Patient data transmission method and system of intelligent terminal

Abstract

A patient data transmission method and system of an intelligent terminal belongs to the technical field of patient data processing, and obtains patient data queues of each patient in each stage so as to obtain suspicion clutter value action amplitude of each patient data queue; the method comprises the following steps of: analyzing patient data of different patients with the same illness state in the same stage to obtain the distinguishing quantity of each patient data queue, and distinguishing according to the suspicion clutter value action amplitude of each patient data queue and the distinguishing quantity of the patient data queue with the same serial number in the adjacent stage; the final clutter value action amplitude of each patient data queue is obtained, so that the patient data of the patients in different stages are analyzed, the patient data under abnormal conditions are distinguished, the clutter value is judged more accurately, the obtained polynomial order value is ensured to be more reasonable, the clutter value clearing function can be improved, and the accuracy of the clutter value is improved. Therefore, the monitoring performance of the patient data is better.

Description

Technical Field

[0001] The present invention belongs to the technical field of patient data processing, and in particular relates to a patient data transmission method and system for an intelligent terminal. Background Art

[0002] Hospital data analysis can be carried out by collecting and organizing patient data, using data mining technology, applying statistical analysis methods, using visualization tools, etc. By collecting and organizing patient data, hospitals can obtain detailed information about patients.

[0003] In practical applications, current patient data processing technology based on smart terminals often uses the existing technical solution with patent publication number "CN103503500A" to process patient data. The MBAN device, which is a smart terminal, is used to transmit the sampled patient data to the display monitor of the central monitoring station via its communication unit for display, thereby performing monitoring and processing of the patient data. The patient data includes the patient's intravenous fluid flow rate, heart rate or respiratory rate.

[0004] During the period when the MBAN device is used to transmit the sampled patient data to the central monitoring station via its communication unit, the patient data sampled in real time during the operation of the MBAN device often contains some noise values ​​due to the disturbance of external radio waves or electric fields, which weakens the quality of the patient data. The Savitzky-Golay method is currently used to clear the noise values ​​of the patient data queue. This method is affected by the value of the pre-defined polynomial order. A constant and inappropriate value of the polynomial order will weaken the function of clearing the noise values, thereby resulting in poor monitoring performance of the patient data. Summary of the invention

[0005] In order to solve the defects in the prior art, the present invention proposes a patient data transmission system and method for an intelligent terminal, which obtains the patient data queues of each patient in each stage, thereby obtaining the suspected noise value amplitude of each patient data queue, and performs initial monitoring of the noise value through the analysis of the patient data of different patients with the same condition in the same stage, combined with the randomness of the noise value, to ensure the accuracy of the noise value monitoring. The difference of each patient data queue is obtained, and the final noise value amplitude of each patient data queue is obtained according to the difference between the suspected noise value amplitude of each patient data queue and the difference of the patient data queue with the same sequence number in the adjacent stage, and the patient data of the patients in different stages are analyzed accordingly, and the patient data under abnormal conditions are distinguished, so as to more accurately determine the noise value, ensure that the value of the obtained polynomial order is more reasonable, and improve the function of noise value elimination, so as to make the monitoring performance of patient data better.

[0006] The present invention uses the following technical solutions.

[0007] A patient data transmission method of an intelligent terminal, comprising: The MBAN device transmits the sampled patient data to the central monitoring station via its communication unit for treatment, and then displays the treated patient data on a display monitor of the central monitoring station, thereby performing a monitoring process of the patient data, wherein the patient data includes the intravenous fluid flow rate, heart rate or respiratory rate of the patient; A method for transmitting sampled patient data to a central monitoring station for processing, including: Step 1, obtain the patient data queue of each patient with the same condition at each stage; Step 2, obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​in the trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue based on the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; Step 3, according to the suspected clutter value effect amplitude of each patient data sub-cohort and the patient data in the same time interval in the patient data cohort of all patients in the same stage, obtain the suspected clutter value effect amplitude of each patient data cohort; Step 4, according to the difference between the trend items of the patient data queues of all patients in the same stage, obtain the difference amount of each patient data queue; according to the difference between the suspected clutter value effect amplitude of each patient data queue and the difference amount of the patient data queue with the same sequence number in the adjacent stage, obtain the final clutter value effect amplitude of each patient data queue; Step 5, according to the final noise value effect amplitude of each patient data queue, obtain the high-quality patient data queue corresponding to each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data.

[0008] Furthermore, in Step 1, a patient data queue of each patient in each stage is sampled. The patient data queue is a queue formed by arranging the patient data in the order of the sampling time points of the patient data.

[0009] Furthermore, in Step 2, the method for obtaining the amplitude of the suspected clutter value in each patient data sub-queue in each patient data queue specifically includes: In the patient data cohort of patients with the same condition in any period, the ARIMA model is used to separate the patient data cohort into trend terms, cycle terms and residual terms; Use Newton's method to derive the trend items and obtain multiple maximum values; At the time points corresponding to the maximum values ​​of the trend items, the patient data queue and the period item are respectively cut into multiple patient data sub-queues and period sub-items; Then, Newton's method is used to derive each periodic sub-term and obtain multiple maximum values; Put the first The period item of the patient data cohort The number of maximum values ​​in the periodic sub-items divided by the Patient data cohort The quotient of the number of patient data in the patient data sub-cohort is defined as Patient data cohort The magnitude of fluctuations in the patient data subcohort; Operation The patient data cohort has a cycle item The standard deviation of the modulus of the quantity obtained by subtracting all adjacent extreme values ​​in the periodic sub-items is added to the standard deviation of the Patient data cohort The amount obtained by multiplying the fluctuation amplitudes in the patient data sub-queues is defined as Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort.

[0010] Further, in Step 2, the calculation equation for the amplitude of the suspected clutter value in each patient data sub-queue in each patient data queue is: In the equation, It is Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is The patient data cohort has a cycle item The number of maximum values ​​in the periodic sub-items, It is Patient data cohort The number of patient data in the patient data sub-cohort, and They are The patient data cohort has a cycle item In the periodic sub-item The first The most valuable, It is The patient data cohort has a cycle item The average of the moduli of the quantities obtained by subtracting all adjacent maximum values ​​in a periodic subterm.

[0011] Furthermore, in Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: Patients with the same condition In the patient data cohort of all patients with the same condition within the stage, Patient data cohort The initial and final time points of the patient data sub-cohorts were cut out in the a baseline patient data subcohort in each patient data cohort other than the patient data cohort; Put the first Patient data cohort The basic data sub-cohort is defined as the average of the patient data sub-cohort and the entire benchmark patient data sub-cohort.

[0012] Furthermore, in Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: Using the PLR ​​method to perform operations on each patient data sub-queue and its corresponding basic data sub-queue, obtaining the distance between each patient data sub-queue and its corresponding basic data sub-queue; In the In the stage In each patient data queue, the amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues is calculated, and then the The quotient obtained by dividing the amplitude of the suspected clutter value in the patient data sub-queue by the summed value is The distance between the patient data sub-cohort and the corresponding basic data sub-cohort multiplied by the quotient is defined as The calibration suspected clutter value action amplitude of the patient data sub-cohort is obtained by adding the calibration suspected clutter value action amplitudes of all patient data sub-cohorts, and is defined as In the stage The magnitude of the suspected clutter effect for a cohort of patient data.

[0013] Furthermore, in Step 3, the calculation equation for the amplitude of the suspected clutter value of the patient data queue of each patient in the same stage is: In the equation, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, It is In the stage Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is In the stage The amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues in a patient data queue, It is In the stage The number of patient data sub-queues in a patient data queue, It is In the stage Patient data cohort patient data subcohorts, It is In the stage Patient data cohort The basic data sub-cohorts corresponding to the patient data sub-cohorts, yes and The distance between .

[0014] Furthermore, in Step 4, the method for obtaining the final clutter value action amplitude of each patient data queue in each stage specifically includes: In the In the patient data set of all patients with the same condition in a stage, the PLR ​​method is used to obtain the distance between the trend items of any pair of patient data sets, and the first patient data cohort and in The normalized value obtained by adding the distances between the trend items of all patient data queues except the patient data queue is defined as The difference between the two patient data cohorts.

[0015] Furthermore, in Step 4, the method for obtaining the final clutter value action amplitude of each patient data queue in each stage specifically includes: In the Stage and In all stages after the first stage, the difference between the patient data queues with the same serial number in a pair of adjacent stages is calculated, and the average of the difference between the patient data queues with the same serial number in a pair of adjacent stages is defined as the first stage. The magnitude of anomalies in each patient data cohort within each stage; In the In this stage, The negative correlation normalization of the abnormal amplitude of the patient data cohort is The quantity obtained by multiplying the amplitude of the suspected clutter value of the patient data queue is defined as In the stage The final clutter value effect amplitude for the patient data cohort.

[0016] Furthermore, in Step 4, In the stage The corresponding equation for the difference between the patient data cohorts is: In the equation, It is In the stage The difference between the patient data cohorts, It is In the stage Patient data cohorts, It is In the first stage Patient data cohort Patient data cohorts, It is In the first stage The number of patient data queues outside the patient data queues, yes and The distance between It is obtained by using the Z-score method The normalized quantity of ; the calculation equation of the abnormal amplitude of the patient data cohort of each patient in each stage is: In the equation, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The difference between the patient data cohorts, It is In the first stage The difference between the patient data cohorts, is the number of stages; the calculation equation for the final clutter value amplitude of the patient data queue of each patient in each stage is: In the equation, It is In the stage The final clutter value effect amplitude of the patient data queue, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, Use Z-score method to obtain The standardized amount of .

[0017] Furthermore, in Step 5, the method for obtaining the value of the polynomial order required by each patient data queue specifically includes: Using the final clutter value action amplitude of each patient data queue to configure the value of the pre-defined polynomial order, obtain the value of the polynomial order required by each patient data queue; The calculation equation for the value of the polynomial order required for the patient data queue of each patient in each stage is: In the equation, It is In the stage The value of the polynomial order required for each patient data cohort, It is In the stage The final clutter value effect amplitude of the patient data cohort; According to the value of the polynomial order required by each patient data queue, the Savitzky-Golay method is used to perform operations on each patient data queue to obtain a high-quality patient data queue after removing the noise value of each patient data queue, and the patient data in the high-quality patient data queue is used as the processed patient data.

[0018] A patient data transmission system for an intelligent terminal, comprising: MBAN device as an intelligent terminal and a central monitoring station connected thereto in communication, the MBAN device is used to transmit sampled patient data to the central monitoring station via its communication unit for treatment, and then display the treated patient data on a display monitor of the central monitoring station, thereby performing monitoring processing of the patient data, wherein the patient data includes intravenous fluid flow rate, heart rate or respiratory rate of the patient; Modules running on the central monitoring station include: An acquisition module, which is used to obtain a patient data queue of each patient with the same condition at each stage; A cutting module is used to obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​of the whole trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue according to the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; An action module, which is used to obtain the suspected clutter value action amplitude of each patient data queue based on the suspected clutter value action amplitude of each patient data sub-queue and the patient data in the same time interval in the patient data queue of all patients in the same stage; A distinguishing module, which is used to obtain the distinguishing amount of each patient data queue according to the difference between the trend items of the patient data queues of all patients in the same stage; and obtain the final noise value effect amplitude of each patient data queue according to the difference between the suspected noise value effect amplitude of each patient data queue and the distinguishing amount of the patient data queue with the same sequence number in the adjacent stage; The processing module is used to obtain the high-quality patient data queues corresponding to each patient data queue according to the final clutter value action amplitude of each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data.

[0019] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include: The patient data queues of each patient in each stage are obtained to obtain the suspected noise value amplitude of each patient data queue. The patient data of different patients with the same condition in the same stage are analyzed, and the randomness of the noise value is combined to perform initial monitoring of the noise value, thereby ensuring the accuracy of noise value monitoring. The difference value of each patient data queue is obtained, and the final noise value amplitude of each patient data queue is obtained based on the difference between the suspected noise value amplitude of each patient data queue and the difference value of the patient data queue with the same sequence number in the adjacent stage. The patient data of patients in different stages are analyzed accordingly, and the patient data under abnormal conditions are distinguished, so as to more accurately determine the noise value, ensure that the value of the obtained polynomial order is more reasonable, and improve the function of noise value elimination, so as to make the monitoring performance of patient data better. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the patient data transmission method of the intelligent terminal of the present invention; Figure 2 It is a partial structural diagram of the patient data transmission system of the intelligent terminal described in the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely express the technical solution of the present invention. The embodiments expressed in this application are only partial embodiments of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by technicians in this field without creative work are all within the protection scope of the present invention.

[0022] like Figure 1 As shown, a patient data transmission method of a smart terminal according to the present invention comprises: The MBAN device transmits the sampled patient data to the central monitoring station via its communication unit for treatment, and then displays the treated patient data on a display monitor of the central monitoring station, thereby performing a monitoring process of the patient data, wherein the patient data includes the intravenous fluid flow rate, heart rate or respiratory rate of the patient; A method for transmitting sampled patient data to a central monitoring station for processing, including: Step 1, obtain the patient data queue of each patient with the same condition at each stage; The key of this application is to determine the noise value by analyzing the patient data of different patients with the same condition in the same stage and the same patients in different stages, thereby eliminating the noise value and obtaining high-quality patient data.

[0023] In a preferred but non-limiting embodiment of the present invention, in Step 1, a patient data queue of each patient in each stage is sampled, and the patient data queue is a queue formed by arranging the patient data in the order of the sampling time points of the patient data.

[0024] The sampling time of the patient data queue in this application can be 2 seconds. Each patient data in the patient data queue corresponds to a sampling time point. Patients with the same condition are multiple patients with the same condition (the same condition can be the same symptoms such as pneumonia, kidney cysts, etc.). The stage can be based on the length of each hour in the twenty-four hours of a day.

[0025] Step 2, obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​in the trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue based on the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; Patients with the same condition in the same stage often have patient data with repeated symptoms, which means that the stability of patient data under repeated symptoms is not low, so the patient data tends to be stable and the duration of regular fluctuations is not short, while the noise values ​​in the patient data often show small fluctuations or jitters, and there is no obvious regularity or tendency. In addition, due to the disturbance of external radio waves or electric fields, the noise values ​​will fluctuate frequently.

[0026] In a preferred but non-limiting embodiment of the present invention, in Step 2, the method for obtaining the amplitude of the suspected clutter value in each patient data sub-queue in each patient data queue specifically includes: In the patient data cohort of patients with the same condition in any period, the ARIMA model is used to separate the patient data cohort into trend terms, cycle terms and residual terms; The trend item and the cycle item correspond one by one to the patient data in the patient data queue respectively.

[0027] Using Newton's method, the trend items are deduced to obtain multiple extreme values; that is, the trend items between a pair of adjacent extreme values ​​are continuously increasing or continuously decreasing.

[0028] The time point corresponding to the maximum value of all trend items (the time point is the sampling time point of the patient data corresponding to the maximum value) is used to cut the patient data queue and the period item into multiple patient data sub-queues and period sub-items respectively; Then, Newton's method is used to derive each periodic sub-term and obtain multiple maximum values; Put the first The period item of the patient data cohort The number of maximum values ​​in the periodic sub-items divided by the Patient data cohort The quotient of the number of patient data in the patient data sub-cohort is defined as Patient data cohort The magnitude of fluctuations in the patient data subcohort; Operation The period item of the patient data cohort The standard deviation of the modulus of the quantity obtained by subtracting all adjacent extreme values ​​in the periodic sub-items is added to the standard deviation of the Patient data cohort The amount obtained by multiplying the fluctuation amplitudes in the patient data sub-queues is defined as Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort.

[0029] In a preferred but non-limiting embodiment of the present invention, in Step 2, the calculation equation for the amplitude of the suspected clutter value in each patient data subqueue in each patient data queue is: In the equation, It is Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is The period item of the patient data cohort The number of maximum values ​​in the periodic sub-items, It is Patient data cohort The number of patient data in the patient data sub-cohort, and They are The patient data cohort has a cycle item In the periodic sub-item The first The most valuable, It is The patient data cohort has a cycle item The average of the moduli of the quantities obtained by subtracting all adjacent maximum values ​​in a periodic subterm, It is Patient data cohort The fluctuation amplitude in the patient data sub-cohort, that is, the higher the fluctuation frequency in the sub-cohort, the higher the fluctuation amplitude, It is The patient data cohort has a cycle item The standard deviation of the modulus of the quantity obtained by subtracting the maximum values ​​of all adjacent periodic sub-items, they respectively reflect the fluctuation effect of the noise value formed in the patient data queue under the same change trend for a long time and the confidence of the noise value effect. This is because the randomness of the noise value makes the fluctuation of the noise value formed different, so the higher the standard deviation, the more likely it is the noise value effect. Therefore, the quantity obtained by multiplying them represents the amplitude of the suspected noise value effect.

[0030] According to the above method, the suspected clutter value effect amplitude in each patient data sub-queue in each patient data queue is obtained.

[0031] Step 3, according to the suspected clutter value effect amplitude of each patient data sub-cohort and the patient data in the same time interval in the patient data cohort of all patients in the same stage, obtain the suspected clutter value effect amplitude of each patient data cohort; Because the patient data cohorts of all patients with the same condition in the same stage are similar, and because of the randomness of noise values, that is, among all patients with the same condition in the same stage, when the patient data of any patient is a noise value at a certain point in time, the patient data of other patients at that point in time are often not noise values. Therefore, the more dissimilar the patient data of one patient are to that of other patients in the same time interval, the more likely they are to be noise values.

[0032] In a preferred but non-limiting embodiment of the present invention, in Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: Patients with the same condition In the patient data cohort of all patients with the same condition within the stage, Patient data cohort The initial and final time points of the patient data sub-cohorts were cut out in the a baseline patient data subcohort in each patient data cohort other than the patient data cohort; Put the first Patient data cohort The average of the patient data sub-cohort and the entire benchmark patient data sub-cohort is defined as the basic data sub-cohort; Here, the average of multiple data queues with the same number of elements is the average of the amounts obtained by performing an addition operation on the values ​​of the corresponding sequence numbers of the data queues.

[0033] According to the above method, the basic data sub-queue corresponding to each patient data sub-queue in the patient data queue of each patient in the same stage is obtained.

[0034] In a preferred but non-limiting embodiment of the present invention, in Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: The PLR ​​method is used to perform operations on each patient data sub-queue and its corresponding basic data sub-queue to obtain the distance between each patient data sub-queue and its corresponding basic data sub-queue; the lower the distance here, the more similar a pair of data sub-queues is.

[0035] In the In the stage In each patient data queue, the amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues is calculated, and then the The quotient obtained by dividing the amplitude of the suspected clutter value in the patient data sub-queue by the summed value is The distance between the patient data sub-cohort and the corresponding basic data sub-cohort multiplied by the quotient is defined as The calibration suspected clutter value action amplitude of the patient data sub-cohort is obtained by adding the calibration suspected clutter value action amplitudes of all patient data sub-cohorts, and is defined as In the stage The magnitude of the suspected clutter effect for a cohort of patient data.

[0036] In a preferred but non-limiting embodiment of the present invention, in Step 3, the calculation equation for the amplitude of the suspected clutter value of the patient data queue of each patient in the same stage is: In the equation, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, It is In the stage Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is In the stage The amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues in a patient data queue, It is In the stage The number of patient data sub-queues in a patient data queue, It is In the stage Patient data cohort patient data subcohorts, It is In the stage Patient data cohort The basic data sub-cohorts corresponding to the patient data sub-cohorts, yes and The distance between It is In the stage Patient data cohort The magnitude of the calibration suspected clutter value in the patient data sub-cohort, The higher it is, the more dissimilar the patient data subqueue is to its corresponding basic data subqueue, that is, the higher the noise value effect caused by the patient data subqueue. Based on this, the suspected noise value effect amplitude in each patient data subqueue is configured to be accumulated to obtain the suspected noise value effect amplitude of each patient data queue.

[0037] According to the above method, the amplitude of the suspected clutter value of each patient data queue in each stage is obtained.

[0038] Step 4, according to the difference between the trend items of the patient data queues of all patients in the same stage, obtain the difference value of each patient data queue; according to the difference between the suspected noise value effect amplitude of each patient data queue and the difference value of the patient data queue with the same serial number in the adjacent stage, obtain the final noise value effect amplitude of each patient data queue; the patient data queues in each stage are numbered one by one according to the order of sampling time points.

[0039] The reason why abnormal fluctuations occur in the patient data queue of a patient and are significantly different from the patient data queues of other patients is not only the effect of the noise value. When an abnormal condition occurs in a patient, the amplitude of the effect of the above-mentioned suspected noise value will also be large. Moreover, when an abnormal condition occurs in the previous stage, the effect on the subsequent stage will increase with the increase of the stage delay, that is, the abnormal condition will gradually be transmitted to the subsequent stage, and with the delay of the time point and the increase of the amount of patient data, the abnormal condition in the previous stage will often cause the negative effect accumulated in the subsequent stage.

[0040] In a preferred but non-limiting embodiment of the present invention, in Step 4, the method for obtaining the final clutter value action amplitude of each patient data queue in each stage specifically includes: In the In the patient data set of all patients with the same condition in a stage, the PLR ​​method is used to obtain the distance between the trend items of any pair of patient data sets, and the first patient data cohort and in The normalized value obtained by adding the distances between the trend items of all patient data queues except the patient data queue is defined as The difference between the two patient data cohorts.

[0041] In a preferred but non-limiting embodiment of the present invention, in Step 4, the method for obtaining the final clutter value action amplitude of each patient data queue in each stage specifically includes: In the Stage and In all stages after the first stage, the difference between the patient data queues with the same serial number in a pair of adjacent stages is calculated, and the average of the difference between the patient data queues with the same serial number in a pair of adjacent stages is defined as the first stage. The magnitude of anomalies for each patient data cohort within each stage; In the In this stage, The negative correlation normalization of the abnormal amplitude of the patient data cohort is The quantity obtained by multiplying the amplitude of the suspected clutter value of the patient data queue is defined as In the stage The final clutter value contribution amplitude for the patient data cohort.

[0042] In a preferred but non-limiting embodiment of the present invention, in Step 4, In the stage The corresponding equation for the difference between the patient data cohorts is: In the equation, It is In the stage The difference between the patient data cohorts, It is In the stage Patient data cohorts, It is In the first stage Patient data cohort Patient data cohorts, It is In the first stage The number of patient data queues outside the patient data queues, yes and The distance between It is obtained by using the Z-score method The standardized amount of The higher the The corresponding patients in the patient data cohort are The higher the abnormality in each stage. Because the abnormality of the same patient in one stage will gradually increase in the later stages, the calculation equation for the abnormal amplitude of the patient data queue of each patient in each stage is: In the equation, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The difference between the patient data cohorts, It is In the first stage The difference between the patient data cohorts, is the number of stages; so The higher it is, the higher the abnormal effect of the suspected clutter value amplitude is, that is, the less reliable the suspected clutter value amplitude is. The calculation equation for the final clutter value amplitude of the patient data queue of each patient in each stage is: In the equation, It is In the stage The final clutter value effect amplitude of the patient data queue, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, Use Z-score method to obtain The standardized quantity used to Standardize to between zero and one. yes The negative correlation normalization value.

[0043] According to the above method, the final clutter value effect amplitude of each patient data queue is obtained.

[0044] Step 5, according to the final noise value effect amplitude of each patient data queue, obtain the high-quality patient data queue corresponding to each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data.

[0045] Because in the Savitzky-Golay method, when the polynomial order is not high, the Savitzky-Golay method responds very sensitively to the current patient data, reflects the changes in patient data in a short period of time, and can protect patient data under abnormal conditions. A very high polynomial order means that patient data in a long period of time will be taken into account, so the response to the current patient data will be very smooth, and noise values ​​can be effectively eliminated.

[0046] In a preferred but non-limiting embodiment of the present invention, in Step 5, the method for obtaining the value of the polynomial order required by each patient data queue specifically includes: The value of the polynomial order predefined in the present application is thirty-two, and the value of the polynomial order predefined is configured using the final noise value acting amplitude of each patient data queue to obtain the value of the polynomial order required by each patient data queue; The calculation equation for the value of the polynomial order required for the patient data queue of each patient in each stage is: In the equation, It is In the stage The value of the polynomial order required for each patient data cohort, It is In the stage The final clutter value amplitude of the patient data queue; here, is to ensure that the value of the polynomial order is singular.

[0047] According to the value of the polynomial order required by each patient data queue, the Savitzky-Golay method is used to perform operations on each patient data queue to obtain a high-quality patient data queue after removing the noise value of each patient data queue, and the patient data in the high-quality patient data queue is used as the processed patient data.

[0048] The value of the polynomial order obtained in this way is more reasonable, which will improve the function of removing clutter values, thereby improving the monitoring performance of patient data.

[0049] like Figure 2 As shown, a patient data transmission system of a smart terminal according to the present invention comprises: MBAN device as an intelligent terminal and a central monitoring station connected thereto in communication, the MBAN device is used to transmit sampled patient data to the central monitoring station via its communication unit for treatment, and then display the treated patient data on a display monitor of the central monitoring station, thereby performing monitoring processing of the patient data, wherein the patient data includes intravenous fluid flow rate, heart rate or respiratory rate of the patient; Modules running on the central monitoring station include: An acquisition module, which is used to obtain a patient data queue of each patient with the same condition at each stage; A cutting module is used to obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​of the whole trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue according to the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; An action module, which is used to obtain the suspected clutter value action amplitude of each patient data queue based on the suspected clutter value action amplitude of each patient data sub-queue and the patient data in the same time interval in the patient data queue of all patients in the same stage; A distinguishing module, which is used to obtain the distinguishing amount of each patient data queue according to the difference between the trend items of the patient data queues of all patients in the same stage; and obtain the final noise value effect amplitude of each patient data queue according to the difference between the suspected noise value effect amplitude of each patient data queue and the distinguishing amount of the patient data queue with the same sequence number in the adjacent stage; The processing module is used to obtain the high-quality patient data queues corresponding to each patient data queue according to the final clutter value action amplitude of each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data. The central monitoring station can be a computer.

[0050] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include: The patient data queues of each patient in each stage are obtained to obtain the suspected noise value amplitude of each patient data queue. The patient data of different patients with the same condition in the same stage are analyzed, and the randomness of the noise value is combined to perform initial monitoring of the noise value, thereby ensuring the accuracy of noise value monitoring. The difference value of each patient data queue is obtained, and the final noise value amplitude of each patient data queue is obtained based on the difference between the suspected noise value amplitude of each patient data queue and the difference value of the patient data queue with the same sequence number in the adjacent stage. The patient data of patients in different stages are analyzed accordingly, and the patient data under abnormal conditions are distinguished, so as to more accurately determine the noise value, ensure that the value of the obtained polynomial order is more reasonable, and improve the function of noise value elimination, so as to make the monitoring performance of patient data better.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be covered within the protection space of the claims of the present invention.

Claims

1. A patient data transmission method of an intelligent terminal, characterized in that: include: The MBAN device transmits the sampled patient data to the central monitoring station via its communication unit for treatment, and then displays the treated patient data on a display monitor of the central monitoring station, thereby performing a monitoring process of the patient data, wherein the patient data includes the intravenous fluid flow rate, heart rate or respiratory rate of the patient; A method for transmitting sampled patient data to a central monitoring station for processing, including: Step 1, obtain the patient data queue of each patient with the same condition at each stage; Step 2, obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​in the trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue based on the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; Step 3, according to the suspected clutter value effect amplitude of each patient data sub-cohort and the patient data in the same time interval in the patient data cohort of all patients in the same stage, obtain the suspected clutter value effect amplitude of each patient data cohort; Step 4, according to the difference between the trend items of the patient data queues of all patients in the same stage, obtain the difference amount of each patient data queue; according to the difference between the suspected clutter value effect amplitude of each patient data queue and the difference amount of the patient data queue with the same sequence number in the adjacent stage, obtain the final clutter value effect amplitude of each patient data queue; Step 5, according to the final noise value effect amplitude of each patient data queue, obtain the high-quality patient data queue corresponding to each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data.

2. The patient data transmission method of the intelligent terminal according to claim 1, characterized in that: In Step 1, a patient data queue of each patient in each stage is sampled. The patient data queue is a queue formed by arranging the patient data in the order of the sampling time points of the patient data.

3. The patient data transmission method of the intelligent terminal according to claim 2, characterized in that: In Step 2, the method for obtaining the amplitude of the suspected clutter value in each patient data sub-queue in each patient data queue specifically includes: In the patient data cohort of patients with the same condition in any period, the ARIMA model is used to separate the patient data cohort into trend terms, cycle terms and residual terms; Use Newton's method to derive the trend items and obtain multiple maximum values; At the time points corresponding to the maximum values ​​of the trend items, the patient data queue and the period item are respectively cut into multiple patient data sub-queues and period sub-items; Then, Newton's method is used to derive each periodic sub-term and obtain multiple maximum values; Put the first The period item of the patient data cohort The number of maximum values ​​in the periodic sub-items divided by the Patient data cohort The quotient of the number of patient data in the patient data sub-cohort is defined as Patient data cohort The magnitude of fluctuations in the patient data subcohort; Operation The period item of the patient data cohort The standard deviation of the modulus of the quantity obtained by subtracting all adjacent extreme values ​​in the periodic sub-items is added to the standard deviation of the Patient data cohort The amount obtained by multiplying the fluctuation amplitudes in the patient data sub-queues is defined as Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort.

4. The patient data transmission method of the intelligent terminal according to claim 3, characterized in that: In Step 2, the calculation equation for the amplitude of the suspected clutter value in each patient data sub-queue in each patient data queue is: In the equation, It is Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is The period item of the patient data cohort The number of maximum values ​​in the periodic sub-items, It is Patient data cohort The number of patient data in the patient data sub-cohort, and They are The period item of the patient data cohort In the periodic sub-item The first The most valuable, It is The period item of the patient data cohort The average of the moduli of the quantities obtained by subtracting all adjacent maximum values ​​in a periodic subterm.

5. The patient data transmission method of the intelligent terminal according to claim 4, characterized in that: In Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: Patients with the same condition In the patient data cohort of all patients with the same condition within the stage, Patient data cohort The initial and final time points of the patient data sub-cohorts were cut out in the a baseline patient data subcohort in each patient data cohort other than the patient data cohort; Put the first Patient data cohort The average of the patient data sub-cohort and the entire benchmark patient data sub-cohort is defined as the basic data sub-cohort; In Step 3, the method for obtaining the amplitude of the suspected clutter value of each patient data queue in each stage specifically includes: Using the PLR ​​method to perform operations on each patient data sub-queue and its corresponding basic data sub-queue, obtaining the distance between each patient data sub-queue and its corresponding basic data sub-queue; In the In the stage In each patient data queue, the amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues is calculated, and then the The quotient obtained by dividing the amplitude of the suspected clutter value in the patient data sub-queue by the summed value is The distance between the patient data sub-cohort and the corresponding basic data sub-cohort multiplied by the quotient is defined as The calibration suspected clutter value action amplitude of the patient data sub-cohort is obtained by adding the calibration suspected clutter value action amplitudes of all patient data sub-cohorts, and is defined as In the stage The magnitude of the suspected clutter effect for a cohort of patient data.

6. The patient data transmission method of the intelligent terminal according to claim 5, characterized in that: In Step 3, the calculation equation for the amplitude of the suspected clutter value of the patient data queue of each patient in the same stage is: In the equation, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, It is In the stage Patient data cohort The magnitude of the suspected clutter value in the patient data sub-cohort, It is In the stage The amount obtained by adding the amplitudes of the suspected clutter values ​​in all patient data sub-queues in a patient data queue, It is In the stage The number of patient data sub-queues in a patient data queue, It is In the stage Patient data cohort patient data subcohorts, It is In the stage Patient data cohort The basic data sub-cohorts corresponding to the patient data sub-cohorts, yes and The distance between .

7. The patient data transmission method of the intelligent terminal according to claim 6, characterized in that: In Step 4, the method for obtaining the final clutter value amplitude of each patient data queue in each stage specifically includes: In the In the patient data set of all patients with the same condition in a stage, the PLR ​​method is used to obtain the distance between the trend items of any pair of patient data sets, and the first patient data cohort and in The normalized value obtained by adding the distances between the trend items of all patient data queues except the patient data queue is defined as The amount of differentiation between patient data cohorts; In Step 4, the method for obtaining the final clutter value amplitude of each patient data queue in each stage specifically includes: In the Stage and In all stages after the first stage, the difference between the patient data queues with the same serial number in a pair of adjacent stages is calculated, and the average of the difference between the patient data queues with the same serial number in a pair of adjacent stages is defined as the first stage. The magnitude of anomalies for each patient data cohort within each stage; In the In this stage, The negative correlation normalization of the abnormal amplitude of the patient data cohort is The quantity obtained by multiplying the amplitude of the suspected clutter value of the patient data queue is defined as In the stage The final clutter value effect amplitude for the patient data cohort.

8. The patient data transmission method of the intelligent terminal according to claim 7, characterized in that: In Step 4, In the stage The corresponding equation for the difference between the patient data cohorts is: In the equation, It is In the stage The difference between the patient data cohorts, It is In the stage Patient data cohorts, It is In the first stage Patient data cohort Patient data cohorts, It is In the first stage The number of patient data queues outside the patient data queues, yes and The distance between It is obtained by using the Z-score method The normalized quantity of ; the calculation equation of the abnormal amplitude of the patient data cohort of each patient in each stage is: In the equation, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The difference between the patient data cohorts, It is In the first stage The difference between the patient data cohorts, is the number of stages; the calculation equation for the final clutter value amplitude of the patient data queue of each patient in each stage is: In the equation, It is In the stage The final clutter value effect amplitude of the patient data queue, It is In the stage The magnitude of anomalies in the patient data cohort, It is In the stage The magnitude of the suspected clutter value effect for each patient data cohort, Use Z-score method to obtain The standardized amount of .

9. The patient data transmission method of the intelligent terminal according to claim 8, characterized in that: In Step 5, the method for obtaining the value of the polynomial order required by each patient data queue specifically includes: Using the final clutter value action amplitude of each patient data queue to configure the value of the pre-defined polynomial order, obtain the value of the polynomial order required by each patient data queue; The calculation equation for the value of the polynomial order required for the patient data queue of each patient in each stage is: In the equation, It is In the stage The value of the polynomial order required for each patient data cohort, It is In the stage The final clutter value effect amplitude of the patient data cohort; According to the value of the polynomial order required by each patient data queue, the Savitzky-Golay method is used to perform operations on each patient data queue to obtain a high-quality patient data queue after removing the noise value of each patient data queue, and the patient data in the high-quality patient data queue is used as the processed patient data.

10. A patient data transmission system for an intelligent terminal, characterized in that: include: MBAN device as an intelligent terminal and a central monitoring station connected thereto in communication, the MBAN device is used to transmit sampled patient data to the central monitoring station via its communication unit for treatment, and then display the treated patient data on a display monitor of the central monitoring station, thereby performing monitoring processing of the patient data, wherein the patient data includes intravenous fluid flow rate, heart rate or respiratory rate of the patient; Modules running on the central monitoring station include: An acquisition module, which is used to obtain a patient data queue of each patient with the same condition at each stage; A cutting module is used to obtain the trend items and period items separated from each patient data queue; use the time points corresponding to the maximum values ​​of the whole trend items to cut each patient data queue and period item into multiple patient data sub-queues and period sub-items; obtain the suspected clutter value action amplitude of each patient data sub-queue according to the difference between the number of maximum values ​​in each period sub-item and the adjacent maximum values; An action module, which is used to obtain the suspected clutter value action amplitude of each patient data queue based on the suspected clutter value action amplitude of each patient data sub-queue and the patient data in the same time interval in the patient data queue of all patients in the same stage; A distinguishing module, which is used to obtain the distinguishing amount of each patient data queue according to the difference between the trend items of the patient data queues of all patients in the same stage; and obtain the final noise value effect amplitude of each patient data queue according to the difference between the suspected noise value effect amplitude of each patient data queue and the distinguishing amount of the patient data queue with the same sequence number in the adjacent stage; The processing module is used to obtain the high-quality patient data queues corresponding to each patient data queue according to the final clutter value action amplitude of each patient data queue; and use the patient data in the high-quality patient data queue as the processed patient data.

Images