JP6813195B2 - Wearable devices for pregnant women, information processing systems, personal digital assistants, uterine contraction measurement methods and their programs - Google Patents

Description

The present invention relates to a wearable device for pregnant women, an information processing system, a personal digital assistant, a method for measuring uterine contraction, and a program thereof.

In the above technical fields, Patent Documents 1 and 2 disclose a technique for detecting uterine activity using a plurality of skin electrodes and generating a fetal heartbeat labor chart (hereinafter, CTG: Cardiotocograph).

Japanese Unexamined Patent Publication No. 2016-73645 Japanese Unexamined Patent Publication No. 2016-537068

However, with the technique described in the above document, it is difficult to accurately attach the sensor, and it is difficult for a pregnant woman without specialized knowledge to check the condition of the foetation at home.

An object of the present invention is to provide a technique for solving the above-mentioned problems.

In order to achieve the above object, the device according to the present invention
A belly-wrapped base material that wraps the abdomen of a pregnant woman,
A plurality of deformation sensors attached to the base material and for detecting the deformation of the base material,
A measuring unit that measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors,
With
The base material has elastic string-like members arranged in a grid pattern.
The deformation sensor is a wearable device for pregnant women that detects the degree of expansion and contraction of the elastic string-like member.

In order to achieve the above object, other devices according to the present invention may be used.
A belly-wrapped base material that wraps the abdomen of a pregnant woman,
A plurality of deformation sensors attached to the base material and for detecting the deformation of the base material,
A measuring unit that measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors,
With
The substrate has a plurality of concentrically arranged elastic cord-like members having a center on the front side of the abdomen.
The deformation sensor is a wearable device for pregnant women that detects the degree of expansion and contraction of the elastic string-like member.

According to the present invention, it can be easily worn and the degree of contraction of the uterus can be accurately measured without any specialized knowledge.

It is a figure which shows the structure of the wearable device for a pregnant woman which concerns on 1st Embodiment of this invention. It is a block diagram which shows the structure of the wearable device for a pregnant woman which concerns on 2nd Embodiment of this invention. It is a figure explaining the processing of the wearable device for a pregnant woman which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the structure of the information processing system which concerns on 3rd Embodiment of this invention. It is a block diagram which shows the structure of the wearable device for a pregnant woman which concerns on 4th Embodiment of this invention. It is a figure which shows the structure of the wearable device for a pregnant woman which concerns on 4th Embodiment of this invention.

Hereinafter, embodiments of the present invention will be described in detail exemplarily with reference to the drawings. However, the components described in the following embodiments are merely examples, and the technical scope of the present invention is not limited to them.

[First Embodiment]
The wearable device 100 for pregnant women as the first embodiment of the present invention will be described with reference to FIG. The wearable device 100 for pregnant women is a device for easily recording a uterine contraction pattern and predicting the timing of delivery.

As shown in FIG. 1, the wearable device 100 for pregnant women includes a belly-wrapped base material 101, a plurality of deformation sensors 102, and a measuring unit 103.

The base material 101 has a belly-wrap shape that wraps around the abdomen of the pregnant woman 110. The deformation sensor 102 is attached to the base material 101 and detects the deformation of the base material 101, as shown by black dots in FIG. The measuring unit 103 measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors 102.

The pregnant woman 110 does not have to worry that the degree of contraction of the uterus cannot be measured due to the displacement of the sensor 102. Moreover, if the uterine contraction pattern can be monitored by such a wearable device, the degree of uterine contraction can be recognized even at home. As a result, it becomes possible to predict the timing of delivery and detect fetal abnormalities at an early stage.

[Second Embodiment]
Next, the wearable device for pregnant women according to the second embodiment of the present invention will be described with reference to FIGS. 2 and 2. FIG. 2 is a diagram for explaining the configuration of the wearable device 200 for pregnant women according to the present embodiment.

As shown in FIG. 2, the pregnant woman wearable device 200 includes a belly-wrapped base material 201, a plurality of deformation sensors 202, a control device 203, and a microphone 204. The control device 203 includes a measurement unit 231, a delivery time determination unit 232, an abnormality determination unit 233, a notification unit 234, a communication unit 235, and an audio signal processing unit 236.

The base material 201 has a belly-wrap shape that wraps around the abdomen of the pregnant woman 210. The deformation sensor 221 is attached to the base material 201 and detects the deformation of the base material 201 as shown by the black dots. The measuring unit 231 measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors 221.

The base material 201 has elastic string-like members 211 arranged in a grid pattern. The deformation sensor 221 is, for example, a string-shaped piezoelectric element, and detects the local elasticity (for example, at the position indicated by a black dot in the figure) of the string-shaped member. This makes it possible to accurately detect both the overall degree of contraction of the uterus and the degree of local contraction. Even in the case of a pregnant woman whose uterus contracts only locally, such as a pregnancy with myoma or a pregnancy after a previous cesarean section, the contraction of the uterus can be detected accurately. Further, conventionally, in order to accurately detect the contraction of the uterus, a medical worker adjusts the deviation of the sensor position at any time, but according to the present embodiment, in order to detect the contraction of the uterus at a plurality of positions. , It is not necessary to adjust such a deviation, and the burden on the medical staff can be greatly reduced.

The pregnant woman wearable device 200 is attached to the base material 201 and further has a plurality of microphones 204 for detecting voice, and the measuring unit 231 further has a fetal in the abdomen of the pregnant woman 210 based on the output signal of the microphone 204. Measure your heart rate. The plurality of microphones 204 function as a microphone array to accurately capture the fetal heart sounds, and use blind sound source separation using independent component analysis, noise suppression technology, etc. to make noises other than the fetal heart sounds (digestive organs, etc.). It is possible to remove the sound of the mother and the heart sound of the mother. Furthermore, the phase difference of the heart sounds captured by multiple microphones makes it possible to roughly grasp the position of the fetal heart. In addition, if a microphone array is used, it is possible to accurately separate and capture a plurality of fetal heart sounds even in the case of multiple births such as twins and triplets. In the conventional method of detecting fetal heart sounds with ultrasonic waves, accurate heartbeat cannot be measured unless the ultrasonic probe is accurately pointed at the fetal heart. In the past, it often happened that the probe was misaligned and the foetation's heart sounds could not be taken, and it was indistinguishable from the case where the foetation itself was weak and the heartbeat was slow, so the burden on the medical staff was very heavy. On the other hand, if the wearable device 200 as in the present embodiment is used, the heartbeat of the foetation can be accurately measured regardless of the posture of the pregnant woman, so that the burden on the medical staff is greatly reduced.

The measuring unit 231 measures the tendency of the maximum change in the abdominal circumference of the pregnant woman 210 based on the output signals of the plurality of deformation sensors 202. Specifically, the measuring unit 231 receives the position information and the measured value of each deformation sensor 202, and based on the information, obtains the shape change of the abdominal plane of the pregnant woman by using the least squares method, and abdomen. The maximum value of the contraction of the uterus is calculated from the maximum displacement of. For example, the measuring unit 231 may generate a 3D graph as shown in FIG. That is, the measured value by the deformation sensor 202 or the change in the measured value may be arranged at each sensor position. The change in the measured value at the place where the change in the measured value is the most accurately represents the uterine contraction curve of the CTG.

For example, a pregnant woman's wearable device 200 can be used for home follow-up of a pregnant woman diagnosed with the possibility of imminent preterm birth. There is no particular problem with weak contractions of about 2 times per hour that occur from about 18 weeks of gestation, but if contractions of about 5 to 6 times per hour are observed, it is desirable to visit a hospital.
On the other hand, uterine contraction due to labor pain is a strong contraction that occurs 1 to 2 days before birth, and has a large fluctuation compared to the movement of the foetation, etc. From the displacements captured by each sensor, the pattern of uterine contraction is calculated in detail as shown in FIG. 3, and then the change in maximum abdominal circumference is measured.
The microphone 204 is attached to the base material 201 and detects the sound in the abdomen. The measuring unit 231 further measures the heartbeat of the foetation in the abdomen of the pregnant woman based on the output signal of the microphone 204. The piezoelectric element as the deformation sensor 221 may capture a minute vibration in the abdomen and convert it into a fetal heartbeat, in which case the microphone 204 becomes unnecessary.

The delivery time determination unit 232 predicts the delivery time based on the time-dependent change in the degree of contraction of the uterus obtained from the measurement unit 231. Here, the time-dependent change in the degree of contraction of the uterus includes not only waveform information but also at least one of the maximum value of the degree of contraction, the transition of the maximum value, and the duration of contraction.

Further, the delivery time determination unit 232 may predict the delivery time by exchanging with an external server. The external server may predict the delivery time by machine learning by comparing it with the past delivery time information by using the morphological characteristics of the uterine contraction and the fetal heartbeat waveform and the pattern of the change over time.

In this case, the external server predicts the delivery time using AI-related technology (machine learning, etc.). When both uterine contractions and fetal heartbeats can be measured with a wearable device, machine learning is used to predict the fetal condition in addition to predicting labor time.

In machine learning to calculate the expected delivery time from uterine contractions, the training set is the time-to-delivery time and time-series waveform. The AI system installed in the external server performs machine learning with this training set, inputs waveform information, and guides the estimated time to delivery.

Specifically, the training set uses information such as the time-series uterine contraction waveform itself or the contraction-contraction interval, the peak intensity of the waveform, and the contraction duration extracted from the uterine contraction waveform. When fetal heart rate information can be obtained with a wearable device, a combination of two time-series waveforms (uterine contraction waveform and fetal heart rate waveform) is used.

The external server builds a prediction algorithm according to the following procedure, centering on machine learning technology including deep learning.
(A) Signal pre-processing: Basic pre-processing such as missing value processing, noise removal, and outlier removal is performed on the measured waveform.
(B) Model construction: An appropriate model is constructed according to the waveform and the characteristics of the prediction target. Specifically, existing models such as recurrent neural networks and one-dimensional convolutional neural networks, and probabilistic models that model the characteristics of waveforms and prediction targets are used in combination.
(C) Learning: Train the model using the training set.
For example, in the case of prediction of Apgar score, the input waveform and the corresponding Apgar score are given to the model together, and the weighting coefficient of the model is updated so that the correct Apgar score corresponding to the input can be output. Further, for example, in the case of predicting the delivery time, the input waveform and the corresponding time until delivery are given to the model, and the weighting coefficient of the model is updated so that the correct delivery time corresponding to the input can be output.
(D) Prediction: By inputting new data (verification data) to the trained model, the predicted value (Apgar score, etc., delivery time) for it is obtained as an output.

The delivery time determination unit 232 may generate a CTG and present it to the pregnant woman 210 via a smartphone 220 or the like. From the morphological characteristics of CTG and the pattern of changes over time, the maternal and fetal conditions during labor (whether hypoxic or not) can be evaluated. In addition, CTG data may be transmitted and stored in a database for each pregnant woman prepared by the hospital so that the medical staff can always monitor the data.

The notification unit 234 notifies the pregnant woman 210 of the delivery time predicted by the delivery time determination unit 232. For example, a notification to a pregnant woman 210 such as "I will be born within half a day", "I have labor pains", "I will be born within 6 hours", "I will be born within 3 hours", "I will be born within 1 hour" It can be done by voice, image or text. Such information may be sent from the communication unit 235 to the smartphone 220 owned by the pregnant woman 210, and may be notified to the pregnant woman 210 through the smartphone 220.

The delivery time determination unit 232 is further based on at least one of age, pregnancy history (whether or not it is a multiparous woman), underlying disease, BMI, and diabetes, which are input as attributes of the pregnant woman via the application of the smartphone 220 or the like. , The predicted delivery time may be adjusted.

In the delivery time determination unit 232, the change over time in the degree of contraction of the uterus measured by the measurement unit 231 using the deformation sensor 202 and the change over time in the fetal heartbeat measured by the measurement unit 231 based on the output signal of the microphone 204. The delivery time may be predicted based on. For example, the delivery time determination unit 232 may predict the time required for delivery based on the time difference between the timing when the degree of contraction reaches the maximum value and the timing when the fetal heartbeat decreases. The frequency of uterine contractions increases several days before delivery, and when the degree of uterine contractions exceeding a predetermined intensity occurs at 10-minute intervals, it is defined as the onset of labor and it is judged that delivery has started. In addition, a pregnant woman who is suffering from labor may be notified of the fetal condition based on the timing of labor and the change in fetal heartbeat. For example, if the heartbeat is maintained even if the uterus contracts, or if the heartbeat drops at the same timing as the uterine contraction but returns immediately, it can be judged that there is no problem with the foetation. On the other hand, if the heartbeat drops later than the labor pain and it takes time to return, it can be judged that the reserve for change is low, that is, the foetation is not healthy and the patient should go to the hospital as soon as possible.

The abnormality determination unit 233 predicts the appearance of an abnormal waveform based on the time course of the fetal heartbeat measured by the measurement unit 231 based on the output signal of the microphone 204. In addition, the abnormality determination unit 233 may detect imminent preterm birth based on the change over time in the degree of contraction of the uterus. The notification unit 234 issues a warning notification when the abnormality determination unit 233 predicts the appearance of an abnormal waveform. The notification unit 234 may notify the imminent premature birth detected by the abnormality determination unit 233.

The audio signal processing unit 236 removes noise from the sound detected by the microphone array 204, generates a clear fetal heart sound signal, and outputs it to the measuring unit 231. It is possible to send the fetal heart sound data to the smartphone 220 and let the pregnant woman hear it. Further, the position of the fetal heart (fetal posture) detected from the voice processing by the microphone array may be notified to the pregnant woman via the smartphone 220.

The deformation sensor 202 may be an optical fiber type strain gauge. Further, the measuring unit 231 may measure the degree of contraction of the uterus by using the impedance method.

As described above, according to the present embodiment, since the degree of uterine contraction is measured by a belly-wrapping wearable device, the pregnant woman 210 can easily wear the device. Further, since a plurality of sensors are arranged in such a wearable device, there is no concern that the sensor position shifts and the measurement cannot be performed, and the uterine contraction pattern can be accurately recorded in a wide range of the wearable device.

The uterine contraction waveform and fetal heart rate can be automatically memorized in the first few days before delivery, and the expected delivery time and the appearance of abnormal waveforms can be predicted and the condition of the mother and fetal during delivery can be evaluated. As a result, safer delivery can be realized, and remote perinatal medical care can be provided by notifying accurate maternal and fetal conditions through smartphones and the like.

It should be noted that several so-called string-shaped piezoelectric elements in which a piezoelectric body using polyvinylidene fluoride or polylactic acid fiber is formed into a string shape may be woven into the fiber as the base material 201 in a grid pattern (in a grid pattern or a contour line shape). .. Even if the position of the belly band shifts a little, the maximum change in the abdominal circumference can be measured as a trend. Cut the string-shaped piezoelectric element into, for example, about 5 cm, install it in a grid pattern or contour line shape vertically and horizontally, and if you can capture the length change of each part of the fabric, the real-time tension change of the belly band of the stretch material Is captured, and the exact degree, frequency, and interval of labor pains are captured.

[Third Embodiment]
Next, the information processing system 400 according to the third embodiment of the present invention will be described with reference to FIG. FIG. 4 is a block diagram for explaining the configuration of the information processing system 400 according to the present embodiment. The information processing system 400 according to the present embodiment is different from the second embodiment in that it has a delivery time determination unit 432, an abnormality determination unit 433, and a notification unit 434 in the smartphone 420 as a mobile information terminal. Since other configurations and operations are the same as those in the second embodiment, the same configurations and operations are designated by the same reference numerals and detailed description thereof will be omitted.

The receiving unit 431 receives the degree of contraction of the uterus from the control device 403 of the wearable device for pregnant women. The delivery time determination unit 432 predicts the delivery time based on the change over time in the degree of contraction of the uterus. The abnormality determination unit 433 determines the abnormality of the foetation based on the fetal heartbeat. The notification unit 434 notifies the determined delivery time and fetal abnormality.

According to the present embodiment, the delivery time can be notified to the pregnant woman via the smartphone 420.

[Fourth Embodiment]
Next, the fourth embodiment of the present invention will be described with reference to FIG. FIG. 5 is a diagram for explaining the configuration of the wearable device 500 for pregnant women according to the present embodiment. The wearable device 500 for pregnant women according to the present embodiment is different from the second embodiment in that the deformation sensor 502 is arranged on the string-shaped member 511 attached in a contour line. Since other configurations and operations are the same as those in the second embodiment, the same configurations and operations are designated by the same reference numerals and detailed description thereof will be omitted.

The string-shaped members 511 are arranged in a plurality of concentric circles having a center on the front side of the abdomen. The deformation sensor 502 detects the degree of expansion and contraction of the string-shaped member 511.

Since the sensors are arranged in contour lines, they can follow various pregnant women's abdominal shapes and do not give a feeling of oppression to the abdomen. Since the deformation sensor 502 is arranged in a contour line, it is not easily affected by the posture of the pregnant woman (standing, sleeping, sitting). Since the sensors are arranged in contour lines, the heartbeat can be accurately detected regardless of the posture of the foetation. As shown in FIG. 6, the wearable device 600 may be provided with a string-shaped member 611 attached in a contour line and a string-shaped member 612 attached radially as deformation sensors. By detecting the degree of expansion and contraction of the string-shaped member indicated by the black dots, it is possible to obtain data on local uterine expansion and contraction at a plurality of points.

[Other Embodiments]
Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the structure and details of the present invention. Also included in the scope of the present invention are systems or devices in any combination of the different features contained in each embodiment.

Further, the present invention may be applied to a system composed of a plurality of devices, or may be applied to a single device. Furthermore, the present invention is also applicable when the information processing program that realizes the functions of the embodiment is supplied directly or remotely to the system or device. Therefore, in order to realize the functions of the present invention on a computer, a program installed on the computer, a medium containing the program, and a WWW (World Wide Web) server for downloading the program are also included in the scope of the present invention. .. In particular, at least a non-transitory computer readable medium containing a program that causes a computer to execute the processing steps included in the above-described embodiment is included in the scope of the present invention.

Claims (4)

A belly-wrapped base material that wraps the abdomen of a pregnant woman,
A plurality of deformation sensors attached to the base material and for detecting the deformation of the base material,
A measuring unit that measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors,
Equipped with a,
The base material has elastic string-like members arranged in a grid pattern.
The deformation sensor is a wearable device for pregnant women that detects the elasticity of the elastic string-like member . The wearable device for pregnant women according to claim 1 , wherein the deformation sensor detects local elasticity at a plurality of points on the elastic cord-like member. A belly-wrapped base material that wraps the abdomen of a pregnant woman,
A plurality of deformation sensors attached to the base material and for detecting the deformation of the base material,
A measuring unit that measures the degree of contraction of the uterus based on the output signals of the plurality of deformation sensors,
With
The substrate has a plurality of concentrically arranged elastic cord-like members having a center on the front side of the abdomen.
The deformation sensor is a wearable device for pregnant women that detects the elasticity of the elastic string-like member. The wearable device for pregnant women according to any one of claims 1 to 3 , wherein the deformation sensor is a piezoelectric element.

Images