CN112992343A - Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients - Google Patents

Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients Download PDF

Info

Publication number
CN112992343A
CN112992343A CN202110259806.2A CN202110259806A CN112992343A CN 112992343 A CN112992343 A CN 112992343A CN 202110259806 A CN202110259806 A CN 202110259806A CN 112992343 A CN112992343 A CN 112992343A
Authority
CN
China
Prior art keywords
module
auxiliary diagnosis
comparator
model
heart disease
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.)
Pending
Application number
CN202110259806.2A
Other languages
Chinese (zh)
Inventor
向天雨
黄浩东
刘小株
段敏捷
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.)
Chongqing Medical University
Original Assignee
Chongqing Medical University
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 Chongqing Medical University filed Critical Chongqing Medical University
Priority to CN202110259806.2A priority Critical patent/CN112992343A/en
Publication of CN112992343A publication Critical patent/CN112992343A/en
Pending legal-status Critical Current

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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
    • 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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention belongs to the technical field of medical equipment, and particularly discloses an auxiliary diagnosis system for coronary heart disease of a type 2 diabetic patient, which comprises a data acquisition module, a data screening module and an auxiliary diagnosis module, wherein the data acquisition module is used for acquiring index data related to coronary heart disease morbidity of a sample, the data screening module is used for receiving the index data acquired by the data acquisition module, processing, counting and analyzing the index data, and screening auxiliary diagnosis parameters, an auxiliary diagnosis model is built in the auxiliary diagnosis module and is used for receiving the auxiliary diagnosis parameters, analyzing the auxiliary diagnosis parameters and assisting in diagnosing the coronary heart disease of the patient. By adopting the technical scheme, the auxiliary diagnosis of the coronary heart disease of the patient is realized through the cooperation of all modules, and the diagnosis result is obtained.

Description

Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients
Technical Field
The invention belongs to the technical field of medical equipment, and relates to an auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients.
Background
With the aging of the population and the change of life style in China, diabetes mellitus is changed into epidemic disease from rare lesion, and the prevalence rate of type 2 diabetes mellitus is dramatically increased from 0.67% in 1980 to 10.4% in 2013. Type 2 diabetes is a major risk factor for the development of microvascular and macrovascular complications, and type 2 diabetics are at a 2-4 fold higher risk of developing cardiovascular disease than non-type 2 diabetics. Coronary heart disease is one of the most prominent and serious complications. 75% of patients with type 2 diabetes die from cardiovascular disease, of which about 75% die from coronary heart disease.
The early disease of coronary heart disease patients can not cause abnormal change of electrocardiogram, only when the coronary artery occlusion rate is more than 70 percent, the ECG (electrocardiogram) can be caused to have obvious change, so that the early diagnosis can not be realized, the patients can not timely master the physical function conditions of the patients, and the detection equipment can only detect one patient at a time, has more complex operation and is not beneficial to large-scale screening of patients suffering from coronary heart disease.
Disclosure of Invention
The invention aims to provide an auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients, which realizes auxiliary diagnosis of coronary heart disease of patients, is simple to operate and is beneficial to large-scale screening.
In order to achieve the purpose, the basic scheme of the invention is as follows: an auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients comprises a data acquisition module, a data screening module and an auxiliary diagnosis module;
the data acquisition module is used for acquiring coronary heart disease morbidity related index data of a sample;
the data screening module is used for receiving the index data acquired by the data acquisition module, processing, counting and analyzing the index data and screening out auxiliary diagnosis parameters;
an auxiliary diagnosis model is constructed in the auxiliary diagnosis module and used for receiving the auxiliary diagnosis parameters and analyzing the auxiliary diagnosis parameters to assist in diagnosing the coronary heart disease of the patient.
The working principle and the beneficial effects of the basic scheme are as follows: the data acquisition module can acquire various index data of the sample and utilize the index data to carry out subsequent auxiliary diagnosis. The data screening module processes the data, screens meaningful data, removes meaningless data, simplifies data types, avoids meaningless calculation operation, accelerates the running speed of the identification module, and is beneficial to subsequent auxiliary diagnosis. The auxiliary diagnosis parameters are utilized to diagnose whether the coronary heart disease is suffered or not, the operation is simple and convenient, and the coronary heart disease can be judged in time so as to be treated in time.
When the diagnosis device is used, the diagnosis result output by the auxiliary diagnosis module can be obtained only by inputting required index data into the data acquisition module, other operations are not needed, the use is convenient, and the diagnosis device is beneficial to screening patients suffering from coronary heart disease on a large scale.
Further, the auxiliary diagnosis module optimizes an XGboost model based on a Bayesian algorithm, a decision tree adopted by the XGboost model is a CART regression tree, 70% of the obtained auxiliary diagnosis parameters are set as a training set, 30% of the obtained auxiliary diagnosis parameters are set as a test set, the training set is input into the XGboost model, an initial learner model is established, the initial learner model is subjected to regularized pruning by utilizing a plurality of decision tree cycle calculations to obtain a strong learner model, and whether the coronary heart disease is suffered or not is taken as an output result of the strong learner.
The XGboost module is high in prediction accuracy, can process various types of data and is beneficial to use. And a training set and a testing set in a proper proportion are set, and a better XGboost model is constructed.
Further, the system also comprises a model evaluation module, wherein evaluation indexes are stored in the model evaluation module: the accuracy, the precision, the recall rate, the F1 score and the rated value range of AUC are obtained, the test set is input into the strong learner model, the model evaluation module collects evaluation indexes of the strong learner model, the model evaluation module compares the collected evaluation index values with the rated value range, the size of the evaluation index values is judged, and the distinguishing capability, the prediction capability and the stability of the auxiliary diagnosis module are analyzed.
And evaluating various data of the auxiliary diagnosis module by using the model evaluation module so as to judge the operational performance of the auxiliary diagnosis module, so that the auxiliary diagnosis module is optimized at a later stage, and the reliability of the auxiliary diagnosis module is judged at the same time.
Further, the auxiliary diagnostic parameters include fibrinogen, creatinine, apolipoprotein AIApolipoprotein B, lipoprotein a, glycated hemoglobin, and urinary glucose.
The correlation between the auxiliary diagnosis parameters and the coronary heart disease is relatively high, and the auxiliary diagnosis module judges whether the patient suffers from the coronary heart disease or not only according to the parameters, so that the judgment accuracy is higher.
Further, after Bayesian optimization, the parameters of the XGboost-based auxiliary diagnosis model are as follows: learning _ rate is 0.14, N _ estimators is 574, Max _ depth is 2, Min _ child _ weight is 7, gamma is 0.001, and subsample is 0.93.
According to the established XGboost classification model, the diagnosis of the coronary heart disease can be realized.
The system further comprises an alarm module, wherein the starting end of the alarm module is connected with the output end of the auxiliary diagnosis module, the danger classification module comprises a first comparator and a second comparator, and the number of the first comparator and the second comparator is equal to that of auxiliary diagnosis parameters;
the first input end of the first comparator is connected with a first threshold memory, the first comparator is connected with the output ends of various auxiliary diagnostic parameters of the data screening module one by one, and the first output end of the first comparator is connected with a first-level early warning device;
the first input end of the second comparator is connected with a second threshold value memory, the second input end of the second comparator is connected with the second output end of the corresponding first comparator, the first comparator can transmit the auxiliary diagnosis parameters to the second comparator, the rated value in the first threshold value memory for storing the same kind of parameters is smaller than the rated value in the second threshold value memory, the output end of the second comparator is connected with a second-stage early warning device, and the output end of the second comparator is connected with a third-stage early warning device through a NOT gate.
And when the diagnosis result output by the auxiliary diagnosis module is that the coronary heart disease is confirmed, the alarm module is started. The first comparator and the second comparator are combined, the numerical values of the auxiliary diagnosis parameters are compared with the numerical values under normal conditions or different pathological changes, the danger levels of the auxiliary diagnosis parameters are judged, corresponding early warning is carried out, and more accurate early warning information can be known by doctors and patients, so that timely treatment can be carried out.
Further, the primary early warning device, the secondary early warning device and the tertiary early warning device adopt LED lamps displaying different colors or buzzers sounding for different times.
The buzzer and the LED lamp are convenient to use, low in manufacturing cost and beneficial to obtaining.
The system further comprises a preventive measure display terminal, a display port of the preventive measure display terminal is correspondingly connected with the first comparator and the second comparator through a wireless communication module or a wired communication module, and a three-level display state is arranged in the preventive measure display terminal;
the preventive measures displayed in the first-stage display state are used for controlling eating habits and living habits, and the preventive measures displayed in the second-stage display state are used for treating medicines, intervening treatment and controlling eating;
the preventive measures of the three-level display state display are doctor-feeding detection and myocardial remodeling.
And a preventive measure display terminal is arranged to display corresponding preventive measures according to the early warning grades of different parameters, so that the method has pertinence and is more beneficial to the examination of doctors and patients.
The invention also provides an auxiliary operation design system based on the coronary heart disease auxiliary diagnosis system, which comprises a manual review module and a coronary angiography module;
the control end of the manual review module is connected with the output end of the auxiliary diagnosis system, and the manual review module is started to remind medical personnel to feed back a diagnosis result;
the coronary angiography module is connected with a storage library for storing coronary artery image information with different pathological changes, the coronary angiography module is used for collecting the image information of the coronary artery of the sample, comparing the collected image information with the coronary artery image information in the storage library and judging the pathological change degree of the coronary artery, and the output end of the coronary angiography module is connected with the manual review module.
The manual review module receives the information output by the auxiliary diagnosis system and the coronary angiography module, and the doctor confirms and feeds back the information, so that the reliability of the diagnosis result is higher.
The invention also provides an auxiliary operation operating system based on the auxiliary operation design system, which comprises a modeling module and a sensing module, wherein the modeling module is used for acquiring CT image data of a patient, the modeling module is connected with the image output end of the coronary angiography module, a three-dimensional model is established by combining the CT image data and the coronary angiography image information, and the three-dimensional model is input into a 3D printer to acquire an entity model;
the perception module comprises a perception sensor and a signal reflector, the perception sensor is arranged on an important organ, an operation opening and a support mounting position of the solid model, the perception sensor detects whether the operation of a doctor is proper or not and transmits a perception signal to the signal reflector, and the signal reflector sends out a signal to reflect the operation condition.
The modeling module establishes a three-dimensional model, which is helpful for doctors to more specifically know the internal condition of patients, and meanwhile, the three-dimensional model is repeatedly analyzed to confirm the operation position, which is more beneficial for the operation of the procedure. And printing the solid model according to the three-dimensional model, and after the doctor is familiar with the operation on the three-dimensional model, performing actual operation simulation on the solid model to help improve the accuracy of the operation.
Drawings
Fig. 1 is a flow chart of an auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients according to 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.
As shown in figure 1, the invention discloses an auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients, which comprises a data acquisition module, a data screening module and an auxiliary diagnosis module.
The data acquisition module is used for acquiring coronary heart disease incidence related index data of a sample, wherein the coronary heart disease incidence related index data comprises D-dimer, fibrinogen, blood creatinine, urea, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, apolipoprotein AI, apolipoprotein B, lipoprotein a, total bilirubin, direct bilirubin, indirect bilirubin, urine glucose and glycosylated hemoglobin, and data after blood drawing inspection and analysis can be adopted.
The data screening module is used for receiving the index data acquired by the data acquisition module, processing and carrying out statistical analysis on the index data, carrying out statistical analysis by adopting R3.6.1 and Python3.7.0, gradually carrying out forward Logistic regression on screening variables, wherein the gradual forward Logistic regression result is shown in table 1, in the table 1, SE represents standard error, B represents regression coefficient, R represents goodness-of-fit index, and P represents: p>1 is a risk factor, P<1 protective factor, P ═ 1 this factor does not work. The auxiliary diagnosis parameters include fibrinogen, creatinine and apolipoprotein AIApolipoprotein B, lipoprotein a, glycated hemoglobin, and urinary glucose.
TABLE 1 stepwise Forward Logistic regression results
Item B SE Z P
Intercept -3.770 1.07 -3.52 ＜0.001
Fibrinogen 0.285 0.12 2.26 0.024
Creatinine 0.021 0.01 3.24 0.001
Apolipoprotein AI -1.478 0.45 -3.29 ＜0.001
Apolipoprotein B 1.861 0.85 2.20 0.028
Lipoprotein a 0.002 ＜0.01 3.83 ＜0.001
Glycated hemoglobin 0.276 0.09 3.08 0.002
Urine glucose 0.661 0.25 2.66 0.007
D-dimers 0.791 0.42 1.88 0.060
Urea 0.070 0.06 1.09 0.275
Total gallbladder fixing deviceAlcohol(s) 0.118 0.251 0.47 0.638
Low density lipoprotein cholesterol -0.516 0.29 -1.75 0.080
High density lipoprotein cholesterol 0.122 0.49 0.25 0.805
Total bilirubin -0.023 0.05 -0.467 0.640
Direct bilirubin -0.088 0.09 -0.96 0.336
Indirect bilirubin 0.276 0.06 0.55 0.581
An auxiliary diagnosis model is constructed in the auxiliary diagnosis module and used for receiving the auxiliary diagnosis parameters and analyzing the auxiliary diagnosis parameters to assist in diagnosing the coronary heart disease of the patient.
In the present embodiment, the diagnostic support equation using logistic regression is: logit (p) ═ 3.545+0.231 × fibrinogen (g/L) +0.024 × blood creatinine (μmol/L) -1.524 × apolipoprotein aI(g/L) +1.005 Xapolipoprotein B (g/L) +0.002 Xlipoprotein a (mg/L) +0.303 Xglycated hemoglobin (%) +0.671 Xurine glucose.
In another preferred embodiment of the invention, the auxiliary diagnosis module is based on an XGBoost model optimized by a bayesian GBDT algorithm, and sets 70% of the acquired auxiliary diagnosis parameters as a training set and 30% as a test set, inputs the training set into the XGBoost model, establishes an initial learner model, performs regularized pruning on the initial learner model by using a plurality of decision tree loop calculations, obtains a strong learner model, and takes whether the coronary heart disease is suffered as an output result of the strong learner.
The parameters of the auxiliary diagnosis model based on XGboost after Bayesian optimization are as follows: learning _ rate is 0.14, N _ estimators is 574, Max _ depth is 2, Min _ child _ weight is 7, gamma is 0.001, and subsample is 0.93. The XGboost aided diagnosis model parameters are as shown in Table 2:
TABLE 2 XGboost aided diagnosis model parameter table
Figure BDA0002969387840000081
In a preferred mode of the invention, the coronary heart disease auxiliary diagnosis system further comprises a model evaluation module. The model evaluation module stores evaluation indexes: the accuracy, precision, recall rate, F1 score and the rated value range of AUC are input into the strong learner model, and the model evaluation module acquires evaluation indexes of the strong learner model. A comparator is arranged in the optimization model evaluation module, the model evaluation module compares the acquired evaluation index value with a rated value range, judges the size of the evaluation index value, and analyzes the distinguishing capability, the predicting capability and the stability of the auxiliary diagnosis module.
In a preferred mode of the present invention, the coronary heart disease auxiliary diagnosis system further includes an alarm module, the starting end of the alarm module is connected to the output end of the auxiliary diagnosis module, the risk classification module includes a first comparator and a second comparator, and the number of the first comparator and the second comparator is equal to the number of the auxiliary diagnosis parameters. The first input end of the first comparator is electrically connected with a first threshold memory, the first comparator is electrically connected with various auxiliary diagnosis parameter output ends of the data screening module one by one, and the first output end of the first comparator is electrically connected with a first-level early warning device.
The first input end of a second comparator in the alarm module is electrically connected with a second threshold memory, the second input end of the second comparator is electrically connected with the second output end of the corresponding first comparator, the first comparator can transmit auxiliary diagnosis parameters to the second comparator, the rated value in the first threshold memory for storing the same kind of parameters is smaller than the rated value in the second threshold memory, the output end of the second comparator is connected with a second-stage early-warning device, and the output end of the second comparator is electrically connected with a third-stage early-warning device through a NOT gate. Preferably, the first-stage early warning device, the second-stage early warning device and the third-stage early warning device adopt LED lamps displaying different colors or buzzers sounding for different times.
In a preferred mode of the present invention, the coronary heart disease auxiliary diagnosis system further includes a preventive measure display terminal, a display port of the preventive measure display terminal is correspondingly connected to the first comparator and the second comparator through a wireless communication module or a wired communication module, and a three-level display state is provided in the preventive measure display terminal. The preventive measures of the first-level display state display are control of eating habits and living habits, the preventive measures of the second-level display state display are medication, intervention treatment and diet control, and the preventive measures of the third-level display state display are medical delivery detection and myocardial remodeling. The preventive measure display terminal can select mobile equipment such as a mobile phone and a notebook computer, and the wireless communication module can select transmission equipment such as WIFI and Bluetooth.
The invention also provides an auxiliary operation design system based on the coronary heart disease auxiliary diagnosis system, which comprises a manual review module and a coronary angiography module, wherein the control end of the manual review module is connected with the output end of the auxiliary diagnosis system, and the manual review module is started to remind medical personnel to feed back the diagnosis result. The coronary angiography module is connected with a storage library for storing coronary artery image information with different pathological changes, the coronary angiography module is used for collecting the image information of the coronary artery of the sample, comparing the collected image information with the coronary artery image information in the storage library and judging the pathological change degree of the coronary artery, and the output end of the coronary angiography module is electrically connected with the manual review module.
The invention also provides an auxiliary operation operating system based on the auxiliary operation design system, which comprises a modeling module and a sensing module, wherein the modeling module is used for acquiring CT image data of a patient, the modeling module is connected with the image output end of the coronary angiography module, a three-dimensional model is established by combining the CT image data and the coronary angiography image information, and the three-dimensional model is input into a 3D printer to acquire an entity model.
The perception module comprises a perception sensor and a signal reflector, the perception sensor is arranged on an important organ, an operation opening and a support mounting position of the solid model, the perception sensor detects whether the operation of a doctor is proper or not and transmits a perception signal to the signal reflector, and the signal reflector sends out a signal to reflect the operation condition. The perception sensor is preferably a touch sensor, an infrared sensor or the like, and the signal reflector is preferably a display screen, a signal lamp or the like.
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. An auxiliary diagnosis system for coronary heart disease of type 2 diabetes patients is characterized by comprising a data acquisition module, a data screening module and an auxiliary diagnosis module;
the data acquisition module is used for acquiring coronary heart disease morbidity related index data of a sample;
the data screening module is used for receiving the index data acquired by the data acquisition module, processing, counting and analyzing the index data and screening out auxiliary diagnosis parameters;
an auxiliary diagnosis model is constructed in the auxiliary diagnosis module and used for receiving the auxiliary diagnosis parameters and analyzing the auxiliary diagnosis parameters to assist in diagnosing the coronary heart disease of the patient.
2. The system of claim 1, wherein the auxiliary diagnosis module constructs an XGBoost model based on a bayesian algorithm, sets 70% of the acquired auxiliary diagnosis parameters as a training set and 30% as a test set, inputs the training set into the XGBoost model, establishes an initial learner model, performs regularized pruning on the initial learner model by using a plurality of decision tree loop calculations to obtain a strong learner model, and takes whether the patient suffers from coronary heart disease as an output result of the strong learner.
3. The system of claim 2, further comprising a model evaluation module, wherein the model evaluation module stores evaluation indexes: the accuracy, the precision, the recall rate, the F1 score and the rated value range of AUC are obtained, the test set is input into the strong learner model, the model evaluation module collects evaluation indexes of the strong learner model, the model evaluation module compares the collected evaluation index values with the rated value range, the size of the evaluation index values is judged, and the distinguishing capability, the prediction capability and the stability of the auxiliary diagnosis module are analyzed.
4. The system of claim 1, wherein the auxiliary diagnostic parameters comprise fibrinogen, creatinine and apolipoprotein aIApolipoprotein B, lipoprotein a, glycated hemoglobin, and urinary glucose.
5. The system of claim 2, wherein the XGBoost-based aided diagnosis model parameters after bayesian optimization are: learning _ rate is 0.14, N _ estimators is 574, Max _ depth is 2, Min _ child _ weight is 7, gamma is 0.001, and subsample is 0.93.
6. The system for assisting coronary heart disease diagnosis of type 2 diabetes mellitus patients according to claim 1, further comprising an alarm module, wherein the starting end of the alarm module is connected with the output end of the auxiliary diagnosis module, the risk classification module comprises a first comparator and a second comparator, and the number of the first comparator and the second comparator is equal to the number of the auxiliary diagnosis parameters;
the first input end of the first comparator is connected with a first threshold memory, the first comparator is connected with the output ends of various auxiliary diagnostic parameters of the data screening module one by one, and the first output end of the first comparator is connected with a first-level early warning device;
the first input end of the second comparator is connected with a second threshold value memory, the second input end of the second comparator is connected with the second output end of the corresponding first comparator, the first comparator can transmit the auxiliary diagnosis parameters to the second comparator, the rated value in the first threshold value memory for storing the same kind of parameters is smaller than the rated value in the second threshold value memory, the output end of the second comparator is connected with a second-stage early warning device, and the output end of the second comparator is connected with a third-stage early warning device through a NOT gate.
7. The system for auxiliary diagnosis of coronary heart disease of type 2 diabetes mellitus patient according to claim 6, wherein the first level early warning device, the second level early warning device and the third level early warning device use LED lamps displaying different colors or buzzers sounding different times.
8. The system of claim 6, further comprising a preventive measure display terminal, wherein a display port of the preventive measure display terminal is connected to the first comparator and the second comparator via a wireless communication module or a wired communication module, and a three-level display state is set in the preventive measure display terminal;
the preventive measures displayed in the first-stage display state are used for controlling eating habits and living habits, and the preventive measures displayed in the second-stage display state are used for treating medicines, intervening treatment and controlling eating;
the preventive measures of the three-level display state display are doctor-feeding detection and myocardial remodeling.
9. An aided surgery planning system based on the coronary heart disease aided diagnosis system of one of claims 1-8, which is characterized by comprising a manual review module and a coronary angiography module;
the control end of the manual review module is connected with the output end of the auxiliary diagnosis system, and the manual review module is started to remind medical personnel to feed back a diagnosis result;
the coronary angiography module is connected with a storage library for storing coronary artery image information with different pathological changes, the coronary angiography module is used for collecting the image information of the coronary artery of the sample, comparing the collected image information with the coronary artery image information in the storage library and judging the pathological change degree of the coronary artery, and the output end of the coronary angiography module is connected with the manual review module.
10. An assisted surgery operation system based on the assisted surgery design system of claim 9, which comprises a modeling module and a sensing module, wherein the modeling module is used for acquiring CT image data of a patient, the modeling module is connected with an image output end of a coronary angiography module, a three-dimensional model is established by combining the CT image data and the coronary angiography image information, and the three-dimensional model is input into a 3D printer to acquire a solid model;
the perception module comprises a perception sensor and a signal reflector, the perception sensor is arranged on an important organ, an operation opening and a support mounting position of the solid model, the perception sensor detects whether the operation of a doctor is proper or not and transmits a perception signal to the signal reflector, and the signal reflector sends out a signal to reflect the operation condition.
CN202110259806.2A 2021-03-10 2021-03-10 Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients Pending CN112992343A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110259806.2A CN112992343A (en) 2021-03-10 2021-03-10 Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110259806.2A CN112992343A (en) 2021-03-10 2021-03-10 Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients

Publications (1)

Publication Number Publication Date
CN112992343A true CN112992343A (en) 2021-06-18

Family

ID=76336312

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110259806.2A Pending CN112992343A (en) 2021-03-10 2021-03-10 Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients

Country Status (1)

Country Link
CN (1) CN112992343A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114974576A (en) * 2022-07-12 2022-08-30 曜立科技(北京)有限公司 Cardiovascular and cerebrovascular disease diagnosis and management system based on metadata
CN117292829A (en) * 2023-10-13 2023-12-26 黄恺 Graded diagnosis and treatment information system for coronary heart disease
US11966374B2 (en) 2022-07-12 2024-04-23 Serv Medical Pte. Ltd. Medical clinical data quality analysis system based on big data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110223772A (en) * 2019-06-10 2019-09-10 青岛大学附属医院 A kind for the treatment of endocrine diseases diagnostic device and data information processing method
CN112117006A (en) * 2020-09-23 2020-12-22 重庆医科大学 Type 2 diabetes kidney disease risk assessment system based on ensemble learning
CN112133427A (en) * 2020-09-24 2020-12-25 江苏天瑞精准医疗科技有限公司 Stomach cancer auxiliary diagnosis system based on artificial intelligence

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110223772A (en) * 2019-06-10 2019-09-10 青岛大学附属医院 A kind for the treatment of endocrine diseases diagnostic device and data information processing method
CN112117006A (en) * 2020-09-23 2020-12-22 重庆医科大学 Type 2 diabetes kidney disease risk assessment system based on ensemble learning
CN112133427A (en) * 2020-09-24 2020-12-25 江苏天瑞精准医疗科技有限公司 Stomach cancer auxiliary diagnosis system based on artificial intelligence

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
姜凤举 著: "《实用医学影像检查与临床诊断》", 31 May 2019 *
张丽: ""3D打印在心血管疾病中的应用"", 《中国医疗器械信息》 *
张军强等: ""CT血管造影与冠状动脉造影在冠心病临床诊断中的价值对比"", 《临床医学研究与实践》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114974576A (en) * 2022-07-12 2022-08-30 曜立科技(北京)有限公司 Cardiovascular and cerebrovascular disease diagnosis and management system based on metadata
US11966374B2 (en) 2022-07-12 2024-04-23 Serv Medical Pte. Ltd. Medical clinical data quality analysis system based on big data
CN117292829A (en) * 2023-10-13 2023-12-26 黄恺 Graded diagnosis and treatment information system for coronary heart disease

Similar Documents

Publication Publication Date Title
CN112992343A (en) Coronary heart disease auxiliary diagnosis system for type 2 diabetes patients
RU2629799C2 (en) Evaluation and observation of acute lung injury (ali) / acute respiratory distress syndrome (ards)
US20210007675A1 (en) Method of detecting sepsis using vital signs, including systolic blood pressure, hematology parameters, and combinations thereof
CN107451417A (en) Dynamic ECG analysis intelligent diagnosis system and method
JP2002022748A (en) Clinical inspection system
CN113035357A (en) Diabetic kidney disease risk assessment system
CN114023441A (en) Severe AKI early risk assessment model and device based on interpretable machine learning model and development method thereof
CN112786203A (en) Machine learning diabetic retinopathy morbidity risk prediction method and application
CN115049069A (en) Visual interactive early intelligent sepsis early warning method
CN112967803A (en) Early mortality prediction method and system for emergency patients based on integrated model
CN115099331A (en) Auxiliary diagnosis system for malignant pleural effusion based on interpretable machine learning algorithm
CN112835316B (en) Neonatal sepsis shock prediction system and monitoring equipment
CN117116477A (en) Construction method and system of prostate cancer disease risk prediction model based on random forest and XGBoost
CN108109696B (en) Data processing method and device
CN117017310A (en) Acoustic-electric dual-mode congenital heart disease prediction device based on knowledge distillation
CN117116462A (en) Method, system and device for predicting glycosylated hemoglobin value
KR20130048597A (en) Method and apparatus for displaying an analysis result of medical measured data
CN115223706A (en) Sepsis early stage screening model suitable for mobile monitoring equipment
Sharma et al. Role of Artificial Intelligence in Biomedical Imaging
CN116452584B (en) Neonatal retinopathy prediction method and system
Yu et al. Intelligent Evaluation Model of Fetal Health based on PCA and Stacking Algorithm
US20230335290A1 (en) System and methods for continuously assessing performance of predictive analytics in a clinical decision support system
US20230215565A1 (en) Health state estimation using machine learning
CN114898858A (en) Acute aortic dissection emergency call preliminary examination prediction system
CN117012371A (en) Intelligent disease diagnosis system based on body fluid inspection equipment

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210618