# US 2026/0026769 A1 · Lung sound analysis system

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

- Number: US 2026/0026769 A1
- Document ID: US20260026769A1
- Status: Published application
- Kind: A1
- Application number: 19/346,710
- Filed: 2025-10-01
- Published: 2026-01-29
- Earliest claimed: 2025-10-01
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Masao HIGUCHI; Mitsuru NOMA; Reishi KONDO; Yumi ARAI
- Web page: https://patentgrep.com/patent/US20260026769A1

## CPC

- A61B 7/003: {Detecting lung or respiration noise}
- A61B 5/087: Measuring breath flow
- A61B 7/04: Electric stethoscopes
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A61B 2562/0204: Acoustic sensors
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A lung sound analysis system includes: an acquisition unit that obtains time-series acoustic signals including lung sounds from a heart failure patient; a determination unit that identifies the pause phase of the patient's breathing; a dividing unit that separates the time-series signals into those during the pause phase and those during other phases, based on the determination; a calculation unit that computes an index value representing the quality of the signals outside the pause phase, using the intensity of signals from both phases after separation; and a warning unit that issues alerts based on the calculated index value. The system supports medical decision making for healthcare professionals monitoring heart failure patients.

## Claims

### Claim 1

A lung sound analysis device comprising:
a memory containing program instructions; and a processor coupled to the memory, wherein the processor is configured to execute the program instructions to:
acquire time-series acoustic signals including lung sounds of a subject;
determine a pause phase of breathing of the subject;
divide the time-series acoustic signals into time-series acoustic signals in a period of the pause phase of the subject and time-series acoustic signals in a period other than the pause phase, according to a result of the determination;
calculate an index value representing quality of the time-series acoustic signals in the period other than the pause phase, from intensity of the time-series acoustic signals in the period of the pause phase and intensity of the time-series acoustic signals in the period other than the pause phase after the division;
give warning based on the calculated index value;
input the lung sounds of the subject into a first normal model trained using only lung sound data without lung sound abnormalities of the subject;
acquire a probability that the lung sounds of the subject are abnormal from the first normal model;
determine that the lung sounds of the subject are abnormal lung sounds based on the probability exceeding a first threshold; and
determine that the lung sounds of the subject are normal lung sounds based on the probability being equal to or less than the first threshold.

### Claim 2 (depends on 1)

The lung sound analysis device according to claim 1, wherein the processor is further configured to execute the instructions to detect abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the division using a machine learning model.

### Claim 3 (depends on 2)

The lung sound analysis device according to claim 2, wherein the processor is further configured to execute the instructions to detect background noise from the time-series acoustic signals in the period of the pause phase after the division.

### Claim 4 (depends on 3)

The lung sound analysis device according to claim 3, wherein the processor is further configured to execute the instructions to remove the detected background noise from the time-series acoustic signals in the period other than the pause phase after the division.

### Claim 5 (depends on 4)

The lung sound analysis device according to claim 4, wherein the detection includes detecting the abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the removal of the background noise.

### Claim 6

A lung sound analysis method comprising:
acquiring time-series acoustic signals including lung sounds of a subject;
determining a pause phase of breathing of the subject;
dividing the time-series acoustic signals into time-series acoustic signals in a period of the pause phase of the subject and time-series acoustic signals in a period other than the pause phase, according to a result of the determination;
calculating an index value representing quality of the time-series acoustic signals in the period other than the pause phase, from intensity of the time-series acoustic signals in the period of the pause phase and intensity of the time-series acoustic signals in the period other than the pause phase after the division; giving warning based on the calculated index value;
inputting the lung sounds of the subject into a first normal model trained using only lung sound data without lung sound abnormalities of the subject;
acquiring a probability that the lung sounds of the subject are abnormal from the first normal model;
determining that the lung sounds of the subject are abnormal lung sounds based on the probability exceeding a first threshold; and
determining that the lung sounds of the subject are normal lung sounds based on the probability being equal to or less than the first threshold.

### Claim 7 (depends on 6)

The lung sound analysis method according to claim 6, further comprising detecting abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the division.

### Claim 8 (depends on 7)

The lung sound analysis method according to claim 7, further comprising detecting background noise from the time-series acoustic signals in the period of the pause phase after the division.

### Claim 9 (depends on 8)

The lung sound analysis method according to claim 8, further comprising removing the detected background noise from the time-series acoustic signals in the period other than the pause phase after the division.

### Claim 10

A non-transitory computer-readable medium storing thereon a program comprising instructions for causing a computer to execute processing to:
acquire time-series acoustic signals including lung sounds of a subject;
determine a pause phase of breathing of the subject;
divide the time-series acoustic signals into time-series acoustic signals in a period of the pause phase of the subject and time-series acoustic signals in a period other than the pause phase, according to a result of the determination;
calculate an index value representing quality of the time-series acoustic signals in the period other than the pause phase, from intensity of the time-series acoustic signals in the period of the pause phase and intensity of the time-series acoustic signals in the period other than the pause phase after the division;
give warning based on the calculated index value;
input the lung sounds of the subject into a first normal model trained using only lung sound data without lung sound abnormalities of the subject;
acquire a probability that the lung sounds of the subject are abnormal from the first normal model;
determine that the lung sounds of the subject are abnormal lung sounds based on the probability exceeding a first threshold; and
determine that the lung sounds of the subject are normal lung sounds based on the probability being equal to or less than the first threshold.

### Claim 11 (depends on 1)

The lung sound analysis device according to claim 1, wherein the processor is further configured to execute the instructions to
input the lung sounds of the subject into a second normal model trained using second lung sound data with lung sound abnormalities of the subject;
acquire a second probability that the lung sounds of the subject are abnormal from the second normal model;
determine that the lung sounds of the subject are a same type of abnormality as the lung sound abnormalities in the second lung sound data used for training the second normal model based on the second probability exceeding a second threshold; and
determine that the lung sounds of the subject are either a different type of abnormality from the lung sound abnormalities in the second lung sound data used for training the second normal model or normal lung sounds based on the second probability being equal to or less than the second threshold.

### Claim 12 (depends on 6)

The lung sound analysis method according to claim 6, further comprising
inputting the lung sounds of the subject into a second normal model trained using second lung sound data with lung sound abnormalities of the subject;
acquiring a second probability that the lung sounds of the subject are abnormal from the second normal model;
determining that the lung sounds of the subject are a same type of abnormality as the lung sound abnormalities in the second lung sound data used for training the second normal model based on the second probability exceeding a second threshold; and
determining that the lung sounds of the subject are either a different type of abnormality from the lung sound abnormalities in the second lung sound data used for training the second normal model or normal lung sounds based on the second probability being equal to or less than the second threshold.

### Claim 13 (depends on 10)

The non-transitory computer-readable storage medium according to claim 10, wherein the instructions further cause the computer to execute processing to
input the lung sounds of the subject into a second normal model trained using second lung sound data with lung sound abnormalities of the subject;
acquire a second probability that the lung sounds of the subject are abnormal from the second normal model;
determine that the lung sounds of the subject are a same type of abnormality as the lung sound abnormalities in the second lung sound data used for training the second normal model based on the second probability exceeding a second threshold; and
determine that the lung sounds of the subject are either a different type of abnormality from the lung sound abnormalities in the second lung sound data used for training the second normal model or normal lung sounds based on the second probability being equal to or less than the second threshold.
