Clinical nursing monitoring device for ward
By real-time monitoring and analyzing pathological parameters changes in the ward nursing monitoring device and identifying abnormal periods, the problem of failure to comprehensively monitor parameter changes in the existing technology is solved, and comprehensive monitoring of ward nursing monitoring parameters and timely identification of abnormal abnormalities is achieved to ensure that Care effects.
Patent Information
- Application Number
- CN202411024918.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing ward nursing monitoring device failed to identify whether the parameters were abnormal during the change based on the parameter changes, resulting in incomplete monitoring effects.
The pathological parameters are monitored in real time through the parameter monitoring end, and the periodic feature analysis end generates a change curve of the associated parameter, identify the period characteristics, determine the abnormal period, and confirm the abnormal situation through homofrequency feature analysis and total value feature monitoring to generate an early warning signal.
A comprehensive monitoring of changes in ward nursing monitoring parameters has been achieved, abnormal situations are identified in a timely manner, the overall effect of the nursing process has been ensured, and medical staff have timely intervention.
Smart Images

Figure CN119033331A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of ward clinical nursing, in particular to a ward clinical nursing monitoring device. Background Art
[0002] Ward nursing care measures include monitoring of vital signs, fluid balance, central venous pressure, microcirculation and other items, aiming to timely understand the body's functions and changes in the condition after surgery so as to take appropriate nursing measures.
[0003] The application with publication number CN110459328B discloses a clinical decision support system for evaluating cardiac arrest, including: an information acquisition module for real-time acquisition of clinical or non-clinical data of patients; an input-output module for providing a user interface, receiving user instructions or displaying content to users; an information processing module for switching several input units in the information acquisition module to obtain clinical or non-clinical data of patients according to input instructions of the input-output module; for data cleaning of structured data using the electronic health records of patients; for building a neural network model based on a genetic algorithm and performing prospective cohort verification of the neural network model; for training based on existing in-hospital cardiac arrest training data, evaluating the real-time acquired patient data, and outputting warning information to the input-output module. The device has high warning accuracy and can be used as an auxiliary device for rescue personnel to perform differential diagnosis of in-hospital cardiac arrest more effectively and accurately.
[0004] During the ward nursing monitoring process, the relevant parameters of the corresponding ward monitoring are generally used to identify whether the monitored parameters are abnormal. However, this monitoring method can only identify the existence of specific abnormalities when the parameters are abnormal. It does not identify whether the parameters are abnormal during the change process based on the changes in the monitored parameters. The original monitoring identification method is not comprehensive, and the resulting monitoring effect cannot achieve the best. Summary of the invention
[0005] In view of the deficiencies of the prior art, the present invention provides a clinical nursing monitoring device for a ward, which solves the problem of not identifying whether a parameter is abnormal during a change process based on the change of the monitored parameter.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A clinical nursing monitoring device for a ward, comprising:
[0007] Parameter monitoring end, monitoring the relevant pathological parameters of clinical nursing related instruments;
[0008] The periodic feature analysis end generates the correlation parameter change curve of the corresponding pathological parameters based on the different relevant pathological parameters corresponding to different moments, and then performs correlation analysis on the curve segments of the same period to identify the period characteristics. Based on the specific parameter performance of the period characteristics, it is confirmed whether there are relevant abnormalities in the specific parameters of the same period, and the abnormal period is determined. The specific method is as follows:
[0009] Based on the preset correlation period T, where T is a preset value, confirm the initial moment of each group of correlation parameter change curves, and identify whether the initial moments are all the same moment. If they are, directly mark the initial moment as the calibration moment J. If not, select a group of initial moments closest to the current moment and mark this initial moment as the calibration moment J.
[0010] Based on this correlation cycle T, determine the related line segment belonging to the time period [J, J+T) in each group of correlation parameter change curves, determine the maximum value Zkmax and the minimum value Zkmin of the corresponding related line segment, where k represents different related line segments, and use Ck=Zkmax-Zkmin to confirm the numerical difference Ck, where the maximum value and the minimum value are both corresponding pathological parameters, and then confirm the fluctuation number of the corresponding related line segment. In this related line segment, when the trends of the two groups of line segments are opposite, the point between the two groups of line segments is the fluctuation point, confirm the total number of times the fluctuation point appears in this related line segment, and record it as the fluctuation number Sk of this related line segment;
[0011] The characteristic value Tk of the relevant line segment is determined by using Tk=Sk×C1+Ck×C2, where C1 and C2 are both preset fixed coefficient factors;
[0012] The characteristic values Tk of several groups of related line segments belonging to the current period [J, J+T) are summed up to confirm the period characteristic Tz of the current period. After the period characteristic Tz is confirmed, the relevant line segments of the subsequent period [J+T, J+2T) are analyzed to confirm the period characteristics of the subsequent period. Similarly, the period characteristics of the subsequent periods with an interval time of T are confirmed in turn.
[0013] Compare the time period feature Tz with the preset value Y1: if Tz>Y1, it means that the current time period is abnormal, and the current time period is marked as an abnormal time period, and the same frequency feature analysis end is executed;
[0014] The same-frequency feature analysis terminal analyzes several groups of related segments belonging to the abnormal period for the same-frequency period, confirms the trend of the segments in the same-frequency period, and identifies whether there is any abnormality in the trend proportion of the same-frequency segments in the related segments. Based on the specific identification results, it is confirmed whether the monitoring parameters in this abnormal period are abnormal and the signal is displayed. The specific method is as follows:
[0015] A group of related line segments is randomly selected from several groups of related line segments in this abnormal period as the standard line segment, and based on the fluctuation points marked inside the standard line segment, the standard line segment is divided into several micro-segments, and the change trend and change time of each micro-segment are determined. If the corresponding micro-segment is climbing upward, then its change trend is recorded as upward, and the change time is the period between the moments corresponding to the two endpoint values of this micro-segment, and so on. After the change trend and change time of each micro-segment are confirmed, the micro-segments are sorted according to the time sequence;
[0016] Confirm the change trend and change time of the first group of micro-segments, and then confirm the change of other related line segments within this change time. If there are some line segments in other related line segments with the same change trend, then mark the line segments with the same change trend as the same-frequency line segments. Otherwise, do not perform the relevant marking of the same-frequency line segments.
[0017] The processing method of the first group of micro-segments is used for the other micro-segments of the standard line segment in turn, and the same-frequency line segments existing in other related line segments are calibrated one by one;
[0018] From other related line segments, where the other related line segments here do not include the standard line segments, confirm the same-frequency line segments marked in the corresponding related line segments, and determine the proportion B of the same-frequency line segments based on the line length of the same-frequency line segments and the line length of the corresponding related line segments, where B = the line length of the same-frequency line segments ÷ the line length of the related line segments, and then after confirming several proportions B in other related line segments one by one, perform average processing on several proportions Z to determine the verification mean HD;
[0019] Compare HD with the preset value Y2. If HD>Y2, an early warning signal is directly generated and displayed through the signal end, indicating that the monitoring parameters of the people monitored in this ward fluctuate abnormally during this abnormal period, and medical staff need to intervene and take relevant measures in time; if HD≤Y2, no processing signal is generated, and subsequent abnormal period analysis and processing are performed to identify whether there are related abnormalities.
[0020] Preferably, it also includes:
[0021] The early warning terminal checks the monitored pathological parameters with the preset intervals of the corresponding pathological parameters. If the pathological parameters are within the preset interval, no processing is performed. If the pathological parameters are If the preset range is exceeded, a warning will be issued directly.
[0022] Preferably, when the time period feature Tz≤Y1, the total value feature monitoring end is executed, and the total value feature monitoring end performs time period feature monitoring based on the time period features of different time periods divided by different cycles, and generates relevant abnormal change signals based on the monitoring results, and displays the signals through the signal end; the specific method is:
[0023] Based on the time period features corresponding to different time periods divided by different cycles, the corresponding time period features Tz are sorted one by one according to the time sequence of the corresponding different time periods to generate a time period feature sequence;
[0024] For the numerical values displayed by the time period feature sequence, if the previous set of values is greater than the next set of values, a value of "1" is assigned; if the previous set of values is equal to the next set of values, no value is assigned; if the previous set of values is less than the next set of values, a value of "-1" is assigned. The values generated in the real-time monitoring process are summed and absolute value processing is performed to determine the total value. When the generated total value is ≥5, a change abnormality signal is directly generated through the signal terminal for display;
[0025] When the resulting sum value is <5, no processing signal is generated.
[0026] The present invention provides a clinical nursing monitoring device for wards. Compared with the prior art, it has the following advantages:
[0027] Beneficial effects:
[0028] The present invention determines the time period characteristics in each cycle by the changes in the monitored relevant pathological parameters, and performs value fluctuation analysis by analyzing the numerical size of the time period characteristics and the synchronous changes in the numerical values of the corresponding abnormal time periods. If the same frequency changes in the same period also exceed the standard, it means that the relevant parameters monitored in this monitoring process are also abnormal. For such abnormal exceeding conditions, it is necessary to generate relevant signals in time for warning, which can not only monitor whether the values exceed the standard, but also monitor the relevant pathological parameters to ensure the comprehensiveness of the monitoring process and the overall effect of the bed nursing monitoring.
[0029] Subsequently, the time period characteristics generated in different cycle time periods are monitored and analyzed. If the time period characteristics gradually become larger or smaller, it needs to be paid attention to. By using the comparison assignment monitoring method, it can be determined whether the monitoring results are abnormal, and the relevant performance status of the time period characteristics can be determined. In this way, signal display can be carried out to ensure the comprehensiveness of the monitoring process. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 It is a schematic diagram of the principle framework of the present invention;
[0031] Figure 2 This is a schematic diagram for determining the time period characteristics of the present invention. DETAILED DESCRIPTION
[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0033] Embodiment 1
[0034] See also Figure 1 , the present application provides a clinical nursing monitoring device for a ward, comprising a parameter monitoring terminal, an early warning terminal, a periodic characteristic analysis terminal, a same-frequency characteristic analysis terminal, a total value characteristic monitoring terminal and a signal terminal, wherein the parameter monitoring terminal is electrically connected to the early warning terminal or the periodic characteristic analysis terminal input node, and the periodic characteristic analysis terminal is electrically connected to the same-frequency characteristic analysis terminal or the total value characteristic monitoring terminal input node, wherein the same-frequency characteristic analysis terminal and the total value characteristic monitoring terminal are both electrically connected to the signal terminal input node;
[0035] The parameter monitoring end monitors the relevant pathological parameters of the clinical nursing related instruments, and transmits the relevant pathological parameters monitored in real time to the periodic feature analysis end or the early warning end, wherein the relevant pathological parameters include but are not limited to basic pathological parameters such as heart rate parameters, blood pressure parameters, body temperature parameters or respiratory saturation parameters;
[0036] Among them, the early warning end checks the monitored relevant pathological parameters with the preset intervals of the corresponding pathological parameters. If the pathological parameter ∈ the preset interval, no processing is performed. If the pathological parameter The preset interval will directly warn the medical staff and take timely response measures. The endpoint values of the preset intervals are all preset values. Different preset intervals correspond to different relevant pathological parameters. The specific values are prepared by the operator in advance based on experience.
[0037] Among them, combined Figure 2 The periodic feature analysis end generates the correlation parameter change curve of the corresponding pathological parameters based on the different relevant pathological parameters corresponding to different moments, and then performs correlation analysis on the curve segments of the same period to identify the period characteristics. Based on the specific parameter performance of the period characteristics, it is confirmed whether the specific parameters of the same period have relevant abnormalities, and the abnormal period is determined. The specific method of confirmation is:
[0038] Based on the preset correlation period T, where T is a preset value, and its specific value is determined by the operator based on experience, confirm the initial moment of each group of correlation parameter change curves, and identify whether their initial moments are all the same moment. If they are, directly mark the initial moment as the calibration moment J. If not, select a group of initial moments closest to the current moment, and mark this initial moment as the calibration moment J;
[0039] Based on this correlation cycle T, determine the related line segment belonging to the time period [J, J+T) in each group of correlation parameter change curves, determine the maximum value Zkmax and the minimum value Zkmin of the corresponding related line segment, where k represents different related line segments, and use Ck=Zkmax-Zkmin to confirm the numerical difference Ck, where the maximum value and the minimum value are both corresponding pathological parameters, and then confirm the fluctuation number of the corresponding related line segment. In this related line segment, when the trends of the two groups of line segments are opposite, the point between the two groups of line segments is the fluctuation point, confirm the total number of times the fluctuation point appears in this related line segment, and record it as the fluctuation number Sk of this related line segment;
[0040] The characteristic value Tk of the relevant line segment is determined by Tk=Sk×C1+Ck×C2, where C1 and C2 are preset fixed coefficient factors, and their specific values are determined by the operator based on experience;
[0041] The characteristic values Tk of several groups of related line segments belonging to the current period [J, J+T) are summed up to confirm the period characteristic Tz of the current period. After the period characteristic Tz is confirmed, the relevant line segments of the subsequent period [J+T, J+2T) are analyzed to confirm the period characteristics of the subsequent period. Similarly, the period characteristics of the subsequent periods with an interval time of T are confirmed in turn.
[0042] Compare the time period feature Tz with the preset value Y1: if Tz>Y1, it means that the current time period is abnormal, and the current time period is marked as an abnormal time period, and the same frequency feature analysis end is executed; if Tz≤Y1, the total value feature monitoring end is executed;
[0043] Specifically, during the monitoring process of different pathological parameters, as the timeline changes, a numerical change curve of the corresponding pathological parameter will be generated, so each numerical change curve has a related related line segment in the corresponding time period;
[0044] If the characteristic value (that is, the number of fluctuations and the performance of the floating value) in a certain curve is large, and the characteristic values in other curves in the same period are also large, then the period characteristics will be large. After the corresponding comparison results, it can be confirmed that there are related anomalies in this period. If the characteristic value of this period in this curve is large, and the characteristic values in other curves are not too large, then its period characteristics will not be too large. Then, the subsequent related execution end can be determined based on the performance of its period characteristics;
[0045] In the corresponding time period, when the time period characteristics are too large, it means that the parameter changes too much. Although the corresponding warning conditions are not triggered, it is necessary to pay attention when the value fluctuates too much. In order to further analyze the relevant segments of this abnormal time period, the subsequent same-frequency feature analysis terminal is executed to perform related analysis of the same-frequency segments and identify the changes between the same-frequency segments.
[0046] Embodiment 2
[0047] In the specific implementation process of this embodiment, compared with the above-mentioned embodiment, in the specific implementation process of this embodiment, the relevant analysis is mainly performed on the curve segments in the abnormal period, and based on the analysis results, it is identified whether the curve segments in the abnormal period are too abnormal, and an abnormal signal is sent out through the signal end in time for display, so that external personnel can view and take timely response measures;
[0048] Among them, the same-frequency feature analysis end performs same-frequency period analysis on several groups of related segments belonging to this abnormal period, confirms the trend of the segments in the same-frequency period, and identifies whether there is any abnormality in the trend proportion of the same-frequency segments in the related segments, and based on the specific identification results, confirms whether the monitoring parameters in this abnormal period are abnormal and displays the signal. Among them, the specific method of identification is:
[0049] A group of related line segments is randomly selected from several groups of related line segments in this abnormal period as the standard line segment, and based on the fluctuation points marked inside the standard line segment, the standard line segment is divided into several micro-segments, and the change trend and change time of each micro-segment are determined. If the corresponding micro-segment is climbing upward, then its change trend is recorded as upward, and the change time is the period between the moments corresponding to the two endpoint values of this micro-segment, and so on. After the change trend and change time of each micro-segment are confirmed, the micro-segments are sorted according to the time sequence;
[0050] Confirm the change trend and change time of the first group of micro-segments, and then confirm the changes of other related segments within this change time. If there are some segments in other related segments with the same change trend, then the segments with the same change trend will be marked as the same-frequency segments. Otherwise, the same-frequency segments will not be marked. Here, combined with an example: the change time of the proposed standard segment is 3:50-4:00, and the change trend is upward. There are three other groups of related segments in this abnormal period, namely A, B and C. Among the A related segments, there are 3:50-3:55 segments that are also in an upward trend. In the B related segments, there are 3:52-3:5 5 is also in the situation of an upward change trend. In the C-related line segment, there is a 3:54-3:59 line segment that is also in the situation of an upward change trend. This is the situation mentioned above that "if there are some line segments in other related line segments with the same change trend", then it is necessary to mark the same-frequency line segments. The marked same-frequency line segments are determined according to the existing same-frequency change time, and the same-frequency change time is: 3:50-3:55, 3:52-3:55 and 3:54-3:59. If there is a corresponding same-frequency change time in the A and B related line segments, but there is no corresponding same-frequency change time in the C related line segment, then the same-frequency line segment will not be calibrated;
[0051] The processing method of the first group of micro-segments is used for the other micro-segments of the standard line segment in turn, and the same-frequency line segments existing in other related line segments are calibrated one by one;
[0052] From other related line segments, where the other related line segments here do not include the standard line segments, confirm the same-frequency line segments marked in the corresponding related line segments, and determine the proportion B of the same-frequency line segments based on the line length of the same-frequency line segments and the line length of the corresponding related line segments, where B = the line length of the same-frequency line segments ÷ the line length of the related line segments, and then after confirming several proportions B in other related line segments one by one, perform average processing on several proportions Z to determine the verification mean HD;
[0053] Compare HD with the preset value Y2. If HD>Y2, a warning signal is directly generated through the signal terminal for direct display, indicating that the monitoring parameters of the people monitored in this ward fluctuate abnormally during this abnormal period, and medical staff need to intervene and take relevant measures in time. If HD≤Y2, no processing signal is generated, and subsequent abnormal period analysis and processing are performed to identify whether there are related abnormalities;
[0054] Specifically, the so-called same-frequency change means that in the same period, all the values change synchronously, that is, they increase or decrease synchronously. Some values change with the same trend. When the characteristic Tz of the determined time period exceeds the standard, if the same-frequency change in the same period also exceeds the standard, then it means that the relevant parameters monitored in this monitoring process are also abnormal. For such abnormal exceeding conditions, it is necessary to generate relevant signals in time for warning. Not only can the values be monitored to see if they exceed the standard, but also the relevant pathological parameters can be monitored to ensure the comprehensiveness of the monitoring process and the overall effect of bed nursing monitoring.
[0055] Embodiment 3
[0056] In the specific implementation process of this embodiment, different from the specific implementation method of the second embodiment, this embodiment is mainly executed through the total value feature monitoring terminal to monitor the performance of the time period features of different time periods corresponding to different cycles, and evaluate whether a signal warning is needed;
[0057] Among them, the total value feature monitoring end performs period feature monitoring based on the period features of different periods divided by different cycles, and generates relevant abnormal change signals based on the monitoring results, and displays the signals through the signal end. Among them, the specific method of performing period feature monitoring is:
[0058] Based on the time period features corresponding to different time periods divided by different cycles, the corresponding time period features Tz are sorted one by one according to the time sequence of the corresponding different time periods to generate a time period feature sequence;
[0059] For the numerical values displayed by the time period characteristic sequence, if the previous group of values is greater than the next group of values, a value of "1" is assigned; if the previous group of values is equal to the next group of values, no value is assigned; if the previous group of values is less than the next group of values, a value of "-1" is assigned. The values generated in the real-time monitoring process are summed and the absolute value is processed to determine the total value. When the generated total value is ≥5, an abnormal change signal is directly generated through the signal end for display, so that external personnel can view it, carry out relevant medical treatment in time, and identify whether its monitoring parameters are abnormal;
[0060] When the resulting sum value is <5, no processing signal is generated.
[0061] Specifically, the time period characteristics monitored are definitely different in different time periods, but as time changes, when the time period characteristics gradually become larger or smaller, they need to be paid attention to. Therefore, by using this value assignment monitoring method, it is possible to determine whether the monitoring results are abnormal and to determine the relevant performance status of the time period characteristics, so as to display signals and ensure the comprehensiveness of the monitoring process.
[0062] Embodiment 4
[0063] The specific implementation process of this embodiment includes all the implementation processes of the above three groups of embodiments.
[0064] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.
[0065] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. A clinical nursing monitoring device for a ward, characterized in that: include: Parameter monitoring end, monitoring the relevant pathological parameters of clinical nursing related instruments; The periodic feature analysis end generates the correlation parameter change curve of the corresponding pathological parameters based on the different relevant pathological parameters corresponding to different moments, and then performs correlation analysis on the curve segments of the same period to identify the period characteristics. Based on the specific parameter performance of the period characteristics, it is confirmed whether there are relevant abnormalities in the specific parameters of the same period, and the abnormal period is determined; The same-frequency feature analysis end conducts same-frequency period analysis on several groups of related line segments belonging to this abnormal period, confirms the trend of the line segments in the same-frequency period, and identifies whether there are related abnormalities in the trend proportion of the same-frequency line segments within the related line segments, and based on the specific identification results, confirms whether the monitoring parameters in this abnormal period are abnormal and displays the signal.
2. A clinical nursing monitoring device for a ward according to claim 1, characterized in that: Also includes: The early warning terminal checks the monitored pathological parameters with the preset intervals of the corresponding pathological parameters. If the pathological parameters are within the preset interval, no processing is performed. If the pathological parameters are If the preset range is exceeded, a warning will be issued directly.
3. A clinical nursing monitoring device for a ward according to claim 1, characterized in that: The specific method for the periodic feature analysis end to confirm whether there are relevant anomalies in the specific parameters of the same period is: Based on the preset correlation period T, where T is a preset value, confirm the initial moment of each group of correlation parameter change curves, and identify whether the initial moments are all the same moment. If they are, directly mark the initial moment as the calibration moment J. If not, select a group of initial moments closest to the current moment and mark this initial moment as the calibration moment J. Based on this correlation cycle T, determine the related line segment belonging to the time period [J, J+T) in each group of correlation parameter change curves, determine the maximum value Zkmax and the minimum value Zkmin of the corresponding related line segment, where k represents different related line segments, and use Ck=Zkmax-Zkmin to confirm the numerical difference Ck, where the maximum value and the minimum value are both corresponding pathological parameters, and then confirm the fluctuation number of the corresponding related line segment. In this related line segment, when the trends of the two groups of line segments are opposite, the point between the two groups of line segments is the fluctuation point, confirm the total number of times the fluctuation point appears in this related line segment, and record it as the fluctuation number Sk of this related line segment; The characteristic value Tk of the relevant line segment is determined by using Tk=Sk×C1+Ck×C2, where C1 and C2 are both preset fixed coefficient factors; The characteristic values Tk of several groups of related line segments belonging to the current period [J, J+T) are summed up to confirm the period characteristic Tz of the current period. After the period characteristic Tz is confirmed, the relevant line segments of the subsequent period [J+T, J+2T) are analyzed to confirm the period characteristics of the subsequent period. Similarly, the period characteristics of the subsequent periods with an interval time of T are confirmed in turn. Compare the time period feature Tz with the preset value Y1: if Tz>Y1, it means that the current time period is abnormal, and the current time period is marked as an abnormal time period, and the same frequency feature analysis end is executed.
4. A clinical nursing monitoring device for a ward according to claim 3, characterized in that: The same-frequency feature analysis terminal identifies whether there is a related anomaly in the trend proportion of the same-frequency line segment in the specific manner as follows: A group of related line segments is randomly selected from several groups of related line segments in this abnormal period as the standard line segment, and based on the fluctuation points marked inside the standard line segment, the standard line segment is divided into several micro-segments, and the change trend and change time of each micro-segment are determined. If the corresponding micro-segment is climbing upward, then its change trend is recorded as upward, and the change time is the period between the moments corresponding to the two endpoint values of this micro-segment, and so on. After the change trend and change time of each micro-segment are confirmed, the micro-segments are sorted according to the time sequence; Confirm the change trend and change time of the first group of micro-segments, and then confirm the change of other related line segments within this change time. If there are some line segments in other related line segments with the same change trend, then mark the line segments with the same change trend as the same-frequency line segments. Otherwise, do not perform the relevant marking of the same-frequency line segments. The processing method of the first group of micro-segments is used for the other micro-segments of the standard line segment in turn, and the same-frequency line segments existing in other related line segments are calibrated one by one; From other related line segments, where the other related line segments here do not include the standard line segments, confirm the same-frequency line segments marked in the corresponding related line segments, and determine the proportion B of the same-frequency line segments based on the line length of the same-frequency line segments and the line length of the corresponding related line segments, where B = the line length of the same-frequency line segments ÷ the line length of the related line segments, and then after confirming several proportions B in other related line segments one by one, perform average processing on several proportions Z to determine the verification mean HD; Compare HD with the preset value Y2. If HD>Y2, an early warning signal is directly generated and displayed through the signal terminal, indicating that the monitoring parameters of the people monitored in this ward fluctuate abnormally during this abnormal period, and medical staff need to intervene and take relevant measures in time.
5. A clinical nursing monitoring device for a ward according to claim 4, characterized in that: The check mean HD: HD≤Y2, then no processing signal is generated, and subsequent abnormal period analysis and processing are performed to identify whether there are related abnormalities.
6. A clinical nursing monitoring device for a ward according to claim 3, characterized in that: When the time period characteristic Tz≤Y1, the total value characteristic monitoring terminal is executed.
7. A clinical nursing monitoring device for a ward according to claim 6, characterized in that: The total value feature monitoring terminal performs time period feature monitoring based on the time period features of different time periods divided by different cycles, generates relevant abnormal change signals based on the monitoring results, and displays the signals through the signal terminal.
8. A clinical nursing monitoring device for a ward according to claim 7, characterized in that: The specific method of the total value feature monitoring end for period feature monitoring is: Based on the time period features corresponding to different time periods divided by different cycles, the corresponding time period features Tz are sorted one by one according to the time sequence of the corresponding different time periods to generate a time period feature sequence; For the numerical values displayed by the time period feature sequence, if the previous set of values is greater than the next set of values, a value of "1" is assigned; if the previous set of values is equal to the next set of values, no value is assigned; if the previous set of values is less than the next set of values, a value of "-1" is assigned. The values generated in the real-time monitoring process are summed and absolute value processing is performed to determine the total value. When the generated total value is ≥5, a change abnormality signal is directly generated through the signal terminal for display; When the resulting sum value is <5, no processing signal is generated.
Citation Information
Cited By
Heart rate monitoring data intelligent analysis method based on deep learning
CN120470313A
