Methods, apparatus, and systems for reducing false positive rates of fetal heart monitoring for high-risk pregnant patients

Abstract

The present application relates to the technical field of electric digital data processing, in particular to a method, device and system for reducing false positive rate of fetal heart monitoring of high-risk pregnant patients, which comprises: obtaining a fetal heart rate time sequence and a uterine contraction pressure time sequence, analyzing the degree of fetal heart rate deviating from the normal range according to the fetal heart rate time sequence to determine the fetal heart abnormality index of each to-be-determined abnormal segment; performing regularity analysis on the suspected fetal heart abnormality segment according to the uterine contraction pressure time sequence to determine the influence degree of each suspected fetal heart abnormality segment on the uterine contraction; and determining the credibility of the fetal heart rate time sequence according to the fetal heart abnormality index and the influence degree of each suspected fetal heart abnormality segment, combined with the ratio of the target time number to the current total fetal heart monitoring time number. By determining the credibility, the misjudgment of abnormality caused by the interference of uterine contraction on the fetal heart monitoring data can be avoided, and thus the false positive rate of fetal heart monitoring of high-risk pregnant patients is reduced.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, specifically to a method, device, and system for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnant women. Background Technology

[0002] The false positive rate of fetal heart rate monitoring in high-risk pregnancies refers to the proportion of cases where fetal heart rate monitoring alerts to abnormalities or emergencies in the fetus, but these do not actually occur (false alarm rate). False positive results may lead to unnecessary medical interventions, such as premature delivery or medication, posing potential risks and psychological stress to both the pregnant woman and the fetus. Therefore, it is necessary to analyze the causes of false positives during monitoring, reduce the false positive rate of fetal heart rate monitoring in high-risk pregnancies, avoid misjudging the fetus's health, and prevent unnecessary interventions.

[0003] High-risk pregnancies often involve hypertension and its complications, such as gestational hypertension (including preeclampsia and preeclampsia), which can cause vasoconstriction, affecting blood supply to the uterus and potentially triggering uterine contractions. When monitoring fetal heart rate in high-risk pregnancies, the data is easily affected by uterine contractions, leading to false abnormalities. These false abnormalities may be mistaken for fetal abnormalities, increasing the probability of false positives in fetal heart rate monitoring for high-risk pregnancies. Summary of the Invention

[0004] To address the technical problem of false positives in existing fetal heart rate monitoring for high-risk pregnancies, the present invention aims to provide a method, device, and system for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies. The specific technical solution adopted is as follows:

[0005] One embodiment of the present invention provides a method for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies, the method comprising the following steps:

[0006] Obtain the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart monitoring process for high-risk pregnant patients;

[0007] Based on the analysis of the fetal heart rate time sequence, the degree of deviation of the fetal heart rate from the normal range is determined, and the fetal heart rate abnormality index of each undetermined abnormal segment is determined.

[0008] Based on fetal heart rate abnormality indicators, several suspected fetal heart rate abnormality segments are screened from all undetermined abnormal segments; the suspected fetal heart rate abnormality segments are analyzed for regularity according to the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment.

[0009] Based on the fetal heart rate abnormality indicators and the degree of impact of each suspected fetal heart rate abnormality segment, and combined with the ratio of the number of target time moments to the total number of current fetal heart rate monitoring time moments, the reliability of the fetal heart rate time series is determined.

[0010] The target time is the time among all suspected fetal heart rate abnormalities whose influence is greater than the influence threshold.

[0011] Furthermore, the step of analyzing the degree of fetal heart rate deviation from the normal range based on the fetal heart rate time sequence and determining the fetal heart rate abnormality index for each undetermined abnormal segment includes:

[0012] A first fetal heart rate threshold and a second fetal heart rate threshold that are less than the first fetal heart rate threshold are set and compared with the fetal heart rate at each moment in the fetal heart rate time sequence. Based on the comparison results, each undetermined abnormal segment is obtained.

[0013] Based on the number of abnormal time periods in each undetermined abnormal segment and the range of fetal heart rate variation between positive and negative abnormalities, the first abnormal factor of each undetermined abnormal segment is determined.

[0014] Based on the duration of each undetermined abnormal segment, the time interval between adjacent undetermined abnormal segments, and the degree of fetal heart rate deviation at all abnormal moments, combined with the first abnormal factor, the fetal heart rate abnormality index of each undetermined abnormal segment is determined.

[0015] The duration, the degree of fetal heart rate deviation, and the first abnormal factor are all positively correlated with the fetal heart rate abnormality index, and the time interval is negatively correlated with the fetal heart rate abnormality index; the abnormal moments include positive abnormal moments and negative abnormal moments.

[0016] Furthermore, the step of obtaining each undetermined abnormal segment based on the comparison results includes:

[0017] The time corresponding to a fetal heart rate greater than the first fetal heart rate threshold is recorded as a positive abnormal time, and the time corresponding to a fetal heart rate less than the second fetal heart rate threshold is recorded as a negative abnormal time.

[0018] In the fetal heart rate time sequence, the sequence segment formed by the fetal heart rates corresponding to consecutive positive abnormal times and negative abnormal times is regarded as the undetermined abnormal segment.

[0019] Furthermore, the determination of the first abnormal factor for each undetermined abnormal segment based on the number of abnormal time periods and the range of fetal heart rate variation between positive and negative abnormalities includes:

[0020] For any undetermined abnormal segment, determine the number of abnormal time periods in the undetermined abnormal segment, wherein the abnormal time period is a positive abnormal time period consisting of consecutively adjacent positive abnormal times and a negative abnormal time period consisting of consecutively adjacent negative abnormal times.

[0021] Calculate the difference between the mean fetal heart rate of adjacent positive and negative abnormal periods in the undetermined abnormal segment, and take the maximum difference as the range of fetal heart rate variation between positive and negative abnormalities.

[0022] By combining the number of abnormal time periods in the undetermined abnormal segment and the variation range of the fetal heart rate between positive and negative abnormalities, the first abnormal factor of the undetermined abnormal segment is obtained.

[0023] Furthermore, the step of performing regularity analysis on the suspected abnormal fetal heart rate segments based on the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected abnormal fetal heart rate segment includes:

[0024] In the contraction pressure time series, the sequence segment consisting of consecutive adjacent contraction pressure values ​​that are greater than the set contraction pressure threshold is recorded as a contraction sequence segment; based on the duration and average contraction pressure of each contraction sequence segment, all contraction sequence segments are clustered to obtain various clusters;

[0025] For any suspected abnormal fetal heart rate segment, the contraction sequence segment that is located before the suspected abnormal fetal heart rate segment and has the smallest time interval is identified as the target contraction sequence segment.

[0026] Based on the suspected abnormal fetal heart rate segments, the target uterine contraction sequence segments, and each uterine contraction sequence segment in the cluster to which the target uterine contraction sequence segment belongs, analyze the similarity of the time intervals in which abnormal fetal heart rate occurs under the same uterine contraction conditions, and determine the degree of comprehensive regularity.

[0027] Based on the duration of the target contraction sequence segment and the average contraction pressure at all times, combined with the aforementioned comprehensive regularity, the degree of influence of contractions on the suspected fetal heart rate abnormality segment is determined.

[0028] Furthermore, the step of analyzing the similarity of time intervals in which abnormal fetal heart rates occur under the same contraction conditions, based on suspected abnormal fetal heart rate segments, target contraction sequence segments, and various contraction sequence segments within the cluster to which the target contraction sequence segment belongs, to determine the degree of comprehensive regularity, includes:

[0029] Obtain the time interval between each contraction sequence segment in the cluster to which the target contraction sequence segment belongs and its corresponding suspected fetal heart rate abnormality segment. Calculate the mean of the time interval between each contraction sequence segment in the cluster and its corresponding suspected fetal heart rate abnormality segment, and use it as the reference time interval for the cluster.

[0030] Based on the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster to which the target uterine contraction sequence segment belongs, and the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, the first regularity factor of the suspected fetal heart rate abnormality segment is determined.

[0031] Calculate the range of uterine contraction pressure at all times in the target uterine contraction sequence segment and the range of fetal heart rate at all times in the suspected fetal heart rate abnormality segment, and use the similarity between the two ranges as the second regularity factor of the suspected fetal heart rate abnormality segment.

[0032] The comprehensive regularity of suspected fetal heart rate abnormalities is obtained by integrating the first regularity factor and the second regularity factor.

[0033] Furthermore, based on the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster to which the target uterine contraction sequence segment belongs, and the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, the first regularity factor of the suspected fetal heart rate abnormality segment is determined, including:

[0034] Calculate the absolute value of the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster, and normalize the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, to obtain the normalized value of the number of uterine contraction sequence segments.

[0035] Calculate the product of the absolute value of the difference and the normalized value of the number of uterine contraction sequence segments, and perform negative correlation normalization on the product to obtain the first regularity factor of the suspected abnormal fetal heart rate segment.

[0036] Furthermore, after determining the reliability of the fetal heart rate time series, the following steps are also included:

[0037] Set a first confidence threshold and a second confidence threshold that is less than the first confidence threshold;

[0038] When the reliability of the fetal heart rate time series is greater than or equal to the first reliability threshold, the authenticity of the fetal heart rate time series is determined to be the first authenticity level, and the examination results of high-risk pregnancy patients are obtained based on the fetal heart rate time series.

[0039] When the reliability of the fetal heart rate time series is less than the first reliability threshold but greater than or equal to the second reliability threshold, the authenticity of the fetal heart rate time series is determined to be the second authenticity level, which is less than the first authenticity level. Further monitoring of other dimensions besides fetal heart rate monitoring is then carried out, and the examination results of high-risk pregnancy patients are obtained by combining the monitoring of multiple dimensions.

[0040] When the reliability of the fetal heart rate time series is less than the second reliability threshold, the authenticity of the fetal heart rate time series is determined to be the third authenticity level, which is less than the second authenticity level, and fetal heart rate monitoring is repeated for high-risk pregnancy patients.

[0041] Another embodiment of the present invention provides a system for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies, comprising:

[0042] The data acquisition module is used to acquire the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart monitoring process for high-risk pregnant patients.

[0043] The abnormal index determination module is used to analyze the degree of deviation of the fetal heart rate from the normal range based on the fetal heart rate time sequence and determine the fetal heart rate abnormal index for each undetermined abnormal segment.

[0044] The influence degree determination module is used to screen out several suspected fetal heart rate abnormality segments from all undetermined abnormal segments based on fetal heart rate abnormality indicators; and to perform regularity analysis on the suspected fetal heart rate abnormality segments according to the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment.

[0045] The credibility determination module is used to determine the credibility of the fetal heart rate time series based on the fetal heart rate abnormality index and the degree of influence of each suspected fetal heart rate abnormality segment, combined with the ratio of the number of target times to the total number of current fetal heart rate monitoring times; wherein, the target time is the time among all suspected fetal heart rate abnormality segments whose degree of influence is greater than the degree of influence threshold.

[0046] Another embodiment of the present invention provides an apparatus for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement a method for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies.

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

[0048] This invention provides a method, device, and system for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies. The method analyzes the fetal heart rate time series to determine the degree of deviation from the normal range, identifying fetal heart rate abnormality indicators for each potential abnormal segment. This allows for the selection of several suspected abnormal fetal heart rate segments. Compared to analyzing the entire time series, selecting representative suspected abnormal segments improves data analysis efficiency and also identifies the abnormality of each suspected segment, facilitating subsequent reliability calculations. Further analysis of the degree to which suspected abnormal fetal heart rate segments are affected by uterine contractions, combined with fetal heart rate abnormality indicators, determines the reliability of the fetal heart rate time series. Reliability characterizes the extent to which the entire fetal heart rate time series is unaffected by uterine contractions. By determining reliability, misjudgments due to interference from uterine contractions in fetal heart rate monitoring data can be avoided, thereby reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies. Attached Figure Description

[0049] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating an embodiment of the present invention of a method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies.

[0051] Figure 2 This is a flowchart illustrating the implementation of step 2 in an embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of the reference segment configuration in an embodiment of the present invention;

[0053] Figure 4 This is a flowchart illustrating the implementation of step S32 in an embodiment of the present invention. Detailed Implementation

[0054] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the technical solution proposed according to the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0055] Unless otherwise defined, 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 pertains.

[0056] The application scenarios targeted by this invention can be:

[0057] When monitoring fetal heart rate in high-risk pregnancies, the effects of uterine contractions may lead to false abnormalities in the fetal heart rate data, i.e., false positives. These may be mistaken for abnormalities in the fetus itself, resulting in low reliability of fetal heart rate monitoring in high-risk pregnancies and increasing the probability of false positives.

[0058] To ensure the reliability of fetal heart rate monitoring in high-risk pregnancies and reduce the probability of false positives, this embodiment provides a method to reduce the false positive rate of fetal heart rate monitoring in high-risk pregnancies, such as... Figure 1 As shown, it includes the following steps:

[0059] S1, obtain the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart rate monitoring process for high-risk pregnant patients.

[0060] Here, fetal heart rate refers to the number of times the fetal heart beats per minute, measured in beats / min. The normal range for fetal heart rate is generally [120, 160]. Uterine contractions refer to regular contractions of the uterus, characterized by symmetry, rhythm, polarity, and retraction. The pressure of uterine contractions is measured in millimeters of mercury (mmHg).

[0061] Fetal heart rate monitoring directly reflects the development of the fetus in the uterus. To prevent abnormalities such as intrauterine hypoxia and acidosis, it is necessary to monitor the fetal heart rate. High-risk pregnancies often involve hypertension and its complications, such as gestational hypertension, which may cause vasoconstriction, thereby affecting the blood supply to the uterus and potentially triggering uterine contractions. Fetal heart rate is easily affected by uterine contractions. To analyze the degree of interference of uterine contractions on fetal heart rate monitoring in high-risk pregnancies, it is necessary to monitor the uterine contraction pressure.

[0062] As an example implementation, during prenatal checkups, obstetricians attach fetal heart rate probes and uterine contraction pressure probes to the pregnant woman for 20 to 30 minutes of monitoring to obtain the fetal heart rate time series and uterine contraction pressure time series during the current fetal heart rate monitoring process for high-risk pregnancies. The monitoring duration for fetal heart rate and uterine contraction pressure can be set by the obstetrician according to the pregnant woman's actual situation.

[0063] It should be noted that in this embodiment, in order to facilitate subsequent data processing and avoid differences in units and numerical magnitudes between data, the data is standardized to eliminate the influence of dimensions in data calculations.

[0064] Thus, this embodiment has obtained two basic sequences for analyzing the interference of uterine contractions on fetal heart rate monitoring in high-risk pregnancies: the fetal heart rate time series sequence and the uterine contraction pressure time series sequence.

[0065] S2, based on the fetal heart rate time sequence analysis, the degree of deviation of the fetal heart rate from the normal range is determined, and the fetal heart rate abnormality index of each undetermined abnormal segment is determined.

[0066] Here, the fetal heart rate abnormality index refers to the degree of abnormality of the fetal heart rate at a certain time. The more the fetal heart rate deviates from the normal range, the greater the degree of abnormality of the fetal heart rate.

[0067] During pregnancy, fetal heart rate may fluctuate temporarily for various reasons. These include temporary compression of the umbilical cord due to fetal movement, improper maternal positioning, and uterine contractions, which can cause a temporary decrease in fetal heart rate. Conversely, stimulation of the fetus or frequent fetal movement can cause a temporary increase. If there is a sudden drop or rise in fetal heart rate, such as a sudden increase from 100 beats / minute in the second minute to 170 beats / minute in the third minute during fetal heart rate monitoring, it may be a physiological response such as temporary compression of the fetal trunk and umbilical vein, or the influence of uterine contractions. However, it could also be due to pathological reasons, requiring further analysis of the fetal heart rate abnormality indicators for each undetermined abnormal segment.

[0068] As an exemplary implementation, step 2 above can be achieved through... Figure 2 Steps S21 to S23 shown are implemented as follows:

[0069] S21, set a first fetal heart rate threshold and a second fetal heart rate threshold that is less than the first fetal heart rate threshold, compare them with the fetal heart rate at each moment in the fetal heart rate time sequence, and obtain each undetermined abnormal segment based on the comparison results.

[0070] The normal fetal heart rate ranges from [120, 160]. Fetal heart rates outside the normal range are considered abnormal. In order to analyze the degree to which abnormal fetal heart rates are affected by uterine contractions, it is necessary to screen out abnormal fetal heart rates to determine the undetermined abnormal segments.

[0071] In this embodiment, the first fetal heart rate threshold is set to 160 beats / minute, and the second fetal heart rate threshold is set to 120 beats / minute. The first and second fetal heart rate thresholds are used to screen for abnormal fetal heart rates, and their values ​​can be set by the implementer according to specific circumstances.

[0072] Furthermore, based on the comparison results, each undetermined anomaly segment is obtained, including:

[0073] S211, the time corresponding to a fetal heart rate greater than the first fetal heart rate threshold is recorded as a positive abnormal time, and the time corresponding to a fetal heart rate less than the second fetal heart rate threshold is recorded as a negative abnormal time.

[0074] In this embodiment, moments when the fetal heart rate is greater than 160 beats / minute are recorded as positive abnormal moments, and moments when the fetal heart rate is less than 120 beats / minute are recorded as negative abnormal moments.

[0075] S212, in the fetal heart rate time sequence, the sequence segment consisting of the fetal heart rates corresponding to consecutive positive abnormal times and negative abnormal times is regarded as the undetermined abnormal segment.

[0076] In this embodiment, the fetal heart rates corresponding to consecutive positive and negative abnormal times are combined to form a reference segment, denoted as the undetermined abnormal segment. A schematic diagram of the reference segment structure is shown below. Figure 3 As shown, Figure 3 Abnormal moments include positive and negative abnormal moments, while normal moments are any moments other than abnormal moments. The fetal heart rate during normal moments is within the range of [120, 160].

[0077] S22, based on the number of abnormal time periods in each undetermined abnormal segment and the range of fetal heart rate variation between positive and negative abnormalities, determine the first abnormal factor of each undetermined abnormal segment.

[0078] Here, the first abnormality factor is used to characterize the mutation of fetal heart rate data in the undetermined abnormal segment. The larger the number of abnormal periods in the undetermined abnormal segment, the more frequently the fetal heart rate fluctuates abnormally within and outside the normal range, the more abnormal changes occur in the fetal heart rate, and the greater the possibility of mutation; the greater the range of change in fetal heart rate between positive and negative abnormalities, the greater the degree of mutation.

[0079] Furthermore, for any undetermined anomalous segment, the first anomalous factor of the undetermined anomalous segment is determined, including:

[0080] S221, determine the number of abnormal time periods in the undetermined abnormal segment. The abnormal time period is a positive abnormal time period consisting of consecutive positive abnormal times and a negative abnormal time period consisting of consecutive negative abnormal times.

[0081] In this embodiment, the abnormal time period includes positive abnormal time periods and negative abnormal time periods. The sum of the number of positive abnormal time periods and the number of negative abnormal time periods in the undetermined abnormal period is taken as the number of abnormal time periods.

[0082] It is worth noting that a single abnormal moment is likely a random phenomenon caused by external interference and not a real fetal abnormality. Therefore, this embodiment does not analyze single abnormal moments.

[0083] S222, calculate the difference between the mean fetal heart rate of adjacent positive and negative abnormal periods in the undetermined abnormal segment, and take the maximum difference as the range of change of fetal heart rate between positive and negative abnormalities.

[0084] In this embodiment, the mean fetal heart rate of each abnormal time period in the undetermined abnormal segment is first calculated to obtain the mean fetal heart rate of each positive abnormal time period and each negative abnormal time period; then, adjacent positive and negative abnormal time periods are selected, and the absolute value of the difference between the mean fetal heart rate of adjacent positive and negative abnormal time periods is calculated to determine the maximum absolute value of the difference; the maximum absolute value of the difference is used as the range of change of fetal heart rate between positive and negative abnormalities.

[0085] S223, by integrating the number of abnormal time periods in the undetermined abnormal segment and the range of fetal heart rate changes between positive and negative abnormalities, the first abnormal factor of the undetermined abnormal segment is obtained.

[0086] In this embodiment, the number of abnormal time periods is positively correlated with the first abnormal factor, and the range of change in fetal heart rate between positive and negative abnormalities is also positively correlated with the first abnormal factor.

[0087] As an example, the formula for calculating the first anomaly factor of the c-th undetermined anomaly segment can be:

[0088] In the formula, Let represent the first anomaly factor of the c-th undetermined anomaly segment, and norm represent the linear normalization function. This represents the number of abnormal time periods in the c-th undetermined abnormal segment. It represents the range of fetal heart rate variation between positive and negative abnormalities in the c-th undetermined abnormal segment, and also represents the maximum absolute value of the difference between the mean fetal heart rate of adjacent positive and negative abnormal periods in the c-th undetermined abnormal segment.

[0089] It is worth noting that, in order to facilitate data processing, the norm function is used to limit the value range of the first outlier to between 0 and 1. Of course, other methods can also be used to achieve normalization.

[0090] S23. Based on the duration of each undetermined abnormal segment, the time interval with adjacent undetermined abnormal segments, and the degree of fetal heart rate deviation at all abnormal moments, combined with the first abnormal factor, determine the fetal heart rate abnormality index for each undetermined abnormal segment.

[0091] Here, the duration of the undetermined abnormal segment can characterize the duration of the abnormal moment. The shorter the duration of the abnormal moment, the more likely it is caused by accidental factors such as a brief stimulation of the fetus, and the less likely it is to be an actual abnormality. The smaller the time interval between the undetermined abnormal segment and the adjacent undetermined abnormal segment, the higher the frequency of the abnormal moment and the greater the degree of abnormality. The greater the degree of fetal heart rate deviation among all the abnormal moments of the undetermined abnormal segment, that is, the higher the overall degree of deviation of the fetal heart rate from the normal range within the undetermined abnormal segment, the greater the fetal heart rate abnormality index of the undetermined abnormal segment. The first abnormal factor represents the abnormal mutation situation of the undetermined abnormal segment. The more severe the abnormal mutation, the greater the fetal heart rate abnormality index.

[0092] In this embodiment, the duration, degree of fetal heart rate deviation, and first abnormal factor are all positively correlated with the fetal heart rate abnormality index, while the time interval is negatively correlated with the fetal heart rate abnormality index; abnormal moments include positive abnormal moments and negative abnormal moments.

[0093] As an example, the formula for calculating the fetal heart rate abnormality index of the c-th undetermined abnormal segment can be:

[0094] In the formula, This represents the fetal heart rate abnormality index of the c-th undetermined abnormal segment. This represents the first anomaly factor of the c-th undetermined anomaly segment. This represents the duration of the c-th undetermined anomaly segment. This represents the mean of the degree of fetal heart rate deviation at all abnormal moments in the c-th undetermined abnormal segment. This represents the time interval between the c-th undetermined anomaly segment and the (c-1)-th undetermined anomaly segment. The time interval can be calculated from the first time of two adjacent undetermined anomaly segments. norm represents the linear normalization function.

[0095] It is worth noting that, in order to improve the accuracy of fetal heart rate abnormality indicators, a comprehensive analysis is conducted from multiple aspects. Duration, degree of fetal heart rate deviation, and time interval are all factors related to fetal heart rate abnormalities. Without considering the influence of dimensions, these factors can be directly applied to... , and Perform multiplication calculations.

[0096] Furthermore, the degree of fetal heart rate deviation at abnormal moments is obtained, including:

[0097] When the abnormal time is a positive abnormal time, the difference between the fetal heart rate at the abnormal time and the first fetal heart rate threshold is taken as the degree of fetal heart rate deviation; when the abnormal time is a negative abnormal time, the difference between the second fetal heart rate threshold and the fetal heart rate at the abnormal time is taken as the degree of fetal heart rate deviation.

[0098] Thus, this embodiment has obtained fetal heart rate abnormality indicators for each undetermined abnormal segment.

[0099] S3. Based on fetal heart rate abnormality indicators, several suspected fetal heart rate abnormality segments are selected from all undetermined abnormal segments; the suspected fetal heart rate abnormality segments are analyzed for regularity according to the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment.

[0100] Here, the suspected abnormal fetal heart rate segment is the undetermined abnormal segment with a relatively large fetal heart rate abnormality index. The larger the undetermined abnormal segment has the larger the fetal heart rate abnormality index, the greater the possibility that it is a suspected abnormal fetal heart rate segment. The degree of influence indicates the degree to which the fetal heart rate corresponding to the suspected abnormal fetal heart rate segment is affected by uterine contractions. The greater the degree of influence, the greater the interference of uterine contractions on the suspected abnormal fetal heart rate segment, and the greater the possibility that the fetal heart rate corresponding to the suspected abnormal fetal heart rate segment will have a false positive.

[0101] As an exemplary implementation, step S3 can be achieved by steps S31 to S32 (not shown in the figure):

[0102] S31, based on fetal heart rate abnormality indicators, selects several suspected fetal heart rate abnormality segments from all undetermined abnormal segments.

[0103] In this embodiment, in order to analyze sequence segments with a high degree of abnormality and reduce the amount of computation, an abnormality threshold is set, and undetermined abnormal segments with fetal heart rate abnormality index greater than the abnormality threshold are identified as suspected fetal heart rate abnormality segments, thereby obtaining each suspected fetal heart rate abnormality segment.

[0104] The value range of the fetal heart rate abnormality index is between 0 and 1, and the value range of the abnormality threshold used for comparison and analysis with the fetal heart rate abnormality index is also between 0 and 1. Therefore, the abnormality threshold can be set to 0.6.

[0105] If the anomaly threshold is set too high, some undetermined anomaly segments with a high degree of abnormality will be ignored. If the anomaly threshold is set too low, some undetermined anomaly segments with a low degree of abnormality will appear, which have little reference value and will affect the efficiency of subsequent calculation and analysis. Therefore, implementers can set it according to the specific actual situation.

[0106] S32, based on the time sequence of uterine contraction pressure, perform regularity analysis on suspected abnormal fetal heart rate segments to determine the degree of influence of uterine contractions on each suspected abnormal fetal heart rate segment.

[0107] High-risk pregnancies may already have issues such as insufficient uteroplacental blood flow. During uterine contractions, the uterine vessels are further compressed, leading to a more significant reduction in placental blood flow. This can cause temporary changes in fetal blood oxygenation, resulting in temporary deceleration or acceleration of the fetal heart rate. These physiological fluctuations in fetal heart rate caused by contractions can easily be misinterpreted as genuine abnormalities such as fetal distress, increasing the false positive rate. Therefore, it is necessary to analyze the patterns of suspected abnormal fetal heart rate segments using a uterine contraction pressure time series sequence to quantify the interference of contractions on each suspected abnormal segment.

[0108] As an exemplary implementation, step S32 described above can be achieved through... Figure 4 Steps S321 to S324 shown are implemented as follows:

[0109] S321, In the uterine contraction pressure time sequence, the sequence segment consisting of consecutive adjacent uterine contraction pressure values ​​that are greater than the set uterine contraction pressure threshold is recorded as a uterine contraction sequence segment; based on the duration and average uterine contraction pressure of each uterine contraction sequence segment, all uterine contraction sequence segments are clustered to obtain various clusters.

[0110] In this embodiment, the uterine contraction pressure threshold is the maximum uterine contraction pressure under normal conditions, and an empirical value of 20 mmHg can be used. The implementer can set the size of the uterine contraction pressure threshold according to the specific actual situation. The uterine contraction sequence segments in the uterine contraction pressure time sequence are obtained. The uterine contraction sequence segments are the sequence segments with greater uterine contraction intensity, which can be used to analyze the regularity of uterine contraction pressure changes.

[0111] It should be noted that uterine contractions are a physiological process, and their pressure changes are not uniform or regular. Evenly dividing the contraction pressure sequence would ignore the differences in contraction pressure magnitude and actual physiological characteristics. However, contraction sequence segments selected based on thresholds highlight contractions with higher pressure that may affect the fetus, facilitating more targeted analysis of contractions that may have a critical impact on the fetus.

[0112] Furthermore, the duration and average contraction pressure of each contraction sequence segment are obtained as the data set for each contraction sequence segment; based on the data set of each contraction sequence segment, the K-means clustering algorithm is used to cluster all contraction sequence segments to obtain several clusters, i.e., each class.

[0113] The elbow method can be used to determine the optimal number of clusters for the K-means clustering algorithm. The implementation process of the K-means clustering algorithm is existing technology and is not within the scope of this invention; therefore, it will not be described in detail here. Each cluster can represent a uterine contraction condition. By analyzing the clusters, the time intervals at which abnormal fetal heart rates occur under the same uterine contraction conditions can be analyzed. Under the influence of uterine contractions, the time intervals at which abnormal fetal heart rates occur under the same uterine contraction conditions may have a certain similarity. The stronger the similarity of the time intervals, the greater the influence of uterine contractions on the abnormal fetal heart rate.

[0114] S322, for any suspected abnormal fetal heart rate segment, determine the contraction sequence segment that is located before the corresponding time of the suspected abnormal fetal heart rate segment and has the smallest time interval as the target contraction sequence segment.

[0115] Abnormal fetal heart rate caused by uterine contractions often occurs after the contractions begin, and the intensity of the abnormality increases with the intensity of the contractions. Therefore, it is necessary to identify a target uterine contraction sequence segment for suspected abnormal fetal heart rate segments. Conversely, each uterine contraction sequence segment also has its corresponding suspected abnormal fetal heart rate segment.

[0116] S323, based on the suspected abnormal fetal heart rate segment, the target uterine contraction sequence segment, and each uterine contraction sequence segment in the cluster to which the target uterine contraction sequence segment belongs, analyze the similarity of the time intervals in which abnormal fetal heart rate occurs under the same uterine contraction conditions, and determine the degree of comprehensive regularity.

[0117] Here, the degree of regularity refers to the regularity of the distribution of fetal heart rate data in the suspected abnormal fetal heart rate segment. The more regular the distribution of fetal heart rate data, the more closely it matches the distribution characteristics of fetal heart rate data affected by uterine contractions, and the greater the degree of interference of uterine contractions on the fetal heart rate data in the suspected abnormal fetal heart rate segment.

[0118] As an exemplary implementation method, determining the degree of comprehensive regularity includes:

[0119] The first step is to obtain the time interval between each contraction sequence segment in the cluster to which the target contraction sequence segment belongs and its corresponding suspected fetal heart rate abnormality segment, and to calculate the mean of the time interval between each contraction sequence segment in the cluster and its corresponding suspected fetal heart rate abnormality segment, which is used as the reference time interval for the cluster.

[0120] In this embodiment, under the same uterine contraction conditions, the time intervals in which fetal heart rate abnormalities occur may have certain similarities. Based on the aforementioned principle of time interval similarity, it is necessary to obtain the time intervals between each uterine contraction sequence segment in the cluster to which the target uterine contraction sequence segment belongs and its corresponding suspected fetal heart rate abnormality segment, and calculate the mean of all time intervals in the cluster as a reference time interval for similarity analysis with individual time intervals in the cluster.

[0121] Regarding the suspected fetal heart rate abnormality segments corresponding to each contraction sequence segment in the cluster, referring to the process of determining the target contraction sequence segment, it can be seen that it refers to the suspected fetal heart rate abnormality segment located after the contraction sequence segment and the closest to it. Each contraction sequence segment has its corresponding suspected fetal heart rate abnormality segment.

[0122] The second step is to determine the first regularity factor of the suspected fetal heart rate abnormality segment based on the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster to which the target uterine contraction sequence segment belongs, and the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs.

[0123] Here, the first regularity factor is obtained based on the principle that the time intervals of abnormal fetal heart rate under the same uterine contraction conditions are similar. The difference between the time interval and the reference time interval is used to analyze the similarity of the time intervals, while the number of uterine contraction sequence segments in the cluster is used to characterize the reliability of the difference between the time interval and the reference time interval.

[0124] Furthermore, the first regularity factor for the suspected abnormal fetal heart rate segment was identified, including:

[0125] First, the absolute value of the difference between the time interval of the target contraction sequence segment and the reference time interval of the cluster is calculated, and the number of contraction sequence segments in the cluster to which the target contraction sequence segment belongs is normalized to obtain the normalized value of the number of contraction sequence segments.

[0126] In this embodiment, the normalized value of the number of uterine contraction sequence segments can be equal to the ratio of the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs to the total number of all uterine contraction sequence segments.

[0127] Secondly, the product of the absolute value of the difference and the normalized value of the number of uterine contraction sequence segments is calculated, and the product is subjected to negative correlation normalization to obtain the first regularity factor of the suspected abnormal fetal heart rate segment.

[0128] As an example, the formula for calculating the first regularity factor of the y-th suspected fetal heart rate abnormality segment can be:

[0129] In the formula, Let represent the first regularity factor of the y-th suspected fetal heart rate abnormality segment, exp represent the exponential function with the natural constant as the base, and exp(-) is used to normalize the data to account for negative correlations. This represents the time interval between the y-th suspected fetal heart rate abnormality segment and the target uterine contraction sequence segment. This represents the reference time interval for the cluster to which the target uterine contraction sequence segment corresponding to the y-th suspected fetal heart rate abnormality segment belongs. This represents the function for finding the absolute value. This represents the number of contraction sequence segments in the cluster to which the target contraction sequence segment corresponding to the y-th suspected fetal heart rate abnormality segment belongs.

[0130] In the formula for calculating the first regularity factor, This represents the difference between the time interval corresponding to the y-th suspected fetal heart rate abnormality segment and the reference time interval corresponding to all suspected fetal heart rate abnormality segments under the same uterine contraction conditions. The smaller the difference between the time interval and the reference time interval, the greater the regularity of the y-th suspected fetal heart rate abnormality segment and the greater its influence from uterine contractions. The larger the number of uterine contraction sequence segments in the cluster, the higher the frequency of uterine contractions under the same uterine contraction conditions, and the larger the corresponding data volume. A large amount of data will offset the influence of some random errors and accidental factors, making the reference time interval closer to the true overall characteristics. Therefore, the reliability of the difference between the time interval used to analyze similar time intervals and the reference time interval is higher.

[0131] The third step is to calculate the range of uterine contraction pressure at all times in the target uterine contraction sequence segment and the range of fetal heart rate at all times in the suspected fetal heart rate abnormality segment, and use the similarity between the two ranges as the second regularity factor of the suspected fetal heart rate abnormality segment.

[0132] In this embodiment, within the suspected abnormal fetal heart rate segment, the closer the amplitude of the changes in fetal heart rate matches the changes in uterine pressure, the higher the regularity of the abnormal fetal heart rate within the segment, and the greater the influence of uterine contractions on the suspected abnormal fetal heart rate segment. Furthermore, since multi-dimensional standardization is used to process the fetal heart rate and uterine contraction pressure data, the influence of different units does not need to be considered when calculating the second regularity factor.

[0133] The fourth step is to integrate the first and second regularity factors to obtain the comprehensive regularity of the suspected abnormal fetal heart rate segments.

[0134] In this embodiment, both the first regularity factor and the second regularity factor are positively correlated with the degree of comprehensive regularity. The larger the first regularity factor and the second regularity factor are, the greater the degree of comprehensive regularity is.

[0135] As an example, the formula for calculating the overall regularity of the y-th suspected fetal heart rate abnormality segment can be:

[0136] In the formula, This represents the overall regularity of the y-th suspected fetal heart rate abnormality segment, where norm represents the linear normalization function. This represents the first regularity factor of the y-th suspected fetal heart rate abnormality segment. The second regularity factor represents the y-th suspected fetal heart rate abnormality segment, and also represents the degree of similarity between the two ranges. This represents the range of fetal heart rate at all times within the y-th suspected abnormal fetal heart rate segment. This represents the range of contraction pressure at all moments within the target contraction sequence segment corresponding to the y-th suspected fetal heart rate abnormality segment. This represents a non-zero constant, used to avoid the possibility of the denominator of a fraction being zero. An empirical value of 0.01 can be used.

[0137] S324, based on the duration of the target contraction sequence segment and the average contraction pressure at all times, combined with the degree of comprehensive regularity, determines the degree of influence of contractions on the suspected abnormal fetal heart rate segment.

[0138] In high-risk pregnancies, increased uterine pressure during contractions can compress the uterine spiral arteries, reducing uteroplacental blood flow. However, when contractions are short in duration and weak in intensity, the increase in intrauterine pressure during contractions is not significant, having little impact on uteroplacental circulation and generally not causing significant changes in fetal heart rate. Therefore, when analyzing the degree to which abnormal segments are affected by contractions, in addition to analyzing the overall regularity of suspected abnormal fetal heart rate segments, it is also necessary to consider the duration of the target contraction sequence segment and the average contraction pressure at all times.

[0139] In this embodiment, the duration of the target uterine contraction sequence segment, the average uterine contraction pressure, and the overall regularity of the y-th suspected fetal heart rate abnormality segment are all positively correlated with the degree of influence of uterine contractions. That is, the greater the duration, the average uterine contraction pressure, and the overall regularity, the greater the degree of influence of uterine contractions on the suspected fetal heart rate abnormality segment.

[0140] As an example, the formula for calculating the degree of influence of uterine contractions on the y-th suspected fetal heart rate abnormality segment can be:

[0141] In the formula, This indicates the degree to which the y-th suspected abnormal fetal heart rate segment is affected by uterine contractions. This represents the duration of the target uterine contraction sequence segment corresponding to the y-th suspected fetal heart rate abnormality segment. This represents the average uterine contraction pressure at all times within the target uterine contraction sequence segment corresponding to the y-th suspected fetal heart rate abnormality segment. This indicates the overall regularity of the y-th suspected fetal heart rate abnormality segment.

[0142] It is worth noting that the duration of the target contraction sequence and the average contraction pressure are factors related to the degree of influence. In order to improve the numerical accuracy of the degree of influence of contractions, the duration and the average contraction pressure are also used to calculate the degree of influence without considering the dimensions of the calculation factors.

[0143] Thus, this embodiment has obtained the degree of influence of uterine contractions on each suspected abnormal fetal heart rate segment.

[0144] S4. Based on the fetal heart rate abnormality indicators and impact of each suspected abnormal fetal heart rate segment, and combined with the ratio of the number of target time points to the total number of current fetal heart rate monitoring time points, the reliability of the fetal heart rate time sequence is determined.

[0145] Here, reliability refers to the dependability of the fetal heart rate time series. The higher the reliability of the fetal heart rate, the less the fetal heart rate time series is affected by uterine contractions, the less likely false positives will occur, and the more accurate the fetal heart rate test results will be. The target time is the time among all suspected fetal heart rate abnormalities whose influence exceeds the influence threshold. The ratio of the number of target times to the total number of current fetal heart rate monitoring times can represent the proportion of fetal heart rates that are significantly affected by uterine contractions among all the total number of fetal heart rates. The more fetal heart rate data that are significantly affected by uterine contractions, the lower the reliability of the fetal heart rate time series that is not affected by uterine contractions, that is, the lower the reliability of the fetal heart rate time series that does not produce false positives. In addition, both the fetal heart rate abnormality index and the influence degree are negatively correlated with the reliability of the current monitored fetal heart rate; the higher the fetal heart rate abnormality index and the influence degree, the lower the reliability of the fetal heart rate time series.

[0146] The purpose of fetal heart rate monitoring is to accurately identify whether the fetus is experiencing pathological conditions such as hypoxia or distress. However, too many suspected fetal heart rate abnormalities caused by uterine contractions can mask the true characteristics of fetal heart rate changes. This makes it difficult to accurately distinguish which fetal heart rate data truly reflects fetal health issues from numerous abnormal data points affected by uterine contractions, and which are false positives caused by uterine contraction interference. This reduces the reliability of the monitoring data and leads to false positives in fetal heart rate monitoring. Therefore, by determining the reliability of fetal heart rate time series, the possibility of false positives in fetal heart rate monitoring can be reduced to some extent.

[0147] As an example, the formula for calculating the reliability of fetal heart rate time series can be:

[0148] In the formula, K represents the reliability of the fetal heart rate time series, exp represents the exponential function with the natural constant as the base, exp(-) is used to normalize the data to account for negative correlations, and N represents the target time, which is the time among all suspected abnormal fetal heart rate segments where the influence is greater than the influence threshold. This indicates the total number of fetal heart rate monitoring sessions currently in progress. This represents the average degree of influence of uterine contractions on all suspected fetal heart rate abnormalities whose impact exceeds the threshold. This represents the average value of fetal heart rate abnormality indicators across all suspected abnormal fetal heart rate segments.

[0149] In the confidence calculation formula, the impact threshold can be set to 0.7, which is used to filter out suspected fetal heart rate abnormalities that are significantly affected by uterine contractions. Implementers can set the impact threshold according to the specific situation. When the impact of uterine contractions is more sensitive, the impact threshold can be set to a smaller value. When the impact of uterine contractions is less sensitive, the impact threshold can be set to a larger value.

[0150] It should be noted that by determining the reliability of the fetal heart rate time series, the false positive rate of fetal heart rate monitoring in high-risk pregnancies can be reduced. The lower the reliability, the greater the possibility of a false positive rate in the fetal heart rate time series. Fetal heart rate time series with a large false positive rate generally cannot be used to confirm the patient's test results and fetal heart rate monitoring needs to be repeated.

[0151] Thus, the reliability of the fetal heart rate time sequence was obtained.

[0152] After determining the reliability of the fetal heart rate time sequence, this embodiment also includes:

[0153] The first step is to set a first confidence threshold and a second confidence threshold that is less than the first confidence threshold.

[0154] In this embodiment, based on experience, the first confidence threshold is set to 0.7 and the second confidence threshold is set to 0.5. The first and second confidence thresholds are used to determine the true level of the fetal heart rate time series. The higher the true level, the lower the false positive rate. The subsequent processing methods for different true levels are different.

[0155] The first and second confidence thresholds are limited to a range of 0 to 1 and are used for comparative analysis of the confidence level of the fetal heart rate time series. The first and second confidence thresholds can be set by the implementer according to the requirements of fetal heart rate authenticity, and no specific limitation is made here.

[0156] The second step is to determine the authenticity of the fetal heart rate time series as the first level of authenticity when the credibility of the fetal heart rate time series is greater than or equal to the first confidence threshold, and to obtain the examination results of high-risk pregnancy patients based on the fetal heart rate time series.

[0157] In this embodiment, when the fetal heart rate time sequence is at the first level of accuracy, it is considered that the current fetal heart rate monitoring data can accurately reflect the intrauterine condition of the fetus. Doctors can directly determine whether the patient's test result is positive or negative based on the monitored fetal heart rate data.

[0158] The third step is to determine the authenticity of the fetal heart rate time series as the second authenticity level, which is less than the first authenticity level, when the credibility of the fetal heart rate time series is less than the first authenticity level. Further monitoring of other dimensions besides fetal heart rate monitoring is then carried out, and the examination results of high-risk pregnancy patients are obtained by combining the monitoring results of multiple dimensions.

[0159] In this embodiment, when the fetal heart rate time sequence is at the second level of authenticity, it is considered that the current fetal heart rate monitoring data may be abnormal, and further examinations by the doctor are needed, such as ultrasound examination, biophysical scoring, umbilical blood flow monitoring, etc., to determine whether the patient's test results are positive or negative.

[0160] When the reliability of the fetal heart rate time series is less than the second reliability threshold, the authenticity of the fetal heart rate time series is determined to be the third authenticity level, which is less than the second authenticity level, and fetal heart rate monitoring is repeated for high-risk pregnancy patients.

[0161] In this embodiment, when the fetal heart rate time sequence is at the second level of accuracy, it is considered that the current fetal heart rate monitoring data is affected by uterine contractions and cannot reflect the intrauterine condition of the fetus, and the patient needs to undergo fetal heart rate monitoring again.

[0162] Another embodiment of the present invention provides a system for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies, comprising:

[0163] The data acquisition module is used to acquire the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart monitoring process for high-risk pregnant patients.

[0164] The abnormal index determination module is used to analyze the degree of deviation of the fetal heart rate from the normal range based on the fetal heart rate time sequence and determine the fetal heart rate abnormal index for each undetermined abnormal segment.

[0165] The influence degree determination module is used to screen out several suspected fetal heart rate abnormality segments from all undetermined abnormal segments based on fetal heart rate abnormality indicators; and to perform regularity analysis on the suspected fetal heart rate abnormality segments according to the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment.

[0166] The credibility determination module is used to determine the credibility of the fetal heart rate time series based on the fetal heart rate abnormality index and the degree of influence of each suspected fetal heart rate abnormality segment, combined with the ratio of the number of target times to the total number of current fetal heart rate monitoring times; wherein, the target time is the time among all suspected fetal heart rate abnormality segments whose degree of influence is greater than the degree of influence threshold.

[0167] Another embodiment of the present invention provides an apparatus for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement a method for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies.

[0168] In summary, this invention analyzes the impact of uterine contractions on fetal heart rate during fetal heart rate monitoring in high-risk pregnant patients, avoiding misjudgments of abnormalities due to interference from uterine contractions on fetal heart rate monitoring data, and helps reduce the false positive rate of fetal heart rate monitoring in high-risk pregnant patients.

[0169] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies, characterized in that, Includes the following steps: Obtain the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart monitoring process for high-risk pregnant patients; A first fetal heart rate threshold and a second fetal heart rate threshold lower than the first fetal heart rate threshold are set and compared with the fetal heart rate at each moment in the fetal heart rate time series. Based on the comparison results, each undetermined abnormal segment is obtained. Based on the number of abnormal periods in each undetermined abnormal segment and the amplitude of fetal heart rate variation between positive and negative abnormalities, a first abnormal factor is determined for each undetermined abnormal segment. Based on the duration of each undetermined abnormal segment, the time interval with adjacent undetermined abnormal segments, and the degree of fetal heart rate deviation at all abnormal moments, combined with the first abnormal factor, a fetal heart rate abnormality index for each undetermined abnormal segment is determined. The duration, the degree of fetal heart rate deviation, and the first abnormal factor are all positively correlated with the fetal heart rate abnormality index, and the time interval is negatively correlated with the fetal heart rate abnormality index. The abnormal moments include positive and negative abnormal moments. Based on the fetal heart rate abnormality index, several suspected fetal heart rate abnormality segments are screened from all undetermined abnormal segments. Based on the uterine contraction pressure time series, the suspected fetal heart rate abnormality segments are analyzed for regularity to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment. Based on the fetal heart rate abnormality indicators and the degree of impact of each suspected fetal heart rate abnormality segment, and combined with the ratio of the number of target time moments to the total number of current fetal heart rate monitoring time moments, the reliability of the fetal heart rate time series is determined. The target time is the time among all suspected fetal heart rate abnormalities whose influence is greater than the influence threshold.

2. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 1, characterized in that, The process of obtaining each undetermined abnormal segment based on the comparison results includes: The time corresponding to a fetal heart rate greater than the first fetal heart rate threshold is recorded as a positive abnormal time, and the time corresponding to a fetal heart rate less than the second fetal heart rate threshold is recorded as a negative abnormal time. In the fetal heart rate time sequence, the sequence segment formed by the fetal heart rates corresponding to consecutive positive abnormal times and negative abnormal times is regarded as the undetermined abnormal segment.

3. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 2, characterized in that, The determination of the first abnormal factor for each undetermined abnormal segment based on the number of abnormal time periods and the range of fetal heart rate variation between positive and negative abnormalities includes: For any undetermined abnormal segment, determine the number of abnormal time periods in the undetermined abnormal segment, wherein the abnormal time period is a positive abnormal time period consisting of consecutively adjacent positive abnormal times and a negative abnormal time period consisting of consecutively adjacent negative abnormal times. Calculate the difference between the mean fetal heart rate of adjacent positive and negative abnormal periods in the undetermined abnormal segment, and take the maximum difference as the range of fetal heart rate variation between positive and negative abnormalities. By combining the number of abnormal time periods in the undetermined abnormal segment and the variation range of the fetal heart rate between positive and negative abnormalities, the first abnormal factor of the undetermined abnormal segment is obtained.

4. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 1, characterized in that, The step of performing regularity analysis on the suspected abnormal fetal heart rate segments based on the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected abnormal fetal heart rate segment includes: In the contraction pressure time series, the sequence segment consisting of consecutive adjacent contraction pressure values ​​that are greater than the set contraction pressure threshold is recorded as a contraction sequence segment; based on the duration and average contraction pressure of each contraction sequence segment, all contraction sequence segments are clustered to obtain various clusters; For any suspected abnormal fetal heart rate segment, the contraction sequence segment that is located before the suspected abnormal fetal heart rate segment and has the smallest time interval is identified as the target contraction sequence segment. Based on the suspected abnormal fetal heart rate segments, the target uterine contraction sequence segments, and each uterine contraction sequence segment in the cluster to which the target uterine contraction sequence segment belongs, analyze the similarity of the time intervals in which abnormal fetal heart rate occurs under the same uterine contraction conditions, and determine the degree of comprehensive regularity. Based on the duration of the target contraction sequence segment and the average contraction pressure at all times, combined with the aforementioned comprehensive regularity, the degree of influence of contractions on the suspected fetal heart rate abnormality segment is determined.

5. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 4, characterized in that, The method involves analyzing the similarity of time intervals between abnormal fetal heart rate occurrences under the same contraction conditions, based on suspected abnormal fetal heart rate segments, target contraction sequence segments, and various contraction sequence segments within the cluster to which the target contraction sequence segment belongs, to determine the degree of comprehensive regularity, including: Obtain the time interval between each contraction sequence segment in the cluster to which the target contraction sequence segment belongs and its corresponding suspected fetal heart rate abnormality segment. Calculate the mean of the time interval between each contraction sequence segment in the cluster and its corresponding suspected fetal heart rate abnormality segment, and use it as the reference time interval for the cluster. Based on the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster to which the target uterine contraction sequence segment belongs, and the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, the first regularity factor of the suspected fetal heart rate abnormality segment is determined. Calculate the range of uterine contraction pressure at all times in the target uterine contraction sequence segment and the range of fetal heart rate at all times in the suspected fetal heart rate abnormality segment, and use the similarity between the two ranges as the second regularity factor of the suspected fetal heart rate abnormality segment. The comprehensive regularity of suspected fetal heart rate abnormalities is obtained by integrating the first regularity factor and the second regularity factor.

6. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 5, characterized in that, Based on the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster to which the target uterine contraction sequence segment belongs, and the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, the first regularity factor for suspected fetal heart rate abnormality segments is determined, including: Calculate the absolute value of the difference between the time interval of the target uterine contraction sequence segment and the reference time interval of the cluster, and normalize the number of uterine contraction sequence segments in the cluster to which the target uterine contraction sequence segment belongs, to obtain the normalized value of the number of uterine contraction sequence segments. Calculate the product of the absolute value of the difference and the normalized value of the number of uterine contraction sequence segments, and perform negative correlation normalization on the product to obtain the first regularity factor of the suspected abnormal fetal heart rate segment.

7. The method for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies according to claim 1, characterized in that, After determining the reliability of the fetal heart rate time series, the following steps are also included: Set a first confidence threshold and a second confidence threshold that is less than the first confidence threshold; When the reliability of the fetal heart rate time series is greater than or equal to the first reliability threshold, the authenticity of the fetal heart rate time series is determined to be the first authenticity level, and the examination results of high-risk pregnancy patients are obtained based on the fetal heart rate time series. When the reliability of the fetal heart rate time series is less than the first reliability threshold but greater than or equal to the second reliability threshold, the authenticity of the fetal heart rate time series is determined to be the second authenticity level, which is less than the first authenticity level. Further monitoring of other dimensions besides fetal heart rate monitoring is then carried out, and the examination results of high-risk pregnancy patients are obtained by combining the monitoring of multiple dimensions. When the reliability of the fetal heart rate time series is less than the second reliability threshold, the authenticity of the fetal heart rate time series is determined to be the third authenticity level, which is less than the second authenticity level, and fetal heart rate monitoring is repeated for high-risk pregnancy patients.

8. A system for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies, characterized in that, include: The data acquisition module is used to acquire the fetal heart rate time sequence and uterine contraction pressure time sequence during the current fetal heart monitoring process for high-risk pregnant patients. The abnormal index determination module is used to analyze the degree of deviation of the fetal heart rate from the normal range based on the fetal heart rate time sequence and determine the fetal heart rate abnormal index for each undetermined abnormal segment. The influence degree determination module is used to screen out several suspected fetal heart rate abnormality segments from all undetermined abnormal segments based on fetal heart rate abnormality indicators; and to perform regularity analysis on the suspected fetal heart rate abnormality segments according to the uterine contraction pressure time sequence to determine the degree of influence of uterine contractions on each suspected fetal heart rate abnormality segment. The credibility determination module is used to determine the credibility of the fetal heart rate time series based on the fetal heart rate abnormality index and the degree of influence of each suspected fetal heart rate abnormality segment, combined with the ratio of the number of target times to the total number of current fetal heart rate monitoring times; wherein, the target time is the time among all suspected fetal heart rate abnormality segments whose degree of influence is greater than the degree of influence threshold.

9. A device for reducing the false positive rate of fetal heart rate monitoring in high-risk pregnancies, characterized in that, The device includes a processor and a memory, the processor being used to process instructions stored in the memory to implement a method for reducing the false positive rate of fetal heart rate monitoring in patients with high-risk pregnancies as described in any one of claims 1-7.

Images