# US 2021/0275073 A1 · Systems And Methods For Uroflowmetry

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0275073 A1
- Document ID: US20210275073A1
- Status: Published application
- Kind: A1
- Application number: 16/810,221
- Filed: 2020-03-05
- Published: 2021-09-09
- Earliest claimed: 2020-03-05
- Assignees: Emano Metrics, Inc.
- Applicants: Emano Metrics, Inc.
- Inventors: Bishara Charles Korkor, II; Alan Reid Hay; Edouard Alan Hay
- Web page: https://patentgrep.com/patent/US20210275073A1

## CPC

- A61B 5/208: {adapted to determine urine quantity, e.g. flow, volume}
- A61B 5/7267: {involving training the classification device}
- A61B 5/742: {using visual displays (displays for heart-related electrical signals, e.g. ECG, A61B5/339)}
- A61B 5/7475: {User input or interface means, e.g. keyboard, pointing device, joystick}
- G01F 1/666: {by detecting noise and sounds generated by the flowing fluid}
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/174: involving the use of two or more images
- G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00)
- A61B 5/202: {Assessing bladder functions, e.g. incontinence assessment}
- A61B 5/6887: {mounted on external non-worn devices, e.g. non-medical devices}
- A61B 5/6898: {Portable consumer electronic devices, e.g. music players, telephones, tablet computers}
- A61B 5/7203: {for noise prevention, reduction or removal}
- A61B 2562/0204: Acoustic sensors
- G01F 15/06: Indicating or recording devices
- G06T 2207/30004: Biomedical image processing
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G01F: MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system for uroflowmetry is disclosed. The system can include an audio device configured to obtain audio data of urination. The system can include a machine learning module with at least one processor and associated memory, wherein the system is configured to: process the audio data of urination via a machine learning model that is trained based on simulated urine flow data and associated audio data received from a urine flow simulator, and real urine flow data and associated audio data received from a urine flow measuring device, and output the processed audio data of urination to be used in uroflowmetry.

## Claims

### Claim 1

A system for uroflowmetry, the system comprising:
an audio device configured to obtain time-varying audio data of urination; and
a machine learning module with at least one processor and associated memory, wherein the machine learning module is configured to:
process the audio data of urination via a machine learning model that is trained based on simulated urine flow data and associated audio data received from a urine flow simulator, real urine flow data and associated audio data received from a urine flow measuring device, wherein the machine learning model is a recurrent model that operates on the time-varying audio data such that a state of the model is input to a subsequent state of the model to leverage time correlations in the time-varying audio data, wherein the time correlations indicate that a current flow rate of urination is dependent on a previous flow rate of urination, and
output the processed audio data of urination to be used in uroflowmetry.

### Claim 2 (depends on 1)

The system of claim 1, wherein the audio data of urination includes a sound recording of urine impacting a surface.

### Claim 3 (depends on 1)

The system of claim 1, wherein the urine flow measuring device comprises:
an imaging device configured to capture multiple image frames of urine flow over the time period; and
one or more processors and associated memory configured to:
apply an image segmentation algorithm on each of the image frames to obtain an image segment for each image frame, wherein the image segment includes image pixels associated with the urine flow, and
combine consecutive image segments to generate the real urine flow data, wherein the audio device is configured to obtain the associated real audio data of the urine flow.

### Claim 4 (depends on 3)

The system of claim 3, wherein the urine flow is associated with a human user.

### Claim 5 (depends on 3)

The system of claim 3, further comprising:
a toilet that receives the urine flow, wherein the imaging device includes two cameras arranged perpendicularly in a plane over the toilet.

### Claim 6 (depends on 1)

The system of claim 1, wherein the urine flow simulator comprises:
a basin that contains water and/or synthetic urine;
a pump configured to pump the urine from the basin at one or more volumetric flow rates;
a container that receives the urine from the pump to provide the simulated urine flow data; and
an audio device configured to obtain the audio data associated with the simulated urine flow data.

### Claim 7 (depends on 6)

The system of claim 6, further comprising:
a flow meter configured to measure volumetric flow rates of the urine;
a tube positioned between the basin and the container, wherein the tube carries the urine from the basin to the container;
a display to receive user input to operate the urine flow simulator; and
a processor configured to operate the pump to synchronize the volumetric flow rates and associated audio data of the urine.

### Claim 8 (depends on 6)

The system of claim 6, wherein the basin is temperature controlled.

### Claim 9 (depends on 6)

system of claim 6, wherein the urine flow simulator is portable.

### Claim 10 (depends on 5)

The system of claim 5, wherein the flow rate varies between about 0 and 50 ml/sec.

### Claim 11

A computer-implemented method for uroflowmetry, the method comprising:
obtaining time-varying audio data of urination from an audio device;
processing, via at least one controller, the audio data of urination via a machine learning model that is trained based on simulated urine flow data and associated audio data received from a urine flow simulator, and real urine flow data and associated audio data received from a urine flow measuring device, wherein the machine learning model is a recurrent model that operates on the time-varying audio data such that a state of the model is input to a subsequent state of the model to leverage time correlations in the time-varying audio data, wherein the time correlations indicate that a current flow rate of urination is dependent on a previous flow rate of urination, and
outputting the processed audio data of urination to be used in uroflowmetry.

### Claim 12 (depends on 11)

The method of claim 11, wherein the audio data of urination includes a sound recording of urine impacting a surface.

### Claim 13 (depends on 11)

The method of claim 11, wherein the urine flow measuring device comprises:
an imaging device configured to capture multiple image frames of urine flow over the time period;
one or more processors and associated memory configured to:
apply an image segmentation algorithm on each of the image frames to obtain an image segment for each image frame, wherein the image segment includes image pixels associated with the urine flow, and
combine consecutive image segments to generate the real urine flow data , wherein the audio device is configured to obtain the associated real audio data of the urine flow.

### Claim 14 (depends on 13)

The method of claim 13, wherein the urine flow is associated with a human user.

### Claim 15 (depends on 13)

The method of claim 13, further comprising:
receiving the urine flow at a toilet, wherein the imaging device includes two cameras arranged perpendicularly in a plane over the toilet.

### Claim 16 (depends on 11)

The method of claim 11, wherein the urine flow simulator comprises:
a basin that contains water and/or synthetic urine;
a pump configured to pump the urine from the basin at one or more volumetric flow rates;
a container that receives the urine from the pump to provide the simulated urine flow data; and
an audio device configured to obtain the audio data associated with the simulated urine flow data.

### Claim 17 (depends on 16)

The method of claim 16, wherein the urine flow simulator comprises:
a flow meter configured to measure volumetric flow rates of the urine;
a tube positioned between the basin and the container, wherein the tube carries the urine from the basin to the container;
a display to receive user input to operate the urine flow simulator, wherein the one or more processors are configured to operate the pump to synchronize the volumetric flow rates and associated audio data of the urine.

### Claim 18 (depends on 16)

The method of claim 16, wherein the basin is temperature controlled.

### Claim 19 (depends on 16)

The method of claim 16, wherein the urine flow simulator is portable.

### Claim 20 (depends on 16)

The method of claim 16, wherein the flow rate varies between about 0 and 50 ml/sec.

### Claim 21 (depends on 1)

The system of claim 1, wherein the machine learning model is further trained on toilet geometry, location and angle of the urine stream's impact upon the toilet's water surface, location and quality of the microphone, patient sex, urination position, and human physiological variation.

### Claim 22 (depends on 11)

The method of claim 11, wherein the machine learning model is further trained on toilet geometry, location and angle of the urine stream's impact upon the toilet's water surface, location and quality of the microphone, patient sex, urination position, and human physiological variation.
