A method and device for collecting vital sign data

By automatically acquiring vital sign data from monitors through image acquisition and recognition technology, the problem of anesthesia information systems being unable to automatically record data due to closed monitor interfaces has been solved, thus improving the work efficiency and data accuracy of anesthesiologists.

CN112336305BActive Publication Date: 2024-11-15GUIYANG LONGMASTER INFORMATION & TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011055257.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-30
Publication Date
2024-11-15
Estimated Expiration
2040-09-30

AI Technical Summary

Technical Problem

The existing monitor interface is not open, and the anesthesia information system cannot automatically read and record the monitor's vital signs data, which increases the workload of anesthesiologists and makes it difficult to guarantee accuracy.

Method used

The system automatically acquires vital signs data by acquiring images from the monitor's interface using an image acquisition device, identifying vital signs data using the monitor's image classifier and digital classifier, and sending the data to the monitor.

Benefits of technology

This reduces the workload of anesthesiologists who frequently need to input vital signs data, improves work efficiency, and ensures data accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112336305B_ABST
    Figure CN112336305B_ABST
Patent Text Reader

Abstract

The present application discloses a method and device for collecting vital sign data, which includes sending a timed collection instruction to an image collector; obtaining a first image collected by the image collector; identifying a monitor image in the first image; if the identification is successful, obtaining first vital sign data in the first image; and sending the first vital sign data to a monitor, so as to achieve the purpose that an anesthesia information system can automatically obtain the monitor vital sign data even if the monitor interface is not open. The present application collects vital sign data on a monitor through an image collection device, identifies vital sign data using recognition technology, and transmits the data to an anesthesia information system for confirmation by a doctor at regular intervals. The doctor only needs to confirm whether the data is correct, which reduces the workload of the anesthesiologist for frequent input and improves the work efficiency of the anesthesiologist.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for collecting vital sign data. Background Art

[0002] The anesthesiologist in the operating room needs to record the vital signs data (diastolic blood pressure, systolic blood pressure, mean blood pressure, heart rate, body temperature, respiratory rate, blood oxygen saturation) of the surgical patient every five minutes. These vital signs are measured by the monitor. Usually, the monitor manufacturer will provide an interface for third parties to use, but obtaining the interface requires a confidentiality agreement with the manufacturer. Since there are many monitor manufacturers, the implementation and calling methods of each manufacturer's interface are not uniform, and the surgical anesthesia information system needs to be connected one by one. In addition, some monitor manufacturers no longer provide interfaces to other companies. Therefore, the workload and complexity of the surgical anesthesia information system to read the vital signs data through the monitor interface are large. In addition, the monitors used in the operating rooms of some hospitals were purchased early and do not support reading vital signs data through the interface.

[0003] If the anesthesia information system cannot automatically read and record the vital signs data of surgical patients measured by the monitor, the anesthesiologist will need to manually enter the multiple vital signs data of surgical patients measured by the monitor into the surgical anesthesia information system at regular intervals, which will undoubtedly increase the workload and it is difficult to guarantee the accuracy. Summary of the invention

[0004] The present application provides a method and device for collecting vital sign data to solve the problem that the interface of the existing monitor is not open and the anesthesia information system cannot automatically read and record the vital sign data of the monitor.

[0005] In a first aspect, to achieve the above-mentioned purpose, the present application provides a method for collecting vital sign data, the method comprising:

[0006] Sending a timing acquisition instruction to the image collector;

[0007] Acquire a first image acquired by the image collector;

[0008] identifying a monitor image within the first image;

[0009] If the recognition is successful, obtaining first vital sign data in the first image;

[0010] The first vital sign data is sent to a monitor.

[0011] Further, identifying the monitor image in the first image includes:

[0012] Get the monitor image classifier;

[0013] A monitor image within the first image is identified by the monitor image classifier.

[0014] Furthermore, if the recognition is successful, obtaining first vital sign data in the first image includes:

[0015] Extracting the vital sign data in the first image to obtain a vital sign data extraction set;

[0016] Get a digital classifier;

[0017] The first vital sign data is acquired by identifying the vital sign data extraction set through the digital classifier.

[0018] Furthermore, after identifying the monitor image in the first image, the method further includes:

[0019] If the monitor image recognition is unsuccessful, a second image from the previous recognition is acquired.

[0020] Furthermore, after acquiring the second image recognized last time, the method further includes:

[0021] Confirm whether the monitor image corresponding to the second image is recognized successfully.

[0022] In a second aspect, the present application further provides a device for collecting vital sign data, the device comprising:

[0023] An instruction sending unit, used for sending a timing acquisition instruction to the image collector;

[0024] An image acquisition unit, used to acquire a first image acquired by the image collector;

[0025] an identification unit, configured to identify a monitor image within the first image;

[0026] a vital sign data acquisition unit, configured to acquire first vital sign data in the first image if the recognition is successful;

[0027] The vital sign data sending unit is used to send the first vital sign data to a monitor.

[0028] Furthermore, the identification unit is also used for:

[0029] Get the monitor image classifier;

[0030] A monitor image within the first image is identified by the monitor image classifier.

[0031] Furthermore, the vital sign data acquisition unit is also used for:

[0032] Extracting the vital sign data in the first image to obtain a vital sign data extraction set;

[0033] Get a digital classifier;

[0034] The first vital sign data is acquired by identifying the vital sign data extraction set through the digital classifier.

[0035] Furthermore, the image acquisition unit is also used for:

[0036] If the monitor image recognition is unsuccessful, a second image from the previous recognition is acquired.

[0037] Furthermore, the identification unit is also used for:

[0038] Confirm whether the monitor image corresponding to the second image is recognized successfully.

[0039] In a third aspect, to achieve the above-mentioned purpose, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an acquirer, implements the steps of any one of the methods for collecting vital sign data in the first aspect.

[0040] In a fourth aspect, to achieve the above-mentioned purpose, the present application provides a computer device, including a memory, an acquirer, and a computer program stored in the memory and executable on the acquirer, wherein when the acquirer executes the program, the steps of any method for collecting vital sign data in the first aspect are implemented.

[0041] It can be seen from the above technical solutions that the embodiment of the present application provides a method and device for collecting vital sign data, which can achieve the purpose of the anesthesia information system automatically obtaining the monitor vital sign data even if the monitor interface is not open, by sending a timed collection instruction to an image collector; obtaining a first image collected by the image collector; identifying the monitor image in the first image; if the recognition is successful, obtaining the first vital sign data in the first image; and sending the first vital sign data to the monitor. The present application collects vital sign data on the monitor through an image collection device, identifies the vital sign data using recognition technology, and transmits the data to the anesthesia information system for the doctor to confirm at regular intervals. The doctor only needs to confirm whether the data is correct, which reduces the workload of the anesthesiologist for frequent input and improves the work efficiency of the anesthesiologist.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A schematic diagram of a flow chart of a method for collecting vital sign data provided in an embodiment of the present application;

[0045] Figure 2 A diagram of the monitor interface provided in the embodiment of the present application;

[0046] Figure 3 A vital sign data table of an anesthesia information system provided in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of the structure of the vital sign data collection provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following detailed description of the present application will make the features and advantages of the present application clearer and more explicit.

[0049] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.

[0050] In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "back", "left" and "right" indicate positions or positional relationships based on the working state of the present application, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" and "fourth" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0051] In order to solve the above problems, the present application provides a method and device for collecting vital sign data. The specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0052] Figure 1 A flow chart of a method for collecting vital sign data provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes steps S1001 to S1003, and the method is applied to a processor.

[0053] S101: Sending a timing acquisition instruction to an image acquisition device.

[0054] In practice, the anesthesiologist in the operating room needs to record the patient's vital signs (diastolic blood pressure, systolic blood pressure, mean blood pressure, heart rate, body temperature, respiratory rate, and blood oxygen saturation) every five minutes. These vital signs are measured by a monitor. In order to facilitate the surgeon and anesthesiologist to check and record the patient's vital signs at any time, the monitor is usually installed in a conspicuous position that is not easily blocked.

[0055] Limited by the instrument interface, this application uses an image collector to collect the vital sign data displayed on the monitor interface. The image collector can be a camera, etc., which can be fixed at a fixed angle or can be moved and rotated. The monitor is usually in a fixed position, and the monitor has obvious appearance characteristics, which makes it easy to locate and identify the monitor in the video collected by the camera. The operating room environment has good, bright and stable light, which is conducive to the camera to collect data. The image collector is connected to the processor, receives the timing acquisition instruction sent by the processor, and starts the image acquisition work according to the timing acquisition instruction. The timing acquisition instruction is a preset value and is performed according to specific surgical requirements. In addition, it is necessary to preset the standard range of vital sign data. Vital signs have a normal value range, such as body temperature is 35-42 degrees Celsius, and the normal body temperature is 36.2-37.3 degrees Celsius. If the collected body temperature data exceeds the range of 35-42 degrees Celsius, a warning is required, and the doctor can take corresponding measures in time.

[0056] S102: Acquire a first image acquired by the image collector.

[0057] S103: Identify a monitor image in the first image.

[0058] During the specific implementation, the image acquisition device is aimed at the monitor to capture the first image. The first image should contain the monitor image and the vital sign data in the monitor interface. However, other situations may arise during the specific implementation, such as obstructions, etc. In this case, there will be color spots in the collected monitor image, or the monitor position will be offset, and the collected monitor image will be incomplete. Therefore, the next step is to identify the monitor image in the first image.

[0059] In a specific implementation, the step of identifying the monitor image in the first image includes:

[0060] S301: Obtain a monitor image classifier.

[0061] S302: Identify a monitor image in the first image by using the monitor image classifier.

[0062] The monitor image classifier is a trained classifier. To train the monitor classifier, a training set of the monitor must be established first. The training set is divided into positive samples and negative samples. All samples are grayscale images. The size of the positive sample image needs to be fixed, generally about 40*40. The size of the negative sample is not fixed, and the number of negative samples is more than the positive sample. After the training set of the monitor is generated, a resource record file is generated, including generating a positive sample resource record file and a negative sample resource record file. Then, the resource record file is converted into a sample vec file, and finally the classifier is trained using a related program, such as using the opencv_traincascade.exe program provided by opencv to train the classifier to obtain a monitor image classifier.

[0063] After obtaining the monitor image classifier, the monitor image in the first image is identified by it. If the monitor image recognition is successful, that is, the outline of the monitor appears at the pixel position in the image, the monitor as a whole appears in the first image, and there are no large color blocks in the first image, then the next step is to extract the vital sign data in the monitor image. If the recognition is unsuccessful, the possible reasons are analyzed and the analysis results are reported to the doctor for timely adjustment.

[0064] S104: If the image recognition of the monitor is successful, first vital sign data in the first image is obtained.

[0065] Specifically, the first image is first converted into grayscale values, and then converted into a binary image, and then contour detection is performed on the binary image. Contour detection represents the connected area in the binary image with a bunch of points. The default contour check will return a sequence of points, so that this sequence forms a figure that surrounds all the points in the connected area, such as four points forming a rectangle. Since there are two circles in the number 8, the default contour check will detect both circles, and 8 will have three contours. The same may also happen with the numbers 4, 6, and 9. Therefore, it is necessary to specify that the findContours() function only searches for the outermost contour, without paying attention to any contours that may appear inside. After detecting the contours, use the contours iterator to traverse each contour, find and draw the minimum matrix that surrounds the contour. However, the rectangle drawn by the above method is a rotated rectangle, so choose to use boundingRect() to draw the rectangle.

[0066] Since contour detection is not necessarily performed in the order given by the numbers on the interface, when detecting contours, it is necessary to record the coordinates of the given numbers, sort them according to the x, y coordinates, and organize the order of the numbers.

[0067] Since the rectangles drawn in the same row using the above method are located in the same horizontal plane, the coordinates of a certain point can be directly compared. After the numbers are sorted, ROI can be used to cut each number, and the cut numbers are placed in the image array in order. Finally, the numbers cut according to the contour line are placed in the program file, and then the pixel-by-pixel traversal method is used for comparison to complete the extraction of the first vital sign data.

[0068] In another embodiment, the first image may be cut into small pictures first, and then the vital sign numbers in each small picture may be extracted, which will not be described in detail here.

[0069] In specific implementation, if the monitor image recognition is successful, the vital sign data in the monitor image is extracted, which may also include:

[0070] S401: Extract vital sign data in the first image to obtain a vital sign data extraction set.

[0071] S402: Obtain a digital classifier.

[0072] S403: Acquire first vital sign data by identifying the vital sign data extraction set through the digital classifier.

[0073] That is, the vital sign data in the first image can be extracted by the above method, and then the first vital sign data can be obtained by using the trained digital classifier to identify the vital sign data, and the first vital sign data is a numerical value corresponding to each parameter in the monitor image interface. The training of the digital classifier can refer to the training process of the monitor image classifier, which will not be repeated here.

[0074] S105: Sending the first vital sign data to a monitor.

[0075] After the processor obtains the first vital sign data, before sending it to the anesthesia monitor, it is necessary to compare the first vital sign data with the normal vital sign data range to determine whether it is within the range. If it is out of range, a warning mark is added to the corresponding data to prompt the doctor. The anesthesia information system receives the relevant vital sign data, and the doctor confirms whether the vital sign data collected this time is the same as the data displayed on the monitor, whether the vital sign data is within the normal value range, and whether it is the patient's current real vital sign data, reducing the workload of the anesthesiologist for frequent input.

[0076] S106: If the image recognition of the monitor is unsuccessful, a second image recognized in the previous time is acquired.

[0077] During the specific implementation process, since the image acquisition device may be blocked or offset, or the monitor may move, it is necessary to analyze the cause of the failure and prompt the doctor.

[0078] After obtaining the second image recognized last time, it is necessary to confirm whether the monitor image recognition corresponding to the second image is successful. If it fails, it is further determined whether the operation is over. If the operation is over, the process ends. If the operation is not over, it returns to step S101 to continue image acquisition.

[0079] If the monitor image corresponding to the second image is successfully recognized, the first image is compared with the second image to analyze the reason why the monitor image recognition in the first image is unsuccessful.

[0080] Specifically include:

[0081] Determine whether there is a large color block in the first image, and the area of ​​the color block covers the monitor area in the second image. If so, the image collector is blocked;

[0082] If not, then find out whether there is a similar area between the first image and the second image, if not, then there are other reasons;

[0083] If yes, then confirm whether the coordinates of the similar areas are the same. If they are the same, the image collector may be blocked;

[0084] If not, the image collector or the monitor may be displaced, causing the image collector to be unable to align with the monitor.

[0085] In specific implementation, if the image collector or monitor has not moved, the content of the two images captured in the same area should be the same. Cut out part of the area outside the monitor position in the second image, and match the image content of this area with the image content of the position with the same coordinates in the first image. By cutting out pictures of different sizes and different areas, matching is performed multiple times. If one can match, it proves that the camera may not have moved. However, the monitor was not identified this time, and the possible reason is that the monitor was blocked.

[0086] Corresponding to the embodiment of the remote consultation method provided in the present application, the present application also provides an embodiment of a device for collecting vital sign data. Figure 4 , is a schematic diagram of the structure of a device for collecting vital sign data provided in an embodiment of the present application, the device comprising:

[0087] The instruction sending unit 100 is used to send a timing acquisition instruction to the image collector;

[0088] An image acquisition unit 200 is used to acquire a first image acquired by the image acquisition device;

[0089] An identification unit 300, configured to identify a monitor image in the first image;

[0090] A vital sign data acquisition unit 400, configured to acquire first vital sign data in the first image if the recognition is successful;

[0091] The vital sign data sending unit 500 is used to send the first vital sign data to a monitor.

[0092] Furthermore, the identification unit 300 is also used for:

[0093] Get the monitor image classifier;

[0094] A monitor image within the first image is identified by the monitor image classifier.

[0095] Furthermore, the vital sign data acquisition unit 400 is also used for:

[0096] Extracting the vital sign data in the first image to obtain a vital sign data extraction set;

[0097] Get a digital classifier;

[0098] The first vital sign data is acquired by identifying the vital sign data extraction set through the digital classifier.

[0099] Furthermore, the image acquisition unit 200 is also used for:

[0100] If the monitor image recognition is unsuccessful, a second image from the previous recognition is acquired.

[0101] Furthermore, the identification unit 300 is also used for:

[0102] Confirm whether the monitor image corresponding to the second image is recognized successfully.

[0103] Determine whether there is a large color block in the first image, and the area of ​​the color block covers the monitor area in the second image. If so, the image collector is blocked;

[0104] If not, then find out whether there is a similar area between the first image and the second image, if not, then there are other reasons;

[0105] If yes, then confirm whether the coordinates of the similar areas are the same. If they are the same, the image collector may be blocked;

[0106] If not, the image collector or the monitor may be displaced, causing the image collector to be unable to align with the monitor.

[0107] It can be seen from the above technical solutions that the embodiment of the present application provides a method and device for collecting vital sign data, which can achieve the purpose of the anesthesia information system automatically obtaining the monitor vital sign data even if the monitor interface is not open, by sending a timed collection instruction to an image collector; obtaining a first image collected by the image collector; identifying the monitor image in the first image; if the recognition is successful, obtaining the first vital sign data in the first image; and sending the first vital sign data to the monitor. The present application collects vital sign data on the monitor through an image collection device, identifies the vital sign data using recognition technology, and transmits the data to the anesthesia information system for the doctor to confirm at regular intervals. The doctor only needs to confirm whether the data is correct, which reduces the workload of the anesthesiologist for frequent input and improves the work efficiency of the anesthesiologist.

[0108] According to the above-mentioned method for collecting vital sign data, the embodiment of the present application also provides a readable storage medium and a computer device. The readable storage medium stores an executable program, and when the program is executed by the acquirer, the steps of the above-mentioned remote consultation method are implemented; the computer device includes a memory, an acquirer, and an executable program stored in the memory and runnable on the acquirer, and when the acquirer executes the program, the steps of the above-mentioned method for collecting vital sign data are implemented.

[0109] The present application is described in detail above in conjunction with specific implementation methods and exemplary examples, but these descriptions cannot be understood as limiting the present application. Those skilled in the art understand that, without departing from the spirit and scope of the present application, a variety of equivalent replacements, modifications or improvements can be made to the technical solution of the present application and its implementation methods, all of which fall within the scope of the present application. The scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for collecting vital sign data, It is characterized in that The method comprises: Sending a timing acquisition instruction to the image collector; Acquire a first image acquired by the image collector; Identify the monitor image in the first image, if the identification is successful, obtain the first vital sign data in the first image; if the monitor image identification is unsuccessful, obtain the second image identified in the previous time, wherein the image acquisition device may be blocked or offset, or the monitor position has moved, and it is necessary to analyze the cause of the failure and prompt the doctor; after acquiring the second image, confirm whether the monitor image corresponding to the second image is successfully identified, if the identification fails, further determine whether the operation is over, if the operation is over, the process is over, if the operation is not over, continue to collect images; if the identification is successful, compare the first image with the second image, and analyze the reason why the monitor image recognition in the first image is unsuccessful, specifically including: determine whether there is a large color block in the first image, and the area of ​​the color block covers the monitor area in the second image, if so, the image collector is blocked; if not, find out whether there are similar areas between the first image and the second image, if not, it is other reasons; if yes, then confirm whether the coordinates of the similar areas are the same, if they are the same, the image collector may be blocked; if not, the image collector or the monitor may be displaced, resulting in the image collector being unable to align with the monitor; The first vital sign data is sent to a monitor.

2. The method for collecting vital sign data according to claim 1, It is characterized in that The identifying the monitor image in the first image includes: Get the monitor image classifier; A monitor image within the first image is identified by the monitor image classifier.

3. The method for collecting vital sign data according to claim 2, It is characterized in that If the recognition is successful, obtaining first vital sign data in the first image includes: Extracting the vital sign data in the first image to obtain a vital sign data extraction set; Get a digital classifier; The first vital sign data is acquired by identifying the vital sign data extraction set through the digital classifier.

4. A device for collecting vital sign data, It is characterized in that The device comprises: An instruction sending unit, used for sending a timing acquisition instruction to the image collector; An image acquisition unit, used to acquire a first image acquired by the image acquisition device; and used to acquire a second image previously recognized if the image recognition of the monitor in the first image is unsuccessful, wherein since the image acquisition device may be blocked or offset, or the position of the monitor has moved, it is necessary to analyze the cause of the failure and prompt the doctor; An identification unit is used to identify the monitor image in the first image; and to confirm whether the monitor image corresponding to the second image is successfully identified. If the identification fails, it is further determined whether the operation is completed. If the operation is completed, the process is completed, and if the operation is not completed, the image acquisition is continued; if the identification is successful, the first image is compared with the second image to analyze the reason for the unsuccessful recognition of the monitor image in the first image, specifically including: determining whether there is a large color block in the first image, and the area of ​​the color block covers the monitor area in the second image. If so, the image collector is blocked; if not, find out whether there are similar areas between the first image and the second image. If not, it is other reasons; if so, then confirm whether the coordinates of the similar areas are the same. If they are the same, the image collector may be blocked; if not, the image collector or the monitor may be displaced, resulting in the image collector being unable to align with the monitor; a vital sign data acquisition unit, configured to acquire first vital sign data in the first image if the recognition is successful; The vital sign data sending unit is used to send the first vital sign data to a monitor.

5. The device for collecting vital sign data according to claim 4, It is characterized in that The identification unit is also used for: Get the monitor image classifier; A monitor image within the first image is identified by the monitor image classifier.

6. The device for collecting vital sign data according to claim 5, It is characterized in that The vital sign data acquisition unit is also used for: Extracting the vital sign data in the first image to obtain a vital sign data extraction set; Get a digital classifier; The first vital sign data is acquired by identifying the vital sign data extraction set through the digital classifier.