Method for monitoring vital sign parameters during medication in patients with severe mental illness

Abstract

The present invention relates to the field of vital sign monitoring technology, and specifically to a method for monitoring vital sign parameters accompanying the medication process of patients with severe mental illness. The present invention captures the dynamic changes of vital sign parameters by obtaining the time series curves of the vital sign parameters of the monitored patient in two stages before and after medication. For each time series curve, the data value difference and the fluctuation duration are analyzed to identify the abnormal fluctuation data segment. Further, the historical normal time series curve is used to determine the historical normal fluctuation segment corresponding to the abnormal fluctuation, and the stable index is calculated through comparative analysis to intuitively reflect the overall state of the vital sign parameters. At the same time, the patient's vital signs are monitored in combination with the stable index of the same vital sign parameters before and after medication and the time series characteristics of the abnormal fluctuation data segment. The method more accurately reflects the patient's vital sign status by comparing the changes in the patient's own sign parameters with the historical normal situation, and provides doctors with more credible data support for drug efficacy judgment or disease analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of vital sign monitoring, and in particular to a method for monitoring vital sign parameters during medication for patients with severe mental illness. Background Art

[0002] In the field of mental health, the treatment of severe mental illnesses (such as schizophrenia, bipolar disorder, etc.) usually relies on drug therapy, which aims to control symptoms, stabilize the condition and improve the patient's quality of life. However, during the medication process, it is usually necessary to continuously and accurately monitor the changes in the patient's vital signs and parameters, so that doctors can make more accurate judgments on the patient's condition, the effect and safety of drug treatment.

[0003] When monitoring the vital sign parameters of patients during medication, the existing technology usually sets a fixed threshold for each vital sign parameter, and issues an alarm when the threshold is exceeded to remind the doctor to further check and analyze the patient's vital sign condition; however, since the conditions of different patients before medication are different, and the changes in vital sign parameters of different patients after medication are also different, the use of fixed thresholds to monitor the vital sign parameters to assist doctors in judging the effectiveness of drug treatment will result in reduced credibility. Summary of the invention

[0004] In order to solve the technical problem that different patients have different conditions before taking medicine, and different patients have different changes in physical sign parameters after taking medicine, using fixed thresholds to monitor physical sign parameters to assist doctors in judging the effect of drug treatment will result in reduced credibility. The purpose of the present invention is to provide a physical sign parameter monitoring method accompanying the medication process of patients with severe mental illness. The technical scheme adopted is as follows:

[0005] Obtain the time series curves of each monitored vital sign parameter of the patient to be monitored in two stages before and after medication;

[0006] For any time series curve to be monitored, the differences between the data values ​​therein are analyzed, and combined with the fluctuation duration of the data values ​​in the time series, the abnormal fluctuation data segment in the time series curve to be monitored is obtained;

[0007] In the historical normal time series curve of each monitored vital sign parameter, determine the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment in the monitored time series curve of the same monitored vital sign parameter at each stage; based on the similarity of the changes in the data values ​​in the abnormal fluctuation data segment in each monitored time series curve and the corresponding historical normal fluctuation data segment, determine the stability index of each monitored vital sign parameter at each stage;

[0008] According to the stable indexes of the same monitored vital sign parameters in the two stages and in combination with the time series characteristics of the abnormal fluctuation data segments in the corresponding monitored time series curve, the vital sign conditions of the monitored patients are monitored.

[0009] Furthermore, the method for acquiring the abnormal fluctuation data segment includes:

[0010] For any time series curve to be monitored, a fluctuation period curve is divided based on the fluctuation of data values ​​in the time series curve to be monitored;

[0011] Determine the fluctuation range of the data value in the time series curve to be monitored, and determine the first abnormal factor of each fluctuation period curve according to the position distribution of the extreme value in each fluctuation period curve in the fluctuation range;

[0012] For any fluctuation period curve in the time series curve to be monitored, the absolute value of the difference between the time length corresponding to the fluctuation period curve and the preset fluctuation time length of the vital sign parameter to be monitored corresponding to the time series curve to be monitored is used as the second abnormal factor of the fluctuation period curve;

[0013] The product of the first abnormal factor and the second abnormal factor of the fluctuation period curve is normalized to a value as the fluctuation abnormal characteristic value of the fluctuation period curve;

[0014] The fluctuation period curve whose fluctuation abnormal characteristic value is greater than the preset fluctuation threshold is taken as the abnormal fluctuation period curve, and each abnormal fluctuation period curve and the curves of preset length before and after in time series are combined into an abnormal fluctuation data segment.

[0015] Furthermore, the method for obtaining the fluctuation period curve includes:

[0016] In the time series curve to be monitored, the average of the data values ​​of all extreme value points is used as a reference value, and a reference line is made in the time series curve to be monitored based on the reference value;

[0017] The intersection of the time series curve to be monitored and the reference line is taken as a division point, and the curve segment between every two adjacent division points on the time series is taken as a fluctuation period curve.

[0018] Furthermore, the method for obtaining the first abnormal factor includes:

[0019] The maximum value and the minimum value in the time series curve to be monitored are respectively used as a boundary value, so as to obtain the fluctuation range of the data value in the time series curve to be monitored;

[0020] For any fluctuation period curve, when the fluctuation period curve is below the baseline, the absolute value of the difference between the minimum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors corresponding to the fluctuation period curve;

[0021] When the fluctuation period curve is above the baseline, the absolute value of the difference between the maximum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors;

[0022] The minimum value of the two distance factors is negatively correlated and normalized as the first abnormal factor corresponding to each fluctuation cycle curve.

[0023] Furthermore, the method for obtaining the historical normal fluctuation data segment includes:

[0024] Obtain the historical normal time series curve of each monitored vital sign parameter of the patient under historical normal conditions in two stages before and after medication;

[0025] For any abnormal fluctuation data segment, in the historical normal time series curve that belongs to the same type of monitored vital sign parameters and the same stage as the abnormal fluctuation data segment, the data segment corresponding to the time of the abnormal fluctuation data segment will be taken as the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment.

[0026] Furthermore, the method for obtaining the stability index includes:

[0027] For any abnormal fluctuation data segment, the absolute value of the difference between the number of extreme value points in the abnormal fluctuation data segment and the number of extreme value points in the corresponding historical normal fluctuation data segment is used as the first deviation factor;

[0028] Analyze the difference between the data values ​​in the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment, and determine the second deviation factor corresponding to the abnormal fluctuation data segment;

[0029] The product of the first deviation factor and the second deviation factor of the abnormal fluctuation data segment is negatively correlated and normalized to a value as the stabilization factor of the abnormal fluctuation data segment;

[0030] In the monitored time series curve of each monitored vital sign parameter at each stage, the stability factors of all abnormal fluctuation data segments are averaged to determine the stability index of each monitored vital sign parameter at each stage.

[0031] Furthermore, the method for obtaining the second deviation factor includes:

[0032] For any abnormal fluctuation data segment, all extreme values ​​in the abnormal fluctuation data segment are sorted in time sequence to obtain a sorted sequence;

[0033] All extreme values ​​in the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment are sorted in time sequence to obtain a comparison sequence;

[0034] In the sorted sequence and the comparison sequence, extreme values ​​with the same sequence number are matched to obtain all matching extreme value pairs;

[0035] The absolute value of the difference between the two extreme values ​​in each matching extreme value pair is calculated as the deviation value, and the average of the deviation values ​​of all matching extreme value pairs is used as the second deviation factor corresponding to the abnormal fluctuation data segment.

[0036] Furthermore, the monitoring of the physical signs of the patient to be monitored is performed based on the stable index of the same physical sign parameters to be monitored in the two stages and in combination with the time series characteristics of the abnormal fluctuation data segment in the corresponding time series curve to be monitored, including:

[0037] The product of the value of each monitored vital sign parameter after negative correlation mapping with the stable index after medication and the stable index before medication is used as the first evaluation parameter of each monitored vital sign parameter;

[0038] For any one of the monitored vital sign parameters, based on the time series characteristics of the abnormal fluctuation data segment in the monitored time series curve of the monitored vital sign parameter after medication administration, determine the second evaluation parameter of the monitored vital sign parameter;

[0039] The product of the first evaluation parameter and the second evaluation parameter of each of the vital sign parameters to be monitored is normalized to a value as an evaluation index of each of the vital sign parameters to be monitored;

[0040] The vital signs of the patient to be monitored are monitored based on evaluation indicators of all types of vital sign parameters to be monitored.

[0041] Furthermore, the method for obtaining the second evaluation parameter includes:

[0042] For any monitored vital sign parameter, the value of the monitored vital sign parameter at the starting time of the first abnormal fluctuation data segment in the monitored time series curve after medication is negatively correlated and mapped as the second evaluation parameter of the monitored vital sign parameter.

[0043] Furthermore, the evaluation indicators based on all types of monitored physical sign parameters are used to monitor the physical sign of the patient to be monitored, including:

[0044] If the evaluation index of a certain vital sign parameter to be monitored is greater than the preset first-level evaluation threshold, an early warning will be issued;

[0045] If the evaluation indicators of all types of monitored vital sign parameters are less than or equal to the preset first-level evaluation threshold, the number of types of monitored vital sign parameters whose evaluation indicators are greater than the preset second-level evaluation threshold is counted, and when the number of types is greater than the preset number threshold, an early warning is issued;

[0046] The preset first-level evaluation threshold is greater than the preset second-level evaluation threshold.

[0047] The present invention has the following beneficial effects:

[0048] Obtain the monitored time series curves of each monitored vital sign parameter of the patient in the two stages before and after medication, so as to capture the dynamic changes of various vital sign parameters of the patient and provide a data basis for the subsequent monitoring process. In view of the different fluctuations of the patient's vital sign parameters at different stages, and the changes in the data values ​​of the vital sign parameters and the duration of the fluctuations can be used as an indicator to reflect the patient's current vital sign state, the present invention analyzes the differences in the data values ​​and the fluctuation duration of the data values ​​in the time series for any time series curve to be monitored, and divides the time series curve to be monitored, thereby identifying the curve segments with abnormal fluctuations as abnormal fluctuation data segments. The abnormal fluctuation data segment reflects the abnormal fluctuation of a certain vital sign parameter. In order to further quantify its abnormal state, the present invention obtains the historical normal time series curve of each vital sign parameter, which also includes two stages before and after the patient takes the medicine, and then determines the historical normal fluctuation data segment corresponding to each abnormal fluctuation data segment in the historical normal time series curve; and then analyzes the data values ​​in the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment for similar changes, so as to determine the stable index of each monitored vital sign parameter of the monitored patient in each stage. The introduction of the stable index can more intuitively reflect the overall state of the monitored vital sign parameters of the monitored patient in the two stages before and after taking the medicine, and at the same time takes into account the individual differences of the patients, thereby effectively improving the accuracy of the subsequent monitoring process. Furthermore, due to the fluctuation of the patient's state before medication, the effect of the drug on the patient's vital sign parameters after medication will interfere, which can be characterized in data by analyzing the stable index of the vital sign parameters to be monitored. Therefore, the present invention is based on the stable index of the same vital sign parameters to be monitored in two stages, and combined with the time series characteristics of the abnormal fluctuation data segment in the time series curve to be monitored. The time series characteristics can reflect the time characteristics of abnormal changes in the vital sign parameters to be monitored, and the two are combined to monitor the vital sign conditions of the monitored patients. The present invention analyzes the changes in each patient's own sign parameters and compares them with the historical normal conditions. It can more accurately reflect the physical signs of each patient on the basis of individual differences, so that the accuracy of the doctor's judgment of drug efficacy or disease analysis based on the monitoring results in the subsequent process will also be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A method flow chart of a method for monitoring vital sign parameters accompanying medication for patients with severe mental illness provided by one embodiment of the present invention;

[0051] Figure 2 A method flow chart of a method for obtaining abnormal fluctuation data segments provided by one embodiment of the present invention;

[0052] Figure 3 A method flow chart of a method for obtaining a stable index provided by an embodiment of the present invention;

[0053] Figure 4 A process flow chart of a monitoring process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for monitoring physical sign parameters accompanying the medication process of patients with severe mental illness proposed by the present invention, in combination with the accompanying drawings and preferred embodiments, its specific implementation method, structure, characteristics and effects are described as follows. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0055] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0056] The following is a detailed description of a method for monitoring vital sign parameters during medication for patients with severe mental illness provided by the present invention in conjunction with the accompanying drawings.

[0057] See also Figure 1 , which shows a method flow chart of a method for monitoring vital sign parameters accompanying medication of patients with severe mental illness provided by an embodiment of the present invention, the method comprising the following steps:

[0058] Step S1: Obtain the time series curves of each monitored vital sign parameter of the patient to be monitored in two stages before and after medication.

[0059] During the medication treatment, patients with severe mental illness may experience mild discomfort after taking the medication due to changes in factors such as medication dosage and medication cycle. This mild discomfort may be ignored during the treatment due to the patient's resistance or because the symptoms are not obvious, resulting in the doctor's failure to detect the patient's adverse symptoms in time, affecting the therapeutic effect of the drug. Therefore, the patient's physical signs and parameters before and after taking the medication are usually monitored, and the monitoring results obtained can assist the doctor in making a more accurate judgment on the therapeutic effect of the drug or the patient's condition.

[0060] Therefore, in an embodiment of the present invention, it is necessary to obtain the time series curve of each monitored vital sign parameter of the patient to be monitored in the two stages before and after medication. The specific process includes: since the behavior of patients with severe mental illness is unpredictable and there may be dangerous behaviors, they can be equipped with portable vital sign detection equipment to obtain various monitored vital sign parameters, and the time period of the acquired data is set to one hour before each medication of the patient to be monitored and two hours after medication, so as to obtain the time series data of each monitored vital sign parameter, the sampling frequency can be set to 50Hz, and the specific value can be adjusted according to the implementation scenario, and the least squares method is used to perform curve fitting to obtain the time series curve of each monitored vital sign parameter of the patient to be monitored in the two stages before and after medication.

[0061] It should be noted that in the embodiment of the present invention, the vital sign parameters to be monitored are heart rate amplitude, breathing depth, pulse strength, etc. Taking heart rate amplitude as an example, when the heart beats, the portable vital sign detection device will monitor the heart rate amplitude and the data values ​​will fluctuate. Thus, the data values ​​can be fitted to obtain a timing curve of the heart rate amplitude when the heart beats within a time period, and the same is true for breathing depth and pulse strength. The process of curve fitting using the least squares method is a well-known technology and will not be elaborated here.

[0062] Step S2: for any time series curve to be monitored, analyze the differences between the data values ​​therein, and combine the fluctuation duration of the data values ​​in the time series to obtain the abnormal fluctuation data segment in the time series curve to be monitored.

[0063] The patient's vital signs can be characterized by changes in various vital sign parameters. Specifically, when the data value of a certain vital sign parameter fluctuates abnormally, it may indicate that the patient's physiological state has changed. These changes may be due to drug effects, changes in the condition, or other external factors, so more attention needs to be paid. Therefore, in an embodiment of the present invention, the timing curve to be monitored is divided by the difference in data values ​​in each timing curve to be monitored and the duration of the fluctuation of the data values ​​in the timing series, and the abnormal fluctuation data segments therein are identified to provide support for subsequent monitoring processes.

[0064] Preferably, in one embodiment of the present invention, the method for acquiring the abnormal fluctuation data segment includes:

[0065] See also Figure 2 , which shows a method flow chart of a method for obtaining abnormal fluctuation data segments in one embodiment of the present invention, the method comprising the following steps:

[0066] Step S201: for any time series curve to be monitored, based on the fluctuation of data values ​​in the time series curve to be monitored, a fluctuation period curve is divided.

[0067] In the time series curve to be monitored, all extreme points are obtained, and the mean of the data values ​​of all extreme points is taken as the baseline value. The baseline value can reflect the average level or central trend of the overall fluctuation of all data values ​​in the time series curve to be monitored. Then, a baseline is made in the time series curve to be monitored based on the baseline value. For example, if the baseline value is 5, a straight line of y=5 is made in the time series curve as the baseline.

[0068] Finally, the intersection of the monitored time series curve and the baseline is taken as the dividing point. The dividing point represents the point where the data fluctuation begins to turn after reaching the central trend. It can be used as the key point for dividing the fluctuation cycle. Therefore, the curve segment between each two adjacent dividing points in the time series is taken as a fluctuation cycle curve. At this time, each fluctuation cycle curve represents a slight fluctuation of the monitored vital sign parameters in the monitored time series curve, so that more refined analysis and monitoring can be achieved in the subsequent process.

[0069] Step S202: determine the fluctuation range of the data value in the time series curve to be monitored, and determine the first abnormal factor of each fluctuation period curve according to the position distribution of the extreme value in each fluctuation period curve in the fluctuation range.

[0070] Generally, the boundary values ​​of the data fluctuation range represent the extreme cases of data changes. Therefore, for any timing curve to be monitored, the maximum value and the minimum value in the timing curve to be monitored are respectively used as boundary values ​​to obtain the fluctuation range of the parameter value in the timing curve to be monitored. The fluctuation range reflects the variation range of the parameter value.

[0071] Then for any fluctuation period curve, when the fluctuation period curve is below the baseline, the absolute difference between the minimum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors corresponding to the fluctuation period curve; conversely, when the fluctuation period curve is above the baseline, the absolute difference between the maximum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors. The maximum value in the distance factor measures the degree to which the maximum or minimum value of the fluctuation period curve is far away from a certain boundary of the fluctuation range, while the minimum value in the distance factor measures the degree to which the maximum or minimum value of the fluctuation period curve is close to a certain boundary of the fluctuation range. For example, if the fluctuation range is [-5,10], a fluctuation period curve is above the baseline, and its maximum value is 6, then the corresponding two distance factors are 4 and 11 respectively.

[0072] Finally, the minimum value of the two distance factors is negatively correlated and normalized to the value obtained as the first abnormal factor corresponding to each fluctuation period curve. At this time, the larger the first abnormal factor is, the closer the maximum or minimum value in the fluctuation period curve is to a certain boundary value in the fluctuation range, and the higher the possibility of abnormality in the fluctuation period curve. Among them, the negative correlation mapping and normalization method in the embodiment of the present invention adopts function, It represents an exponential function with the natural constant e as the base, and x represents the independent variable.

[0073] Step S203: In the time series curve to be monitored, analyzing the fluctuation duration of the fluctuation period curve, and determining the second abnormal factor of each fluctuation period curve.

[0074] The duration stability of the fluctuation cycle curve can also be used as an important indicator to evaluate whether the monitored time series curve has abnormal fluctuations.

[0075] Therefore, for any fluctuation cycle curve in any time series curve to be monitored, the time length corresponding to the fluctuation cycle curve (that is, the time difference between the two endpoints of the fluctuation cycle curve) is calculated, and the absolute value of the difference between the preset fluctuation time length of the vital sign parameter to be monitored is used as the second abnormal factor of the fluctuation cycle curve. At this time, the larger the second abnormal factor is, the greater the deviation of the fluctuation cycle curve of the vital sign parameter to be monitored from the normal fluctuation is, which means that the possibility of abnormality of the fluctuation cycle curve is higher.

[0076] It should be noted that the preset fluctuation time length of each monitored vital sign parameter is set as an empirical value, which can be set according to the implementation scenario; or the historical normal time series curves of each monitored vital sign parameter of the patient to be monitored under historical normal conditions in the two stages before and after medication can be obtained in the database, and each historical normal time series curve is also divided into a fluctuation period curve, and then the average time length of all fluctuation period curves in each historical normal time series curve is used as the preset fluctuation time length of each monitored vital sign parameter in each stage.

[0077] Step S204: in the time series curve to be monitored, based on the first abnormal factors and the second abnormal factors of all fluctuation period curves, identify the abnormal fluctuation data segment.

[0078] Based on the above analysis, it can be seen that the larger the first abnormal factor is, the closer the maximum or minimum value in the fluctuation period curve is to a boundary value in the fluctuation range, and the higher the possibility of abnormality in the fluctuation period curve is; the larger the second abnormal factor is, the greater the deviation of the fluctuation period curve of a certain monitored vital sign parameter from the normal fluctuation is, which also indicates that the possibility of abnormality in the fluctuation period curve is higher.

[0079] Therefore, the product of the first abnormal factor and the second abnormal factor of each fluctuation period curve is normalized to the value obtained as the fluctuation abnormal characteristic value of the fluctuation period curve. At this time, the larger the fluctuation abnormal characteristic value is, the more abnormal fluctuations occur in the fluctuation period curve. Normalization is a technical means well known to those skilled in the art, and the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0080] Finally, in the monitored time series curve of the vital sign parameter to be monitored, the fluctuation period curve whose fluctuation abnormality characteristic value is greater than the preset fluctuation threshold is taken as the abnormal fluctuation period curve. At the same time, considering that the abnormal vital sign state is usually persistent, each abnormal fluctuation period curve is combined with the curves of preset length before and after in the time series to form an abnormal fluctuation data segment.

[0081] It should be noted that the preset fluctuation threshold is set to 0.6, and the specific value can be adjusted according to the implementation scenario and is not limited here; the preset length is set to 1 minute, and the specific duration can be adjusted according to the implementation scenario and is not limited here.

[0082] Step S3: In the historical normal time series curve of each vital sign parameter to be monitored, determine the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment in the time series curve to be monitored at each stage of the same vital sign parameter to be monitored; based on the similarity of the changes in the data values ​​in the abnormal fluctuation data segment in each time series curve to be monitored and the corresponding historical normal fluctuation data segment, determine the stability index of each vital sign parameter to be monitored at each stage.

[0083] Patients with severe mental illness may experience emotional agitation or no emotional fluctuations in daily life, but after taking medication, they may experience calm emotions or excitement or full emotions. At the same time as this phenomenon occurs, the patient's vital sign parameters will change. Therefore, for the data segments of the patient with suspected abnormal states, that is, for the abnormal fluctuation data segments obtained in step S2, in order to more accurately evaluate their abnormal fluctuations, the differences between the abnormal fluctuation data segments of the patient's monitored vital sign parameters and the normal fluctuation data segments can be compared, thereby better quantifying the abnormal fluctuations of the monitored vital sign parameters.

[0084] Therefore, in this step, the historical normal fluctuation data segment corresponding to each abnormal fluctuation data segment should be obtained first.

[0085] Preferably, in one embodiment of the present invention, the method for obtaining the historical normal fluctuation data segment includes:

[0086] Obtain in the database the historical normal time series curves of each monitored vital sign parameter of the patient under historical normal conditions in two stages before and after medication.

[0087] Then, for any abnormal fluctuation data segment, in the historical normal time series curve that belongs to the same type of monitored vital sign parameter and the same stage as the abnormal fluctuation data segment (ensuring the same conditions), the data segment corresponding to the abnormal fluctuation data segment in time (ensuring time correspondence) is used as the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment. For example, if the monitored vital sign parameter of a certain abnormal fluctuation data segment is pulse strength, the stage it belongs to is after medication, and the corresponding time is 5 to 10, then in the historical normal time series curve where the monitored vital sign parameter is pulse strength and the stage it belongs to is after medication, the curve segment at time 5-10 is used as the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment. The historical normal fluctuation data segment provides a benchmark for the subsequent analysis process.

[0088] By comparing and analyzing each abnormal fluctuation data segment with its corresponding historical normal fluctuation data segment, the abnormal fluctuation of the monitored vital sign parameters corresponding to the abnormal fluctuation data segment can be further quantified to obtain a specific stability index. This index can intuitively reflect the stability or abnormality of the monitored vital sign parameters at each stage, providing support for subsequent analysis and decision-making.

[0089] Preferably, in one embodiment of the present invention, the method for obtaining the stability index includes:

[0090] See also Figure 3 , which shows a method flow chart of a method for obtaining a stable index in one embodiment of the present invention, the method comprising the following steps:

[0091] Step S301: for any abnormal fluctuation data segment, analyze the difference in the number of extreme value points between the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment, and determine the first deviation factor of the abnormal fluctuation data segment.

[0092] Extreme points usually mean that the changing trend of the data value before and after has changed. Therefore, the number of extreme points can reflect the volatility or stability characteristics of a set of data. Therefore, for any abnormal fluctuation data segment, the absolute value of the difference between the number of extreme points in the abnormal fluctuation data segment and the number of extreme points in the corresponding historical normal fluctuation data segment is used as the first deviation factor. The larger the first deviation factor, the greater the degree of deviation between the abnormal fluctuation data segment and the normal fluctuation state.

[0093] Step S302: Analyze the difference between the data values ​​in the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment, and determine the second deviation factor corresponding to the abnormal fluctuation data segment.

[0094] The size of the extreme value directly reflects the extreme situation of the data, which is more representative. Therefore, by comparing the difference between the extreme values ​​of the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment, the degree of deviation of each abnormal fluctuation state from the normal fluctuation state can be quantified from the perspective of data value.

[0095] For any abnormal fluctuation data segment, all extreme values ​​in the abnormal fluctuation data segment are sorted in time sequence to obtain a sorted sequence.

[0096] All extreme values ​​in the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment are sorted in time sequence to obtain a comparison sequence.

[0097] Then, in the sorting sequence and the comparison sequence, the extreme values ​​with the same serial number are matched to obtain all the matching extreme value pairs. It should be noted that, for example, if there are 5 extreme value points in the abnormal fluctuation data segment, and there are 7 extreme value points in the corresponding historical normal fluctuation data segment, then the final matching extreme value pairs are 5 (the last two extreme value points in the comparison sequence do not participate in the matching); similarly, if there are 7 extreme value points in the abnormal fluctuation data segment, and there are 5 extreme value points in the corresponding historical normal fluctuation data segment, the final matching extreme value pairs are still 5 (the last two extreme value points in the sorting sequence do not participate in the matching).

[0098] Then, the absolute value of the difference between the two extreme values ​​in each matching extreme value pair is calculated as the deviation value. The larger the deviation value, the greater the deviation between the extreme values, and the higher the possibility that the abnormal fluctuation data segment deviates from the normal fluctuation state.

[0099] Finally, the mean of the deviation values ​​of all matching extreme value pairs is taken as the second deviation factor corresponding to the abnormal fluctuation data segment. The larger the second deviation factor, the greater the deviation between the extreme value of the abnormal fluctuation data segment and the extreme value of the corresponding historical normal fluctuation data segment, and the lower the stability index of the abnormal fluctuation data segment should be.

[0100] Step S303: In the monitored time series curve of each monitored vital sign parameter at each stage, the first deviation factor and the second deviation factor of all abnormal fluctuation data segments are comprehensively analyzed to determine the stability index of each monitored vital sign parameter at each stage.

[0101] Based on the above analysis, it can be seen that the larger the first deviation factor of the abnormal fluctuation data segment is, the greater the deviation between the abnormal fluctuation data segment and the normal fluctuation state is; when the second deviation factor is larger, it also indicates that the greater the deviation between the extreme value of the abnormal fluctuation data segment and the extreme value of the corresponding historical normal fluctuation data segment is.

[0102] Therefore, the product of the first deviation factor and the second deviation factor of the abnormal fluctuation data segment is negatively correlated and normalized to achieve logical relationship correction, and the value after negative correlation mapping and normalization is used as the stability factor of the abnormal fluctuation data segment. At this time, the larger the stability factor is, the higher the fluctuation similarity between the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment is, and the higher the stability index of the corresponding vital sign parameter to be monitored should be. Among them, the negative correlation mapping and normalization method in the embodiment of the present invention adopts function, It represents an exponential function with the natural constant e as the base, and x represents the independent variable.

[0103] Based on the above process, the stability factor of each abnormal fluctuation data segment in the monitored time series curve of each monitored vital sign parameter at each stage can be obtained. Finally, in the monitored time series curve of each monitored vital sign parameter at each stage, the stability factors of all abnormal fluctuation data segments are averaged to determine the stability index of each monitored vital sign parameter at each stage. At this time, the larger the stability index of a certain monitored vital sign parameter, the more the fluctuation of the monitored vital sign parameter at a certain stage conforms to the characteristics of normal vital sign parameter changes.

[0104] Step S4: According to the stable indexes of the same type of monitored vital sign parameters in the two stages, and in combination with the time series characteristics of the abnormal fluctuation data segments in the corresponding monitored time series curve, the vital sign conditions of the monitored patient are monitored.

[0105] Considering that the patient's physical sign status before taking the medicine will have a certain impact on the physical sign status after taking the medicine, for example, if the patient's physical sign status before taking the medicine is poor, there will be a relatively abnormal fluctuation. Then after taking the medicine, various monitored physical sign parameters may still show abnormal fluctuations. In step S3, the stability index of each monitored physical sign parameter in each stage can be obtained. Therefore, in an embodiment of the present invention, the stability index of the same monitored physical sign parameter in the two stages is comprehensively analyzed, and combined with the time series characteristics of the abnormal fluctuation data segment in the monitored time series curve of the monitored physical sign parameter (used to reflect the time characteristics of abnormal fluctuations in the physical sign status of the patient to be monitored), the physical sign of the patient to be monitored is monitored.

[0106] Preferably, in one embodiment of the present invention, the monitoring process includes:

[0107] See also Figure 4 , which shows a process flow chart of a monitoring process in one embodiment of the present invention, the process includes the following steps:

[0108] Step S401: Determine a first evaluation parameter for each of the vital sign parameters to be monitored based on a stable index of each of the vital sign parameters to be monitored before and after medication.

[0109] The larger the stability index of a certain monitored vital sign parameter at a certain stage is, the more the fluctuation of the monitored vital sign parameter of the monitored patient at a certain stage conforms to the variation characteristics of the normal vital sign parameter.

[0110] Therefore, if the stability index before medication is larger, it means that the fluctuation of the patient's physical signs before medication is more normal. If the stability index after medication is smaller, it can be regarded as the drug has an impact on the patient's physical signs, and an early warning is needed.

[0111] Therefore, the value of each monitored vital sign parameter after negative correlation mapping of the stable index after medication is multiplied by the stable index before medication, and is used as the first evaluation parameter of each monitored vital sign parameter. At this time, the larger the first evaluation parameter is, the more it indicates that the drug may have an abnormal effect on the monitored vital sign parameter of the patient to be monitored, and an early warning is needed to remind the doctor to make further judgment and analysis.

[0112] Step S402: For any one of the monitored vital sign parameters, a second evaluation parameter of the monitored vital sign parameter is determined based on the time series characteristics of the abnormal fluctuation data segment in the monitored time series curve of the monitored vital sign parameter after medication.

[0113] For any of the monitored vital sign parameters, the value of the monitored vital sign parameter at the start time of the first abnormal fluctuation data segment in the monitored time series curve after medication is negatively correlated and used as the second evaluation parameter of the monitored vital sign parameter. The smaller the value at the start time of the first abnormal fluctuation data segment, the smaller the difference between it and the start time of the monitored time series curve, indicating that the abnormal fluctuation of the monitored vital sign parameter occurs earlier, which also indicates that the drug may have an abnormal effect on the monitored vital sign parameter of the patient to be monitored, and an early warning is required. Among them, the negative correlation mapping can be adopted by using function, represents an exponential function with the natural constant e as the base, and x represents the independent variable; it can also be used The fractional form of x represents the independent variable. It indicates a preset parameter, which is used to prevent the denominator from being 0. The value can be 0.001. The specific value can be adjusted according to the implementation scenario and is not limited here.

[0114] Step S403: Determine an evaluation index for each of the vital sign parameters to be monitored by combining the first evaluation parameter and the second evaluation parameter for each of the vital sign parameters to be monitored.

[0115] The value after normalizing the product of the first evaluation parameter and the second evaluation parameter of each monitored vital sign parameter is used as the evaluation index of each monitored vital sign parameter. The larger the evaluation index, the greater the degree of abnormal change in the monitored vital sign parameter, and the higher the possibility of needing an early warning. Normalization is a technical means well known to those skilled in the art, and the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0116] Step S404: monitoring the physical sign of the patient to be monitored based on the evaluation indicators of all types of physical sign parameters to be monitored.

[0117] If the evaluation index of a certain monitored vital sign parameter is greater than the preset first-level evaluation threshold, an early warning will be issued, and the doctor will be required to conduct further inspection and analysis of the vital sign condition of the monitored patient.

[0118] If the evaluation indicators of all types of monitored vital sign parameters are less than or equal to the preset first-level evaluation threshold, the number of types of monitored vital sign parameters whose evaluation indicators are greater than the preset second-level evaluation threshold is counted. When the number of types is greater than the preset number threshold, it indicates that there may be potential risks and an early warning is still required to remind the doctor to conduct further inspection and analysis of the vital sign status of the monitored patient. Among them, the preset first-level evaluation threshold is greater than the preset second-level evaluation threshold.

[0119] It should be noted that the preset and evaluation thresholds are set to 0.85, the preset secondary evaluation threshold is set to 0.6, and the quantity threshold is set to half of the total number of types of vital sign parameters to be monitored, rounded up. The specific values ​​can be adjusted according to the implementation scenario and are not limited here.

[0120] In summary, the monitored time series curves of each monitored vital sign parameter of the patient to be monitored in the two stages before and after medication are obtained, so as to capture the dynamic changes of various vital sign parameters of the patient and provide a data basis for the subsequent monitoring process. In view of the different fluctuations of the patient's vital sign parameters at different stages, and the changes in the data values ​​of the vital sign parameters and the duration of the fluctuations can be used as an indicator to reflect the patient's current vital sign state, the embodiment of the present invention analyzes the differences in the data values ​​and the fluctuation duration of the data values ​​in the time series for any monitored time series curve, divides the monitored time series curve, and identifies the curve segments with abnormal fluctuations as abnormal fluctuation data segments. The abnormal fluctuation data segment reflects the abnormal fluctuation of a certain vital sign parameter. In order to further quantify its abnormal state, the embodiment of the present invention obtains the historical normal time series curve of each vital sign parameter, which also includes two stages before and after the patient takes the medicine, and then determines the historical normal fluctuation data segment corresponding to each abnormal fluctuation data segment in the historical normal time series curve; and then analyzes the data values ​​in the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment for similar changes, so as to determine the stable index of each monitored vital sign parameter of the monitored patient in each stage. The introduction of the stable index can more intuitively reflect the overall state of the monitored vital sign parameters of the monitored patient in the two stages before and after taking the medicine, and at the same time takes into account the individual differences of the patients, thereby effectively improving the accuracy of the subsequent monitoring process. Furthermore, due to the fluctuation of the patient's state before medication, the effect of the drug on the patient's vital sign parameters after medication will interfere, which can be characterized in data by analyzing the stable index of the vital sign parameters to be monitored. Therefore, the present invention is based on the stable index of the same vital sign parameters to be monitored in two stages, and combined with the time series characteristics of the abnormal fluctuation data segment in the time series curve to be monitored. The time series characteristics can reflect the time characteristics of abnormal changes in the vital sign parameters to be monitored, and the two are combined to monitor the vital sign conditions of the monitored patients. The present invention analyzes the changes in each patient's own sign parameters and compares them with the historical normal conditions. It can more accurately reflect the physical signs of each patient on the basis of individual differences, so that the accuracy of the doctor's judgment of drug efficacy or disease analysis based on the monitoring results in the subsequent process will also be improved.

[0121] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring vital sign parameters during medication for patients with severe mental illness, characterized in that: The method comprises: Obtain the time series curves of each monitored vital sign parameter of the patient to be monitored in two stages before and after medication; For any time series curve to be monitored, the differences between the data values ​​are analyzed, and combined with the fluctuation duration of the data values ​​in the time series, the abnormal fluctuation data segment in the time series curve to be monitored is obtained; In the historical normal time series curve of each monitored vital sign parameter, determine the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment in the monitored time series curve of the same monitored vital sign parameter at each stage; based on the similarity of the changes in the data values ​​in the abnormal fluctuation data segment in each monitored time series curve and the corresponding historical normal fluctuation data segment, determine the stability index of each monitored vital sign parameter at each stage; According to the stable indexes of the same type of monitored vital sign parameters in the two stages, and in combination with the time series characteristics of the abnormal fluctuation data segments in the corresponding monitored time series curve, the vital sign conditions of the monitored patients are monitored; The method for acquiring the abnormal fluctuation data segment includes: For any time series curve to be monitored, a fluctuation period curve is divided based on the fluctuation of data values ​​in the time series curve to be monitored; Determine the fluctuation range of the data value in the time series curve to be monitored, and determine the first abnormal factor of each fluctuation period curve according to the position distribution of the extreme value in each fluctuation period curve in the fluctuation range; For any fluctuation period curve in the time series curve to be monitored, the absolute value of the difference between the time length corresponding to the fluctuation period curve and the preset fluctuation time length of the vital sign parameter to be monitored corresponding to the time series curve to be monitored is used as the second abnormal factor of the fluctuation period curve; The product of the first abnormal factor and the second abnormal factor of the fluctuation period curve is normalized to a value as the fluctuation abnormal characteristic value of the fluctuation period curve; The fluctuation period curve whose fluctuation abnormal characteristic value is greater than the preset fluctuation threshold is taken as the abnormal fluctuation period curve, and each abnormal fluctuation period curve and the curves of preset length before and after in time series are combined into an abnormal fluctuation data segment.

2. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 1, characterized in that: The method for obtaining the fluctuation period curve includes: In the time series curve to be monitored, the average of the data values ​​of all extreme value points is used as a reference value, and a reference line is made in the time series curve to be monitored based on the reference value; The intersection of the time series curve to be monitored and the reference line is taken as a division point, and the curve segment between every two adjacent division points on the time series is taken as a fluctuation period curve.

3. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 1, characterized in that: The method for obtaining the first abnormal factor includes: The maximum value and the minimum value in the time series curve to be monitored are respectively used as a boundary value, so as to obtain the fluctuation range of the data value in the time series curve to be monitored; For any fluctuation period curve, when the fluctuation period curve is below the baseline, the absolute value of the difference between the minimum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors corresponding to the fluctuation period curve; When the fluctuation period curve is above the baseline, the absolute value of the difference between the maximum value of the fluctuation period curve and the boundary value of the fluctuation range is calculated to obtain two distance factors; The minimum value of the two distance factors is negatively correlated and normalized as the first abnormal factor corresponding to each fluctuation cycle curve.

4. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 1, characterized in that: The method for obtaining the historical normal fluctuation data segment includes: Obtain the historical normal time series curve of each monitored vital sign parameter of the patient under historical normal conditions in two stages before and after medication; For any abnormal fluctuation data segment, in the historical normal time series curve that belongs to the same type of monitored vital sign parameters and the same stage as the abnormal fluctuation data segment, the data segment corresponding to the time of the abnormal fluctuation data segment will be taken as the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment.

5. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 1, characterized in that: The method for obtaining the stable index includes: For any abnormal fluctuation data segment, the absolute value of the difference between the number of extreme value points in the abnormal fluctuation data segment and the number of extreme value points in the corresponding historical normal fluctuation data segment is used as the first deviation factor; Analyze the difference between the data values ​​in the abnormal fluctuation data segment and the corresponding historical normal fluctuation data segment, and determine the second deviation factor corresponding to the abnormal fluctuation data segment; The product of the first deviation factor and the second deviation factor of the abnormal fluctuation data segment is negatively correlated and normalized to a value as the stabilization factor of the abnormal fluctuation data segment; In the monitored time series curve of each monitored vital sign parameter at each stage, the stability factors of all abnormal fluctuation data segments are averaged to determine the stability index of each monitored vital sign parameter at each stage.

6. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 5, characterized in that: The method for obtaining the second deviation factor includes: For any abnormal fluctuation data segment, all extreme values ​​in the abnormal fluctuation data segment are sorted in time sequence to obtain a sorted sequence; All extreme values ​​in the historical normal fluctuation data segment corresponding to the abnormal fluctuation data segment are sorted in time sequence to obtain a comparison sequence; In the sorted sequence and the comparison sequence, extreme values ​​with the same sequence number are matched to obtain all matching extreme value pairs; The absolute value of the difference between the two extreme values ​​in each matching extreme value pair is calculated as the deviation value, and the average of the deviation values ​​of all matching extreme value pairs is used as the second deviation factor corresponding to the abnormal fluctuation data segment.

7. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 1, characterized in that: The monitoring of the physical signs of the patient to be monitored according to the stable index of the same physical sign parameter to be monitored in the two stages and in combination with the time series characteristics of the abnormal fluctuation data segment in the corresponding time series curve to be monitored includes: The product of the value of each monitored vital sign parameter after negative correlation mapping with the stable index after medication and the stable index before medication is used as the first evaluation parameter of each monitored vital sign parameter; For any one of the monitored vital sign parameters, based on the time series characteristics of the abnormal fluctuation data segment in the monitored time series curve of the monitored vital sign parameter after medication administration, determine the second evaluation parameter of the monitored vital sign parameter; The product of the first evaluation parameter and the second evaluation parameter of each of the vital sign parameters to be monitored is normalized to a value as an evaluation index of each of the vital sign parameters to be monitored; The vital signs of the patient to be monitored are monitored based on evaluation indicators of all types of vital sign parameters to be monitored.

8. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 7, characterized in that: The method for obtaining the second evaluation parameter includes: For any monitored vital sign parameter, the value of the monitored vital sign parameter at the starting time of the first abnormal fluctuation data segment in the monitored time series curve after medication is negatively correlated and mapped as the second evaluation parameter of the monitored vital sign parameter.

9. A method for monitoring vital sign parameters accompanying medication in patients with severe mental illness according to claim 7, characterized in that: The evaluation indicators based on all kinds of monitored physical sign parameters are used to monitor the physical sign of the patient to be monitored, including: If the evaluation index of a certain vital sign parameter to be monitored is greater than the preset first-level evaluation threshold, an early warning will be issued; If the evaluation indicators of all types of monitored vital sign parameters are less than or equal to the preset first-level evaluation threshold, the number of types of monitored vital sign parameters whose evaluation indicators are greater than the preset second-level evaluation threshold is counted, and when the number of types is greater than the preset number threshold, an early warning is issued; The preset first-level evaluation threshold is greater than the preset second-level evaluation threshold.

Images