Monitor data feature comparison method and device, monitor and product

Abstract

The invention provides a monitor data feature comparison method and device, a monitor and a product, and the method comprises the steps: carrying out the time marking of collected vital sign data, splitting the data, and obtaining the vital sign data of different vital sign types; performing feature extraction on each type of vital sign data in a predetermined time period to obtain one or more predetermined feature parameters associated with each type of vital sign data; calculating a first similarity of each predetermined feature parameter; calculating the parameter similarity of each predetermined feature parameter through the first similarity of each predetermined feature parameter; calculating the vital sign similarity according to the parameter similarity of each predetermined feature parameter contained in each type of vital sign data; and calculating the patient similarity through the vital sign similarity of each type of vital sign data. By means of the technical scheme, new patients can be automatically recognized to avoid data chaos, and it is ensured that data recorded by the monitor is accurate.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing, and in particular to a method, a device, a monitor and a product for comparing monitor data characteristics. Background Art

[0002] In modern medical practice, monitors are important devices for monitoring and recording patients' vital signs, and they play an important role in timely detecting patients' critical conditions and assisting clinical decision-making. Patients need to wear monitors to collect vital signs, including electrocardiogram, blood pressure, blood oxygen, respiration, end-tidal carbon dioxide, electroencephalogram, electromyography, etc. In many medical scenarios, such as when there are many patients in the emergency department and ICU and medical staff are busy, the monitor is in a long-term power-on state. When each bed is replaced with a patient, the monitor will not shut down and restart and register new patient information, resulting in the same monitor actually recording the information of multiple patients in a period of time, but the information of multiple patients is marked as the information of the same patient in the memory of the monitor, that is, the name, age and other information of the previous patient are still displayed on the monitor interface. This situation will cause medical staff to have incorrect patient information and incorrect acquisition of patients' vital sign parameters when viewing the monitor or central monitoring system, which will bring more serious adverse consequences to the patient's ward tracking and medication decision-making. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, monitor and product for comparing monitor data features, so as to realize automatic identification of new patients to avoid data confusion and ensure that the data recorded by the monitor is accurate.

[0004] In order to achieve the above object, on the one hand, a method for comparing data features of a monitor is provided, the method comprising:

[0005] Step S1, time-stamping the vital sign data collected by the monitor at a predetermined frequency to obtain the vital sign data with time stamp;

[0006] Step S2, splitting the vital sign data with time stamps according to predetermined vital sign types to obtain vital sign data of different vital sign types with time stamps; wherein the vital sign types include electrocardiogram, blood pressure, blood oxygen, respiratory wave and / or electroencephalogram;

[0007] Step S3, performing feature extraction on each type of vital sign data within a predetermined time period, and obtaining one or more predetermined feature parameters associated with each type of vital sign data within the predetermined time period;

[0008] Step S4, for one or more predetermined characteristic parameters associated with each type of vital sign data within the predetermined time period, by comparing the value at a selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period saved in advance, to calculate a first similarity of each predetermined characteristic parameter within the predetermined time period and at each time granularity, wherein the time granularity includes: seconds;

[0009] Step S5, obtaining the parameter similarity corresponding to each of the predetermined characteristic parameters by calculating the average value of the first similarity of each of the predetermined characteristic parameters within the predetermined time period and at each of the time granularities;

[0010] Step S6, performing weighted calculation on the parameter similarities corresponding to the predetermined characteristic parameters contained in each type of vital sign data according to the weights preset for the predetermined characteristic parameters, to obtain the vital sign similarities corresponding to each type of vital sign data;

[0011] Step S7, performing weighted calculation according to the vital sign similarity corresponding to each type of vital sign data and the weight preset for each type of vital sign data, to obtain the patient similarity.

[0012] Preferably, the method for comparing the characteristics of the monitor data comprises:

[0013] The predetermined characteristic parameters associated with the electrocardiogram include: parameters related to the QRS wave characteristics of each heartbeat; the parameters related to the QRS wave characteristics of each heartbeat include: PR interval, RQS width, R wave amplitude, ST segment elevation amplitude, ST segment depression amplitude, P wave amplitude, S wave amplitude, compensatory interval, QRS area, time interval between every two heartbeats and / or pp interval;

[0014] The predetermined characteristic parameters associated with the respiratory wave include: flow rate, pressure, volume, respiratory rate, respiratory ratio and / or PEEP level;

[0015] The predetermined characteristic parameters associated with the electroencephalogram include: alpha wave, alpha wave frequency, amplitude, rhythm, beta wave frequency and / or amplitude rhythm.

[0016] Preferably, the method for comparing monitor data features further includes, when the patient similarity is higher than a preset threshold, determining that the patient to which the vital signs data collected this time and the vital signs data collected last time belong is the same person; when the patient similarity is lower than the preset threshold, determining that the vital signs data collected this time belongs to a new patient.

[0017] Preferably, the method for comparing the characteristics of the monitor data, wherein the first similarity of each predetermined characteristic parameter in the predetermined time period and at each time granularity is calculated by comparing the value at a selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period saved in advance, comprises:

[0018] The first similarity=1-(the absolute value of the difference between the first value of the predetermined characteristic parameter in each current predetermined time period at the selected moment and the second value corresponding to the predetermined characteristic parameter in the previous predetermined time period saved in advance at the selected moment / the larger data value between the first value and the second value).

[0019] Preferably, in the method for comparing features of monitor data, the first similarity in step S4 can be obtained by normalization, cosine similarity, Euclidean distance, Manhattan distance, dynamic time warping, Pearson correlation coefficient, Jaccard similarity coefficient or Gaussian kernel similarity calculation.

[0020] Preferably, in the method for comparing features of monitor data, step S1 is performed when the following scenario occurs:

[0021] Restart the monitor; or,

[0022] The monitor will re-collect vital sign data after a preset period of time without sampling in the running state.

[0023] Preferably, in the method for comparing features of monitor data, in step S1, time-stamping the vital sign data collected by the monitor at a predetermined frequency comprises:

[0024] The vital sign data is associated with the current system time of the monitor according to a predetermined frequency to obtain the vital sign data with a time stamp.

[0025] On the other hand, the present invention provides a device for comparing monitor data features, which includes a memory and a processor, the memory stores at least one program, and the at least one program is executed by the processor to implement the method for comparing monitor data features as described above.

[0026] In yet another aspect, the present invention provides a monitor, which includes the device for comparing monitor data features as described above.

[0027] In yet another aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for comparing features of monitor data as described above is implemented.

[0028] The above technical solution has the following technical effects:

[0029] The technical solution of the embodiment of the present invention obtains time-stamped vital signs data by time-stamping the vital signs data collected by the monitor; splits the time-stamped vital signs data into vital signs data of different vital signs types according to predetermined vital signs types; extracts features of each type of vital signs data within a predetermined time period to obtain predetermined feature parameters associated with each type of vital signs data; and designs multiple similarity calculations for the values ​​of the predetermined feature parameters of each type of extracted vital signs data, including similarity calculations for a single parameter and each time granularity such as seconds; overall similarity calculations for a single parameter; similarity calculations for different types of vital signs; and finally patient similarity calculations. The use of the above-mentioned similarities can not only improve the accuracy of patient identification, but also ensure the clarity and consistency of monitor data, thereby effectively avoiding data confusion and improving the quality and safety of medical monitoring.

[0030] In a further embodiment, patient similarity is used to determine whether the vital sign data collected by the monitor belongs to a new patient, so that new patients can be automatically identified, thereby ensuring the accuracy of patient data, reducing the risk of medical errors, and improving the safety and efficiency of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a flow chart of a method for comparing features of monitor data according to an embodiment of the present invention;

[0032] Figure 2 It is an overall flow chart of a method for comparing features of monitor data according to an embodiment of the present invention;

[0033] Figure 3 In the method for comparing the characteristics of monitor data according to an embodiment of the present invention, the values ​​of the predetermined characteristic parameters of the electrocardiogram measured within the current 5 seconds and the previous 5 seconds are taken every second;

[0034] Figure 4 An example of parameter similarity corresponding to predetermined feature parameters of different feature types in a method for comparing features of monitor data according to an embodiment of the present invention;

[0035] Figure 5 An example of calculating the similarity of electrocardiogram feature types in a method for comparing features of monitor data according to an embodiment of the present invention;

[0036] Figure 6 This is a schematic diagram of an output result interface in a system using a monitor data feature comparison method according to an embodiment of the present invention;

[0037] Figure 7 FIG. 4 is a schematic diagram of a device for comparing features of monitor data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] To further illustrate the various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, a person of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0039] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0040] Embodiment 1:

[0041] In order to automatically identify new patients to avoid confusion in monitor data and ensure that the data recorded by the monitor is accurate, an embodiment of the present invention provides a method for comparing monitor data features. Figure 1 FIG. 1 is a flow chart of a method for comparing features of monitor data according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0042] Step S1, time-stamping the vital sign data collected by the monitor at a predetermined frequency to obtain the vital sign data with time stamp;

[0043] Step S2, splitting the vital sign data with time stamps according to predetermined vital sign types to obtain vital sign data of different vital sign types with time stamps; wherein the vital sign types include electrocardiogram, blood pressure, blood oxygen, respiratory wave and / or electroencephalogram;

[0044] Step S3, extracting features of each type of vital sign data within a predetermined time period, and obtaining one or more predetermined feature parameters associated with each type of vital sign data within the predetermined time period;

[0045] Step S4, for one or more predetermined characteristic parameters associated with each type of vital sign data within the predetermined time period, by comparing the value at a selected moment in the current predetermined time period with the corresponding value at a selected moment in the previous predetermined time period saved in advance, to calculate a first similarity of each predetermined characteristic parameter within the predetermined time period and at each time granularity, the time granularity including: seconds;

[0046] Step S5, obtaining the parameter similarity corresponding to each predetermined characteristic parameter by calculating the average value of the first similarity of each predetermined characteristic parameter in a predetermined time period and at each time granularity;

[0047] Step S6, performing weighted calculation on the parameter similarities corresponding to the predetermined characteristic parameters contained in each type of vital sign data according to the weights preset for each predetermined characteristic parameter, to obtain the vital sign similarities corresponding to each type of vital sign data;

[0048] Step S7, performing weighted calculation according to the vital sign similarity corresponding to each type of vital sign data and the weight preset for each type of vital sign data, to obtain the patient similarity.

[0049] Embodiment 2:

[0050] The embodiment of the present invention aims at the problem of data record confusion caused by a monitor not being restarted for a long time and not entering new patient information in a medical scenario, and proposes a method for comparing monitor data features. Figure 2 FIG. 1 is an overall flow chart of a method for comparing features of monitor data according to an embodiment of the present invention. Figure 2 As shown, the overall process of the method includes:

[0051] Step 1: Real-time detection of the monitoring device's collection status, monitoring the vital signs data actually collected by the monitoring device; when a predetermined condition is met, time-stamping the actual vital signs data collected each time, and obtaining vital signs data with time-stamping. Preferably, the time-stamping is accurate to seconds.

[0052] Preferably, the predetermined condition includes: restarting the monitor; or, the monitor re-collecting vital sign data after a predetermined period of time in a running state.

[0053] In a specific embodiment, after the monitor is started, the collection state of the monitor is detected in real time, and the vital sign data actually collected by the monitor is monitored. Whenever the monitor is restarted or the monitor collects vital sign data again after a predetermined period of time in the running state, the currently collected vital sign data is associated with the current system time of the monitor according to a predetermined frequency to obtain vital sign data with a time mark. Preferably, the predetermined frequency is every second.

[0054] Step 2: After parsing the vital sign data with time stamps according to the protocols of different types of monitors, the data are split according to predetermined vital sign types to obtain vital sign data of different vital sign types with time stamps.

[0055] Preferably, the predetermined vital sign types include: electrocardiogram, blood pressure, blood oxygen, respiratory wave and / or electroencephalogram.

[0056] Step 3: extract features from each type of vital sign data within a predetermined time period, obtain one or more predetermined feature parameters associated with each type of vital sign data within the predetermined time period, and save the one or more predetermined feature parameters associated with each type of vital sign data within the predetermined time period. In a specific implementation, the predetermined time period is 5 seconds.

[0057] In a specific embodiment, the predetermined characteristic parameters associated with the electrocardiogram include: parameters related to the QRS wave characteristics of each heartbeat; wherein the parameters related to the QRS wave characteristics of each heartbeat include: PR interval, RQS width, R wave amplitude, ST segment elevation amplitude, ST segment depression amplitude, P wave amplitude, S wave amplitude, compensatory interval, QRS area, the time interval between every two heartbeats (RR interval) and / or pp interval.

[0058] In a specific embodiment, the predetermined characteristic parameters associated with the respiratory wave include: flow rate, pressure, volume, respiratory rate, respiratory ratio and / or PEEP level.

[0059] In a specific embodiment, the predetermined characteristic parameters associated with the electroencephalogram include: alpha waves, alpha wave frequency, amplitude, rhythm, beta wave frequency and / or amplitude rhythm.

[0060] In a specific embodiment, each type of split vital signs data is combined with time for feature extraction, and merged with similar feature parameters extracted from each type of vital signs data received this time and each type of vital signs data of the latest 4 seconds to obtain each feature parameter contained in each type of vital signs data of 5 seconds, and each feature parameter contained in each type of vital signs data of 5 seconds is saved.

[0061] Step four, for one or more predetermined characteristic parameters associated with each type of vital sign data within the predetermined time period, calculate the first similarity of each predetermined characteristic parameter within the predetermined time period and at each time granularity by comparing the value at the selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period that was saved in advance. In this embodiment, the time granularity is seconds.

[0062] In a specific implementation, calculating the first similarity of each predetermined feature parameter in the predetermined time period and at each time granularity by comparing the value at the selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period saved in advance includes:

[0063] The first similarity = 1-(the absolute value of the difference between the first value of the predetermined characteristic parameter in each current predetermined time period at the selected moment and the second value corresponding to the predetermined characteristic parameter in the previous predetermined time period saved in advance at the selected moment / the larger data value between the first value and the second value).

[0064] In a specific embodiment, the first similarity of each predetermined characteristic parameter within the predetermined time period and at each time granularity is calculated by comparing the value at the selected moment within the current predetermined time period with the corresponding value at the selected moment within the previous predetermined time period that was saved in advance: first similarity = 1-(the absolute value of the difference between the value of each predetermined characteristic parameter within the current predetermined time period at the selected moment and the corresponding value of the predetermined characteristic parameter within the previous predetermined time period that was saved in advance at the selected moment / the pre-set value for each predetermined characteristic parameter).

[0065] Preferably, there are many different ways to calculate the first similarity, which can be selected or improved according to the characteristics of the feature parameters, the required accuracy, the calculation efficiency and the actual situation; for example, the first similarity is calculated by Euclidean distance, Manhattan distance or Jaccard similarity coefficient.

[0066] In a specific embodiment, in order to improve the accuracy of similarity calculation, a normalization method can be used to normalize each feature parameter to a relative proportion to avoid the dimensional differences of different vital signs. For feature parameters of different vital sign types, the feature parameters are first normalized and the standardized differences of the feature parameters are calculated, which can reduce the scale influence between different feature parameter values. The first similarity is calculated by the following similarity calculation formula:

[0067]

[0068] The characteristic parameter value represents the characteristic parameter value at the selected moment in the current scheduled time period, and the characteristic parameter value 2 represents the corresponding characteristic parameter value at the selected moment in the previous scheduled time period that was saved in advance.

[0069] In a specific embodiment, for the first similarity calculation, if the characteristic parameter value at the selected moment in the current predetermined time period and the corresponding characteristic parameter value at the selected moment in the previous predetermined time period stored in advance show obvious periodicity or time series characteristics, the first similarity is calculated by dynamic time warping (DTW) or cosine similarity; when the characteristic parameter is time series data (i.e., the RR interval of the electrocardiogram), the characteristic parameter value is regarded as a vector, and the first similarity is calculated by the following formula:

[0070]

[0071] A represents the characteristic parameter value of the selected moment in the current scheduled time period, and B represents the corresponding characteristic parameter value of the selected moment in the previous scheduled time period that was saved in advance.

[0072] In a specific embodiment, if it is necessary to measure the linear relationship between the characteristic parameter value at a selected moment in the current predetermined time period and the corresponding characteristic parameter value at a selected moment in the previous predetermined time period saved in advance, the first similarity is calculated by the Pearson correlation coefficient;

[0073] In a specific embodiment, for higher dimensional or nonlinear feature parameter values, the first similarity is calculated by Gaussian kernel similarity. Figure 3 In the method for comparing the characteristics of monitor data in one embodiment of the present invention, the values ​​of the predetermined characteristic parameters of the electrocardiogram measured within the current 5 seconds and the previous 5 seconds are taken every second. Figure 3 In the example shown, the predetermined time period is 5 seconds, and 5 seconds is used as a time period to obtain the values ​​of the characteristic parameters RR interval, P wave amplitude, and ST elevation amplitude associated with the vital sign data of the electrocardiogram within 5 seconds, and then compare the values ​​of each characteristic parameter in each second of the current 5 seconds with the values ​​saved at the corresponding moment in the previous 5 seconds. For example, for the RR interval parameter, the value of 890 milliseconds in the first second of the current time is compared with the value of 900 milliseconds in the first second of the previous 5 seconds, and according to the predetermined algorithm, the similarity of the characteristic parameter in the first second, i.e., the first similarity, is obtained.

[0074] In a specific embodiment, Figure 3 As shown, when the characteristic parameter RR interval has a first similarity of: 1-(|900-890| / 900)=0.99 at the first second; its first similarity of: 1-(|990-890| / 990)=0.9 at the second second.

[0075] Step 5: Calculate the average value of the first similarity of each predetermined feature parameter in a predetermined time period and at each time granularity to obtain the parameter similarity corresponding to each predetermined feature parameter. Figure 4 This is an example of parameter similarity corresponding to predetermined feature parameters of different feature types in a method for comparing features of monitor data according to an embodiment of the present invention. Figure 4 As shown, for multiple first similarities of the same feature parameter at different times, the parameter similarity of the feature parameter can be obtained by averaging the multiple first similarities calculated for the same feature parameter.

[0076] Step six, weighted calculation is performed on the parameter similarities corresponding to the predetermined characteristic parameters contained in each type of vital sign data according to the weights preset for each predetermined characteristic parameter, so as to obtain the vital sign similarities corresponding to each type of vital sign data.

[0077] In a specific embodiment, when the vital sign similarity is higher than a preset threshold, it is determined that the current vital sign data is highly similar to the corresponding previous vital sign data saved in advance. Preferably, the preset threshold is 90%. Preferably, the preset threshold is manually set by a doctor according to a specific application scenario.

[0078] In a specific embodiment, Figure 5 This is an example of calculating the similarity of electrocardiogram feature types in a method for comparing monitor data features in an embodiment of the present invention. A weighted calculation is performed based on each predetermined feature parameter contained in the vital sign data of the electrocardiogram and a weight pre-set for each predetermined feature parameter, that is, the weighted results of each predetermined feature parameter contained in the vital sign data of the electrocardiogram are added together to obtain the vital sign similarity of the electrocardiogram, such as Figure 5 As shown, the similarity of the vital signs of the electrocardiogram obtained by calculation is 0.92.

[0079] Specifically, that is:

[0080] 0.98*40%+0.9*50%+0.78*10%=0.39+0.45+0.08=0.92

[0081] Step seven, performing weighted calculation according to the vital sign similarity corresponding to each type of vital sign data and the pre-set weight for each type of vital sign data, to obtain the patient similarity.

[0082] In a specific embodiment, a weighted calculation is performed based on the vital sign similarity of each vital sign data and a pre-set weight for each vital sign data, that is, the weighted results of the vital sign similarity of each vital sign data are added together to obtain the patient similarity.

[0083] Step eight, when the patient similarity is higher than a preset threshold, it is determined that the patient to which the vital signs data collected this time belongs is the same person as the patient to which the vital signs data collected last time belongs; when the patient similarity is lower than a preset threshold, it is determined that the vital signs data collected this time belongs to a new patient; and the determination result is output.

[0084] In a specific embodiment, Figure 6 FIG. 1 is a schematic diagram of the output result interface in a system using a monitor data feature comparison method according to an embodiment of the present invention. When it is determined that the vital sign data collected this time belongs to a new patient, the determination result is as follows: Figure 6Preferably, when the user selects "new patient", the currently collected vital sign data is additionally stored with a new patient identification.

[0085] Preferably, the output judgment result content includes: patient similarity and / or vital sign similarity of different types of vital signs. The technical solution of the embodiment of the present invention is closely integrated with the medical application scenario, and fully considers the correlation and difference between different vital sign data, so that the recognition result is more in line with the actual situation. Specifically, the characteristic parameters in the currently measured vital sign data are compared with the characteristic data in the last saved vital sign data in multiple dimensions, and the patient similarity is obtained through complex mathematical operations and logical judgments.

[0086] Furthermore, the technical solution of the embodiment of the present invention not only considers the parameter similarity of a single feature parameter, but also integrates the vital sign similarities of different vital sign types through weighted calculation, thereby improving the accuracy and reliability of identifying the vital sign data of new patients.

[0087] Furthermore, through accurate feature extraction and efficient data comparison, automatic identification of new patients is achieved, effectively avoiding the confusion of patient data recorded by the monitor. Compared with the prior art, the technical solution of the embodiment of the present invention has higher accuracy and reliability, providing strong support for the critical condition warning and clinical diagnosis and treatment of medical institutions.

[0088] Embodiment three:

[0089] The present invention also provides a device for comparing monitor data characteristics, such as Figure 7 As shown, the device includes a processor 701, a memory 702, a bus 703, and a computer program stored in the memory 702 and executable on the processor 701. The processor 701 includes one or more processing cores. The memory 702 is connected to the processor 701 via the bus 703. The memory 702 is used to store program instructions. When the processor executes the computer program, the steps in the above method embodiment of the first embodiment of the present invention are implemented.

[0090] Further, as an executable solution, the device for comparing the data features of the monitor may be a computer unit, which may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art may understand that the composition structure of the above-mentioned computer unit is only an example of a computer unit and does not constitute a limitation on the computer unit, and may include more or less components than the above-mentioned, or a combination of certain components, or different components. For example, the computer unit may also include input and output devices, network access devices, buses, etc., which are not limited in the embodiments of the present invention.

[0091] Further, as an executable solution, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, and various interfaces and lines are used to connect the various parts of the entire computer unit.

[0092] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the computer unit by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0093] Embodiment 4:

[0094] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the method described above are implemented.

[0095] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A method for comparing features of monitor data, characterized in that: include: Step S1, time-stamping the vital sign data collected by the monitor at a predetermined frequency to obtain the vital sign data with time stamp; Step S2, splitting the vital sign data with time stamps according to predetermined vital sign types to obtain vital sign data of different vital sign types with time stamps; wherein the vital sign types include electrocardiogram, blood pressure, blood oxygen, respiratory wave and / or electroencephalogram; Step S3, performing feature extraction on each type of vital sign data within a predetermined time period, and obtaining one or more predetermined feature parameters associated with each type of vital sign data within the predetermined time period; Step S4, for one or more predetermined characteristic parameters associated with each type of vital sign data within the predetermined time period, by comparing the value at a selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period saved in advance, to calculate a first similarity of each predetermined characteristic parameter within the predetermined time period and at each time granularity, wherein the time granularity includes: seconds; Step S5, obtaining the parameter similarity corresponding to each of the predetermined characteristic parameters by calculating the average value of the first similarity of each of the predetermined characteristic parameters within the predetermined time period and at each of the time granularities; Step S6, performing weighted calculation on the parameter similarities corresponding to the predetermined characteristic parameters contained in each type of vital sign data according to the weights preset for the predetermined characteristic parameters, to obtain the vital sign similarities corresponding to each type of vital sign data; Step S7, performing weighted calculation according to the vital sign similarity corresponding to each type of vital sign data and the weight preset for each type of vital sign data, to obtain the patient similarity.

2. The method for comparing characteristics of monitor data according to claim 1, characterized in that: The predetermined characteristic parameters associated with the electrocardiogram include: parameters related to the QRS wave characteristics of each heartbeat; the parameters related to the QRS wave characteristics of each heartbeat include: PR interval, RQS width, R wave amplitude, ST segment elevation amplitude, ST segment depression amplitude, P wave amplitude, S wave amplitude, compensatory interval, QRS area, time interval between every two heartbeats and / or pp interval; The predetermined characteristic parameters associated with the respiratory wave include: flow rate, pressure, volume, respiratory rate, respiratory ratio and / or PEEP level; The predetermined characteristic parameters associated with the electroencephalogram include: alpha wave, alpha wave frequency, amplitude, rhythm, beta wave frequency and / or amplitude rhythm.

3. The method for comparing monitor data characteristics according to claim 1, characterized in that: It also includes, when the patient similarity is higher than a preset threshold, determining that the patient to which the vital signs data collected this time and the vital signs data collected last time belong is the same person; when the patient similarity is lower than the preset threshold, determining that the vital signs data collected this time belongs to a new patient.

4. The method for comparing characteristics of monitor data according to claim 1, characterized in that: Calculating the first similarity of each predetermined feature parameter in the predetermined time period and at each time granularity by comparing the value at the selected moment in the current predetermined time period with the corresponding value at the selected moment in the previous predetermined time period saved in advance comprises: The first similarity=1-(the absolute value of the difference between the first value of the predetermined characteristic parameter in each current predetermined time period at the selected moment and the second value corresponding to the predetermined characteristic parameter in the previous predetermined time period saved in advance at the selected moment / the larger data value between the first value and the second value).

5. The method for comparing characteristics of monitor data according to claim 1, characterized in that: The first similarity in step S4 is obtained by normalization, cosine similarity, Euclidean distance, Manhattan distance, dynamic time warping, Pearson correlation coefficient, Jaccard similarity coefficient or Gaussian kernel similarity calculation.

6. The method for comparing characteristics of monitor data according to claim 1, characterized in that: When the following scenario occurs, step S1 is executed: Restart the monitor; or, The monitor will re-collect vital sign data after a preset period of time without sampling in the running state.

7. The method for comparing characteristics of monitor data according to claim 1, characterized in that: In step S1, time-stamping the vital sign data collected by the monitor at a predetermined frequency includes: The vital sign data is associated with the current system time of the monitor according to a predetermined frequency to obtain the vital sign data with a time stamp.

8. A device for comparing features of monitor data, characterized in that: It comprises a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement the method for comparing monitor data features as claimed in any one of claims 1 to 7.

9. A monitor, characterized in that: A device for comparing monitor data features as described in claim 8.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for comparing monitor data features as claimed in any one of claims 1 to 7 is implemented.

Images