Disease prediction model construction apparatus and method, and disease prediction apparatus

• US 10,729,383 B2
• Filed: 08/15/2016
• Issued: 08/04/2020
• Est. Priority Date: 11/16/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Shin, Eui Seok, Park, Jin Young, Lee, Seung Jun
• Primary Examiner(s): Winakur, Eric F
• Assistant Examiner(s): Fardanesh, Marjan
• Application Number:
  US15/237,012
• Publication Number:
  US 20170135645A1
• Time in Patent Office: 1,450 Days
• Field of Search: None
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/1455 using optical sensors, e.g. spectral photometrical oximeters
• CPC Class Codes: A61B 5/4848 Monitoring or testing the effects of treatment, e.g. of medication
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7405 using sound
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/7455 characterised by tactile indication, e.g. vibration or electrical stimulation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A disease prediction model construction apparatus is provided. The disease prediction model construction apparatus may include a spectral data acquisition unit that emits near-infrared rays toward a skin of a subject to acquire near-infrared spectral data and a prediction model construction unit that constructs a disease prediction model based on a time-blood glucose graph generated from the acquired near-infrared spectral data.

Claims

1. A disease prediction model construction apparatus comprising:

a spectral data acquisition circuitry configured to emit near-infrared rays toward a skin of a subject, and acquire near-infrared spectral data based on the emitted near-infrared rays; and

a prediction model construction circuitry configured to construct a disease prediction model that analyzes an impaired glucose tolerance (IGT) of the subject, based on a correlation between an area under a curve (AUC) of a time-blood glucose graph and the acquired near-infrared spectral data, the time-blood glucose graph being a graph indicating a change in blood glucose of the subject for a predetermined time after the subject takes glucose in a fasting state.

2. The disease prediction model construction apparatus according to claim 1, further comprising a preprocessing circuitry configured to remove noise from the acquired near-infrared spectral data.

3. The disease prediction model construction apparatus according to claim 2, wherein the preprocessing circuitry is further configured to use a Savitzky-Golay filter algorithm to remove the noise from the acquired near-infrared spectral data.

4. The disease prediction model construction apparatus according to claim 1, wherein the prediction model construction circuitry is further configured to determine the correlation by using the acquired near-infrared spectral data as an independent variable of a predefined regression analysis algorithm and using the area under the curve as a dependent variable.

5. The disease prediction model construction apparatus according to claim 4, wherein the predefined regression analysis algorithm includes at least one of a partial least square regression algorithm, a principal components regression algorithm, and a multivariate regression algorithm.

6. The disease prediction model construction apparatus according to claim 1, further comprising a feature information input circuitry configured to receive one or more of sex, age, height, and body weight of the subject as feature information,

wherein the prediction model construction circuitry is further configured to construct the disease prediction model based on the feature information of the subject.

7. A disease prediction model construction method comprising:

emitting near-infrared rays toward a skin of a subject, and acquiring near-infrared spectral data based on the emitted near-infrared rays; and

constructing a disease prediction model that analyzes an impaired glucose tolerance (IGT) of the subject, based on a correlation between an area under a curve (AUC) of a time-blood glucose graph and the acquired near-infrared spectral data, the time-blood glucose graph being a graph indicating a change in blood glucose of the subject for a predetermined time after the subject takes glucose in a fasting state.

8. The method according to claim 7, wherein the constructing the disease prediction model comprises determining the correlation by using the acquired near-infrared spectral data as an independent variable of a predefined regression analysis algorithm and by using the area under the curve as a dependent variable.