CN114724721A - AI colon cancer risk early screening modeling method based on electronic medical record - Google Patents
AI colon cancer risk early screening modeling method based on electronic medical record Download PDFInfo
- Publication number
- CN114724721A CN114724721A CN202210215584.9A CN202210215584A CN114724721A CN 114724721 A CN114724721 A CN 114724721A CN 202210215584 A CN202210215584 A CN 202210215584A CN 114724721 A CN114724721 A CN 114724721A
- Authority
- CN
- China
- Prior art keywords
- colon cancer
- data
- screening
- model
- sample
- 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
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
- G16H50/50—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
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an AI colon cancer risk early screening modeling method based on an electronic medical record, which comprises the following steps: step S1: establishing an effective colon cancer risk early screening model, and step S2: sorting sample data to be screened, and step S3: and inputting the sample with the screening into a colon cancer early screening model to perform model calculation scoring, and finally obtaining a sample colon cancer risk early screening prediction result. The colon cancer early screening method based on the machine learning XGboost algorithm trains the colon cancer early screening model, can predict early stage morbidity probability score of the sample colon cancer according to related medical features of the electronic medical record, has the advantages that the specificity, the sensitivity and the ROCAC can be as high as 0.95, can screen in a large scale, high efficiency and high accuracy, solves the problem that the current colon cancer risk screening requires inspectors to check in hospitals, and is judged by doctors combining clinical guidelines and practical experience, so that the inspection efficiency is low, and can effectively save medical resources.
Description
Technical Field
The invention relates to the technical field of medical risk assessment, in particular to an AI colon cancer risk early screening modeling method based on an electronic medical record.
Background
The colon cancer is a common digestive tract malignant tumor occurring in a colon part, has great correlation with eating red meat by people, is better at the junction of rectum and sigmoid colon, has the highest incidence rate in an age group of 40-50 years, and has the ratio of 2-3: 1, the incidence rate accounts for the 3 rd position of gastrointestinal tumors. The colon cancer is mainly adenocarcinoma, mucinous adenocarcinoma, undifferentiated carcinoma, polyp-shaped, ulcer-shaped, and the like. The colon cancer can develop along the circulation of the intestinal wall, can spread up and down along the longitudinal diameter of the intestinal canal or infiltrate into the deep layer of the intestinal wall, can be planted in the abdominal cavity or spread and transferred along a suture line and a cut surface besides being transferred through a lymphatic vessel and blood flow and locally invaded, and patients with chronic colitis, colon polyp patients, male obesity patients and the like are susceptible people.
Early symptoms of colon cancer are not obvious and are frequently missed for diagnosis, at present, colon cancer risk screening needs inspectors to inspect in hospitals, and doctors combine clinical guidelines and practical experience to judge, so that the inspection efficiency is low, and large-batch general inspection cannot be carried out, and therefore an AI colon cancer risk early screening modeling method based on electronic medical records is provided to solve the problem.
Disclosure of Invention
The invention aims to provide an AI colon cancer risk early screening modeling method based on an electronic medical record, which has the advantages of large-batch, high-efficiency and high-accuracy screening and solves the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: an AI colon cancer risk early screening modeling method based on an electronic medical record comprises the following steps:
step S1: establishing an effective colon cancer risk early screening model;
step S2: arranging sample data to be screened;
step S3: and inputting the sample with the screening into a colon cancer early screening model to perform model calculation scoring, and finally obtaining a sample colon cancer risk early screening prediction result.
The establishment of the effective colon cancer early screening model comprises the following steps:
step S1.1: preparing electronic medical record data: collecting electronic medical records of patients from an electronic medical record platform of a hospital, and collecting electronic medical records of colon cancer patients and non-colon cancer patients as diagnosis results;
step S1.2: the medical characteristic extraction step:
performing colon cancer medical feature extraction on the qualified electronic medical record data obtained in the step S1.1, and extracting medical features and medical feature values;
step S1.3: the method comprises the following steps of characteristic data standardization and data cleaning:
carrying out characteristic data standardization on the large data information of colon cancer clinical manifestations obtained in the step S1.2, removing data with missing values, and obtaining a standard data sample, wherein the standard data sample comprises a standard medical data set and a standard diagnosis result set;
step S1.4: and (3) feature screening:
combining the colon cancer related characteristics provided by a colon cancer expert, calculating a standard data sample by using a statistical method, screening out the colon cancer related characteristics, summarizing the inspection and symptom characteristics for early screening of colon cancer to obtain a selected medical characteristic data set, calculating the standard data sample, and screening out the colon cancer related characteristics by using a multiple of difference and T test;
step S1.5: splitting a characteristic data set; randomly dividing the selected characteristic data set obtained in the step S1.3 into 4 parts by using a sample function in an R base packet, selecting 3 parts as a training data set of the model, and using the rest part as a test data set of the model;
step S1.6: training data to obtain a colon cancer risk early screening model, adopting mlr packages of R language, selecting an XGboost learning classifier, and predicting sample classification by fully utilizing medical characteristic data through a machine learning model based on the XGboost;
step S1.7: the colon cancer risk early screening model test comprises the following steps:
the colon cancer early-screening model carries out prediction calculation on the test data set obtained in the step S1.5, calculates specificity, sensitivity and area under the ROC curve (AUC) of the obtained result, and is effective if all three indexes reach 0.95;
step S1.8: establishing an effective colon cancer risk early screening model; and (3) judging the colon cancer early-screening model with the specificity, the sensitivity and the area under the ROC curve (AUC) reaching 0.95 obtained in the steps S1.6 and S1.7 as an effective colon cancer early-screening model, and finally obtaining the colon cancer early-screening model.
Preferably, in step S1, the diagnosis result is that the colon cancer patient is a diagnosed patient, the non-colon cancer patient is a normal physical examination patient who has received the colon cancer patient at the same time, the electronic medical record data includes medical history records, examination and test results, medical orders, mobile phone records, and nursing records, and the examination and test results include medical characteristics and thresholds.
Preferably, the step S1.3 of normalizing the feature data and cleaning the data includes the following two steps:
s1.3.1 standardizing characteristic data, standardizing medical characteristic values, specifically unified symbols, letters, characters and medical codes;
and step S1.3.2, cleaning data, and removing missing data from the normalized medical characteristic data. And (4) removing extreme value data by adopting a 2-time standard deviation method aiming at quantitative data.
Preferably, the step S1.6 of training data to obtain a colon cancer risk early-screening model includes the following two steps:
step S1.6.1: defining model variables, taking the medical characteristic value screened in the step S1.4 as an independent variable, and taking a colon cancer diagnosis result as a dependent variable;
step S1.6.2: and (4) inputting the training data set in the step S1.5 into an XGboost model, optimizing parameters according to cross validation, selecting the model with the highest score of the area under the ROC curve (AUC), and storing the model for testing in the subsequent steps.
Preferably, in step S1.7, the rate of negative judgment in a sample having specificity that is actually negative (not normally diseased) is lower as the specificity is higher.
Preferably, in the step S1.7, the rate of the positive determination in the sample with sensitivity actually positive (colon cancer patient) is lower as the sensitivity is higher.
Preferably, in step S1.7, the ROC curve is a curve plotted according to a series of different two classification thresholds with sensitivity as ordinate and false positive rate (1-specificity) as abscissa.
Preferably, in step S2, when sample data to be screened is collated, the hospital or the physical examination center provides user data to be screened, and performs data standardization on the provided user data with screening.
Preferably, in step S3, inputting the standardized sample data of the user to be screened into the colon cancer risk early screening model to perform model prediction to calculate a score, and finally obtaining a colon cancer risk prediction result.
Compared with the prior art, the invention has the following beneficial effects:
according to the AI colon cancer risk early screening modeling method based on the electronic medical record, provided by the invention, the machine learning XGboost algorithm is adopted to train the colon cancer early screening model, the early stage morbidity probability score of the colon cancer of a sample can be predicted according to the related medical characteristics of the electronic medical record, the specificity, the sensitivity and the ROCAC can be as high as 0.95, the method has the advantages of being capable of screening in a large scale, high in efficiency and high in accuracy, and the problem that the existing colon cancer risk screening needs inspectors to inspect in hospitals, and the lower inspection efficiency is caused by combination of clinical guidelines and practical experience judgment of doctors is solved, so that medical resources can be effectively saved.
Drawings
FIG. 1 is a flow chart of a method for establishing an effective colon cancer early screening model according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: an AI colon cancer risk early screening modeling method based on an electronic medical record comprises the following steps:
step S1: establishing an effective colon cancer risk early screening model;
step S2: arranging sample data to be screened;
step S3: and inputting the sample with the screening into a colon cancer early screening model to perform model calculation scoring, and finally obtaining a sample colon cancer risk early screening prediction result.
The establishment of the effective colon cancer early screening model comprises the following steps:
step S1.1: preparing electronic medical record data: collecting electronic medical records of patients from an electronic medical record platform of a hospital, and collecting electronic medical records of colon cancer patients and non-colon cancer patients as diagnosis results;
step S1.2: the medical characteristic extraction step:
performing colon cancer medical feature extraction on the qualified electronic medical record data obtained in the step S1.1, and extracting medical features and medical feature values;
step S1.3: the method comprises the following steps of characteristic data standardization and data cleaning:
carrying out characteristic data standardization on the big data information of the colon cancer clinical manifestation obtained in the step S1.2, removing data with missing values, and obtaining a standard data sample, wherein the standard data sample comprises a standard medical data set and a standard diagnosis result set;
further, step S1.3 includes the following two steps:
s1.3.1 standardizing characteristic data, standardizing medical characteristic values, specifically unified symbols, letters, characters and medical codes;
and step S1.3.2, cleaning data, and removing missing data from the normalized medical characteristic data. Eliminating extreme value data by adopting 2-time standard deviation method aiming at quantitative data
Step S1.4: and (3) feature screening:
combining the colon cancer related characteristics provided by a colon cancer expert, calculating a standard data sample by using a statistical method, screening out the colon cancer related characteristics, summarizing the inspection and symptom characteristics for early screening of colon cancer to obtain a selected medical characteristic data set, calculating the standard data sample, and screening out the colon cancer related characteristics by using a multiple of difference and T test;
specifically, the difference multiple and the T test are common methods, belong to the prior art, a computer program which applies the difference multiple and the T test R is an existing computer program, and also belong to the prior art, the invention only applies the statistical method and related software to calculate to obtain the difference multiple fold and the probability value P, the set fold is 2-fold difference, and the P value is less than 0.05, so that the selected characteristics and the colon cancer diagnosis can be considered to have extremely obvious correlation, and the characteristics are selected to suggest a model to be reasonable.
Step S1.5: splitting a characteristic data set; randomly dividing the selected characteristic data set obtained in the step S1.3 into 4 parts by using a sample function in an R base packet, selecting 3 parts as a training data set of the model, and using the rest part as a test data set of the model;
step S1.6: training data to obtain a colon cancer risk early screening model, adopting mlr packages of R language, selecting an XGboost learning classifier, and predicting sample classification by fully utilizing medical characteristic data through a machine learning model based on the XGboost;
further, the step of obtaining the colon cancer risk early screening model by training data in the step S1.6 comprises the following two steps:
step S1.6.1: defining model variables, taking the medical characteristic value screened in the step S1.4 as an independent variable, and taking a colon cancer diagnosis result as a dependent variable;
step S1.6.2: inputting the training data set in the step S1.5 into an XGboost model, performing parameter optimization according to cross validation, selecting a model with the highest area under the ROC curve (AUC) score, and storing the model for testing in subsequent steps;
specifically, the XGBoost algorithm is an improved algorithm based on the GBDT (gradient spanning tree) principle, can implement parallel operation and incremental learning, and can process large-scale data.
Step S1.7: the colon cancer risk early screening model test comprises the following steps:
the colon cancer early-screening model carries out prediction calculation on the test data set obtained in the step S1.5, calculates specificity, sensitivity and area under the ROC curve (AUC) of the obtained result, and is effective if all three indexes reach 0.95;
further, if one or more of the three indexes do not reach 0.95, the step S1.6.2 is returned, the training data set is used again for algorithm parameter adjustment, a new colon cancer risk screening parameter set is obtained again, and a colon cancer risk early screening model is obtained again;
step S1.8: establishing an effective colon cancer risk early screening model; and (3) judging the colon cancer early-screening model with the specificity, the sensitivity and the area under the ROC curve (AUC) reaching 0.95 obtained in the steps S1.6 and S1.7 as an effective colon cancer early-screening model, and finally obtaining the colon cancer early-screening model.
Further, in step S1, the diagnosis result is that the colon cancer patient is a diagnosed patient, the non-colon cancer patient is a normal physical examination patient who has not been suffered from a disease and is received contemporaneously, the electronic medical record data includes medical history records, examination and inspection results, medical orders, mobile phone records, and nursing records, and the examination and inspection results include medical characteristics and threshold values.
Further, in step S2, when sample data to be screened is collated, the hospital or the physical examination center provides user data to be screened, and performs data standardization on the provided user data with screening.
Further, in step S3, inputting the standardized sample data of the user to be screened into the colon cancer risk early screening model to perform model prediction to calculate a score, and finally obtaining a colon cancer risk prediction result.
In summary, the AI colon cancer risk early-screening modeling method based on the electronic medical record provided by the invention adopts the machine learning XGboost algorithm to train the colon cancer early-screening model, can predict the early-stage morbidity probability score of the sample colon cancer according to the relevant medical characteristics of the electronic medical record, has the advantages of high specificity, high sensitivity and ROCAC (rock-roc-curve coefficient) of 0.95, can screen in a large scale and with high efficiency and high accuracy, solves the problem that the current colon cancer risk screening needs inspectors to check in hospitals, and is lower in inspection efficiency due to the combination of clinical guidelines and practical experience judgment of doctors, thereby effectively saving medical resources.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. An AI colon cancer risk early screening modeling method based on an electronic medical record is characterized by comprising the following steps:
step S1: establishing an effective colon cancer risk early screening model;
step S2: arranging sample data to be screened;
step S3: inputting the sample with the screening into a colon cancer early screening model to perform model calculation scoring, and finally obtaining a sample colon cancer risk early screening prediction result;
the establishment of the effective colon cancer early screening model comprises the following steps:
step S1.1: preparing electronic medical record data: collecting electronic medical records of patients from an electronic medical record platform of a hospital, and collecting electronic medical records of colon cancer patients and non-colon cancer patients as diagnosis results;
step S1.2: the medical characteristic extraction step:
performing colon cancer medical feature extraction on the qualified electronic medical record data obtained in the step S1.1, and extracting medical features and medical feature values;
step S1.3: the method comprises the following steps of characteristic data standardization and data cleaning:
carrying out characteristic data standardization on the large data information of colon cancer clinical manifestations obtained in the step S1.2, removing data with missing values, and obtaining a standard data sample, wherein the standard data sample comprises a standard medical data set and a standard diagnosis result set;
step S1.4: and (3) feature screening:
combining the colon cancer related characteristics provided by a colon cancer expert, calculating a standard data sample by using a statistical method, screening out the colon cancer related characteristics, summarizing the inspection and symptom characteristics for early screening of colon cancer to obtain a selected medical characteristic data set, calculating the standard data sample, and screening out the colon cancer related characteristics by using a multiple of difference and T test;
step S1.5: splitting a characteristic data set; randomly dividing the selected characteristic data set obtained in the step S1.3 into 4 parts by using a sample function in an R base packet, selecting 3 parts as a training data set of the model, and using the rest part as a test data set of the model;
step S1.6: training data to obtain a colon cancer risk early screening model, adopting mlr packages of R language, selecting an XGboost learning classifier, and predicting sample classification by fully utilizing medical characteristic data through a machine learning model based on the XGboost;
step S1.7: the colon cancer risk early screening model test comprises the following steps:
the colon cancer early-screening model carries out prediction calculation on the test data set obtained in the step S1.5, calculates specificity, sensitivity and area under the ROC curve (AUC) of the obtained result, and is effective if all three indexes reach 0.95;
step S1.8: establishing an effective colon cancer risk early screening model; and (4) judging the colon cancer early screening model with the specificity, the sensitivity and the area under the ROC curve (AUC) reaching 0.95 obtained in the steps S1.6 and S1.7 as an effective colon cancer early screening model, and finally obtaining the colon cancer early screening model.
2. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in step S1, the diagnosis result is that the colon cancer patient is a diagnosed patient, the non-colon cancer patient is a normal physical examination patient who has received the colon cancer patient at the same time, the electronic medical record data includes a medical history record, an examination and inspection result, a medical order, a mobile phone record, and a nursing record, and the examination and inspection result includes medical characteristics and a threshold.
3. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: step S1.3, the steps of characteristic data standardization and data cleaning comprise the following two steps:
s1.3.1 standardizing characteristic data, standardizing medical characteristic values, specifically unified symbols, letters, characters and medical codes;
and step S1.3.2, cleaning data, and removing missing data from the normalized medical characteristic data. And (4) removing extreme value data by adopting a 2-time standard deviation method aiming at quantitative data.
4. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: the step S1.6 of obtaining the colon cancer risk early screening model by training data comprises the following two steps:
step S1.6.1: defining model variables, taking the medical characteristic value screened in the step S1.4 as an independent variable, and taking a colon cancer diagnosis result as a dependent variable;
step S1.6.2: and (4) inputting the training data set in the step S1.5 into an XGboost model, optimizing parameters according to cross validation, selecting the model with the highest score of the area under the ROC curve (AUC), and storing the model for testing in the subsequent steps.
5. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in step S1.7, in the sample whose specificity is actually negative (not normally diseased), the rate of negative is determined, and the higher the specificity is, the lower the misdiagnosis rate is.
6. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in step S1.7, in the sample whose sensitivity is actually positive (colon cancer patient), the rate of diagnosis omission is determined to be positive, and the higher the sensitivity is, the lower the rate of diagnosis omission is.
7. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in step S1.7, the ROC curve is a curve drawn according to a series of different secondary classification thresholds, with sensitivity as the ordinate and false positive rate (1-specificity) as the abscissa.
8. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in step S2, when sample data to be screened is sorted, the hospital or the physical examination center provides user data to be screened, and performs data standardization on the provided user data with screening.
9. The AI colon cancer risk early-screening modeling method based on electronic medical record of claim 1, wherein: in the step S3, inputting the standardized user sample data to be screened into the colon cancer risk early screening model to perform model prediction to calculate scores, and finally obtaining a colon cancer risk prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210215584.9A CN114724721A (en) | 2022-03-10 | 2022-03-10 | AI colon cancer risk early screening modeling method based on electronic medical record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210215584.9A CN114724721A (en) | 2022-03-10 | 2022-03-10 | AI colon cancer risk early screening modeling method based on electronic medical record |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114724721A true CN114724721A (en) | 2022-07-08 |
Family
ID=82236878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210215584.9A Pending CN114724721A (en) | 2022-03-10 | 2022-03-10 | AI colon cancer risk early screening modeling method based on electronic medical record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114724721A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486921A (en) * | 2023-03-31 | 2023-07-25 | 北京大学深圳医院（北京大学深圳临床医学院） | Breast cancer risk prediction method based on electronic medical record big data |
-
2022
- 2022-03-10 CN CN202210215584.9A patent/CN114724721A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486921A (en) * | 2023-03-31 | 2023-07-25 | 北京大学深圳医院（北京大学深圳临床医学院） | Breast cancer risk prediction method based on electronic medical record big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108806792B (en) | Deep learning face diagnosis system | |
| CN111710420B (en) | Complication onset risk prediction method, system, terminal and storage medium based on electronic medical record big data | |
| CN111476774B (en) | Intelligent sign recognition device based on novel coronavirus pneumonia CT detection | |
| CN111739641A (en) | Gastric cancer risk prediction method and system, computer equipment and readable storage medium | |
| CN109785973B (en) | Quantitative prediction method for complications of surgical patients in perioperative period | |
| KR20170061222A (en) | The method for prediction health data value through generation of health data pattern and the apparatus thereof | |
| CN108511055A (en) | Ventricular premature beat identifying system and method based on Multiple Classifier Fusion and diagnostic rule | |
| CN110189824B (en) | Prognosis grouping method, device and system for primary liver cancer radical resection | |
| CN109273094A (en) | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on Boosting algorithm | |
| KR20100021804A (en) | Method and apparatus of diagnosing prostate cancer | |
| CN114724721A (en) | AI colon cancer risk early screening modeling method based on electronic medical record | |
| CN109215781A (en) | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on logistic algorithm | |
| Perumal et al. | Prediction of COVID criticality score with laboratory, clinical and CT images using hybrid regression models | |
| CN113128654B (en) | Improved random forest model for coronary heart disease pre-diagnosis and pre-diagnosis system thereof | |
| Bhanushali et al. | WOMEN'S BREAST CANCER PREDICTED USING THE RANDOM FOREST APPROACH AND COMPARISON WITH OTHER METHODS | |
| CN117116477A (en) | Construction method and system of prostate cancer disease risk prediction model based on random forest and XGBoost | |
| Bhaskar et al. | Pulmonary lung nodule detection and classification through image enhancement and deep learning | |
| Beaulah et al. | Lung Melanoma Recognition through Platelet Count Composition Using Supervised ML Technique | |
| TWI790479B (en) | Physiological status evaluation method and physiological status evaluation device | |
| CN113707327A (en) | Multi-tumor marker tumor diagnosis model based on medical big data | |
| CN109492690B (en) | Method for detecting CT image based on convolutional neural network | |
| Chen et al. | Using Machine Learning Techniques to Predict Recurrent Breast Cancer in Taiwan | |
| CN112259231A (en) | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system | |
| CN114550921A (en) | Risk of illness prediction modeling method based on LI-RADS classification | |
| Liu et al. | Traditional Chinese medicine constitution and clinical data association with machine learning for prediction of spontaneous abortion |
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 |