System and method for physiological data classification for use in facilitating diagnosis
A system and method for physiological data classification for use in facilitating diagnosis is provided. A physiological monitor includes a feedback button and physiological data obtained via the physiological monitor is stored in a database. The physiological data is divided into segments and one or more data segments are classified as noise. A determination is made that at least one of the data segments classified as noise includes a marker indicating a press of the feedback button on the physiological monitor. A set of the physiological data including and surrounding the physiological data occurring during the press of the feedback button is identified within the data segment classified as noise. The identified set of physiological data is provided with the data segments classified as valid for analysis.
1. A system for physiological data classification for use in facilitating diagnosis, comprising:
a feedback button on a physiological monitor;
a database to store physiological data obtained via the physiological monitor; and
a server comprising a central processing unit, memory, an input port to receive the physiological data from the database, and an output port, wherein the central processing unit is configured to:
maintain the physiological data that occurs around a press of the feedback button on the physiological monitor, comprising:
divide the physiological data into segments;
identify one or more data segments classified as noise;
determine that at least one of the data segments classified as noise comprises a marker indicating the press of the feedback button on the physiological monitor; and
identify a set of the physiological data including and surrounding the physiological data occurring during the press of the feedback button within the data segment classified as noise; and
analyze the identified set of physiological data with the data segments classified as valid.
2. A system in accordance with claim 1 , wherein the central processing unit removes those data segments classified as noise.
3. A system in accordance with claim 1 , further comprising:
an adaptive noise detector to perform noise detection analysis on the data segments by classifying the data segments as valid or noise.
4. A system in accordance with claim 3 , wherein the adaptive noise detector is trained by annotating training data with markers for valid data or noise via one or more of software analysis, human review, and a combination of software analysis and human review.
5. A system in accordance with claim 3 , wherein the central processing unit identifies a predetermined amount of physiological data at a beginning of each data segment and removes the predetermined amount of physiological data from each segment prior to the noise detection analysis.
6. A system in accordance with claim 3 , wherein the central processing unit determines a testing accuracy of the adaptive noise detector by comparing results of testing data from the adaptive noise detector with results of the testing data from a human reviewer or different noise detection analyzer.
7. A system in accordance with claim 1 , wherein the data segments comprise contiguous data segments or overlapping data segments.
8. A system in accordance with claim 1 , wherein the press of the feedback button represents a patient identified physiological event.
9. A system in accordance with claim 1 , wherein the set of physiological data comprises a predetermined amount of data prior to and after the data occurring during the press of the feedback button and the predetermined amount of data prior to and after are one of the same and different.
10. A system in accordance with claim 1 , wherein the set of physiological data is displayed.
11. A method for physiological data classification for use in facilitating diagnosis, comprising:
monitoring a physiological monitor comprising a feedback button;
storing in a database physiological data obtained via the physiological monitor;
maintaining the physiological data that occurs around a press of the feedback button on the physiological monitor, comprising:
dividing the physiological data into segments via a central processing unit of a server comprising memory, an input port to receive the physiological data from the database, and an output port;
identifying by the central processing unit one or more data segments classified as noise;
determining via the central processing unit that at least one of the data segments classified as noise comprises a marker indicating a press of the feedback button on the physiological monitor; and
identifying a set of the physiological data including and surrounding the physiological data occurring during the press of the feedback button within the data segment classified as noise via the central processing unit; and
providing for analysis the identified set of physiological data with the data segments classified as valid.
12. A method in accordance with claim 11 , further comprising:
removing those data segments classified as noise.
13. A method in accordance with claim 11 , further comprising:
training an adaptive noise detector to perform noise detection analysis on the data segments.
14. A method in accordance with claim 13 , wherein the adaptive noise detector is trained by annotating training data with markers for valid data or noise via one or more of software analysis, human review, and a combination of software analysis and human review.
15. A method in accordance with claim 13 , further comprising:
identifying a predetermined amount of physiological data at a beginning of each data segment; and
removing the predetermined amount of physiological data from each segment prior to the noise detection analysis.
16. A method in accordance with claim 13 , further comprising:
determining a testing accuracy of the adaptive noise detector by comparing results of testing data from the adaptive noise detector with results of the testing data from a human reviewer or different noise detection analyzer.
17. A method in accordance with claim 11 , wherein the data segments comprise contiguous data segments or overlapping data segments.
18. A method in accordance with claim 11 , wherein the press of the feedback button represents a patient identified physiological event.
19. A method in accordance with claim 11 , wherein the set of physiological data comprises a predetermined amount of data prior to and after the data occurring during the press of the feedback button and the predetermined amount of data prior to and after are one of the same and different.
20. A method in accordance with claim 11 , further comprising:
displaying the set of physiological data.