CN114400063A

CN114400063A - Child development screening method based on medical big data

Info

Publication number: CN114400063A
Application number: CN202111667804.3A
Authority: CN
Inventors: 王磊
Original assignee: Beijing Peking University Medical Brain Health Technology Co ltd
Current assignee: Beijing Peking University Medical Brain Health Technology Co ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2022-04-26

Abstract

Embodiments of the present disclosure provide methods, apparatuses, devices, and computer-readable storage media for child development screening based on medical big data. The method comprises acquiring child medical data; the child medical data comprises images, voice and/or text; cleaning the medical data, and extracting attribute characteristics of the children; the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure; and inputting the attribute characteristics of the children into a child development model to obtain a growth and development report of the children. In this way, the technical effect of objectively evaluating the growth and development conditions of the children is achieved, the labor cost is reduced, and the detection efficiency is improved.

Description

Child development screening method based on medical big data

Technical Field

Embodiments of the present disclosure relate generally to the field of medical data screening, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for child development screening based on medical big data.

Background

Understanding the development ability of children and making a nursing strategy aiming at the development ability of children are scientific infant-raising modes at present. For example, for the development evaluation of children of 0-3 years old, the evaluation of the aspects of large exercise, fine movement, cognitive ability, language, social behaviors and the like is required.

Currently, a common evaluation mode is manual evaluation, that is, an evaluator determines a comprehensive score of a child to be evaluated according to evaluation values of evaluation items in an evaluation table of the child to be evaluated so as to complete evaluation.

However, the manual evaluation method consumes a lot of manpower and time, is costly and inefficient, and is limited by the professional ability of the evaluator, and the accuracy of the evaluation cannot be guaranteed.

Disclosure of Invention

According to an embodiment of the present disclosure, a child development screening program based on medical big data is provided.

In a first aspect of the disclosure, a method of screening for child development based on medical big data is provided. The method comprises the following steps:

acquiring medical data of children; the child medical data comprises images, voice and/or text;

cleaning the medical data, and extracting attribute characteristics of the children; the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure;

and inputting the attribute characteristics of the children into a child development model to obtain a growth and development report of the children.

Further, the cleaning the medical data and extracting the attribute features of the child includes:

according to the type of the child medical data, cleaning the child medical data to obtain data characteristics of the child;

if the type of the child medical data is an image, analyzing the image information through a first algorithm, and determining a table region and a text region in the image information; extracting text lines in the table area and the text area through an OCR text recognition algorithm, and converting the text lines into text information;

if the type of the child medical data is voice, performing echo cancellation and noise reduction processing on the voice to obtain a clean voice signal; converting the clean voice into text information through a preset voice conversion algorithm;

and performing word segmentation processing on the text information through a preset word segmentation dictionary to obtain the attribute characteristics of the children.

Further, the analyzing the image information by the first algorithm, and the determining the table area in the image information includes:

acquiring all horizontal lines and vertical lines in the image information;

combining any two transverse lines and any two vertical lines;

judging whether the combination meets the construction rule of the cell;

if yes, adjacent cells are combined to form the table area.

Further, the performing echo cancellation and noise reduction processing on the speech to obtain a clean speech signal includes:

preprocessing the voice to obtain an audio frequency spectrum of the voice signal;

and based on the audio frequency spectrum, carrying out echo cancellation and noise reduction processing on the voice to obtain an optimized voice signal.

Further, the preprocessing the voice to obtain the audio frequency spectrum of the voice signal includes:

obtaining the central frequency value of the voice by the following formula:

wherein, the N represents the number of filters;

e is a frequency constant;

h is a frequency hertz value;

the I represents the arrangement number of the band-pass filters;

carrying out mathematical conversion on the central frequency value to obtain the logarithm of the central frequency value;

and performing offline cosine transform on the logarithm to obtain the audio frequency spectrum of the voice.

Further, the child development model is constructed by:

inputting the marked training sample into a pre-established logistic regression model; the target function in the logistic regression model is a log-likelihood function;

determining a weight vector of a decision function in the logistic regression model through a gradient rise algorithm;

and iterating the weight vector until the gradient is smaller than a preset threshold value, and finishing the training of the child development model.

Further, still include:

and before the training process of the child development model, expanding the sample numerical range based on the child growth development reference standard.

In a second aspect of the present disclosure, a child development screening device based on medical big data is provided. The device includes:

the acquisition module is used for acquiring medical data of children; the child medical data comprises images, voice and/or text;

the cleaning module is used for cleaning the medical data and extracting attribute characteristics of the children; the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure;

and the generation module is used for inputting the attribute characteristics of the children into a child development model to obtain a growth and development report of the children.

In a third aspect of the disclosure, an electronic device is provided. The electronic device includes: a memory having a computer program stored thereon and a processor implementing the method as described above when executing the program.

In a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, implements a method as in accordance with the first aspect of the present disclosure.

According to the child development screening method based on the medical big data, the medical data of children are obtained; the child medical data comprises images, voice and/or text; cleaning the medical data, and extracting attribute characteristics of the children; the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure; the attribute characteristics of the children are input into the child development model to obtain a child growth and development report, so that the technical effect of objectively evaluating the child growth and development conditions is achieved, the labor cost is reduced, and the efficiency is improved.

It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:

FIG. 1 illustrates a schematic diagram of an exemplary operating environment in which embodiments of the present disclosure can be implemented;

FIG. 2 shows a flow diagram of a method of child development screening based on medical big data, according to an embodiment of the present disclosure;

FIG. 3 illustrates a block diagram of a child development screening device based on medical big data according to an embodiment of the present disclosure;

FIG. 4 illustrates a block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the medical big data-based child development screening method or medical big data-based child development screening apparatus of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a model training application, a video recognition application, a web browser application, social platform software, etc., may be installed on the

terminal devices

101, 102, 103.

The

terminal apparatuses

101, 102, and 103 may be hardware or software. When the

terminal devices

101, 102, and 103 are hardware, they may be various electronic devices with a display screen, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg Audio Layer 4), laptop portable computers, desktop computers, and the like. When the

terminal apparatuses

101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.

When the

terminals

101, 102, 103 are hardware, a video capture device may also be installed thereon. The video acquisition equipment can be various equipment capable of realizing the function of acquiring video, such as a camera, a sensor and the like. The user may capture video using a video capture device on the terminal 101, 102, 103.

The server 105 may be a server that provides various services, such as a background server that processes data displayed on the

terminal devices

101, 102, 103. The background server may perform processing such as analysis on the received data, and may feed back a processing result (e.g., a growth and development report of a child) to the terminal device.

The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. In particular, in the case where the target data does not need to be acquired from a remote place, the above system architecture may not include a network but only a terminal device or a server.

Fig. 2 is a flowchart of a child development screening method based on medical big data according to an embodiment of the present application. As can be seen from fig. 2, the child development screening method based on medical big data of the embodiment includes the following steps:

and S210, acquiring medical data of the children.

Wherein the child medical data comprises images, speech and/or text.

In the present embodiment, an executing subject (for example, a server shown in fig. 1) for a child development screening method based on medical big data may acquire child medical data in a wired manner or a wireless connection manner.

Furthermore, the execution main body may acquire the child medical data transmitted by an electronic device (for example, the terminal device shown in fig. 1) in communication connection with the execution main body, or may be the child medical data stored locally in advance.

In some embodiments, the child medical data includes doctor's medical findings, physical examination data, and/or test results, and the like.

And S220, cleaning the medical data and extracting the attribute characteristics of the children.

Wherein the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure.

In some embodiments, the medical data is classified, data types in the medical data are determined, and text information corresponding to different data types is extracted.

Specifically, if the type of the child medical data is an image, the image is analyzed by a centret model, inclined horizontal lines and vertical lines (display borders or table lines in screen display contents, etc.) in the image are detected, and the whole picture is corrected by perspective transformation. And determining the center of the image, scanning from the center of the image to four directions, namely, up, down, left and right, to find the edge of the screen (according to the change degree of color distribution), and cutting the image into a screen area. Determining the center of the screen area, scanning from the center of the screen area to four directions, namely, up, down, left and right, to find the edges of the main content area (according to the change degree of color distribution), and cutting the image into the main content area (determining the coordinates of four corners in the area). The main content area includes a table area and a text area.

The method for determining the table area comprises the following steps:

combining adjacent transverse lines to form transverse line areas; combining adjacent vertical lines to form a vertical line area;

deleting transverse line and/or vertical line areas with small length-width ratios; the length-width ratio can be preset according to actual conditions;

sequencing all the transverse lines and the vertical lines respectively;

combining any two transverse lines and any two vertical lines, judging whether the rules of the cells are met, if so, keeping the combination (the cells);

all cells are merged (neighbor principle) to form the table area. If the adjacent cells are missing, cell completion is performed (forming a complete table area).

And further, extracting text lines in the table area and the text area through an OCR text recognition algorithm, and converting the text lines into text information.

If the type of the child medical data is voice, obtaining a center frequency value of the voice through the following formula:

wherein, the N represents the number of filters;

e is a frequency constant;

h is a frequency hertz value;

the I represents the arrangement number of the band-pass filters;

performing offline cosine transform on the logarithm to obtain an audio frequency spectrum of the voice;

based on the audio frequency spectrum, carrying out echo cancellation and noise reduction processing on the voice to obtain an optimized voice signal;

further, the clean voice is converted into text information through a preset voice conversion algorithm. The preset voice conversion algorithm comprises an acoustic model, a language model and a decoding part. Wherein, the acoustic model can be RNN-CTC, the language model can be N-Gram or RNN-based language model, and the decoding algorithm can be beam search. And automatically correcting the clean speech by a language model-based method and/or a seq2seq (sequence-to-sequence) deep learning method so as to improve the recognition accuracy of the clean speech.

In some embodiments, the text information (including text information derived from images, converted speech, and medical data of the child) is segmented by a preset segmentation dictionary, so as to obtain attribute characteristics of the child.

And S230, inputting the attribute characteristics of the children into a child development model to obtain a growth and development report of the children.

In some embodiments, the labeled training samples are input into a pre-established logistic regression model; the sample is a sample for expanding the numerical range of the sample based on the reference standard for the growth and development of children;

wherein the logistic regression model is a decision function represented by conditional probabilities, namely:

in the formula, a sample feature vector x is input data, a label y belongs to {0,1} and is output data, w is a weight vector (a logistic regression model parameter), and wx is an inner product of w and x.

Expressing a decision function by using a conditional probability form, then obtaining a parameter w (obtaining a best model) which is optimal relative to a training set sample by using a method of maximizing a likelihood function, and analyzing and predicting the sample by using the model;

wherein the objective function in the logistic regression model is a log-likelihood function;

it is pushed to the formula: let P (y-1 | x) ═ pi (x), P (y-0 | x) ═ 1-pi (x); the likelihood function is then:

further, based on the meaning and nature of the log-likelihood function, the problem translates into a maximization of the objective function.

In some embodiments, a gradient ascent algorithm is used to maximize the objective function. The gradient ascent algorithm is an iterative method that makes the objective function l (w) larger and larger by changing the value of the variable w continuously until the function l (w) takes a maximum value, at which point w determines a best logistic regression model.

The gradient is a vector that indicates that the objective function grows fastest as the variables of the objective function l (w) move along the gradient direction. The gradient direction is calculated from the partial derivative of the function with respect to the variable, and the objective function l (w) can be expressed as:

further, the gradient direction of the objective function is:

initializing a parameter w, and then continuously iterating w towards the gradient direction, wherein the iteration formula is as follows:

wherein the constant eta is a learning rate and can be self-defined along with the iteration times;

and continuously updating w until the modulus of the gradient is smaller than a set threshold value, and substituting the final w value into a decision model to obtain the best logistic regression model to finish the training of the child development model.

In some embodiments, the attribute characteristics of the child are input into a child development model, a growth and development report of the child is obtained, and whether the growth and development of the child are normal or not is determined.

According to the embodiment of the disclosure, the following technical effects are achieved:

according to the type of medical big data, the medical big data are cleaned through different processing methods respectively to obtain required child attribute characteristics, the child attribute characteristics are processed through a child development model trained based on a logistic regression model and a gradient ascent algorithm, a child growth and development report containing whether child growth and development are normal or not can be obtained quickly and accurately, the labor cost is reduced, and meanwhile the processing efficiency is greatly improved.

It is noted that while for simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present disclosure is not limited by the order of acts, as some steps may, in accordance with the present disclosure, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that acts and modules referred to are not necessarily required by the disclosure.

The above is a description of embodiments of the method, and the embodiments of the apparatus are further described below.

Fig. 3 illustrates a block diagram of a child development screening device 300 based on medical big data according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus 300 includes:

an obtaining module 310, configured to obtain child medical data; the child medical data comprises images, voice and/or text;

the cleaning module 320 is used for cleaning the medical data and extracting attribute characteristics of the children; the attribute characteristics include age, gender, height, weight, blood routine, urine routine, heart rate, and/or blood pressure;

the generating module 330 is configured to input the attribute characteristics of the child into a child development model, so as to obtain a growth and development report of the child.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the described module may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.

FIG. 4 shows a schematic block diagram of an electronic device 400 that may be used to implement embodiments of the present disclosure. As shown, device 400 includes a Central Processing Unit (CPU)401 that may perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)402 or loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data required for the operation of the device 400 can also be stored. The CPU401, ROM402, and RAM403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

A number of components in device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, or the like; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408 such as a magnetic disk, optical disk, or the like; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Processing unit 401 performs various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM402 and/or the communication unit 409. When the computer program is loaded into RAM403 and executed by CPU401, one or more steps of method 200 described above may be performed. Alternatively, in other embodiments, the CPU401 may be configured to perform the method 200 in any other suitable manner (e.g., by way of firmware).

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System On Chip (SOCs), load programmable logic devices (CPLDs), and the like.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A child development screening method based on medical big data is characterized by comprising the following steps:

2. The method of claim 1, wherein the cleaning the medical data to extract attribute features of the child comprises:

3. The method of claim 2, wherein analyzing the image information by the first algorithm to determine a table region within the image information comprises:

acquiring all horizontal lines and vertical lines in the image information;

combining any two transverse lines and any two vertical lines;

judging whether the combination meets the construction rule of the cell;

if yes, adjacent cells are combined to form the table area.

4. The method of claim 3, wherein the performing echo cancellation and noise reduction on the speech to obtain a clean speech signal comprises:

5. The method of claim 4, wherein the pre-processing the speech to obtain the audio spectrum of the speech signal comprises:

obtaining the central frequency value of the voice by the following formula:

wherein, the N represents the number of filters;

e is a frequency constant;

h is a frequency hertz value;

the I represents the arrangement number of the band-pass filters;

6. The method of claim 5, wherein the child development model is constructed by:

7. The method of claim 6, further comprising:

8. A child development screening device based on medical big data, comprising:

9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 7.