CN117747116A - Intelligent early warning method for physiological index of obstetrical department midwifery - Google Patents
Intelligent early warning method for physiological index of obstetrical department midwifery Download PDFInfo
- Publication number
- CN117747116A CN117747116A CN202410185149.5A CN202410185149A CN117747116A CN 117747116 A CN117747116 A CN 117747116A CN 202410185149 A CN202410185149 A CN 202410185149A CN 117747116 A CN117747116 A CN 117747116A
- Authority
- CN
- China
- Prior art keywords
- data
- physiological index
- physiological
- sample data
- current time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims abstract description 61
- 238000005070 sampling Methods 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 230000036541 health Effects 0.000 claims abstract description 29
- 230000005856 abnormality Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 6
- 230000036772 blood pressure Effects 0.000 claims description 3
- 230000036760 body temperature Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000035606 childbirth Effects 0.000 description 1
- 210000003754 fetus Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a physiological index intelligent early warning method for obstetrical delivery, which comprises the following steps: in the sampling period, sample data of each physiological index is collected, an isolated forest of each physiological index is constructed, each sampling time after the sampling period is taken as the current time, the isolated forest of each physiological index is updated according to the data of each physiological index at the current time, the abnormal score of the data of each physiological index at the current time is determined according to the isolated forest updated by each physiological index at the current time, and whether the health condition of the lying-in woman at the current time is abnormal or not is judged and early warned according to the abnormal score of the data of all physiological indexes at the current time. The invention improves the accuracy of the abnormal data detection result of each physiological index at the current moment, and timely carries out correct early warning on the health condition of the puerpera so as to ensure the safety of the puerpera.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent early warning method for physiological indexes of obstetrics and midwifery.
Background
The data of the physiological indexes of obstetrical delivery relate to the data of various physiological parameters of a puerpera in the processes of waiting for delivery, delivering and postpartum, and medical staff can better know the health condition of the puerpera by analyzing the data of the physiological indexes of obstetrical delivery, and meanwhile, early warning is carried out on the health condition of the puerpera, potential problems are found and treated in time, so that the safety of the puerpera is ensured.
The isolated forest anomaly detection algorithm is a conventional anomaly detection method, and is used for constructing an isolated forest according to historical sample data, calculating an anomaly score of new data according to the isolated forest, and further judging the anomaly condition of the new data, wherein the new data is not added into the isolated forest as sample data; thus, in conventional isolated forest anomaly detection algorithms, the isolated forest is not updated with new data.
Because the health conditions of the puerpera in different time periods are different, the generated data of the physiological indexes are also different, and therefore, the abnormal detection result of the data of the new physiological indexes is inaccurate only by carrying out abnormal detection on the data of the new physiological indexes according to the isolated forest constructed by the historical sample data.
In summary, a new intelligent early warning method for the physiological index of obstetric delivery is needed.
Disclosure of Invention
In order to solve one or more of the above technical problems, the present invention provides a physiological index intelligent early warning method for obstetrical delivery, which comprises the following steps:
collecting sample data of each physiological index in a sampling period, wherein the physiological indexes comprise blood pressure, body temperature and heart rate;
constructing an isolated forest of each physiological index through an isolated forest anomaly detection algorithm according to sample data of each physiological index, and setting the initial weight of each sample data to be equal to a preset value;
sequentially taking each sampling time after the sampling period as the current time according to the time sequence, and determining an isolated forest after each physiological index update at the current time comprises the following steps: adding the data of each physiological index at the current moment into an isolated forest of each physiological index as new sample data, wherein the initial weight of the new sample data is equal to a preset value, and adjusting the weight of each sample data according to the difference between the sampling moment of each sample data and the current moment;
in the isolated forest with updated physiological indexes at the current moment, determining the abnormal score of the data of each physiological index at the current moment according to the quantity of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight value adjusted by each sample data;
and judging whether the health condition of the puerpera at the current moment is abnormal or not according to the abnormal scores of the data of all the physiological indexes at the current moment and carrying out early warning.
Further, the collecting sample data of each physiological index includes:
according to the preset sampling frequency, the data of each physiological index of the puerpera are collected at each sampling time by the monitor and used as sample data of each physiological index, and the length of the sampling period is equal to the preset length.
Further, the constructing an isolated forest of each physiological index by an isolated forest anomaly detection algorithm according to the sample data of each physiological index includes:
for each physiological index, inputting a data sample of the physiological index into an isolated forest abnormality detection algorithm to generate a preset number of isolated trees, wherein all the isolated trees form an isolated forest of the physiological index.
Further, the adjusted weight of the sample data satisfies the expression:。
in the method, in the process of the invention,indicating the weight of the i-th sample data after adjustment, i indicating the serial number of the sample data,/and->Represents taking the maximum value, Q represents a preset value, T represents the current time,/and>sample time representing the ith sample data, < +.>Representing the division remainder.
Further, the anomaly score of the data of each physiological index at the current time satisfies the expression:
wherein x represents the data of the physiological index at the current time,abnormal score of data x representing physiological index at current time, K representing preset quantity, N representing quantity of sample data in isolated forest after physiological index at current time is updated, < + >>The path length of data x representing the physiological index at the current time in the ith isolated tree in the isolated forest after the physiological index at the current time is updated, < ->Weight of corresponding node on ith isolated tree in isolated forest after current time physiological index update of data x representing current time physiological index, +.>The number of sample data contained in the corresponding node on the ith isolated tree in the isolated forest after the current time physiological index update of data x representing the current time physiological index +.>Represents an exponential function based on natural constants, < ->Representing the expected value of the path length.
Further, the weight of the node refers to an average value of the weights of all sample data contained in the node.
Further, the expected value of the path length satisfies the expression:
further, the determining whether the health condition of the parturient at the current moment is abnormal or not and performing early warning according to the abnormal scores of the data of all the physiological indexes at the current moment includes:
if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is larger than the preset score threshold value, the health condition of the puerpera at the current moment is abnormal; if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is smaller than or equal to a preset score threshold value, the health condition of the puerpera at the current moment is normal;
and if the health condition of the puerpera is abnormal at each moment within the preset time, early warning is carried out.
The embodiment of the invention has at least the following beneficial effects: according to the invention, when the isolated forest of each physiological index is constructed according to the sample data of each physiological index, the initial weight of each sample data is set, the data of each physiological index at the current moment is used as new sample data to be added into the isolated forest of each physiological index, the initial weight of the new sample data is set, the weight of each sample data is adjusted according to the difference between the sampling moment of each sample data and the current moment, the isolated forest of each physiological index is updated, in the isolated forest after the current moment physiological index update, the abnormal score of the data of each physiological index at the current moment is determined according to the quantity of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight after the adjustment of each sample data, the accuracy of the abnormal data detection result of each physiological index at the current moment is improved, the health condition of a lying-in woman is correctly pre-warned in time, and the safety of the lying-in woman is ensured.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for intelligent early warning of physiological indexes of obstetrical delivery according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a physiological index intelligent early warning method for obstetrical delivery according to the invention, which is provided by combining the accompanying drawings and the preferred embodiment, wherein the specific implementation, structure, characteristics and effects of the physiological index intelligent early warning method are as follows. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a specific scheme of an intelligent early warning method for physiological indexes of obstetrical delivery, which is specifically described below with reference to the accompanying drawings.
In order to ensure the safety of the puerpera in the childbirth process, the health condition of the puerpera needs to be pre-warned by carrying out abnormal detection on the data of the physiological indexes; the isolated forest anomaly detection algorithm is a conventional anomaly detection method, the algorithm constructs an isolated forest according to historical sample data, calculates an anomaly score of new data according to the isolated forest for new data to be generated, and further judges the anomaly condition of the new data, but the new data is not added into the isolated forest as sample data, so that in the conventional isolated forest anomaly detection algorithm, the isolated forest is not updated according to the new data; therefore, when the abnormality detection is performed on the data of the physiological index of the puerpera through the conventional isolated forest abnormality detection algorithm, the abnormality score of the new data is calculated according to the isolated forest, in fact, the abnormality detection is performed on the data of the new physiological index only according to the isolated forest constructed by the historical sample data, and the health conditions of the puerpera in different time periods are different, and the generated data of the physiological index are also different, so that the abnormality detection result of the obtained data of the new physiological index is inaccurate only by performing the abnormality detection on the data of the new physiological index according to the historical sample data.
In summary, when constructing an isolated forest of each physiological index according to sample data of each physiological index, the invention sets an initial weight of each sample data, adds data of each physiological index at the current moment into the isolated forest of each physiological index as new sample data, sets the initial weight of the new sample data, adjusts the weight of each sample data according to the difference between the sampling moment of each sample data and the current moment, updates the isolated forest of each physiological index, and determines the abnormal score of the data of each physiological index at the current moment according to the quantity of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight adjusted by each sample data in the isolated forest after the physiological index update at the current moment, thereby improving the accuracy of the abnormal detection result of the data of each physiological index at the current moment, timely carrying out correct early warning on the health condition of a lying-in woman and ensuring the safety of the lying-in woman.
Referring to fig. 1, a flowchart of a method for intelligent early warning of physiological indicators of obstetric delivery according to an embodiment of the present invention is shown, the method includes the following steps:
and S001, collecting sample data of each physiological index in a sampling period.
It should be noted that, the physiological index of obstetrical delivery relates to various physiological parameters of puerpera in three stages of delivery, delivery and postpartum, and by monitoring and evaluating the physiological index of obstetrical delivery, medical staff can better understand the health conditions of puerpera and fetus, discover and deal with potential problems in time, and ensure the safety of delivery process.
Specifically, in a sampling period, according to a preset sampling frequency, data of each physiological index of the puerpera is collected at each sampling moment through a monitor, and the data are used as sample data of each physiological index, wherein the physiological index comprises, but is not limited to, blood pressure, body temperature and heart rate of the puerpera, and the length of the sampling period is equal to the preset length.
The sampling frequency and length can be set by the practitioner according to the actual implementation, for example, the sampling frequency is once per second, and the length is 300 seconds.
Step S002, constructing an isolated forest of each physiological index, taking each sampling time after the sampling period as the current time, and updating the isolated forest of each physiological index according to the data of each physiological index at the current time.
It should be noted that, in the conventional isolated forest anomaly detection algorithm, the isolated forest is not updated according to the newly acquired data, but the health condition of the puerpera is different in different time periods, and the generated data of the physiological indexes are also different, so that the anomaly detection result of the data of the new physiological indexes is not accurate only by carrying out anomaly detection on the data of the new physiological indexes according to the historical sample data; the method and the device have the advantages that the initial weight is set for each sample data constructing the isolated forest, the newly acquired data is used as new sample data and added into the isolated forest, the distribution difference between the data with earlier sampling time and the data with the current time is larger as time goes by, the weight of the sample data with different sampling time is weakened for improving the accuracy of the abnormal detection result of the data with the new physiological index, the degree of weakening of the weight of the sample data with earlier sampling time is larger, and when the abnormal score of the data with the physiological index with the current time is determined according to the distribution situation of all the data in the isolated forest, the influence of the data with earlier sampling time on the abnormal score of the data with the physiological index with the current time is smaller, namely the abnormal score of the data with the physiological index with the current time is smaller.
Specifically, constructing an isolated forest of each physiological index through an isolated forest anomaly detection algorithm according to sample data of each physiological index, and setting an initial weight of each sample data to be equal to a preset value; sequentially taking each sampling time after the sampling period as the current time according to the time sequence, updating the isolated forest of each physiological index according to the data of each physiological index at the current time, and determining the updated isolated forest of each physiological index at the current time, wherein the method comprises the following steps: the data of each physiological index at the current moment is used as new sample data to be added into an isolated forest of each physiological index, the initial weight of the new sample data is equal to a preset value, and the weight of each sample data is adjusted according to the difference between the sampling moment of each sample data and the current moment.
The constructing an isolated forest of each physiological index through an isolated forest anomaly detection algorithm according to the sample data of each physiological index comprises the following steps: for each physiological index, inputting a data sample of the physiological index into an isolated forest abnormality detection algorithm to generate a preset number of isolated trees, wherein all the isolated trees form an isolated forest of the physiological index.
The operator can set a preset number and a preset value according to the actual implementation situation, for example, the preset number is 100, and the preset value is 1.
It should be noted that, the isolated forest anomaly detection algorithm is a known technique, and will not be described here.
The adjusting the weight of each sample data according to the difference between the sampling time of each sample data and the current time comprises the following steps: the weight after the adjustment of the ith sample data satisfies the expression:
in the method, in the process of the invention,indicating the weight of the i-th sample data after adjustment, i indicating the serial number of the sample data,/and->Represents taking the maximum value, Q represents a preset value, T represents the current time,/and>sample time representing the ith sample data, < +.>Representing the division remainder.
It should be noted that the number of the substrates,the difference between the sampling time of the i-th sample data and the current time is represented, and the earlier the sampling time of the sample data is, the larger the difference between the sampling time of the sample data and the current time is, the smaller the weight of the sample data is.
And step S003, determining the abnormal score of the data of each physiological index at the current moment according to the updated isolated forest of each physiological index at the current moment.
Specifically, in the isolated forest after the update of the physiological index at the current moment, determining the abnormal score of the data of each physiological index at the current moment according to the number of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight adjusted by each sample data, wherein the abnormal score comprises the following steps: for any one physiological index, the abnormal score of the data of the physiological index at the current moment satisfies the expression:
wherein x represents the data of the physiological index at the current time,an abnormality score of data x representing the physiological index at the current time, K representing a preset number, and also representing the number of isolated trees in the isolated forest after the physiological index at the current time is updated, N representing the number of sample data in the isolated forest after the physiological index at the current time is updated,/">The path length of the data x representing the physiological index at the current moment in the ith isolated tree in the isolated forest after the physiological index at the current moment is updated, wherein the path length is the number of nodes passing between the root node and the node corresponding to the data x, and the weight is equal to the sum of the number of nodes passing between the root node and the node corresponding to the data x>Weight of corresponding node on ith isolated tree in isolated forest after current time physiological index update of data x representing current time physiological index, +.>The number of sample data contained in the corresponding node on the ith isolated tree in the isolated forest after the current time physiological index update of data x representing the current time physiological index +.>Represents an exponential function based on natural constants, < ->Representing the expected value of the path length.
It should be noted that the number of the substrates,the weight of the corresponding node on the i-th isolated tree in the isolated forest after the current time physiological index update of the data x representing the current time physiological index is larger, the more likely the sample data contained in the node corresponding to the data x is to be collected at the sampling time which is closer to the current time, the smaller the difference between the distribution of the sample data and the distribution of the current time data is, and the larger the influence on the abnormal score of the data for judging the current time physiological index is;the number of sample data included in the node corresponding to the i-th isolated tree in the isolated forest after the current time physiological index update is represented by the data x of the current time physiological indexThe smaller the value, the smaller the sample data having the same distribution as the data x, the data x and possibly the abnormal data, at this time, the larger the abnormal score of the data x of the physiological index at the current time, the application is by the proportional function ∈ ->Implementing the logical relationship; />The smaller the path length of the data x representing the physiological index at the current time in the i-th isolated tree in the isolated forest after the physiological index at the current time is updated, the more easily the data x is isolated in the isolated tree relative to other sample data, so the more likely the data x is abnormal data, and at this time, the greater the abnormal score of the data x of the physiological index at the current time is.
The weight of the node refers to an average value of weight values of all sample data contained in the node.
Wherein the expected value of the path lengthThe expression is satisfied:
it should be noted that, the expected value of the path length is a well-known step in the isolated forest anomaly detection algorithm, and will not be described here.
In the isolated forest with updated physiological indexes at the current moment, according to the quantity of sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight value adjusted by each sample data, the abnormal score of the data of each physiological index at the current moment is determined, the accuracy of the abnormal detection result of the data of each physiological index at the current moment is improved, the health condition of the puerpera is accurately pre-warned in time, and the safety of the puerpera is ensured.
It should be noted that, because the health conditions of the parturient in different time periods are different, the generated data of the physiological indexes are also different, and the distribution difference between the data with earlier sampling time and the data with the current time is larger as time goes on, in order to ensure the accuracy of the abnormal detection result of the data of the physiological indexes with the current time, when the time difference between the sample data with earliest sampling time and the current time in the isolated forest is larger, the isolated forest of each physiological index needs to be reconstructed according to the new sample data; because the data of the physiological indexes of the puerpera have a certain relevance, when the health condition of the puerpera is abnormal at a certain moment, the generated data of different physiological indexes show abnormality, and the abnormal degree of the data of different physiological indexes is different, but the difference of the abnormal scores of the data of all physiological indexes is smaller, and when the difference of the abnormal scores of the data of all physiological indexes is larger, the abnormal score of the data of each physiological index is inaccurate when the updated isolated forest of each physiological index at the current moment is determined according to the updated isolated forest of each physiological index at the current moment, and the isolated forest of each physiological index needs to be reconstructed according to new sample data.
Specifically, if the maximum difference between the current time and the sampling time of all the sample data in the isolated forest updated by each physiological index at the current time is greater than or equal to a preset time threshold, or the variance of the abnormal scores of the data of all the physiological indexes at the current time is greater than a preset difference threshold, the current time is taken as the ending time of a new sampling period, the sample data of each physiological index is collected in the new sampling period, and the isolated forest of each physiological index is constructed by an isolated forest abnormality detection algorithm according to the sample data of each physiological index.
The operator may set a preset time threshold and a preset difference threshold according to the actual implementation, for example, the preset time threshold is 1200 seconds, and the preset difference threshold is 3.
And S004, judging whether the health condition of the puerpera at the current moment is abnormal or not according to the abnormal scores of the data of all the physiological indexes at the current moment and carrying out early warning.
Specifically, if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is greater than a preset score threshold value, the health condition of the lying-in woman at the current moment is abnormal; if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is smaller than or equal to the preset score threshold value, the health condition of the puerpera at the current moment is normal.
Further, if the health condition of the puerpera is abnormal at each moment within the preset time, early warning is carried out.
The operator may set a preset score threshold and a preset duration, for example, the preset score threshold is 0.76 and the preset duration is 30 seconds, according to the actual implementation situation.
In summary, when constructing an isolated forest of each physiological index according to sample data of each physiological index, the invention sets an initial weight of each sample data, adds data of each physiological index at the current moment into the isolated forest of each physiological index as new sample data, sets the initial weight of the new sample data, adjusts the weight of each sample data according to the difference between the sampling moment of each sample data and the current moment, updates the isolated forest of each physiological index, and determines the abnormal score of the data of each physiological index at the current moment according to the quantity of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight after the adjustment of each sample data in the isolated forest after the update of the physiological index at the current moment, thereby improving the accuracy of the abnormal detection result of the data of each physiological index at the current moment, and timely carrying out correct early warning on the health condition of the lying-in women, and ensuring the safety of the lying-in advance.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. An intelligent early warning method for physiological indexes of obstetrical department delivery is characterized by comprising the following steps:
collecting sample data of each physiological index in a sampling period, wherein the physiological indexes comprise blood pressure, body temperature and heart rate;
constructing an isolated forest of each physiological index through an isolated forest anomaly detection algorithm according to sample data of each physiological index, and setting the initial weight of each sample data to be equal to a preset value;
sequentially taking each sampling time after the sampling period as the current time according to the time sequence, and determining an isolated forest after each physiological index update at the current time comprises the following steps: adding the data of each physiological index at the current moment into an isolated forest of each physiological index as new sample data, wherein the initial weight of the new sample data is equal to a preset value, and adjusting the weight of each sample data according to the difference between the sampling moment of each sample data and the current moment;
in the isolated forest with updated physiological indexes at the current moment, determining the abnormal score of the data of each physiological index at the current moment according to the quantity of the sample data contained in the node corresponding to the data of each physiological index at the current moment and the weight value adjusted by each sample data;
and judging whether the health condition of the puerpera at the current moment is abnormal or not according to the abnormal scores of the data of all the physiological indexes at the current moment and carrying out early warning.
2. The method for intelligent pre-warning of physiological indexes of obstetric delivery according to claim 1, wherein the step of collecting sample data of each physiological index comprises the steps of:
according to the preset sampling frequency, the data of each physiological index of the puerpera are collected at each sampling time by the monitor and used as sample data of each physiological index, and the length of the sampling period is equal to the preset length.
3. The method for intelligently pre-warning the physiological indexes of obstetrical department delivery according to claim 1, wherein the constructing the isolated forest of each physiological index through the isolated forest abnormality detection algorithm according to the sample data of each physiological index comprises the following steps:
for each physiological index, inputting a data sample of the physiological index into an isolated forest abnormality detection algorithm to generate a preset number of isolated trees, wherein all the isolated trees form an isolated forest of the physiological index.
4. The method for intelligently pre-warning physiological indexes of obstetrical delivery according to claim 1, wherein the weight value of the sample data after adjustment satisfies the expression:
in the method, in the process of the invention,indicating the weight of the i-th sample data after adjustment, i indicating the serial number of the sample data,/and->Represents taking the maximum value, Q represents a preset value, T represents the current time,/and>sample time representing the ith sample data, < +.>Representing the division remainder.
5. The intelligent pre-warning method for physiological indexes of obstetrical department delivery according to claim 1, wherein the abnormal score of the data of each physiological index at the current moment satisfies the expression:
wherein x represents the data of the physiological index at the current time,an abnormality score of data x representing the physiological index at the current time, K representing a preset number, N representing the number of sample data in the isolated forest after the physiological index at the current time is updated,the path length of data x representing the physiological index at the current time in the ith isolated tree in the isolated forest after the physiological index at the current time is updated, < ->Weight of corresponding node on ith isolated tree in isolated forest after current time physiological index update of data x representing current time physiological index, +.>The number of sample data contained in the corresponding node on the ith isolated tree in the isolated forest after the current time physiological index update of data x representing the current time physiological index +.>Represents an exponential function based on natural constants, < ->Representing the expected value of the path length.
6. The method of claim 5, wherein the weight of the node is an average of weights of all sample data contained in the node.
7. A physiological index intelligent pre-warning method for obstetrical delivery according to claim 5, wherein the expected value of the path length satisfies the expression:。
8. the method for intelligently pre-warning the physiological index of obstetrical department delivery according to claim 1, wherein the step of judging whether the health condition of the puerpera at the current moment is abnormal or not and pre-warning according to the abnormal scores of the data of all the physiological indexes at the current moment comprises the following steps:
if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is larger than the preset score threshold value, the health condition of the puerpera at the current moment is abnormal; if the average value of the abnormal scores of the data of all the physiological indexes at the current moment is smaller than or equal to a preset score threshold value, the health condition of the puerpera at the current moment is normal;
and if the health condition of the puerpera is abnormal at each moment within the preset time, early warning is carried out.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410185149.5A CN117747116B (en) | 2024-02-19 | 2024-02-19 | Intelligent early warning method for physiological index of obstetrical department midwifery |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410185149.5A CN117747116B (en) | 2024-02-19 | 2024-02-19 | Intelligent early warning method for physiological index of obstetrical department midwifery |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117747116A true CN117747116A (en) | 2024-03-22 |
CN117747116B CN117747116B (en) | 2024-05-17 |
Family
ID=90261242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410185149.5A Active CN117747116B (en) | 2024-02-19 | 2024-02-19 | Intelligent early warning method for physiological index of obstetrical department midwifery |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117747116B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104320362A (en) * | 2014-09-29 | 2015-01-28 | 电子科技大学 | Method for PCMA signal blind separation |
CN108337639A (en) * | 2018-05-02 | 2018-07-27 | 鹿建银 | A kind of Monte Carlo mobile node location algorithm based on Newton interpolation |
CN110487276A (en) * | 2019-08-20 | 2019-11-22 | 北京理工大学 | A kind of sample vector matching locating method based on correlation analysis |
CN114509938A (en) * | 2022-01-07 | 2022-05-17 | 东南大学 | Single-effect lithium bromide unit load rapid tracking control method |
CN115565675A (en) * | 2022-07-25 | 2023-01-03 | 郑州大学第三附属医院(河南省妇幼保健院) | Delivery prediction system for pregnant and lying-in women |
CN116054780A (en) * | 2023-01-02 | 2023-05-02 | 桂林电子科技大学 | Particle filtering method based on state track clustering similarity and application |
CN116181508A (en) * | 2022-12-30 | 2023-05-30 | 浙江吉利控股集团有限公司 | Fuel evaporation system leakage calculation method, device, equipment and storage medium |
CN116246777A (en) * | 2023-04-24 | 2023-06-09 | 山东工业职业学院 | Gynaecology and obstetrics information analysis method based on community yield test data stream |
CN116962272A (en) * | 2023-08-02 | 2023-10-27 | 北京优特捷信息技术有限公司 | Abnormality detection method, device, equipment and storage medium for network index |
CN117194920A (en) * | 2023-09-06 | 2023-12-08 | 万仁企业管理技术(深圳)有限公司 | Data system processing platform and processing method based on big data analysis |
-
2024
- 2024-02-19 CN CN202410185149.5A patent/CN117747116B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104320362A (en) * | 2014-09-29 | 2015-01-28 | 电子科技大学 | Method for PCMA signal blind separation |
CN108337639A (en) * | 2018-05-02 | 2018-07-27 | 鹿建银 | A kind of Monte Carlo mobile node location algorithm based on Newton interpolation |
CN110487276A (en) * | 2019-08-20 | 2019-11-22 | 北京理工大学 | A kind of sample vector matching locating method based on correlation analysis |
CN114509938A (en) * | 2022-01-07 | 2022-05-17 | 东南大学 | Single-effect lithium bromide unit load rapid tracking control method |
CN115565675A (en) * | 2022-07-25 | 2023-01-03 | 郑州大学第三附属医院(河南省妇幼保健院) | Delivery prediction system for pregnant and lying-in women |
CN116181508A (en) * | 2022-12-30 | 2023-05-30 | 浙江吉利控股集团有限公司 | Fuel evaporation system leakage calculation method, device, equipment and storage medium |
CN116054780A (en) * | 2023-01-02 | 2023-05-02 | 桂林电子科技大学 | Particle filtering method based on state track clustering similarity and application |
CN116246777A (en) * | 2023-04-24 | 2023-06-09 | 山东工业职业学院 | Gynaecology and obstetrics information analysis method based on community yield test data stream |
CN116962272A (en) * | 2023-08-02 | 2023-10-27 | 北京优特捷信息技术有限公司 | Abnormality detection method, device, equipment and storage medium for network index |
CN117194920A (en) * | 2023-09-06 | 2023-12-08 | 万仁企业管理技术(深圳)有限公司 | Data system processing platform and processing method based on big data analysis |
Non-Patent Citations (1)
Title |
---|
刘思颖: ""基于贝叶斯网络的糖尿病并发症预测模型研究"", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》, no. 04, 30 April 2021 (2021-04-30), pages 065 - 25 * |
Also Published As
Publication number | Publication date |
---|---|
CN117747116B (en) | 2024-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2023157993A (en) | Systems and methods for predicting patient health status | |
US6423016B1 (en) | System and method for evaluating labor progress during childbirth | |
CN113077900B (en) | Diabetes early risk assessment method, device, computer equipment and medium | |
CN117747116B (en) | Intelligent early warning method for physiological index of obstetrical department midwifery | |
CN115862793A (en) | Apparatus and method for cardiovascular medical data analysis, computer storage medium | |
Almeida et al. | Electrohysterography extracted features dependency on anthropometric and pregnancy factors | |
CN116246777B (en) | Gynaecology and obstetrics information analysis method based on community yield test data stream | |
Yeang | The kinetics of latex flow from the rubber tree in relation to latex vessel plugging and turgor pressure | |
Spilka et al. | Stability of variability features computed from fetal heart rate with artifcially infused missing data | |
CN113223713A (en) | Dynamic monitoring method, system and storage medium based on risk assessment | |
CN117747094A (en) | Abnormal detection method for gynecological disease clinical sign data | |
TW201400087A (en) | Estimating method for vascular access function of dialysis fistula | |
CN117442212B (en) | Intelligent monitoring method for obstetrical nursing | |
CN116439661B (en) | Perinatal puerpera physiological state monitoring and evaluating method and system | |
RU2779371C1 (en) | Method for predicting the recurrence of stone formation in patients with urolithiasis | |
JP2020179143A (en) | Method and electronic device for predicting sudden drop in blood pressure | |
CN117727458B (en) | BEFAST stroke screening system and method based on online learning | |
CN115171890A (en) | Non-invasive IUI treatment scoring system based on artificial intelligence technology | |
US20240221951A1 (en) | Atrial tachycardia analysis module providing evolving blueprint of tachycardia events | |
CN113057597A (en) | Method and system for monitoring physiological state of puerpera in real time in production process | |
CN115424729A (en) | Path simulation method for virtual intervention of microcatheter | |
JP2024524042A (en) | Atrial tachycardia analysis module that provides an evolving schedule of tachycardia events | |
Zhang et al. | Prediction of Deterioration in Critically Ill Patients with Heart Failure Based on Vital Signs Monitoring | |
EP1289416B1 (en) | Apparatus for evaluating labor progress during childbirth | |
RU2624372C1 (en) | Method for delivery prediction for pregnant women with uterine scar |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |