Long Term Active Learning from Large Continually Changing Data Sets

• US 20160162786A1
• Filed: 01/27/2016
• Published: 06/09/2016
• Est. Priority Date: 10/29/2008
• Status: Abandoned Application

• Current Assignee: The Board of Regents of the University of Colorado (University of Colorado System)
• Original Assignee: The Board of Regents of the University of Colorado (University of Colorado System)
• Inventors: Grudic, Gregory Zlatko, Moulton, Steven Lee, Mulligan, Isobel Jane
• Application Number:
  US15/007,489
• Publication Number:
  US 20160162786A1
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

Methods and systems are disclosed for autonomously building a predictive model of outcomes. A most-predictive set of signals S_k is identified out of a set of signals s₁, s₂, . . . , s_D for each of one or more outcomes o_k. A set of probabilistic predictive models ô_k=M_k(S_k) is autonomously learned, where ô_k is a prediction of outcome o_k derived from the model M_k that uses as inputs values obtained from the set of signals S_k. The step of autonomously learning is repeated incrementally from data that contains examples of values of signals s₁, s₂, . . . , s_D and corresponding outcomes o₁, o₂, . . . , o_K. Various embodiments are also disclosed that apply predictive models to various physiological events and to autonomous robotic navigation.

Claims

1. A method of predicting cardiovascular collapse in a patient, the method comprising:

receiving, at a computer, real-time, continuous pulsatile waveform data from one or more sensors that are measuring physiological characteristics of a patient;

analyzing, with the computer, the real-time, continuous pulsatile waveform data with multiple linear probability density models generated by exposing a plurality of test subjects to simulated cardiovascular collapse, the models identifying one or more sensor signals as being most predictive of cardiovascular collapse, the one or more sensor signals representing continuous pulsatile waveform data;

deriving, with the computer and from the linear probability density model, physiological feature data indicative of a probability that the patient will experience cardiovascular collapse;

estimating, with the computer and using the multiple linear probability density model, a probability that the patient will experience cardiovascular collapse, based on the real-time, continuous pulsatile waveform data received from the one or more sensors; and

displaying, with a display device, an estimate of the probability that the patient will experience cardiovascular collapse.

2. The method of claim 1, wherein the linear probability density model comprises a hemodynamic compensation model that is generated by:

identifying a most-predictive set of signals S_k out of a set of signals s₁, s₂, . . . , s_D for each of one or more outcomes Ok, each of the signals corresponding to data values collected from the plurality of test subjects;

autonomously learning a set of probabilistic predictive models ô

_k=M_k(S_k), where ô

_k is a prediction of outcome Ok derived from the model Mk that uses as inputs values obtained from the set of signals S_k; and

repeating the step of autonomously learning incrementally from data that contains examples of values of signals s₁, S₂, . . . , s_D and corresponding outcomes o₁, o₂, . . . , o_K.

3. The method of claim 2, wherein autonomously learning the set of probabilistic predictive models comprises using a linear model framework to identify predictive variables for each increment of data.

4. The method of claim 3, wherein the linear model framework is constructed with the form

5. The method of claim 1, wherein the physiological feature data reflects physiological information contained in the real-time, continuous pulsatile waveform data.

6. The method of claim 1, further comprising:

determining a physiological response to treatment by monitoring the convergence or divergence to a physiological threshold of the real-time, continuous pulsatile waveform data and the physiological feature data as a function of time.

7. The method of claim 1, further comprising:

displaying, with the display device and in real time, an indication of effectiveness of intravenous therapy.

8. The method of claim 1, wherein displaying, with the display device, an estimate of the probability that the patient will experience cardiovascular collapse comprises displaying a graph of a volume of acute blood loss of the patient and a volume of blood loss that will cause cardiovascular collapse as a function of time.

9. The method of claim 1, further comprising:

deriving, with the computer and from the multiple linear probability density models, second physiological feature data;

determining, with the computer and from the multiple linear probability density models, a physiological threshold from the second physiological feature data and from historical data, wherein the physiological threshold corresponds to a point such that when the second physiological feature data reaches the physiological threshold a different physiological event occurs or is detected; and

displaying, with the display device, a relationship between the physiological threshold and the physiological feature data as the second physiological feature data is derived.

10. The method of claim 1, wherein the one or more sensors comprise one or more photoplethysmograph (“

PPG”

) sensors, one or more transcranial Doppler sensors, one or more noninvasive or invasive pulsatile sensors, one or more ECG sensors, and/or one or more blood flow sensors.

11. A system for predicting cardiovascular collapse in a patient, the system comprising:

a physiological sensor interface configured to couple with one or more physiological sensors that collect physiological data values from a patient; and

a processor having a non-transitory computer-readable storage medium, the processor in electrical communication with the sensor interface, the non-transitory computer-readable storage medium comprising instructions executable by the processor to;

receive, via the physiological sensor interface, real-time, continuous pulsatile waveform data from one or more sensors that are measuring physiological characteristics of the patient;

analyze the real-time, continuous pulsatile waveform data with multiple linear probability density models generated by exposing a plurality of test subjects to simulated cardiovascular collapse, the models identifying one or more sensor signals as being most predictive of cardiovascular collapse, the one or more sensor signals including continuous pulsatile waveform data;

derive, from the linear probability density models, physiological feature data indicative of a probability that the patient will experience cardiovascular collapse;

estimate, using the linear probability density models, a probability that the patient will experience cardiovascular collapse, based on the real-time, continuous pulsatile waveform data received from the one or more sensors; and

display, with a display device in communication with the system, an estimate of the probability that the patient will experience cardiovascular collapse.

12. The system of claim 11, wherein the linear probability density model comprises a hemodynamic compensation model that is generated by:

identifying a most-predictive set of signals S_k out of a set of signals s₁, s₂, . . . , s_D for each of one or more outcomes o_k, each of the signals corresponding to data values collected from the plurality of test subjects;

autonomously learning a set of probabilistic predictive models ô

_k=M_k(S_k), where ô

_k is a prediction of outcome Ok derived from the model M_k that uses as inputs values obtained from the set of signals S_k; and

repeating the step of autonomously learning incrementally from data that contains examples of values of signals s₁, S₂, . . . , s_D and corresponding outcomes o₁, o₂, . . . , o_K.

13. The system of claim 12, wherein autonomously learning the set of probabilistic predictive models comprises using a linear model framework to identify predictive variables for each increment of data.

14. The system of claim 13, wherein the linear model framework is constructed with the form

15. The system of claim 11, wherein the physiological feature data reflects physiological information contained in the real-time, continuous pulsatile waveform data.

16. The system of claim 11, wherein the instructions are further executable to:

determine a physiological response to treatment by monitoring the convergence or divergence to a physiological threshold of the real-time, continuous pulsatile waveform data and the physiological feature data as a function of time.

17. The system of claim 11, wherein the instructions are further executable to:

display, with the display device and in real time, an indication of effectiveness of intravenous therapy.

18. The system of claim 11, wherein the instructions executable to display, with the display device, an estimate of the probability that the patient will experience cardiovascular collapse comprises instructions executable to graph a volume of acute blood loss of the patient and a volume of blood loss that will cause cardiovascular collapse as a function of time.

19. The system of claim 11, wherein the instructions are further executable to:

derive, from the multiple linear probability density model, second physiological feature data;

determine, from the multiple linear probability density models, a physiological threshold from the second physiological feature data and from historical data, wherein the physiological threshold corresponds to a point such that when the second physiological feature data reaches the physiological threshold a different physiological event occurs or is detected; and

display, with the display device, a relationship between the physiological threshold and the physiological feature data as the second physiological feature data is derived.

20. The system of claim 11, wherein the one or more sensors comprise one or more photoplethysmograph (“

PPG”

) sensors, one or more transcranial Doppler sensors, one or more noninvasive or invasive pulsatile sensors, one or more ECG sensors, and/or one or more blood flow sensors.