Patent Forecast

1. A method comprising: (6) (2)

capturing, using one or more sensors of a device, signals including information about a user's symptoms;

using one or more processors of the device to: collect other data correlative of symptoms experienced by the user;

determine, using a symptom classifier with the signals and the other data as input, one or more symptoms of the user;

determine, using a disease classifier with the one or more symptoms and one or more sleep features as input, a disease or disease state of the user;

determine, using a medication effectiveness classifier with the disease or disease state as input, a medication effectiveness in suppressing the one or more symptoms or improving the disease state of the user; and

presenting, using an output device, data for the one or more symptoms, the disease, the disease state, or an indication of the medication effectiveness for the user.

2. The method of claim 1, wherein the other data correlative of symptoms experienced by the user includes at least one of vital information or physical characteristics of the user. (0)

3. The method of claim 1, wherein the one or more sensors includes at least one of a microphone, a peripheral capillary oxygen saturation (SPO2) sensor, a heart rate sensor, an accelerometer, a gyroscope or a mattress sensor. (1) (0)

4. The method of claim 3, wherein the one or more sensors includes one or more microphones, the method further comprising: (2) (4)

capturing, using the one or more microphones, an audio signal indicative of the one or more symptoms of the user;

augmenting the audio signal by adjusting one or more frequencies of the audio signal;

extracting one or more features from a frame or subframe of the augmented audio signal; and

using the extracted features to train the symptom classifier, the disease classifier and the medication effectiveness classifier.

5. The method of claim 4, wherein augmenting the signal includes changing one or more characteristics of the signal. (0)

6. The method of claim 4, wherein extracting one or more features from the frame or subframe of the audio signal comprises calculating from the frame or subframe at least one of Mel Frequency Cepstral Coefficients (MFCC), Discrete Cosine Transform (DCT) coefficients, Fast Fourier Transform (FFT) coefficients, zero crossing rate, dynamic range, spectral flatness, spectral flux or self-learned autoencoder features. (0)

8. The method of claim 1, wherein the symptom, disease and medication effectiveness classifiers are convolutional neural networks. (0)

11. The method of claim 1, wherein the one or more sleep features are input into a sleep disorder classifier, and the output of the sleep disorder classifier is input into the disease classifier. (0)

12. The method of claim 1, wherein the output of the disease classifier is input into the medication effectiveness classifier, together with a trigger identified as causing a change in the one or more symptoms or the disease or the disease state from a baseline of previously determined one or more symptoms or disease or disease state. (1) (0)

16. The method of claim 1, wherein the device is a far field device. (1) (0)

7. (canceled) (0)

9. (canceled) (0)

10. (canceled) (0)

13. (canceled) (0)

18. A system comprising: (6) (4)

an output device;

one or more sensors;

one or more processors;

memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising: capturing, using the one or more sensors, signals including information about a user's symptoms;

collecting other data correlative of symptoms experienced by the user;

determining, using a symptom classifier with the signals and the other data as input, one or more symptoms of the user;

determining, using a disease classifier with the one or more symptoms and one or more sleep features as input, a disease or disease state of the user;

determining, using a medication effectiveness classifier with the disease or disease state as input, a medication effectiveness in suppressing the one or more symptoms or improving the determined disease state of the user; and

presenting, using the output device, data for the one or more symptoms, the disease, the disease state, or an indication of the medication effectiveness for the user.

19. The system of claim 18, wherein the other information correlative of symptoms experienced by the user includes at least one of vital information or physical characteristics of the user. (0)

20. The system of claim 18, wherein the one or more sensors includes at least one of a microphone, a peripheral capillary oxygen saturation (SPO2) sensor, a heart rate sensor, a gyroscope or a mattress sensor. (0)

21. The system of claim 18, wherein the system includes one or more microphones and the operations further comprise: (2) (4)

capturing, using the one or more microphones, an audio signal indicative of the one or more symptoms of the user;

augmenting the audio signal by adjusting one or more frequencies of the audio signal;

extracting one or more features from a frame or subframe of the augmented audio signal; and

using the extracted features to train the symptom classifier, the disease classifier and the medication effectiveness classifier.

22. The system of claim 21, wherein augmenting the signal includes changing one or more characteristics of the signal. (0)

23. The system of claim 21, wherein extracting the one or more features from the frame or subframe of the audio signal comprises calculating from the frame or subframe at least one of Mel Frequency Cepstral Coefficients (MFCC), Discrete Cosine Transform (DCT) coefficients, Fast Fourier Transform (FFT) coefficients, zero crossing rate, dynamic range, spectral flatness, spectral flux or self-learned autoencoder features. (0)

25. The method of claim 18, wherein the one or more sleep features are input into a sleep disorder classifier, and the output of the sleep disorder classifier is input into the disease classifier. (0)

26. The system of claim 18, wherein the output of the disease classifier is input into the medication effectiveness classifier, together with a trigger identified as causing a change in the one or more symptoms or the disease or the disease state from a baseline of previously determined one or more symptoms or disease or disease state. (1) (0)

30. The system of claim 18, wherein the system includes: (0) (5)

a housing having a first portion configured to be inserted inside an ear canal of a user and a second portion worn around the ear of the user;

a first microphone or microphone array disposed in the first portion of the housing;

a second microphone or microphone array disposed in the second portion of the housing;

and wherein the one or more sensors include at least one of a motion sensor, a peripheral capillary oxygen saturation (SPO2) sensor or a heart rate sensor disposed in the housing and configured to detect motion, oxygen levels and heart rate, respectively, of the user during a health-related event;

and wherein the one or more processors are coupled to the first and second microphones and the motion sensor, and configured to: obtain a first audio signal from the first microphone;

obtain a second audio signal from the second microphone;

obtain data from the one or more sensors; and

determine, based on the first audio signal, the second audio signal and the data, one or more health-related events for the user.

24. (canceled) (0)

Application US20200146623

Intelligent Health Monitoring

Patent Matrix® Search