A canine study demonstrating restoration/maintenance of SVV targets with controlled and uncontrolled hemorrhage scenarios.

Computer-simulation and hardware implementation examples for the described closed-loop architecture.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.