CN113421641A - Eclampsia patient protection device and prediction system - Google Patents
Eclampsia patient protection device and prediction system Download PDFInfo
- Publication number
- CN113421641A CN113421641A CN202110748361.4A CN202110748361A CN113421641A CN 113421641 A CN113421641 A CN 113421641A CN 202110748361 A CN202110748361 A CN 202110748361A CN 113421641 A CN113421641 A CN 113421641A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- light shield
- patient
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G7/00—Beds specially adapted for nursing; Devices for lifting patients or disabled persons
- A61G7/05—Parts, details or accessories of beds
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
Abstract
The invention belongs to the technical field of eclampsia medical equipment, and particularly discloses a protective device and a prediction system for an eclampsia patient. Adopt this technical scheme, utilize the lens hood to shield light for the patient, avoid extrudeing patient's eye, real-time supervision patient simultaneously to in time send early warning signal when patient eclampsia is onset.
Description
Technical Field
The invention belongs to the technical field of eclampsia medical equipment, and relates to a protective device and a prediction system for an eclampsia patient.
Background
Hypertensive disorders of pregnancy are a group of disorders in which pregnancy coexists with elevated blood pressure, which seriously affect the health and safety of the mother and child. The diagnosis and treatment guidelines for hypertensive disorders of pregnancy (2020) classify them into 4 categories: gestational hypertension, preeclampsia-eclampsia, pregnancy combined with chronic hypertension and chronic hypertension accompanied with preeclampsia. Among them, preeclampsia-eclampsia is one of the main causes of the increase of the fatality rate of pregnant and lying-in women and perinatal infants. Preeclampsia is mainly manifested by hypertension and proteinuria after 20 weeks of pregnancy, the incidence rate is 4% -5%, and the preeclampsia can be accompanied by functional damage of important organs such as brain, heart, liver, kidney and the like.
The etiology and pathogenesis of preeclampsia have not been fully elucidated, no effective preventive measures exist, and early discovery and management are the main clinical strategies. In order to reduce the adverse effects of preeclampsia, it is necessary to predict the risk of preeclampsia in pregnant women. With the continuous development of gene sequencing and proteomics technologies, part of biomarker molecules such as sFlt-1 and PlGF can be used as a prediction index of preeclampsia, but all screening evaluation indexes used alone or in combination cannot well predict preeclampsia.
In the prior art, an eye mask is usually adopted to prevent the eye part from being stimulated by the strong light to cause eclampsia symptoms, but the eye mask is worn on the head of a patient and is easy to fall off due to the influence of the activity of the patient during sleeping, and the eye mask is easy to press eyeballs and skin around the eyes after being worn for a long time to cause unsmooth eye blood circulation. Meanwhile, the sudden eclampsia of the patient can be trapped into coma during sleeping and cannot take measures to save oneself, asphyxia or aspiration pneumonia can be caused if vomiting occurs in the coma of the pregnant woman, at the moment, measures need to be taken timely to enable the head of the pregnant woman to be deviated to one side, the phenomenon that secretion is inhaled by mistake and asphyxia is avoided, and otherwise life danger is easily caused. It is therefore desirable to design a device that will provide a timely check for the onset of eclampsia, signal an alarm, and take timely rescue measures for the patient.
Disclosure of Invention
The invention aims to provide a protective device and a prediction system for a patient suffering from eclampsia, which can shade the light of the patient, avoid the extrusion of the eyes of the patient, and timely send out an early warning signal when the eclampsia of the patient occurs by monitoring the condition of the patient in real time, so that the safety of the patient is ensured.
In order to achieve the purpose, the basic scheme of the invention is as follows: a protective device for epilepsy patients comprises an arc-shaped light shield, an image acquisition module and an early warning module;
one side of the light shield is detachably connected with the bed head or the chair back through a connecting piece, the light shield can swing and be positioned relative to the connecting piece, and the light shield is used for shielding the head light of a patient;
the image acquisition module is arranged on the shading cover and is used for acquiring a whole body image and a head image of a patient;
the input end of the early warning module is connected with the output end of the image acquisition module, the body state image characteristics of a patient with eclampsia are stored in the early warning module, the early warning module compares the acquired image with the stored body state image characteristics, the similarity of the comparison is obtained through analysis, whether an early warning signal is output or not is judged according to the similarity, and the early warning signal output end of the early warning module is arranged at the installation position of the light shield and/or on a remote terminal.
The working principle and the beneficial effects of the basic scheme are as follows: the installation position of the light shield can be selected according to the position of the patient during sleeping, which is more beneficial to use. The lens hood can swing and be positioned relative to the connecting piece, and the swing angle of the lens hood can be flexibly controlled, so that the relative position between the lens hood and the head of a patient can be adjusted, and the position of the lens hood can be automatically adjusted by the patient to achieve a better light shielding effect.
The image acquisition module acquires the whole-body image and the head image of the patient, the acquired information is more comprehensive, and the accuracy of judgment is improved by judging whether the patient has eclampsia. The early warning module compares the acquired image information with the stored image information, analyzes the similarity between the images, judges whether the patient has eclampsia according to the numerical value of the similarity, and judges that an early warning signal is output when the eclampsia occurs if the similarity is too high. The output end of the early warning module is arranged at the installation position of the light shield or a remote terminal, and personnel close to the rest position of the patient can acquire early warning information at the light shield to timely rescue the patient; if the patient is eclampsia in the independent place, the early warning signal is transmitted to the remote terminal, so that remote medical personnel or family members of the patient can receive the early warning signal and timely arrive at the place of the patient to take treatment measures.
Furthermore, a piston cylinder is arranged on the inner side of the light shield, one end of the piston cylinder is fixedly arranged on the inner side wall of the light shield, and the other end of the piston cylinder faces to one side face of a patient in the light shield;
the piston plate is connected with a control mechanism which controls the piston plate to move back and forth along the piston cylinder, and the control end of the control mechanism is connected with the output end of the early warning module;
the side of the piston plate far away from the light shield is fixedly connected with a piston rod, the piston rod extends out from one side of the piston cylinder towards the human face, an air bag is arranged at the end part of the piston rod, the air bag is communicated with one side of the piston cylinder close to the human face, and air is arranged in a space communicated with the piston cylinder.
The control mechanism can control the piston plate to move, when the piston plate moves towards one side far away from the light shield, the piston rod moves synchronously along with the piston plate, and the piston rod is gradually close to the face of one side of the patient. Simultaneously, the piston plate moves to push gas in the piston cylinder to the air bag, the air bag expands, the piston rod is propped against the face on one side of the human body through the air bag, the head of the patient is pushed to turn to one side, and the patient is prevented from vomiting and suffocation. Gasbag and human face contact, the relative piston rod of gasbag is more soft, avoids haring patient face, and the gasbag inflation has certain length simultaneously, reduces the distance that the piston rod required removed for promote the askew efficiency to one side of patient's head.
Further, control mechanism includes motor and U-shaped rack, motor fixed mounting is on the light shield, the incomplete gear of fixedly connected with on the output shaft of motor, U-shaped rack and incomplete gear engagement, the tip of U-shaped rack and one side fixed connection that the piston plate is close to the light shield, U-shaped rack perpendicular to piston plate still install the ventilation fan on the output shaft of motor.
The motor has simple structure and is beneficial to operation. The motor controls the incomplete gear to rotate, and the incomplete gear is meshed with the U-shaped rack so as to drive the U-shaped rack to move back and forth. The U-shaped rack drives the piston plate to move towards one side far away from the light shield until the air bag pushes the face of the patient to be deviated to one side, the incomplete gear continues to rotate to drive the U-shaped rack to reset, and the air bag and the piston rod are prevented from shielding the face of the patient and influencing air circulation around the patient. The ventilation fan of installation rotates along with the motor on the motor for the circulation of air is favorable to the patient to breathe unobstructed.
Further, the light shield includes a main shield plate, an extension plate, and an auxiliary shield plate;
two side faces of the main cover plate adjacent to the connecting piece are provided with placing grooves, the extending plates are respectively placed in the placing grooves, magnets are embedded in the positions, close to the notches, of the placing grooves, and metal attracted with the magnets is arranged on the extending plates;
the auxiliary cover plate is of a folding fan structure, a sliding groove is formed in the center line, parallel to the upper surface of the main cover plate, of the side where the placing groove is located, the central shaft of the folding fan structure is in sliding connection with the sliding groove, and when no external force is applied, static friction exists between the central shaft and the side wall of the sliding groove.
Extension board and vice apron all can expand the main cover plate size, guarantee simultaneously that extension board, vice apron are fixed a position stably on the main cover plate, simple structure. The size of the light shield can be flexibly adjusted by a user according to the difference of the body size or the installation position of the user, and the use is convenient.
Furthermore, a threaded hole is formed in the connecting piece, a threaded rod is connected to the threaded hole in a threaded mode, and the side wall of the light shield is fixedly connected with the threaded rod.
The lens hood passes through threaded connection with the connecting piece, and it is stable to connect, and rotates the lens hood, drives the threaded rod and rotates at the screw hole internal rotation, realizes lens hood and connects the relative position between and adjusts.
The present invention also provides a preeclampsia prediction system for a eclampsia patient protection device, comprising:
a data acquisition module for acquiring clinical data of a sample;
the data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters;
the risk factor acquisition module is used for receiving the variable parameters, inputting the variable parameters into the analysis model and screening to obtain risk factors;
the prediction module is internally provided with a machine learning model, receives the risk factors and brings the risk factors into the machine learning model, establishes the prediction model, predicts the occurrence risk of an early stage of epilepsy by using the prediction model, and the output end of the prediction module is connected with the starting end of the image acquisition module.
The data acquisition module can acquire various clinical data of the sample, and the acquired data is utilized to perform subsequent prediction operation. The data processing module is used for preprocessing and statistically analyzing the data, primarily screening meaningful data, removing meaningless data, simplifying data types and facilitating the data operation of a subsequent prediction module. The risk factor acquisition module can further screen the preliminarily screened data, so that the predicted data type is more accurate, unnecessary calculation operation is avoided, and the running speed of the prediction module is increased. Whether the patient has preeclampsia is predicted by utilizing the risk factors, the operation is simple and convenient, and the timely judgment on whether the patient has preeclampsia is realized so as to treat the preeclampsia in time.
Further, the system also comprises a model evaluation module, wherein the model evaluation module is internally stored with quota evaluation parameters: the model evaluation module acquires corresponding data of the prediction model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value.
And evaluating each item of data of the prediction module by using the model evaluation module so as to judge the operational performance of the prediction module, so that the prediction module is optimized at a later period, and meanwhile, the reliability of the prediction module is judged.
The data processing system further comprises a data filling module, wherein the input end of the data filling module is connected with the output end of the data acquisition module, the data filling module performs interpolation on data with the loss rate of less than or equal to 30% by adopting a multiple interpolation method, and the output end of the data filling module is connected with the input end of the data processing module.
Data collection or storage failure caused by mechanical reasons or human reasons causes data loss, a loss value is generated, authenticity of the data cannot be guaranteed due to the loss value in the data, and therefore the data needs to be filled up, and reliability of the data is enhanced. And the data with too large missing rate has lower authenticity, does not have filling value and can be directly eliminated.
Further, the prediction model adopts a LightGBM model.
The LightGBM model has high operation speed and strong performance and is beneficial to use.
Further, the risk factors include specific gravity of urine, uric acid, hemoglobin concentration of red blood cells, globulin, distribution width of platelets, potassium ion, age at visit, family history of hypertension, systolic pressure, diastolic pressure, pulse and gestational period of not less than 34.
The relevance between the factors and whether the patient has preeclampsia is high, and the prediction module judges the preeclampsia more accurately only according to the risk factors.
Drawings
FIG. 1 is a schematic flow diagram of a preeclampsia prediction system of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
The invention discloses a protective device for an epileptic, which comprises an arc-shaped light shield, an image acquisition module and an early warning module.
One side of the light shield is detachably connected with the bed head or the chair back through a connecting piece, the light shield can swing and be positioned relative to the connecting piece, and the light shield is used for shielding the head light of a patient. One side of the light shield far away from the connecting piece is slightly inclined downwards and bent for a certain angle, so that light blocking is facilitated. The connecting piece is provided with a threaded hole, the threaded hole is in threaded connection with a threaded rod, and the side wall of the light shield is fixedly connected (such as welding, riveting and the like) with the threaded rod. The connecting piece can be connected with the bed head or the seat by adopting a screw structure, or connected with a sucker structure, etc.
The lens hood includes main cover plate, extension board and vice cover plate, is equipped with the standing groove on the main cover plate and the adjacent both sides face of connecting piece, and in the standing groove was arranged respectively in to the extension board, the standing groove was close to notch department and inlays and have magnet, is provided with the metal (like iron etc.) that attracts mutually with magnet on the extension board. When the magnetic adsorption type extension plate is used, the extension plate is pushed or drawn manually, the extension plate is controlled to slide along the placing groove, and when the extension plate moves to a required position, the extension plate is connected with the magnet at the groove opening of the placing groove in a magnetic adsorption mode, so that the extension plate is positioned. The auxiliary cover plate is of a folding fan structure, a sliding groove is formed in the center line, parallel to the upper surface of the main cover plate, of the side where the placing groove is located, the central shaft of the folding fan structure is in sliding connection with the sliding groove, and when no external force is applied, static friction exists between the central shaft and the side wall of the sliding groove. When the size of the light shield needs to be adjusted, the central shaft of the auxiliary shield plate is manually controlled to slide in the sliding groove, and when the central shaft slides to a required position, the auxiliary shield plate is positioned by utilizing the static friction force of the central shaft and the sliding groove. The auxiliary cover plate is arranged into a folding fan structure, and the unfolding degree of the folding fan structure can be controlled according to needs, so that the size of the auxiliary cover plate is adjusted.
The image acquisition module is installed on the outer wall and the inside wall of lens hood for gather patient's whole body image and head image, the camera that can gather the image at night is chooseed for use to the image acquisition module. The input end of the early warning module is electrically connected with the output end of the image acquisition module, the body state image characteristics of a patient with eclampsia are stored in the early warning module, the early warning module compares the acquired image with the stored body state image characteristics, and the similarity of the comparison is obtained through analysis. The early warning module can judge whether to output an early warning signal according to the numerical value of the similarity, the early warning signal is preferably a sound signal and/or a character prompt signal, and the like, and the early warning signal output end of the early warning module is arranged at the installation position of the light shield and/or on a remote terminal.
In a preferred scheme of the invention, a piston cylinder is arranged on the inner side of the light shield, one end of the piston cylinder is fixedly arranged on the inner side wall of the light shield, and the other end of the piston cylinder faces one side surface of a patient in the light shield. The piston plate is connected with a control mechanism for controlling the piston plate to move back and forth along the piston cylinder, and the control end of the control mechanism is electrically connected with the output end of the early warning module. When the early warning module outputs an early warning signal, the control mechanism is started to drive the piston plate to move.
One side fixed connection (such as welding, bonding etc.) that the lens hood was kept away from to the piston plate has the piston rod, and the piston rod stretches out and this end of piston rod is equipped with the gasbag from the piston cylinder towards human facial one side, surface one side and piston rod fixed connection of gasbag, and gasbag and piston cylinder are close to the facial one side intercommunication of human, are equipped with gas in the space of gasbag and piston cylinder intercommunication, and the gasbag is through thinner trachea and piston cylinder intercommunication. When the piston plate moves to one side of keeping away from the light shield, the piston plate moves to push gas in the piston cylinder to the air bag, the air bag expands, the piston rod pushes the head of the patient to one side through the air bag to be abutted against the face on one side of the human body, and the patient is prevented from vomitting and suffocation. When the piston plate resets, the space between the piston plate and one side of the piston cylinder facing the face is increased to form negative pressure, and the air in the air bag is sucked into the piston cylinder through the negative pressure, so that the air bag gradually shrinks and resets.
The control mechanism comprises a motor and a U-shaped rack, the motor is fixedly installed on the shading cover, an incomplete gear is fixedly connected to an output shaft of the motor, and the incomplete gear is coaxially connected with the output shaft of the motor. The U-shaped rack is meshed with the incomplete gear, a support for placing is welded on the shading cover, and the U-shaped rack is placed on the support for positioning. The end part of the U-shaped rack is fixedly connected with one side of the piston plate close to the light shield, and the U-shaped rack is perpendicular to the piston plate. The motor rotates to drive the incomplete gear to rotate, so that the U-shaped rack is controlled to do reciprocating linear motion. Still install the ventilating fan on the output shaft of motor, have certain clearance between ventilating fan and the U-shaped rack, each other do not influence each other.
As shown in fig. 1, the present invention further provides a preeclampsia prediction system for a eclampsia patient protection device, which includes a data acquisition module, a data processing module, a risk factor acquisition module, and a prediction module.
The data acquisition module is used for acquiring clinical data of a sample, and the clinical data comprises: general data of the patient, such as age, family history of hypertension, family history of diabetes, etc.; physical sign data, such as systolic pressure, diastolic pressure, pregnancy status, etc.; laboratory data such as blood routine, liver function, kidney function, electrolytes, blood coagulation function index, etc.
The data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters. And (4) expressing data which obey normal distribution in the metering data of the clinical index parameters by adopting X +/-S, and carrying out t test. the t-test is also called Student's t test and is mainly used for the sample with small content (such as n)<30) The overall standard deviation σ is an unknown normal distribution. Median and interquartile M (Q) for data not normally distributed in measurement data of clinical index parameters25～Q75) The Mann-Whitney U test (man-Whitney rank sum test), which is one of the nonparametric tests, assumes that the two samples are respectively from two populations that are identical except for the mean of the populations, in order to test whether the mean of the two populations differs significantly, is indicated and used.
The measurement data in the data processing module is expressed by a rate (%), and the comparison between groups adopts a chi value2Inspection, χ2The test is also called chi-square test, and is a hypothesis test method, and the basic formula of the test is as follows:
a is an actual number, T is a theoretical number deduced according to a test hypothesis, and the obtained characteristic parameters are shown in Table 1. The measurement data is data of blood pressure, height and the like, and the data can be directly used for measuring the size. The counting data is data such as gender and whether hypertension exists, and is used for measuring the number of the data. The measurement data is data of blood pressure, height and the like, and the data can be directly used for measuring the size. The counting data is data such as gender and whether hypertension exists, and is used for measuring the number of the data. The data processing module acquires 35 indexes of glutamyltransferase, glutamic-pyruvic transaminase, thrombin time and the like, which have statistical difference (P < 0.05), wherein the indexes are shown in Table 1.
TABLE 1 analysis results of data processing modules
The input end of the risk factor acquisition module is electrically connected with the output end of the data processing module, and the risk factor acquisition module is used for receiving the variable parameters, inputting the variable parameters into the analysis model and screening to obtain the risk factors. The risk factors include. The analysis model is preferably a binary Logistic regression analysis model, and Logistic regression analysis (α) is performed using whether preeclampsia occurs as a dependent variable (1, 0 or not)Into＝0.05，αGo out0.10), the results show that the urine specific gravity, the uric acid, the erythrocyte hemoglobin concentration, the globulin, the distribution width of the blood platelets, the potassium ions, the visit age, the family history of hypertension, the systolic pressure, the diastolic pressure, the pulse and the gestational period are more than or equal to 34, and the 12 parameter indexes are eclampsiaThe risk factors predicted in the early stage are shown in table 2.
TABLE 2 analysis results of the Risk factors obtaining Module
| Index (I) | B | SE | OR | 95％CI | P |
| Specific gravity of urine | 43.036 | 17.973 | 4.89921E+18 | 2463.308～9.74E+33 | 0.017 |
| Uric acid | 0.008 | 0.001 | 1.008 | 1.005～1.011 | <0.001 |
| Hemoglobin concentration of erythrocytes | 0.016 | 0.007 | 1.016 | 1.003～1.029 | 0.019 |
| Globulin protein | -0.11 | 0.025 | 0.896 | 0.853～0.941 | <0.001 |
| Breadth of platelet distribution | 0.116 | 0.044 | 1.123 | 1.03～1.225 | 0.009 |
| Potassium salt | 1.144 | 0.385 | 3.139 | 1.477～6.67 | 0.003 |
| Age of doctor | 0.064 | 0.026 | 1.066 | 1.012～1.123 | 0.016 |
| Family history of hypertension | 0.852 | 0.459 | 2.343 | 1.159～1.218 | 0.063 |
| Systolic pressure | 0.172 | 0.013 | 1.188 | 1.159～1.218 | <0.001 |
| Diastolic blood pressure | 0.006 | 0.003 | 1.006 | 1.001～1.011 | 0.019 |
| Pulse rate | 0.027 | 0.012 | 1.027 | 1.004～1.051 | 0.021 |
| Gestational period is more than or equal to 34 | -1.738 | 0.441 | 0.176 | 0.074～0.417 | <0.001 |
The prediction module is internally provided with a machine learning model, receives the risk factors and brings the risk factors into the machine learning model, establishes a prediction model, takes the risk factors as input parameters of the model, takes whether the pregnant woman has preeclampsia as an outcome variable, carries out model training, predicts the risk of the preeclampsia by using the prediction model, and the output end of the prediction module is electrically connected with the starting end of the image acquisition module. The LightGBM model is preferably used as the prediction model, the LightGBM model is a gradient lifting algorithm framework based on a decision tree algorithm, Taylor expansion of a loss function is used in the model, the model is closer to the loss function, convergence is faster, and a regular term is added in the loss function, so that the complexity of the model can be effectively controlled, and overfitting of the model is prevented.
Prediction value of prediction model
Predicted values obtained for t-1 trained models
Adding the predicted value f of the weak classifier trained for the t timet(xi),xiIs a vector.
fk(xi) For sample x in kth treeiK is the total number of the tree; the complexity of the tree is represented by the number T of leaf nodes of the tree and the output result omega of the leaf nodes of each treejSum of squares (equivalent to L2 regularization):
where γ and λ are parameters that need to be manually adjusted, ωjIs a leaf node value;
the loss function is calculated as follows:
wherein l represents the difference between the predicted value and the true value, Ω represents the regularization term of the tree, N represents the number of the feature vectors, and t represents the number of iterations. The extreme points of the minimization loss function are independent of the constants and can be rounded off.
Compared with the traditional mode that the splitting threshold is searched again in the characteristic pre-sorting of GBDT and XGBoost, the LightGBM adopts the characteristic bucket reconstruction histogram to perform splitting calculation, and the formula is as follows:
meanwhile, the LightGBM uses a leaf-wise growth level-wise algorithm with depth limitation, and abandons a layer-wise growth level-wise algorithm used by the XGboost, so that the leaf-wise can reduce more errors and obtain better precision under the same splitting times. The range of the output value of the LightGBM model is [0,1], if the output value is less than or equal to 0.5, the prediction type is IVIG reaction, and if the output value is more than 0.5, the probable IVIG resistance is predicted.
In a preferred embodiment of the present invention, the prediction system further includes a model evaluation module, and the model evaluation module stores a quota evaluation parameter: the model evaluation module collects corresponding data of the prediction model, compares the collected data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value. The model evaluation module evaluates the model by adopting a Holdout verification method, and samples are evaluated according to the following steps of 7: and 3, randomly dividing the training set into a training set and a testing set, wherein the training set is used for training the model, and the testing set verifies the generalization capability of the model.
In a preferred mode of the invention, the prediction system further comprises a data filling module, wherein the input end of the data filling module is connected with the output end of the data acquisition module, the data filling module performs interpolation on the data with the loss rate less than or equal to 30% by adopting a multiple interpolation method, and the output end of the data filling module is connected with the input end of the data processing module.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A protective device for epilepsy patients is characterized by comprising an arc-shaped light shield, an image acquisition module and an early warning module;
one side of the light shield is detachably connected with the bed head or the chair back through a connecting piece, the light shield can swing and be positioned relative to the connecting piece, and the light shield is used for shielding the head light of a patient;
the image acquisition module is arranged on the shading cover and is used for acquiring a whole body image and a head image of a patient;
the input end of the early warning module is connected with the output end of the image acquisition module, the body state image characteristics of a patient with eclampsia are stored in the early warning module, the early warning module compares the acquired image with the stored body state image characteristics, the similarity of the comparison is obtained through analysis, whether an early warning signal is output or not is judged according to the similarity, and the early warning signal output end of the early warning module is arranged at the installation position of the light shield and/or on a remote terminal.
2. The eclamptic patient protection device of claim 1, wherein a piston cylinder is provided inside the light shield, one end of the piston cylinder being fixedly mounted to an inside wall of the light shield and the other end facing a side of the patient within the light shield;
the piston plate is connected with a control mechanism which controls the piston plate to move back and forth along the piston cylinder, and the control end of the control mechanism is connected with the output end of the early warning module;
the side of the piston plate far away from the light shield is fixedly connected with a piston rod, the piston rod extends out from one side of the piston cylinder towards the human face, an air bag is arranged at the end part of the piston rod, the air bag is communicated with one side of the piston cylinder close to the human face, and air is arranged in a space communicated with the piston cylinder.
3. The eclamptic patient protection device of claim 2, wherein the control mechanism comprises a motor and a U-shaped rack, the motor is fixedly mounted on the light shield, an incomplete gear is fixedly connected to an output shaft of the motor, the U-shaped rack is engaged with the incomplete gear, an end of the U-shaped rack is fixedly connected to one side of the piston plate close to the light shield, the U-shaped rack is perpendicular to the piston plate, and a ventilation fan is further mounted on the output shaft of the motor.
4. The eclamptic patient protection device of claim 1, wherein the light shield comprises a primary mask, an extension panel, and a secondary mask;
two side faces of the main cover plate adjacent to the connecting piece are provided with placing grooves, the extending plates are respectively placed in the placing grooves, magnets are embedded in the positions, close to the notches, of the placing grooves, and metal attracted with the magnets is arranged on the extending plates;
the auxiliary cover plate is of a folding fan structure, a sliding groove is formed in the center line, parallel to the upper surface of the main cover plate, of the side where the placing groove is located, the central shaft of the folding fan structure is in sliding connection with the sliding groove, and when no external force is applied, static friction exists between the central shaft and the side wall of the sliding groove.
5. The eclamptic patient protection device of claim 1, wherein the connector has a threaded bore, the threaded bore having a threaded rod threadedly connected thereto, the side wall of the light shield being fixedly connected to the threaded rod.
6. A preeclampsia prediction system for use in the eclamptic patient protection device of any one of claims 1-5, comprising:
a data acquisition module for acquiring clinical data of a sample;
the data processing module is used for receiving the data information acquired by the data acquisition module, performing statistical analysis on the data information and acquiring variable parameters;
the risk factor acquisition module is used for receiving the variable parameters, inputting the variable parameters into the analysis model and screening to obtain risk factors;
the prediction module is internally provided with a machine learning model, receives the risk factors and brings the risk factors into the machine learning model, establishes the prediction model, predicts the occurrence risk of an early stage of epilepsy by using the prediction model, and the output end of the prediction module is connected with the starting end of the image acquisition module.
7. The preeclampsia prediction system of claim 6, further comprising a model evaluation module having credit evaluation parameters stored therein: the model evaluation module acquires corresponding data of the prediction model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the prediction model according to the comparison difference value.
8. The preeclampsia prediction system of claim 6, further comprising a data padding module, wherein an input end of the data padding module is connected to an output end of the data acquisition module, the data padding module performs interpolation on data with a loss rate of less than or equal to 30% by using a multiple interpolation method, and an output end of the data padding module is connected to an input end of the data processing module.
9. The preeclampsia prediction system of claim 6, wherein the prediction model employs a LightGBM model.
10. The preeclampsia prediction system of claim 6, wherein the risk factors comprise specific gravity of urine, uric acid, erythrocyte hemoglobin concentration, globulin, platelet distribution width, potassium ions, age of visit, family history of hypertension, systolic pressure, diastolic pressure, pulse, and peripregnancy ≧ 34.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110748361.4A CN113421641B (en) | 2021-06-30 | 2021-06-30 | Eclampsia patient protection device and prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110748361.4A CN113421641B (en) | 2021-06-30 | 2021-06-30 | Eclampsia patient protection device and prediction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113421641A true CN113421641A (en) | 2021-09-21 |
| CN113421641B CN113421641B (en) | 2023-01-10 |
Family
ID=77720039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110748361.4A Active CN113421641B (en) | 2021-06-30 | 2021-06-30 | Eclampsia patient protection device and prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421641B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113995587A (en) * | 2021-10-27 | 2022-02-01 | 重庆医科大学 | Acute myocardial infarction intervention postoperative care device and risk prediction system |
| CN114681249A (en) * | 2022-04-26 | 2022-07-01 | 重庆医科大学 | Multifunctional detection nursing bed and danger prediction system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN107432802A (en) * | 2017-09-06 | 2017-12-05 | 葛荣华 | A kind of multi-functional patients head position adjustment vomitus collects anti-suffocation device |
| CN107495971A (en) * | 2017-07-27 | 2017-12-22 | 大连和创懒人科技有限公司 | Morbidity's alarm medical system and its detection method based on skeleton identification |
| CN109745004A (en) * | 2019-01-18 | 2019-05-14 | 北京小成素问信息技术有限公司 | Lingual diagnosis mirror and lingual diagnosis system |
| CN211244776U (en) * | 2019-06-12 | 2020-08-14 | 张青 | First-aid sputum suction mask for medical doctor |
| CN211299186U (en) * | 2019-11-18 | 2020-08-21 | 王晨晨 | Sleep light chopper |
| CN112582068A (en) * | 2020-12-31 | 2021-03-30 | 山东省妇幼保健院 | Safety device for gestational eclampsia symptoms |
| CN213190543U (en) * | 2020-06-05 | 2021-05-14 | 上海市第一妇婴保健院 | Eye-mask special for epilepsy patient |
| CN112835316A (en) * | 2021-01-06 | 2021-05-25 | 重庆医科大学 | Neonatal sepsis shock prediction system and monitoring equipment |
| CN213525551U (en) * | 2020-10-14 | 2021-06-25 | 南阳医学高等专科学校第一附属医院 | Unobstructed auxiliary device of shock patient's respiratory track |
-
2021
- 2021-06-30 CN CN202110748361.4A patent/CN113421641B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN107495971A (en) * | 2017-07-27 | 2017-12-22 | 大连和创懒人科技有限公司 | Morbidity's alarm medical system and its detection method based on skeleton identification |
| CN107432802A (en) * | 2017-09-06 | 2017-12-05 | 葛荣华 | A kind of multi-functional patients head position adjustment vomitus collects anti-suffocation device |
| CN109745004A (en) * | 2019-01-18 | 2019-05-14 | 北京小成素问信息技术有限公司 | Lingual diagnosis mirror and lingual diagnosis system |
| CN211244776U (en) * | 2019-06-12 | 2020-08-14 | 张青 | First-aid sputum suction mask for medical doctor |
| CN211299186U (en) * | 2019-11-18 | 2020-08-21 | 王晨晨 | Sleep light chopper |
| CN213190543U (en) * | 2020-06-05 | 2021-05-14 | 上海市第一妇婴保健院 | Eye-mask special for epilepsy patient |
| CN213525551U (en) * | 2020-10-14 | 2021-06-25 | 南阳医学高等专科学校第一附属医院 | Unobstructed auxiliary device of shock patient's respiratory track |
| CN112582068A (en) * | 2020-12-31 | 2021-03-30 | 山东省妇幼保健院 | Safety device for gestational eclampsia symptoms |
| CN112835316A (en) * | 2021-01-06 | 2021-05-25 | 重庆医科大学 | Neonatal sepsis shock prediction system and monitoring equipment |
Non-Patent Citations (2)
| Title |
|---|
| 张颜: "子痫前期患者剖宫产术后静脉血栓的高危因素及预防措施探讨", 《人人健康》 * |
| 贾慧芳: "新生儿中重度缺血缺氧性脑病的护理体会", 《当代护士(下旬刊)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113995587A (en) * | 2021-10-27 | 2022-02-01 | 重庆医科大学 | Acute myocardial infarction intervention postoperative care device and risk prediction system |
| CN114681249A (en) * | 2022-04-26 | 2022-07-01 | 重庆医科大学 | Multifunctional detection nursing bed and danger prediction system |
| CN114681249B (en) * | 2022-04-26 | 2024-02-13 | 重庆医科大学 | Multifunctional detection nursing bed and danger prediction system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113421641B (en) | 2023-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113421641B (en) | Eclampsia patient protection device and prediction system | |
| CN110827993A (en) | Early death risk assessment model establishing method and device based on ensemble learning | |
| JP6522059B2 (en) | Erythrocyte dynamics for diagnosis | |
| Furr et al. | Development of a colic severity score for predicting the outcome of equine colic | |
| Piper et al. | Delayed appearance of pulmonary maturation markers is associated with poor glucose control in diabetic pregnancies | |
| CN111513726B (en) | System for evaluating AMS risk based on IHT dynamic performance | |
| CN111989752A (en) | Test panel for detecting sepsis | |
| CN114023441A (en) | Severe AKI early risk assessment model and device based on interpretable machine learning model and development method thereof | |
| CN114373544A (en) | Method, system and device for predicting membranous nephropathy based on machine learning | |
| CN112835316B (en) | Neonatal sepsis shock prediction system and monitoring equipment | |
| CN113209402A (en) | Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis | |
| CN105496412B (en) | A kind of expiration inflammation monitoring method and device | |
| CN112768057B (en) | System for identifying child fever cause to be checked | |
| King et al. | A model for prediction of survival in critically III dogs | |
| CN110841152A (en) | Heatable pressure device for blood transfusion of hematology department | |
| CN113409939A (en) | Prediction system and monitoring device for COPD acute exacerbation concurrent respiratory failure | |
| US20220293210A1 (en) | Single-cell modeling of clinical data to determine red blood cell regulation | |
| Azeez et al. | Effect of heat stress on vital and hematobiochemical parameters of healthy dogs | |
| CN113380329A (en) | Prediction system and device for resistance of first injection gamma globulin of Kawasaki disease patient child | |
| Umut et al. | Prediction of sepsis disease by Artificial Neural Networks | |
| CN113456501A (en) | Monitoring and drug administration device and prediction system for essential hypertension | |
| CN115346666A (en) | System and method for quickly detecting human health indexes | |
| CN111292852A (en) | Encephalitis and meningitis intelligent auxiliary diagnosis system based on random forest algorithm | |
| KR102543914B1 (en) | Alzheimer's disease risk prediction device including artificial intelligence model | |
| Mignucci-Giannoni et al. | Blood reference intervals for Antillean manatees (Trichechus manatus manatus) from Puerto Rico |
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 |