KR-102964335-B1 - METHOD AND APPARATUS FOR EVALUATING PAIN

Abstract

A pain evaluation method comprises: a step in which an analysis device receives a brain activity image of a target animal; a step in which the analysis device preprocesses the activation signals of regions of interest in the brain activity image to extract features; a step in which the analysis device inputs the features into an analysis model; and a step in which the analysis device evaluates the pain of the target animal based on the output value of the analysis model.

Inventors

• 김선광
• 윤희라
• 박하늬
• 박명성

Assignees

• 경희대학교 산학협력단
• 주식회사 뉴로그린

Dates

Publication Date

20260513

Application Date

20230227

Claims (16)

1. A step in which the analysis device receives an image of the brain activity of the target animal; A step in which the analysis device preprocesses the activation signals of regions of interest in the brain activation image to extract features; The step of the above analysis device inputting the above features into an analysis model; and The above analysis device evaluates the pain of the target animal based on the output value of the analysis model; the method comprising: The above region of interest is a region indicating the activity of individual cells, and The above features include information regarding changes in the activation signal, and The above analysis model is a model trained based on training data, and is a model trained to classify a target animal into either a first state of feeling pain or a second state of not feeling pain based on input features. The information regarding the change in the above-mentioned activation signal includes information regarding the rate of increase or decrease in the deltaF or Zscore value obtained by normalizing the activation signal measured in any one of the following states: the movement state of the target animal, the non-movement state of the target animal, and the total state combining the movement state and the non-movement state of the target animal. Pain assessment methods.
2. delete
3. In paragraph 1, Information regarding the rate of increase or decrease in the above delta-F or Z-score value is a value calculated through the following mathematical formula (D i ), a pain evaluation method. [Mathematical Formula] In the above mathematical formula, i represents the index value of the region of interest. In the above mathematical formula, n represents the total number of regions of interest (total number of cells). In the above mathematical formula represents the deltaF form or Zscore form of the i-th region of interest activation signal in session A. In the above mathematical formula represents the deltaF Form or Zscore Form of the activation signal of the i-th region of interest in session B.
4. In paragraph 1, The above features further include the Pearson Correlation Coefficient between the activation signals of the regions of interest, a pain assessment method.
5. In paragraph 1, A pain assessment method in which the above-mentioned activation signal includes a calcium (Ca 2+ ) signal in the brain of the target animal.
6. delete
7. In paragraph 1, The above analysis model is a model trained to classify a target animal into one of the first state, the second state, and the third state based on input features, and The above third state is a state in which the target animal has been treated to induce pain or to reduce pain, and The above third state is one of the cases where it is different from the above first state and the above second state, where it is inseparable from the above first state, and where it is inseparable from the above second state. Pain assessment methods.
8. In Paragraph 7, The above pain-inducing treatment includes at least one of administering a substance to be tested for causing pain and performing surgery to be tested for causing pain, and The above pain-reducing treatment includes administering a drug with an analgesic effect, Pain assessment methods.
9. Input device for receiving brain activity images of a target animal; A computing device that preprocesses activation signals of regions of interest in the brain activation image to extract features, inputs the features into an analysis model, and evaluates the pain of the target animal based on the output value of the analysis model; and A storage device for storing the above analysis model; comprising The above region of interest is a region indicating the activity of individual cells, and The above features include information regarding changes in the activation signal, and The above analysis model classifies the target animal into either a first state of feeling pain or a second state of not feeling pain, based on the input features, and The information regarding the change in the above-mentioned activation signal includes information regarding the rate of increase or decrease in the deltaF or Zscore value obtained by normalizing the activation signal measured in any one of the following states: the movement state of the target animal, the non-movement state of the target animal, and the total state combining the movement state and the non-movement state of the target animal. Pain assessment device.
10. delete
11. In Paragraph 9, Information regarding the rate of increase or decrease in the above deltaF or Zscore value is a value calculated through the following mathematical formula (D i ), a pain assessment device. [Mathematical Formula] In the above mathematical formula, i represents the index value of the region of interest. In the above mathematical formula, n represents the total number of regions of interest (total number of cells). In the above mathematical formula represents the deltaF form or Zscore form of the i-th region of interest activation signal in session A. In the above mathematical formula represents the deltaF Form or Zscore Form of the activation signal of the i-th region of interest in session B.
12. In Paragraph 9, A pain evaluation device in which the above-mentioned activation signal includes a calcium (Ca 2+ ) signal from the brain of the target animal.
13. In Paragraph 9, The above features further include a Pearson Correlation Coefficient between the activation signals of the regions of interest, a pain assessment device.
14. delete
15. In paragraph 9 The above analysis model is a model trained to classify a target animal into one of the first state, the second state, and the third state based on input features, and The above third state is a state in which the target animal has been treated to induce pain or to reduce pain, and The above third state is one of the cases where it is different from the above first state and the above second state, where it is inseparable from the above first state, and where it is inseparable from the above second state. Pain assessment device.
16. In paragraph 15 The above pain-inducing treatment includes at least one of administering a substance to be tested for causing pain and performing surgery to be tested for causing pain, and The above pain-reducing treatment includes administering a drug with an analgesic effect, Pain assessment device.

Description

Method and apparatus for evaluating pain The technology described below relates to a method for evaluating pain using animal models. Animal pain models are an essential component in understanding pain mechanisms and developing effective therapeutic drugs or treatments. Research is ongoing to create animal pain models that most closely resemble the condition of pain patients. Conventional methods for assessing persistent pain have primarily relied on detecting changes in facial expressions associated with pain or on behavioral experiments utilizing traditional compensatory mechanisms. Figure 1 shows the overall process of an analysis device evaluating pain. Figure 2 is a flowchart of the process in which the analysis device evaluates pain. Figure 3 is an example of features extracted by the analysis device. Figure 4 shows the process of a researcher acquiring training data. Figure 5 is a flowchart of the process in which a researcher trains an analysis model. Figure 6 shows the characteristics that the third class can have. Figure 7 shows the results of analyzing the relationship between calcium signals and movement. Figure 8 shows the experimental results evaluating the performance of the analysis model. Figure 9 shows the experimental results evaluating the performance of the analysis model when a drug with no analgesic effect was administered. Figure 10 shows the results of analyzing pain when an anti-inflammatory drug was administered to a CFA-induced pain model. Figure 11 shows the results of measuring spontaneous pain in an anticancer drug-induced pain model. Figure 12 shows the results of measuring spontaneous pain in a Parkinson's disease-induced pain model. FIG. 13 is an example of the configuration of an analysis device. The technology described below may be subject to various modifications and may have various embodiments. Specific embodiments of the technology described below may be described in the drawings of the specification. However, this is for the purpose of explaining the technology described below and is not intended to limit the technology described below to specific embodiments. Accordingly, it should be understood that all modifications, equivalents, and substitutions that fall within the spirit and scope of the technology described below are included in the technology described below. In the terms used below, singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "includes" should be understood to mean that the described features, number, steps, actions, components, parts, or combinations thereof exist, and not to exclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Before providing a detailed description of the drawings, it is to clarify that the classification of components in this specification is merely based on the primary function each component is responsible for. That is, two or more components described below may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Furthermore, each component described below may additionally perform some or all of the functions of other components in addition to its own primary function, and it is obvious that some of the primary functions of each component may be exclusively performed by other components. Furthermore, in performing the method or operation method, each process constituting the method may occur differently from the specified order unless a specific order is clearly indicated in the context. That is, each process may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order. First, the analysis device explains the overall process of evaluating pain. Figure 1 shows the entire process of an analysis device (100) evaluating pain. The analysis device (100) can receive a brain activity image of a target animal. The analysis device (100) can extract features by preprocessing the activation signal of a Region of Interest (ROI) in the brain activity image. The analysis device (100) can input the features into an analysis model. The analysis device (100) can evaluate the pain of the target animal based on the output value of the analysis model. The region of interest may be an area representing the activity of individual cells. Features include information regarding changes in activation signals. The process by which the analysis device evaluates pain is explained in detail below. Figure 2 shows a flowchart of the process (200) in which an analysis device evaluates pain. The analysis device can receive brain activity images of the target animal (210). The target animal may be an animal used for pain assessment. The animal used for pain assessment may include various animals. The animal used for pain assessment includes vario