CN110660481A - Artificial intelligence technology-based primary liver cancer recurrence prediction method - Google Patents
Artificial intelligence technology-based primary liver cancer recurrence prediction method Download PDFInfo
- Publication number
- CN110660481A CN110660481A CN201910921696.4A CN201910921696A CN110660481A CN 110660481 A CN110660481 A CN 110660481A CN 201910921696 A CN201910921696 A CN 201910921696A CN 110660481 A CN110660481 A CN 110660481A
- Authority
- CN
- China
- Prior art keywords
- liver cancer
- recurrence
- hepatitis
- artificial intelligence
- model
- 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.)
- Withdrawn
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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a primary liver cancer recurrence prediction method based on artificial intelligence technology, which utilizes the powerful computing power of a computer and an artificial intelligence algorithm to automatically capture and learn the subtle difference characteristics of physiological indexes of different liver cancer patients from massive primary liver cancer patient data, finds potential risk factors of liver cancer recurrence, further constructs a recurrence probability and recurrence period prediction model suitable for the primary liver cancer patients, finally provides a client for a client to use in a software packaging mode or a webpage mode, and a user uploads a new case through a computer or a smart phone to return the recurrence condition prediction result of the case after receiving treatment.
Description
Technical Field
The invention relates to the field of medical treatment, in particular to a primary liver cancer recurrence prediction method based on an artificial intelligence technology.
Background
Primary liver cancer is a common malignant tumor with the morbidity and mortality rate in China ranked in the front, and about 38.3 thousands of people die of liver cancer every year, which is more than half of the death cases of liver cancer in the whole world. The current treatment methods of liver cancer include surgical resection, liver transplantation, local ablation, interventional therapy, radiotherapy, targeted therapy, immunobiotherapy and the like. The liver cancer of China is different from foreign countries in the causes of disease, molecular biological characteristics, epidemiological characteristics, clinical manifestations and stages, and even treatment strategies and means, and is one of the tumors with Chinese characteristics. However, after the primary liver cancer patient passes through treatment, many patients often relapse, and the prognosis and survival period of the patients are seriously affected, and no instrument or equipment can be used for deducing whether the patients relapse after the treatment.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a primary liver cancer recurrence prediction method based on an artificial intelligence technology so as to solve the problems in the technical background.
The purpose of the invention is realized by the following technical scheme:
a primary liver cancer recurrence prediction method based on artificial intelligence technology comprises the following steps:
s1, acquiring case data of the liver cancer patient from a hospital data center;
s2, performing preprocessing such as cleaning, feature screening, feature combination and the like on the original data by comprehensively adopting a statistical means and an artificial intelligence technology and combining doctor experience so as to facilitate training of an artificial intelligence algorithm;
s3, carrying out layered sampling on the preprocessed data according to the treatment scheme adopted by the patient, wherein each treatment scheme is as follows: 2: 1 into a training set, a verification set and a test set;
s4, training the training set under each treatment scheme by using a GBDT model, automatically capturing nuances among different liver cancer patients by a trainer, learning the hidden relation among each body index, the recurrence rate and the recurrence period, and realizing the prediction function of the recurrence probability and the recurrence period;
s5, the GBDT classifier has variable hyper-parameters such as subtree number, sub-number depth, learning rate and the like, cross validation is carried out by using validation set data during training, and a hyper-parameter combination with the best prediction effect is selected; if the optimal model can also perform well on the test set, determining the optimal model as a final prediction model, otherwise, still needing further parameter adjustment;
and S6, carrying the final GBDT model on a mobile phone end or serving as a network end background, providing liver cancer recurrence prediction service for patients in an auxiliary diagnosis product mode, and giving recurrence probability and recurrence period results of primary liver cancer.
Further, in step S2, the data includes 47 main indicators in total, which are respectively: gender, age, number of visits, cirrhosis indicator, hepatitis b indicator, alpha-fetoprotein, oncofetal protein, height, weight, BMI, Child-trough score, hepatitis b history, hepatitis c history, portal hypertension condition, alcohol consumption, hemoglobin, platelets, leukocytes, neutrophil ratio, lymphocyte ratio, NLR, monocyte ratio, eosinophil ratio, basophil ratio, total bilirubin, direct bilirubin, aspartate aminotransferase, glutamate aminotransferase, albumin, urea, creatinine, cystatin, prothrombin time, activated partial thromboplastin time, tumor number, maximum tumor size, total tumor size, tumor location, macroscopic vascular invasion, lymphatic metastasis location, treatment history, relapse history.
Further, in step S5, if the predicted effect of the model on the test set reaches the standard, the model parameter is determined and the model is saved; otherwise, the hyper-parameters need to be set again, even the division of the data set needs to be adjusted, and the training and the testing are repeated until the model effect reaches the standard.
Further, the index of liver cirrhosis comprises INR and FIB, and the index of hepatitis B comprises hepatitis B surface antigen, hepatitis B surface antibody, hepatitis B E antigen and hepatitis B core antibody.
Furthermore, the method can be loaded on a computer or a smart phone in the form of client software or a webpage.
The invention has the beneficial effects that:
the method is based on artificial intelligence classification and regression technology, makes full use of the powerful computing capacity of a computer, automatically extracts and analyzes the subtle difference characteristics of physiological indexes of different liver cancer patients from massive primary liver cancer patient data by using a gradient lifting tree method, finds potential risk factors of liver cancer recurrence, and further constructs a recurrence probability and recurrence period prediction model suitable for the primary liver cancer patients. And finally, the client is provided for a client to use in a software packaging mode or a webpage mode, and a user uploads a new case through a computer or a smart phone to return the relapse condition of the case after receiving treatment.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a flow chart of training and debugging of the learner in the present invention.
Detailed Description
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The first embodiment is as follows:
a primary liver cancer recurrence prediction method based on artificial intelligence technology comprises the following steps:
s1, acquiring case data of the liver cancer patient from a hospital data center;
s2, performing preprocessing such as cleaning, feature screening, feature combination and the like on the original data by comprehensively adopting a statistical means and an artificial intelligence technology and combining doctor experience so as to facilitate training of an artificial intelligence algorithm;
s3, carrying out layered sampling on the preprocessed data according to the treatment scheme adopted by the patient, wherein each treatment scheme is as follows: 2: 1 into a training set, a verification set and a test set;
s4, training the training set under each treatment scheme by using a GBDT model, automatically capturing nuances among different liver cancer patients by a trainer, learning the hidden relation among each body index, the recurrence rate and the recurrence period, and realizing the prediction function of the recurrence probability and the recurrence period;
s5, the GBDT classifier has variable hyper-parameters such as subtree number, sub-number depth, learning rate and the like, cross validation is carried out by using validation set data during training, and a hyper-parameter combination with the best prediction effect is selected; if the optimal model can also perform well on the test set, determining the optimal model as a final prediction model, otherwise, still needing further parameter adjustment;
and S6, carrying the final GBDT model on a mobile phone end or serving as a network end background, providing liver cancer recurrence prediction service for patients in an auxiliary diagnosis product mode, and giving recurrence probability and recurrence period results of primary liver cancer.
Further, in step S2, the data includes 47 main body indicators in total, which are respectively: gender, age, number of visits, cirrhosis index, hepatitis B index, alpha fetoprotein, oncofetal protein, height, weight, BMI, Child-trough score, hepatitis B history, hepatitis C history, portal hypertension condition, drinking condition, hemoglobin, platelets, leukocytes, neutrophil ratio, lymphocyte ratio, NLR, monocyte ratio, eosinophil ratio, basophil ratio, total bilirubin, direct bilirubin, aspartate aminotransferase, glutamate aminotransferase, albumin, urea, creatinine, cystatin, prothrombin time, activated partial thromboplastin time, tumor number, maximum tumor size, total tumor size, tumor location, macroscopic vascular invasion, lymphatic metastasis location, treatment history, recurrence history, which are all characterized in each dimension of physical characteristics, biochemical examination, liver condition, tumor parameters, therefore, the accuracy of the invention for predicting the recurrence of the liver cancer is higher.
Further, in step S5, if the predicted effect of the model on the test set reaches the standard, the model parameter is determined and the model is saved; otherwise, the hyper-parameters need to be set again, even the division of the data set needs to be adjusted, and the training and the testing are repeated until the model effect reaches the standard.
Furthermore, in the invention, the partial indexes are subjected to characteristic extraction or characteristic combination, for example, the cirrhosis index is combined by INR and FIB, the hepatitis B index comprises sub-indexes such as hepatitis B surface antigen, hepatitis B surface antibody, hepatitis B E antigen and hepatitis B core antibody, and the indexes of relapse history and treatment history are quantified.
Furthermore, the method can be loaded on a computer or a smart phone in the form of client software or a webpage.
The method is based on artificial intelligence classification and regression technology, makes full use of the powerful computing capacity of a computer, automatically extracts and analyzes the subtle difference characteristics of physiological indexes of different liver cancer patients from massive primary liver cancer patient data by using a gradient lifting tree method, finds potential risk factors of liver cancer recurrence, and further constructs a recurrence probability and recurrence period prediction model suitable for the primary liver cancer patients. And finally, the client is provided for a client to use in a software packaging mode or a webpage mode, and a user uploads a new case through a computer or a smart phone to return the relapse condition of the case after receiving treatment.
The above-mentioned embodiments only express the specific embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (5)
1. A primary liver cancer recurrence prediction method based on artificial intelligence technology covers all processes from data acquisition to product service, and specifically comprises the following steps:
s1, acquiring case data of the liver cancer patient from a hospital data center;
s2, performing preprocessing such as cleaning, feature screening, feature combination and the like on the original data by comprehensively adopting a statistical means and an artificial intelligence technology and combining doctor experience so as to facilitate training of an artificial intelligence algorithm;
s3, carrying out layered sampling on the preprocessed data according to the treatment scheme adopted by the patient, wherein each treatment scheme is as follows: 2: 1 into a training set, a verification set and a test set;
s4, training the training set under each treatment scheme by using a GBDT model, automatically capturing nuances among different liver cancer patients by a trainer, learning the hidden relation among each body index, the recurrence rate and the recurrence period, and realizing the prediction function of the recurrence probability and the recurrence period;
s5, the GBDT classifier has variable hyper-parameters such as subtree number, sub-number depth, learning rate and the like, cross validation is carried out by using validation set data during training, and a hyper-parameter combination with the best prediction effect is selected; if the optimal model can also perform well on the test set, determining the optimal model as a final prediction model, otherwise, still needing further parameter adjustment;
and S6, carrying the final GBDT model on a mobile phone end or serving as a network end background, providing liver cancer recurrence prediction service for patients in an auxiliary diagnosis product mode, and giving recurrence probability and recurrence period results of primary liver cancer.
2. The method of claim 1, wherein in step S2, the data includes 47 main indicators, which are: gender, age, number of visits, cirrhosis indicator, hepatitis b indicator, alpha-fetoprotein, oncofetal protein, height, weight, BMI, Child-trough score, hepatitis b history, hepatitis c history, portal hypertension condition, alcohol consumption, hemoglobin, platelets, leukocytes, neutrophil ratio, lymphocyte ratio, NLR, monocyte ratio, eosinophil ratio, basophil ratio, total bilirubin, direct bilirubin, aspartate aminotransferase, glutamate aminotransferase, albumin, urea, creatinine, cystatin, prothrombin time, activated partial thromboplastin time, tumor number, maximum tumor size, total tumor size, tumor location, macroscopic vascular invasion, lymphatic metastasis location, treatment history, relapse history.
3. The method of claim 1, wherein in step S5, if the prediction effect of the model on the test set meets the standard, the model parameters are determined and the model is saved; otherwise, the hyper-parameters need to be set again, even the division of the data set needs to be adjusted, and the training and the testing are repeated until the model effect reaches the standard.
4. The artificial intelligence technology-based primary liver cancer recurrence prediction method of claim 2, wherein the cirrhosis indicator comprises INR and FIB, and the hepatitis b indicator comprises hepatitis b surface antigen, hepatitis b surface antibody, hepatitis b E antigen and hepatitis b core antibody.
5. The method for predicting recurrence of primary liver cancer based on artificial intelligence technology as claimed in claim 1, wherein the method can be loaded on computer or smart phone in the form of client software or web page.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921696.4A CN110660481A (en) | 2019-09-27 | 2019-09-27 | Artificial intelligence technology-based primary liver cancer recurrence prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921696.4A CN110660481A (en) | 2019-09-27 | 2019-09-27 | Artificial intelligence technology-based primary liver cancer recurrence prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110660481A true CN110660481A (en) | 2020-01-07 |
Family
ID=69039406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910921696.4A Withdrawn CN110660481A (en) | 2019-09-27 | 2019-09-27 | Artificial intelligence technology-based primary liver cancer recurrence prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110660481A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524594A (en) * | 2020-06-12 | 2020-08-11 | 山东大学 | Target population blood system malignant tumor screening system |
| CN111739638A (en) * | 2020-06-16 | 2020-10-02 | 刘�文 | Postoperative self-service evaluation system suitable for differentiated thyroid cancer patients |
| CN112768060A (en) * | 2020-07-14 | 2021-05-07 | 福州宜星大数据产业投资有限公司 | Liver cancer postoperative recurrence prediction method based on random survival forest and storage medium |
| CN113160969A (en) * | 2021-04-14 | 2021-07-23 | 青岛大学附属医院 | Soft tissue sarcoma recurrence probability prediction method based on machine learning |
| CN113724875A (en) * | 2021-09-10 | 2021-11-30 | 北京思泰瑞健康科技有限公司 | Method, device and equipment for predicting cancer recurrence rate |
| CN114155956A (en) * | 2021-12-02 | 2022-03-08 | 首都医科大学附属北京地坛医院 | System for predicting blood vessel invasion probability of primary liver cancer patient incapable of being resected by surgery |
| CN115966309A (en) * | 2023-03-17 | 2023-04-14 | 杭州堃博生物科技有限公司 | Recurrence position prediction method, recurrence position prediction device, nonvolatile storage medium, and electronic device |
| CN117809853A (en) * | 2024-02-29 | 2024-04-02 | 首都医科大学附属北京友谊医院 | Construction method of hepatocellular carcinoma pathological recognition model and electronic equipment |
-
2019
- 2019-09-27 CN CN201910921696.4A patent/CN110660481A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524594A (en) * | 2020-06-12 | 2020-08-11 | 山东大学 | Target population blood system malignant tumor screening system |
| CN111739638A (en) * | 2020-06-16 | 2020-10-02 | 刘�文 | Postoperative self-service evaluation system suitable for differentiated thyroid cancer patients |
| CN112768060A (en) * | 2020-07-14 | 2021-05-07 | 福州宜星大数据产业投资有限公司 | Liver cancer postoperative recurrence prediction method based on random survival forest and storage medium |
| CN113160969A (en) * | 2021-04-14 | 2021-07-23 | 青岛大学附属医院 | Soft tissue sarcoma recurrence probability prediction method based on machine learning |
| CN113724875A (en) * | 2021-09-10 | 2021-11-30 | 北京思泰瑞健康科技有限公司 | Method, device and equipment for predicting cancer recurrence rate |
| CN114155956A (en) * | 2021-12-02 | 2022-03-08 | 首都医科大学附属北京地坛医院 | System for predicting blood vessel invasion probability of primary liver cancer patient incapable of being resected by surgery |
| CN115966309A (en) * | 2023-03-17 | 2023-04-14 | 杭州堃博生物科技有限公司 | Recurrence position prediction method, recurrence position prediction device, nonvolatile storage medium, and electronic device |
| CN117809853A (en) * | 2024-02-29 | 2024-04-02 | 首都医科大学附属北京友谊医院 | Construction method of hepatocellular carcinoma pathological recognition model and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660481A (en) | Artificial intelligence technology-based primary liver cancer recurrence prediction method | |
| Sahu et al. | FINE_DENSEIGANET: Automatic medical image classification in chest CT scan using Hybrid Deep Learning Framework | |
| US11341631B2 (en) | System and method for automatically detecting a physiological condition from a medical image of a patient | |
| CN108694718A (en) | The same period new chemoradiation therapy curative effect evaluation system and method before rectal cancer | |
| EP3357000B1 (en) | Cancer detection systems and methods | |
| Banna et al. | The promise of digital biopsy for the prediction of tumor molecular features and clinical outcomes associated with immunotherapy | |
| CN107369151A (en) | System and method are supported in GISTs pathological diagnosis based on big data deep learning | |
| Gutta et al. | Improved glioma grading using deep convolutional neural networks | |
| CN106156484A (en) | Disease of brain individuation Forecasting Methodology based on nuclear magnetic resonance image and system | |
| CN108511056A (en) | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system | |
| CN110991536B (en) | Training method of early warning model of primary liver cancer | |
| CN109271969A (en) | A kind of Histopathologic Grade of Cerebral Gliomas evaluation method and its device | |
| Banerjee et al. | Brain tumor detection and classification from multi-sequence MRI: Study using ConvNets | |
| WO2021146516A1 (en) | System and method for predicting the risk of future lung cancer | |
| Kyriazis et al. | An end-to-end system for automatic characterization of iba1 immunopositive microglia in whole slide imaging | |
| Li et al. | Radiomics features as predictors to distinguish fast and slow progression of Mild Cognitive Impairment to Alzheimer's disease | |
| Kumar et al. | Untangling classification methods for melanoma skin cancer | |
| CN111027548B (en) | Brain glioma molecular marker nondestructive prediction method and system based on image histology | |
| Artzi et al. | Classification of pediatric posterior fossa tumors using convolutional neural network and tabular data | |
| CN113128654B (en) | Improved random forest model for coronary heart disease pre-diagnosis and pre-diagnosis system thereof | |
| Van Buren et al. | Artificial intelligence and deep learning to map immune cell types in inflamed human tissue | |
| Rosita et al. | Prediction of Hospital Intesive Patients Using Neural Network Algorithm | |
| Aminikhanghahi et al. | Effective tumor feature extraction for smart phone based microwave tomography breast cancer screening | |
| Zhang et al. | An intelligent decision-making support system for the detection and staging of prostate cancer in developing countries | |
| Moghaddasi et al. | Comparing the efficiency of artificial neural network and gene expression programming in predicting coronary artery disease |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200107 |