Apparatus and method for predicting potential change of coronary artery calcification (CAC) level

Patent metadata

Field	Value
Publication number	US-9324035-B2
Application number	US-201313835855-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Mar 15, 2012
Publication date	Apr 26, 2016
Grant date	Apr 26, 2016

Abstract

An apparatus and a method predict a patient's potential change of Coronary Artery Calcification (CAC) level using various risk factors including a Coronary Artery Calcification Score (CACS). The apparatus includes a receiving unit, a cluster determining unit, a risk factor score extracting unit, a prediction model storage unit, a prediction model learning unit, and a predicting unit, and the method includes a receiving process, a risk factor score extracting process, and an operation performing process.

First claim

What is claimed is:

1. An apparatus for predicting a potential change of a Coronary Artery Calcification (CAC) level, the apparatus comprising:
a receiving processor configured to receive a patient's medical test data relating to CAC and corresponding operation information;
a cluster determining processor configured to determine a cluster to which the patient's medical test data belong based on a characteristic of the patient;
a risk factor score extracting processor configured to extract a risk factor score from the patient's medical test data;
a prediction model storage processor configured to store a plurality of prediction models used for predicting a potential CAC level;
a prediction model learning processor configured to perform machine learning by applying the extracted risk factor score to a prediction model corresponding to the determined cluster to which the patient's medical test data belong among the plurality of prediction models; and
a predicting processor configured to obtain an outcome by applying the extracted risk factor score to the prediction model corresponding to the determined cluster to which the patient's medical test data belong,
wherein the extracted risk factor score comprises a Coronary Artery Calcification Score (CACS) and a corresponding measurement date,
wherein the prediction model learning processor is further configured to classify all CACSs into at least two sections; and
each section of the at least two sections is representative of a specific CAC level or a specific range of CAC levels, and
wherein the prediction model learning processor is further configured to:
assign a first outcome to the patient's medical test data when a CAC level corresponding to a last measured CACS of the patient's medical test data is higher than a CAC level corresponding to a first measured CACS of the patient's medical test data; and
assign a second outcome to the patient's medical test data in other cases.

2. The apparatus of claim 1 , wherein the prediction model learning processor is further configured to perform the machine learning when the operation information is a learning instruction; and
the predicting processor is further configured to obtain the outcome when the operation information is a predicting instruction.

3. The apparatus of claim 1 , wherein when the predicting processor obtains the first outcome when the patient's medical test data is received with the predicting instruction, a CAC level of the patient is predicted to increase; and
when the predicting processor obtains the second outcome when the patient's medical test data is received with the predicting instruction, the CAC level of the patient is predicted not to increase.

4. The apparatus of claim 1 , wherein the extracted risk factor comprises at least two Coronary Artery Calcification Score (CACS) scores; and
the prediction model learning processor is further configured to perform the machine learning using the at least two CACS scores.

5. A method of predicting a potential change of a Coronary Artery Calcification (CAC) level, the method comprising:
receiving a patient's medical test data relating to CAC and corresponding operation information;
determining a cluster to which the patient's medical test data belong based on a characteristic of the patient;
extracting from the patient's medical test data a risk factor score of a risk factor of a risk factor set of the determined cluster to which the patient's medical test data belong; and
selectively performing machine learning or performing prediction using a prediction model according to the operation information,
wherein the extracted risk factor score comprises a Coronary Artery Calcification Score (CACS) and a corresponding measurement date, and
wherein the performing of the machine learning comprises classifying all CACSs into at least two sections; and
each section of the at least two sections is representative of a specific CAC level or a specific range of CAC levels, and
wherein the performing of the machine learning further comprises:
assigning a first outcome to the patient's medical test data when a CAC level corresponding to a last measured CACS of the patient's medical test data is higher than a CAC level corresponding to a first measured CACS of the patient's medical test data; and
assigning a second outcome to the patient's medical test data in other cases.

6. The method of claim 5 , wherein the selectively performing of the machine learning or performing the prediction using a prediction model comprises:
when the operation information is a learning instruction, performing the machine learning by applying the extracted risk factor score to a prediction model corresponding to the determined cluster to which the patient's medical test data belong among a plurality of prediction models; and
when the operation information is a predicting instruction, performing the prediction using a prediction model by applying the extracted risk factor score to the prediction model corresponding to the determined cluster to which the patient's medical test data belong.

7. The method of claim 5 , wherein when the performing of the prediction using a prediction model obtains the first outcome when the patient's medical test data is received with the predicting instruction, a CAC level of the patient is predicted to increase; and
when the performing of the prediction using a prediction model obtains the second outcome when the patient's medical test data is received with the predicting instruction, the CAC level of the patient is predicted not to increase.

8. The method of claim 5 , wherein the determining of a cluster to which the patient's medical test data belong comprises:
determining that the patient's medical test data belong to a first cluster when the patient's medical test data comprises a Coronary Artery Calcification Score (CACS) of 0; and
determining that the patient's medical test data belong to a second cluster when the patient's medical test data comprises a CACS greater than 0.

9. An apparatus for predicting a potential change of a Coronary Artery Calcification (CAC) level, the apparatus comprising:
a receiving processor configured to receive a patient's medical test data relating to CAC;
a cluster determining processor configured to determine a cluster to which the patient's medical test data belong based on a Coronary Artery Calcification Score (CACS) of the patient's medical test data;
a risk factor score extracting processor configured to extract from the patient's medical test data a risk factor score of a risk factor of a risk factor set of the determined cluster to which the patient's medical test data belong;
a prediction model storage processor configured to store a plurality of prediction models used for predicting a potential change of a CAC level; and
a predicting processor configured to predict a potential change of a CAC level by applying the extracted risk factor score to a prediction model corresponding to the determined cluster to which the patient's medical test data belong among the plurality of prediction models,
wherein the extracted risk factor score comprises a Coronary Artery Calcification Score (CACS) and a corresponding measurement date,
wherein the prediction model learning processor is further configured to classify all CACSs into at least two sections; and
each section of the at least two sections is representative of a specific CAC level or a specific range of CAC levels, and
wherein the prediction model learning processor is further configured to:
assign a first outcome to the patient's medical test data when a CAC level corresponding to a last measured CACS of the patient's medical test data is higher tha

Assignees

• Samsung Electronics Co Ltd
• Samsung Life Welfare Found

Inventors

• Lee Ji-Hyun
• Kam Hye-Jin
• Kim Ha-Young
• Yoo Sang-Hyun
• Choi Yoonho
• Kang Mira
• Park Jeongeuy
• Sung Jidong
• Shin Heeyoung
• Cho Sungwon
• Cho Soojin

Classifications

• G06F19/345

  Physics · mapped topic

• G06N99/005 Primary

  Physics · mapped topic

• G06F19/3431

  Physics · mapped topic

• G16H50/70 Primary

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G06N20/00

  Machine learning · CPC title