CN115274098B - Intelligent system for predicting height based on bone age and height - Google Patents

Intelligent system for predicting height based on bone age and height Download PDF

Info

Publication number
CN115274098B
CN115274098B CN202210998020.7A CN202210998020A CN115274098B CN 115274098 B CN115274098 B CN 115274098B CN 202210998020 A CN202210998020 A CN 202210998020A CN 115274098 B CN115274098 B CN 115274098B
Authority
CN
China
Prior art keywords
age
current
height
bone
analysis module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210998020.7A
Other languages
Chinese (zh)
Other versions
CN115274098A (en
Inventor
谢林洲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Dongbao Yunxin Technology Co.,Ltd.
Original Assignee
Beijing Ge Ge Network Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Ge Ge Network Technology Co ltd filed Critical Beijing Ge Ge Network Technology Co ltd
Priority to CN202210998020.7A priority Critical patent/CN115274098B/en
Publication of CN115274098A publication Critical patent/CN115274098A/en
Application granted granted Critical
Publication of CN115274098B publication Critical patent/CN115274098B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of data calculation, in particular to an intelligent system for predicting body height based on bone age and body height, which comprises a data storage module, a learning processing module, a prediction analysis module and a bone age X-ray film database, wherein the data storage module comprises a sample database and a bone age X-ray film database and is used for storing a large amount of previous data for predicting body height, the learning processing module is used for establishing a mathematical distribution model of a bone age X-ray film characteristic value and carrying out deep learning so as to provide reliable bone age identification data, and the prediction analysis module is used for respectively establishing a mathematical distribution model of bone age and a mathematical distribution model of age and body height and carrying out deep learning so as to predict bone age identification data, current age and bone dirty line closed body height corresponding to the current height according to the respectively established models. By neglecting subjective limitation caused by parent height factors and only predicting future height by predicting the existing multi-time development condition of a prediction object, the method can better adapt to the change of the era and obtain a more accurate height prediction value.

Description

Intelligent system for predicting height based on bone age and height
Technical Field
The invention relates to the technical field of data calculation, in particular to an intelligent system for predicting body height based on bone age and body height.
Background
In the process of the prior art for predicting the height, the adopted methods only predict the height by the current height and the height of parents, but the methods for predicting the height do not combine the prior development indexes of children, are difficult to achieve accurate prediction, and do not predict the trend of the future height of the children only according to the current bone age and the height state of the children when predicting the height.
Chinese patent publication no: CN110265119A. A bone age estimation and height prediction model, a system thereof and a prediction method thereof are disclosed, which comprises an image capturing unit and a non-transitory machine readable medium. The image acquisition unit is used for acquiring X-ray image data of a target hand bone of a subject. The non-transitory machine readable medium is configured to store a program that, when executed by the processing unit, is configured to determine a hand bone development status, a bone age, and predict an adult height of the subject. Therefore, the bone age assessment and height prediction system can effectively improve the accuracy and sensitivity of the bone age assessment and height prediction, and can shorten the judgment time of the bone age assessment and height prediction; therefore, the bone age estimation and height prediction model, the system thereof and the prediction method thereof still have the problem that the condition for predicting the height of the adult is only based on the development state and the bone age of the hand bone, so that the predicted adult still has large error.
Disclosure of Invention
Therefore, the invention provides an intelligent system for predicting the height based on the bone age and the height, which is used for solving the problem of inaccurate prediction caused by predicting the height at a plurality of future moments only by the parent height and not only combining the current bone age, the current age and the current height in the conventional height prediction technology.
In order to achieve the above object, the present invention provides an intelligent system for predicting height based on bone age and height, comprising a data storage module, a learning processing module, and a prediction analysis module, wherein,
the data storage module comprises a sample database and a bone age X-ray film database, wherein the sample database is used for respectively storing the relational data of bone age and the relational data of age and current height, and the bone age X-ray film database is used for storing standard bone age X-rays of non-used hands corresponding to the bone age;
the learning processing module is used for deeply learning the standard bone age X-ray film of the non-used hand stored in the bone age X-ray film database in the data storage module, establishing a mathematical distribution model of the characteristic value of the standard bone age X-ray film of the non-used hand, learning the characteristic value by referring to the corresponding standard bone age X-ray film of the non-used hand in the mathematical distribution model of the bone age and the age, transmitting the standard bone age X-ray film of the non-used hand corresponding to the relational data to the bone age X-ray film database, and updating the established mathematical model;
specifically, the standard bone age X-ray film of the non-used hand is an X-ray film which is shot by taking a correction position of the non-used hand to judge the bone age, namely, five fingers of the left hand are naturally opened, the palm of the hand is downward, the middle finger and the forearm keep a straight line, the palm is not shifted left or right, the arm is laid flat and is not lifted, and the development degree of ossification centers at the lower ends of the metacarpal bones, the carpal bones and the ulna of the left hand is observed through the X-ray film.
Specifically, the learning processing module includes a deep learning algorithm for automatically evaluating bone age, which may be a pre-trained convolutional neural network model based on a computer vision system identification project ImageNet created by using a migration learning method, or a zero-base training model of a non-used hand X-ray film based on a specific convolutional neural network, and only needs to be able to satisfy the automatic evaluation of the bone age of the X-ray film in this embodiment, which is not described herein again.
The prediction analysis module is used for respectively establishing a bone age and age mathematical distribution model and an age and height mathematical distribution model according to the sample database, importing the relation data of the current bone age and the current age into the bone age and age mathematical distribution model, importing the relation data of the current age and the current height into the age and height mathematical distribution model, predicting the height and the maximum height at multiple moments in the future, transmitting the prediction result to the sample database in real time, and updating the mathematical distribution model established by the prediction analysis module.
The data storage module is internally stored with relationship data of bone age and age, wherein the relationship data respectively comprise relationship data of male bone age and relationship data of female bone age and age, the relationship data of age and current height are stored in the data storage module, the relationship data respectively comprise relationship data of male age and current height and relationship data of female age and current height, and the data storage module is simultaneously stored with standard non-dominant hand bone age X-ray films in the whole stage of bone age growth and used for the learning processing module to carry out deep learning on the stored data;
the learning processing module establishes a bone age and age mathematical distribution model BA through deep learning of relationship data of the bone age and the age, wherein the BA comprises a male bone age and age mathematical distribution model BAM and a female bone age and age mathematical distribution model BAW, any sample data in the bone age and age mathematical distribution model BA is IB, IA and I is any sample in the sample data, the I comprises data of the bone age B1 and the height S1 of the sample at the age A1, data of the bone age B2 and the height S2 at the age A2 and data of the bone age B3 and the height S3 at the age A3, \ 8230; \\ 8230;
the learning processing module establishes an age and current height mathematical distribution model AS through deep learning of the relation data of the age and the current height, and any sample data in the age and current height mathematical distribution model AS IS IA: IS;
the prediction analysis module is provided with a current bone age B0 comprising a current male bone age BM0 and a current female bone age BW0, a current age A0 comprising a current male age AM0 and a current female age AW0, a current height S0 comprising a current male age SM0 and a current female age SW0, and the prediction analysis module automatically identifies and matches corresponding data models in the data storage module according to the current gender;
the prediction analysis module judges the closest reference data of the current bone age B0, the current age A0 and the current height S0 in the model BA and the model AS according to the comparison results of the current bone age B0, the current age A0 and the current height S0 with the bone age and age mathematical distribution model BA and the age and current height mathematical distribution model AS respectively, predicts the predicted heights and predicted adult heights at the future multiple moments corresponding to the current bone age B0, the current age A0 and the current height S0 according to the reference data, leads the predicted heights and predicted adult heights at the future multiple moments into the data storage module, leads the actual heights and actual adults at the future multiple moments into the data storage module, and carries out deep learning on the predicted heights and predicted adult height line closed heights at the future multiple moments according to the actual heights and actual heights at the future multiple moments corresponding to the current bone age B0, the current age A0 and the current height S0 to obtain the curves and the total curves of the predicted heights and the predicted heights at the future moments, and the predicted heights at the current moments are used for improving the trend of the prediction module.
The prediction analysis module substitutes the relation between the current bone age B0 and the current age A0 into a bone age and age mathematical distribution model BA to determine the relation between the current bone age and the corresponding sample data in the data storage module, wherein the age is equal as a comparison condition,
when B0 > 101%;
when B0 is less than 99 percent, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 do not match with the samples in the data storage module respectively;
the predictive analysis module determines that the current bone age B0 and the current age A0 data match the samples in the data storage module, respectively, when 101% IB.gtoreq.B 0.gtoreq.99% IB.
The prediction analysis module substitutes the relation between the current age A0 and the current height S0 into the mathematical distribution model AS of the age and the current height to determine the relation between the current age A0 and the current height S and the corresponding sample data in the data storage module, wherein the age is equal AS a comparison condition,
when S0 is more than 101% IS, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 are not matched with the samples in the data storage module respectively;
when S0 is less than 99% IS, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 are not matched with the samples in the data storage module respectively;
the predictive analysis module determines that the current age A0 and current height S0 data match the samples in the data storage module, respectively, when 101% IS ≧ S0 ≧ 99% IS.
When the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are respectively matched with the samples in the data storage module, the prediction analysis module predicts the current bone age B0, the current bone age A0 and the current bone scale line closed height corresponding to the current height S0 according to the sample bone age IB, the sample age IA and the sample height IS, and corrects the current bone scale line closed height according to the current bone age B0', the current age A0' and the current height S0 'which are acquired according to a preset period, the sample bone age IB', the sample age IA 'and the sample height IS' which correspond to the preset period, wherein the prediction analysis module sets the acquisition period of the current data and the sample data as t, the prediction analysis module sets the bone scale line closed age as c, the sample bone scale line closed age as IBc, the current bone scale line closed age IS B0c, the prediction analysis module sets the bone scale line closed age as e, the sample bone scale line closed age line closed line as IAe, the current bone scale line closed age A0e, the prediction analysis module sets the bone scale line closed height as ISu, and the current bone scale line closed height as ISu;
when in use
Figure BDA0003806417700000041
The prediction analysis module determines the current bone dirt line closureThe closing speed is increased, if so, then>
Figure BDA0003806417700000042
The prediction analysis module determines that the current bone dirty line closing height S0u needs to be corrected, the value of the current bone dirty line closing height S0u needs to be increased, and the corrected value is ^ greater than or equal to>
Figure BDA0003806417700000043
Figure BDA0003806417700000044
When in use
Figure BDA0003806417700000045
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000046
The prediction analysis module determines that the current bone scaling line closing height S0u needs to be corrected, reduces the value of the current bone scaling line closing height S0u, and corrects the value>
Figure BDA0003806417700000051
/>
Figure BDA0003806417700000052
When in use
Figure BDA0003806417700000053
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000054
The prediction analysis module determines that the current bone dirty line closing height S0u needs to be corrected, the value of the current bone dirty line closing height S0u needs to be increased, and the corrected value is changed>
Figure BDA0003806417700000055
Figure BDA0003806417700000056
When the temperature is higher than the set temperature
Figure BDA0003806417700000057
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000058
The prediction analysis module determines that the current bone scaling line closing height S0u needs to be corrected, reduces the value of the current bone scaling line closing height S0u, and corrects the value>
Figure BDA0003806417700000059
Figure BDA00038064177000000510
When in use
Figure BDA00038064177000000511
Then the predictive analysis module judges that the closing speed of the current bone dirty line is accelerated, if so, the device makes a judgment on whether the current bone dirty line is closed or not>
Figure BDA00038064177000000512
The prediction analysis module determines that the current bone mineral line closure height S0u does not require correction.
When the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are not matched with the samples in the data storage module respectively, the prediction analysis module carries out trend prediction on the current bone age B0, the current age A0 and the current height S0, determines samples in the same proportion corresponding to the current bone age B0, the current age A0 and the current height S0, and predicts the current bone dirty line closed height S0u according to the samples in the same proportion, wherein the ages are equal as comparison conditions,
when B0 > 101%
Figure BDA0003806417700000061
And->
Figure BDA0003806417700000062
The prediction analysis module judges that the current bone age B0 and the current height S0 are the same proportion increasing samples of the sample I under the condition of the same age, and the prediction analysis module predicts according to the ISu
Figure BDA0003806417700000063
When B0 < 99% IB and S0 < 99% IS, the predictive analysis module determines that the current bone age B0 and the current height S0 are both below the sample I ratio, if
Figure BDA0003806417700000064
And is provided with
Figure BDA0003806417700000065
The prediction analysis module judges that the current bone age B0 and the current height S0 are samples with the same reduction ratio of the sample I under the condition of the same age, and the prediction analysis module predicts according to ISu
Figure BDA0003806417700000066
When B0 < 99% IB, and S0 > 101% IS, the predictive analysis module determines that the current bone age B0 and the current height S0 do not have corresponding samples of the same scale at the same age,
when B0 > 101%.
When B0 < 99% IB, and S0 > 101% IS, and the prediction analysis module determines that the current bone age B0 and the current height S0 have no samples with similar values and the same proportion at the same age, determining
Figure BDA0003806417700000067
And &>
Figure BDA0003806417700000068
To correspond to/>
Figure BDA0003806417700000069
And &>
Figure BDA00038064177000000610
Whether the proportional trends are similar or not, and predicting the trend, and predicting the bone dirty line closing age A0e and the bone dirty line closing height S0u according to the result of the trend prediction, wherein,
when in use
Figure BDA00038064177000000611
The prediction analysis module makes a decision->
Figure BDA00038064177000000612
Based on sample I->
Figure BDA00038064177000000613
Trends are similar, predicting B0c,. Based on IBc>
Figure BDA00038064177000000614
Calculating according to the B0c and the IBc to obtain A0e, wherein the A0e = (B0 c-IBc) + IAe;
when in use
Figure BDA0003806417700000071
The prediction analysis module makes a decision->
Figure BDA0003806417700000072
Based on sample I>
Figure BDA0003806417700000073
Trends are similar, predicting A0e ', -based on I' Ae>
Figure BDA0003806417700000074
Predicting S0u, S0u = (B0 c-IBc) + IBe according to A0e' and ISu; the prediction analysis module predicts S0u', -based on the predicted bone age and trend results of age and height>
Figure BDA0003806417700000075
/>
When the predictive analysis module determines
Figure BDA0003806417700000076
And &>
Figure BDA0003806417700000077
Corresponds to>
Figure BDA0003806417700000078
And &>
Figure BDA0003806417700000079
When the proportions of the bone dirty lines are only similar in trend, predicting the current bone dirty line closed height S0u according to the similar proportions;
when the predictive analysis module determines
Figure BDA00038064177000000710
And &>
Figure BDA00038064177000000711
Corresponds to>
Figure BDA00038064177000000712
And &>
Figure BDA00038064177000000713
When the proportions of the bone mass lines are not close to each other, the prediction analysis module only records the current bone age B0, the current age A0 and the current height S0, and does not predict the current bone mass line closed height S0u.
When B0 > 101%
Figure BDA00038064177000000714
And &>
Figure BDA00038064177000000715
Corresponding->
Figure BDA00038064177000000716
And &>
Figure BDA00038064177000000717
Whether the proportional trends are similar or not, and predicting the trend, and predicting the bone dirty line closing age A0e and the bone dirty line closing height S0u according to the result of the trend prediction, wherein,
when in use
Figure BDA00038064177000000718
The prediction analysis module makes a decision->
Figure BDA00038064177000000719
In combination with sample I>
Figure BDA00038064177000000720
Trends are similar, predicting B0c,. Based on IBc>
Figure BDA00038064177000000721
Calculating according to the B0c and the IBc to obtain A0e, wherein the A0e = IAe- (B0 c-IBc);
when in use
Figure BDA00038064177000000722
The prediction analysis module makes a decision->
Figure BDA00038064177000000723
In combination with sample I>
Figure BDA00038064177000000724
Trends are similar, predicting A0e ', -based on I' Ae>
Figure BDA00038064177000000725
Predicting S0u according to A0e' and ISu, wherein S0u = IBe- (B0 c-IBc); the prediction analysis module predicts S0u', -and/or based on the predicted trend results of bone age and height>
Figure BDA0003806417700000081
When the predictive analysis module determines
Figure BDA0003806417700000082
And &>
Figure BDA0003806417700000083
Corresponds to>
Figure BDA0003806417700000084
And &>
Figure BDA0003806417700000085
When the individual trends of the proportions are similar, predicting the current bone dirty line closed height S0u according to the similar proportions;
when the predictive analysis module determines
Figure BDA0003806417700000086
And &>
Figure BDA0003806417700000087
Corresponds to>
Figure BDA0003806417700000088
And &>
Figure BDA0003806417700000089
When the proportions of the two kinds of bone marrow and the bone marrow are not close to each other, the prediction analysis module only records the current bone age B0, the current age A0 and the current height S0, but does not predict the current bone marrow closed height S0u.
When the prediction analysis module determines that the comparison condition is equal to the age,
when B0 < 99% IB, and S0 > 99% IS, or, B0 > 101% IB, and S0 < 101% IS, the predictive analysis module only records the current bone age B0, current age A0, and current height S0, does not predict the current bone streak closed height S0u, until such sample number satisfies the height prediction requirement.
The prediction analysis module transmits the predicted current height and the current bone scaling line closed height at a plurality of moments in the future to the sample database, corrects the current height and the current bone scaling line closed height according to the actual height and the actual adult height at a plurality of moments in the future, transmits the corrected height and the corrected adult height to the sample database, supplements the sample database, and meanwhile enables the prediction analysis module to carry out deep learning on the sample database, so that the accuracy rate of the height prediction is increased.
Compared with the prior art, the height forecasting method has the advantages that firstly, a large amount of past data for forecasting the height can be stored through the arranged data storage module, a favorable basis is provided for the module for identifying and learning types, the accuracy rate of the height forecasting can be greatly improved by continuously adding latest forecasting data to the data storage module, and under the condition that the data are mature enough, more accurate forecasting data can be provided for a few cases, so that a doctor is helped to provide an accurate and effective coping means for the case of the height abnormity through the mature forecasting data, and the misdiagnosis probability is reduced.
Secondly, a mathematical model of the characteristic value of the standard bone age X-ray film of the non-used hand is established through an arranged learning processing module, deep learning is carried out, reliable bone age identification data are provided, the identification accuracy of the standard bone age X-ray film of the non-used hand is continuously improved, and a good data precision basis is further provided for final height prediction.
And thirdly, modeling is carried out on the previous height prediction data stored in the data storage module through the provided prediction analysis module, so that corresponding sample data matched with the current bone age, the current age and the current height can be better judged, and data visualization analysis is provided, so that the height prediction accuracy is improved.
And fourthly, the prediction analysis module can judge the numerical value of the current data and the sample data which are successfully matched with the numerical value through the established multiple mathematical models, so that the height prediction accuracy is further improved.
And fifthly, the prediction analysis module performs bone age/age ratio matching on the current data and the sample data which are not successfully matched in numerical value through the established bone age/age mathematical model, judges the specific relation between the current data and the bone age/age in the sample data, including rule increase, rule decrease, rule increment and rule decrement, and further improves the accuracy of height prediction by taking the relation as one of bases of height prediction.
And sixthly, the prediction analysis module performs age/height ratio matching on the current data which is not successfully matched in numerical value and the sample data through the established age/height mathematical model, judges the specific relation between the current data and the age/height in the sample data, and takes the relation as one of basis of height prediction to further improve the accuracy of the height prediction, wherein the specific relation comprises rule increase, rule decrease, rule increment and rule decrement.
And seventhly, the prediction analysis module comprehensively considers the current data and the sample data of which the numerical values are not successfully matched through the established multiple mathematical models, predicts the numerical value of the bone age of the bone dirty line closure, predicts the numerical value of the bone height of the bone dirty line closure according to the numerical value, and further improves the accuracy of height prediction.
And eighthly, the prediction analysis module transmits the predicted current height and the current bone dirty line closed height at multiple moments in the future to a sample database, corrects the current height and the current bone dirty line closed height according to the actual height and the actual adult height at multiple moments in the future, transmits the corrected height and the corrected adult height to the sample database, supplements the sample database, and meanwhile enables the prediction analysis module to carry out deep learning on the sample database, so that the accuracy rate of the height prediction is increased.
And ninthly, the prediction analysis module can predict the height of various known abnormal data by continuously supplementing the database when the number of the abnormal height cases meets the prediction requirement, so that the accuracy of the system for predicting the height is continuously improved.
The subjective limitation caused by the height factor of parents is neglected when the height is predicted, the height is predicted only through the existing multi-time development condition of the predicted object, the conditions that the materials are abundant and the nutrition intake is balanced can be better adapted, a doctor can be better helped to provide effective suggestions and height improving means for the predicted object, including sufficient sleep, proper motion, reasonable diet collocation and the like, and the data can help the doctor to collect and arrange in various different means or suggestions for changing the height, so that the method or suggestion for changing the height of the current predicted object is more suitable.
Drawings
FIG. 1 is a schematic structural diagram of an intelligent system for predicting height based on bone age and height according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and do not delimit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Please refer to fig. 1, which is a schematic structural diagram of an intelligent system for predicting height based on bone age and height according to an embodiment of the present invention, the embodiment includes a data storage module, a learning processing module, and a prediction analysis module, wherein,
the data storage module comprises a sample database and a bone age X-ray film database, wherein the sample database is used for respectively storing the relational data of bone age and the relational data of age and current height, and the bone age X-ray film database is used for storing standard bone age X-rays of non-used hands corresponding to the bone age;
the learning processing module is used for deeply learning the standard bone age X-ray film of the non-used hand stored in the bone age X-ray film database in the data storage module, establishing a mathematical distribution model of the characteristic value of the standard bone age X-ray film of the non-used hand, learning the characteristic value by referring to the standard bone age X-ray film of the non-used hand corresponding to the mathematical distribution model of the bone age and the age, transmitting the standard bone age X-ray film of the non-used hand corresponding to the relational data to the bone age X-ray film database and updating the established mathematical model;
in this embodiment, the standard bone age X-ray film of the non-used hand is an X-ray film obtained by taking a positive shot of the non-used hand to judge the bone age, that is, the five fingers of the left hand are naturally opened, the palm is downward, the middle finger and the forearm keep a straight line, the palm is not shifted left or right, the arm is laid flat and is not lifted, and the development degree of the ossification center of the lower ends of the metacarpal bones, the carpal bones and the ulna of the left hand is observed through the X-ray film.
In this embodiment, the relationship data between the bone age and the corresponding standard bone age X-ray film of the non-dominant hand include the relationship data in a certain hospital database and the corresponding standard bone age X-ray film of the non-dominant hand, and include the relationship data in a certain area database and the corresponding standard bone age X-ray film of the non-dominant hand, and may also include the relationship data in a certain country database and the corresponding standard bone age X-ray film of the non-dominant hand, which only needs to satisfy the training of the learning processing module in this embodiment, and is not described herein again.
In this embodiment, the relationship data between the age and the current height includes relationship data in a certain hospital database, including relationship data in a certain area database, and may also include relationship data in a certain country database, and only the training of the learning processing module in this embodiment needs to be satisfied, which is not described herein again.
In this embodiment, the learning processing module includes a deep learning algorithm for automatic bone age assessment, which may be a pre-trained convolutional neural network model based on a computer vision system identification item ImageNet created by using a transfer learning method, or may be a zero-base training model of a non-used hand X-ray film based on a specific convolutional neural network, and only needs to be able to satisfy the automatic assessment of the bone age of the X-ray film in this embodiment, which is not described herein again.
The prediction analysis module is used for respectively establishing a bone age and age mathematical distribution model and an age and height mathematical distribution model according to the sample database, importing the relation data of the current bone age and the current age into the bone age and age mathematical distribution model, importing the relation data of the current age and the current height into the age and height mathematical distribution model, predicting the height and the maximum height at multiple moments in the future, transmitting the prediction result to the sample database in real time, and updating the mathematical distribution model established by the prediction analysis module.
The data storage module is internally stored with relationship data of bone age and age, wherein the relationship data respectively comprise relationship data of male bone age and relationship data of female bone age and age, the relationship data of age and current height are stored in the data storage module, the relationship data respectively comprise relationship data of male age and current height and relationship data of female age and current height, and the data storage module is simultaneously stored with standard non-dominant hand bone age X-ray films in the whole stage of bone age growth and used for the learning processing module to carry out deep learning on the stored data;
the learning processing module establishes a bone age and age mathematical distribution model BA through deep learning of relationship data of the bone age and the age, wherein the BA comprises a male bone age and age mathematical distribution model BAM and a female bone age and age mathematical distribution model BAW, any sample data in the bone age and age mathematical distribution model BA is IB, IA and I is any sample in the sample data, the I comprises data of the bone age B1 and the height S1 of the sample at the age A1, data of the bone age B2 and the height S2 at the age A2 and data of the bone age B3 and the height S3 at the age A3, \ 8230; \\ 8230;
in the embodiment, the sample data selection is not limited in consideration of individual differences.
The male bone age and age mathematical distribution model BAM comprises { BM1: AM1, BM2: AM2, BM3: AM3, \8230, BMn: AMn }, wherein n is the total number of male sample data, BMi: AMi is any bone age and age sample data in the male sample data, i is any sample in the male sample data, i =1,2,3, \8230; \8230, n;
the female bone age and age mathematical distribution model BAW comprises { BW1: AW1, BW2: AW2, BW3: AW3, \8230, BWh: AWh }, wherein h is the total amount of female sample data, BWr: AWr is any bone age and age sample data in the female sample data, r is any sample in the female sample data, and r =1,2,3, \8230;, h;
the learning processing module establishes an age and current height mathematical distribution model AS through deep learning of the relation data of the age and the current height, any sample data in the age and current height mathematical distribution model AS IS IA: IS, the AS comprises a male age and current height mathematical distribution model ASM and a female age and current height mathematical distribution model ASW, wherein,
the male age and current height mathematical distribution model ASM comprises { AM1: SM1, AM2: SM2, AM3: SM3, \8230 \ 8230, AMn: SMn }, and AMI: SMi is any age and current height sample data in male sample data;
the female age and current height mathematical distribution model ASW comprises { AW1: SW1, AW2: SW2, AW3: SW3, \ 8230 \ 8230a \ AWh: SWh }, wherein AWr: SWr is sample data of any age and current height in female sample data;
the prediction analysis module is provided with a current bone age B0 comprising a current male bone age BM0 and a current female bone age BW0, a current age A0 comprising a current male age AM0 and a current female age AW0, a current height S0 comprising a current male age SM0 and a current female age SW0, and the prediction analysis module automatically identifies and matches corresponding data models in the data storage module according to the current gender;
the prediction analysis module is used for judging the closest reference data of the current bone age B0, the current age A0 and the current height S0 in the model BA and the model AS according to the comparison results of the current bone age B0, the current age A0 and the current height S0 with the bone age and age mathematical distribution model BA and the age and current height mathematical distribution model AS respectively, predicting the predicted heights and predicted adult heights at multiple moments in the future corresponding to the current bone age B0, the current age A0 and the current height S0 according to the reference data, leading the predicted heights and predicted adult heights at the multiple moments in the future into the data storage module by the prediction analysis module, leading the actual heights and actual adults at the multiple moments in the future into the data storage module by the prediction analysis module, carrying out deep learning on the predicted heights and predicted adult height line closed heights at the multiple moments in the future according to the actual heights and actual heights at the multiple moments corresponding to the current bone age B0, the current age A0 and the current height S0, and obtaining a total curve and a prediction curve of the predicted heights at the multiple moments in the future corresponding to the current age B0, and the predicted heights S0, and accurately analyzing the trend of the predicted heights of the prediction analysis module according to the trend of the multiple moments in the future.
The prediction analysis module substitutes the relation between the current bone age B0 and the current age A0 into a bone age and age mathematical distribution model BA to determine the relation between the current bone age and the corresponding sample data in the data storage module, wherein the age is equal as a comparison condition,
when B0 > 101%;
when B0 is less than 99 percent, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 do not match with the samples in the data storage module respectively;
the predictive analysis module determines that the current bone age B0 and the current age A0 data match the samples in the data storage module, respectively, when 101% IB.gtoreq.B 0.gtoreq.99% IB.
The prediction analysis module substitutes the relation between the current age A0 and the current height S0 into the mathematical distribution model AS of the age and the current height to determine the relation between the current age A0 and the current height S and the corresponding sample data in the data storage module, wherein the age is equal AS a comparison condition,
when S0 is more than 101% IS, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 are not matched with the samples in the data storage module respectively;
when S0 is less than 99% IS, the prediction analysis module judges that the data of the current bone age B0 and the data of the current age A0 are not matched with the samples in the data storage module respectively;
the predictive analysis module determines that the current age A0 and current height S0 data match the samples in the data storage module, respectively, when 101% IS ≧ S0 ≧ 99% IS.
When the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are respectively matched with the samples in the data storage module, the prediction analysis module predicts the current bone age B0, the current bone age A0 and the current bone scale line closed height corresponding to the current height S0 according to the sample bone age IB, the sample age IA and the sample height IS, and corrects the current bone scale line closed height according to the current bone age B0', the current age A0' and the current height S0 'which are acquired according to a preset period, the sample bone age IB', the sample age IA 'and the sample height IS' which correspond to the preset period, wherein the prediction analysis module sets the acquisition period of the current data and the sample data as t, the prediction analysis module sets the bone scale line closed age as c, the sample bone scale line closed age as IBc, the current bone scale line closed age IS B0c, the prediction analysis module sets the bone scale line closed age as e, the sample bone scale line closed age line closed line as IAe, the current bone scale line closed age A0e, the prediction analysis module sets the bone scale line closed height as ISu, and the current bone scale line closed height as ISu;
when in use
Figure BDA0003806417700000141
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000142
The prediction analysis module determines the current bone dirty line closing heightS0u needs to be corrected, the S0u value of the current bone dirty line closing height needs to be increased, and the corrected value is changed>
Figure BDA0003806417700000143
/>
Figure BDA0003806417700000144
When the temperature is higher than the set temperature
Figure BDA0003806417700000145
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000146
The prediction analysis module determines that the current bone scaling line closing height S0u needs to be corrected, reduces the value of the current bone scaling line closing height S0u, and corrects the value>
Figure BDA0003806417700000147
Figure BDA0003806417700000148
When in use
Figure BDA0003806417700000149
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA00038064177000001410
The prediction analysis module determines that the current bone dirty line closing height S0u needs to be corrected, the value of the current bone dirty line closing height S0u needs to be increased, and the corrected value is ^ greater than or equal to>
Figure BDA00038064177000001411
Figure BDA00038064177000001412
Figure BDA0003806417700000151
When in use
Figure BDA0003806417700000152
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000153
The prediction analysis module determines that the current scale line closing height S0u needs to be corrected, reduces the value of the current scale line closing height S0u, and corrects the scale line closing height S0u>
Figure BDA0003806417700000154
Figure BDA0003806417700000155
When in use
Figure BDA0003806417700000156
Then, the prediction analysis module judges that the closing speed of the current bone dirty line is accelerated, and if so, the current bone dirty line is judged to be on or off>
Figure BDA0003806417700000157
The prediction analysis module determines that the current bone mineral line closure height S0u does not require correction.
When the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are not matched with the samples in the data storage module respectively, the prediction analysis module carries out trend prediction on the current bone age B0, the current age A0 and the current height S0, determines samples in the same proportion corresponding to the current bone age B0, the current age A0 and the current height S0, and predicts the current bone dirty line closed height S0u according to the samples in the same proportion, wherein the ages are equal as comparison conditions,
when B0 > 101%
Figure BDA0003806417700000158
And is
Figure BDA0003806417700000159
The prediction analysis module judges that the current bone age B0 and the current height S0 are the same proportion sample of the sample I under the same age condition, and the prediction analysis module predicts according to the ISu
Figure BDA00038064177000001510
When B0 < 99% IB and S0 < 99% IS, the predictive analysis module determines that the current bone age B0 and the current height S0 are both below the sample I ratio, if
Figure BDA00038064177000001511
And is
Figure BDA0003806417700000161
The prediction analysis module judges that the current bone age B0 and the current height S0 are samples with the same reduction ratio of the sample I under the condition of the same age, and the prediction analysis module predicts according to the ISu
Figure BDA0003806417700000162
When B0 < 99% IB, and S0 > 101% IS, the predictive analysis module determines that the current bone age B0 and the current height S0 do not have corresponding samples of the same scale at the same age,
when B0 > 101%.
When B0 < 99%
Figure BDA0003806417700000163
And &>
Figure BDA0003806417700000164
Corresponding->
Figure BDA0003806417700000165
And &>
Figure BDA0003806417700000166
Whether the proportional trends are similar or not, and predicting trends, and predicting the bone dirty line closing age A0e and the bone dirty line closing height S0u according to the trend prediction result, wherein,
when in use
Figure BDA0003806417700000167
The prediction analysis module makes a decision->
Figure BDA0003806417700000168
Based on sample I->
Figure BDA0003806417700000169
Trends are similar, predicting B0c,. Based on IBc>
Figure BDA00038064177000001610
Calculating according to the B0c and the IBc to obtain A0e, wherein the A0e = (B0 c-IBc) + IAe; />
When in use
Figure BDA00038064177000001611
The prediction analysis module makes a decision->
Figure BDA00038064177000001612
Based on sample I>
Figure BDA00038064177000001613
Trends are similar, predicting A0e ', -based on I' Ae>
Figure BDA00038064177000001614
Predicting S0u, S0u = (B0 c-IBc) + IBe according to A0e' and ISu; the prediction analysis module predicts S0u', -based on the predicted bone age and trend results of age and height>
Figure BDA00038064177000001615
When the predictive analysis module determines
Figure BDA00038064177000001616
And &>
Figure BDA00038064177000001617
Corresponds to>
Figure BDA00038064177000001618
And &>
Figure BDA00038064177000001619
When the individual trends of the proportions are similar, predicting the current bone dirty line closed height S0u according to the similar proportions;
when the predictive analysis module determines
Figure BDA00038064177000001620
And &>
Figure BDA00038064177000001621
Corresponds to>
Figure BDA00038064177000001622
And &>
Figure BDA00038064177000001623
When the proportions of the bone mass lines are not close to each other, the prediction analysis module only records the current bone age B0, the current age A0 and the current height S0, and does not predict the current bone mass line closed height S0u.
When B0 > 101%
Figure BDA0003806417700000171
And &>
Figure BDA0003806417700000172
In combination with corresponding>
Figure BDA0003806417700000173
And &>
Figure BDA00038064177000001722
Whether the proportional trends are similar or not, and predicting the trend, and predicting the bone dirty line closing age A0e and the bone dirty line closing height S0u according to the result of the trend prediction, wherein,
when in use
Figure BDA0003806417700000175
The prediction analysis module makes a decision->
Figure BDA0003806417700000176
Based on sample I->
Figure BDA0003806417700000177
Trends are similar, predicting B0c,. Based on IBc>
Figure BDA0003806417700000178
Calculating according to the B0c and the IBc to obtain A0e, wherein the A0e = IAe- (B0 c-IBc);
when the temperature is higher than the set temperature
Figure BDA0003806417700000179
The prediction analysis module makes a decision->
Figure BDA00038064177000001710
Based on sample I>
Figure BDA00038064177000001711
Trends are similar, predicting A0e ', -based on I' Ae>
Figure BDA00038064177000001712
Predicting S0u according to A0e' and ISu, wherein S0u = IBe- (B0 c-IBc); the prediction analysis module predicts S0u', -based on the predicted bone age and trend results of age and height>
Figure BDA00038064177000001713
When the predictive analysis module determines
Figure BDA00038064177000001714
And &>
Figure BDA00038064177000001715
Corresponds to>
Figure BDA00038064177000001716
And &>
Figure BDA00038064177000001717
When the proportions of the bone dirty lines are only similar in trend, predicting the current bone dirty line closed height S0u according to the similar proportions; />
When the prediction analysis module judges
Figure BDA00038064177000001718
And &>
Figure BDA00038064177000001719
And correspond to>
Figure BDA00038064177000001720
And &>
Figure BDA00038064177000001721
When the proportions of the bone mass lines are not close to each other, the prediction analysis module only records the current bone age B0, the current age A0 and the current height S0, and does not predict the current bone mass line closed height S0u.
In the present embodiment, for abnormal cases such as dwarfism (dwarfism) corresponding when B0 < 99% IB, and S0 > 99% IS, or B0 > 101% IB, and A0 > 101% IA, and S0 < 101% IS, only the records are not predicted until the number of cases satisfies the prediction requirement.
The prediction analysis module transmits the predicted current height and the current bone scaling line closed height at a plurality of moments in the future to the sample database, corrects the current height and the current bone scaling line closed height according to the actual height and the actual adult height at a plurality of moments in the future, transmits the corrected height and the corrected adult height to the sample database, supplements the sample database, and meanwhile enables the prediction analysis module to carry out deep learning on the sample database, so that the accuracy rate of the height prediction is increased.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (2)

1. An intelligent system for predicting the height based on the bone age and the height is characterized by comprising a data storage module, a learning processing module and a prediction analysis module, wherein,
the data storage module comprises a sample database and a bone age X-ray film database, wherein the sample database is used for respectively storing the relationship data of bone age and the relationship data of age and current height, and the bone age X-ray film database is used for storing standard bone age X-rays of non-conventional hands corresponding to bone age;
the learning processing module is used for deeply learning the standard bone age X-ray film of the non-used hand stored in the bone age X-ray film database, establishing a data model of the characteristic value of the standard bone age X-ray film of the non-used hand, learning the characteristic value by referring to the standard bone age X-ray film of the non-used hand corresponding to the model of the bone age and the age, transmitting the standard bone age X-ray film of the non-used hand corresponding to the corresponding relation data to the bone age X-ray film database, and updating the established data model;
the prediction analysis module is used for respectively establishing a bone age and age data model and an age and height data model according to the sample database, importing the relation data of the current bone age and the current age into the bone age and age data model, importing the relation data of the current age and the current height into the age and height data model, predicting the height and the maximum height at multiple moments in the future, transmitting the prediction result to the sample database in real time, and updating the data model established by the prediction analysis module;
the bone age and age data model is set AS BA by the prediction analysis module, the age and current height data model is set AS AS by the prediction analysis module, and I is any sample in the sample data and comprises bone age B and height S data of the sample at age A; the prediction analysis module is provided with a current bone age B0, a current age A0 and a current height S0, and the prediction analysis module automatically matches corresponding data models according to gender;
the prediction analysis module judges the closest reference data of B0, A0 and S0 in the model BA and the model AS respectively according to the comparison results of B0, A0 and S0 with the model BA and the model AS respectively, predicts the body height and the predicted adult height according to the periods corresponding to B0, A0 and S0, respectively introduces the predicted periodic predicted body height and the predicted adult height AS well AS the periodic actual body height and the actual adult height into the data storage module, and deeply learns the periodic predicted body height and the predicted skeleton line closed height according to the periodic actual body height and the actual adult height corresponding to B0, A0 and S0 to obtain a total trend curve and a sectional trend curve corresponding to B0, A0 and S0;
the prediction analysis module substitutes the relation between B0 and A0 into the model BA to determine the data relation between the model BA and the corresponding sample in the data storage module, wherein the age is equal as a comparison condition,
said predictive analysis module determining that current bone age B0 and current age A0 data, respectively, do not match samples within said data storage module when B0 > 101%;
said predictive analysis module determining that the current bone age B0 and current age A0 data match the samples in said data storage module, respectively, when 101% IB.gtoreq.B 0.gtoreq.99% IB;
the prediction analysis module substitutes the relation between A0 and S0 into a model AS to determine the data relation between the model AS and the corresponding sample in the data storage module, wherein age is equal AS a comparison condition,
said predictive analysis module determining that the current bone age B0 and current age A0 data, respectively, do not match the samples in said data storage module when S0 > 101%;
when 101% IS is ≧ S0 ≧ 99% IS, the predictive analysis module determines that current age A0 and current height S0 data respectively match the sample in the data storage module;
when the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are respectively matched with the samples in the data storage module, the prediction analysis module predicts the current bone age line closed heights corresponding to the current bone age B0, the current age A0 and the current height S0 by referring to the sample bone age IB, the sample age IA and the sample height IS ', and corrects the current bone age line closed height according to the current bone age B0', the current age A0' and the current height S0' which are acquired in a preset period, the sample bone age IB ', the sample age IA ' and the sample height IS ' which correspond to the preset period, wherein the prediction analysis module sets the acquisition period of the current data and the sample data to be t, the prediction analysis module sets the bone age line with closed bone scales to be c, the sample bone scale line closed age to be IBC, the current bone scale line closed age line to be B0c, the prediction analysis module sets the age line with closed bone scale line to be e, the sample bone scale line closed age line to be IAe, the current bone scale line closed age line to be A0e, the height of the prediction analysis module sets the bone scale closed line closed scales to be ISu, and the current height to be ISu;
when in use
Figure QLYQS_1
When the bone dirty line is closed, the prediction analysis module judges that the bone dirty line closing speed is too high,if at this time->
Figure QLYQS_2
Judging that S0u needs to be corrected upwards;
when in use
Figure QLYQS_3
The prediction analysis module judges that the closing speed of the bone dirty line is too high, and if the closing speed is too high, the prediction analysis module judges that the bone dirty line is too fast>
Figure QLYQS_4
Judging that S0u needs to be corrected downwards;
when in use
Figure QLYQS_5
The prediction analysis module judges that the closing speed of the bone dirty line is too high, and if the closing speed is too high, the prediction analysis module judges that the bone dirty line is too fast>
Figure QLYQS_6
Judging that S0u needs to be corrected upwards;
when in use
Figure QLYQS_7
The prediction analysis module judges that the closing speed of the bone dirty line is too high, and if the closing speed is too high, the prediction analysis module judges that the bone dirty line is too fast>
Figure QLYQS_8
Judging that S0u needs to be corrected downwards;
when the temperature is higher than the set temperature
Figure QLYQS_9
The prediction analysis module judges that the closing speed of the bone dirty line is too high, and if the closing speed is too high, the prediction analysis module judges that the bone dirty line is too fast>
Figure QLYQS_10
Judging that S0u does not need to be corrected;
when the prediction analysis module judges that the current bone age B0, the current age A0 and the current height S0 are not matched with the samples in the data storage module respectively, the prediction analysis module carries out trend prediction on the current bone age B0, the current age A0 and the current height S0, determines samples in the same proportion corresponding to the current bone age B0, the current age A0 and the current height S0, and predicts the current bone dirty line closed height S0u according to the samples in the same proportion, wherein the ages are equal as comparison conditions,
when B0 > 101%;
when B0 IS less than 99 and IB IS less than 99 and S0 IS less than 99 and IS, the prediction analysis module judges that the current bone age B0 and the current height S0 are both lower than the proportion of the sample I, if the percentages of B0 and S0 which are respectively lower than IB and IS are less than 1 percent, the prediction analysis module judges that the current bone age B0 and the current height S0 are samples with the same reduction proportion of the sample I under the condition of the same age, and the prediction analysis module predicts S0u according to ISu;
when B0 < 99% IB, and S0 > 101% IS, or, B0 > 101% IB, and S0 < 99% IS, the predictive analysis module determines that the current bone age B0 and the current height S0 do not have corresponding same-scale samples for the same age;
when B0 < 99% IB and S0 > 101% IS, and the predictive analysis module determines that there are no samples of similar value and same proportion for the current bone age B0 and the current height S0 at the same age, the predictive analysis module bases the method on
Figure QLYQS_11
And &>
Figure QLYQS_12
Respectively correspond to>
Figure QLYQS_13
And &>
Figure QLYQS_14
Ratio trend to current bone mineral line closure age A0e and current bone mineral line closure height S0u, a prediction is made in which, among others,
when in use
Figure QLYQS_15
When the prediction analysis module makes a decision->
Figure QLYQS_16
Based on sample I->
Figure QLYQS_17
Predicting B0c according to IBc, and calculating to obtain A0e according to the B0c and the IBc;
when the temperature is higher than the set temperature
Figure QLYQS_18
When the prediction analysis module makes a decision->
Figure QLYQS_19
In combination with sample I>
Figure QLYQS_20
The trends are similar, A0e 'is predicted according to I' Ae ', and S0u is predicted according to A0e' and ISu; the prediction analysis module predicts S0u' according to predicted trend results of B/A and A/S;
when the prediction analysis module determines
Figure QLYQS_21
And &>
Figure QLYQS_22
Respectively correspond to>
Figure QLYQS_23
And &>
Figure QLYQS_24
When the proportions are only similar in a single trend, predicting the current bone dirty line closed height S0u only according to the similar proportions;
when the prediction analysis module determines
Figure QLYQS_25
And &>
Figure QLYQS_26
Respectively correspond to>
Figure QLYQS_27
And &>
Figure QLYQS_28
When the proportions of the bone mass lines are not close to each other, the prediction analysis module only records the current bone age B0, the current age A0 and the current height S0, and does not predict the current bone mass line closed height S0u;
when B0 > 101%
Figure QLYQS_29
And &>
Figure QLYQS_30
Respectively correspond to>
Figure QLYQS_31
And &>
Figure QLYQS_32
The scale trend predicts A0e and S0u, where,
when in use
Figure QLYQS_33
When the prediction analysis module makes a decision->
Figure QLYQS_34
Based on sample I->
Figure QLYQS_35
Trends are similar, B0c is predicted according to IBc, and thenCalculating according to the B0c and the IBc to obtain A0e;
when in use
Figure QLYQS_36
When the prediction analysis module makes a decision->
Figure QLYQS_37
Based on sample I>
Figure QLYQS_38
Predicting A0e 'according to I' Ae ', and predicting S0u according to A0e' and ISu; the prediction analysis module predicts S0u' according to the trend results of B/A and A/S prediction;
when the prediction analysis module determines
Figure QLYQS_39
And &>
Figure QLYQS_40
Respectively correspond to>
Figure QLYQS_41
And &>
Figure QLYQS_42
When the proportions of the S0u are similar to each other, predicting the S0u only according to the similar proportions when the single trends are similar to each other;
when the prediction analysis module determines
Figure QLYQS_43
And &>
Figure QLYQS_44
Respectively correspond to>
Figure QLYQS_45
And &>
Figure QLYQS_46
When the proportions of (A) and (B) are not close to each other, the predictive analysisThe module only records B0, A0 and S0, and does not predict S0u;
when the prediction analysis module determines that the ages are equal to each other as a comparison condition,
when B0 < 99% IB, and S0 > 99% IS, or, B0 > 101% IB, and S0 < 101% IS, the predictive analysis module only records the current bone age B0, current age A0, and current height S0, does not predict the current bone streak closed height S0u, until such sample number satisfies the height prediction requirement.
2. The intelligent system for predicting height based on bone age and height according to claim 1, wherein the prediction analysis module transmits the predicted current height in t periods and the current closed height of the bone scaling line to the sample database, corrects the current height and the current closed height of the bone scaling line according to the actual height and the actual adult height in the future t periods, and transmits the corrected height and the corrected adult height to the sample database, so that the prediction analysis module can perform deep learning on the sample database.
CN202210998020.7A 2022-08-19 2022-08-19 Intelligent system for predicting height based on bone age and height Active CN115274098B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210998020.7A CN115274098B (en) 2022-08-19 2022-08-19 Intelligent system for predicting height based on bone age and height

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210998020.7A CN115274098B (en) 2022-08-19 2022-08-19 Intelligent system for predicting height based on bone age and height

Publications (2)

Publication Number Publication Date
CN115274098A CN115274098A (en) 2022-11-01
CN115274098B true CN115274098B (en) 2023-04-07

Family

ID=83753297

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210998020.7A Active CN115274098B (en) 2022-08-19 2022-08-19 Intelligent system for predicting height based on bone age and height

Country Status (1)

Country Link
CN (1) CN115274098B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117423472B (en) * 2023-12-18 2024-03-08 天津医科大学总医院 Multi-element height prediction method and system based on bone age identification

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016140432A2 (en) * 2015-03-04 2016-09-09 주식회사 바이오에이지 Method for predicting residual life using biological age
CN114550929A (en) * 2022-02-15 2022-05-27 周口市中医院 Juvenile bone age data management method based on big data and abnormity early warning method

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050228237A1 (en) * 2004-04-12 2005-10-13 Frank Shallenberger Method for analyzing the biological age of a subject
US20130030862A1 (en) * 2011-07-30 2013-01-31 International Business Machines Corporation Trend-based target setting for process control
JP2016224879A (en) * 2015-06-04 2016-12-28 からだ環境総研株式会社 Body height prediction method and body weight prediction method
CN104965953A (en) * 2015-07-13 2015-10-07 熊妹珍 Establishing method for juvenile height predication model
CN109583272B (en) * 2017-09-29 2020-10-30 大连恒锐科技股份有限公司 Footprint system capable of acquiring living state of human body
CN107731304A (en) * 2017-09-30 2018-02-23 北京好啦科技有限公司 A kind of prediction of height method and system
CN108836338A (en) * 2018-04-04 2018-11-20 浙江康体汇科技有限公司 A kind of calculating of online stone age and prediction of height method based on web database
CN110265119A (en) * 2018-05-29 2019-09-20 中国医药大学附设医院 Bone age assessment and prediction of height model, its system and its prediction technique
CN109994172A (en) * 2019-03-06 2019-07-09 杭州津禾生物科技有限公司 Stone age digitizes measuring and calculating and height data base management system online
CN110211700B (en) * 2019-06-14 2023-06-23 成都高鹿科技有限公司 Individual height prediction method, system, readable storage medium and terminal
CN110660484B (en) * 2019-08-01 2022-08-23 平安科技（深圳）有限公司 Bone age prediction method, device, medium, and electronic apparatus
CN111833298B (en) * 2020-06-04 2022-08-19 石家庄喜高科技有限责任公司 Skeletal development grade detection method and terminal equipment
CN112182067A (en) * 2020-09-27 2021-01-05 深圳市伊欧乐科技有限公司 Individual height prediction method and device, electronic equipment and storage medium
CN112397202B (en) * 2020-10-20 2024-03-29 浙江工业大学 Prediction method for height growth curve of teenager and child
CN112465104B (en) * 2020-12-04 2023-10-10 石家庄喜高科技有限责任公司 Height development evaluation method and terminal equipment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016140432A2 (en) * 2015-03-04 2016-09-09 주식회사 바이오에이지 Method for predicting residual life using biological age
CN114550929A (en) * 2022-02-15 2022-05-27 周口市中医院 Juvenile bone age data management method based on big data and abnormity early warning method

Also Published As

Publication number Publication date
CN115274098A (en) 2022-11-01

Similar Documents

Publication Publication Date Title
CN115274098B (en) Intelligent system for predicting height based on bone age and height
CN107887022B (en) SSTM-based intelligent diagnosis method for traditional Chinese medicine syndromes
CN111671448A (en) Bone age detection method and device based on deep learning
CN108614071B (en) Distributed outdoor air quality monitoring precision correction system and parameter updating method
CN111458661A (en) Power distribution network line variation relation diagnosis method, device and system
CN111489019B (en) Sleep quality prediction method and device
CN115644823A (en) Dynamic prediction and individualized intervention method and system for rehabilitation effect
CN117116412A (en) Intelligent nursing suggestion generation method based on medical record data analysis
CN112182067A (en) Individual height prediction method and device, electronic equipment and storage medium
CN113935535A (en) Principal component analysis method for medium-and-long-term prediction model
CN114041741B (en) Data processing unit, processing device, surgical system, surgical instrument, and medium
CN113951868B (en) Method and device for detecting man-machine asynchronism of mechanical ventilation patient
CN107480721A (en) A kind of ox only ill data analysing method and device
CN107358019A (en) Suitable for the commending system and method for the medical scheme of concept drift
CN117095828A (en) Blood glucose value prediction and alarm method based on follow-up record of diabetics
CN110472788B (en) Personnel information prediction method and device
CN111833298B (en) Skeletal development grade detection method and terminal equipment
CN110045691A (en) A kind of multitasking fault monitoring method of multi-source heterogeneous big data
CN115394442A (en) Development evaluation method, device, equipment and medium
CN115201394A (en) Multi-component transformer oil chromatography online monitoring method and related device
CN211261182U (en) Sensor, controller, electronic device, air conditioner
CN112465104A (en) Height development evaluation method and terminal equipment
CN111243697A (en) Method and system for judging target object data based on neural network
CN117423472B (en) Multi-element height prediction method and system based on bone age identification
CN117936114B (en) Electronic medical record intelligent analysis and optimization system based on large language model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 100101 3-1501, Jinquan Times Square, Datun Road, Chaoyang District, Beijing

Patentee after: Beijing Dongbao Yunxin Technology Co.,Ltd.

Address before: 100101 3-1501, Jinquan Times Square, Datun Road, Chaoyang District, Beijing

Patentee before: Beijing Ge Ge Network Technology Co.,Ltd.

CP01 Change in the name or title of a patent holder