Patient monitoring system and monitoring method

Abstract

A patient monitoring system comprises: a physiological parameter information input unit configured to receive physiological parameters of a patient; an image processing unit configured to acquire image data of the patient and output analysis results; a data processing unit configured to determine an abnormal physiological parameter, generate a first alarm event based on an original alarm strategy when no analysis result is received, generate an image-related alarm strategy when an analysis result is received, and mask an alarm based on the image-related alarm strategy or generate a second alarm event based on the image-related alarm strategy, wherein the second alarm event has an alarm prompt mode different from that of the first alarm event at least in part; and an information output unit configured to alarm prompt the abnormal physiological parameter. The present application reduces the interference of false alarms caused by patient self-motion or nursing operation on medical staff. The present application also provides a patient monitoring method and a storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical field, and in particular to a patient monitoring system and a monitoring method. BACKGROUND

[0002] At present, patient monitoring systems have been widely applied in medical and health care places such as hospitals, nursing homes and clinics. Generally, the patient monitoring system is used to detect and monitor the physiological parameters of patients, and an alarm is generated when the physiological parameters are abnormal. The alarm of the monitoring device in the clinic is important information for the nurse to judge the patient's condition. Through the alarm information, the nurse will decide whether to intervene or report to the doctor. However, the problem of alarm fatigue caused by false alarms reduces the trust of nurses in the alarm.

[0003] The intensive care unit (ICU) is a cross-disciplinary field that focuses on real-time monitoring, rapid diagnosis and timely intervention and treatment of critical illness. For most patients, if appropriate exercise can be performed when their physical condition permits, it will help the patient recover as soon as possible. However, the rehabilitation activities of the patient can cause false alarms. The false alarms caused by the one-off autonomous movement of the patient or the nursing operation process belong to meaningless alarms, which not only brings invalid work to the medical staff, but also may cause the medical staff to make wrong assessment of the patient's condition. SUMMARY

[0004] The technical problem solved by the present application is to provide a patient monitoring system and a monitoring method to reduce the interference of false alarms caused by the autonomous movement of the patient or the nursing operation process on the medical staff.

[0005] According to a first aspect, a patient monitoring system is provided in an embodiment, comprising:

[0006] a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or a monitor;

[0007] an image processing unit configured to obtain image data containing a patient associated with the image acquisition device from at least one image acquisition device, and analyze the image data of each patient to output an analysis result representing the activity state of the patient;

[0008] a data processing unit configured to determine, based on the parameter values of the physiological parameters, abnormal physiological parameters, generate, when no analysis result is received, a first alarm event for the abnormal physiological parameters based on a raw alarm strategy, and generate, when the analysis result is received, an image-related alarm strategy based on at least the analysis result or both the analysis result and at least part of the abnormal physiological parameters, and mask alarms for at least part of the abnormal physiological parameters based on the image-related alarm strategy or generate a second alarm event based on the image-related alarm strategy, the second alarm event having at least partially different alarm prompting manners from the first alarm event;

[0009] an information output unit configured to prompt alarms for the abnormal physiological parameters in at least partially different manners based on the first alarm event or the second alarm event, the alarm prompting including at least one of auditory, visual and tactile prompting.

[0010] According to a second aspect, an embodiment provides a patient monitoring system, comprising:

[0011] a physiological parameter information input unit configured to receive physiological parameters of patients output by at least one sensor or monitor;

[0012] an image processing unit configured to acquire image data containing patients associated with the image acquisition device from at least one image acquisition device, and analyze the image data of each patient to output an analysis result representing an activity state of the patient;

[0013] a data processing unit configured to determine abnormal physiological parameters based on parameter values of the physiological parameters;

[0014] an information output unit, the information output unit comprising a display unit, a display interface of the display unit comprising at least one display area, each patient having a corresponding display area, at least one physiological parameter of each patient being displayed in the corresponding display area of the patient, the data processing unit displaying a prompt identifier representing the analysis result corresponding to the patient in the display area corresponding to the patient, and highlighting the abnormal physiological parameters, display areas of the abnormal physiological parameters or display areas of the patients corresponding to the abnormal physiological parameters.

[0015] According to a third aspect, an embodiment provides a patient monitoring system, comprising:

[0016] a physiological parameter information input unit configured to receive physiological parameters of associated patients output by at least one sensor or monitor;

[0017] an image processing unit configured to obtain image data containing a patient associated with the image acquisition device from at least one image acquisition device, and analyze the image data of each patient to output an analysis result representing an activity state of the patient;

[0018] a data processing unit configured to determine abnormal physiological parameters based on the parameter values of the physiological parameters, generate an image-related alarm strategy for a corresponding patient based on at least the analysis result or both the analysis result and at least part of the abnormal physiological parameters upon receiving the analysis result, and mask alarms or generate alarm events for at least part of the abnormal physiological parameters based on the image-related alarm strategy, the alarm events including an alarm-producing physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, so that the information output unit prompts the alarm-producing physiological parameter in the corresponding mode based on the alarm events.

[0019] According to a fourth aspect, in an embodiment, a patient monitoring system is provided, comprising:

[0020] a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or monitor;

[0021] an image processing unit configured to obtain image data containing a patient associated with the image acquisition device from at least one image acquisition device, and analyze the image data of each patient to output an analysis result representing an activity state of the patient;

[0022] a data processing unit configured to monitor and generate alarm events for physiological parameters based on an original alarm strategy when the analysis result is not received, and generate an image-related alarm strategy based on at least the analysis result when the analysis result is received, monitor and generate alarm events for physiological parameters based on the image-related alarm strategy, the image-related alarm strategy relative to the original alarm strategy causing the alarm events to be enhanced or suppressed.

[0023] According to a fifth aspect, in an embodiment, a patient monitoring system is provided, comprising:

[0024] a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or monitor;

[0025] an image processing unit configured to obtain image data containing a patient associated with the image acquisition device from at least one image acquisition device, and analyze the image data of each patient to output an analysis result representing an activity state of the patient;

[0026] a data processing unit configured to generate an image-related alarm strategy for a corresponding patient based on at least the analysis result when the analysis result is received, adjust a parameter value of a physiological parameter of the patient according to the image-related alarm strategy, determine an abnormal physiological parameter based on the adjusted parameter value, generate an alarm event based on the image-related alarm strategy, the alarm event including the abnormal physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, and cause an information output unit to perform alarm prompting of the abnormal physiological parameter in the corresponding mode based on the alarm event.

[0027] According to a sixth aspect, a patient monitoring method is provided in an embodiment, comprising:

[0028] receiving physiological parameters of a patient output by at least one sensor or monitor;

[0029] receiving an analysis result for characterizing an activity state of the patient, the analysis result being obtained based on image data output by an image acquisition device, the image data containing the patient associated with the image acquisition device;

[0030] determining an abnormal physiological parameter based on a parameter value of the physiological parameter, and generating an alarm event;

[0031] displaying the received at least one physiological parameter of the patient on a display interface, the display interface including at least one display area, each display area corresponding to a patient, each patient having a corresponding display area, displaying at least one physiological parameter of the patient in each display area corresponding to the patient, displaying a prompt identifier corresponding to the analysis result of the patient in the display area corresponding to the patient when the analysis result associated with the patient is received, and highlighting the display area of the abnormal physiological parameter or the patient corresponding to the abnormal physiological parameter when the abnormal physiological parameter is determined.

[0032] According to a seventh aspect, a patient monitoring system is provided in an embodiment, comprising:

[0033] an image acquisition device associated with a patient, configured to capture and output image data containing the patient associated with the image acquisition device;

[0034] a monitor configured to receive physiological parameter signals of a patient detected by at least one sensor, and output parameter values of the physiological parameters of the patient after processing;

[0035] a server configured to obtain image data containing the patient associated with at least one image acquisition device output by the image acquisition device, and analyze the image data of each patient to output an analysis result for characterizing an activity state of the patient;

[0036] A central station for performing the method according to the sixth aspect.

[0037] According to the eighth aspect, a computer readable storage medium is provided in an embodiment, on which a program is stored, which can be executed by a processor to implement the method according to the sixth aspect.

[0038] According to the patient monitoring system of the above-mentioned embodiments, since the first alarm event for the physiological parameter with the abnormality is generated based on the original alarm strategy when the analysis result is not received, and the alarm for the physiological parameter with at least part of the abnormality is shielded based on the image-related alarm strategy or the second alarm event is generated based on the image-related alarm strategy when the analysis result is received, and the alarm prompt mode of the second alarm event is at least partially different from that of the first alarm event, the disturbance of the false alarm caused by the patient's autonomous movement or the nursing operation process to the medical staff is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 Schematic diagram of patient activity;

[0040] Figure 2 Schematic diagram of a patient monitoring system in an embodiment;

[0041] Figure 3 Flowchart for determining whether a patient is moving in an embodiment;

[0042] Figure 4 Schematic diagram of a display interface of a display unit;

[0043] Figure 5a Schematic diagram of a patient monitoring system in an embodiment;

[0044] Figure 5b Schematic diagram of a patient monitoring system in another embodiment;

[0045] Figure 5c Schematic diagram of a patient monitoring system in yet another embodiment;

[0046] Figure 5d Schematic diagram of a patient monitoring system in still another embodiment;

[0047] Figure 6 Flowchart for generating an alarm event in an embodiment;

[0048] Figure 7 Flowchart for generating an alarm event in another embodiment;

[0049] Figure 8 Flowchart for physiological parameter value preservation processing in an embodiment. Detailed Implementation

[0050] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of this application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to this application are not shown or described in the specification. This is to avoid obscuring the core parts of this application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0051] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0052] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0053] In recent years, with the popularization of video acquisition equipment and the development of video analysis technology, video monitoring systems have been gradually introduced into isolation wards, ICUs, and general wards. This invention envisions analyzing patient video image data output by image acquisition equipment to automatically identify whether a patient is engaged in bedside activity or receiving care. Based on this information, an alarm can be triggered. The goal is to allow nurses to simultaneously obtain information about the patient's current movement scene when they receive the alarm remotely, such as whether the patient is moving or whether there are medical or nursing procedures at the bedside. This is particularly beneficial at night when nurses are limited in number, enabling nurses to directly obtain movement scene information for any bed from the nurses' station. This information can then help determine the patient's condition and whether the alarm information matches clinical expectations, or whether it is a false alarm. If immediate action is needed, the nurse can go to the bedside immediately; otherwise, the alarm can be remotely confirmed, avoiding unnecessary trips to the bedside for alarm confirmation.

[0054] Further, based on the video judgment of the patient's fine behavior, fine movement of each part, and fine behavior information of medical operation, intelligent device alarm processing strategies can be implemented based on such information, such as shielding false alarms or meaningless alarms, prolonging the refractory period, or reducing the alarm level and changing the alarm sound and light.

[0055] Please refer to Figure 1 , the patient 100 performs rehabilitation activities on the bed, and the patient 100 wears at least one sensor 140 for detecting physiological parameter signals of the patient and transmitting the physiological parameter signals to the bedside monitor 130 through wired or wireless means. The sensor 140 can be, for example, an electrocardiogram sensor, a blood pressure sensor, a temperature sensor, a blood oxygen sensor, etc., which respectively detect the patient's electrocardiogram signal, blood pressure signal, temperature signal, and blood oxygen signal. The monitor 130 is used to process the received physiological parameter signals, calculate the parameter values of each physiological parameter through a specific algorithm, such as electrocardiogram, heart rate, respiratory rate, blood pressure, and blood oxygen, etc. The monitor 130 displays the calculated physiological parameters on the display unit in the form of real-time numerical values and / or time-related trend graphs. The monitor 130 can further monitor the physiological parameters, determine the abnormal physiological parameters, and generate an alarm event.

[0056] In a medical place with a central station, the monitor 130 can also send the obtained parameter values of the patient's physiological parameters to the central station through wired or wireless means, or send the physiological parameter signals output by the sensor to the central station 150. Some sensors 140 can also directly send the detected physiological parameter signals to the central station 150 through wireless means. The central station 150 processes the received physiological parameter signals, calculates the parameter values of each physiological parameter through a specific algorithm. The central station 150 can further monitor the physiological parameters, determine the abnormal physiological parameters, and generate an alarm event.

[0057] The central station 150 is used to receive the physiological parameters of multiple patients and monitor and / or manage the multiple patients. Therefore, the display interface of the display unit provided in the central station 150 is usually divided into multiple display areas, each patient has a corresponding display area, and the physiological parameters of the patient are displayed in the form of real-time numerical values and / or time-related trend graphs in the display area corresponding to the patient. Generally, the central station 150 includes a communication module for communicating with the monitor or sensor through wired or wireless means, receiving the data transmitted by the monitor or sensor, or transmitting instructions, configuration information, or alarm information to the monitor or sensor. In some embodiments, the central station also communicates with the portable PAD or wearable device (such as a monitoring device worn on the wrist) through the communication module, so as to send the monitoring results to the PAD or wearable device carried by the medical staff.

[0058] An image acquisition device 120 is installed beside the hospital bed to capture images of the patient. In practical applications, the image acquisition device 120 is associated with the patient, and the acquired image data is attributed to that patient. The image acquisition device 120 can be an RGB camera, an infrared camera, or a depth camera. The image acquisition device 120 captures image data (e.g., photographs or continuous frame video data) containing the patient, and then outputs the image data as image frames to a bedside monitor or other dedicated electronic equipment for processing image or video data, such as a central station computer or a dedicated image processor. The image data acquired by the image acquisition device 120 has a timestamp, i.e., the real-time time of image data acquisition, or the receiving electronic equipment adds a timestamp to the image data subsequently for time function analysis of the image data.

[0059] In one embodiment, a patient monitoring system based on image acquisition device 120 is as follows: Figure 2 As shown, the system includes a display unit 200, an image processing unit 210, a physiological parameter information input unit 215, and a data processing unit 220. The image processing unit 210 is communicatively connected to the image acquisition device 120, receiving image data output by the image acquisition device 120. The image processing unit 210 is also communicatively connected to the data processing unit 220, sending the analysis results of the images to the data processing unit 220. The physiological parameter information input unit 215 is connected to a physiological parameter source 240, which can be a sensor for detecting physiological parameter information. The output of the physiological parameter information input unit 215 is connected to the data processing unit 220, used to output the received physiological parameters to the data processing unit 220. When the data processing unit 220 is the processor of the central station, the physiological parameter source 240 can also be a bedside monitor. The data processing unit 220 is connected to the display unit 200, sending data that needs to be presented in a visual manner to the display unit 200 for display. The data processing unit 220 can also be communicatively connected to the image acquisition device 120, receiving image data output by the image acquisition device 120. In another embodiment, the image processing unit 210 receives image data output by the image acquisition device 120 and then transmits the image data to the data processing unit 220. The data processing unit 220 can store the received image data in the memory 230, and can also store the resulting monitoring results in the memory. The monitoring results can be parameter values ​​of physiological parameters and / or alarm events. When the data (including the patient's image data and monitoring results) is stored in the memory, it can be stored in a one-to-one correspondence with the time it was generated, making the data a function of time, so as to facilitate the subsequent generation of trend graphs and / or playback of corresponding times.

[0060] The image processing unit 210 acquires image data containing a patient output by the image acquisition device 120, and analyzes the image data to obtain analysis results representing the activity state of the patient. The image processing unit 210 can be a chip or composed of multiple chips to jointly complete the analysis function of the image data. The image processing unit 210 receives the image data in the form of image frames. If the image acquisition device 120 sends a photo, one photo can be one image frame. If the image acquisition device 120 needs to send a continuous video, the image acquisition device 120 needs to divide the continuous video into multiple continuous image frames in time sequence. The encoding method of the sent image frames can be to encode and send each frame, or to encode and send the initial image frame plus the inter-frame difference, so as to reduce the amount of data transmission. After receiving the image frames, the image processing unit 210 decodes the image frames in time sequence to obtain the image frames, and combines the image frames into continuous video data in time sequence. The image processing unit 210 can analyze the video data by a specific algorithm or artificial intelligence to output analysis results, which include analysis results representing the activity state of the patient and / or other information. The analysis results representing the activity state of the patient can be information representing whether the patient is moving, such as an analysis result of 1 indicating that the patient is active, and an analysis result of 0 indicating that the patient's body is not active.

[0061] As shown in FIG. 4, a specific embodiment for determining whether the patient is moving is given, and the processing process includes the following steps: Figure 3

[0062] Step 300, input image frames. The image processing unit 210 inputs the image frames of the video data in time sequence frame by frame.

[0063] Step 310, determine the position of the human body in the image frame. First, human body detection needs to be performed in the image frames of the video data. Since the video is taken for the patient on the bed, at least one image frame of the image frames to be analyzed should contain a human body and a bed, otherwise the image frames will continue to be detected until the human body is detected. The human body in the image can be the patient or other personnel such as medical staff. The human body detection method can adopt an artificial intelligence method, and the image frame is input into a pre-trained model for comparison. The detection model can adopt an existing yolo-x model, which is trained by appropriate samples so that the image frame data containing the patient and the bed can be detected to contain the human body and the bed. The positions and areas of the “human” and the “bed” are labeled, such as using a rectangular box to label the positions and areas of the “human” and the “bed”.

[0064] ​Step 320, determine whether the detected "person" is a patient. Based on the detection result of step 310, take the rectangular frame as an example to illustrate how to determine the identity of the detected "person". First, calculate the overlapping part of the rectangular frame of the "person" and the rectangular frame of the "bed", calculate the proportion of the overlapping part in the rectangular frame of the "bed", and compare the proportion with a preset threshold value; if the rectangular frame of the "person" is mostly within the rectangular frame of the "bed", the detected "person" is considered to be a patient; if the rectangular frame of the "person" is mostly outside the rectangular frame of the "bed", the detected "person" is considered to be a medical staff beside the bed. When the rectangular frame is changed to other region marking methods, the same way can be used to identify the identity of the detected "person". When the detected "person" is considered to be a patient, step 330 is executed to perform subsequent patient activity monitoring and evaluation. If the detected "person" is not considered to be a patient, steps 300-320 can be executed in a loop until a patient is detected.

[0065] Step 330, determine the region of interest including the patient. Still take the rectangular frame as an example to illustrate. Take the rectangular frame of the patient as the target frame, and expand the target frame in a predetermined manner to form a new region, for example, expand the target frame by a certain proportion with the center of the target frame as the center to form a new enclosed region, and take the new region as the region of interest for subsequent patient activity monitoring.

[0066] Step 340, calculate the inter-frame difference. Collect image frames sorted by time from the video data, compare the regions with differences between each two adjacent image frames, calculate the difference value between each two adjacent image frames as the inter-frame difference. The difference between adjacent image frames may be caused by the activity of one or more parts of the body (such as the bending of limbs, posture change, displacement) or the displacement of the whole body. These differences will be reflected as pixel differences, and the number of pixels with differences can be counted as the difference value between each two adjacent image frames.

[0067] Step 350, mark the region with differences in the region of interest. The region of interest is composed of a plurality of pixels arranged in rows and columns, and the pixels in the region of interest are binarized, for example, the pixel values of the region with differences calculated in step 340 are set to 255, and the pixel values of other regions are set to 0.

[0068] Step 360, accumulate the calculated inter-frame difference in real time to obtain the accumulated absolute difference value. For example, the inter-frame difference between the nth-1 frame and the nth-2 frame is A, and the inter-frame difference between the nth-1 frame and the nth frame is B, then the accumulated absolute difference value after two operations is A+B. In order to make the accumulated absolute difference value more accurate, the inter-frame difference can be filtered (such as median filtering) after accumulation.

[0069] In accumulating the inter-frame difference, the binarization of the different pixels in the region of interest is also performed, i.e. as more inter-frame differences are detected, the pixels in the region of interest that are set to 255 also increase.

[0070] At step 370, the accumulated absolute difference is compared with a predetermined threshold. When the accumulated absolute difference is less than the predetermined threshold, it is considered that the patient has no body movement, and the process continues to step 340. Otherwise, it is considered that the patient has movement. When it is determined that the patient has movement, the process proceeds to step 380, and the image processing unit 210 outputs the movement analysis result representing that the patient is in a movement state to the data processing unit 220. After step 380, the process continues to step 340.

[0071] In another embodiment, the analysis result representing the movement state of the patient can further include information of the movement part of the patient, such as “right upper limb movement”, “both legs movement”, etc. The detection of the movement part can be achieved by pre-training a sample model by artificial intelligence, and then inputting the current image into the model to determine.

[0072] In other embodiments, in addition to the above-mentioned activity information of the patient, the image processing unit 210 can further output information of whether the patient is cared by medical staff to the data processing unit 220. For example, in some embodiments, the analysis result of the analysis performed by the image processing unit based on the video data further includes whether the patient is on the bed and whether there is other person beside the bed, and the analysis result is output to the data processing unit. Based on the alarm event in the monitoring result, when the analysis result of the patient corresponding to the alarm event is that the patient is on the bed and there is no other person beside the bed, the current video data of the patient is displayed on the display unit to remind the medical staff to pay attention. When it is determined that there is a person beside the bed, it can be further determined whether the patient is cared by whether the rectangular frame of the patient and the rectangular frame of the person beside the bed overlap, so that the analysis result representing the movement state of the patient can further include information representing that the patient is being cared. When it is determined that the patient is being cared, the analysis result can further include the cared part of the patient. The cared part of the patient can be determined by pre-training a sample model by artificial intelligence, and then inputting the current image into the model to determine.

[0073] Please continue to refer to Figure 2The data processing unit 220 receives physiological parameter signals collected from at least one patient and obtains monitoring results for each patient, which include parameter values of at least one physiological parameter and / or alarm events. The data processing unit 220 can be a chip or composed of multiple chips, which calculates the required parameter values of various physiological parameters, such as electrocardiogram, heart rate, respiration rate, blood pressure, blood oxygen, etc., based on specific algorithms according to the physiological parameter signals. The data processing unit 220 displays the calculated physiological parameters on the display unit 200 in the form of real-time numerical values and / or time-dependent trend graphs.

[0074] The data processing unit 220 can further compare the parameter values of the physiological parameters with preset upper and lower threshold values, and when the parameter value of a certain physiological parameter exceeds the upper and lower threshold value range, it is considered that the physiological parameter is abnormal, and thus an alarm event is generated. The data processing unit 220 can output an alarm prompt in the form of sound, light and / or touch through the information output unit. The information output unit includes a display unit, a sound player and a vibration module, for example, by highlighting or flashing the display of the abnormal physiological parameter on the display interface through the display unit, for example, by playing a sound through the sound player, and for example, by prompting through the vibration of the wearable device worn by the medical staff. The data processing unit 220 can divide the alarm event into different alarm levels, such as high, medium and low alarm levels, according to the type of physiological parameter and / or the degree to which the parameter value exceeds the alarm threshold. Different alarm levels use different alarm prompt methods with different degrees of attention. The degree of attention of the alarm prompt method refers to the degree of difficulty in arousing the interest and attention of the subject receiving the alarm prompt in the sense of hearing, sight and / or touch by the alarm prompt method. The alarm prompt method with a high degree of attention can have more alarm prompt methods than the alarm prompt method with a low degree of attention, or in the case of using the same kind of alarm prompt method, the alarm prompt method with a high degree of attention uses a more stimulating prompt method in the sense of hearing, sight and / or touch than the alarm prompt method with a low degree of attention. For example, the alarm prompt method with a high degree of attention can use both sound and display prompt methods, while the alarm prompt method with a high degree of attention only uses display prompt method or only uses sound prompt method; if the same kind of alarm prompt method is used, for example, both use sound prompt, the alarm prompt method with a high degree of attention uses a larger sound volume, a higher sound interval frequency or a longer duration, etc., while the alarm prompt method with a low degree of attention uses a smaller sound volume, a lower sound interval frequency or a shorter duration, etc.; for example, both use display prompt, for example, the physiological parameter that occurs alarm is displayed as red, the display prompt method with a high degree of attention uses a larger red color and a deeper color or a higher flashing frequency, etc., while the display prompt method with a low degree of attention uses a smaller red color and a lighter color or a lower flashing frequency; for example, both use vibration prompt, the vibration prompt method with a high degree of attention uses a larger vibration amplitude, a higher vibration frequency or a longer duration, etc., while the vibration prompt method with a low degree of attention uses a smaller vibration amplitude, a lower vibration frequency or a shorter duration, etc.

[0075] In a specific embodiment, the data processing unit 220 can be a processor of a bedside monitor.

[0076] In another specific embodiment, the data processing unit 220 can be a processor of the central station. When the data processing unit 220 is a processor of the central station, the data processing unit 220 configures the display interface of the display unit of the central station 150 into a plurality of display regions, each patient has a corresponding display region, in the display region corresponding to the patient, the physiological parameters of the patient are displayed in the form of real-time numerical values and / or time-dependent trend graphs (e.g. real-time heart rate waveform graphs), as shown in Figure 4 .

[0077] The data processing unit 220 is also configured to receive the analysis results of the image data output by the image processing unit 210 and the video data including the patient. The data processing unit 220 fuses and displays the monitoring results and the activity information of the patient corresponding to the same patient and generated in the same preset time interval. The same preset time interval corresponds to the monitoring results and the activity information in time, that is, the monitoring results and the activity information are generated at the same time, or the generation time of the two is within a shorter time interval, but in actual cases, the two are considered to be generated at the same time. For example, when the data processing unit 220 receives the activity information including the motion analysis result indicating that the patient is in a motion state, the data processing unit 220 displays the motion analysis result on the monitoring result corresponding to the same patient through the display unit, and the motion analysis result includes at least one of a string, a schematic diagram, and a thumbnail. For example, when the data processing unit 220 is a processor of the central station, the data processing unit 220 displays the string "patient motion" indicating that the patient is in motion in the display region corresponding to the patient, as shown in Figures 5a-5d . The schematic diagram fused with the activity information of the patient, the video data of patient 1 is analyzed and the result shows that the patient is in motion, and the data processing unit 220 displays the string "patient motion" indicating that the patient is in motion in the display region corresponding to the patient 1. When an alarm event is triggered, the display region of the physiological parameter with an abnormality, the display region of the physiological parameter with an abnormality, or the display region of the patient corresponding to the physiological parameter with an abnormality is highlighted. For example, the physiological parameter with an abnormality is displayed in a more noticeable way, such as a larger and / or bold font, or in red, etc., as shown in Figure 5b . For another example, the display region of the physiological parameter with an abnormality is highlighted, such as a red or blue background, or flashing, as shown in Figure 5c . For another example, the display region of the patient corresponding to the physiological parameter with an abnormality is highlighted, such as the entire display region of the corresponding patient is displayed in red or blue, or flashing, as shown in Figure 5d .

[0078] Thus, when the medical staff is aware of the alarm event, the medical staff can refer to the prompt information of the patient in motion to analyze and judge the alarm event.

[0079] In the improved embodiment, the analysis result characterizing the activity state of the patient can also be associated with the current video data, for example, when the medical staff clicks the string "patient motion", the data processing unit 220 can display the current motion video of the patient in a predetermined area of the display interface (for example, in the lower right corner of the display unit) based on the triggering operation instruction, as shown in the figure, so as to provide more detailed information and assistance for the medical staff, and enable the medical staff to make a more objective assessment of the alarm event. Figures 5a-5d

[0080] To further reduce the unnecessary disturbance of the false alarm caused by the patient activity to the medical staff, in some embodiments, when the patient is not active, a kind of alarm strategy, referred to herein as the original alarm strategy, can be used, and when the patient is active, another kind of alarm strategy, referred to herein as the image-related alarm strategy, can be used. When there is an abnormal physiological parameter, a first alarm event can be generated based on the original alarm strategy, and a second alarm event can be generated based on the image-related alarm strategy.

[0081] Please refer to Figure 6 In some embodiments, the step of screening the alarm based on the image-related alarm strategy includes the following steps.

[0082] Step 400: receiving the physiological parameters of the patient. The physiological parameters of the patient can be obtained directly from the sensor, such as the blood oxygen sensor worn on the patient's limbs, which directly outputs the physiological parameters of the patient to the data processing unit through wireless means after detecting the physiological parameters of the patient. The physiological parameters of the patient can also be obtained by the bedside monitor and output to the data processing unit.

[0083] Step 405: determining the abnormal physiological parameters according to the parameter values of the physiological parameters. The data processing unit compares the parameter values of the physiological parameters with the predetermined threshold range, and determines the physiological parameters whose parameter values exceed the upper or lower limit of the threshold range as the abnormal physiological parameters.

[0084] Step 410: detecting the activity state of the patient. The image processing unit obtains the image data containing the patient associated with the image acquisition device from the at least one image acquisition device, and analyzes each patient's image data to output an analysis result characterizing the activity state of the patient.

[0085] The analysis result characterizing the activity state of the patient can include at least one of the following contents:

[0086] ​1. Information representing the patient's movement can be further included, such as information about the parts of the body in motion. Methods for detecting these parts of the body can be implemented using artificial intelligence or image recognition.

[0087] 2. Information representing the patient being cared for can further include information about the area being cared for. The detection of the area being cared for can be achieved through artificial intelligence or image recognition.

[0088] 3. Information characterizing patient agitation. In one embodiment, based on the fact that patients are usually more active or have larger movements when agitated, agitation can be determined by detecting the frequency and amplitude of the patient's activity. In another embodiment, agitation can be determined by recognizing the patient's facial expressions.

[0089] 4. Information representing a patient falling out of bed. In one embodiment, it can be determined whether a patient has fallen out of bed based on changes in the patient's position on the bed. For example, if the patient is detected and their position is outside the bed, it can be determined that the patient has fallen out of bed. Alternatively, it can be determined whether a patient has fallen out of bed by observing the patient's displacement in consecutive image frames.

[0090] 5. Indicates that someone is at the patient's bedside.

[0091] In some embodiments, patient agitation and falls from bed can be pre-trained using artificial intelligence to obtain data by inputting the current image into the model and making a judgment.

[0092] In addition to the information mentioned above, the analysis results can also include more information.

[0093] When the analysis result is detected, the analysis result is output by the image processing unit. The analysis result representing the patient's activity status can be a command, a number, or a string with a certain meaning. For example, "1" represents that the patient is in an active state, and "0" represents that the patient is in a stationary state.

[0094] Step 415: Determine whether an analysis result has been received. If no analysis result representing the patient's activity status has been received, proceed to step 420; if the analysis result has been received, proceed to step 425.

[0095] Step 420: generating a first alarm event for the physiological parameter that is abnormal based on the original alarm strategy. In some embodiments, when the data processing unit 220 does not receive the analysis result from the image processing unit 210, it can be that the original alarm strategy is not considered in the influence of the patient's activity on the physiological parameter, or it can be that the patient is not in an active state, so the patient's physiological parameter will not fluctuate significantly due to activity. At this time, the original alarm strategy can be used, and if the parameter value of the physiological parameter output by the physiological parameter information input unit 215 exceeds the preset upper and lower threshold values, it is considered that the physiological parameter is abnormal, and a first alarm event is generated.

[0096] Step 425: generating an image-related alarm strategy when the analysis result is received. The image-related alarm strategy can be generated based on at least the analysis result, or can be generated based on both the analysis result and at least part of the abnormal physiological parameter.

[0097] For example, in some embodiments, the influence of the physiological parameter on the vital sign can be divided into different alarm levels, such as high, medium and low levels. The higher the alarm level, the higher the alarm priority or the alarm method with higher attention. When the abnormal physiological parameter is determined, and the analysis result representing the patient's activity state is received, whether to generate an image-related alarm strategy is determined according to the alarm level of the physiological parameter and the analysis result. For example, when the abnormal physiological parameter of the low alarm level generates an alarm event, an image-related alarm strategy is generated. When the abnormal physiological parameter of the high alarm level generates an alarm event, the original alarm strategy is used to generate an alarm event, that is, the alarm event is not affected by the image data.

[0098] Step 430: determining whether the content of the analysis result is information representing that the patient is exercising and / or information representing that the patient is being cared for. If so, step 435 is performed, otherwise step 415 is performed.

[0099] Step 435: masking the alarm for at least part of the abnormal physiological parameter based on the image-related alarm strategy.

[0100] When the abnormal physiological parameter is determined, an alarm event for the abnormal physiological parameter should be generated, but in order to reduce unnecessary alarms to interfere with medical staff, in an embodiment, when the analysis result representing the patient's activity state is received at the same time, if the analysis result is information representing that the patient is exercising and / or information representing that the patient is being cared for, the alarm event for the abnormal physiological parameter is masked and no alarm prompt is performed, so as not to interfere with the medical staff.

[0101] In some embodiments, the alarm event can also be shielded according to the alarm level of the physiological parameter. For example, when an abnormality exists in a physiological parameter with a low alarm level and an alarm event is generated, the alarm event is shielded. When an abnormality exists in a physiological parameter with a high alarm level and an alarm event is generated, the alarm event is not shielded, but a second alarm event is generated based on the image-related alarm strategy or step 415 is performed.

[0102] In some embodiments, it can also be determined whether the content of the analysis result includes information indicating that the patient is agitated and / or falls out of bed. If so, and there is no one else at the bedside, an alarm is generated.

[0103] Reference can be made to Figure 7 In other embodiments, a second alarm event is generated based on the image-related alarm strategy, and the alarm prompt mode of the second alarm event is at least partially different from the alarm prompt mode of the first alarm event. The process includes the following steps.

[0104] Step 500: receiving a physiological parameter of a patient.

[0105] Step 505: determining a physiological parameter with an abnormality based on the parameter value of the physiological parameter.

[0106] Step 510: detecting an activity state of the patient.

[0107] Step 515: determining whether an analysis result is received. The analysis result is output by an image processing unit, which acquires image data containing the patient associated with the image acquisition device output by at least one image acquisition device, and analyzes the image data of each patient to determine whether the patient is moving. The analysis can be performed in the manner described above. When it is determined that the patient is not at rest, the analysis result indicating the activity state of the patient is output. When the analysis result indicating the activity state of the patient is not received, step 520 is performed, and when the analysis result is received, step 525 is performed.

[0108] Step 520: generating a first alarm event for the physiological parameter with an abnormality based on the original alarm strategy.

[0109] Step 525: generating an image-related alarm strategy when the analysis result is received. The image-related alarm strategy can be generated based on at least the analysis result, or can be generated based on both the analysis result and at least part of the physiological parameter with an abnormality.

[0110] Step 530: identifying the content of the analysis result.

[0111] whether the content of the analysis result includes information indicative of the patient being agitated and / or information indicative of the patient falling out of bed, whether the content of the analysis result includes information indicative of the patient being in motion, and whether the content of the analysis result includes information indicative of the patient being attended.

[0112] Step 535: generating, based on the content of the analysis result, a second alarm event with a corresponding alarm prompting manner according to the image-related alarm strategy.

[0113] When the content of the analysis result includes information indicative of the patient being agitated and / or information indicative of the patient falling out of bed, the attention degree of the alarm prompting manner of the second alarm event is higher than the attention degree of the alarm prompting manner of the first alarm event. When the content of the analysis result includes information indicative of the patient being in motion and / or information indicative of the patient being attended, the attention degree of the alarm prompting manner of the second alarm event is lower than the attention degree of the alarm prompting manner of the first alarm event.

[0114] The alarm prompting includes at least one of an audible, visual and tactile prompt. The audible alarm prompting may, for example, be playing a predetermined alarm sound, and in general, a higher volume, a higher frequency and a shorter sound interval sound is more likely to attract the attention of a person. For example, the alarm prompting sound generated based on the first alarm event has a larger volume, a higher frequency and / or a shorter sound interval (faster), and thus is more likely to attract the attention and vigilance of medical staff, while the alarm prompting sound generated based on the second alarm event has a smaller volume, a lower frequency and / or a longer sound interval (slower), and thus is less likely to attract the attention and vigilance of medical staff.

[0115] The visual alarm prompting may, for example, be a light signal prompt through a display screen or an LED light, which may, for example, be implemented in different colors. In general, a person's vision is more sensitive to red light, and the higher the saturation of red, the more likely it is to attract the attention of a person's vision, and thus the physiological parameter of the alarm may be displayed in red or a deeper red, or an LED or the like may emit red light. For example, the light signal generated based on the first alarm event has a deeper red, and thus is more likely to attract the attention and vigilance of medical staff, while the light signal generated based on the second alarm event has a lighter red, and thus is less likely to attract the attention and vigilance of medical staff. The light signal prompt may also be implemented through different flashing frequencies of light, for example, the light signal generated based on the first alarm event has a higher flashing frequency, and thus is more likely to attract the attention and vigilance of medical staff, while the light signal generated based on the second alarm event has a lower flashing frequency, and thus is less likely to attract the attention and vigilance of medical staff.

[0116] The haptic alarm prompt can be realized by a wearable device such as a wristwatch, a wristband, or the like worn by the medical staff. When an alarm event occurs, the wearable device transmits a signal to the part of the human body in contact with it through vibration, thereby arousing the attention and vigilance of the medical staff. For example, the alarm vibration based on the first alarm event is larger in amplitude and / or higher in frequency, thereby being more likely to arouse the attention and vigilance of the medical staff, while the alarm vibration based on the second alarm event is smaller in amplitude and / or lower in frequency, thereby being less likely to arouse the attention and vigilance of the medical staff.

[0117] The different attention degrees can be realized not only by different parameters of the auditory, visual, and haptic prompts, but also by different combinations of the auditory, visual, and haptic prompts, and combinations of different parameters of the auditory, visual, and haptic prompts. For example, the simultaneous prompt of a sound and a light signal has a higher attention degree and is more likely to arouse the attention and vigilance of the medical staff than a simple light signal prompt. The simultaneous prompt of a sound and a light signal with a larger volume and / or a more urgent frequency has a higher attention degree and is more likely to arouse the attention and vigilance of the medical staff than the simultaneous prompt of a sound and a light signal with a smaller volume and / or a slower frequency. Conversely, it is less likely to arouse the attention and vigilance of the medical staff.

[0118] Step 540: outputting an alarm prompt. The information output unit generates an alarm prompt of at least one of an auditory, visual, and haptic prompt for the physiological parameter based on the first alarm event or the second alarm event.

[0119] In this embodiment, the alarm prompt mode of the second alarm event is at least partially different from the alarm prompt mode of the first alarm event. On the one hand, the alarm prompt mode can be adjusted to reduce or increase the attention and vigilance of the medical staff. On the other hand, the medical staff can also distinguish the two alarms. For example, for a physiological parameter that is easily fluctuated by patient activity, when the first alarm event and the second alarm event are generated based on the original alarm strategy and the image-related alarm strategy respectively, the first alarm event and the second alarm event use different alarm prompt modes, so that the medical staff can know whether the alarm is affected by patient activity according to the different alarm prompt modes, thereby reducing the interference with the alarm caused by patient activity.

[0120] In some embodiments, for a second alarm event and a first alarm event for the same physiological parameter, if the alarm prompt manners of the two are different, the attention degree of the alarm prompt manner of the second alarm event can be lower than that of the first alarm event. For example, when the analysis result representing the activity state of the patient includes information representing that the patient is exercising, or for example, when the analysis result representing the activity state of the patient includes information representing that the patient is being cared for, the alarm level of the second alarm event can adopt a low alarm level, and the first alarm event can adopt a high or medium alarm level. In this embodiment, since the patient is in the state of exercising or being cared for, which can affect the physiological parameter of the patient, and this state of the patient can generally cause the physiological parameter to be non-physiological and even exceed the threshold range, resulting in an alarm event. Therefore, the attention degree of the alarm prompt manner of the second alarm event for the same physiological parameter is lower than that of the first alarm event, which can make the medical staff reduce the attention to the second alarm event, so as to reduce the unnecessary interference of the alarm caused by the patient's activity to the medical staff.

[0121] In some embodiments, for a second alarm event and a first alarm event for the same physiological parameter, if the alarm prompt manners of the two are different, the attention degree of the alarm prompt manner of the second alarm event can be higher than that of the first alarm event. For example, when the analysis result representing the activity state of the patient includes information representing that the patient is agitated and / or information representing that the patient is falling out of bed, the alarm level of the second alarm event can adopt a high or medium alarm level, and the first alarm event can adopt a low alarm level. In this embodiment, since the patient is in the state of agitation or falling out of bed, which will have an unreasonable impact on the physiological parameter of the patient, so that this state needs to be paid extra attention by the medical staff. Therefore, the attention degree of the alarm prompt manner of the second alarm event for the same physiological parameter needs to be higher than that of the first alarm event, so as to make the medical staff increase the attention to the second alarm event, so as to timely notice the agitation state or the falling out of bed state of the patient, so as to improve the monitoring effect on the patient.

[0122] In some embodiments, for the second alarm event and the first alarm event of the same physiological parameter, if the alarm prompt manners of the two are different, the attention degrees of the alarm prompt manners of the second alarm event and the first alarm event can also be adjusted according to the same physiological parameter, so that the attention degrees of the alarm prompt manners of the two are obviously different or not obviously different. In some embodiments, when the physiological parameter does not belong to the parameter that needs to be focused on by the patient, the attention degrees of the alarm prompt manners of the second alarm event and the first alarm event can be made to be obviously different, for example, the alarm level of the second alarm event can adopt a low alarm level, and the first alarm event can adopt a high alarm level. Conversely, when the physiological parameter belongs to the parameter that needs to be focused on by the patient, the attention degrees of the alarm prompt manners of the second alarm event and the first alarm event can be made to be not obviously different, for example, the alarm level of the second alarm event can adopt a medium alarm level, and the first alarm event can adopt a high alarm level. Thus, the medical staff has different attention degrees for the alarms of different physiological parameters, and the attention degree for the important physiological parameter is higher than that for the unimportant physiological parameter.

[0123] In some embodiments, when the data processing unit 220 receives the analysis result of the image processing unit 210, for the physiological parameter with at least part of the abnormality, in addition to generating the second alarm strategy based on the image-related alarm strategy, the alarm can also be shielded or the refractory period can be prolonged. For example, for the physiological parameter that reasonably fluctuates due to the patient's activity, when the patient is in motion, the physiological parameter will probably exceed the upper and lower threshold range, so that if the alarm is given for the abnormal physiological parameter at this time, unnecessary human and material resources will be wasted to analyze the reason for the alarm. Therefore, the alarm for the abnormal physiological parameter is shielded, thereby reducing the false alarm or meaningless alarm caused by the patient's activity. For example, after the abnormal physiological parameter alarms, if the alarm is given again within a certain time, the alarm can not be responded to, or the alarm can be shielded, and the certain time can be referred to as the refractory period. In some embodiments, after the alarm for the physiological parameter is shielded, the information output unit can not output the alarm prompt in the form of sound, light and / or touch, but can display the alarm on the display unit, so that the medical staff knows that the shielded alarm is generated.

[0124] As described above, when generating the image-related alarm strategy, the image-related alarm strategy can be generated according to the analysis result of the image processing unit 210, or the image-related alarm strategy can be generated according to the analysis result and the physiological parameter with at least part of the abnormality.

[0125] In some embodiments, when the analysis result characterizing the activity state of the patient further comprises information of a motion part of the patient, such as "right upper limb motion", "both legs motion", etc., the data processing unit 220 can mask the alarm of the physiological parameter with abnormality related to the motion part of the patient based on the image-related alarm strategy, or generate a second alarm event.

[0126] In some embodiments, when the analysis result characterizing the activity state of the patient further comprises information of a cared part of the patient, such as "right upper limb care", "both legs care", etc., the data processing unit 220 can mask the alarm of the physiological parameter with abnormality related to the cared part of the patient based on the image-related alarm strategy, or generate a second alarm event. For example, when the blood oxygen of the hand of the patient is measured, if the hand of the patient moves or the hand of the patient is cared, it can cause the blood oxygen parameter to have a reasonable abnormality, and the alarm of the abnormal blood oxygen parameter can be masked based on the image-related alarm strategy, or a second alarm event of the blood oxygen parameter can be generated. In this embodiment, since the patient can only affect the local physiological parameter when the local motion and the local care are generated, such as affecting the physiological parameter related to the motion part and the cared part, the alarm of the physiological parameter related to the motion part and the cared part can be masked or the second alarm event can be generated, so that more accurate physiological parameter monitoring can be performed.

[0127] In some embodiments, when the analysis result characterizing the activity state of the patient is received, the alarm event can be enhanced or suppressed relative to the original alarm strategy based on the analysis result characterizing the activity state of the patient, so as to generate the image-related alarm strategy. In this embodiment, when the alarm event of the physiological parameter is enhanced based on the analysis result characterizing the activity state of the patient, it is hoped that the medical staff will pay more attention to the alarm of the physiological parameter at this time. For example, when the analysis result characterizing the activity state of the patient comprises information characterizing the restlessness of the patient and / or information characterizing the bed falling of the patient, the alarm event of the physiological parameter needs to be enhanced, so that the medical staff will pay more attention to the alarm of the physiological parameter when the patient is restless and the patient falls out of bed. In some embodiments, when the alarm event is enhanced relative to the original alarm strategy based on the image-related alarm strategy, the alarm event of the image-related alarm strategy can be prompted in a way with higher attention, such as higher than the attention of the alarm event of the original alarm strategy.

[0128] In some embodiments, when the alarm event of the physiological parameter is suppressed based on the analysis result representing the activity state of the patient, it is desired that the medical staff pay less attention to the alarm generated by the physiological parameter at this time, for example, when the analysis result representing the activity state of the patient includes information representing that the patient is moving and / or being cared for, the alarm event of the physiological parameter needs to be suppressed so that the medical staff pays less attention to the alarm generated by the physiological parameter when the patient is moving and being cared for, thereby reducing unnecessary interference of the alarm caused by the patient's activity on the medical staff.

[0129] In some embodiments, when the analysis result is received, the data processing unit generates an image-related alarm strategy for the corresponding patient based at least on the analysis result, adjusts the parameter value of the physiological parameter of the patient according to the image-related alarm strategy, determines the abnormal physiological parameter based on the adjusted parameter value, generates an alarm event based on the image-related alarm strategy, and the alarm event includes the abnormal physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, so that the information output unit generates an alarm prompt in the corresponding mode for the physiological parameter generating the alarm based on the alarm event. The way of adjusting the parameter value of the physiological parameter of the patient according to the image-related alarm strategy can adopt the parameter value preserving and anti-shake mode.

[0130] Please refer to Figure 8 , wherein the value preserving processing includes the following steps.

[0131] Step 600: receiving the physiological parameter of the patient.

[0132] Step 610: determining whether the current parameter value of the physiological parameter exceeds the set threshold range. For example, the received current parameter value of the physiological parameter and the set threshold range can be compared, and if it does not exceed the set threshold range, the alarm event is not triggered. If the current parameter value exceeds the set threshold range, step 620 is performed to determine whether the cumulative number of consecutive threshold range exceedances is less than a first preset value. If it is less than the first preset value, step 630 is performed to adjust the current parameter value to a value within the set threshold range. For example, the value is adjusted to the same value as the average of the previous parameter value or the average of the previous multiple parameter values, and the alarm event is not triggered, otherwise step 640 is performed to trigger the alarm event.

[0133] The anti-shake processing can be to compare the received current parameter value of the physiological parameter with the set threshold range, and if the current parameter value exceeds the set threshold range, to determine whether the cumulative number of consecutive threshold range exceedances is greater than a second preset value. If it is greater than the second preset value, the alarm event is triggered, otherwise the alarm event is not triggered.

[0134] In some embodiments, the image-related alarm strategy can adjust the parameter value of the physiological parameter of the patient, determine the abnormal physiological parameter based on the adjusted parameter value, and generate an alarm event based on the image-related alarm strategy, wherein the alarm event comprises the abnormal physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, so that the information output unit prompts the alarm of the physiological parameter in the corresponding mode based on the alarm event. In this embodiment, before determining whether the physiological parameter is abnormal, the image-related alarm strategy adjusts the parameter value of the physiological parameter of the patient, so that the adjusted physiological parameter is more likely to be determined as an abnormal physiological parameter, thereby making the corresponding physiological parameter be more focused, or making the adjusted physiological parameter more difficult to be determined as an abnormal physiological parameter, thereby making the corresponding physiological parameter be less focused.

[0135] In some embodiments, when adjusting the parameter value of the physiological parameter of the patient, the image-related alarm strategy can perform anti-shake processing on the parameter value of the physiological parameter. In this embodiment, because the cumulative number of times of exceeding the threshold range needs to be greater than or equal to the first preset value to trigger the generation of the alarm event during the value-preserving processing, the adjusted physiological parameter is more difficult to be determined as an abnormal physiological parameter, which can be suitable for physiological parameters that are reasonably affected by patient activities, such as when the patient is exercising or being nursed, so that the physiological parameter is less focused when the patient is active. For example, for the heart rate of the patient, when the patient is not active, the heart rate is 81, and when the patient is active, the heart rate is 101. Assuming that the heart rate of 101 exceeds the set threshold range, if the cumulative number of times of continuously exceeding the threshold range is less than the first preset value, the heart rate of 101 is adjusted to the heart rate of 81, and the generation of the alarm event is not triggered. On the contrary, if the cumulative number of times of continuously exceeding the threshold range is greater than or equal to the first preset value, the generation of the alarm event is triggered. In some embodiments, when adjusting the parameter value of the physiological parameter of the patient, in order to make the adjusted physiological parameter more difficult to be determined as an abnormal physiological parameter, the image-related alarm strategy can also perform anti-shake processing on the parameter value of the physiological parameter. In some embodiments, when adjusting the parameter value of the physiological parameter of the patient, for physiological parameters that are unreasonably affected by patient activities, such as when the patient is agitated or falls out of bed, the image-related alarm strategy can also make the adjusted physiological parameter more likely to be determined as an abnormal physiological parameter, such as increasing the current parameter value of the physiological parameter or reducing the threshold range.

[0136] Those skilled in the art can understand that all or part of the functions of various methods in the above embodiments can be realized by hardware or by a computer program. When all or part of the functions in the above embodiments are realized by a computer program, the program can be stored in a computer readable storage medium, which can include read-only memory, random access memory, magnetic disk, optical disk, hard disk, etc. The above functions are realized by executing the program by a computer. For example, the program is stored in the memory of the device, and the above functions are realized by executing the program in the memory by the processor. In addition, when all or part of the functions in the above embodiments are realized by a computer program, the program can also be stored in a storage medium such as a server, another computer, a disk, an optical disk, a flash disk or a mobile hard disk, and is saved in the memory of the local device by downloading or copying, or the system of the local device is updated, and the above functions are realized by executing the program in the memory by the processor. For example, the image processing unit can be one chip or composed of multiple chips, and the data processing unit can be one chip or composed of multiple chips. When the data processing unit is composed of multiple chips, each chip can execute one or more functions, for example, some chips are used to process physiological parameters, some chips are used to process received activity information of the patient and calculate the correlation coefficient, and some chips are used to process visual data. Of course, those skilled in the art can understand that the functions of the image processing unit and the data processing unit can also be realized by one chip.

[0137] The above application of specific examples to the present application is described, which is only used to help understand the present application and does not limit the present application. For those skilled in the art, according to the idea of the present application, several simple deductions, deformations or substitutions can be made.

Claims

1. A patient monitoring system, characterized by The application comprises: a physiological parameter information input unit configured to receive physiological parameters of patients output by at least one sensor or monitor; an image processing unit configured to acquire image data containing patients associated with at least one image acquisition device and analyze image data of each patient to output an analysis result representing an activity state of the patient; a data processing unit configured to determine an abnormal physiological parameter based on a parameter value of the physiological parameter, generate a first alarm event for the abnormal physiological parameter based on an original alarm strategy when the analysis result is not received, and generate an image-related alarm strategy based on at least the analysis result or both the analysis result and at least part of the abnormal physiological parameter when the analysis result is received, and mask alarms for at least part of the abnormal physiological parameter based on the image-related alarm strategy or generate a second alarm event based on the image-related alarm strategy, wherein the second alarm event has an alarm prompt mode different from that of the first alarm event; an information output unit configured to prompt alarms for the physiological parameter based on the first alarm event or the second alarm event in different ways, wherein the alarm prompt includes at least one of auditory, visual and tactile prompts; wherein the analysis result representing the activity state of the patient includes information representing that the patient is being cared for; the analysis result representing the activity state of the patient further includes information of a cared-for part of the patient, and the data processing unit masks alarms for the abnormal physiological parameter related to the cared-for part of the patient based on the image-related alarm strategy or generates the second alarm event. The second alarm event has a lower degree of attention than the first alarm event.

2. The system of claim 1, wherein, The information output unit comprises a display unit, and a display interface of the display unit comprises at least one display area, each display area being configured to display at least one physiological parameter of a patient and highlight a physiological parameter having an alarm event.

3. The system of claim 1 or 2, wherein, The display unit further displays a prompt identifier representing the analysis result corresponding to the patient in the display area corresponding to the patient.

4. The system of claim 3, wherein, The prompt identifier of the analysis result includes at least one of a character string, a schematic diagram and a thumbnail.

5. The system of claim 4, wherein, The prompt identifier is associated with image data corresponding to the analysis result, the display unit outputs a play instruction after detecting that the prompt identifier is triggered, and the data processing unit outputs the image data to a predetermined area of the display unit for display based on the play instruction.

6. The system of claim 4, wherein, Further comprising a storage unit, and the data processing unit stores at least the second alarm event, the analysis result corresponding to the second alarm event and image data corresponding to the analysis result in the storage unit, and outputs the corresponding image data to a predetermined area of the display unit for display when a playback instruction is received.

7. The system of claim 3, wherein, The application comprises:

8. A patient monitoring system characterized by a physiological parameter information input unit configured to receive physiological parameters of patients output by at least one sensor or monitor; ​ an image processing unit configured to acquire image data output by at least one image acquisition device, the image data comprising a patient associated with the image acquisition device, and analyze image data of each patient to output an analysis result representing an activity state of the patient; a data processing unit configured to determine a physiological parameter having an abnormal parameter value based on the parameter value of the physiological parameter; an information output unit, the information output unit comprising a display unit, a display interface of the display unit comprising at least one display area, each patient having a corresponding display area, at least one physiological parameter of each patient being displayed in the corresponding display area of the patient, the data processing unit displaying a prompt identifier representing the analysis result corresponding to the patient in the display area corresponding to the patient, and highlighting the physiological parameter having an abnormal parameter value, a display area of the physiological parameter having an abnormal parameter value, or a display area of the patient corresponding to the physiological parameter having an abnormal parameter value; wherein the analysis result representing the activity state of the patient comprises information representing that the patient is being cared for; the analysis result representing the activity state of the patient further comprises information of a cared-for part of the patient, an image-related alarm strategy is generated based on at least the analysis result or simultaneously based on the analysis result and at least part of the physiological parameters having an abnormal parameter value, and the data processing unit masks an alarm of the physiological parameter having an abnormal parameter value related to the cared-for part of the patient based on the image-related alarm strategy.

9. The system of claim 8, wherein, The prompt identifier of the analysis result comprises at least one of a character string, a schematic diagram, and a thumbnail.

10. The system of claim 8, wherein, The data processing unit generates a first alarm event for the physiological parameter having an abnormal parameter value based on an original alarm strategy when the analysis result is not received; when the analysis result is received, an alarm of at least part of the physiological parameters having an abnormal parameter value is masked based on the image-related alarm strategy, or a second alarm event is generated based on the image-related alarm strategy, the alarm prompt mode of the second alarm event being at least partially different from that of the first alarm event, the alarm prompt comprising at least one of auditory, visual, and tactile prompts.

11. The system of claim 8, wherein, The prompt identifier is associated with image data corresponding to the analysis result, the display unit outputs a playback instruction after detecting that the prompt identifier is triggered, and the data processing unit outputs associated image data of a predetermined time period to a predetermined area of the display unit based on the playback instruction and displays the physiological parameter having an abnormal parameter value on the same screen.

12. The system of claim 8, wherein, The display interface of the display unit displays at least one physiological parameter of one patient, and the prompt identifier of the analysis result is displayed in an area close to the physiological parameter having an abnormal parameter value.

13. A patient monitoring system, characterized by comprising: a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or monitor; an image processing unit configured to acquire image data output by at least one image acquisition device, the image data comprising a patient associated with the image acquisition device, and analyze image data of each patient to output an analysis result representing an activity state of the patient; The data processing unit is configured to determine abnormal physiological parameters based on parameter values of the physiological parameters, generate an image-related alarm strategy for the corresponding patient based on at least the analysis result or both the analysis result and at least part of the abnormal physiological parameters upon receiving the analysis result, and mask alarms or generate alarm events for at least part of the abnormal physiological parameters based on the image-related alarm strategy, the alarm events including an alarm physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, so that the information output unit alarms the alarm physiological parameter in the corresponding mode based on the alarm events. The analysis result indicating the activity state of the patient includes information indicating that the patient is being cared for. The analysis result indicating the activity state of the patient further includes information of a cared-for part of the patient, and the data processing unit masks alarms of the abnormal physiological parameters related to the cared-for part of the patient based on the image-related alarm strategy.

14. A patient monitoring system, characterized by The system comprises: a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or monitor; an image processing unit configured to acquire image data containing the patient associated with the image acquisition device output by at least one image acquisition device, and analyze the image data of each patient to output an analysis result indicating the activity state of the patient; a data processing unit configured to monitor physiological parameters and generate alarm events based on an original alarm strategy when the analysis result is not received, and generate an image-related alarm strategy based on at least the analysis result when the analysis result is received, monitor physiological parameters and generate alarm events based on the image-related alarm strategy, the image-related alarm strategy relative to the original alarm strategy causing the alarm events to be enhanced or suppressed; The analysis result indicating the activity state of the patient includes information indicating that the patient is being cared for. The analysis result indicating the activity state of the patient further includes information of a cared-for part of the patient, and the data processing unit masks alarms of the abnormal physiological parameters related to the cared-for part of the patient based on the image-related alarm strategy.

15. The system of claim 14, wherein, The image-related alarm strategy relative to the original alarm strategy causes the alarm events to be suppressed in any of the following ways: masking events of physiological parameters determined to be abnormal; alarm prompting in a less-attended mode; value-preserving processing or anti-jitter processing of parameter values of physiological parameters.

16. The system of claim 14, wherein, The image-related alarm strategy relative to the original alarm strategy causes the alarm events to be enhanced in the following way: alarm prompting in a more-attended mode.

17. A patient monitoring system, characterized by The system comprises: a physiological parameter information input unit configured to receive physiological parameters of a patient output by at least one sensor or monitor; an image processing unit configured to acquire image data containing the patient associated with the image acquisition device output by at least one image acquisition device, and analyze the image data of each patient to output an analysis result indicating the activity state of the patient; The data processing unit is configured to generate an image-related alarm strategy for the patient based on the analysis result when the analysis result is received, adjust a parameter value of a physiological parameter of the patient according to the image-related alarm strategy, determine an abnormal physiological parameter based on the adjusted parameter value, generate an alarm event based on the image-related alarm strategy, and the alarm event includes the abnormal physiological parameter and an alarm prompt mode corresponding to the image-related alarm strategy, so that the information output unit generates an alarm prompt in the corresponding mode for the physiological parameter that generates the alarm based on the alarm event. The analysis result indicating the activity state of the patient includes information indicating that the patient is being cared for. The analysis result indicating the activity state of the patient further includes information of a cared-for part of the patient, and the data processing unit masks the alarm of the abnormal physiological parameter related to the cared-for part of the patient based on the image-related alarm strategy.

18. The system of claim 17, wherein, The adjusting of the parameter value of the physiological parameter of the patient according to the image-related alarm strategy and the determination of the abnormal physiological parameter based on the adjusted parameter value, and the generation of the alarm event based on the image-related alarm strategy include: comparing the current parameter value of the received physiological parameter with a set threshold range; if the current parameter value exceeds the set threshold range, determining whether the cumulative number of continuous threshold range exceedings is less than a first preset value, if yes, adjusting the current parameter value to a value within the set threshold range, and not triggering the generation of the alarm event, otherwise, triggering the generation of the alarm event; or the adjusting of the parameter value of the physiological parameter of the patient according to the image-related alarm strategy and the determination of the abnormal physiological parameter based on the adjusted parameter value, and the generation of the alarm event based on the image-related alarm strategy include: comparing the current parameter value of the received physiological parameter with a set threshold range; if the current parameter value exceeds the set threshold range, determining whether the cumulative number of continuous threshold range exceedings is greater than a second preset value, if yes, triggering the generation of the alarm event, otherwise, not triggering the generation of the alarm event.

19. A method of patient monitoring, characterized by The method includes: receiving physiological parameters of a patient output by at least one sensor or monitor; receiving an analysis result indicating the activity state of the patient, the analysis result being obtained based on image data output by an image acquisition device and containing the patient associated with the image acquisition device; determining an abnormal physiological parameter based on the parameter value of the physiological parameter, and generating an alarm event; displaying at least one physiological parameter of at least one patient received on a display interface, the display interface including at least one display area, each display area corresponding to one patient, each patient having a corresponding display area, and each display area corresponding to the patient displaying at least one physiological parameter of the patient, when an analysis result associated with the patient is received, displaying a prompt identifier indicating the analysis result corresponding to the patient in the display area corresponding to the patient, and when an abnormal physiological parameter is determined, highlighting the display area of the abnormal physiological parameter or the patient corresponding to the abnormal physiological parameter. The analysis result characterizing the activity state of the patient comprises information characterizing that the patient is being cared for; The analysis result characterizing the activity state of the patient further comprises information of a cared-for site of the patient, and an image-related alarm strategy is generated based at least on the analysis result or simultaneously based on the analysis result and at least part of the abnormal physiological parameters, and the data processing unit screens alarms of the abnormal physiological parameters related to the cared-for site of the patient based on the image-related alarm strategy.

20. The method of claim 19, wherein, The abnormal physiological parameters are determined based on the parameter values of the physiological parameters, and an alarm event is generated, comprising: a first alarm event for the abnormal physiological parameters is generated based on an original alarm strategy when the analysis result is not received; when the analysis result is received, alarms for at least part of the abnormal physiological parameters are screened based on the image-related alarm strategy, or a second alarm event is generated, and the alarm prompt mode of the second alarm event is at least partially different from that of the first alarm event, and the alarm prompt comprises at least one of auditory, visual and tactile prompts.

21. The method of claim 20, wherein, The attention of the alarm prompt mode of the second alarm event is lower than that of the alarm prompt mode of the first alarm event.

22. The method of claim 19, wherein, The prompt identifier of the analysis result comprises at least one of a string, a schematic diagram and a thumbnail.

23. The method of claim 19, wherein Further comprising, the prompt identifier is associated with image data corresponding to the analysis result, a play instruction is generated after it is detected that the prompt identifier is triggered, and image data is output to a predetermined area of a display interface based on the play instruction and displayed on the same screen with the abnormal physiological parameters.

24. The method of claim 19, wherein Further comprising, at least the alarm event, the analysis result corresponding thereto and the image data corresponding to the analysis result are associated and saved, and when a playback instruction for the alarm event or the analysis result is received, the corresponding image data is output to a predetermined area of a display interface for display.

25. A patient monitoring system, characterized by comprising: an image acquisition device associated with a patient, for shooting and outputting image data containing the patient associated with the image acquisition device; a monitor for receiving physiological parameter signals of a patient detected by at least one sensor and outputting parameter values of the physiological parameters of the patient after processing; a server for acquiring image data containing a patient associated with at least one image acquisition device output by the image acquisition device, and analyzing image data of each patient to output an analysis result characterizing the activity state of the patient; a central station for executing the method of any one of claims 19-24.

26. A computer-readable storage medium, characterized in that, The medium has a program stored thereon, which can be executed by a processor to implement the method of any one of claims 19-24. The medium has a program stored thereon, which can be executed by a processor to implement the method of any one of claims 19-24.

Images