KR102568306B1 - Mobile delivery progress evaluation method using mobile birth calculator and terminal for the same - Google Patents

Abstract

A first step in which the user terminal receives patient data, which is data including at least one of personal information of the patient, clinical data of the patient, and measurement data according to the progress of delivery of the patient, wherein the user terminal performs caesarean section delivery. A second step of inputting the patient data into a mobile delivery calculator to which an arithmetic expression of a predictive model for probability is applied and calculating a probability value for the possibility of a caesarean section of the patient, wherein the user terminal uses the measurement data to calculate the cervix per hour. A third step of generating a graph showing the band, and a fourth step of displaying, by the user terminal, a mobile delivery chart including the generated graph and the calculated probability value on the screen of the user terminal, mobile Methods for evaluating delivery progress are disclosed.

Description

Mobile delivery progress evaluation method using mobile birth calculator and terminal for the same}

The present invention relates to a mobile delivery progress evaluation method using a mobile delivery calculator and a terminal therefor, and more particularly, to a method for predicting the possibility of a caesarean section and providing an expression and an alarm.

Modern obstetric care has progressed in two directions since Friedman's labor analysis of the labor process in 1954. One is a field of predictive medicine that statistically analyzes childbirth data to identify risk factors and predicts high-risk mothers. It is a graph analysis in the preventive medicine dimension that is drawn and analyzed. This made a great contribution to reducing maternal mortality, one of the greatest innovations in medicine in the 20th century.

Recently, various risk factors and predictive models for high-risk delivery based on statistical analysis have been developed. Recently, such predictive models are being used in counseling for patients who calculate on a computer or web basis, such as a calculator for Vaginal Birth After Cesarean Delivery (VBAC), a calculator for induction of labor, and an emergency cesarean section. There is an emergency cesarean delivery calculator and a calculator of predicting cesarean section. However, these programmable risk calculators are used only at the level of calculators for counseling on the patient's caesarean section, etc., and are not integrated with the progress of childbirth, and thus have limitations in actual clinical practice.

Graphical analysis of the delivery process is representative of the WHO pogram including alert and action lines. In this regard, there is a US registered patent (US7207941) for a birth monitoring system that automates the paper-based WHO patogram, and an epartogram that is digitally converted and used for mobile, There is also Daksh--Intelligent-Labor-Monitoring-Tool, and there is also a prior patent (US Patent Publication US20080097908, Korean Patent Publication 10-2014-0105806) for automated analysis of abnormal childbirth disorders based on the warning and treatment lines of the WHO pogram. . The prior art based on such a WHO phatogram is only used for the purpose of the WHO phatogram, maternal mortality reduction (preventive medicine), and shows limitations that cannot be used in medical care in developed countries. The prior art simply converts the paper-based WHO pogram into electronic or mobile, but the concept of a certain treatment method has not changed.

The delivery process cannot be standardized or universalized due to the concept of "normality" in labor and delivery, and can vary depending on the patient's preference and the expert's subjective judgment. Therefore, there are many problems in determining whether the delivery process is normal or abnormal using the standardized WHO pogram. There can be unnecessary interference in clinical work, it can limit clinical work, reduce the autonomy of medical staff, and limit the flexibility to treat treatment of individual patients.

Maternal deaths have decreased as treatment for the delivery process has become highly medicalized, but normal childbirth is treated similarly to complicated births, and unnecessary interventions increase, and caesarean section delivery is rapidly increasing. In particular, the WHO pogram, which evaluates the delivery process based on the individual cervical dilatation curve, is mistaken for an abnormality if it is out of this standard, leading to an increase in medical treatment, induction of labor and caesarean section.

In addition, since normality and abnormality can only be determined retrospectively during the delivery process, medical disputes arise if the health of the mother and fetus deteriorates due to delivery without a caesarean section. This is especially true when the understanding of mothers and guardians is insufficient. Although the JAMA study recommends that the caesarean section rate not exceed 19% when considering maternal and newborn health, 1/3 of mothers in the United States do caesarean section, and in Korea, the caesarean section rate, which was 35-36%, increased to 42.3% in 2015. % is increasing.

Modern obstetric care is not satisfied with preventive care that simply reduces maternal mortality. Patients' demands for participatory, predictive, and personalized care must be met, the frequency of caesarean sections must be reduced, and the risk of medical disputes and accidents must be managed. Eventually, automated and digitized patograms as well as programmable risk calculators at the level of calculators that simply counsel patients cannot meet the needs of modern obstetrics and are neglected in medical care in developed countries.

Recently, official development projects (ODAs) in underdeveloped countries, UN Sustainable Development Goals (SDGs), and Korea's KOICA are also making efforts to introduce innovative technologies (mhealth), and the above-mentioned prior technologies are being used. However, even in underdeveloped countries or public development projects, it is not an era to be satisfied with prior technologies that are ignored in medical care in advanced countries. Now is the era of artificial intelligence treatment. Prior technology based on the WHO phatogram at the level of preventive medicine used in the UN Sustainable Development Goals (SDG) and Korea's KOICA must be replaced with an artificial intelligence-level official development project (SDG) to provide high-quality medical care for successful public development. You could call it a business. In addition, in the medical care of developed countries, there is a demand for caesarean section and medical disputes, mobile patient participatory care, predictive and individualized care. While satisfying this, a new method of objectively managing the delivery process is required.

In the present invention, it is intended to provide a mobile delivery progress evaluation method using a mobile delivery calculator.

In addition, in the present invention, it is intended to provide a mobile delivery calculator that provides a knowledge-based objective evaluation of the delivery progress of the mobile delivery chart and provides a decision-making means for managing delivery systematically.

An object of the present invention is not simply to develop a predictive model, but to provide a new approach to how a mobile delivery calculator applying the developed predictive model can be used clinically. It is aimed to overcome the limitations of the patient counseling level prediction calculator and the WHO patogram-based delivery chart of the prior art, which have been used independently in the past, so that the mobile delivery calculator of the present invention can actually be used clinically.

According to one aspect of the present invention, a first step of receiving, by a user terminal, patient data, which is data including at least one of personal information of the patient, clinical data of the patient, and measurement data according to the progress of delivery of the patient; A second step of, by the user terminal, inputting the patient data into a mobile delivery calculator to which an arithmetic expression of a prediction model for a possibility of a caesarean section is applied, and calculating a probability value for the possibility of a caesarean section of the patient; a third step of generating, by the user terminal, a graph showing cervical dilatation per hour using the measurement data; And a fourth step of displaying, by the user terminal, a mobile delivery chart including the generated graph and the calculated probability value on the screen of the user terminal, it is possible to provide a mobile delivery progress evaluation method. At this time, the received patient data includes the measurement data.

In this case, after the step of generating the probability value, the user terminal further includes displaying an alarm name corresponding to the probability value on a screen of the user terminal, and the alarm name is normal when the probability value is less than or equal to a predetermined value. (normal), and when the probability value exceeds the predetermined value, attention is set, and the alarm name is updated whenever the probability value changes and displayed on the screen of the user terminal.

At this time, the measurement data is, cervical dilatation, uterine contraction degree, contraction period, contraction intensity, fetal head position descent, fetal heart rate, fetal head position molding state, maternal respiration rate, maternal pulse rate, maternal respiration rate, maternal blood pressure, maternal body temperature , amnion status, amniotic fluid status, urine volume, and delivery treatment.

At this time, the user terminal is configured to repeat the process including the first to fourth steps, and when the user terminal has a first pre-determined cervical dilatation value among the received measurement data displaying additionally an alert line connected to the coordinate points at a predetermined first interval from the coordinate points at which the patient's cervical dilatation becomes the first predetermined dilatation value on the graph; and immediately after the lapse of a second predetermined time greater than the first time in parallel with the warning line, the user terminal draws an action line connecting the coordinate points of the first interval at every first time to the graph. It may further include the step of displaying additionally in .

At this time, when the user terminal determines that labor of the patient has started based on the received measurement data, the labor start line (labor start line) that is a vertical line passing through the coordinate point corresponding to the cervical dilatation at the time the labor started. ) is additionally displayed on the graph; and when the user terminal determines, based on the received measurement data, that the patient's cervical dilatation has reached a predetermined second dilation value, the predetermined second dilatation value at the point of time when the predetermined second dilatation value is reached. A step of additionally displaying a second stage of labor, which is a vertical line passing through the coordinates of the second maximum value, on the graph may be further included.

At this time, the predictive model is a statistical model learned by taking patient clinical data classified into caesarean section and vaginal delivery as input values and using a probability value for the possibility of caesarean section as an output value, including a logistic regression analysis prediction model, The predictive model may include a first predictive model capable of predicting the probability value throughout the delivery process of the patient, and a second predictive model capable of predicting the probability value after the patient enters the active stage of delivery.

Alternatively, the prediction model is a machine-learned caesarean section prediction model through an artificial intelligence deep learning algorithm, and the dependent variable of the prediction model may include caesarean section and vaginal delivery data.

According to one aspect of the present invention, a terminal including a receiving unit, a processing unit, and an outputting unit may be provided. The receiving unit is configured to receive patient data, which is at least one data of the patient's personal information, the patient's clinical data, and the patient's delivery progress measurement data, and the processing unit is configured to receive a predictive model for the possibility of caesarean section delivery. It is designed to calculate a probability value for the possibility of a cesarean delivery of the patient by inputting the patient data to, and to generate a graph showing cervical dilatation per hour using the measurement data, and the display unit is configured to generate the generated It may be configured to display a mobile delivery chart including a graph and the calculated probability value. At this time, the received patient data includes the measurement data.

At this time, the processing unit is configured to generate an alarm name corresponding to the probability value after generating the probability value, and the processing unit is configured to display the generated alarm name to the display unit, and the alarm name corresponds to the probability value. If it is less than a predetermined value, it is set to normal, and if the probability value exceeds the predetermined value, it is set to attention. The processing unit updates the alarm name whenever the probability value changes, and the display unit It may be intended to be expressed in

At this time, the measurement data is, cervical dilatation, uterine contraction degree, contraction period, contraction intensity, fetal head position descent, fetal heart rate, fetal head position molding state, maternal respiration rate, maternal pulse rate, maternal respiration rate, maternal blood pressure, maternal body temperature , amnion status, amniotic fluid status, urine volume, and delivery treatment.

In this case, the processing unit is configured to update the graph whenever the measurement data is received from the reception unit, and among the measurement data received from the reception unit, the processing unit has a first cervical dilatation value determined in advance. In this case, the patient's cervical dilatation is additionally displayed on the graph as an alert line connecting coordinate points at a predetermined first interval at a predetermined first time from the coordinate point at which the first predetermined value is obtained And, immediately after the elapse of a second predetermined time greater than the first time in parallel with the warning line, an action line connecting the coordinate points of the first interval for every first time is additionally displayed on the graph. may be made to do.

At this time, if the processing unit determines that labor of the patient has started based on the measurement data received from the receiving unit, the labor start line (Labor start) is additionally displayed on the graph, and when it is determined that the patient's cervical dilatation has reached a predetermined second dilatation value (eg, 10 cm), at the time of reaching the predetermined second dilatation value A second stage of labor, which is a vertical line passing through the coordinates of the predetermined second maximum value, may be additionally displayed on the graph.

Each execution step provided by the embodiments of the present invention described in this specification may be executed by an app installed and executed in the user terminal.

According to the present invention, it is possible to provide a mobile delivery progress evaluation method using a mobile delivery calculator.

According to the present invention, as the condition of the patient's cervical dilatation curve, the probability of caesarean section, and the change of the alarm can be checked visually at a glance on the mobile delivery chart, mobile delivery progress evaluation that can intuitively and systematically manage the delivery process method can be provided.

If the features of the present invention are applied, it can provide an objective criterion for ambiguous surgical decisions for mothers in the process of childbirth. After all, before deciding on caesarean section surgery, the medical staff first inputs the mother's main clinical indicators using the mobile delivery calculator to calculate the probability of needing surgery. Accordingly, it is possible to achieve the induction of medical optimization in parturient mothers. In particular, considering that there is a high need for medical optimization to prevent waste of medical expenses in medical institutions such as insurance authorities (Korea) or insurance companies (eg, USA), the mobile delivery calculator of the present invention provides actual clinical big data As a birth prediction calculator that can support decision-making based on .

Efforts have been made to reduce the rapid increase in caesarean sections in Korea, but it is difficult to evaluate caesarean sections objectively under the comprehensive fee system. The mobile delivery calculator developed according to the present invention can reduce the number of caesarean sections by inducing medical optimization, and can be an objective evaluation tool for delivery care by hospitals and doctors.

According to the present invention, mutual exchange of opinions is possible through the mobile delivery calculator app installed in the terminal, so that telemedicine using mobile can be provided.

According to the present invention, the mobile delivery calculator shows the probability of risk prediction, that is, the possibility of caesarean section, on the mobile delivery chart as a percentage, and the alarm based on the knowledge-based treatment algorithm is displayed together, so the patient and guardian can also monitor their delivery progress. At first glance, it can be intuitively grasped. In addition, the patient (or guardian) can exchange opinions with the medical staff while viewing the mobile delivery chart, provide detailed information to the patient (or guardian) through an application program on the user terminal, or provide detailed information through a phone call. You can also exchange opinions. After all, the mobile delivery calculator of the present invention enables two-way communication between the medical staff and the patient (or guardian), creating an environment in which the patient can participate in the treatment, and the delivery process can proceed with the consent of the treatment in the patient's full understanding. . Therefore, medical disputes due to lack of communication between medical staff and patients, non-reflection of patient preferences, negligence in explanation, and patient consent issues are reduced.

1 shows a screen of a user terminal according to an embodiment of the present invention.
Figure 2 is a flow chart showing a mobile childbirth chart display process performed in the user terminal according to an embodiment of the present invention.
3 is a diagram for explaining a process of calculating a probability value through a mobile delivery calculator button and changing an alarm name according to the probability value through a screen of a user terminal according to an embodiment of the present invention.
4 is a diagram for explaining the process after FIG. 3 through a screen of a user terminal.
Figure 5 shows a mobile delivery chart after the probability value is calculated according to an embodiment of the present invention.
6 is a flowchart illustrating a process of adding a warning line and a treatment line to a graph by a user terminal according to an embodiment of the present invention.
7 is a flowchart illustrating a process of adding a labor start line and a second baseline labor line to a graph by a user terminal according to an embodiment of the present invention.
8 illustrates a screen for manually inputting measurement data through a measurement data input button and a screen for generating a graph accordingly, according to an embodiment of the present invention.
9 shows a screen in which an alarm and a probability value are not shown and a screen in which an alarm and a probability value are shown for comparison with the prior art.
10 shows a conventional WHO phatogram according to an embodiment.
Figure 11 is a view for explaining the evaluation process of childbirth progress according to the first embodiment and the second embodiment of the present invention.
Figure 12 is a view for explaining the evaluation process of the progress of childbirth according to the third and fourth embodiments of the present invention.
13 shows a configuration diagram of a terminal according to an embodiment of the present invention.
14 is a table showing the characteristics of a case of caesarean section and vaginal delivery due to dystocia according to an embodiment of the present invention.
15A is a table showing a caesarean section model and an operating formula due to dystocia in the first predictive model according to an embodiment of the present invention, and FIG. The table shows the caesarean section model and calculation formula.
16 shows ROC curve analysis graphs for two caesarean section prediction models developed by logistic regression analysis according to an embodiment of the present invention.
17 tabulates the predicted results of mobile calculations for four virtual patients according to an embodiment of the present invention.
18 shows a basic calculator and calculation formula to which a first cesarean section prediction model developed according to an embodiment of the present invention is applied.
19 shows an additional delivery calculator and calculation formula to which a second cesarean section prediction model developed according to an embodiment of the present invention is applied.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be implemented in various other forms. Terms used in this specification are intended to aid understanding of the embodiments, and are not intended to limit the scope of the present invention. Also, the singular forms used herein include the plural forms unless the phrases clearly dictate the contrary.

1 shows a screen of a user terminal according to an embodiment of the present invention. 1 (a) shows a state in which the first screen of the app (mobile delivery application) installed on the user terminal is displayed on the screen (display unit) 13 of the user terminal 10 to evaluate the progress of mobile delivery, Figure 1 (b) shows the screen 13 after the mobile childbirth chart 30 is created in the app.

The first screen of the app may be a user login screen. After the user logs in and goes through a series of steps, a mobile childbirth chart 23 may be generated on the screen 13 of the user terminal 10 . At this time, the information that the user can check through the screen 13 is the logged-in user information 21, the measurement data input button 22, the mobile delivery chart button 23, the mobile delivery calculator button 24, and the alarm Information (alarm name) 25 may be included.

At this time, the user terminal 10 may be a fixed or portable dedicated equipment, a smartphone, a desktop computer, a tablet PC, a laptop, and a digital camera that can be used in a medical field, and is limited to a device on which the app can be installed. It doesn't work.

Also, the user terminal 10 may be a patient's terminal or a doctor's terminal. In the case of a patient's terminal, the user's user information 21 is displayed as shown in (b) of FIG. In this case, when the user terminal 10 is a doctor's terminal, a button (icon) for selecting a patient may be separately added to the screen 13 of the user terminal 10 .

At this time, the screen 13 of the user terminal 10 may be referred to as an expression unit below.

Figure 2 is a flow chart showing a mobile childbirth chart display process performed in the user terminal according to an embodiment of the present invention.

Hereinafter, it will be described with reference to FIGS. 1 and 2 together.

In step S10, the user terminal 10 may receive one or more of the patient's personal information, clinical data, and measurement data according to the delivery progress of the patient. At this time, the received data may be referred to as patient data.

The personal information and the clinical data may be data input and received at one time, and the measurement data may be data measured by a medical staff at regular intervals.

The clinical data can be divided into 1) clinical data input at the time of hospitalization of the patient, 2) clinical data calculated from measurement data, and 3) clinical data calculated from childbirth results.

Among these, as the clinical data entered at the time of hospitalization, the patient's age, race, obstetric history including delivery history, prenatal diagnosis history, socioeconomic status (smoking, drinking, drugs, education, marital history, workplace, etc.), past history, internal medicine Pregnancy disease, maternal weight (pre-pregnancy weight, weight at admission), maternal height, maternal body mass index (pre-pregnancy body mass index, maternal body mass index at admission), gestational age at admission, ultrasound findings (estimated fetal weight and Low birth weight, overweight infant, amniotic fluid volume, fetal health condition, etc.), blood pressure, urine test findings (proteinuria, etc.), blood test findings (liver function test, anemia, kidney function test), time of onset of labor, presence and time of rupture of amniotic fluid, meconium ), presence or absence of drug administration and time, etc., and high-risk mothers (pregnancy toxemia, gestational diabetes, intrauterine fetal growth failure, hypopelvic imbalance, infectious disease, medical disease, neurological disease, etc.) may be included.

Among them, the clinical data calculated from the measurement data include the elapsed time of childbirth (elapsed time of the 1st stage of labor, the elapsed time of the 2nd stage of labor, the elapsed time of the active phase, and the total delivery progress time), and the clinical data diagnosed by the measurement data ( toxemia of pregnancy, gestational diabetes, maternal infection, fetal asphyxia, hypohydramnios, polyhydramnios, intrauterine infection, medical disease, neurological disease, etc.).

Among these, the clinical data calculated as a result of the birth include the method of delivery (caesarean section delivery and normal vaginal delivery, etc.), causes of cesarean section delivery (dystocia, fetal distress, failure to induce delivery, premature delivery, sudden delivery, high-risk mothers, patient requests, etc.) ), date and time of delivery and elapsed time from hospitalization to delivery, postpartum neonatal health and complications (weight, height, Afka score, oxygen saturation, blood PH, neonatal hospitalization and other complications), postpartum maternal health and complications (postpartum hemorrhage, postpartum infection, postpartum hospitalization, postpartum anemia, medical illness, etc.).

At this time, the patient's personal information includes patient name, patient alias, patient ID, guardian name, guardian alias, guardian ID, hospital name, doctor (including ID), nurse (including ID), and patient registration date and time. can include At this time, in some cases, password information for each ID may be included.

At this time, the measurement data may be data input at regular intervals according to the progress of childbirth. The measurement data may be manually input from a medical staff through the measurement data input button 22, or may be automatically received and input from a medical device, sensor, or EMR server.

The measurement data can be entered per hour according to the progress of childbirth, cervical dilatation (cm), degree of uterine contraction (uterine contraction)-number of contractions per 10 minutes, contraction duration (second), contraction intensity (mild, moderate, strong) ), fetal head position descent (station), fetal heart rate, fetal head molding status (0-4), maternal respiration rate, maternal pulse rate, maternal respiration rate, maternal blood pressure (systolic/diastolic blood pressure), maternal body temperature, urine volume, amniotic membrane Status (retention of membranes, ruptured membranes), status of amniotic fluid (clean status, reduced amniotic fluid status, meconium status, blood status), delivery treatment (use of uterine contractions, artificial rupture of membranes, medical intervention), and additional risk comments. One or more of them may be included.

In addition, the measurement data may include additional variable values for calculating probability values. The separate variable values may be input through the mobile delivery calculator button 24 or may be input through the measurement data input button 22.

The separate variable values include, for example, parity, presence or absence of risk factors (meconium, mild blood pressure, mild gestational diabetes, hypoamniosis and hyperamniosis), induction of labor, gestational age, weeks ), maternal age (years), maternal height (cm), pre-gestational weight (kg), maternal weight at hospitalization (pre-delivery weight, kg), weight gain during pregnancy (pregnancy weight gain, kg), pre-gestational body mass index (BMI), pre-delivery BMI, cervical dilatation at admission (cm), at admission rupture of membranes at admission, oxytocin use, and estimated fetal weight (EFW). Estimated fetal weight was calculated using three parameters: biparietal diameter, fetal abdominal circumference, femur length, prolonged latent phase, and appropriateness in the active phase. Information on the presence or absence of adequate uterine contraction and the case of fetal descent of -1 or more (station ≥ -1) in the active phase may be included.

In step S20, the user terminal 10 inputs the patient data into a mobile delivery calculator to which an arithmetic formula of a predictive model for the possibility of a caesarean section is applied, and calculates a probability value for the possibility of a caesarean section of the patient. .

At this time, the predictive model is a statistical model learned by taking patient clinical data classified into caesarean section and vaginal delivery as input values and using a probability value for the possibility of caesarean section as an output value, and may include a logistic regression analysis prediction model. there is. Alternatively, the predictive model may be a cesarean delivery possibility prediction model machine-learned through an artificial intelligence deep learning algorithm. In this case, the dependent variable of the prediction model may include caesarean section and vaginal delivery data.

The predictive model may include a first predictive model and a second predictive model described later.

At this time, the screen displayed when the user presses the mobile delivery calculator button 24 may be provided with buttons (icons) for selecting before entering active delivery and after entering active delivery. Before entering the active period of labor, the probability value may be calculated with the first prediction model, and after entering the active period of labor, the probability value may be calculated with the second prediction model.

Alternatively, in the graph of the mobile delivery chart 30, the mobile delivery calculator is set to the second prediction model rather than the first prediction model from the time point when the individual cervical dilation becomes, for example, 4 cm (or from the time when the first delivery baseline is displayed). can be changed. Accordingly, after entering the active period of labor, a probability value may be automatically calculated through the second predictive model.

The first prediction model and the second prediction model will be described later in detail.

In step S30, the user terminal 10 may display the alarm name 25 corresponding to the probability value on the screen 13 of the user terminal 10. The alarm name 25 may be updated whenever the probability value changes and displayed on the screen 13 of the user terminal 10 .

At this time, the alarm name 25 is set to normal, which is the minimum risk level, when the probability value is less than or equal to a predetermined value (eg, 20%), and the probability value exceeds the predetermined value (eg, 20%). In one case, it may be set to attention including a severity risk level and a high risk level. In another embodiment, the alarm is, for example, normal when the probability value is less than 20%, low-level attention when the probability value is 20% to 30%, and attention when the probability value is 31% or more. meaning high-level attention).

At this time, in this embodiment, if the alarm name 25 is normal, it is displayed in green, and if the alarm name 25 is attention, it is displayed in red. can

In step S40, the user terminal 10 may generate a graph 32 showing cervical dilatation per hour using the measurement data.

In step (S50), the user terminal 10 can display the generated graph 32 and the mobile delivery chart 30 including the calculated probability value on the screen 13 of the user terminal 10. there is. The probability value may be displayed on the probability display unit 31 on the mobile childbirth chart (30).

3 and 4 are views for explaining a process of calculating a probability value through a mobile delivery calculator button and changing an alarm name according to the probability value through a screen of a user terminal according to an embodiment of the present invention.

3 (a) shows the screen 13 of the terminal 10 when the user of the terminal 10 presses the mobile delivery calculator button 24. In (a) of FIG. 3 , the user can select primiparous or multiparous.

3(b) shows a screen 13 of the user terminal 10 for selecting a range of fetal weight as a screen for inputting variable values for calculating probability values. In addition to the weight of the fetus, various calculation variable values may be input. Information on the variable values may be as shown in FIGS. 15A and 15B.

Figures 3 (a) and 3 (b) are screens for inputting various operation variable values for calculating probability values, and since the probability values are not yet calculated, the user is not yet able to use the mobile delivery chart button 23 in the app. may not be created.

Figure 4 (a) shows the screen 13 of the terminal 10 for setting whether or not to save when the input of variable values is completed. At this time, the values input by the user may be stored in the storage unit of the user terminal 10 .

Figure 4 (b) shows the screen 13 of the user terminal 10 where the calculation through the mobile delivery calculator is completed and the description of the probability value is expressed. At this time, the mobile delivery calculator is applied to the prediction model described above in FIG. 2, and the prediction model may be a prediction model learned through big data. At this time, the predictive model may be a predictive model capable of predicting the entire delivery process after hospitalization.

In the present invention, the prediction model may include two sub-prediction models. As described above, the first predictive model is a first predictive model capable of predicting the entire delivery process after the patient is hospitalized, and the second predictive model is a second predictive model that can be used only when the patient enters the active stage of delivery. The first prediction model and the second prediction model may be programmed in a calculator within the app, respectively.

As shown in (b) of FIG. 4, it can be seen that the possibility of caesarean section calculated by the mobile delivery calculator in this embodiment is 30%.

Before the probability value is calculated as shown in FIG. 4(b), the alarm name 25 may be expressed as normal as shown in FIGS. 3(a), 3(b), and 4(a). can However, when the probability value is calculated as shown in (b) of FIG. 4, the alarm name 25 may be changed according to the range of the probability value. In this embodiment, the probability value is calculated as 30%, and the alarm name 25 may be changed to attention.

In addition, when the probability value is calculated as shown in (b) of Figure 4, it can be seen that the mobile childbirth chart button 23 is formed. That is, the mobile delivery chart button 23 continues to exist on the screen 13 after the patient is hospitalized and the probability value is calculated once.

According to the knowledge-based schedule norms and treatment algorithms for the probability values calculated through the mobile delivery calculator, corresponding alarms can be sequentially expressed. As described above, after delivery is performed, the alarm name ( 25) is characterized by variations.

In the above-described embodiment, it has been described that the probability value must be calculated to generate the mobile childbirth chart button 23 and the mobile childbirth chart, but in another embodiment, the mobile childbirth chart button 23 can be basically expressed, and the user can When the chart button 23 is selected, an empty chart 30 may be displayed on the screen 13 .

Figure 5 shows a mobile delivery chart after the probability value is calculated according to an embodiment of the present invention.

Figure 5 (a) shows the mobile delivery chart 30 created for the first time on the screen 13, and Figure 5 (b) shows the mobile delivery displayed as a line graph of cervical dilatation every 30 minutes on the screen 13. Chart 30 is shown.

In (a) and (b) of FIG. 5 , the horizontal axis of the graph 32 represents time (eg, 30-minute intervals), and the vertical axis represents cervical dilatation (cm). At this time, in (a) of FIG. 5 , since coordinates are generated at intervals of, for example, 30 minutes, coordinates have not yet been generated.

Referring to Figure 5 (a) and Figure 5 (b), when the user selects the mobile childbirth chart button 23, the time of the 30-minute interval is listed right below the mobile menstrual chart button 23 it can be seen that there is The most recent time among the listed times may be highlighted in white, or may be marked with other markings to quickly catch the user's eye.

For example, according to (a) of FIG. 5, it can be seen that the patient (Ahee) is first hospitalized at 20:00 and the calculated probability value at 20:30 is 30%. For example, according to (b) of FIG. 5 , it can be seen that the value of the cervical dilatation of the patient Ahee started to change after 11:30 as time passed, and the measurement data was updated every 30 minutes. At this time, it can be seen that the probability value at 18:30 is 6%. If you press any one of the times listed in (b) of FIG. 5, you may see the mobile delivery chart 30 that was expressed at that time (ie, was updated) again.

Referring back to (a) of FIG. 5, there is no pain at 20:30 at the time of hospitalization of the patient (ie, mother), and the possibility of individual caesarean section (predicted probability) is 30% in the mobile delivery calculator. An alarm was displayed as Attention on the progress chart. In this case, the doctor may consider the health of the mother and the fetus, and proceed with natural childbirth based on her own medical judgment and the patient's will (desire and consent to natural childbirth).

Referring to (b) of FIG. 5 , probability values may be displayed on the cervical dilatation curve 32 and the cesarean section probability display unit 31 on the mobile delivery chart 30 while attempting natural childbirth. In addition, a corresponding alarm 25 is displayed on the screen 13 and is changed at regular intervals to show the user of the terminal 10 the process of childbirth. As shown in (a) of FIG. 5, at 20:30 at the time of hospitalization, it was confirmed that the alarm indication of attention was shown as the probability of cesarean section prediction (31) was calculated as 30%. However, as the delivery proceeded further as shown in FIG. 5 (b), according to the treatment algorithm sequentially calculated by the mobile delivery calculator, the probability of caesarean section was changed to 6% as shown in the probability display box 31, and the corresponding alarm (25 ) is changed to normal, showing that the possibility of vaginal delivery is high in the app of the user terminal 10 after all.

6 is a flowchart illustrating a process of adding a warning line and a treatment line to a graph by a user terminal according to an embodiment of the present invention.

Hereinafter, it will be described with reference to FIG. 5(b) and FIG. 6 together.

The user terminal 10 may update the probability value, the alarm name, and the graph by repeating the process including steps S10 to S40 described above with reference to FIG. 2 .

At this time, in step S110, the user terminal 10, if the patient's (ie, mother's) cervical dilatation is a predetermined first dilatation value (eg, 4 cm) among the received measurement data, the patient's cervical dilatation is A warning line (e.g., 1 cm) from the coordinate point (P1) at which the pole becomes the first predetermined maximum value (e.g., 4 cm) to a coordinate point at a predetermined first interval (e.g., 1 cm) every predetermined first time (e.g., 1 hour) ( alert line) may be additionally displayed on the graph.

And in step S120, the user terminal 10, immediately after the elapse of a fourth predetermined time (eg, 4 hours) greater than the first time (eg, 1 hour) parallel to the warning line, An action line connecting coordinate points of the first interval (eg, 1 cm) may be additionally displayed on the graph every hour (eg, 1 hour).

7 is a flowchart illustrating a process of adding a labor start line and a second baseline labor line to a graph by a user terminal according to an embodiment of the present invention.

In step S210, if the user terminal 10 determines that the patient's labor has started based on the received measurement data, it is a vertical line passing through the coordinate point corresponding to the cervical dilatation at the time the labor started. A labor start can be additionally plotted on the graph.

In step S220, when the user terminal 10 determines that the patient's cervical dilatation has reached a predetermined second dilatation value (eg, 10 cm) based on the received measurement data, the predetermined second dilatation value (eg, 10 cm). A second stage of labor, which is a vertical line passing through the coordinates of the predetermined second maximum value at the time of reaching the two maximum value, may be additionally displayed on the graph.

Referring back to (b) of FIG. 1, the start of labor pain drawn as a vertical line at the coordinate point P2 corresponding to the cervical dilatation (eg, 3 cm) at the time point (eg, 12 o'clock) when the labor pain started after the patient was hospitalized. The second stage of labor (37) expressed as a vertical line at the labor start line (35) and the coordinates (P3) corresponding to the point at which the cervical dilatation is 10 cm (eg, 20 o'clock) can be further displayed. there is. In addition, an active phase 36 drawn as a vertical line at the coordinate point P4 at which the cervical dilatation is, for example, 4 cm may be further displayed.

8 illustrates a screen for manually inputting measurement data through a measurement data input button and a screen for generating a graph accordingly, according to an embodiment of the present invention.

8(a) shows a screen for inputting measurement data through a measurement data input button, and FIG. 8(b) shows a graph generated up to 12:00, for example.

For example, if the mother is hospitalized, the possibility of caesarean section is calculated, and if there is a judgment of the medical staff and consent of the patient and guardian, natural delivery is attempted.

As shown in (a) of FIG. 8, when natural childbirth is attempted, measurement data can be input according to the lapse of time by pressing the measurement data input button 22 in the mobile birth application of the user terminal. Accordingly, as shown in (b) of FIG. 8, the individual cervical dilatation curve 32, which is a continuous line of measured data coordinates, is calculated in contrast to the mobile delivery chart 30 composed of coordinates of cervical dilatation per hour. And since the patient has entered the active phase of delivery (that is, because the first baseline of delivery has been expressed), it can be seen that a new probability calculation for the possibility of caesarean section delivery is required through the mobile delivery calculator.

Figure 8 (b) is, for example, at the current time of 12 o'clock, mobile birth application (mobile birth application) according to the second prediction model mobile birth calculator is not yet used, and the personal cervical dilatation curve is calculated only by inputting measurement data that shows the chart. At this time, the probability of caesarean section is not displayed and is in the default state, and the 'Normal' alarm is displayed as a result of the treatment algorithm in addition to the previously calculated probability of caesarean section.

9 shows a screen in which an alarm and a probability value are not shown and a screen in which an alarm and a probability value are shown for comparison with the prior art.

9(a) shows a screen on which probability values and alarm names are not displayed, and FIG. 9(b) shows a screen on which probability values and alarm names are displayed according to the present invention.

10 shows a conventional WHO phatogram according to an embodiment.

Hereinafter, it will be described with reference to FIGS. 9 and 10 together.

If it is assumed that there is no mobile delivery calculator, the mobile delivery chart will be the same as the screen of FIG. Childbirth charts such as (a) of FIG. 9 are merely charts such as the prior art in which the existing WHO patogram shown in FIG. 10 is simply digitized. That is, the delivery chart as shown in (a) of FIG. 9 is the same type of delivery as the epartogram or Daksh--Intelligent-Labor-Monitoring-Tool that provides services by converting the recently programmed patogram to mobile it's a chart

9(a) and 9(b) are individual cervical dilatation curves of the same mother. However, the mobile delivery chart 30 of the present invention in which the mobile delivery calculator is provided in the app of the user terminal 10 of the present invention is in the form of FIG. 8 (b), and the mobile delivery chart expressed when the mobile delivery calculator is executed ( 30) is the form of FIG. 9 (b). In (b) of FIG. 9, it can be seen that the probability of caesarean section (4%) and the corresponding 'Normal' alarm are displayed.

In this embodiment, the probability value can be calculated using the mobile delivery calculator to which the above-described second predictive model is applied when entering the active period of labor. As shown in (b) of FIG. 8, for example, when the cervical dilatation is 4 cm, the probability value can be newly calculated through the mobile delivery calculator button 24 by using the second prediction model instead of the first prediction model. The result may be the same as that of FIG. 9(b) as described above.

In (a) of FIG. 5, the patient had a 30% probability of caesarean section at the time of admission, and an attention alarm was generated, but as shown in (b) of FIG. 9, a mobile delivery calculator (based on the second predictive model) It can be seen at a glance that the calculated probability is lowered to 4% and the alarm has been changed to normal. As such, in the present invention, as the result value (i.e., probability value) of the mobile delivery calculator is displayed on the mobile delivery chart 30, an alarm is displayed according to the risk level of caesarean section by a knowledge-based certain norm and treatment algorithm, The process of childbirth is evaluated and managed through a series of changes. Therefore, the present invention has value as a completely different concept from that of FIG. 9 (a) as an example of a childbirth chart in which the existing WHO phatogram as shown in FIG. 10 is simply mobileized.

According to the conventional techniques, it is difficult to escape from the compulsory restrictions on medical autonomy, which is the limit of the existing WHO phatogram, and the number of caesarean section surgeries increases. On the other hand, according to the present invention, it is possible to objectively evaluate the delivery progress, and it is possible to prevent an indiscriminate cesarean section.

In the embodiment of the present invention, a case in which different predictive models (first predictive model and second predictive model) are used at the time of hospitalization and when entering the active phase is described. The first predictive model and the second predictive model were developed by the inventors of the present invention, and as described above, the first predictive model is a predictive model for all childbirth processes after hospitalization (pre-active labor and active labor), and all childbirth processes It is a model that can be predicted from, and the second predictive model is a predictive model that can be used only when the active stage delivery is confirmed as an active stage delivery prediction model.

Through the present invention, it is possible to predict the delivery process for the patient in various ways. In the above-described embodiment, it was described as a probability of whether or not a caesarean section was possible, but it can be seen that it may be calculated and expressed as a probability of predicting whether or not a vaginal delivery is possible. In another aspect, as a predictive model, a risk delivery (caesarean section or vaginal delivery) prediction model for dystocia, a risk delivery (caesarean section or vaginal delivery) prediction model for fetal distress, an induction delivery (induction) of labor) at-risk delivery (caesarean section or vaginal delivery) prediction model, preterm labor-risk delivery (caesarean section or vaginal delivery) prediction model, vaginal birth after CD (VBAC) progress It is also possible to evaluate the progress of labor through a risk delivery (caesarean section or vaginal delivery) prediction model and an emergency caesarean section delivery model.

Figure 11 is a view for explaining the evaluation process of childbirth progress according to the first embodiment and the second embodiment of the present invention.

Figure 11 (a) shows a screen when a situation to be evaluated as delayed delivery occurs, and Figure 11 (b) shows a screen when probability values are recalculated according to the first embodiment. (c) shows a screen when probability values are recalculated according to the second embodiment.

As shown in (a) of FIG. 11, when a situation to be evaluated as delayed delivery occurs, the risk level of caesarean section can be re-evaluated through the mobile delivery calculator button 24 in the mobile delivery application.

As shown in (b) of FIG. 11, when a probability of 36% for the possibility of caesarean section is obtained as a result of calculation, the probability value is provided to the mobile delivery chart 30, and the corresponding alarm can also be changed from 'normal' to 'attention'. . The cesarean section probability of 36% is significantly higher than the previously calculated value of 4% (Fig. 11 (a)) using a mobile delivery calculator. In the first embodiment, the treatment algorithm set in the mobile delivery application of the user terminal 10 classifies the caesarean section probability of 36% as a high risk level and is displayed as an 'Attention' alarm. This means that delayed delivery progress shown in the individual cervical dilatation curve 32 in the mobile delivery chart 30 means a real delivery disorder, so active medical intervention should be considered to overcome delivery failure rather than attempting natural delivery. Accordingly, the mobile childbirth application recommends the treatment according to the treatment algorithm, and the medical treatment is performed by the doctor's judgment with the consent of the patient and guardian.

In the second embodiment as shown in (c) of FIG. 11, as a result of re-evaluating the risk level of cesarean section through the mobile delivery calculator, a cesarean section probability of 18% was obtained, and as this was provided to the mobile delivery chart 30, ' You can see that the 'Normal' alarm is maintained. The caesarean section probability of 18% is an increase from the previous calculated value of 4% in FIG. 11 (a). However, based on the treatment algorithm set in the second embodiment of the present invention, the caesarean section probability of 18% is within the normal range (average range) and is classified as the minimum risk level. ' is indicated.

If (c) of FIG. 11 is judged with only the prior art delivery chart without a mobile delivery calculator, it can be evaluated as an obstacle to delivery progress (delayed delivery). However, in the present invention using the mobile delivery calculator, since the possibility of caesarean section was expressed as a 'Normal' alarm indicating the minimum level, it can be seen that the delivery obstacle of delayed delivery means a delivery obstacle that can be overcome. The patient can continue to attempt natural childbirth under the consent of the mother and guardian under the judgment of the doctor after receiving such an evaluation of the progress of childbirth.

Figure 12 is a view for explaining the evaluation process of the progress of childbirth according to the third and fourth embodiments of the present invention.

FIG. 12(a) shows a chart of a situation in which childbirth occurs through vaginal delivery, and FIG. 12(b) shows a chart of a situation in which childbirth occurs through a cesarean section.

As shown in (a) of FIG. 12, when the probability of caesarean section is continuously expressed as 18%, the mother can give birth only by vaginal delivery.

On the other hand, as shown in (b) of FIG. 12, if the probability of cesarean delivery continues to be 36% (36% means a high risk level), the alarm information 25 will continue as 'Attention'. This means that delayed delivery progress shown in the individual cervical dilatation curve 32 in the mobile delivery chart means a real delivery disorder, so active medical intervention should be considered to overcome delivery failure rather than attempting natural delivery. That is, FIG. 12(b) illustrates a situation in which a caesarean section was proposed according to a 17:30 medical treatment algorithm and the caesarean section was performed under the doctor's judgment and the consent of the mother and guardian.

As described above, consultation with the mother about the possibility of caesarean section or vaginal delivery when using a simple conventional delivery calculator, rather than a mobile delivery calculator combined with a mobile delivery chart including alarms, probability values, and graphs of the present invention /It stays at the level of advice, but it gets out of actual treatment. A mobile delivery calculator including an alarm, a probability value, and a graph as in the present invention is used as a decision-making means for objectively and systematically evaluating and managing the delivery progress of a mobile delivery chart. Specifically, a knowledge-based certain norm for the risk level of maternal risk delivery (cesarean section delivery or vaginal delivery) of the mobile delivery calculator is prepared, and the personal cervical dilatation curve of the mobile delivery chart is prepared using the mobile delivery calculator through a medical algorithm. It is possible to systematically manage childbirth while objectively evaluating the progress of childbirth and displaying relevant alarms.

13 shows a configuration diagram of a terminal according to an embodiment of the present invention.

The terminal 10 may include a receiving unit 11, a processing unit 12, an output unit 13, and a storage unit 14.

The receiver 11 may be a concept including an input unit and a communication unit. The receiving unit 11 may manually receive information including measurement data through an input means of a terminal. Alternatively, measurement data may be received from an external device through wired/wireless communication. In addition, the receiving unit 11 may receive clinical variable values of big data in the learning step of the predictive model.

The processing unit 12 may perform the above steps S10 to S40, S110 to S120, and S210 to S220.

The display unit 13 may display patient information, an alarm name, a probability value, and a chart on the app screen.

The storage unit 14 may store information received by the receiver 11 and information generated by the processing unit 12 .

The terminal 10 described above may be a medical staff terminal, a nurse terminal, a remote doctor terminal, a hospital terminal, and a patient and guardian terminal.

As shown in FIG. 1, when a user logs in to the app installed on the terminal 10, the range of data input and use of the mobile delivery calculator may vary depending on the given qualification (ie, patient, guardian, nurse, or doctor).

Hereinafter, an embodiment of a series of processes after the user installs the app (mobile childbirth application) will be described.

In step S300, the user terminal may receive patient personal information from the user.

In step S310, the user terminal may receive first measurement data according to the progress of delivery of the patient from the user, for example, at 30-minute intervals.

In step S320, the user terminal may receive second measurement data for calculating a probability value from the user through an input window of the mobile delivery calculator displayed by pressing the mobile delivery calculator button on the screen of the user terminal.

In step S330, the user terminal may calculate a probability value for the possibility of a caesarean section of the patient through the mobile delivery calculator to which an arithmetic formula of a predictive model for the possibility of a caesarean section is applied.

In step S340, the user terminal may generate a graph showing cervical dilatation per hour (eg, 30 minutes) using the input first measurement data.

In step (S350), the user terminal, the mobile childbirth chart including the generated graph and the calculated probability value can be displayed on the screen of the user terminal.

If you select the mobile delivery calculator button 24 described above in Figure 1, it is possible to run the mobile delivery calculator. At this time, if you enter the items (ie, input variables) required by the mobile delivery calculator, the probability value can be calculated through the formula of the above-described predictive model. That is, the mobile delivery calculator is a calculator to which the formula of the above-described predictive model is applied. The above-described predictive model is a predictive model learned with clinical variables of big data.

For example, the above-described predictive model may be a predictive model learned by an artificial intelligence deep learning (machine learning) algorithm or may be a statistical model. Specifically, it may be a logistic regression analysis prediction model among statistical models.

If the prediction model is a prediction model learned with an artificial intelligence deep learning algorithm, as an artificial intelligence deep learning algorithm, CNN (Convolution Neural Network) algorithm, RNN (Recurrent Neural Network) algorithm, DNN (Deep Neural Network) ) Artificial Neural Network, Support Vector Machine, Decision Tree, Random Tree, and Random Forest, including deep learning of algorithms A predictive model can be created using the like. Alternatively, various machine learning techniques such as stochastic learning of statistics such as a Bayesian Network or a Hidden Markov Model (HMM) may be used, but are not limited thereto.

Development of this predictive model of the present inventor is a model derived based on big data input through the mobile childbirth application of the user terminal (10).

In the present invention, it is described as a predictive model for the possibility of a risky delivery (caesarean section or vaginal delivery), but the predictive model is specifically a risky delivery (cesarean section or vaginal delivery) predictive model for dystocia, labor risk (caesarean section or vaginal delivery) prediction model, induction of labor (caesarean section or vaginal delivery) prediction model, risk delivery (caesarean section or vaginal delivery) for preterm labor vaginal delivery) prediction model, vaginal birth after CD (VBAC) risk delivery (caesarean section or vaginal delivery) prediction model, and emergency cesarean delivery prediction model.

If the predictive model is a logistic regression analysis predictive model, the mobile delivery calculator through the predictive model includes the step of calculating and predicting the dependent variable, the possibility of risk delivery (caesarean section or vaginal delivery) in %, but the following regression equation (formula 1) can be used to calculate the calculated value.

[Equation 1]

Probability of cesarean delivery (or vaginal delivery) =

Probability refers to probability, vaginal delivery (VD) refers to vaginal delivery, and CD (cesarean delivery) refers to cesarean delivery.

x _i is an independent variable selected using logistic regression analysis among at least one or more independent variables related to at-risk delivery (caesarean section or vaginal delivery) among the big data.

β ₀ is a weight (coefficient) for variables of a predictive model produced using logistic regression analysis among at least one or more independent variables related to risk delivery.

Using the value of β _i determined and stored for the independent variable x _i selected from the big data, the existence or nonexistence of the subject x _i or the value is substituted into the above formula to indicate the probability of a dependent variable (caesarean section or vaginal delivery) in a probability % Statistical probability can be calculated.

<Subjects and Methods for Development of Predictive Models - Patients and Evaluation>

The primary outcome was a caesarean section due to dystocia, and dystocia was defined as cervical dilatation less than 0.5 cm for 2-4 hours after the active phase. The target group for the invention included cases in which mothers of singleton fetuses of 36 weeks or longer without complications gave birth while experiencing active labor pain.

In order to collect the subject data, cases of caesarean section delivery without pain, fetal distress due to fetal distress, and caesarean section delivery without dystocia were excluded. In addition, cases of vaginal delivery within 2 hours of hospitalization, multiple pregnancy, non-pariety, and delivery under epidural anesthesia were excluded from the study data collection. In addition, considering maternal health conditions, serious complications of pregnancy requiring treatment (preeclampsia, gestational diabetes) and mothers with medical diseases requiring treatment (hypertensive patients, heart disease patients, etc.) were excluded. In addition, cases showing serious fetal health abnormalities such as fetal malformations or intrauterine death were excluded from the subject data collection.

For the purpose of the present invention, caesarean section delivery due to dystocia (vaginal delivery vs. caesarean section delivery) was set as a dependent variable, and 24 independent variables related to this delivery were selected through clinical review.

In the present invention, general variables related to childbirth (pre-active labor variables) and variables that appear only after entering the active labor period (active labor variables) can be distinguished.

Common variables associated with delivery are common variables that mothers have during hospitalization or delivery, and are readily available. These include parity, presence of risk factors (meconium, mild blood pressure, mild gestational diabetes, hypoamniosis and hyperhydramnios), induction of labor, gestational age (weeks), maternal age (maternal age). age, years), maternal height (cm), pre-gestational weight (kg), pre-delivery weight (kg), pregnancy weight gain (kg) ), pre-gestational body mass index (BMI), pre-delivery BMI, cervical dilatation at admission (cm), rupture of membrane at admission at admission), oxytocin use, and estimated fetal weight (EFW). Estimated fetal weight was estimated using Hadlock's formula using three parameters: fetal biparietal diameter, fetal abdominal circumference, and fetal femur length, which were classified into four categories ( <3.0, 3.0-3.49, 3.5-3.99, ≥4.0 kg) and used for analysis (categorized estimated fetal weight).

Three variables related to childbirth, which can be known only after entering the active phase, were established and used to calculate the predictive model (active labor variables). ) presence or absence, fetal descent in the active phase is more than -1 (station ≥ -1). Prolonged latent phase was defined as more than 20 hours in primiparous women and more than 14 hours in multiparous women, and adequate uterine contraction was defined as 3-60 seconds per 10 minutes lasting more than 40-60 seconds in a tocodynamic 2-hour test. It was defined as when there were 5 contractions. The degree of uterine descent was measured in the range of -5 to +5 by the relationship between the lowermost part of the fetal head and the mother's ischial spine.

<Statistical analysis>

The first step for generating the predictive model of the present invention is to establish candidate variables related to caesarean section delivery with dystocia among the 24 independent variables related to delivery selected through clinical consideration. To this end, the present inventors performed univariate analysis by classifying mothers who had vaginal delivery and mothers who had caesarean section due to dystocia. Student's t test and Pearson's Chi-square (χ 2) test were conducted, and a logistic regression model was developed.

In univariate analysis, logistic regression was performed using a stepwise backward method using a likelihood-ration test for variables related to caesarean section delivery, selected on the basis of P<0.10. analysis) was performed to select P<0.05 as a variable included in the final model, and through this, the present inventor develops two predictive models for caesarean section related to dystocia, one is the first predictive model using general variables related to delivery, (model A), and the other is a second prediction model (model B) by adding the variables that are confirmed by entering the active period of labor to the variables related to the labor.

The receiver-operating characteristic curve (AUROC) was used for the discriminatory accuracy of the two prediction models (models A and B), and the calibration, the degree to which the predicted value and the actual observed value match, was Hosmer- Lemeshow goodness-of-fit statistic was used. The adequacy of the model was evaluated through Akaike information criterion (AIC) and Bayesian information criterion (BIC).

More specifically, the discriminant ability evaluates how well the predictive model separates, for example, caesarean section delivery patients from vaginal delivery patients, and the calibration capability evaluates how well the predictive probability is related to the real outcome. It's a way to evaluate how close you are.

The model developed according to the present invention is internally tested using a bootstrapping procedure, and an optimal cut-off point (optimal cut-off) is considered in consideration of the sensitivity and specificity of the two models. point) was considered. The best cut-off point is the point where the sum of (1-sensitivity)2 and (1-specificity)2 is minimized and is closest to (0, 1) on the ROC curve, or the point where Youden index is maximum. Accuracy, Sensitivity, Specificity, Positive Predictive Value (PPV), and Negative Predictive Value (NPV) are obtained to evaluate validity.

The formula thus developed can be applied to a computer spreadsheet such as Microsoft Excel. The two calculators applied in this way are the basic intrapartum calculator developed using general variables related to delivery and the additional intrapartum CD calculator developed by adding variables identified after entering the active phase. The mobile delivery calculator of the present invention was completed through the above two calculators.

STATA version 13.1 (STATA Corp, Texas, USA) was used for the statistical analysis of the present invention, and G*Power version 3.1 was used for the statistical power of 1326 study data (post-hoc power of 83.7% with a two- sided α of 0.05)

<result>

14 is a table showing the characteristics of a case of caesarean section and vaginal delivery due to dystocia according to an embodiment of the present invention.

Each row of the table of FIG. 14 represents each variable, and each column represents vaginal delivery, cesarean section, and P value.

In FIG. 14 , SD means standard deviation, DM means diabetes mellitus, BMI means body mass index, and n means the number of people.

Of the total 1326 data subject to invention, 14.2% (189 cases) were delivered by cesarean section due to dystocia and 1137 were vaginally delivered.

A predictive probability model for the presence or absence of a caesarean section using the above-described clinical data may use logistic regression analysis. At this time, the regression equation may be the same as Equation 1 described above.

15A is a table showing a caesarean section model and an operating formula due to dystocia in the first predictive model according to an embodiment of the present invention, and FIG. The table shows the caesarean section model and calculation formula.

In FIG. 15A, 'model A' is the above-described first prediction model, which is a prediction model using general variables related to maternal delivery during hospitalization and delivery, and in FIG. 15B, 'model B' is the above-described second prediction model. , It is a predictive model created by adding variables that can only be confirmed after entering the active phase.

In the first prediction model (model A), general variables related to 8 births were selected, and in the second prediction model (model B), general variables related to 7 births and 3 variables that were confirmed after entering the active phase were selected. .

15A and 15B, each row of the table represents each variable, and each column represents weight (β), odds ratio, 98% CI, and P value.

15A and 15B, CI is the confidence interval, EFW is the estimated fetal weight, CD is the cesarean delivery, and UC is the uterine contraction. it means.

16 shows ROC curve analysis graphs for two caesarean section prediction models developed by logistic regression analysis according to an embodiment of the present invention.

The horizontal axis of the graph represents the specificity value, and the vertical axis of the graph represents the sensitivity value.

Graph 110 is a graph for a first prediction model (model A), graph 120 is a graph for a second prediction model (model B), and graph 130 represents a reference line.

Hereinafter, it will be described with reference to FIGS. 15A to 16 together.

The ROC curve (AUC) value of the first prediction model (model A) was 0.859 (95% confidence interval, 0.832-0.885) and showed adequate goodness-of-fit (p=0.970) in the Hosmer-Lemeshow test, log -Likelihood was -385.9, AIC was 793.8, and BIC was 850.9.

The ROC curve (AUC) value of the second predictive model (model B) was 0.887 (95% confidence interval, 0.863-0.910), and showed adequate goodness-of-fit (p=0.624) in the Hosmer-Lemeshow test, log The -likelihood value was 355.8, the AIC was 37.7, and the BIC was 805.1. When the goodness-of-fit of each model was compared, the second predictive model showed a significantly low AIC and BIC (p<0.001), and a high AUC (p = 0.0003) value, the second prediction The model showed superior performance not only in terms of calibration but also in terms of discriminant accuracy.

In the internal verification using the bootstrapping procedure, the minimal optimism value of the first cesarean delivery prediction model (model A) was 0.0070491 (95% confidence interval, -0.0339732-0.0437875), and the second cesarean delivery prediction model ( model B) was 0.0068976 (95% confidence interval, -0.0281747-0.0415336). After correcting Optimism, the AUC value of the first cesarean delivery prediction model (model A) was 0.851, and the AUC value of the second caesarean section delivery prediction model (model B) was 0.880, showing good internal verification.

In the present invention, the calculator using the first predictive model (model A) may be referred to as a basic intrapartum calculator, and the calculator using the second predictive model (model B) may be referred to as an additional intrapartum CD calculator. ) can be referred to as

At this time, the basic delivery calculator developed through the present invention is inferior to the additional delivery calculator in terms of accuracy, but has the advantage of being able to calculate the possibility of delivery by cesarean section at any time during delivery. The additional delivery calculator is a calculator developed by adding variables created by clinical measurement and judgment of medical staff after entering the active phase to labor-related variables. Therefore, although it has the disadvantage that it can be used only during the active period, it is more accurate than the basic calculator and has the advantage of complying with the treatment guidelines because it is a variable calculated by medical staff during the active period of labor.

17 tabulates the predicted results of mobile calculations for four virtual patients according to an embodiment of the present invention.

Each row in FIG. 17 represents a variable value, and each column represents each case of four people.

When calculated using the basic delivery calculator using the first prediction model (model A), the predicted probability of caesarean section delivery was 6.57%, 17.81%, 29.62%, and 1.63%, while the second prediction model (model B) The probability of caesarean section is 24.83% when calculated using an additional mobile delivery calculator with variables identified only after entering the active phase (Prolonged latent phase, Station ≥-1 in active phase, Adequate uterine contraction (yes or no) in active phase). , 6.24%, 10.84%, and 3.35%. As shown in FIG. 17, it can be seen that the predicted probability varies depending on the calculator. For example, in the case of Case 1 patient, the probability of caesarean delivery calculated by the basic calculator is 6.57%, but the probability calculated by the additional calculator is 24.83%, indicating that the probability value is different.

18 shows a basic calculator and calculation formula to which a first cesarean section prediction model developed according to an embodiment of the present invention is applied.

Figure 18 (a) shows the variable values of the basic calculator, Figure 18 (b) shows the calculation formula.

19 shows an additional delivery calculator and calculation formula to which a second cesarean section prediction model developed according to an embodiment of the present invention is applied.

Figure 19 (a) shows the variable values of the additional delivery calculator, Figure 19 (b) shows the calculation formula.

Hereinafter, FIG. 4, FIG. 8, FIG. 9, FIG. 18, and FIG. 19 will be described together.

The probability value calculation in FIG. 4 may be performed using a mobile delivery calculator equipped with an arithmetic formula (ie, FIG. 18 ) that can be calculated during the entire delivery process after the mother is hospitalized. In addition, the probability value calculation in FIGS. 8 and 9 may be performed using a mobile delivery calculator equipped with an arithmetic formula (ie, FIG. 19 ) that can be used only when the mother enters the active stage of childbirth.

The calculator programmed as shown in FIGS. 18 and 19 only calculates the predicted probability of caesarean section, and thus has limitations in clinical use. However, as shown in Figure 1, when using the mobile delivery calculator of the mobile application of the present invention, the probability of caesarean section (%) is confirmed through the mobile delivery chart along with the individual cervical dilatation curve, so the delivery of the mobile delivery chart is progressed through the mobile delivery calculator It helps you make intuitive judgments about the process.

In addition, since the risk level of risky delivery (caesarean section or natural delivery) is displayed on the mobile delivery chart as an alarm and fluctuates according to the knowledge-based schedule norms and treatment algorithm, the delivery process of the mobile delivery chart can be monitored through the mobile delivery calculator. You will be able to objectively and systematically manage the delivery process.

When the mobile delivery chart is fused with the mobile delivery calculator in the application of the user terminal and used for treatment, the existing WHO patogram, a simple mobile delivery chart as an example of the present invention, or the existing mobile epartogram However, while overcoming the limitations of Daksh--Intelligent-Labor-Monitoring-Tool, the concept of a calculator as a means of decision-making on childbirth progress can be transformed.

In addition, the knowledge-based alarm is provided to the user terminal where the application is installed, or it is delivered as a message, or the mobile delivery chart of the medical staff and the individual mother can be viewed together anywhere at the same time, and opinions can be exchanged or opinions can be expressed through direct mobile phone calls. Telemedicine becomes feasible. In the end, it has characteristics as a calculator as a decision-making support tool with clinical value, not a simple risk calculator.

Using the above-described embodiments of the present invention, those belonging to the technical field of the present invention will be able to easily implement various changes and modifications without departing from the essential characteristics of the present invention. The content of each claim of the claims may be combined with other claims without reference relationship within the scope understandable through this specification.

Claims (15)

A first step of receiving, by a user terminal, patient data, which is data including at least one of personal information of the patient, clinical data of the patient, and measurement data according to the progress of delivery of the patient;
A second step of, by the user terminal, inputting the patient data into a mobile delivery calculator to which an arithmetic expression of a prediction model for a possibility of a caesarean section is applied, and calculating a probability value for the possibility of a caesarean section of the patient;
a third step of generating, by the user terminal, a graph showing cervical dilatation per hour using the measurement data; and
A fourth step of displaying, by the user terminal, a mobile delivery chart including the generated graph and the calculated probability value on a screen of the user terminal;
Including,
Further comprising, by the user terminal, displaying an alarm name corresponding to the probability value on a screen of the user terminal after the step of calculating the probability value,
The alarm name is set to normal when the probability value is less than or equal to a predetermined value, and set to attention when the probability value exceeds the predetermined value,
The alarm name is updated whenever the probability value changes and displayed on the screen of the user terminal;
The predictive model is a predictive model learned by taking clinical data of patients classified as cesarean section and vaginal delivery as input values and using a probability value for the possibility of caesarean section as an output value. The probability value can be predicted in the entire delivery process of the patient. A first predictive model with and a second predictive model capable of predicting the probability value after the patient enters active labor,
The user terminal is configured to calculate the probability value by using the first prediction model before the patient enters labor in the active phase and by using the second prediction model after the patient enters labor in the active phase,
The first predictive model uses general variables related to childbirth, and the second predictive model uses variables that are confirmed by entering the general variables and active childbirth.
Mobile labor progress evaluation method. According to claim 1,
A mobile delivery chart button and a mobile delivery calculator button are displayed on the screen of the user terminal,
When the mobile delivery chart button is selected, the mobile delivery chart is displayed on the screen of the user terminal,
When the mobile delivery calculator button is selected, the screen of the user terminal displays a button for selecting before entering active delivery or after entering active delivery,
When the button for selecting the active period before entry into labor is selected, the probability value is calculated with the first predictive model, and when the button for selecting the active period before entry into labor is selected, the probability value is calculated with the second predictive model,
Mobile labor progress evaluation method. The method of claim 1, wherein the measurement data is, cervical dilatation, uterine contraction degree, contraction period, contraction strength, fetal head position descent, fetal heart rate, fetal head molding state, maternal respiration rate, maternal pulse rate, maternal respiration rate, maternal respiration rate Blood pressure, maternal body temperature, amniotic membrane status, amniotic fluid status, urine volume, and a mobile delivery progress evaluation method, including one or more of delivery treatment. According to claim 1,
The user terminal is configured to repeat the process including the first to fourth steps,
Among the received measurement data, if the user terminal has the patient's cervical dilatation equal to the first predetermined dilatation value, the patient's cervical dilatation is the first predetermined dilatation value at the coordinate point at every predetermined first time. additionally displaying an alert line connected to coordinate points at a predetermined first interval on the graph; and
The user terminal draws an action line connected to the coordinate points of the first interval at every first time on the graph immediately after the elapse of a fourth predetermined time greater than the first time in parallel with the warning line. further displaying;
Including more,
Mobile labor progress evaluation method. According to claim 1,
When the user terminal determines that labor of the patient has started based on the received measurement data, the labor start line, which is a vertical line passing through the coordinate point corresponding to the cervical dilatation at the time when labor started, is drawn. further displaying on the graph; and
When the user terminal determines, based on the received measurement data, that the patient's cervical dilatation has reached a predetermined second dilatation value, the predetermined second dilatation value at the time point when the predetermined second dilatation value is reached. additionally displaying a second stage of labor, which is a vertical line passing through the coordinates of two major values, on the graph;
Including more,
Mobile labor progress evaluation method. The method of claim 1, wherein the patient's personal information and measurement data according to the progress of delivery of the patient are received by the user of the user terminal through a user interface of the user terminal, or from a device different from the user terminal. A method for evaluating mobile delivery progress, which is automatically received through the network. delete delete delete delete A terminal including a receiving unit, a processing unit, and an output unit,
The receiving unit is configured to receive patient data, which is data including at least one of the patient's personal information, the patient's clinical data, and the patient's delivery progress measurement data,
The processing unit,
By entering the patient data into a prediction model for the possibility of caesarean section, the probability value for the possibility of caesarean section of the patient is calculated, and a graph showing cervical dilatation per hour is generated using the measurement data, ,
The display unit is configured to display a mobile delivery chart including the generated graph and the calculated probability value,
The processing unit is configured to generate an alarm name corresponding to the probability value after calculating the probability value;
The processing unit is configured to display the generated alarm name to the displaying unit,
The alarm name is set to normal when the probability value is less than or equal to a predetermined value, and set to attention when the probability value exceeds the predetermined value,
The processing unit updates the alarm name whenever the probability value changes and displays the alarm name to the displaying unit;
The predictive model is a predictive model learned by taking clinical data of patients classified as cesarean section and vaginal delivery as input values and using a probability value for the possibility of caesarean section as an output value. The probability value can be predicted in the entire delivery process of the patient. A first predictive model with and a second predictive model capable of predicting the probability value after the patient enters active labor,
The processing unit is configured to calculate the probability value by using the first prediction model before the patient enters labor in the active phase and by using the second prediction model after the patient enters labor in the active phase,
The first predictive model uses general variables related to childbirth, and the second predictive model uses variables that are confirmed by entering the general variables and active childbirth.
terminal. According to claim 11,
A mobile delivery chart button and a mobile delivery calculator button are displayed in the display unit,
When the mobile delivery chart button is selected, the mobile delivery chart is displayed on the screen of the display unit,
When the mobile delivery calculator button is selected, the display unit is configured to display a button for selecting before entering active delivery or after entering active delivery,
When the button for selecting the active period before entry into labor is selected, the probability value is calculated with the first predictive model, and when the button for selecting the active period before entry into labor is selected, the probability value is calculated with the second predictive model,
terminal. The method of claim 11, wherein the measurement data, cervical dilatation, uterine contraction degree, contraction period, contraction strength, fetal head position depression, fetal heart rate, fetal head position molding, maternal respiration rate, maternal pulse rate, maternal respiration rate, maternal respiration rate A terminal comprising one or more of blood pressure, maternal body temperature, amnion status, amniotic fluid status, urine volume, and delivery treatment. According to claim 11,
The processing unit updates the graph whenever the measurement data is received from the receiving unit,
The processing unit,
Among the measurement data received from the receiving unit, when the patient's cervical dilatation is the first predetermined dilatation value, the patient's cervical dilatation is the first predetermined dilatation value. An alert line connected to coordinate points at 1 interval is additionally displayed on the graph,
In parallel with the warning line, immediately after the elapse of a predetermined fourth time greater than the first time, an action line following the coordinate points of the first interval for every first time is additionally displayed on the graph there is,
terminal. According to claim 11,
The processing unit,
Based on the measurement data received from the receiving unit, when it is determined that the patient's labor has started, a labor start line, which is a vertical line passing through the coordinate points corresponding to the cervical dilatation at the time the labor started, is displayed on the graph. are additionally indicated,
When it is determined that the patient's cervical dilatation has reached the second predetermined dilation value (eg, 10 cm), a vertical line passing through the coordinates of the second predetermined dilatation value at the time point when the predetermined second dilatation value is reached The second stage of labor is further displayed on the graph,
terminal.

Images