Cough detection using frontal accelerometer

Abstract

This disclosure is directed to techniques for recording and recognizing physiological parameter patterns associated with symptoms. A medical device system includes a medical device including an accelerometer configured to collect an accelerometer signal that indicates one or more patient movements that occur during a cough. Additionally, the medical device system includes processing circuitry configured to: determine whether the accelerometer signal satisfies a set of criteria corresponding to a cough pattern comprising a smooth increase from a baseline, then a sharp decrease, a peak within the sharp decrease, then a gradual return to the baseline; and identify a cough based on the determination that the accelerometer signal satisfies the set of criteria.

What is claimed is: 
     
         1 . A medical device system comprising:
 a medical device comprising:
 an accelerometer configured to collect an accelerometer signal, wherein the accelerometer signal is indicative of one or more patient movements that occur during a cough; and 
   processing circuitry configured to:
 determine whether the accelerometer signal satisfies a set of criteria corresponding to a cough pattern comprising a smooth increase from a baseline, then a sharp decrease, a peak within the sharp decrease, then a gradual return to the baseline; and 
 identify a cough based on the determination that the accelerometer signal satisfies the set of criteria. 
   
     
     
         2 . The medical device system of  claim 1 , wherein the processing circuitry is further configured to increment a cough count value. 
     
     
         3 . The medical device system of  claim 1 , wherein the processing circuitry is further configured to:
 save, to a database in memory, a set of data including the accelerometer signal; and   notify a physician of the data set.   
     
     
         4 . The medical device system of  claim 1 , wherein to determine whether the accelerometer signal satisfies the set of criteria corresponding to a cough pattern, the processing circuitry is further configured to:
 execute an algorithm in a series of steps determining whether each criterion of the set of criteria is satisfied individually; and   terminate the algorithm without proceeding to the later steps responsive to one of the criteria not being satisfied.   
     
     
         5 . The medical device system of  claim 4 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine a long-term average signal from the accelerometer signal;   identify a dropoff point in the long-term average signal;   identify a valley point in the long-term average signal; and   identify a stabilization point in the long-term average signal.   
     
     
         6 . The medical device system of  claim 5 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine whether an amplitude difference between the dropoff point and the valley point is greater than a threshold value.   
     
     
         7 . The medical device system of  claim 5 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine whether an amplitude difference between the stabilization point and the valley point is less than a threshold value.   
     
     
         8 . The medical device system of  claim 5 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine whether a ratio of a number of samples between the stabilization point and valley point to the sampling rate is both above a first threshold value and below a second threshold value;   
     
     
         9 . The medical device system of  claim 5 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine if noisy fluctuations exist in the accelerometer signal preceding the dropoff point in the long-term average signal; and   
     
     
         10 . The medical device system of  claim 5 , wherein to perform the series of steps, the processing circuitry is further configured to:
 determine if a peak point exists between the dropoff point and the valley point such that a difference signal between the dropoff point and the valley point contains a value above a first threshold value and a value below a second threshold value.   
     
     
         11 . A method comprising:
 collecting, using an accelerometer of a medical device, an accelerometer signal, wherein the accelerometer signal is indicative of one or more patient movements that occur during a cough;   determining whether the accelerometer signal satisfies a set of criteria corresponding to a cough pattern comprising a smooth increase from a baseline, then a sharp decrease, a peak within the sharp decrease, then a gradual return to the baseline; and   identifying a cough based on determining that the accelerometer signal satisfies the set of criteria.   
     
     
         12 . The method of  claim 11 , wherein the method further comprises incrementing a cough count value in response to identifying a cough. 
     
     
         13 . The method of  claim 11 , wherein the method further comprises:
 saving, to a database in memory, a set of data including the accelerometer signal; and   notifying a physician of the data set.   
     
     
         14 . The method of  claim 11 , wherein determining whether the accelerometer signal satisfies the set of criteria corresponding to a cough pattern further comprises:
 executing an algorithm in a series of steps determining whether each criterion of the set of criteria is satisfied individually; and   terminating the algorithm without proceeding to the later steps responsive to one of the criteria not being satisfied.   
     
     
         15 . The method of  claim 14 , wherein the series of steps comprises:
 determining a long-term average signal from the accelerometer signal;   identifying a dropoff point in the long-term average signal;   identifying a valley point in the long-term average signal; and   identifying a stabilization point in the long-term average signal.   
     
     
         16 . The method of  claim 15 , wherein the series of steps further comprises:
 determining whether the amplitude difference between the dropoff point and the valley point is greater than a threshold value;   
     
     
         17 . The method of  claim 15 , wherein the series of steps further comprises determining whether the amplitude difference between the stabilization point and the valley point is less than a threshold value. 
     
     
         18 . The method of  claim 15 , wherein the series of steps further comprises determining whether a ratio of a number of samples between the stabilization point and valley point to the sampling rate is both above a first threshold value and below a second threshold value; 
     
     
         19 . The method of  claim 15 , wherein the series of steps further comprises:
 determining if noisy fluctuations exist in the accelerometer signal preceding the dropoff point in the long-term average signal; and   determining if a peak point exists between the dropoff point and the valley point such that a difference signal between the dropoff point and the valley point contains a value above a first threshold value and a value below a second threshold value.   
     
     
         20 . A non-transitory computer-readable medium comprising instructions for causing processing circuitry of a medical device system to:
 determine whether an accelerometer signal satisfies a set of criteria corresponding to a cough pattern comprising a smooth increase from a baseline, then a sharp decrease, a peak within the sharp decrease, then a gradual return to the baseline, wherein the accelerometer signal is collected by an accelerometer of a medical device, and is indicative of one or more patient movements that occur during a cough; and   identify a cough based on the determination that the accelerometer signal satisfies the set of criteria.