Rapid detection of bleeding before, during, and after fluid resuscitation

Abstract

Novel tools and techniques are provided for assessing, predicting and/or estimating a probability that a patent is bleeding, in some cases, noninvasively. In various embodiments, tools and techniques are provided for implementing rapid detection of bleeding before, during, and after fluid resuscitation, in some instances, in real-time.

1 .- 35 . (canceled) 
     
     
         36 . A monitoring device, comprising:
 one or more input devices configured to receive raw waveform data of a patient;   one or more processing circuits configured to:
 monitor the raw waveform data corresponding to cardiovascular state of the patient; 
 analyze, using a compensatory reserve model, the raw waveform data to generate a physiological estimation of the patient based on a subset of signals of a set of signals of the raw waveform data; and 
 provide the physiological estimation of the patient. 
   
     
     
         37 . The monitoring device of  claim 36 , wherein the one or more processing circuits select the subset of signals of the set of signals based on a determination of predictiveness corresponding to blood loss or an effectiveness of a treatment, wherein the determination of predictiveness comprises a likelihood of cardiovascular collapse or near-cardiovascular collapse. 
     
     
         38 . The monitoring device of  claim 37 , wherein the subset of signals corresponds to identified predicative variables the compensatory reserve model used during model building, wherein the one or more processing circuits identify the identified predictive variables based on a linear or non-linear model framework. 
     
     
         39 . The monitoring device of  claim 36 , wherein each signal of the subset of signals corresponds to a signal value, wherein the one or more processing circuits perform learning of the compensatory reserve model based on example values of signals corresponding with one or more outcomes. 
     
     
         40 . The monitoring device of  claim 36 , wherein the subset of signals of the raw waveform data is correlated with one or more physiological state measurements, and wherein the one or more physiological state measurements comprises at least one of a state of blood loss or fluid resuscitation. 
     
     
         41 . The monitoring device of  claim 36 , wherein the physiological estimation of the patient is a compensatory reserve value measuring a hemodynamic state of the patient over a particular period of time, and wherein the raw waveform data corresponding to the cardiovascular state of the patient is continuously collected over the particular period of time. 
     
     
         42 . The monitoring device of  claim 36 , the one or more processing circuits are further configured to:
 analyze, using the compensatory reserve model, the raw waveform data to generate a future physiological estimation of the patient.   
     
     
         43 . The monitoring device of  claim 36 , wherein the compensatory reserve model is learned on the subset of signals of the set of signals and correlations between lower body negative pressure (LBNP) data, wherein one or more test subjects are subjected to LBNP during the learning. 
     
     
         44 . A method, comprising:
 receiving, by the one or more processing circuits, raw waveform data of a patient;   monitoring, by the one or more processing circuits, the raw waveform data corresponding to cardiovascular state of the patient;   analyzing, by the one or more processing circuits using a compensatory reserve model, the raw waveform data to generate a physiological estimation of the patient based on a subset of signals of a set of signals of the raw waveform data; and   providing, by the one or more processing circuits, the physiological estimation of the patient.   
     
     
         45 . The method of  claim 44 , wherein the one or more processing circuits select the subset of signals of the set of signals based on a determination of predictiveness corresponding to blood loss or an effectiveness of a treatment, wherein the determination of predictiveness comprises a likelihood of cardiovascular collapse or near-cardiovascular collapse. 
     
     
         46 . The method of  claim 45 , wherein the subset of signals corresponds to identified predicative variables the compensatory reserve model used during model building, wherein the one or more processing circuits identify the identified predictive variables based on a linear or non-linear model framework. 
     
     
         47 . The method of  claim 44 , wherein each signal of the subset of signals corresponds to a signal value, wherein the one or more processing circuits perform learning of the compensatory reserve model based on example values of signals corresponding with one or more outcomes. 
     
     
         48 . The method of  claim 44 , wherein the subset of signals of the raw waveform data is correlated with one or more physiological state measurements, and wherein the one or more physiological state measurements comprises at least one of a state of blood loss or fluid resuscitation. 
     
     
         49 . The method of  claim 44 , wherein the physiological estimation of the patient is a compensatory reserve value measuring a hemodynamic state of the patient over a particular period of time, and wherein the raw waveform data corresponding to the cardiovascular state of the patient is continuously collected over the particular period of time. 
     
     
         50 . The method of  claim 44 , further comprising:
 analyzing, by the one or more processing circuits using the compensatory reserve model, the raw waveform data to generate a future physiological estimation of the patient.   
     
     
         51 . The method of  claim 44 , wherein the compensatory reserve model is learned on the subset of signals of the set of signals and correlations between lower body negative pressure (LBNP) data, wherein one or more test subjects are subjected to LBNP during the learning. 
     
     
         52 . One or more non-transitory computer-readable storage media having instructions stored thereon that, when executed by one or more processing circuits, causes the one or more processing circuits to:
 receive raw waveform data of a patient;   monitor the raw waveform data corresponding to cardiovascular state of the patient;   analyze, using a compensatory reserve model, the raw waveform data to generate a physiological estimation of the patient based on a subset of signals of a set of signals of the raw waveform data; and   provide the physiological estimation of the patient.   
     
     
         53 . The one or more non-transitory computer-readable storage media of  claim 52 , wherein the instructions cause the one or more processing circuits to select the subset of signals of the set of signals based on a determination of predictiveness corresponding to blood loss or an effectiveness of a treatment, wherein the determination of predictiveness comprises a likelihood of cardiovascular collapse or near-cardiovascular collapse associated with the cardiovascular state of the patient. 
     
     
         54 . The one or more non-transitory computer-readable storage media of  claim 53 , wherein the subset of signals corresponds to identified predicative variables the compensatory reserve model used during model building, wherein the instructions cause the one or more processing circuits to identify the identified predictive variables based on a linear or non-linear model framework. 
     
     
         55 . The one or more non-transitory computer-readable storage media of  claim 52 , wherein each signal of the subset of signals corresponds to a signal value, wherein the instructions cause the one or more processing circuits to perform learning of the compensatory reserve model based on example values of signals corresponding with one or more outcomes.