CN115497630B - Method and system for processing acute severe ulcerative colitis data - Google Patents
Method and system for processing acute severe ulcerative colitis data Download PDFInfo
- Publication number
- CN115497630B CN115497630B CN202211016121.6A CN202211016121A CN115497630B CN 115497630 B CN115497630 B CN 115497630B CN 202211016121 A CN202211016121 A CN 202211016121A CN 115497630 B CN115497630 B CN 115497630B
- Authority
- CN
- China
- Prior art keywords
- hormone
- value
- intravenous
- uceis
- crp
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 60
- 206010009900 Colitis ulcerative Diseases 0.000 title claims abstract description 41
- 201000006704 Ulcerative Colitis Diseases 0.000 title claims abstract description 41
- 230000001154 acute effect Effects 0.000 title claims abstract description 37
- 239000005556 hormone Substances 0.000 claims abstract description 99
- 229940088597 hormone Drugs 0.000 claims abstract description 99
- 238000001990 intravenous administration Methods 0.000 claims abstract description 64
- 238000000605 extraction Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims description 45
- 206010009887 colitis Diseases 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000009533 lab test Methods 0.000 claims description 10
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 210000000601 blood cell Anatomy 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 230000000740 bleeding effect Effects 0.000 claims description 7
- 238000000556 factor analysis Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000003672 processing method Methods 0.000 claims description 7
- 238000003657 Likelihood-ratio test Methods 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 6
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 5
- 239000003862 glucocorticoid Substances 0.000 claims description 5
- 230000036262 stenosis Effects 0.000 claims description 5
- 208000037804 stenosis Diseases 0.000 claims description 5
- 208000025865 Ulcer Diseases 0.000 claims description 4
- 230000000968 intestinal effect Effects 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 238000011868 Wald Chi square test Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001839 endoscopy Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 231100000397 ulcer Toxicity 0.000 claims description 3
- 230000002792 vascular Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 238000002790 cross-validation Methods 0.000 claims 1
- 108010074051 C-Reactive Protein Proteins 0.000 description 41
- 102100032752 C-reactive protein Human genes 0.000 description 41
- 208000032843 Hemorrhage Diseases 0.000 description 7
- 238000012795 verification Methods 0.000 description 7
- 238000012216 screening Methods 0.000 description 4
- 210000003462 vein Anatomy 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 208000035861 hematochezia Diseases 0.000 description 3
- 229960000598 infliximab Drugs 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- PMATZTZNYRCHOR-CGLBZJNRSA-N Cyclosporin A Chemical compound CC[C@@H]1NC(=O)[C@H]([C@H](O)[C@H](C)C\C=C\C)N(C)C(=O)[C@H](C(C)C)N(C)C(=O)[C@H](CC(C)C)N(C)C(=O)[C@H](CC(C)C)N(C)C(=O)[C@@H](C)NC(=O)[C@H](C)NC(=O)[C@H](CC(C)C)N(C)C(=O)[C@H](C(C)C)NC(=O)[C@H](CC(C)C)N(C)C(=O)CN(C)C1=O PMATZTZNYRCHOR-CGLBZJNRSA-N 0.000 description 2
- 108010036949 Cyclosporine Proteins 0.000 description 2
- 241000701022 Cytomegalovirus Species 0.000 description 2
- 208000012671 Gastrointestinal haemorrhages Diseases 0.000 description 2
- 206010061218 Inflammation Diseases 0.000 description 2
- 208000022559 Inflammatory bowel disease Diseases 0.000 description 2
- 239000000090 biomarker Substances 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 229960001265 ciclosporin Drugs 0.000 description 2
- 230000000112 colonic effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000001794 hormone therapy Methods 0.000 description 2
- JYGXADMDTFJGBT-VWUMJDOOSA-N hydrocortisone Chemical compound O=C1CC[C@]2(C)[C@H]3[C@@H](O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 JYGXADMDTFJGBT-VWUMJDOOSA-N 0.000 description 2
- 230000004054 inflammatory process Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- VHRSUDSXCMQTMA-PJHHCJLFSA-N 6alpha-methylprednisolone Chemical compound C([C@@]12C)=CC(=O)C=C1[C@@H](C)C[C@@H]1[C@@H]2[C@@H](O)C[C@]2(C)[C@@](O)(C(=O)CO)CC[C@H]21 VHRSUDSXCMQTMA-PJHHCJLFSA-N 0.000 description 1
- 108010088751 Albumins Proteins 0.000 description 1
- 102000009027 Albumins Human genes 0.000 description 1
- 241000193163 Clostridioides difficile Species 0.000 description 1
- 229930105110 Cyclosporin A Natural products 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 208000035965 Postoperative Complications Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 206010057071 Rectal tenesmus Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011088 calibration curve Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 210000001072 colon Anatomy 0.000 description 1
- 229930182912 cyclosporin Natural products 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000013872 defecation Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000001079 digestive effect Effects 0.000 description 1
- 230000009266 disease activity Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 230000003054 hormonal effect Effects 0.000 description 1
- 229960000890 hydrocortisone Drugs 0.000 description 1
- 229960003444 immunosuppressant agent Drugs 0.000 description 1
- 230000001861 immunosuppressant effect Effects 0.000 description 1
- 239000003018 immunosuppressive agent Substances 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 208000027866 inflammatory disease Diseases 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 229960004584 methylprednisolone Drugs 0.000 description 1
- 230000000813 microbial effect Effects 0.000 description 1
- 210000004877 mucosa Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 238000009118 salvage therapy Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 229940037128 systemic glucocorticoids Drugs 0.000 description 1
- 208000012271 tenesmus Diseases 0.000 description 1
- 230000036269 ulceration Effects 0.000 description 1
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
- G16H50/70—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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The application discloses a method, a system, equipment and a computer readable storage medium for processing acute severe ulcerative colitis data, wherein the method comprises the following steps: obtaining a prediction factor of a sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment; respectively carrying out feature extraction on the predictive factors of the sample to be detected to obtain the predictive factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features; and obtaining the effective risk value of the intravenous hormone based on the UCEIS scoring characteristic and the CRP value characteristic. The clinical difficult problem is solved by simply and intuitively evaluating the data of the sample to be tested, and the method has important clinical value and application scene.
Description
Technical Field
The application relates to the field of microbial data analysis, in particular to a method and a system for processing acute severe ulcerative colitis data.
Background
Ulcerative colitis (ulcerative colitis, UC) is a chronic, non-specific inflammatory disease of the intestinal tract, which is manifested by hematochezia, diarrhea, tenesmus, decreased body mass, fever, etc. 20% -30% of UC patients develop at least one severe episode in the course of the disease, i.e. acute severe ulcerative colitis (acute severe ulcerative colitis, ASUC). Intravenous use of glucocorticoids (hereinafter intravenous hormones) is a first-line treatment of ASUC, but more than 30% of patients are resistant to hormones and require conversion therapy, which includes drug rescue therapy or surgical therapy, which mainly includes cyclosporin (ciclosporin) and Infliximab (IFX).
ASUC is an acute medical condition that requires a clinician to quickly judge and administer appropriate treatment, and untimely changeover treatment can lead to increased risk of adverse patient outcomes and complications. Thus, early prediction of the outcome of intravenous hormonal therapy is of great clinical significance.
There are currently three predictions of ASUC intravenous hormone therapy outcome:
1. predicting the biomarker; biomarkers such as C-reactive protein (CRP), blood sedimentation (ESR), albumin (Alb) and the like can reflect the activity level of inflammation of patients and are considered to be important factors for prediction of the ASUC venous hormone outcome. Studies have shown that 3-8 times per day in combination with CRP > 45mg/L on day 3of intravenous hormone treatment can accurately predict whether a colorectal resection will ultimately be accepted in 85% of patients. However, an study involving 54 ASUC patients in australia showed that CRP could not accurately predict whether surgery was ultimately accepted for patients receiving IFX shift treatment following intravenous hormone treatment. Thus, the specific predictive value of CRP remains to be further determined. In addition to CRP, ESR, alb are also considered as important factors for prediction of the ASUC venous hormone outcome, but current studies report a different evaluation of the predictive value of these two indicators.
2. Predicting the performance of an endoscope; international IBD research organization expert opinion indicates that endoscopic inflammatory manifestations are the most important clinical factors in determining the extent of ulcerative colitis disease activity. Studies as early as 1994 indicated that deep ulcers in the colon under endoscopy could predict whether an ASUC patient will eventually operate. With the proposal and popularization of the endoscopic Mayo score and the UCEIS score, the use of endoscopic manifestations to predict the clinical outcome of intravenous hormone treatment for ASUC patients becomes a quantifiable, reproducible, verifiable process. However, at present, the problems of optimal cut-off points for UCEIS prediction, predictive value of UCEIS for different outcomes and the like still do not have consistent conclusions.
In addition, there is no current study to incorporate endoscopes into the integrated predictive score. How to predict performance of endoscopes compared with the existing scoring system, how to predict the prediction effect of individual endoscope scoring compared with clinical/endoscope composite scoring, and the like are all problems which need to be concerned and explored at present.
3. Predicting by a comprehensive scoring system; a plurality of comprehensive scoring systems combining the defecation times, hematochezia conditions and inflammation indexes of patients are internationally established and are used for predicting the clinical outcome of ASUC patients and guiding time nodes of curative effect judgment and conversion treatment. Widely used scoring systems include Oxford index, ho index, and the like. However, the existing comprehensive scoring system has the following problems:
(1) predictive ability was not fully validated, scoring system predictive efficacy was lower in the validation queue than in the original literature report: only two studies currently retrospectively verify the predictive efficacy of each comprehensive scoring system; of these, a large retrospective study involving 980 ASUC patients showed that only about 30% of patients with Oxford and Ho indices scored into the high risk category were eventually operated on (the original literature reported a positive predictive value of 85%);
(2) each scoring system is established before the biological preparation is widely applied to ulcerative colitis treatment, and the prediction capability and clinical applicability of each scoring system in the biological preparation era are required to be further verified;
(3) the parameter dimension is single, and the performance of the non-incorporated endoscope is evaluated: existing scoring systems rely primarily on patient clinical performance in combination with laboratory indicators to predict, and no scoring system has been incorporated into patient endoscopic performance.
In order to solve the problems, the application provides a method and a system for processing acute severe ulcerative colitis data, and a new model for predicting the outcome of intravenous hormone treatment by combining clinical information, endoscopic performance and laboratory indexes of ASUC patients.
Disclosure of Invention
According to the method, the multidimensional parameters are included, so that a processing prediction model integrating the clinical information of the ASUC patient, the endoscope performance and the laboratory index data is established, and the evaluation prediction performance is more comprehensive, more stable and more credible; meanwhile, the model can carry out simple and visual risk assessment on the data of the sample, solves the clinical difficult problem, and has important clinical value and application scene.
The application discloses a method for processing acute severe ulcerative colitis data, which comprises the following steps:
obtaining a prediction factor of a sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
respectively carrying out feature extraction on the predictive factors of the sample to be detected to obtain the predictive factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
and obtaining the effective risk value of the intravenous hormone based on the UCEIS scoring characteristic and the CRP value characteristic.
The risk value acquisition method comprises the following steps: riskvalue=β0+β1×a+β2×b;
where a is the UCEIS scoring characteristic and b is the CRP value characteristic of the third day of intravenous hormone treatment.
The processing method further comprises the following steps: based on the risk value, obtaining a hormone resistance or hormone effective classification result; hormone is effective less than or equal to the risk value classification threshold, and hormone resistance greater than or equal to the risk value classification threshold.
The classification result is obtained based on a colitis short-term outcome prediction model;
optionally, the training method of the colitis short-term outcome prediction model includes:
obtaining a predictive factor and a classification label of a training set sample, wherein the label comprises hormone resistance and hormone effectiveness;
extracting features of the predictive factors of the training set samples to obtain the predictive factors of the training set samples after feature extraction; the predictive factors of the training set sample comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
and constructing a model by using the predictive factors of the training set samples to obtain a constructed colitis short-term ending predictive model.
The method or the step for obtaining the predictive factor of the training set sample comprises the following steps: acquiring original prediction data of a training set sample; respectively carrying out feature extraction on the original prediction data to obtain original prediction data after feature extraction; performing first data processing on the original predicted data after the feature extraction to obtain a result after the first data processing; performing second data processing on the result after the first data processing to obtain a result after the second data processing;
optionally, the result after the first data processing includes: platelet count at admission, CRP value at day 3of intravenous hormone treatment, glucocorticoid administration history within 1 month prior to this admission, UCEIS score prior to intravenous hormone treatment;
optionally, the result after the second data processing includes: CRP values on day 3of intravenous hormone treatment, UCEIS score prior to intravenous hormone treatment;
optionally, the method of the first data processing includes, but is not limited to, one or several of the following: single factor analysis, optimal subset regression, lasso regression and cross verification, condition parameter estimation likelihood ratio test, maximum bias likelihood estimation likelihood ratio test and Wald chi-square test;
optionally, the second data processing method includes, but is not limited to, one or more of the following: multi-factor analysis, random forest, decision tree, limit gradient lifting and support vector machine;
the original predicted data of the training set samples comprises: endoscope related indicators and laboratory examination indicators; the endoscope related index comprises a CRP value, wherein the CRP value is a value before receiving intravenous hormone treatment after admission and 1 day, 3 days and 5 days after receiving the intravenous hormone treatment; the laboratory test indicators include UCEIS scores;
optionally, the endoscope related index further includes one or more of the following: endoscopy Mayo score, vascular texture index, bleeding index, erosion and ulcer index, intestinal lumen stenosis index, and rectal exemption index.
Optionally, the laboratory test index further includes: whole blood cell analysis, ESR, alb test results;
optionally, the laboratory test indexes are laboratory test indexes at different time points, and specifically include: whole blood cell analysis, ESR, alb test results 1 day, 3 days, 5 days after admission, before receiving intravenous hormone treatment;
optionally, the raw prediction data of the training set sample further comprises a comprehensive scoring system, wherein the comprehensive scoring system comprises an Oxford index and a Ho index.
Model construction is carried out on the predictive factors of the training set samples by using a machine learning method, and a constructed colonitis short-term ending predictive model is obtained;
optionally, the machine learning method includes one or more of the following: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightGBM, limit gradient boosting (XGB);
a device for processing acute severe ulcerative colitis data, the device comprising: a memory and a processor;
the memory is used for storing program instructions;
the processor is configured to invoke program instructions, which when executed, are configured to perform a method of processing acute severe ulcerative colitis data as described above.
A system for processing acute severe ulcerative colitis data, comprising:
the acquisition unit is used for acquiring the prediction factor of the sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
the processing unit is used for respectively carrying out feature extraction on the prediction factors of the sample to be detected to obtain the prediction factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
and the output unit is used for obtaining the risk value of the venous hormone effect based on the UCEIS scoring characteristic and the CRP value characteristic.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of processing acute severe ulcerative colitis data as described above.
The application has the following beneficial effects:
1. the application creatively discloses a novel method for processing acute severe ulcerative colitis data, which establishes a processing prediction model integrating ASUC patient clinical information, endoscope performance and laboratory index data, and compared with the prior model, the prediction model incorporates multidimensional parameters, in particular endoscope quantization scores, so that the evaluation prediction performance is more comprehensive, more stable and more credible, and the accuracy and depth of data analysis are greatly improved;
2. the application creatively evaluates the prediction capability of laboratory indexes under different time nodes after using vein hormone and the prediction capability of different terms of UCEIS endoscope scores, thereby more comprehensively evaluating the prediction factor of the ASUC outcome of the treatment of the vein hormone;
3. according to the model established in the application, simple and visual risk assessment is carried out on sample data, so that the clinical problem is solved, and the method has important clinical value and application scene.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for processing acute severe ulcerative colitis data provided by an embodiment of the application;
fig. 2 is a schematic diagram of a processing device for acute severe ulcerative colitis data according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a processing system for acute severe ulcerative colitis data provided by an embodiment of the application;
FIG. 4 is a table of regression analysis of the relevant factors for the outcome of intravenous hormone treatment of patients with ASUC according to the examples of the present application;
fig. 5 is an alignment chart created from a short-term outcome prediction model for colitis provided by an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present application and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments according to the application without any creative effort, are within the protection scope of the application.
Fig. 1 is a schematic flow chart of a method for processing acute severe ulcerative colitis data according to an embodiment of the present application, specifically, the method includes the following steps:
101: obtaining a prediction factor of a sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
in one embodiment, the predictor of the test sample uses P value <0.05 as the screening threshold.
102: respectively carrying out feature extraction on the predictive factors of the sample to be detected to obtain the predictive factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
103: obtaining a risk value of the venous hormone effectiveness based on the UCEIS scoring characteristic and the CRP value characteristic;
in one embodiment, the method for acquiring the risk value includes: riskvalue=β0+β1×a+β2×b;
wherein a is UCEIS scoring characteristic, and b is CRP value characteristic of the third day of intravenous hormone treatment; β0 is the coefficient, the value is-12.871, β1 is the coefficient of UCEIS, the value is 1.543, β2 is the coefficient of CRP on the third day of intravenous hormone treatment, and the value is 0.053. When in use, a and b of the sample to be detected are directly input to obtain the Riskvalue of the sample to be detected.
In one embodiment, the processing method further comprises: based on the risk value, obtaining a hormone resistance or hormone effective classification result; hormone is effective less than or equal to the risk value classification threshold, and hormone resistance greater than or equal to the risk value classification threshold.
The classification result is obtained based on a colitis short-term outcome prediction model; the training method of the colitis short-term outcome prediction model comprises the following steps:
obtaining a predictive factor and a classification label of a training set sample, wherein the label comprises hormone resistance and hormone effectiveness;
extracting features of the predictive factors of the training set samples to obtain the predictive factors of the training set samples after feature extraction; the predictive factors of the training set sample comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
and constructing a model by using the predictive factors of the training set samples to obtain a constructed colitis short-term ending predictive model.
In one embodiment, the method or step of obtaining the predictor of the training set sample includes: acquiring original prediction data of a training set sample; respectively carrying out feature extraction on the original prediction data to obtain original prediction data after feature extraction; performing first data processing on the original predicted data after the feature extraction to obtain a result after the first data processing; performing second data processing on the result after the first data processing to obtain a result after the second data processing;
optionally, the result after the first data processing includes: platelet count at admission, CRP value at day 3of intravenous hormone treatment, glucocorticoid administration history within 1 month prior to this admission, UCEIS score prior to intravenous hormone treatment; the application considers sufficient statistical performance when screening with data processing and refers to clinician opinion to screen according to clinical experience and clinical knowledge.
Optionally, the result after the second data processing includes: CRP values on day 3of intravenous hormone treatment, UCEIS score prior to intravenous hormone treatment;
optionally, the method of the first data processing includes, but is not limited to, one or several of the following: single factor analysis, optimal subset regression, lasso regression, cross verification, condition parameter estimation likelihood ratio test, maximum bias likelihood estimation likelihood ratio test and Wald chi-square test; based on the data set in the application, the multi-factor logistic regression obtains the best prediction efficiency after modeling by using the above methods. The preferred method is to evaluate the relevance of each factor to the outcome using single factor logistic regression and calculate the ratio (OR), combining the prior knowledge and clinical experience to perform variable prescreening. And simultaneously, the optimal subset regression, lasso regression and cross verification methods are used for data processing, so that the aim of variable primary screening is fulfilled.
Optionally, the second data processing method includes, but is not limited to, one or more of the following: multi-factor analysis, random forest, decision tree, limit gradient lifting and support vector machine;
optionally, the second data processing method is multi-factor analysis; and (3) obtaining two independent outcome prediction factors, namely a CRP value on the 3 rd day of vein hormone treatment and UCEIS score before vein hormone treatment, by using multi-factor logistic regression analysis, and simultaneously constructing a model and an alignment chart. The accuracy, degree of calibration and clinical utility of the model were analyzed using the area under the subject's working characteristics curve (area under the curve, AUC), calibration curve and decision curve. Internal validation was performed using boottrap method while external validation was performed using ASUC patient data from different central sources.
In one embodiment, the raw prediction data of the training set samples comprises: endoscope related indicators and laboratory examination indicators; the endoscope related index comprises a CRP value, wherein the CRP value is a value before receiving intravenous hormone treatment after admission and 1 day, 3 days and 5 days after receiving the intravenous hormone treatment; the laboratory test indicators include UCEIS scores;
optionally, the endoscope related index further includes one or more of the following: endoscopic Mayo score, vascular texture index (normal, partial disappearance, total disappearance), whether bleeding index (no bleeding, punctiform/linear bleeding of mucosa, mild intracavity bleeding, moderate to severe intracavity bleeding), whether erosive and ulceratory index (no erosive and ulceratory, erosive, superficial ulceratory, deep ulceratory), whether intestinal lumen stenosis index (yes/no intestinal lumen stenosis), whether rectal exemption index (yes/no rectal exemption).
Optionally, the laboratory test index further includes: whole blood cell analysis, ESR, alb test results;
optionally, the laboratory test indexes are laboratory test indexes at different time points, and specifically include: whole blood cell analysis, ESR, alb test results 1 day, 3 days, 5 days after admission, before receiving intravenous hormone treatment;
optionally, the raw prediction data of the training set sample further comprises a comprehensive scoring system, wherein the comprehensive scoring system comprises an Oxford index and a Ho index.
In one embodiment, the training set sample relies on clinical data of digestive departments of two comprehensive hospitals in China, has high data reliability, can embody typical characteristics of the acute severe ulcerative colitis, and has higher irreplaceability; the training set sample is taken into 296 ASUC patients hospitalized in Beijing co-ordinates hospitals from 12 months 2012 to 1 month 2020, and medical record information of the patients is collected and arranged. And then further screening according to the diagnosis standard of the acute severe ulcerative colitis and other input and output standards set by the study, and finally determining to build a training set for 129 patients with the acute severe ulcerative colitis.
In one embodiment, the raw prediction data of the training set samples further comprises: patient demographic information; pre-admission drug use (pre-admission glucocorticoid, immunosuppressant, biologic use); patients who receive intravenous hormone treatment after admission have the symptoms of stool, blood and stool, body temperature, heart rate and extra-intestinal manifestation, and patients who receive intravenous hormone treatment have the symptoms of stool and blood and stool; receiving a whole blood cell analysis before intravenous hormone treatment and a CRP, ESR, alb test result after admission, and a whole blood cell analysis after intravenous hormone treatment and a CRP, ESR, alb test result; cytomegalovirus (CMV) and clostridium difficile (cdiff) infection; endoscopic results: endoscopic severity was quantified using the mayo score (range 0-3) and UCEIS (range 0-8), including three descriptive factors-vascular texture (0-2 minutes), hemorrhage (0-3 minutes), and erosion and ulceration (0-3 minutes), while collecting luminal oedema stenosis and rectal involvement; determining the disease range (rectal involvement E1, left colonic involvement E2, wide colonic involvement E3) according to the montal typing; the hormone type, the using time, the hospitalization time and the conversion treatment type are used, if an operation exists, the operation indication, the operation type and the postoperative complications are recorded;
in one embodiment, the rank criteria for the training set samples include: ASUC-based diagnosis is defined as UC patients meeting the following conditions according to the guidelines of the institute of gastroenterology in the united kingdom for adult inflammatory bowel disease management in 2019: bloodstool is more than or equal to 6 times per day and meets any one of the following: body temperature is more than 37.8 ℃, HR is more than 90bpm, hgb is less than 105g/L, CRP is more than 30mg/L of original predicted data; intravenous hormones are used as first line treatment (hydrocortisone or methylprednisolone) for ASUC patients in this hospitalization; hospitalization time > 24 hours. The exclusion criteria for the training set samples include: intravenous hormone is started to be used before the hospital is admitted; in the subsequent diagnosis and treatment, the pathological examination proves that other diseases are misdiagnosed into ulcerative colitis; the critical clinical information such as endoscopes, laboratory examinations and the like is too much missing.
In one embodiment, SPSS 26.0 (IBM Corp., armonk, NY, USA) and R (4.5.2) were used for data analysis. Descriptive statistics are performed on demographic information, clinical information, endoscope scores, laboratory exam results, and the like.
In one embodiment, a machine learning method is utilized to carry out model construction on the prediction factors of the training set samples, and a constructed colitis short-term outcome prediction model is obtained;
optionally, the machine learning method includes one or more of the following: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightGBM, limit gradient boosting (XGB);
optionally, the machine learning method is as follows: logistic regression. The present application attempts to build models using Decision Tree (DT), random Forest (RF), and extreme gradient boost (XGB) methods and compare the predictive performance between different models. Through the verification of the internal and external verification sets, the model and the alignment chart established based on the logistic method in the research have the highest prediction performance.
FIG. 2 is a schematic diagram of a conventional deviceThe embodiment of the application provides a processing device for acute severe ulcerative colitis data, which comprises: a memory and a processor;
the memory is used for storing program instructions;
the processor is configured to invoke program instructions, which when executed, are configured to perform a method of processing acute severe ulcerative colitis data as described above.
FIG. 3 is a schematic diagram of a preferred embodiment of the present applicationThe application is thatThe embodiment provides a processing system for acute severe ulcerative colitis data, comprising:
an obtaining unit 301, configured to obtain a predictor of a sample to be tested; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
the processing unit 302 is configured to perform feature extraction on the predictors of the sample to be tested, so as to obtain the predictors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
an output unit 303, configured to obtain a risk value for the venous hormone to be effective based on the UCEIS scoring feature and the CRP value feature.
As shown in fig. 4, a table of logistic regression analysis of the factors related to the outcome of intravenous hormone treatment for patients with ASUC, wherein the P value of UCEIS score and CRP at day 3ofIVCS meets the requirements; as shown in fig. 5, for the alignment chart established according to the short-term outcome prediction model of colitis, score Points corresponding to UCEIS score and score Points corresponding to CRP at day 3ofIVCS are obtained respectively, total Points are the result obtained by adding the above 2 Points, total Points correspond to Risk ofIVCS resistance, and risk value is obtained; in the current clinical detection, the risk value classification threshold is 0.9, namely that the risk value is greater than or equal to 0.9 and is hormone resistance, and the risk value is less than or equal to 0.9 and is hormone effective. The risk value classification threshold is not limited to 0.9 but may also be changed according to updates of clinical studies.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of processing acute severe ulcerative colitis data as described above.
The results of the verification of the present verification embodiment show that assigning an inherent weight to an indication may moderately improve the performance of the present method relative to the default settings.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in implementing the methods of the above embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the storage medium may be a read only memory, a magnetic disk or optical disk, etc.
While the foregoing describes a computer device provided by the present application in detail, those skilled in the art will appreciate that the foregoing description is not meant to limit the application thereto, as long as the scope of the application is defined by the claims appended hereto.
Claims (14)
1. A method of processing acute severe ulcerative colitis data, comprising:
obtaining a prediction factor of a sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
respectively carrying out feature extraction on the predictive factors of the sample to be detected to obtain the predictive factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
obtaining a risk value of the venous hormone effectiveness based on the UCEIS scoring characteristic and the CRP value characteristic; the risk value acquisition method comprises the following steps:
a is UCEIS scoring characteristic, b is CRP value characteristic of the third day of intravenous hormone treatment; β0 is the coefficient, the value is-12.871, β1 is the coefficient of UCEIS, the value is 1.543, β2 is the coefficient of CRP on the third day of intravenous hormone treatment, the value is 0.053;
the processing method further comprises the following steps: based on the risk value, obtaining a hormone resistance or hormone effective classification result;
the classification result is obtained based on a colitis short-term outcome prediction model; the training method of the colitis short-term outcome prediction model comprises the following steps: obtaining a predictive factor and a classification label of a training set sample, wherein the label comprises hormone resistance and hormone effectiveness; extracting features of the predictive factors of the training set samples to obtain the predictive factors of the training set samples after feature extraction; the predictive factors of the training set sample comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment; and constructing a model by using the predictive factors of the training set samples to obtain a constructed colitis short-term ending predictive model.
2. The method of claim 1, wherein the risk value classification threshold is less than or equal to hormone-effective and the risk value classification threshold is greater than hormone-resistant; alternatively, a hormone effective value less than the risk value classification threshold and a hormone resistant value greater than or equal to the risk value classification threshold.
3. The method for processing acute severe ulcerative colitis data according to claim 1, wherein the method or step of obtaining the predictor of the training set sample comprises: acquiring original prediction data of a training set sample; respectively carrying out feature extraction on the original prediction data to obtain original prediction data after feature extraction; performing first data processing on the original predicted data after the feature extraction to obtain a result after the first data processing; performing second data processing on the result after the first data processing to obtain a result after the second data processing;
the result after the first data processing includes: platelet count at admission, CRP value at day 3of intravenous hormone treatment, glucocorticoid administration history within 1 month prior to this admission, UCEIS score prior to intravenous hormone treatment;
the second data processed result comprises: CRP values on day 3of intravenous hormone treatment, UCEIS score prior to intravenous hormone treatment.
4. A method of processing acute severe ulcerative colitis data according to claim 3 wherein the method of first data processing includes, but is not limited to, one or more of the following: single factor analysis, optimal subset regression, lasso regression and cross validation, conditional parameter estimation likelihood ratio test, maximum bias likelihood estimation likelihood ratio test, wald chi-square test.
5. A method of processing acute severe ulcerative colitis data according to claim 3 wherein the second data processing method includes, but is not limited to, one or more of the following: multi-factor analysis, random forest, decision tree, limit gradient promotion and support vector machine.
6. The method of processing acute severe ulcerative colitis data according to claim 1, wherein the raw predictive data of the training set samples comprises: endoscope related indicators and laboratory examination indicators; the endoscope related index comprises a CRP value, wherein the CRP value is a value before receiving intravenous hormone treatment after admission and 1 day, 3 days and 5 days after receiving the intravenous hormone treatment; the laboratory test index includes a UCEIS score.
7. The method of claim 6, wherein the endoscope-related indicator further comprises one or more of the following: endoscopy Mayo score, vascular texture index, bleeding index, erosion and ulcer index, intestinal lumen stenosis index, and rectal exemption index.
8. The method of processing acute severe ulcerative colitis data according to claim 6, wherein the laboratory test index further comprises: whole blood cell analysis, ESR, alb test results; the laboratory examination indexes are laboratory examination indexes at different time points, and specifically comprise: whole blood cell analysis, ESR, alb test results 1 day, 3 days, 5 days after admission, before receiving intravenous hormone treatment.
9. The method of claim 6, wherein the raw predictive data of the training set sample further comprises a composite scoring system comprising an Oxford index and a Ho index.
10. The method for processing acute severe ulcerative colitis data according to any one of claims 1-9, wherein the prediction factor of the training set sample is model-constructed by a machine learning method to obtain the constructed short-term outcome prediction model of colitis.
11. The method of processing acute severe ulcerative colitis data according to claim 10, wherein the method of machine learning comprises one or more of: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightweight gradient hoist (LightGBM), limiting gradient hoist (XGB).
12. A device for processing acute severe ulcerative colitis data, the device comprising: a memory and a processor;
the memory is used for storing program instructions;
the processor is configured to invoke program instructions, which when executed, are configured to perform the method of processing acute severe ulcerative colitis data according to any of claims 1-11.
13. A system for processing acute severe ulcerative colitis data, comprising:
the acquisition unit is used for acquiring the prediction factor of the sample to be detected; the predictive factors of the sample to be tested comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment;
the processing unit is used for respectively carrying out feature extraction on the prediction factors of the sample to be detected to obtain the prediction factors after feature extraction; extracting features of the UCEIS score to obtain UCEIS score features; performing feature extraction on the CRP value of the third day of the intravenous hormone treatment to obtain CRP value features;
an output unit for obtaining a risk value for venous hormone effectiveness based on the UCEIS scoring feature and the CRP value feature; the risk value acquisition method comprises the following steps:
a is UCEIS scoring characteristic, b is CRP value characteristic of the third day of intravenous hormone treatment; β0 is the coefficient, the value is-12.871, β1 is the coefficient of UCEIS, the value is 1.543, β2 is the coefficient of CRP on the third day of intravenous hormone treatment, the value is 0.053;
the processing system further includes: based on the risk value, obtaining a hormone resistance or hormone effective classification result;
the classification result is obtained based on a colitis short-term outcome prediction model; the training method of the colitis short-term outcome prediction model comprises the following steps: obtaining a predictive factor and a classification label of a training set sample, wherein the label comprises hormone resistance and hormone effectiveness; extracting features of the predictive factors of the training set samples to obtain the predictive factors of the training set samples after feature extraction; the predictive factors of the training set sample comprise UCEIS scores and CRP values of the third day of intravenous hormone treatment; and constructing a model by using the predictive factors of the training set samples to obtain a constructed colitis short-term ending predictive model.
14. A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of processing acute severe ulcerative colitis data according to any of the preceding claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211016121.6A CN115497630B (en) | 2022-08-24 | 2022-08-24 | Method and system for processing acute severe ulcerative colitis data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211016121.6A CN115497630B (en) | 2022-08-24 | 2022-08-24 | Method and system for processing acute severe ulcerative colitis data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115497630A CN115497630A (en) | 2022-12-20 |
| CN115497630B true CN115497630B (en) | 2023-11-03 |
Family
ID=84465726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211016121.6A Active CN115497630B (en) | 2022-08-24 | 2022-08-24 | Method and system for processing acute severe ulcerative colitis data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115497630B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908096A (en) * | 2010-06-30 | 2010-12-08 | 厦门大学附属中山医院 | Forecasting method of treating effect of interferon on treating chronic hepatitis B |
| CN110993099A (en) * | 2019-12-18 | 2020-04-10 | 山东大学齐鲁医院 | Ulcerative colitis severity evaluation method and system based on deep learning |
| CN113838583A (en) * | 2021-09-27 | 2021-12-24 | 中国人民解放军空军军医大学 | Intelligent drug efficacy evaluation method based on machine learning and application thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7455757B2 (en) * | 2018-04-13 | 2024-03-26 | フリーノーム・ホールディングス・インコーポレイテッド | Machine learning implementation for multianalyte assay of biological samples |
| US20210327540A1 (en) * | 2018-08-17 | 2021-10-21 | Henry M. Jackson Foundation For The Advancement Of Military Medicine | Use of machine learning models for prediction of clinical outcomes |
-
2022
- 2022-08-24 CN CN202211016121.6A patent/CN115497630B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908096A (en) * | 2010-06-30 | 2010-12-08 | 厦门大学附属中山医院 | Forecasting method of treating effect of interferon on treating chronic hepatitis B |
| CN110993099A (en) * | 2019-12-18 | 2020-04-10 | 山东大学齐鲁医院 | Ulcerative colitis severity evaluation method and system based on deep learning |
| CN113838583A (en) * | 2021-09-27 | 2021-12-24 | 中国人民解放军空军军医大学 | Intelligent drug efficacy evaluation method based on machine learning and application thereof |
Non-Patent Citations (2)
| Title |
|---|
| 侯玲玲.双歧杆菌四联活菌片在溃疡性结肠炎治疗中的应用效果.《河南医学研究》.2020,第5118-5120页. * |
| 曹珊等."溃疡性结肠炎患者激素抵抗预测因素分析".《胃肠病学和肝病学杂志》.2010,第1040-1042页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115497630A (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Du et al. | Accurate prediction of coronary heart disease for patients with hypertension from electronic health records with big data and machine-learning methods: model development and performance evaluation | |
| Yu et al. | Predicting metabolic syndrome with machine learning models using a decision tree algorithm: retrospective cohort study | |
| Bai et al. | Development of a machine learning model to predict the risk of late cardiogenic shock in patients with ST-segment elevation myocardial infarction | |
| Ak et al. | Comparison of AIMS65 and Glasgow Blatchford scores in predicting mortality in patients with upper gastrointestinal bleeding | |
| EP4162065A1 (en) | Electronic health record (ehr)-based classifier for acute respiratory distress syndrome (ards) subtyping | |
| CN111081334B (en) | Chronic disease early warning method based on risk factor probability combination analysis | |
| Bai et al. | Using machine learning for the early prediction of sepsis-associated ARDS in the ICU and identification of clinical phenotypes with differential responses to treatment | |
| Pournik et al. | A diagnostic model for cirrhosis in patients with non-alcoholic fatty liver disease: an artificial neural network approach | |
| CN115240855A (en) | Gastric cancer resection postoperative severe complication nursing risk prediction model and construction method thereof | |
| Yang et al. | Development and validation of a prediction model for moderately severe and severe acute pancreatitis in pregnancy | |
| e Silva et al. | Prediction of mortality in coronary artery disease: role of machine learning and maximal exercise capacity | |
| CN115497630B (en) | Method and system for processing acute severe ulcerative colitis data | |
| CN112259219B (en) | System, equipment and storage medium for predicting diseases based on upper gastrointestinal bleeding | |
| Chang et al. | Early prediction of cardiogenic shock using machine learning | |
| Edvinsson et al. | Predicting intensive care need in women with preeclampsia using machine learning–a pilot study | |
| CN115602319B (en) | Noninvasive hepatic fibrosis assessment device | |
| TWI827184B (en) | System and method for assessing risk of type 2 diabetes mellitus complications | |
| CN116580847A (en) | Modeling method and system for prognosis prediction of septic shock | |
| Rubin et al. | Frequency decision theoretical approach to automated medical diagnosis | |
| CN113724873B (en) | Preeclampsia risk prediction method based on MLP multi-platform calibration | |
| CN113488170B (en) | Method for constructing acute pre-uveitis recurrence risk prediction model and related equipment | |
| CN114898859A (en) | Acute aortic dissection hospital internal prognosis prediction system | |
| CN114822691B (en) | Clinical event prediction device based on graph convolution neural network | |
| Wang et al. | Machine learning approaches for early prediction of gestational diabetes mellitus based on prospective cohort study | |
| Yördan et al. | Hybrid AI-Based Chronic Kidney Disease Risk Prediction |
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 |