Granted Patent B2

US 12,471,839 · App. 17/648,289 · Granted Nov 18, 2025

Inventors: Ziheng Wang (Sendai, JP); Keizo Sato (Sendai, JP); Ryoichi Nagatomi (Sendai, JP)

Assignee: TOHOKU UNIVERSITY

A61B5/4824A61B5/1118A61B5/6891A61B5/7264A61B5/7275G16H50/20G16H50/70

Abstract

Claims (32)

1 . A low back pain analysis device comprising:

furniture including a sensor that acquires gravity center movement data during a period in which a person is sitting on the furniture:

a processor; and

a storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by the processor, perform processing of:

receiving the gravity center movement data from the sensor;

processing the gravity center movement data from the sensor in real-time to obtain a unit classification of the gravity center movement data, including dividing the gravity center movement data for each unit of time during the period in which the person is sitting on the furniture;

performing clustering on the unit classification of the gravity center movement data;

identifying a movement pattern, including based on both a stable sitting state and a body movement based on the clustering on the unit classification of the gravity center movement data; and

determining a relationship between the pattern and a low back pain.

2 . The low back pain analysis device according to claim 1 , wherein the computer program instructions further perform processing of:

estimating a probability of the low back pain occurring in a person, who is a subject of analysis, using a frequency of appearance of the pattern; and

acquiring the frequency of appearance of the pattern based on the gravity center movement data of the person who is the subject of analysis.

3 . The low back pain analysis device according to claim 2 ,

wherein the frequency of appearance is a condition from an appearance pattern having a highest frequency of appearance to an appearance pattern having an N-th highest frequency of appearance (N is a predetermined integer of 1 or greater).

4 . The low back pain analysis device according to claim 2 , wherein the computer program instructions further perform processing of:

analyzing the pattern using a hidden Markov process to estimate an appearance pattern from fluctuating time series.

5 . The low back pain analysis device according to claim 2 , wherein the computer program instructions further perform processing of:

estimating the probability of the low back pain occurring in the person, who is the subject of analysis, wherein the estimating is performed using a machine learning model using the gravity center movement data.

6 . The low back pain analysis device according to claim 1 , wherein determining the relationship between the pattern and low back pain includes correlating a frequency of alternating appearance of the stable sitting state and body movement classifications with a probability of low back pain occurrence.

7 . The low back pain analysis device according to claim 1 , further comprising, based on the determined relationship, providing a warning to a user.

8 . The low back pain analysis device according to claim 1 , further comprising, based on the determined relationship, providing a predetermined exercise to a user.

9 . A low back pain analysis method, the method comprising:

acquiring gravity center movement data with a sensor included in furniture during a period in which a person is sitting on the furniture;

using a processor performing computer program instructions for:

receiving the gravity sensor movement data;

processing the gravity center movement data in real-time to obtain a unit classification of the gravity center movement data, including dividing the gravity center movement data for each unit of time during the period in which the person is sitting on the furniture;

performing clustering on the unit classification of the gravity center movement data;

identifying a movement pattern, including based on both a stable sitting state and a body movement based on the clustering on the unit classification of the gravity center movement data; and

determining a relationship between the pattern and a low back pain.

10 . The low back pain analysis method according to claim 9 , further comprising, using the processor for:

estimating a probability of the low back pain occurring in a person, who is a subject of analysis, using a frequency of appearance of the pattern, and

acquiring the frequency of appearance of the pattern based on the gravity center movement data of the person who is the subject of analysis.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (12)