Identification of Asthma Triggering Conditions Based on Medicament Device Monitoring for a Patient

Abstract

This description provides trigger identification notifications to patients suffering from respiratory diseases based on large amounts of patient data in order to help effect behavior changes in a patient to prevent inhaler rescue usage events from occurring. Rescue medication events, environmental conditions, and other contextually relevant patient information are detected by sensors associated with the patient's medicament devices and are collected from other sources, respectively to provide a basis to determine identify various triggers of recue inhaler usage events for a patient. Each trigger is analyzed to determine the severity of the patient's reaction to the trigger and is used to send notifications accordingly.

1 . (canceled) 
     
     
         2 . A method for identifying triggers of rescue inhaler usage for a patient, the method comprising:
 receiving, from a medicament device sensor removably attached to a rescue inhaler unit and configured to monitor medicament usage of the rescue inhaler unit, a record of rescue inhaler usage events recorded by the medicament device sensor when the rescue inhaler unit dispense a rescue medication to the patient, the record comprising measurements of one or more environmental triggers recorded during each rescue inhaler usage event of the record;   for each rescue inhaler usage event of the record, encoding a feature vector comprising patient data for the patient and a value assigned to each of the one or more environmental triggers recorded during the rescue inhaler usage event, wherein the value is assigned to each environmental trigger based on the measurement recorded for the environmental trigger during the rescue usage event and describes whether a trigger condition for the environmental trigger was satisfied when the rescue inhaler usage event was detected;   for each trigger condition,
 determining a relative risk score of the patient based on a count of feature vectors in a first subset where the trigger condition is present and a second subset where the trigger condition is not present; 
 determining a sensitivity of the patient to the trigger condition based on a weighted normalization term output by a statistical model based on the relative risk score and a similarity between the patient and each user of a plurality of secondary users; 
   generating, for presentation to the patient, a notification describing the relative risk score of the patient and the sensitivity of the patient.   
     
     
         3 . The method of  claim 2 , further comprising:
 at periodic intervals,
 determining, for the patient, a relative risk score for the trigger condition based on feature vectors encoded with patient data recorded during each interval; and 
 identifying the patient as sensitive to the corresponding trigger by inputting the relative risk score to the statistical model. 
   
     
     
         4 . The method of  claim 2 , wherein an environmental trigger describes a threshold indicating one or more of the following:
 a presence of a measurable quantity indicative of increased usage of the rescue medication; and   an absence of a measurable quantity indicative of decreased usage of the rescue medication.   
     
     
         5 . The method of  claim 2 , further comprising:
 assigning a first weight to values of environmental triggers encoded for the patient;   assigning a second weight to values of environmental triggers encoded for each secondary user of the plurality; and   inputting the first and second weights into the function to determine the relative risk score.   
     
     
         6 . The method of  claim 5 , wherein the first weight is correlated with a count of rescue inhaler usage events for the patient encoded in the plurality of feature vectors encoded with patient data for the patient. 
     
     
         7 . The method of  claim 5 , wherein the second weights are correlated with a similarity of secondary users to the patient. 
     
     
         8 . The method of  claim 5 , further comprising:
 determining the first weight and the second weight based on the count of rescue inhaler usage events encoded in the plurality of feature vectors; and   inputting the first and second weights into the function to determine the relative risk score for the patient.   
     
     
         9 . The method of  claim 5 , further comprising:
 for each user of the plurality of secondary users, determining a similarity measurement between the secondary user and the patient based on a closeness of demographic information and values for environmental triggers encoded for the patient and the secondary user;   ranking the plurality of secondary users based on the determined similarity measurements; and   adjusting the second weight assigned to each secondary user of the plurality based on the ranking such that a higher ranked secondary user is assigned a greater second weight than a lower ranked secondary user.   
     
     
         10 . The method of  claim 2 , further comprising:
 for each environmental trigger of the one or more environmental triggers, identifying a set of binary conditions each representing a range of possible values for the environmental trigger; and   for each feature vector of the plurality of feature vectors, assigning a label to each trigger value identifying which binary condition of the set of binary conditions is satisfied by the trigger value.   
     
     
         11 . The method of  claim 2 , wherein determining the relative risk score for the patient further comprises:
 for each trigger condition,
 identifying a first plurality of days where a rescue usage event occurred and the trigger condition was met; 
 identifying a second plurality of days where a rescue usage event occurred and the trigger condition was not met; and 
 comparing the first plurality of days and the second plurality of days to determine the relative risk score. 
   
     
     
         12 . The method of  claim 2 , wherein determining the sensitivity of the patient to the trigger condition further comprises:
 comparing the relative risk score for the trigger condition to a confidence interval using a lookup table; and   determining that the patient is sensitive to the trigger condition based on the comparison.   
     
     
         13 . A non-transitory computer readable storage medium comprising computer program instructions that when executed by a computer processor cause the processor to:
 receive, from a medicament device sensor removably attached to a rescue inhaler unit and configured to monitor medicament usage of the rescue inhaler unit, a record of rescue inhaler usage events recorded by the medicament device sensor when the rescue inhaler unit dispense a rescue medication to the patient, the record comprising measurements of one or more environmental triggers recorded during each rescue inhaler usage event of the record;   for each rescue inhaler usage event of the record, encode a feature vector comprising patient data for the patient and a value assigned to each of the one or more environmental triggers recorded during the rescue inhaler usage event, wherein the value is assigned to each environmental trigger based on the measurement recorded for the environmental trigger during the rescue usage event and describes whether a trigger condition for the environmental trigger was satisfied when the rescue inhaler usage event was detected;   for each trigger condition,
 determine a relative risk score of the patient based on a count of feature vectors in a first subset where the trigger condition is present and a second subset where the trigger condition is not present; 
 determine a sensitivity of the patient to the trigger condition based on a weighted normalization term output by a statistical model based on the relative risk score and a similarity between the patient and each user of a plurality of secondary users; 
   generate, for presentation to the patient, a notification describing the relative risk score of the patient and the sensitivity of the patient.   
     
     
         14 . The non-transitory computer-readable storage medium of  claim 13 , further comprising instructions that cause the processor to:
 at periodic intervals,
 determine, for the patient, a relative risk score for the trigger condition based on feature vectors encoded with patient data recorded during each interval; and 
 identify the patient as sensitive to the corresponding trigger by inputting the relative risk score to the statistical model. 
   
     
     
         15 . The non-transitory computer-readable storage medium of  claim 13 , wherein an environmental trigger describes a threshold indicating one or more of the following:
 a presence of a measurable quantity indicative of increased usage of the rescue medication; and   an absence of a measurable quantity indicative of decreased usage of the rescue medication.   
     
     
         16 . The non-transitory computer-readable storage medium of  claim 13 , further comprising instructions that cause the processor to:
 assign a first weight to values of environmental triggers encoded for the patient;   assign a second weight to values of environmental triggers encoded for each secondary user of the plurality; and   input the first and second weights into the function to determine the relative risk score.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , further comprising instructions that cause the processor to:
 determine the first weight and the second weight based on the count of rescue inhaler usage events encoded in the plurality of feature vectors; and   input the first and second weights into the function to determine the relative risk score for the patient.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 16 , further comprising instructions that cause the processor to:
 for each user of the plurality of secondary users, determine a similarity measurement between the secondary user and the patient based on a closeness of demographic information and values for environmental triggers encoded for the patient and the secondary user;   rank the plurality of secondary users based on the determined similarity measurements; and   adjust the second weight assigned to each secondary user of the plurality based on the ranking such that a higher ranked secondary user is assigned a greater second weight than a lower ranked secondary user.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 13 , further comprising instructions that cause the processor to:
 for each environmental trigger of the one or more environmental triggers, identify a set of binary conditions, each representing a range of possible values for the environmental trigger; and   for each feature vector of the plurality of feature vectors, assign a label to each trigger value identifying which binary condition of the set of binary conditions is satisfied by the trigger value.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 13 , wherein instructions for determining the relative risk score for the patient further comprise instructions that cause the processor to:
 for each trigger condition,
 identify a first plurality of days where a rescue usage event occurred and the trigger condition was met; 
 identify a second plurality of days where a rescue usage event occurred and the trigger condition was not met; and 
 compare the first plurality of days and the second plurality of days to determine the relative risk score. 
   
     
     
         21 . The non-transitory computer-readable storage medium of  claim 13 , wherein instructions for determining the sensitivity of the patient to the trigger condition further comprise instructions that cause the processor to:
 compare the relative risk score for the trigger condition to a confidence interval using a lookup table; and   determine that the patient is sensitive to the trigger condition based on the comparison.