CN109378072A - A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model - Google Patents
A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model Download PDFInfo
- Publication number
- CN109378072A CN109378072A CN201811192652.4A CN201811192652A CN109378072A CN 109378072 A CN109378072 A CN 109378072A CN 201811192652 A CN201811192652 A CN 201811192652A CN 109378072 A CN109378072 A CN 109378072A
- Authority
- CN
- China
- Prior art keywords
- model
- fasting blood
- blood sugar
- prediction
- early warning
- 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
- 210000004369 blood Anatomy 0.000 title claims abstract description 58
- 239000008280 blood Substances 0.000 title claims abstract description 58
- 235000000346 sugar Nutrition 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000004927 fusion Effects 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 17
- 238000012417 linear regression Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 34
- 239000008103 glucose Substances 0.000 claims abstract description 29
- 238000007637 random forest analysis Methods 0.000 claims abstract description 20
- 210000003743 erythrocyte Anatomy 0.000 claims description 14
- BPYKTIZUTYGOLE-IFADSCNNSA-N Bilirubin Chemical compound N1C(=O)C(C)=C(C=C)\C1=C\C1=C(C)C(CCC(O)=O)=C(CC2=C(C(C)=C(\C=C/3C(=C(C=C)C(=O)N\3)C)N2)CCC(O)=O)N1 BPYKTIZUTYGOLE-IFADSCNNSA-N 0.000 claims description 10
- 208000002672 hepatitis B Diseases 0.000 claims description 10
- 210000001772 blood platelet Anatomy 0.000 claims description 9
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 claims description 8
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 6
- 102000004420 Creatine Kinase Human genes 0.000 claims description 6
- 108010042126 Creatine kinase Proteins 0.000 claims description 6
- 108060003951 Immunoglobulin Proteins 0.000 claims description 6
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 claims description 6
- 239000000427 antigen Substances 0.000 claims description 6
- 102000036639 antigens Human genes 0.000 claims description 6
- 108091007433 antigens Proteins 0.000 claims description 6
- 238000004820 blood count Methods 0.000 claims description 6
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 claims description 6
- 102000018358 immunoglobulin Human genes 0.000 claims description 6
- 210000000265 leukocyte Anatomy 0.000 claims description 6
- 102000001554 Hemoglobins Human genes 0.000 claims description 5
- 108010054147 Hemoglobins Proteins 0.000 claims description 5
- 102000004357 Transferases Human genes 0.000 claims description 5
- 108090000992 Transferases Proteins 0.000 claims description 5
- 210000004698 lymphocyte Anatomy 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 4
- 239000002253 acid Substances 0.000 claims description 4
- 235000012000 cholesterol Nutrition 0.000 claims description 4
- 210000000232 gallbladder Anatomy 0.000 claims description 4
- 210000004185 liver Anatomy 0.000 claims description 4
- HSINOMROUCMIEA-FGVHQWLLSA-N (2s,4r)-4-[(3r,5s,6r,7r,8s,9s,10s,13r,14s,17r)-6-ethyl-3,7-dihydroxy-10,13-dimethyl-2,3,4,5,6,7,8,9,11,12,14,15,16,17-tetradecahydro-1h-cyclopenta[a]phenanthren-17-yl]-2-methylpentanoic acid Chemical compound C([C@@]12C)C[C@@H](O)C[C@H]1[C@@H](CC)[C@@H](O)[C@@H]1[C@@H]2CC[C@]2(C)[C@@H]([C@H](C)C[C@H](C)C(O)=O)CC[C@H]21 HSINOMROUCMIEA-FGVHQWLLSA-N 0.000 claims description 3
- AFENDNXGAFYKQO-VKHMYHEASA-N (S)-2-hydroxybutyric acid Chemical compound CC[C@H](O)C(O)=O AFENDNXGAFYKQO-VKHMYHEASA-N 0.000 claims description 3
- 108090000124 3-hydroxybutyrate dehydrogenases Proteins 0.000 claims description 3
- 102000034279 3-hydroxybutyrate dehydrogenases Human genes 0.000 claims description 3
- 101710169336 5'-deoxyadenosine deaminase Proteins 0.000 claims description 3
- 102000055025 Adenosine deaminases Human genes 0.000 claims description 3
- 108010088751 Albumins Proteins 0.000 claims description 3
- 102000009027 Albumins Human genes 0.000 claims description 3
- 102000002260 Alkaline Phosphatase Human genes 0.000 claims description 3
- 108020004774 Alkaline Phosphatase Proteins 0.000 claims description 3
- 239000004382 Amylase Substances 0.000 claims description 3
- 102000013142 Amylases Human genes 0.000 claims description 3
- 108010065511 Amylases Proteins 0.000 claims description 3
- 241001566735 Archon Species 0.000 claims description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 3
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 claims description 3
- 102000003914 Cholinesterases Human genes 0.000 claims description 3
- 108090000322 Cholinesterases Proteins 0.000 claims description 3
- 102000012192 Cystatin C Human genes 0.000 claims description 3
- 108010061642 Cystatin C Proteins 0.000 claims description 3
- 101710088194 Dehydrogenase Proteins 0.000 claims description 3
- 102000004190 Enzymes Human genes 0.000 claims description 3
- 108090000790 Enzymes Proteins 0.000 claims description 3
- 102000006395 Globulins Human genes 0.000 claims description 3
- 108010044091 Globulins Proteins 0.000 claims description 3
- 102000003886 Glycoproteins Human genes 0.000 claims description 3
- 108090000288 Glycoproteins Proteins 0.000 claims description 3
- 108010023302 HDL Cholesterol Proteins 0.000 claims description 3
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 claims description 3
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 3
- 238000008050 Total Bilirubin Reagent Methods 0.000 claims description 3
- 102000002070 Transferrins Human genes 0.000 claims description 3
- 108010015865 Transferrins Proteins 0.000 claims description 3
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 claims description 3
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 claims description 3
- 235000019418 amylase Nutrition 0.000 claims description 3
- 239000003613 bile acid Substances 0.000 claims description 3
- 239000011575 calcium Substances 0.000 claims description 3
- 229910052791 calcium Inorganic materials 0.000 claims description 3
- 239000004202 carbamide Substances 0.000 claims description 3
- 239000001569 carbon dioxide Substances 0.000 claims description 3
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 3
- 239000000460 chlorine Substances 0.000 claims description 3
- 229910052801 chlorine Inorganic materials 0.000 claims description 3
- 229940048961 cholinesterase Drugs 0.000 claims description 3
- 229940109239 creatinine Drugs 0.000 claims description 3
- 230000035487 diastolic blood pressure Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 229940088598 enzyme Drugs 0.000 claims description 3
- 235000021588 free fatty acids Nutrition 0.000 claims description 3
- 238000005534 hematocrit Methods 0.000 claims description 3
- 229940099472 immunoglobulin a Drugs 0.000 claims description 3
- 229940027941 immunoglobulin g Drugs 0.000 claims description 3
- 239000011777 magnesium Substances 0.000 claims description 3
- 229910052749 magnesium Inorganic materials 0.000 claims description 3
- 239000011574 phosphorus Substances 0.000 claims description 3
- 229910052698 phosphorus Inorganic materials 0.000 claims description 3
- 239000011591 potassium Substances 0.000 claims description 3
- 229910052700 potassium Inorganic materials 0.000 claims description 3
- 235000018102 proteins Nutrition 0.000 claims description 3
- 102000004169 proteins and genes Human genes 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 239000011734 sodium Substances 0.000 claims description 3
- 229910052708 sodium Inorganic materials 0.000 claims description 3
- 150000003626 triacylglycerols Chemical class 0.000 claims description 3
- 229940045136 urea Drugs 0.000 claims description 3
- 229940116269 uric acid Drugs 0.000 claims description 3
- 210000002700 urine Anatomy 0.000 claims description 3
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 claims description 2
- 108010082126 Alanine transaminase Proteins 0.000 claims description 2
- 102000013918 Apolipoproteins E Human genes 0.000 claims description 2
- 108010025628 Apolipoproteins E Proteins 0.000 claims description 2
- 108010074051 C-Reactive Protein Proteins 0.000 claims description 2
- 229910021529 ammonia Inorganic materials 0.000 claims description 2
- 230000008859 change Effects 0.000 claims description 2
- 210000004493 neutrocyte Anatomy 0.000 claims description 2
- -1 r- glutamyl Chemical group 0.000 claims description 2
- 108010007622 LDL Lipoproteins Proteins 0.000 claims 1
- 102000007330 LDL Lipoproteins Human genes 0.000 claims 1
- OUUQCZGPVNCOIJ-UHFFFAOYSA-M Superoxide Chemical class [O-][O] OUUQCZGPVNCOIJ-UHFFFAOYSA-M 0.000 claims 1
- 206010012601 diabetes mellitus Diseases 0.000 abstract description 18
- 230000003907 kidney function Effects 0.000 abstract description 5
- 150000002632 lipids Chemical class 0.000 abstract description 5
- 230000003908 liver function Effects 0.000 abstract description 5
- 238000007689 inspection Methods 0.000 abstract description 4
- 241001269238 Data Species 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 3
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 210000001616 monocyte Anatomy 0.000 description 2
- 230000000291 postprandial effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000002562 urinalysis Methods 0.000 description 2
- 102000057234 Acyl transferases Human genes 0.000 description 1
- 108700016155 Acyl transferases Proteins 0.000 description 1
- 241000700721 Hepatitis B virus Species 0.000 description 1
- FFFHZYDWPBMWHY-VKHMYHEASA-N L-homocysteine Chemical compound OC(=O)[C@@H](N)CCS FFFHZYDWPBMWHY-VKHMYHEASA-N 0.000 description 1
- 108010028554 LDL Cholesterol Proteins 0.000 description 1
- 102000010445 Lactoferrin Human genes 0.000 description 1
- 108010063045 Lactoferrin Proteins 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 208000031662 Noncommunicable disease Diseases 0.000 description 1
- 102000019197 Superoxide Dismutase Human genes 0.000 description 1
- 108010012715 Superoxide dismutase Proteins 0.000 description 1
- 206010067584 Type 1 diabetes mellitus Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 235000004279 alanine Nutrition 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 235000018417 cysteine Nutrition 0.000 description 1
- XUJNEKJLAYXESH-UHFFFAOYSA-N cysteine Natural products SCC(N)C(O)=O XUJNEKJLAYXESH-UHFFFAOYSA-N 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000004104 gestational diabetes Diseases 0.000 description 1
- 210000003714 granulocyte Anatomy 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- CSSYQJWUGATIHM-IKGCZBKSSA-N l-phenylalanyl-l-lysyl-l-cysteinyl-l-arginyl-l-arginyl-l-tryptophyl-l-glutaminyl-l-tryptophyl-l-arginyl-l-methionyl-l-lysyl-l-lysyl-l-leucylglycyl-l-alanyl-l-prolyl-l-seryl-l-isoleucyl-l-threonyl-l-cysteinyl-l-valyl-l-arginyl-l-arginyl-l-alanyl-l-phenylal Chemical compound C([C@H](N)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CS)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CC=1C2=CC=CC=C2NC=1)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CC=1C2=CC=CC=C2NC=1)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](C)C(=O)N1CCC[C@H]1C(=O)N[C@@H](CO)C(=O)N[C@@H]([C@@H](C)CC)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CS)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](C)C(=O)N[C@@H](CC=1C=CC=CC=1)C(O)=O)C1=CC=CC=C1 CSSYQJWUGATIHM-IKGCZBKSSA-N 0.000 description 1
- 229940078795 lactoferrin Drugs 0.000 description 1
- 235000021242 lactoferrin Nutrition 0.000 description 1
- 108010022197 lipoprotein cholesterol Proteins 0.000 description 1
- 210000002751 lymph Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 150000002927 oxygen compounds Chemical class 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000008288 physiological mechanism Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 150000008163 sugars Chemical class 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 208000001072 type 2 diabetes mellitus Diseases 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
- G16H50/30—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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (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 invention discloses a kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model.The present invention passes through the physical examinations data such as blood routine, liver function, blood lipid, the renal function for combining individual, using the method for integrated study, merges the models such as gradient regression tree, random forest, linear regression to predict fasting blood sugar;By a large amount of training datas training prediction model, to improve the accuracy of prediction model, universality and robustness.Fasting blood-glucose prediction can be carried out to no individual for carrying out fasting blood-glucose inspection in time, effective early warning is carried out to diabetes high-risk patient.
Description
Technical field
The present invention relates to intelligent medical treatments, machine learning field, and in particular to a kind of based on the different of integrated study Fusion Model
Normal fasting blood sugar method for early warning.
Background technique
With the acceleration of rapid economic development and process of industrialization, the acceleration of living-pattern preservation and aging process,
The illness rate for being China's diabetes is just being in zooming trend, another is serious referred to as after cardiovascular and cerebrovascular disease, tumour
Endanger the important Chronic Non-Communicable Diseases of people's health.Prevent guide (version in 2013) from estimating by Type 2 Diabetes In China,
In 2005-2015, the Chinese economic loss as caused by diabetes and related cardiovascular disease is up to 557,700,000,000 dollars, diabetes
Not only bring the human body and spiritual damage to diseased individuals and lead to the shortening in service life, return personal and country bring it is heavy
The financial burden of weight.
Different according to the pathogenesis of diabetes, diabetes are broadly divided into type 1 diabetes, diabetes B, other special defectss
Patients with type Ⅰ DM and gestational diabetes mellitus, secondary diabetes.The healing of diabetes is extremely difficult at this stage, therefore prevents and do in time
It is to cope with the best means of diabetes in advance.The detection of pathoglycemia is the important link of diabetes early warning, the judgement of pathoglycemia
Mode generally detects fasting blood-glucose or postprandial blood sugar, as fasting blood-glucose >=7.0mmol/L or postprandial blood sugar >=11.1mmol/L,
It can suspect that individual with diabetes, should carry out early warning to it.In view of every physical signs of human body connects each other, it is based on it
He becomes a kind of possibility to the prediction of fasting blood-glucose by physiological data.
A kind of existing fasting blood-glucose prediction technique based on physical examination data modeling is to utilize examinee using random forest
1 year following to examinee fasting blood sugar of physical examination information predict, and then show that the examinee compares 1 year sky
The situation of change of abdomen blood glucose value carries out effective to judge the onset diabetes situation of examinee in onset diabetes early period
Prevention blocks, and wherein the physical examination information of examinee includes basic body inspection information, blood routine detection, blood biochemistry detection, routine urinalysis
The one or more information of detection, internal medicine, electrocardiogram section now totally 50 physical examination indexs.
The technology extracts the physical examination information of each examinee of needs from magnanimity physical examination data first, and to data into
Row cleaning and formatting, obtain the data set comprising all characteristic sets.Subsequent technology binding sequence backward selection algorithm choosing
Optimal feature subset is selected out as the characteristic set of prediction fasting blood sugar, the step is first with random forest to feature set
Its feature importance of each of conjunction feature calculation, then according to sequence backward selection algorithm, by whole features of data set
Set is modeled, and calculates the Scoring effect of its fasting blood sugar prediction on test set, it is minimum then successively to remove score
Feature after calculate its on test set fasting blood-glucose prediction Scoring effect, until characteristic set in contain only a physical examination
, it is optimal feature subset that choosing, which has the feature set of maximum Scoring effect,.Finally the technology use has selected optimal characteristics
The data set training Random Forest model of subset, the predicted value to blood glucose is the blood glucose prediction value of each decision tree in random forest
Mean value.At this point, the regression model foundation of fasting blood sugar prediction finishes.The technology can reach certain prediction effect.
But on the physiological mechanism of human body, fasting blood-glucose and other physical signs have complicated relationship, for training with
The physical examination index (feature) of machine forest model is insufficient, the existing biggish risk of fasting blood sugar prediction deviation.What next was used
Random Forest model is larger as the deviation of Individual forecast model result in the prediction of successive value, and precision of prediction needs further
It improves.In addition, the technology is used as according to the fasting blood sugar of next year and the difference of current fasting blood sugar judges diabetes disease
The risk of hair, not in view of the quantitative relationship between fasting blood sugar occurrence and diabetes.
Summary of the invention
The purpose of the present invention is overcoming the shortcomings of existing methods, a kind of exception based on integrated study Fusion Model is proposed
Fasting blood sugar method for early warning.The present invention passes through the physical examinations data such as blood routine, liver function, blood lipid, the renal function for combining individual, makes
With the method for integrated study, merge that gradient promotes decision tree, the empty stomach to examinee is realized in random forest, model linear regression
Blood glucose value is predicted;By a large amount of training datas training prediction model, thus improve the accuracy of prediction model, universality and
Robustness.
To solve the above-mentioned problems, the invention proposes a kind of abnormal fasting blood sugars based on integrated study Fusion Model
Method for early warning, which comprises
The physical examination data that examinee group is obtained from hospital, as original training set.
Missing values processing, the standardization of data are carried out to original training set.
To treated, training set carries out Feature Selection, removes extraneous features and redundancy feature.
Using selected feature, respectively as the instruction of gradient regression tree model, Random Forest model, linear regression model (LRM)
Practice collection, select linear regression to come the gradient regression tree that Fusion training completes, random forest, linear regression as meta-model later pre-
Model is surveyed, the linear regression model (LRM) as meta-model is trained in the input by the output of three kinds of prediction models as meta-model again,
To establish complete prediction model.
The physical examination data that user inputs are predicted using trained prediction model, obtain the empty stomach of physical examination data
Whether blood glucose prediction value is abnormal fasting blood sugar according to preset threshold decision, and result is fed back to user.
Preferably, the physical examination data for obtaining examinee group, specifically include:
Gender, age, diastolic pressure, Tianmen east propylhomoserin transferase, alanine aminotransferase, alkaline phosphatase, r- paddy ammonia
It is acyltransferase, total number of lymphocytes, total protein, albumin, globulin, Archon ratio, triglycerides, total cholesterol, low close
Spend lipoprotein cholesterol, high-density lipoprotein cholesterol, urea, creatinine, uric acid, hepatitis B surface antibody, hepatitis B surface antigen, second
It is liver e antigen, hbv antibody, hepatitis B core antibody, white blood cell count(WBC), red blood cell count(RBC), hemoglobin, hematocrit, red thin
Born of the same parents' average external volume, MC Hgb, erythrocyte mean hemoglobin concentration, erythrocyte volume distribution width, blood
Platelet number, mean platelet volume, glycoprotein Ⅵ, mean platelet volume, neutrophil leucocyte %, lymph are thin
It is born of the same parents %, monocyte %, acidophil %, basocyte %, chlorine, carbon dioxide, sodium, potassium, calcium, magnesium, phosphorus, urine bilirubin, straight
Connect bilirubin, total bilirubin, cholinesterase, lactic dehydrogenase, total bile acid, cystatin C, Angiotensin-Converting, super oxygen
Compound mutase, a- hydroxybutyrate dehydrogenase, creatine kinase, hs-CRP, amylase, carries rouge at Creatine Kinase MB
Albumen E, immunoglobulin M, immunoglobulin A, immunoglobulin C, immunoglobulin G, liver and gallbladder acid, free fatty acid, homotype
Cysteine, transferrins, adenosine deaminase, electrocardiogram, heart rate.
Preferably, described to establish complete prediction model, it specifically includes:
The basic model for having the gradient regression tree model of good nonlinear fitting ability as Fusion Model is introduced, according to
Training set obtains gradient regression tree fasting blood-glucose value prediction model;
Since gradient regression tree reply over-fitting ability is weaker, Random Forest model is introduced as the another of Fusion Model
One basic model obtains random forest fasting blood-glucose value prediction model according to training set;
In view of the more big then syncretizing effect of the model difference merged in integrated study is better, therefore it is also introduced into and above-mentioned model
Basic model of the linear regression to differ greatly as Fusion Model obtains the prediction of linear regression fasting blood sugar according to training set
Model;
After introducing basic model, select linear regression as meta-model come Fusion training completion gradient regression tree, with
Machine forest, Linear Regression Forecasting Model, the input by the output of three kinds of prediction models as meta-model, training is as first mould again
The linear regression model (LRM) of type, to establish complete prediction model.
A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model proposed by the present invention, in conjunction with individual
The physical examinations data such as blood routine, liver function, blood lipid, renal function merge gradient regression tree, random using the method for integrated study
The models such as forest, linear regression predict fasting blood sugar, can be in time to no individual for carrying out fasting blood-glucose inspection
Fasting blood-glucose prediction is carried out, effective early warning is carried out to diabetes high-risk patient.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the abnormal fasting blood sugar method for early warning flow chart of the embodiment of the present invention;
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is the abnormal fasting blood sugar method for early warning flow chart of the embodiment of the present invention, as shown in Figure 1, this method comprises:
S1 obtains the physical examination data of examinee group from hospital, as original training set.
S2 carries out missing values processing, the standardization of data to original training set.
S3, to treated, training set carries out Feature Selection, removes extraneous features and redundancy feature.
S4, using selected feature, respectively as gradient regression tree model, Random Forest model, linear regression model (LRM)
Training set, select linear regression to carry out the gradient regression tree of Fusion training completion as meta-model, random forest, linear return later
Return prediction model, the linear regression as meta-model is trained in the input by the output of three kinds of prediction models as meta-model again
Model, to establish complete prediction model.
S5 predicts the physical examination data that user inputs using trained prediction model, obtains physical examination data
Whether fasting blood-glucose predicted value is abnormal fasting blood sugar according to preset threshold decision, and result is fed back to user.
Step S1, specific as follows:
From Guangdong Province, hospital obtains the physical examination data of 19802 examinees, as the original training set of this method,
In each examinee physical examination information include gender, age, blood routine, liver function, renal function, blood lipid, routine urinalysis etc. it is personal with
And physical examination related data 74 dimensional feature in total.
The physical examination information used specifically includes: gender, age, diastolic pressure, Tianmen east propylhomoserin transferase, alanine amino turn
Move enzyme, alkaline phosphatase, r- glutamyl transferase, total number of lymphocytes, total protein, albumin, globulin, Archon ratio,
Triglycerides, total cholesterol, low density lipoprotein cholesterol, high-density lipoprotein cholesterol, urea, creatinine, uric acid, hepatitis B table
Face antibody, hepatitis B surface antigen, hepatitis B virus e antigen, hbv antibody, hepatitis B core antibody, white blood cell count(WBC), red blood cell count(RBC), blood
Lactoferrin, hematocrit, average volume of red blood cells, MC Hgb, erythrocyte mean hemoglobin concentration,
Erythrocyte volume distribution width, platelet count, mean platelet volume, glycoprotein Ⅵ, mean platelet volume, in
Property granulocyte %, lymphocyte %, monocyte %, acidophil %, basocyte %, chlorine, carbon dioxide, sodium, potassium, calcium,
Magnesium, phosphorus, urine bilirubin, bilirubin direct, total bilirubin, cholinesterase, lactic dehydrogenase, total bile acid, cystatin C, blood vessel
Converting Enzyme, superoxide dismutase, Creatine Kinase MB, a- hydroxybutyrate dehydrogenase, creatine kinase, super quick C are anti-
Answer albumen, amylase, apo E, immunoglobulin M, immunoglobulin A, immunoglobulin C, immunoglobulin G, liver and gallbladder
Acid, free fatty acid, homocysteine, transferrins, adenosine deaminase, electrocardiogram, heart rate.
Step S2, specific as follows:
S21, the processing of shortage of data value:
(1) characteristic is traversed, to the data for lacking feature of the degree more than or equal to 70% or more in data
It is abandoned.
(2) characteristic is traversed, the data that the feature that degree is lower than 70% is lacked in data is considered as acceptable
Range of loss calculates the average value for the data not lacked to the feature of acceptable range of loss, and fills up this with the average value
Missing data in feature.
S22, data normalization processing:
Using Min-Max standardized method, to each feature, according to the maximum value and minimum value of this feature, by this feature
In each data carry out Linear Mapping, be mapped in section [0,1], convert function are as follows:
Wherein x is the data for currently needing to convert in current signature, xmaxFor the maximum value of data in this feature, xminFor spy
The minimum value of data, x in sign*For according to the conversion values of the data currently converted.
Step S3, specific as follows:
S31 calculates the information gain of each characteristic, wherein the information gain gain of each feature is by following formula meter
It calculates:
H (Y)=- ∑y∈Yp(y)log2p(y)
H (Y | X)=- ∑x∈Xp(x)∑y∈Yp(y|x)log2p(y|x)
Gain=H (Y)+H (X)-H (X | Y)
Wherein y indicates that the fasting blood sugar of some data of training, H (Y) indicate the information of the fasting blood sugar of training data
Entropy, some data for the feature that x expression is currently calculating, the comentropy of H (X) expression feature X, H (X | Y) it indicates in feature
The comentropy of fasting blood sugar under X.
S32 is standardized the information gain of each feature, wherein standardized formula is as follows:
S33, given threshold traverse feature, and the feature to the information gain having been standardized lower than threshold value carries out screening removal,
Remove extraneous features.
S34 calculates the Pearson correlation coefficients between every two feature, the correlation between feature is obtained, wherein calculating
Formula is as follows:
Wherein X is first feature, and Y is second feature,For the average value of the data of first feature,It is second
The average value of the data of a feature, sXFor the standard deviation of first feature, sYFor the standard deviation of second feature.
S35, given threshold traverse every a pair of of feature, Pearson correlation coefficients are lower than with the feature pair of threshold value, screening is gone
Except the lower feature of the information gain having been standardized in feature pair, redundancy feature is removed.
Step S4, specific as follows:
S41, since the characteristic dimension that blood glucose prediction is related to is higher, and directly there is multicollinearity in feature, general
Logical linear regression not can solve this problem, therefore introduce the gradient regression tree with good nonlinear fitting ability
Basic model of the model as Fusion Model.User is needed to be adjusted according to real data collection and training effect to parameter herein
It is excellent, gradient regression tree fasting blood-glucose value prediction model is obtained according to training set.
S42, since gradient regression tree belongs to additivity decision-tree model, the ability for coping with over-fitting is weaker, in order to cope with
This problem introduces another basic model of the Random Forest model as Fusion Model.Need user according to actual number herein
Tuning is carried out to parameter according to collection and training effect, random forest fasting blood-glucose value prediction model is obtained according to training set.
S43, finally in view of the model difference merged in integrated study is bigger, syncretizing effect is better, thus handle with it is upper
State the basic model that the biggish linear regression of model difference is also used as Fusion Model.Linear regression fasting blood is obtained according to training set
Sugared value prediction model.
S44 selects linear regression as meta-model to merge gradient regression tree, random forest after introducing basic model
And linear regression.Gradient regression tree model, the Random Forest model, linear regression that will be completed by step S41, S42, S43 training
Input of the output of model as meta-model, trains the linear regression model (LRM) as meta-model again.
Step S5, specific as follows:
S51 predicts fasting blood sugar:
The physical examination data of input are carried out using the linear regression fasting blood-glucose value prediction model for the meta-model trained pre-
It surveys, obtains the fasting blood-glucose predicted value of physical examination data.
S52 judges abnormal fasting blood sugar and early warning:
Abnormal fasting blood sugar is judged whether it is according to whether fasting blood-glucose predicted value is greater than 6.1mmol/L, if prediction
Fasting blood sugar is more than or equal to 6.1mmol/L, then judges that the tester has abnormal fasting blood sugar, if the fasting blood-glucose of prediction
Value is lower than 6.1mmol/L, then judges the tester for normal fasting blood sugar.Result is finally fed back to user.
A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model that the embodiment of the present invention proposes, knot
The physical examinations data such as blood routine, liver function, blood lipid, the renal function of individual are closed, using the method for integrated study, gradient is merged and returns
The models such as tree, random forest, linear regression predict fasting blood sugar, can in time to no progress fasting blood-glucose inspection
Individual carry out fasting blood-glucose prediction, effective early warning is carried out to diabetes high-risk patient.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read OnlyMemory), random access memory (RAM, Random Access
Memory), disk or CD etc..
In addition, being provided for the embodiments of the invention a kind of abnormal fasting blood-glucose based on integrated study Fusion Model above
Value method for early warning is described in detail, and specific case used herein explains the principle of the present invention and embodiment
It states, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas;Meanwhile for this field
Those skilled in the art, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the contents of this specification are not to be construed as limiting the invention.
Claims (2)
1. a kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model, which is characterized in that the method packet
It includes:
The physical examination data that examinee group is obtained from hospital, as original training set.
Missing values processing, the standardization of data are carried out to original training set.
To treated, training set carries out Feature Selection, removes extraneous features and redundancy feature.
Using selected feature, respectively as the training of gradient regression tree model, Random Forest model, linear regression model (LRM)
Collection selects linear regression to come the gradient regression tree of Fusion training completion, random forest, linear regression prediction as meta-model later
Model, the input by the output of three kinds of prediction models as meta-model, trains the linear regression model (LRM) as meta-model again, from
And establish complete prediction model.
The physical examination data that user inputs are predicted using trained prediction model, obtain the fasting blood-glucose of physical examination data
Whether predicted value is abnormal fasting blood sugar according to preset threshold decision, and result is fed back to user.
2. a kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model as described in claim 1, special
Sign is that the physical examination data for obtaining examinee group specifically include:
Gender, age, diastolic pressure, Tianmen east propylhomoserin transferase, alanine aminotransferase, alkaline phosphatase, r- glutamyl
Transferase, total number of lymphocytes, total protein, albumin, globulin, Archon ratio, triglycerides, total cholesterol, low density lipoprotein
Protein cholesterol, high-density lipoprotein cholesterol, urea, creatinine, uric acid, hepatitis B surface antibody, hepatitis B surface antigen, hepatitis B e
Antigen, hbv antibody, hepatitis B core antibody, white blood cell count(WBC), red blood cell count(RBC), hemoglobin, hematocrit, red blood cell are flat
Equal volume, MC Hgb, erythrocyte mean hemoglobin concentration, erythrocyte volume distribution width, blood platelet
Counting, mean platelet volume, glycoprotein Ⅵ, mean platelet volume, neutrophil leucocyte %, lymphocyte %, list
Nucleus %, acidophil %, basocyte %, chlorine, carbon dioxide, sodium, potassium, calcium, magnesium, phosphorus, urine bilirubin, direct gallbladder are red
Element, total bilirubin, cholinesterase, lactic dehydrogenase, total bile acid, cystatin C, Angiotensin-Converting, superoxides discrimination
Change enzyme, Creatine Kinase MB, a- hydroxybutyrate dehydrogenase, creatine kinase, hs-CRP, amylase, apo E,
Immunoglobulin M, immunoglobulin A, immunoglobulin C, immunoglobulin G, liver and gallbladder acid, free fatty acid, half Guang ammonia of homotype
Acid, transferrins, adenosine deaminase, electrocardiogram, heart rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811192652.4A CN109378072A (en) | 2018-10-13 | 2018-10-13 | A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811192652.4A CN109378072A (en) | 2018-10-13 | 2018-10-13 | A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109378072A true CN109378072A (en) | 2019-02-22 |
Family
ID=65397838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811192652.4A Pending CN109378072A (en) | 2018-10-13 | 2018-10-13 | A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109378072A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109682976A (en) * | 2019-02-28 | 2019-04-26 | 东北大学 | Continuous blood sugar based on multi-model fusion monitors the online fault detection method of sensor |
CN110120265A (en) * | 2019-04-29 | 2019-08-13 | 天津大学 | The method of raising prediction blood uric acid precision based on multidimensional characteristic and Model Fusion |
CN110136836A (en) * | 2019-03-27 | 2019-08-16 | 周凡 | A kind of disease forecasting method based on physical examination report clustering |
CN110197728A (en) * | 2019-03-12 | 2019-09-03 | 平安科技(深圳)有限公司 | Prediction technique, device and the computer equipment of diabetes |
CN110197720A (en) * | 2019-03-12 | 2019-09-03 | 平安科技(深圳)有限公司 | Prediction technique and device, storage medium, the computer equipment of diabetes |
CN110516762A (en) * | 2019-10-10 | 2019-11-29 | 深圳大学 | A kind of muscular states quantization assessment method, apparatus, storage medium and intelligent terminal |
CN111128327A (en) * | 2019-12-30 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and device |
CN111859238A (en) * | 2020-07-27 | 2020-10-30 | 平安科技(深圳)有限公司 | Method and device for predicting data change frequency based on model and computer equipment |
CN112216394A (en) * | 2019-07-11 | 2021-01-12 | 浙江远图互联科技股份有限公司 | Blood glucose change trend prediction system based on self-adaptive optimization model |
CN112446425A (en) * | 2020-11-20 | 2021-03-05 | 北京思特奇信息技术股份有限公司 | Method and device for automatically acquiring suspected card-maintaining channel |
CN112819045A (en) * | 2021-01-20 | 2021-05-18 | 国家卫生健康委科学技术研究所 | Method, apparatus, electronic device and medium for user physiological state classification |
WO2021098842A1 (en) * | 2019-11-21 | 2021-05-27 | 四川省人民医院 | Machine learning based method for predicting health status using physical examination indicators |
CN113113140A (en) * | 2021-04-02 | 2021-07-13 | 中山大学 | Diabetes early warning method, system, equipment and storage medium based on self-supervision DNN |
CN113140325A (en) * | 2020-01-20 | 2021-07-20 | 柳州市人民医院 | Method for establishing prediction model of incidence probability of Marneffei pannieri disease of HIV patient |
CN113159132A (en) * | 2021-03-26 | 2021-07-23 | 上海市杨浦区中心医院(同济大学附属杨浦医院) | Hypertension grading method based on multi-model fusion |
CN113642643A (en) * | 2021-08-13 | 2021-11-12 | 山东中科先进技术研究院有限公司 | Training and application method and system of hemoglobin concentration prediction regression model |
CN113936803A (en) * | 2021-12-17 | 2022-01-14 | 北京因数健康科技有限公司 | Method and device for determining insulin resistance index, storage medium and electronic equipment |
CN114530228A (en) * | 2022-01-28 | 2022-05-24 | 广东工业大学 | Blood glucose prediction method and system based on smoothing and fusion and medical equipment |
US20230260651A1 (en) * | 2022-02-17 | 2023-08-17 | Wistron Corp. | Method, electronic system, and computer program product for establishing decision tree for disease prediction |
CN118016315A (en) * | 2024-04-09 | 2024-05-10 | 数据空间研究院 | Pancreatic cancer prediction system and prediction method based on data analysis |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102298663A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Method for automatically identifying syndrome type in traditional Chinese medical science |
CN103226835A (en) * | 2013-04-15 | 2013-07-31 | 北京大学深圳研究生院 | Target tracking method and system based on on-line initialization gradient enhancement regression tree |
CN106682412A (en) * | 2016-12-22 | 2017-05-17 | 浙江大学 | Diabetes prediction method based on medical examination data |
CN107194138A (en) * | 2016-01-31 | 2017-09-22 | 青岛睿帮信息技术有限公司 | A kind of fasting blood-glucose Forecasting Methodology based on physical examination data modeling |
-
2018
- 2018-10-13 CN CN201811192652.4A patent/CN109378072A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102298663A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Method for automatically identifying syndrome type in traditional Chinese medical science |
CN103226835A (en) * | 2013-04-15 | 2013-07-31 | 北京大学深圳研究生院 | Target tracking method and system based on on-line initialization gradient enhancement regression tree |
CN107194138A (en) * | 2016-01-31 | 2017-09-22 | 青岛睿帮信息技术有限公司 | A kind of fasting blood-glucose Forecasting Methodology based on physical examination data modeling |
CN106682412A (en) * | 2016-12-22 | 2017-05-17 | 浙江大学 | Diabetes prediction method based on medical examination data |
Non-Patent Citations (1)
Title |
---|
曹薇著: "《区域技术创新影响因素、网络特征及空间效应研究》", 30 September 2018 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109682976B (en) * | 2019-02-28 | 2020-05-22 | 东北大学 | Continuous blood glucose monitoring sensor online fault detection method based on multi-model fusion |
CN109682976A (en) * | 2019-02-28 | 2019-04-26 | 东北大学 | Continuous blood sugar based on multi-model fusion monitors the online fault detection method of sensor |
CN110197720A (en) * | 2019-03-12 | 2019-09-03 | 平安科技(深圳)有限公司 | Prediction technique and device, storage medium, the computer equipment of diabetes |
CN110197728A (en) * | 2019-03-12 | 2019-09-03 | 平安科技(深圳)有限公司 | Prediction technique, device and the computer equipment of diabetes |
WO2020181805A1 (en) * | 2019-03-12 | 2020-09-17 | 平安科技(深圳)有限公司 | Diabetes prediction method and apparatus, storage medium, and computer device |
CN110136836A (en) * | 2019-03-27 | 2019-08-16 | 周凡 | A kind of disease forecasting method based on physical examination report clustering |
CN110120265A (en) * | 2019-04-29 | 2019-08-13 | 天津大学 | The method of raising prediction blood uric acid precision based on multidimensional characteristic and Model Fusion |
CN110120265B (en) * | 2019-04-29 | 2023-03-31 | 天津大学 | Method for improving blood uric acid prediction precision based on multi-dimensional feature and model fusion |
CN112216394A (en) * | 2019-07-11 | 2021-01-12 | 浙江远图互联科技股份有限公司 | Blood glucose change trend prediction system based on self-adaptive optimization model |
CN110516762B (en) * | 2019-10-10 | 2022-11-15 | 深圳大学 | Muscle state quantitative evaluation method and device, storage medium and intelligent terminal |
CN110516762A (en) * | 2019-10-10 | 2019-11-29 | 深圳大学 | A kind of muscular states quantization assessment method, apparatus, storage medium and intelligent terminal |
WO2021098842A1 (en) * | 2019-11-21 | 2021-05-27 | 四川省人民医院 | Machine learning based method for predicting health status using physical examination indicators |
CN111128327A (en) * | 2019-12-30 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and device |
WO2021135688A1 (en) * | 2019-12-30 | 2021-07-08 | 中国科学院深圳先进技术研究院 | Method and device for early warning of hypoglycemia |
CN111128327B (en) * | 2019-12-30 | 2023-05-26 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and device |
CN113140325A (en) * | 2020-01-20 | 2021-07-20 | 柳州市人民医院 | Method for establishing prediction model of incidence probability of Marneffei pannieri disease of HIV patient |
CN111859238A (en) * | 2020-07-27 | 2020-10-30 | 平安科技(深圳)有限公司 | Method and device for predicting data change frequency based on model and computer equipment |
CN112446425A (en) * | 2020-11-20 | 2021-03-05 | 北京思特奇信息技术股份有限公司 | Method and device for automatically acquiring suspected card-maintaining channel |
CN112819045A (en) * | 2021-01-20 | 2021-05-18 | 国家卫生健康委科学技术研究所 | Method, apparatus, electronic device and medium for user physiological state classification |
CN113159132A (en) * | 2021-03-26 | 2021-07-23 | 上海市杨浦区中心医院(同济大学附属杨浦医院) | Hypertension grading method based on multi-model fusion |
CN113113140A (en) * | 2021-04-02 | 2021-07-13 | 中山大学 | Diabetes early warning method, system, equipment and storage medium based on self-supervision DNN |
CN113642643A (en) * | 2021-08-13 | 2021-11-12 | 山东中科先进技术研究院有限公司 | Training and application method and system of hemoglobin concentration prediction regression model |
CN113936803A (en) * | 2021-12-17 | 2022-01-14 | 北京因数健康科技有限公司 | Method and device for determining insulin resistance index, storage medium and electronic equipment |
CN114530228A (en) * | 2022-01-28 | 2022-05-24 | 广东工业大学 | Blood glucose prediction method and system based on smoothing and fusion and medical equipment |
CN114530228B (en) * | 2022-01-28 | 2022-09-27 | 广东工业大学 | Blood glucose prediction method and system based on smoothing and fusion and medical equipment |
US20230260651A1 (en) * | 2022-02-17 | 2023-08-17 | Wistron Corp. | Method, electronic system, and computer program product for establishing decision tree for disease prediction |
CN118016315A (en) * | 2024-04-09 | 2024-05-10 | 数据空间研究院 | Pancreatic cancer prediction system and prediction method based on data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109378072A (en) | A kind of abnormal fasting blood sugar method for early warning based on integrated study Fusion Model | |
CN109036502B (en) | Physical examination report health management method and system | |
CN109308545A (en) | The method, apparatus, computer equipment and storage medium of diabetes probability are suffered from prediction | |
CN106339593A (en) | Kawasaki disease classification and prediction method based on medical data modeling | |
CN110246577B (en) | Method for assisting gestational diabetes genetic risk prediction based on artificial intelligence | |
CN107194138B (en) | Fasting blood glucose prediction method based on physical examination data modeling | |
WO2021190300A1 (en) | Method for constructing ai chronic kidney disease risk screening model, and chronic kidney disease risk screening method and system | |
CN110808097A (en) | Gestational diabetes prediction system and method | |
CN106980757A (en) | The concurrent coronary artery pathological changes hazards management system of Kawasaki disease and method for digging | |
CN110097975A (en) | A kind of nosocomial infection intelligent diagnosing method and system based on multi-model fusion | |
US20210217528A1 (en) | Method to personalize a biomarker signal and medical procedures using the same | |
CN113128654B (en) | Improved random forest model for coronary heart disease pre-diagnosis and pre-diagnosis system thereof | |
CN106295229A (en) | Kawasaki disease hierarchical prediction method based on medical data modeling | |
CN113470816A (en) | Machine learning-based diabetic nephropathy prediction method, system and prediction device | |
CN116386860A (en) | Diabetes and complications intelligent auxiliary prediction and diagnosis platform based on multiple modes | |
CN109585011A (en) | The Illnesses Diagnoses method and machine readable storage medium of chest pain patients | |
CN114974585A (en) | Construction method of early risk prediction and evaluation model of metabolic syndrome in gestational period | |
CN114373544A (en) | Method, system and device for predicting membranous nephropathy based on machine learning | |
CN117116477A (en) | Construction method and system of prostate cancer disease risk prediction model based on random forest and XGBoost | |
CN109841278A (en) | A method of the screening of coronary disease disease is carried out with angiocarpy mark and rote learning operation method | |
Oanh et al. | Predicting hypertension based on machine learning methods: A case study in northwest vietnam | |
CN112820397B (en) | Method for establishing peri-operative risk prediction model of coronary artery bypass grafting | |
CN111627559B (en) | System for predicting patient mortality risk | |
CN112700859A (en) | Medical diagnosis assisting method and system based on medical images | |
Radha | Hybrid prediction model for the risk of cardiovascular disease in type-2 diabetic patients |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190222 |
|
RJ01 | Rejection of invention patent application after publication |