CN101149767A - Damage-free type health evaluation model general establishment method and its device - Google Patents
Damage-free type health evaluation model general establishment method and its device Download PDFInfo
- Publication number
- CN101149767A CN101149767A CNA2007101242084A CN200710124208A CN101149767A CN 101149767 A CN101149767 A CN 101149767A CN A2007101242084 A CNA2007101242084 A CN A2007101242084A CN 200710124208 A CN200710124208 A CN 200710124208A CN 101149767 A CN101149767 A CN 101149767A
- Authority
- CN
- China
- Prior art keywords
- damage
- free type
- wound
- health
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013210 evaluation model Methods 0.000 title claims description 22
- 238000012549 training Methods 0.000 claims abstract description 28
- 201000010099 disease Diseases 0.000 claims abstract description 22
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims description 25
- 238000013213 extrapolation Methods 0.000 claims description 18
- 238000007418 data mining Methods 0.000 claims description 8
- 238000006467 substitution reaction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 239000004615 ingredient Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 238000011156 evaluation Methods 0.000 abstract description 9
- 239000002131 composite material Substances 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 9
- 230000000977 initiatory effect Effects 0.000 description 9
- 239000008280 blood Substances 0.000 description 8
- 210000004369 blood Anatomy 0.000 description 8
- 239000000090 biomarker Substances 0.000 description 6
- 230000036772 blood pressure Effects 0.000 description 6
- 230000000391 smoking effect Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000003786 synthesis reaction Methods 0.000 description 4
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 3
- 230000037396 body weight Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- 208000031940 Disease Attributes Diseases 0.000 description 2
- 238000001467 acupuncture Methods 0.000 description 2
- 238000000151 deposition Methods 0.000 description 2
- 238000009396 hybridization Methods 0.000 description 2
- 230000000302 ischemic effect Effects 0.000 description 2
- 150000002632 lipids Chemical class 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010061818 Disease progression Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000069 prophylactic effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
Images
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention provides a general build up method and device of noninvasive health assessment module, the method is as follows: measure invasive and noninvasive properties to the same health assessed individual and accumulate sufficient cases, enter the invasive properties tested into invasive epidemiology disease predictive module which has been in clinical and give out appraisal results for the case; the composite non-invasive and invasive properties epidemiological assessment results together constitute training data set for machine learning; the data performing machine learning mine and set up noninvasive evaluation module to be tested, apply extrapolated data into the noninvasive evaluation module to be tested to set up non-invasive health assessment module when meet the set accuracy, otherwise finally set up non-invasive health assessment module which meet the set accuracy through recursive recycled learning process. The device include: personal computer or micro-computer for data processing equipment, non-invasive biological information sensor, analog or digital converters, non-invasive health assessment module, health assessment individual.
Description
Technical field
The present invention relates to the general establishment method and the implement device thereof in health administrative skill field, particularly a kind of damage-free type health evaluation model.
Background technology
The detection of inferior health and assessment are that health control finally provides the intervention means of individuation and requisite condition precedent.But at present all do not pass through the applied research and the implementation data support of scientific system because most inferior healths of being done to get up by market " stir-frys " detect with assessing " product ", thus only be short-lived just without a trace.[see for details: Wu Liuxin etc. the detection of inferior health and assessment, inferior health, Beijing: Chinese traditional Chinese medical science publishing house, 2007.79-126]
Some existing commercialization inferior healths detect the evaluation measures classification:
1. test the damage-free type assessment models that back diagnosis case is concluded based on both depositing disease
Although the mechanism of the damage-free type detection means of this type of inferior health detection evaluation measures is different, as can being channels and collaterals metrical information (as surface skin resistance), quantum and thermal imaging measured value etc., be not perspective health risk assessment on the strict disease early warning meaning but study carefully its assessment models of setting up by the information of being obtained through cave place; Because its modelling mechanism is to conclude the existing retrospective prompting (although this type of specious commercial propaganda that detects evaluating system claims it that disease is had early stage suggesting effect) that has produced disease attribute by detecting data in fact.The logic vagueness of setting up the methodology of this type of assessment models is that detection information is taken at and has the non-sub-health population of both depositing disease, the reality that adopts data processing to conclude then to draw had been for both having deposited the sign of disease attribute, and confused in the detection information criterion of the perspective health risk assessment on the disease early warning meaning under the sub-health state.
For solving above drawback, be necessary to adopt following based on inferior health--under the strictness prediction forecast meaning of-disease time series trend statistical study wound type epidemiology assessment models arranged.
2. based on inferior health---disease time series trend Statistic analysis models wound type epidemiology assessment models arranged
Any chronic disease all has its distinctive physiology and pathological change.Although these variations are complicated, very little variation all can embody on biomarker to some extent.The biomarker group does not here just consider the measured value of each single index, but comprise that numerous meaningful biological medical science indexs and other index that complete observation arrives reach to survey and interview etc., be total evaluation basically to people's physical condition; Therefore, if before disease takes place, record its biomarker pattern, and observe in the disease progression process situation of change of biomarker under the time series trend continuously, adopt the epidemiology statistics analytical approach, as Cox proportional hazard model [Cox DR.Regression models and life tables.J.R Stat Soc B, 1972,34:226-230] etc. set up assessment models and just can find to cause disease to take place and the key factor of development, health control just detects the detection information criterion of the perspective health risk assessment on the disease early warning meaning that institute is really expected in the assessment at sub-health population.The biomarker group input computer that certain is individual will be automatically compares the predictive mode of entry information and software and analyze based on the predictive software systems of assessment models, and then determines the trend and the possibility of this individuality generation disease.This process has been created condition for taking proper prophylactic methods.
The sorry part that this kind detects evaluation measures is must include wound property blood biochemistry index and increased inconvenience.
3. cross-synthesis appraisal procedure
In sum, be necessary that means by comprehensive assessment make sublate separately relative merits of the entirely different detection assessment models " hybridization " of above two class generation mechanisms.Because the new model of being constructed derives from " hybridization " of the entirely different source model of two class generation mechanisms; Therefore new model both can not can not help the converging of clinical case of original generation two class models to rebuild by nationality by obtaining synthesizing of two class model algorithms also, can only obtain according to the original sufficient new clinical case of trial design accumulation of the present invention.
Summary of the invention
Health evaluating is to provide individuation inferior health intervention means institute important key link according to health and fitness information in the health control process.Based on the system biological information science, the present invention proposes the total system variable of macroscopical human body, is the teaching standard with the nationality strictness based on EPDML perspective model, and it is shorter to develop the lead time, the cross-synthesis general establishment method and the implement device thereof of the comparatively economic and damage-free type health evaluation model that is easy to apply.And enumerate with compatriots' ICD initiation potential assessment models as the teaching standard control, having developed the assessment models of corresponding nothing wound collaterals of human detected value, the extrapolation forecast result of model has shown the application feasibility of the method.
The objective of the invention is to overcome shortcoming of the prior art, and propose a kind of general establishment method and device thereof of damage-free type health evaluation model.
A kind of general establishment method of damage-free type health evaluation model, its step is corresponding label shown in Fig. 1 process flow diagram: step is as follows:
Step 1: same health evaluating individuality is measured the wound attribute simultaneously and do not have wound attribute and accumulate abundant case, here the sufficient amount of case can not be expressed with stable constant value, and determine by the program recursive procedure of study more shown in Figure 1, what promptly the abundance of the individual case that is accumulated depended on that following step 6 tests whether the extrapolation precision that draws reach setting requires 90%, sees embodiment example (1) and (2) in the following instructions for details;
Step 2: substitution provides assessment result in the wound type epidemiology disease prediction model that has that obtains clinical practice to case by the wound attribute that has that above-mentioned steps 1 measures;
Step 3: the nothing wound attribute that has wound type epidemiology assessment result and above-mentioned steps 1 to measure that synthetic above-mentioned steps 2 is obtained;
Step 4: create attribute and have wound type epidemiology assessment result to constitute the training cases data set of machine learning jointly by above-mentioned steps 3 synthetic nothings;
Step 5: carry out data mining based on machine learning to set up noninvasively estimating model to be tested;
Step 6: substitution is by the nothing wound attribute that measures at new health evaluating individuality as above-mentioned step 1, the nothing wound that promptly never is used to set up noninvasively estimating model to be tested detects the damage-free type assessment models to be tested that value obtains in above-mentioned steps 5 and draws the noninvasively estimating result of this model, compare with the wound type assessment result of obtaining by above-mentioned steps 2 that has of same health evaluating individuality, the total new case number that is used for this extrapolation accuracy test is not less than 2: 8 with the ratio of the total training cases number that is used to set up this noninvasively estimating model to be tested, with the coincidence rate of comparison as the extrapolation precision of damage-free type assessment models to be tested, the extrapolation accuracy test of model by standard for being not less than 90%, being lower than 90% as the precision of extrapolating after tested returns above-mentioned steps 3 and closes the former training cases data set of And and extrapolation accuracy test data set is that new training cases data set is to re-execute step 4-6, until the damage-free type assessment models foundation that conforms with the precision of extrapolate.
A kind of general apparatus for establishing of damage-free type health evaluation model, its ingredient is as follows:
With the personal computer that possesses display device or microcomputer as data processing equipment, under its CPU control, the damage-free type biometric information sensor measures the damage-free type continuous quantity biological information of health evaluating individuality, imports data processing equipment so far through the analog/digital energy converter again; This data processing equipment obtains as healthy questionnaire information class discrete magnitude biological information and finally exports the health evaluating result through the operation of the described computer program of above-mentioned steps 1-6 in display device and printable or do not have paper by the internet and read simultaneously, and offer the health evaluating individuality, realized the closed loop running of this data processing equipment as the information source of this data handling system and reduction point with the health evaluating individuality.
Beneficial effect of the present invention:
Is the teaching standard with the nationality strictness based on EPDML perspective model, and it is shorter to develop the lead time, the comparatively economic and disease Early-warning Model that is easy to apply and preventing trouble before it happens, with respond that present health ministry advocated to prevention " reach " and to the policy of basic unit's " sinking ".
Description of drawings
In conjunction with following accompanying drawing, further specify the present invention.
Fig. 1 is the process flow diagram of the general establishment method of damage-free type health evaluation model of the present invention;
Fig. 2 is the general apparatus for establishing structure composition diagram of damage-free type health evaluation model of the present invention.
Embodiment
Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention
Here provide a computer machine study of adopting the system biological information science to obtain the scheme step 1-6 as shown in Figure 1 of the cross-synthesis control test of damage-free type assessment models, individual from health evaluating, by being arranged, the wound type goes out damage-free type health evaluation (disease early warning) model as the teaching standard development based on seasonal effect in time series epidemiology disease prediction model.This model also can constantly be followed the accumulation of clinical case and optimize.Following feasibility illustration as this universal method, summary [sees for details: Wu Yangfeng etc. with compatriots' ischemic cardiovascular assessment models.The appraisal procedure of compatriots' ICD initiation potential and the development research of simple and easy assessment tool, China's cardiovascular disease magazine, 2003,31,12:893-901] in contrast, develop of process and the interpretation of result of corresponding damage-free type based on this macrosystem biomarker group's of collaterals of human detected value assessment models.
Choose achievement in research among the present invention as the outer cardiovascular disease hospital epidemiology Wu Yangfeng of the research department professor of China Concord Medical Science University of above-mentioned Chinese Academy of Medical Sciences angiocardiopathy institute's mound of illustration seminar---the assessment models of compatriots' ICD initiation potential can reflect preferably that the comprehensive danger of cardiovascular disease takes place compatriots, and predict satisfactorily in certain individual following 10 years and suffer from ICD (ischemic cardiovascular diseases, danger classes ICVD).This assessment models is determined jointly by age, blood pressure, body mass index, whether smoking, blood sugar and lipids contents six factors.Age and whether smoking just can obtain by filling in questionnaires in the middle of this six factors, blood pressure can be measured by sphygmomanometer and obtain, body mass index can calculate acquisition again by measuring height and body weight, has only blood sugar and lipids contents could obtain by wound blood drawing chemical examination is arranged.
The cross-synthesis control test scheme of damage-free type assessment models is obtained in computer machine study as shown in Figure 1, has wound type ICVD epidemiology disease prediction model to choose the neuroid algorithm as the teaching standard to realize developing non-invasive health evaluating (disease early warning) model based on the data mining of computer machine study by above; Because the neuroid algorithm is fit to handle the such sensing data that contains complicated noise of similar channels and collaterals skin surface resistance detection value very much.
In this implementation procedure we at first with the channels and collaterals person under inspection's that obtains in 297 routine physical examinations data training set as the neuroid machine learning, and with other 227 data as test set to be used to test the forecast precision of institute's established model.Because training set and test set come from diverse colony on sample time and the place, on statistics, be fully independently therefore.
These testers' data comprise that all whether and the detailed information such as channels and collaterals resistance at 24 main acupuncture points, human body skin surface age, sex, blood pressure, height, body weight, blood pressure and blood lipoid content, smoking.According to the computing method in the angiocardiopathy assessment models (referring to table 3 and table 4), we can calculate each tester's ICVD initiation potential in 10 years futures (%), by with compare with sex section in age in the same year crowd's ICVD morbidity in 10 years futures average dangerous (%), we are defined as the high-risk tendency person of angiocardiopathy to the following 10 years people that surpass with sex section in age in the same year crowd's morbidity average dangerous (%) of ICVD initiation potential (%).For this reason, we have introduced a target variable " whether high-risk " in model, for following 10 years the ICVD initiation potential (%) surpass people, target variable value 1 (high-risk) then, otherwise be 0 (non-high-risk) with sex section in age in the same year crowd's ICVD morbidity in 10 years futures average dangerous (%).As at teaching standard source model---the age, sex, blood pressure, height, body weight, blood pressure and blood lipoid content, the smoking whether corresponding information that obtain in the routine physical examination that 297 data training sets of substitution in the wound assessment models are arranged of compatriots' ICD initiation potential, can draw 0,100 data value of 197 data values 1 and be the teaching standard.Utilization neural network algorithm [14] training obtains model, then again model result is applied to the precision of prediction that forecasts on the test set with testing model.
Neural network model can roughly be expressed as minor function:
Certain body-centered vascular diseases forecast risk " whether high-risk "=f (age, sex, systolic pressure, body mass index, smoking whether, and the channels and collaterals resistance value at 24 main acupuncture points, human body skin surface)
Hence one can see that, and this model is not for comprising the damage-free type model of blood sugar and blood fat.
Predicting the outcome of 227 data test collection is as follows:
(1) uses 297 original data to do the training set training and obtain model, then with being somebody's turn to do
Model is made prediction to 227 data;
Actual prediction
| 0 | 1 | amount to
--------+---------+---------+
0 | 153?| 14 | 167
--------+---------+---------+
1 | 12 | 48 | 60
--------+---------+---------+
Amount to 165 62 227
We know from above confusion matrix, at test set altogether in the middle of 227 data, actual value be 167 data of 0 by model prediction after 153 still be that 0,14 wrong report is 1; Actual value be 60 data of 1 by model prediction after 48 still be that 1,12 wrong report is 0.Wherein model prediction value and actual value are coincide 201 data, and what misfit has 26 data, and the predictablity rate of model is 88.55%.
(2) precision of extrapolating after tested is lower than 90% and returns the step 3 of above-mentioned Fig. 1 and close the former training cases data set of And and extrapolation accuracy test data set is that new training cases data set is to re-execute step 4-6, it is the learning process again that the sequential clinical data that progressively increases the accumulation routine physical examination enters a new round, promptly do training set altogether and obtain learning model, then up-to-date other 878 data of obtaining are made prediction with this model with original individual training of 524 (297+227) and test data;
Actual prediction
| 0 | 1 | amount to
--------+---------+---------+
0 | 636 | 31 | 667
--------+---------+---------+
1 | 27 | 184 | 211
--------+---------+---------+
Amount to 663 215 878
We know from above confusion matrix, at test set altogether in the middle of 878 data, actual value be 667 data of 0 by model prediction after 636 still be that 0,31 wrong report is 1; Actual value be 211 data of 1 by model prediction after 184 still be that 1,27 wrong report is 0.Wherein model prediction value and actual value are coincide 820 data, and what misfit has 58 data, and the predictablity rate of model is 93.39%.
Contrast predicting the outcome as can be known of above-mentioned (1), the learning process again that training data continues to increase can make model accuracy be improved constantly and reach set extrapolation accuracy standard, has promptly set up this damage-free type health evaluation model greater than 90%.
Table 3: ICD (ICVD) 10 years initiation potential degree evaluation form (man)
Table 4: ICD (ICVD) 10 years initiation potential degree evaluation form (woman)
A kind of general establishment method of damage-free type health evaluation model, its step is corresponding label shown in Fig. 1 process flow diagram:
Step 1: same health evaluating individuality is measured the wound attribute simultaneously and do not have wound attribute and accumulate abundant case, here the sufficient amount of case can not be expressed with stable constant value, and determine by the program recursive procedure of study more shown in Figure 1, what promptly the abundance of the individual case that is accumulated depended on that following step 6 tests whether the extrapolation precision that draws reach setting requires 90%, sees embodiment example (1) and (2) in the following instructions for details;
Step 2: substitution provides assessment result in the wound type epidemiology disease prediction model that has that obtains clinical practice to case by the wound attribute that has that above-mentioned steps 1 measures;
Step 3: the nothing wound attribute that has wound type epidemiology assessment result and above-mentioned steps 1 to measure that synthetic above-mentioned steps 2 is obtained;
Step 4: create attribute and have wound type epidemiology assessment result to constitute the training cases data set of machine learning jointly by above-mentioned steps 3 synthetic nothings;
Step 5: carry out data mining based on machine learning to set up noninvasively estimating model to be tested;
Step 6: the nothing wound attribute that substitution is measured at new health evaluating individuality by above-mentioned steps 1, the nothing wound that promptly never is used to set up noninvasively estimating model to be tested detects the damage-free type assessment models to be tested that value obtains in above-mentioned steps 5 and draws the noninvasively estimating result of this model, compare with the wound type assessment result of obtaining by above-mentioned steps 2 that has of same health evaluating individuality, the total new case number that is used for this extrapolation accuracy test is not less than 2: 8 with the ratio of the total training cases number that is used to set up this noninvasively estimating model to be tested, with the coincidence rate of comparison as the extrapolation precision of damage-free type assessment models to be tested, the extrapolation accuracy test of model by standard for being not less than 90%, being lower than 90% as the precision of extrapolating after tested returns above-mentioned steps 3 and closes the former training cases data set of And and extrapolation accuracy test data set is that new training cases data set is to re-execute step 4-6, until the damage-free type assessment models foundation that conforms with the precision of extrapolate.
The general establishment method of described damage-free type health evaluation model is with any decision value set that has obtained the result that wound type epidemiology disease prediction model is arranged of clinical practice as the data mining training cases.
The general establishment method of described damage-free type health evaluation model detects the property value set of polynary array variable as the data mining training cases with any nothing wound that can quantize.
Above-mentioned feature reaches and has caused versatility of the present invention.
A kind of general apparatus for establishing of damage-free type health evaluation model as shown in Figure 2, its principle of work and ingredient are as follows:
With the personal computer that possesses display device or microcomputer as data processing equipment, under its CPU control, the damage-free type biometric information sensor measures the damage-free type continuous quantity biological information of health evaluating individuality, imports data processing equipment so far through the analog/digital energy converter again; This data processing equipment obtains as healthy questionnaire information class discrete magnitude biological information and finally exports the health evaluating result through the operation of the described computer program of above-mentioned steps 1-6 in display device and printable or do not have paper by the internet and read simultaneously, and offering the health evaluating individuality, the health evaluating individuality has been realized the closed loop running of this data processing equipment as the information source of this data handling system and reduction point.
The general apparatus for establishing of described damage-free type health evaluation model, the general establishment method of above-mentioned damage-free type health evaluation model is not damage-free type biometric information sensor, analog/digital energy converter because of each unit in this device and changes to the variation of the way of realization of class personal computer or microcomputer that this i.e. the versatility of this device.
More than though exemplary embodiments of the present invention has been described, should be understood that and the invention is not restricted to these embodiment, concerning the professional and technical personnel, various changes and modifications of the present invention can both realize, but these are all within the spirit and scope of claim of the present invention.
Claims (6)
1. the general establishment method of a damage-free type health evaluation model, its step is as follows:
Step 1: same health evaluating individuality is measured the wound attribute simultaneously and do not have wound attribute and accumulate abundant case, here the sufficient amount of case can not be expressed with stable constant value, and determine that by the program recursive procedure of study again what promptly the abundance of the individual case that is accumulated depended on that following step 6 tests whether the extrapolation precision that draws reach setting requires 90%;
Step 2: substitution provides assessment result in the wound type epidemiology disease prediction model that has that obtains clinical practice to case by the wound attribute that has that above-mentioned steps 1 measures;
Step 3: the nothing wound attribute that has wound type epidemiology assessment result and above-mentioned steps 1 to measure that synthetic above-mentioned steps 2 is obtained;
Step 4: create attribute and have wound type epidemiology assessment result to constitute the training cases data set of machine learning jointly by above-mentioned steps 3 synthetic nothings;
Step 5: carry out data mining based on machine learning to set up noninvasively estimating model to be tested;
Step 6: substitution is by the nothing wound attribute that measures at new health evaluating individuality as above-mentioned step 1, the nothing wound that promptly never is used to set up noninvasively estimating model to be tested detects the damage-free type assessment models to be tested that value obtains in above-mentioned steps 5 and draws the noninvasively estimating result of this model, compare with the wound type assessment result of obtaining by above-mentioned steps 2 that has of same health evaluating individuality, the total new case number that is used for this extrapolation accuracy test is not less than 2: 8 with the ratio of the total training cases number that is used to set up this noninvasively estimating model to be tested, with the coincidence rate of comparison as the extrapolation precision of damage-free type assessment models to be tested, the extrapolation accuracy test of model by standard for being not less than 90%, being lower than 90% as the precision of extrapolating after tested returns above-mentioned steps 3 and closes the former training cases data set of And and extrapolation accuracy test data set is that new training cases data set is to re-execute step 4-6, until the damage-free type assessment models foundation that conforms with the precision of extrapolate.
2. the general establishment method of damage-free type health evaluation model according to claim 1 is characterized in that, with any decision value set that has obtained the result that wound type epidemiology disease prediction model is arranged of clinical practice as the data mining training cases.
3. the general establishment method of damage-free type health evaluation model according to claim 1 is characterized in that, detects the property value set of polynary array variable as the data mining training cases with any nothing wound that can quantize.
4. aforesaid right requires 2 and 3 to reach the versatility that has caused claim 1.
5. the general apparatus for establishing of a damage-free type health evaluation model, its ingredient is as follows:
With the personal computer that possesses display device or microcomputer as data processing equipment, under its CPU control, the damage-free type biometric information sensor measures the damage-free type continuous quantity biological information of health evaluating individuality, imports data processing equipment so far through the analog/digital energy converter again; This data processing equipment obtains as healthy questionnaire information class discrete magnitude biological information and finally exports the health evaluating result through the operation of the described computer program of above-mentioned steps 1-6 in display device and printable or do not have paper by the internet and read simultaneously, and offer the health evaluating individuality, realized the closed loop running of this data processing equipment as the information source of this data handling system and reduction point with the health evaluating individuality.
6. the general apparatus for establishing of damage-free type health evaluation model according to claim 5, it is characterized in that, the general establishment method of above-mentioned damage-free type health evaluation model is not damage-free type biometric information sensor, analog/digital energy converter because of each unit in this device and changes to the variation of the way of realization of class personal computer or microcomputer that this i.e. the versatility of this device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101242084A CN101149767A (en) | 2007-10-29 | 2007-10-29 | Damage-free type health evaluation model general establishment method and its device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101242084A CN101149767A (en) | 2007-10-29 | 2007-10-29 | Damage-free type health evaluation model general establishment method and its device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101149767A true CN101149767A (en) | 2008-03-26 |
Family
ID=39250292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2007101242084A Pending CN101149767A (en) | 2007-10-29 | 2007-10-29 | Damage-free type health evaluation model general establishment method and its device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101149767A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336900A (en) * | 2013-06-26 | 2013-10-02 | 广州军区广州总医院 | Method of establishing health layering model for cardiovascular patient |
| CN105184107A (en) * | 2015-10-20 | 2015-12-23 | 沈阳国际旅行卫生保健中心 | Health risk pre-warning system for human body circulatory system |
| CN105232054A (en) * | 2015-10-20 | 2016-01-13 | 沈阳国际旅行卫生保健中心 | Human body endocrine system health risk early warning system |
| CN105303041A (en) * | 2015-10-20 | 2016-02-03 | 沈阳国际旅行卫生保健中心 | Human digestive system health risk early-warning system |
| CN109009009A (en) * | 2018-07-26 | 2018-12-18 | 方顺丽 | Blood vessel appraisal procedure, device and intelligent terminal |
| CN110111882A (en) * | 2011-10-24 | 2019-08-09 | 哈佛大学校长及研究员协会 | Enhancing diagnosis is carried out to illness by artificial intelligence and mobile health approach, in the case where not damaging accuracy |
| CN111048206A (en) * | 2019-12-24 | 2020-04-21 | 新绎健康科技有限公司 | Multi-dimensional health state assessment method and device |
| CN111949691A (en) * | 2020-07-29 | 2020-11-17 | 合肥森亿智能科技有限公司 | Clinical aid decision making method, system, equipment and medium based on rule attenuation |
| CN112057072A (en) * | 2020-08-19 | 2020-12-11 | 广州中康先觉健康科技有限责任公司 | Human body meridian signal detection and health assessment system |
| US11972336B2 (en) | 2015-12-18 | 2024-04-30 | Cognoa, Inc. | Machine learning platform and system for data analysis |
| US12205725B2 (en) | 2016-11-14 | 2025-01-21 | Cognoa, Inc. | Methods and apparatus for evaluating developmental conditions and providing control over coverage and reliability |
| US12402840B2 (en) | 2015-08-11 | 2025-09-02 | Cognoa, Inc. | Methods and apparatus to determine developmental progress with artificial intelligence and user input |
-
2007
- 2007-10-29 CN CNA2007101242084A patent/CN101149767A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110111882A (en) * | 2011-10-24 | 2019-08-09 | 哈佛大学校长及研究员协会 | Enhancing diagnosis is carried out to illness by artificial intelligence and mobile health approach, in the case where not damaging accuracy |
| CN110111882B (en) * | 2011-10-24 | 2024-03-15 | 哈佛大学校长及研究员协会 | Enhanced diagnosis of conditions without compromising accuracy through artificial intelligence and mobile health techniques |
| CN103336900A (en) * | 2013-06-26 | 2013-10-02 | 广州军区广州总医院 | Method of establishing health layering model for cardiovascular patient |
| US12402840B2 (en) | 2015-08-11 | 2025-09-02 | Cognoa, Inc. | Methods and apparatus to determine developmental progress with artificial intelligence and user input |
| CN105303041A (en) * | 2015-10-20 | 2016-02-03 | 沈阳国际旅行卫生保健中心 | Human digestive system health risk early-warning system |
| CN105232054A (en) * | 2015-10-20 | 2016-01-13 | 沈阳国际旅行卫生保健中心 | Human body endocrine system health risk early warning system |
| CN105184107A (en) * | 2015-10-20 | 2015-12-23 | 沈阳国际旅行卫生保健中心 | Health risk pre-warning system for human body circulatory system |
| US11972336B2 (en) | 2015-12-18 | 2024-04-30 | Cognoa, Inc. | Machine learning platform and system for data analysis |
| US12205725B2 (en) | 2016-11-14 | 2025-01-21 | Cognoa, Inc. | Methods and apparatus for evaluating developmental conditions and providing control over coverage and reliability |
| CN109009009A (en) * | 2018-07-26 | 2018-12-18 | 方顺丽 | Blood vessel appraisal procedure, device and intelligent terminal |
| CN111048206A (en) * | 2019-12-24 | 2020-04-21 | 新绎健康科技有限公司 | Multi-dimensional health state assessment method and device |
| CN111949691A (en) * | 2020-07-29 | 2020-11-17 | 合肥森亿智能科技有限公司 | Clinical aid decision making method, system, equipment and medium based on rule attenuation |
| CN112057072A (en) * | 2020-08-19 | 2020-12-11 | 广州中康先觉健康科技有限责任公司 | Human body meridian signal detection and health assessment system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101149767A (en) | Damage-free type health evaluation model general establishment method and its device | |
| Vos et al. | Ensemble machine learning model trained on a new synthesized dataset generalizes well for stress prediction using wearable devices | |
| JP5400217B2 (en) | Computer-aided diagnosis system for determining skin composition based on the principles of traditional Chinese medicine (TCM) | |
| CN104217095A (en) | Human-body health function-status evaluating model | |
| CN107153774A (en) | The disease forecasting system of the structure and application of chronic disease risk assessment the hyperbolic model model | |
| CN108742513A (en) | Patients with cerebral apoplexy rehabilitation prediction technique and system | |
| CN114943629A (en) | A health management health care service system and its health management method | |
| CN113506640B (en) | Cerebral perfusion state classification device, method, device and model training device | |
| CN107358556A (en) | Health monitoring and evaluation platform based on Internet of Things | |
| CN116864062B (en) | Health physical examination report data analysis management system based on Internet | |
| CN115775625A (en) | Construction method of model for evaluating risk of hypertension of college teaching staff based on healthy and fitness | |
| CN101703391A (en) | Method for dynamically assessing human performance | |
| CN117095817A (en) | A feature-based and CT image-based fracture risk prediction method | |
| CN116019429B (en) | Health monitoring method, device, equipment and storage medium based on physiological index | |
| US20240266062A1 (en) | Disease risk evaluation method, disease risk evaluation system, and health information processing device | |
| KR20100102963A (en) | Method for producing wellbeing life care index model in ubiquitous environment | |
| CN114388129B (en) | Atherosclerosis risk prediction method based on dynamic information value criterion and ensemble learning | |
| CN103976719A (en) | Dynamic physical examination method and automatic corporeity evaluation system | |
| CN119833121B (en) | An automatic detection system for diabetes symptoms | |
| KR102477592B1 (en) | Sarcopenia artificial intelligence diagnosis system using body fluid samples and method thereof | |
| KR102369001B1 (en) | Estimation score display method for metabolic syndrome | |
| CN114176532B (en) | A clinical verification method and application system for measuring cfPWV parameters | |
| EP4239569B1 (en) | System for determining mechanical tissue characteristics from imaging data | |
| CN116313038A (en) | A device, device and system for diagnosing sarcopenia | |
| RU129681U1 (en) | SYSTEM FOR DETERMINING THE FUNCTIONAL CONDITION OF A GROUP OF FEEDBACK PEOPLE |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: ZHAO HONG Free format text: FORMER OWNER: SHENZHEN TIANXIN BIOLOGICAL TECHNOLOGY CO., LTD. Effective date: 20090904 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20090904 Address after: Guangdong province Shenzhen city Luohu District road Jihao gorgeous garden building F room 18 Hua Ge post encoding: 518000 Applicant after: Zhao Hong Address before: Guangdong Province, Shenzhen City People's road shenfang Plaza B block 2301 post encoding: 518001 Applicant before: Shenzhen Tianxin Biotechnology Co., Ltd. |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20080326 |