Physiologic audio methods and arrangements

Abstract

Reference imagery of dermatological conditions is compiled in a crowd-sourced database (contributed by clinicians and/or the lay public), together with associated diagnosis information. A user later submits a query image to the system (e.g., captured with a smartphone). Image-based derivatives for the query image are determined (e.g., color histograms, FFT-based metrics, etc.), and are compared against similar derivatives computed from the reference imagery. This comparison identifies diseases that are not consistent with the query image, and such information is reported to the user. Depending on the size of the database, and the specificity of the data, 90% or more of candidate conditions may be effectively ruled-out, possibly sparing the user from expensive and painful biopsy procedures, and granting some peace of mind (e.g., knowledge that an emerging pattern of small lesions on a forearm is probably not caused by shingles, bedbugs, malaria or AIDS). A great number of other features and arrangements are also detailed.

1 - 56 . (canceled) 
     
     
         57 . A personal appliance incorporating a battery, a processor, a memory, a display, one or more microphones, and one or more other sensors, said appliance being adapted for wearing or carrying by a user and being characterized by instructions in the memory that configure the appliance to process audio sensed by the microphone(s) to determine physiologic health information about the user. 
     
     
         58 . The appliance of  claim 57  in which said instructions configure the appliance to apply a prediction-based technique to sensed audio corresponding to cardiovascular or respiratory sounds sensed from the user. 
     
     
         59 . The appliance of  claim 58  in which said instructions configure the appliance to employ a prediction error to detect an irregularity in said sounds. 
     
     
         60 . The appliance of  claim 58  in which said instructions configure the appliance to isolate a murmur from a stronger heart beat signal. 
     
     
         61 . The appliance of  claim 57  in which said instructions configure the appliance to parameterize cyclically-recurring sounds by identifying a time interval over which a threshold portion of spectral energy in said sounds is expressed. 
     
     
         62 . The appliance of  claim 57  in which said instructions configure the appliance to parameterize cyclically-recurring sounds by identifying a frequency bandwidth within which a threshold portion of spectral energy in said sounds is expressed. 
     
     
         63 . The appliance of  claim 57  in which said instructions configure the appliance to process waveforms of cardiovascular or respiratory sounds that repeat with a period, by averaging different of said repeating waveforms. 
     
     
         64 . The appliance of  claim 57  in which said instructions configure the appliance to process waveforms of cardiovascular or respiratory sounds that repeat with a period, by correlating different of said repeating waveforms. 
     
     
         65 . The appliance of  claim 57  in which said instructions configure the appliance to sense electric signals from the user's heart using one of said other sensors, and to utilize timing derived from said sensed electric heart signals in connection with processing the sensed audio. 
     
     
         66 . The appliance of  claim 57  that further includes an auxiliary microphone system coupled thereto, wherein said instructions configure the appliance to employ audio from the one or more microphones of said appliance, in conjunction with audio from said auxiliary microphone system, to perform a noise cancellation function. 
     
     
         67 . The appliance of  claim 57  in which the instructions configure the appliance to employ information about the user's age in determining said physiologic health information. 
     
     
         68 . The appliance of  claim 57  in which the instructions configure the appliance to employ information about the user's weight in determining said physiologic health information. 
     
     
         69 . The appliance of  claim 57  in which the instructions configure the appliance to employ information about the user's gender in determining said physiologic health information. 
     
     
         70 . The appliance of  claim 69  in which the instructions configure the appliance to process the sensed audio using a trained classifier, wherein said classifier was trained based on data gathered from persons of said user's gender.