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

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.

1 . A system for fluid or drug administration comprising:
 a) a monitoring module configured to receive hemodynamic measurements of a subject from at least one medical monitoring device attached to the subject;   b) a controller module configured to:
 (i) estimate a current value of one or more physiological parameters of the subject based at least in part on the hemodynamic measurements; 
 (ii) compute an updated infusion rate based at least in part on the estimate of the current value of one or more physiological parameters of the subject and the received hemodynamic measurements; and 
 (iii) communicate the updated infusion rate to an infusion pump; and 
   c) a graphical user interface to receive a start and/or stop command from a user to start and/or stop the controller module.   
     
     
         2 . The system of  claim 1 , wherein the controller module is further configured to approximate at least one unknown function describing distribution of a fluid and/or drug in the body of the subject based at least in part on the received hemodynamic measurements. 
     
     
         3 . The system of  claim 1 , wherein the updated infusion rate is computed based at least in part on an initial infusion rate set by the user by way of the graphical user interface. 
     
     
         4 . The system of  claim 1 , wherein the controller module is further configured to:
 (a) verify whether the updated infusion rate meets infusion rate requirements; and   (b) verify whether a performance criterion is violated.   
     
     
         5 . The system of  claim 1 , wherein the controller module is further configured to disengage based on violation of a performance criterion. 
     
     
         6 . The system of  claim 1 , wherein the at least one unknown function describing distribution of a fluid and/or drug in the body of the subject is approximated using a function approximator. 
     
     
         7 . The system of  claim 6 , wherein the function approximator is a neural network with sigmoidal basis functions. 
     
     
         8 . The system of  claim 1 , wherein the user interface is further configured to receive a measurement target value from the user. 
     
     
         9 . The system of  claim 1 , wherein the user interface is further configured to receive a range of safe infusion rates from the user. 
     
     
         10 . The system of  claim 1 , wherein the user interface is further configured to display the updated infusion rate. 
     
     
         11 . The system of  claim 1 , wherein the user is notified if at least one infusion therapy performance criterion is violated. 
     
     
         12 . The system of  claim 1 , wherein the updated infusion rate is updated to a backup infusion rate if the hemodynamic measurements is unavailable. 
     
     
         13 . The system of  claim 1 , wherein the hemodynamic measurements of the subject comprises the subject's blood pressure, heart rate, stroke volume variation, urine output rate, urine output, central venous pressure, pulse pressure variation, dynamic arterial elastance, systolic pressure variation, mean arterial pressure, systolic pressure, diastolic pressure, cardiac output, cardiac index, systemic vascular resistance, or stroke volume. 
     
     
         14 . A method for fluid and/or cardiovascular drug administration, the method comprising:
 receiving from a sensor hemodynamic measurements of a subject by a controller, wherein the controller comprises an estimator to estimate a current value of one or more physiological parameters of the subject based at least in part on the hemodynamic measurements;   computing an updated infusion rate based at least in part on the estimate of the current value of one or more physiological parameters of the subject and the received hemodynamic measurements and a target measurement value set by a user;   notifying the user and disengaging the controller if at least one performance criterion is violated by dropping below or exceeding a set threshold; and   administering the fluid and/or cardiovascular drug at the new infusion rate to the subject.   
     
     
         15 . The method of  claim 14 , wherein the controller further comprises a function approximator to approximate at least one unknown function describing distribution of a fluid and/or drug in the body of the subject based at least in part on the received hemodynamic measurements. 
     
     
         16 . The method of  claim 15 , wherein the updated infusion rate is computed based on at least one parameter of the function approximator. 
     
     
         17 . The method of  claim 15 , wherein the function approximator is a neural network with sigmoidal basis functions. 
     
     
         18 . The method of  claim 14 , wherein the performance criterion is an infusion therapy performance criterion. 
     
     
         19 . The method of  claim 14 , wherein the hemodynamic measurements of the subject comprises the subject's blood pressure, heart rate, stroke volume variation, urine output rate, urine output, central venous pressure, pulse pressure variation, dynamic arterial elastance, systolic pressure variation, mean arterial pressure, systolic pressure, diastolic pressure, cardiac output, cardiac index, systemic vascular resistance, or stroke volume. 
     
     
         20 . The method of  claim 14 , wherein the updated infusion rate is computed based at least in part on an initial infusion rate set by the user.