CN112037919A - Risk assessment model for papillary carcinoma of thyroid nodule patient - Google Patents
Risk assessment model for papillary carcinoma of thyroid nodule patient Download PDFInfo
- Publication number
- CN112037919A CN112037919A CN202010964802.XA CN202010964802A CN112037919A CN 112037919 A CN112037919 A CN 112037919A CN 202010964802 A CN202010964802 A CN 202010964802A CN 112037919 A CN112037919 A CN 112037919A
- Authority
- CN
- China
- Prior art keywords
- model
- thyroid
- neural network
- indexes
- training
- 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
- 208000030045 thyroid gland papillary carcinoma Diseases 0.000 title claims abstract description 18
- 206010033701 Papillary thyroid cancer Diseases 0.000 title claims abstract description 17
- 238000012502 risk assessment Methods 0.000 title claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 7
- 238000007477 logistic regression Methods 0.000 claims abstract description 6
- 238000013210 evaluation model Methods 0.000 claims abstract description 5
- 238000000556 factor analysis Methods 0.000 claims abstract description 4
- 210000001685 thyroid gland Anatomy 0.000 claims description 19
- 208000024770 Thyroid neoplasm Diseases 0.000 claims description 10
- 238000002604 ultrasonography Methods 0.000 claims description 10
- 208000009453 Thyroid Nodule Diseases 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 4
- 102000009027 Albumins Human genes 0.000 claims description 3
- 108010088751 Albumins Proteins 0.000 claims description 3
- 102000005666 Apolipoprotein A-I Human genes 0.000 claims description 3
- 108010059886 Apolipoprotein A-I Proteins 0.000 claims description 3
- 206010054107 Nodule Diseases 0.000 claims description 3
- 102000009843 Thyroglobulin Human genes 0.000 claims description 3
- 108010034949 Thyroglobulin Proteins 0.000 claims description 3
- 102000011923 Thyrotropin Human genes 0.000 claims description 3
- 108010061174 Thyrotropin Proteins 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 201000010198 papillary carcinoma Diseases 0.000 claims description 3
- 230000035488 systolic blood pressure Effects 0.000 claims description 3
- 229960002175 thyroglobulin Drugs 0.000 claims description 3
- -1 thyroid autoantibody Proteins 0.000 claims description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract 1
- 238000003745 diagnosis Methods 0.000 description 18
- 230000000405 serological effect Effects 0.000 description 4
- 201000002510 thyroid cancer Diseases 0.000 description 4
- 238000007689 inspection Methods 0.000 description 2
- 238000010882 preoperative diagnosis Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 208000024799 Thyroid disease Diseases 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000002308 calcification Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013188 needle biopsy Methods 0.000 description 1
- 210000005259 peripheral blood Anatomy 0.000 description 1
- 239000011886 peripheral blood Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 208000021510 thyroid gland disease Diseases 0.000 description 1
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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a risk assessment model for papillary carcinoma of thyroid nodule patients, which is characterized by comprising the following steps: performing PTC risk factor analysis by Logistic regression, and selecting a specific index as an independent variable of the model; constructing a BP neural network model of a feedforward neural network structure comprising three layers of an input layer, a hidden layer and an output layer, and training and predicting the BP neural network model by using data information comprising the specific indexes; and comparing the predicted value output by the model with the true value, drawing an ROC curve to obtain an area AUC under the curve, and evaluating the diagnostic performance of the model by using the AUC value, wherein the model with the standard diagnostic performance is the target risk evaluation model. The risk evaluation model can be used as a reference for doctors to diagnose papillary thyroid cancer, and the accuracy of diagnosing papillary thyroid cancer diseases is improved.
Description
Technical Field
The invention relates to a risk assessment model constructed based on a neural network model, which is particularly used for risk assessment of papillary carcinoma of thyroid nodule patients.
Background
In recent years, it is widely considered by those skilled in the art that the popularization of thyroid disease screening and the progress of detection technology are main reasons for the remarkable increase of the thyroid cancer incidence data acquired by us. Among the known data of incidence rate of thyroid cancer, the majority of them are thyroid papillary carcinomas (PTC) with better prognosis. The increase in a large number of PTC cases not only increases the medical burden, but also increases the potential for over-treatment. In the aspect of preoperative diagnosis of thyroid cancer, neck ultrasound is recommended in domestic and foreign guidelines as the first-choice examination of all known or suspected thyroid nodule patients, the characteristics of the soundness texture, edge morphology, calcification condition, internal and peripheral blood flow, growth trend and the like of the nodule can be clearly shown, but the diagnosis accuracy is not enough to be used as an independent diagnosis means, and the patients suspected of thyroid cancer need to be subjected to cytopathology examination of fine needle biopsy of thyroid nodule as a invasive examination, so that the operation risk and the probability of puncture failure are certain, and meanwhile, some cases which cannot be clearly diagnosed by cytology exist. The previous research shows that besides the imaging examination, the general condition of the patient and some serological indexes are related to the benign and malignant properties of the nodule, and the general condition and some serological indexes are often only used as clinical reference indexes due to low independent diagnosis performance.
Disclosure of Invention
The technical purpose of the invention is to provide a risk assessment model for papillary carcinoma of thyroid nodule patient, the output index of which can be used as the basis for assisting a doctor to make diagnosis, and the diagnosis accuracy of papillary carcinoma of thyroid gland of the patient is improved.
The technical scheme of the invention is as follows:
a risk assessment model for papillary carcinoma of thyroid nodule patients comprising the steps of:
s1, collecting clinical data of a patient, carrying out PTC risk factor analysis by Logistic regression, selecting 9 indexes of age, gender, systolic pressure, thyroid stimulating hormone, thyroid autoantibody, thyroglobulin, thyroid ultrasound TI-RADS grading, apolipoprotein A-I and albumin as independent variables of a model, and assigning values according to classification indexes in the 9 indexes, wherein the classification indexes comprise gender, thyroid autoantibody and thyroid ultrasound TI-RADS grading;
s2, constructing a BP neural network model, wherein the BP neural network model comprises three layers of feedforward neural network structures, namely an input layer, a hidden layer and an output layer, the input indexes of the input layer are 9 indexes selected in the step S1, and the output indexes of the output layer are the prediction results of papillary carcinoma of a thyroid nodule patient;
s3, collecting clinical data of a patient, creating a training set and a prediction set, and inputting the data of the training set into the BP neural network model constructed in the step S2 for training; after the training is finished, inputting the data of the prediction set into the model, comparing the predicted value output by the model with the true value, drawing an ROC curve to obtain the area AUC under the curve, and evaluating the diagnostic performance of the model by using the AUC value, wherein the model with the standard diagnostic performance is the target risk evaluation model.
On the basis of the above scheme, a further improved or preferred scheme further comprises:
further, in step S1, the classification index is assigned as:
sex: male assigned 1 and female assigned 0;
thyroid autoantibodies: positive TgAb or TPOAb is positive (+) and the value is assigned to 1; negative (-) if both are negative, the assignment is 2;
thyroid ultrasound TI-RADS grading: level 2 is 0; grade 3 is 1; 4a level is 2; grade 4b is 3; 4c grade is 4; grade 5 is 5;
in step S2, the output layer output index is assigned as: benign nodules were 1 and papillary thyroid carcinoma was 2.
Preferably, in step S2, the number of hidden layers of the constructed BP neural network model is 1, the number of neuron nodes is 15, the training function is a Levenberg-Marquardt function, the weight updating method of error back propagation is a gradient descent method, the number of model iterations is 1000, and the learning rate is 0.01.
Has the advantages that:
although the prior preoperative noninvasive diagnosis means of papillary thyroid carcinoma are abundant, the prior preoperative noninvasive diagnosis means still have respective defects in independent diagnosis efficiency, and the former doctors usually take the ultrasonic results as the main reference and give the next diagnosis and treatment opinions by combining general data of patients, serological indexes and the like. The invention constructs an objective preoperative noninvasive diagnosis model (data processing model) by combining some serological indexes and general data of a patient with an ultrasonic result, fully utilizes clinical data of the patient, can be used as a reference to assist a doctor to make a diagnosis, and increases the accuracy of preoperative diagnosis. In addition, the model is applied without additional examination, the medical cost of a patient is not obviously increased, and the model is suitable for popularization and application. The BP neural network model belongs to the category of machine learning, and the more abundant the patient data providing training is, the more accurate the obtained model prediction is.
Drawings
FIG. 1 is a schematic structural diagram of a BP neural network model according to the present invention;
FIG. 2 is a ROC curve of a BP neural network prediction model according to an embodiment of the present invention.
Detailed Description
To clarify the technical solution and working principle of the present invention, the present invention will be further described with reference to the accompanying drawings and specific embodiments.
A risk assessment model for papillary carcinoma of thyroid nodule patients comprising the steps of:
s1, collecting clinical data of the patient, including general data of age, sex, etc.; ② thyroid-related hormone and antibody inspection result; ③ a biochemical inspection result; and fourthly, thyroid nodule ultrasonic TI-RADS grading results and the like. The method carries out PTC risk factor analysis by Logistic regression, selects 9 indexes of age (year), gender (male/female), systolic pressure (mmHg), thyroid stimulating hormone (mIU/L), thyroid autoantibody (positive/negative), thyroglobulin (nmol/L), thyroid ultrasound TI-RADS grading, apolipoprotein A-I (g/L), albumin (g/L) and the like as independent variables of a model, and assigns values according to classification indexes in the 9 indexes, wherein the classification indexes comprise gender, thyroid autoantibody and thyroid ultrasound TI-RADS grading, and the specific assignment is as follows:
1) sex: male assigned 1 and female assigned 0;
2) thyroid autoantibodies: positive TgAb or TPOAb is positive (+) and the value is assigned to 1; negative (-) if both are negative, the assignment is 2;
3) thyroid ultrasound TI-RADS grading: level 2 is 0; grade 3 is 1; 4a level is 2; grade 4b is 3; 4c grade is 4; grade 5 is 5;
s2, constructing a BP neural network model by using a neural network toolbox carried by MATLAB software, wherein the BP neural network model comprises three layers of feedforward neural network structures which are an input layer, a hidden layer and an output layer respectively, the structures of the feedforward neural network structures are shown in figure 1, the input indexes of the input layer are 9 indexes selected in the step S1, the output indexes of the output layer are the prediction results of papillary carcinoma of a thyroid nodule patient, and the assignment of the output indexes of the output layer is as follows: benign nodules were 1 and papillary thyroid carcinoma was 2. The number of hidden layers in the BP neural network model is 1, the number of neuron nodes is 15, a training function is a Levenberg-Marquardt function, a weight updating method of error back propagation is a gradient descent method, the number of model iterations is 1000, and the learning rate is 0.01.
S3, collecting enough clinical data of the patient for creating a training set and a prediction set, and inputting the data of the training set into the BP neural network model constructed in the step S2 for training; after training is finished, inputting data of the prediction set into the model, comparing a predicted value output by the model with a true value of illness, drawing an ROC curve to obtain an area AUC under the curve, and evaluating the diagnosis performance of the model by using the AUC value, wherein the model with the standard diagnosis performance is the target risk evaluation model. The model with unqualified diagnostic performance can improve the accuracy of model prediction by increasing the patient data of the training set, namely, the richer the patient data providing training, the more accurate the obtained model prediction.
In this example, a training set was created based on clinical data of 1622 patients for learning, and clinical data of 406 patients was used as a prediction set to predict the results, so as to obtain ROC curves as shown in fig. 2, where AUC is 0.943, 95% CI is 0.912 to 0.973, standard error is 0.016, and P is less than 0.001. Similarly, a predicted value approximation 1.7835 with the highest sensitivity and specificity is selected as a diagnosis tangent point from the coordinates of the SPSS output ROC curve, and the sensitivity, the specificity, the NPV (negative predicted value) and the PPV (positive predicted value) of the BP neural network model are respectively 90.1%, 90.2%, 75.4% and 96.5%, respectively. The comparison of the node property prediction performance evaluation indexes of 2028 patients according to the prediction results of the model and the traditional ultrasonic TI-RADS grading independent diagnosis and multi-factor Logistic regression combined diagnosis model is shown in Table 1, and the prediction accuracy of the model is higher than the diagnosis results of the traditional ultrasonic and multi-factor Logistic regression combined diagnosis model, and the model has higher reliability.
Note: AUC represents the area under the receiver operating characteristic curve (ROC), with a 95% confidence interval in parentheses. Jotan index-sensitivity + specificity-1.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the foregoing description only for the purpose of illustrating the principles of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the invention as defined by the appended claims, specification, and equivalents thereof.
Claims (3)
1. A risk assessment model for papillary carcinoma of thyroid nodule patients comprising the steps of:
s1, collecting clinical data of a patient, carrying out PTC risk factor analysis by Logistic regression, selecting 9 indexes of age, gender, systolic pressure, thyroid stimulating hormone, thyroid autoantibody, thyroglobulin, thyroid ultrasound TI-RADS grading, apolipoprotein A-I and albumin as independent variables of a model, and assigning values according to classification indexes in the 9 indexes, wherein the classification indexes comprise gender, thyroid autoantibody and thyroid ultrasound TI-RADS grading;
s2, constructing a BP neural network model, wherein the BP neural network model comprises three layers of feedforward neural network structures, namely an input layer, a hidden layer and an output layer, the input indexes of the input layer are 9 indexes selected in the step S1, and the output indexes of the output layer are the prediction results of papillary carcinoma of a thyroid nodule patient;
s3, collecting clinical data of a patient, creating a training set and a prediction set, and inputting the data of the training set into the BP neural network model constructed in the step S2 for training; after the training is finished, inputting the data of the prediction set into the model, comparing the predicted value output by the model with the true value, drawing an ROC curve to obtain the area AUC under the curve, and evaluating the diagnostic performance of the model by using the AUC value, wherein the model with the standard diagnostic performance is the target risk evaluation model.
2. A risk assessment model for papillary carcinoma of thyroid nodule patients according to claim 1, wherein:
in step S1, the classification index is assigned as:
sex: male assigned 1 and female assigned 0;
thyroid autoantibodies: positive TgAb or TPOAb is positive (+) and the value is assigned to 1; negative (-) if both are negative, the assignment is 2;
thyroid ultrasound TI-RADS grading: level 2 is 0; grade 3 is 1; 4a level is 2; grade 4b is 3; 4c grade is 4; grade 5 is 5;
in step S2, the output layer output index is assigned as: benign nodules were 1 and papillary thyroid carcinoma was 2.
3. A risk assessment model for papillary carcinoma of thyroid nodule patients according to claim 1, wherein:
in step S2, the number of hidden layers of the constructed BP neural network model is 1, wherein the number of neuron nodes is 15, the training function is a Levenberg-Marquardt function, the weight updating method of error back propagation is a gradient descent method, the number of model iterations is 1000, and the learning rate is 0.01.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010964802.XA CN112037919B (en) | 2020-09-15 | 2020-09-15 | Risk assessment model for papillary carcinoma of thyroid nodule patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010964802.XA CN112037919B (en) | 2020-09-15 | 2020-09-15 | Risk assessment model for papillary carcinoma of thyroid nodule patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112037919A true CN112037919A (en) | 2020-12-04 |
| CN112037919B CN112037919B (en) | 2024-02-23 |
Family
ID=73589321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010964802.XA Active CN112037919B (en) | 2020-09-15 | 2020-09-15 | Risk assessment model for papillary carcinoma of thyroid nodule patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112037919B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820403A (en) * | 2021-02-25 | 2021-05-18 | 中山大学 | Deep learning method for predicting prognosis risk of cancer patient based on multiple groups of mathematical data |
| CN114694836A (en) * | 2020-12-30 | 2022-07-01 | 上海交通大学医学院附属瑞金医院 | Evaluation system based on thyroid cancer lymph node metastasis prediction model |
| CN115116594A (en) * | 2022-06-06 | 2022-09-27 | 中国科学院自动化研究所 | Method and device for detecting effectiveness of medical device |
| CN118280577A (en) * | 2024-05-30 | 2024-07-02 | 南通大学附属医院 | Neural network-based digestive tract hemorrhage risk assessment method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140099261A1 (en) * | 2011-03-22 | 2014-04-10 | Cornell University | Distinguishing benign and malignant indeterminate thyroid lesions |
| CN109243604A (en) * | 2018-09-14 | 2019-01-18 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on neural network algorithm |
| RU2725749C1 (en) * | 2019-11-22 | 2020-07-03 | федеральное государственное автономное образовательное учреждение высшего образования Первый Московский государственный медицинский университет имени И.М. Сеченова Министерства здравоохранения Российской Федерации (Сеченовский университет) (ФГАОУ ВО Первый МГМУ им. И.М. Сеченова Минздрава России (Се | Method for assessing the risk of thyroid cancer in a patient with nodular thyroid formations |
-
2020
- 2020-09-15 CN CN202010964802.XA patent/CN112037919B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140099261A1 (en) * | 2011-03-22 | 2014-04-10 | Cornell University | Distinguishing benign and malignant indeterminate thyroid lesions |
| CN109243604A (en) * | 2018-09-14 | 2019-01-18 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on neural network algorithm |
| RU2725749C1 (en) * | 2019-11-22 | 2020-07-03 | федеральное государственное автономное образовательное учреждение высшего образования Первый Московский государственный медицинский университет имени И.М. Сеченова Министерства здравоохранения Российской Федерации (Сеченовский университет) (ФГАОУ ВО Первый МГМУ им. И.М. Сеченова Минздрава России (Се | Method for assessing the risk of thyroid cancer in a patient with nodular thyroid formations |
Non-Patent Citations (4)
| Title |
|---|
| SABRI 等: "A comparison of logistic regression and artificial neural networks in predicting central lymph node metastases in papillary thyroid microcarinoma", ANN.ITAL.CHIR., vol. 89, no. 3, pages 193 - 198 * |
| XIAOWEN ZHANG 等: "Risk factors and diagnostic prediction models for papillary thyroid carcinoma", FRONTIERS IN ENDOCRINOLOGY, pages 10 * |
| 余小兰;姚永忠;桑剑锋;苏磊;王雪晨;: "基于BP神经网络的甲状腺癌无创诊断模型的研究", 现代生物医学进展, no. 36, pages 7104 - 7108 * |
| 郑晓 等: "甲状腺乳头状癌风险评估量表的建立及与甲状腺细针穿刺细胞学检查的诊断效能比较", 中华内分泌代谢杂志, vol. 33, no. 9, pages 755 - 759 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114694836A (en) * | 2020-12-30 | 2022-07-01 | 上海交通大学医学院附属瑞金医院 | Evaluation system based on thyroid cancer lymph node metastasis prediction model |
| CN114694836B (en) * | 2020-12-30 | 2024-06-04 | 上海交通大学医学院附属瑞金医院 | Assessment system based on thyroid cancer lymph node metastasis prediction model |
| CN112820403A (en) * | 2021-02-25 | 2021-05-18 | 中山大学 | Deep learning method for predicting prognosis risk of cancer patient based on multiple groups of mathematical data |
| CN112820403B (en) * | 2021-02-25 | 2024-03-29 | 中山大学 | Deep learning method for predicting prognosis risk of cancer patient based on multiple sets of learning data |
| CN115116594A (en) * | 2022-06-06 | 2022-09-27 | 中国科学院自动化研究所 | Method and device for detecting effectiveness of medical device |
| CN115116594B (en) * | 2022-06-06 | 2024-05-31 | 中国科学院自动化研究所 | Method and device for detecting effectiveness of medical device |
| CN118280577A (en) * | 2024-05-30 | 2024-07-02 | 南通大学附属医院 | Neural network-based digestive tract hemorrhage risk assessment method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112037919B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112037919B (en) | Risk assessment model for papillary carcinoma of thyroid nodule patient | |
| El Houby | A survey on applying machine learning techniques for management of diseases | |
| Qi et al. | Automated diagnosis of breast ultrasonography images using deep neural networks | |
| CN109447940B (en) | Convolutional neural network training method, ultrasonic image identification and positioning method and system | |
| CN112801168B (en) | Lesion area prediction analysis method, system and terminal equipment of tumor image | |
| CN113393938B (en) | Breast cancer risk prediction system fusing image and clinical characteristic information | |
| CN113113130A (en) | Tumor individualized diagnosis and treatment scheme recommendation method | |
| Wang et al. | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis | |
| CN105957092B (en) | Breast molybdenum target characteristics of image self study extracting method for computer-aided diagnosis | |
| CN115602327A (en) | Construction method of prediction model for lung nodule lung cancer risk | |
| CN111428066A (en) | Method for classifying and segmenting lesion image based on convolutional neural network | |
| Lan et al. | Deep learning-based artificial intelligence improves accuracy of error-prone lung nodules | |
| CN116884631B (en) | Comprehensive liver failure prediction and treatment reference system based on AI and similar patient analysis | |
| Jony et al. | Deep Learning Paradigms for Breast Cancer Diagnosis: A Comparative Study on Wisconsin Diagnostic Dataset | |
| Li et al. | A deep learning trial on transient elastography for assessment of liver fibrosis | |
| CN111265234A (en) | Method and system for judging properties of lung mediastinal lymph nodes | |
| CN116206756A (en) | Lung adenocarcinoma data processing method, system, equipment and computer readable storage medium | |
| CN116091484A (en) | Method and system for predicting Ki-67 expression level of lung cancer | |
| Chowdary et al. | Multiple Disease Prediction by Applying Machine Learning and Deep Learning Algorithms | |
| Mohammed et al. | A Novel Approach to Multi-Disease Detection in Healthcare using CNN, Random Forest & XGBoost | |
| Wang et al. | X-ray images detection of COVID-19 based on deepwise separable DenseNet | |
| Akshara et al. | A Survey: Identification of Throat Cancer byMachine Learning | |
| Cao et al. | A Non-Invasive Interpretable NAFLD Diagnostic Method Combining TCM Tongue Features | |
| Selvaraj et al. | Optimized Machine Learning for CHD Detection using 3D CNN-based Segmentation, Transfer Learning and Adagrad Optimization | |
| Hemanth et al. | Diabetic Retinopathy Prediction and Analysis Using Ensemble Classifier in Deep Learning Technique |
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 |