Detection of sleep condition

Abstract

Automated devices provide methodologies for determining sleep conditions, which may be in conjunction with treatment of sleep disordered breathing by a pressure treatment apparatus such as a continuous positive airway pressure device. Based on a measure of respiratory airflow, respiratory characteristics are extracted to detect arousal conditions, sleep stability, sleep states and/or perform sleep quality assessments. The methodologies may be implemented for data analysis by a specific purpose computer, a monitoring device that measures a respiratory airflow and/or a respiratory treatment apparatus that provides a respiratory treatment regime based on the detected conditions.

1 . A method for detecting sleep onset comprising:
 determining a set of respiratory features from a measure of respiratory flow;   thresholding the set of respiratory features;   determining a sleep state score based on the thresholding, the sleep state score being indicative of a sleep state; and   detecting sleep onset as a function of the thresholding and the determined sleep state score.   
     
     
         2 . The method of  claim 1  wherein the set of respiratory features comprises a function of a determined expiratory peak flow location. 
     
     
         3 . The method of  claim 2  wherein the function is a difference between (a) a ratio of the expiratory peak flow location and an expiratory time and (b) an average of a plurality of the ratios determined over a number of breaths. 
     
     
         4 . The method of  claim 1 , wherein the thresholding attributes a sleep state weight output for each of the set of respiratory features for each of a plurality of sleep states. 
     
     
         5 . The method of  claim 4 , wherein the plurality of sleep states includes an awake state and a sleep state. 
     
     
         6 . The method of  claim 5 , wherein the plurality of sleep states includes a non-REM sleep state and a REM sleep state. 
     
     
         7 . The method of  claim 4 , wherein the sleep state output weights are determined empirically from a group of measured respiratory data from a number of patients or from a single patient. 
     
     
         8 . The method of  claim 4 , further including combining the sleep state weight outputs of one or more of the set of respiratory features in patterns to calculate pattern weights. 
     
     
         9 . The method of  claim 8 , further comprising biasing the pattern weights with biasing factors in the calculation of the pattern weights. 
     
     
         10 . The method of  claim 9 , wherein the biasing factors are based on one or more characteristics of a patient. 
     
     
         11 . The method of  claim 8 , wherein the sleep state score is determined based on the calculated pattern weights for each sleep state. 
     
     
         12 . The method of  claim 11 , wherein sleep onset is determined when the sleep state score indicates a transition from an awake state to a sleep state has occurred. 
     
     
         13 . The method of  claim 1  further comprising, based on the detecting, outputting a sleep onset index representing a transition into a first sleep period for a treatment session. 
     
     
         14 . The method of  claim 13 , wherein the sleep onset index is a binary switch that is preset to 0 at the beginning of the treatment session and transitions to 1 when the first sleep period is detected. 
     
     
         15 . A device to detect sleep onset comprising:
 a processor configured to determine a set of respiratory features from a measure of respiratory flow;   wherein the processor is further configured to threshold the set of respiratory features, determine a sleep state store based on the thresholding and detect a sleep onset state based on the thresholding and the determined sleep state score.   
     
     
         16 . The device of  claim 15  wherein the set of respiratory features comprises a function of a determined expiratory peak flow location. 
     
     
         17 . The device of  claim 16  wherein the function is a difference between (a) a ratio of the expiratory peak flow location and an expiratory time and (b) an average of a plurality of the ratios determined over a number of breaths. 
     
     
         18 . The device of  claim 15 , wherein the thresholding attributes a sleep state weight output for each of the set of respiratory features for each of a plurality of sleep states. 
     
     
         19 . The device of  claim 18 , wherein the plurality of sleep states includes an awake state and a sleep state. 
     
     
         20 . The device of  claim 18 , wherein the plurality of sleep states includes a non-REM sleep state and a REM sleep state. 
     
     
         21 . The device of  claim 18 , wherein the sleep state output weights are determined empirically from a group of measured respiratory data from a number of patients or from a single patient. 
     
     
         22 . The device of  claim 18 , wherein the sleep state weight outputs of one or more of the set of respiratory features are combined in patterns to calculate pattern weights. 
     
     
         23 . The device of  claim 22 , wherein the calculation of the pattern weights includes biasing factors. 
     
     
         24 . The device of  claim 23 , wherein the biasing factors are based on one or more characteristics of a patient. 
     
     
         25 . The device of  claim 22 , wherein the sleep state score is determined based on the calculated pattern weights for each sleep state. 
     
     
         26 . The device of  claim 25 , wherein sleep onset is determined when the sleep state score indicates a transition from an awake state to a sleep state has occurred. 
     
     
         27 . The device of  claim 15  wherein the processor is further configured, based on the detecting, to output a sleep onset index representing a transition into a first sleep period for a treatment session. 
     
     
         28 . The device of  claim 27 , wherein the sleep onset index is a binary switch that is preset to 0 at the beginning of the treatment session and transitions to 1 when the first sleep period is detected. 
     
     
         29 . The device of  claim 15 , wherein the processor is further configured to control a respiratory pressure treatment regime based on the detected sleep onset state. 
     
     
         30 . The device of  claim 29 , wherein the respiratory pressure treatment regime includes an expiratory pressure relief mode configured to deliver a reduced treatment pressure during an expiratory phase of a breathing cycle compared to the treatment pressure delivered during an inspiratory phase of the breathing cycle. 
     
     
         31 . The device of  claim 30 , wherein the processor is configured to disengage the expiratory pressure relief mode after sleep onset is detected. 
     
     
         32 . The device of  claim 31 , wherein the processor is configured to gradually disengage the expiratory pressure relief mode by gradually ramping down an amount of reduction of treatment pressure delivered during the expiratory phase over a period of time. 
     
     
         33 . The device of  claim 31 , wherein the processor is configured to gradually disengage the expiratory pressure relief mode by gradually ramping down an amount of reduction of treatment pressure delivered during the expiratory phase over a number of breathing cycles. 
     
     
         34 . The device of  claim 31 , wherein the processor is configured to re-engage the expiratory pressure relief mode upon detection of a patient having returned to a subsequent awake state. 
     
     
         35 . The device of  claim 34 , wherein the processor is configured to re-engage the expiratory pressure relief mode after the patient has been in the subsequent awake state for a period of time. 
     
     
         36 . The device of  claim 34 , wherein the processor is configured to gradually re-engage the expiratory pressure relief mode by gradually increasing an amount of reduction of treatment pressure delivered during the expiratory phase over a period of time. 
     
     
         37 . The device of  claim 34 , wherein the processor is configured to gradually re-engage the expiratory pressure relief mode by gradually increasing an amount of reduction of treatment pressure delivered during the expiratory phase over a number of breathing cycles.