Health monitoring, surveillance and anomaly detection

Abstract

A wearable patch and method for automatically monitoring, screening, and/or reporting events related to one or more health conditions (e.g., sleeping or breathing disorders, physical activity, arrhythmias) of a subject.

1 . A method of wirelessly monitoring a condition of a subject, said method comprising:
 capturing, at a processor, a first signal indicative of the condition over a first period of time, the first signal being derived from acoustic data captured over the first period of time;   removing, at the processor, noise from the captured first signal to create a second signal indicative of the condition;   computing, at the processor, a plurality of moving averages of the second signal using a temporal window defining a second period of time, wherein each moving average is an average value of the second signal across the temporal window;   determining, at the processor, that at least one of the moving averages has a constant value for the entirety of the temporal window;   identifying, at the processor, an event in response to the determining, and   reporting, at the processor, the identified event using a display.   
     
     
         2 . The method of  claim 1 , wherein the first signal has a first frequency and said method further comprises down-sampling the captured first signal to a second lower frequency. 
     
     
         3 . The method of  claim 1 , wherein said removing noise from the captured first signal comprises:
 estimating the noise over a period of time; and   subtracting the estimated noise from the captured first signal.   
     
     
         4 . The method of  claim 3 , wherein the noise is estimated by filtering out portions of the first signal having an intensity less than twice a standard deviation of a distribution of signal intensity captured over a period of time. 
     
     
         5 . The method of  claim 1 , wherein said condition comprises a breathing condition and said first signal is a breathing signal. 
     
     
         6 . The method of  claim 5 , wherein said event comprises an apneic event. 
     
     
         7 . The method of  claim 5 , wherein said event comprises an apneic event and said determining comprises detecting the constant value as zero. 
     
     
         8 . The method of  claim 1 , further comprising counting a number of events to determine a severity of the condition. 
     
     
         9 . The method of  claim 8 , wherein said condition comprises a breathing condition, the event comprises and apneic event and the severity of the condition comprises one of mild, moderate or severe sleep apnea. 
     
     
         10 - 18 . (canceled) 
     
     
         19 . A system configured to wirelessly monitor a condition of a subject, said system comprising:
 an acoustic sensor configured to capture acoustic data over a first period of time;   a display device; and   a processor in communication with the acoustic sensor and the display device, the processor being configured to perform at least the following:
 deriving a first signal indicative of the condition over a first period of time from the acoustic data; 
 removing noise from the captured first signal to create a second signal indicative of the condition; 
 computing a plurality of moving averages of the second signal using a temporal window defining a second period of time, wherein each moving average is an average value of the second signal across the temporal window; 
 determining that at least one of the moving averages has a constant value for the entirety of the temporal window; 
 identifying an event in response to the determining, and 
 causing the display to report the identified event. 
   
     
     
         20 . The system of  claim 19 , wherein the first signal has a first frequency and the processor is configured to perform down-sampling of the captured first signal to a second lower frequency. 
     
     
         21 . The system of  claim 19 , wherein said removing noise from the captured first signal comprises:
 estimating the noise over a period of time; and   subtracting the estimated noise from the captured first signal.   
     
     
         22 . The system of  claim 21 , wherein the processor estimates the noise by filtering out portions of the first signal having an intensity less than twice a standard deviation of a distribution of signal intensity captured over a period of time. 
     
     
         23 . The system of  claim 19 , wherein said condition comprises a breathing condition and said first signal is a breathing signal. 
     
     
         24 . The system of  claim 23 , wherein said event comprises an apneic event. 
     
     
         25 . The system of  claim 23 , wherein said event comprises an apneic event and said determining comprises detecting the constant value as zero. 
     
     
         26 . The system of  claim 19 , wherein the processor is further configured to perform counting of a number of events to determine a severity of the condition. 
     
     
         27 . The system of  claim 26 , wherein said condition comprises a breathing condition, the event comprises and apneic event and the severity of the condition comprises one of mild, moderate or severe sleep apnea.