CN107301326A - Individualized disease risk class analysis method based on regular factor - Google Patents
Individualized disease risk class analysis method based on regular factor Download PDFInfo
- Publication number
- CN107301326A CN107301326A CN201710758822.XA CN201710758822A CN107301326A CN 107301326 A CN107301326 A CN 107301326A CN 201710758822 A CN201710758822 A CN 201710758822A CN 107301326 A CN107301326 A CN 107301326A
- Authority
- CN
- China
- Prior art keywords
- factor
- disease
- regular
- risk
- disease name
- 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
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 298
- 201000010099 disease Diseases 0.000 title claims abstract description 297
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 206010012601 diabetes mellitus Diseases 0.000 claims description 26
- 230000007774 longterm Effects 0.000 claims description 23
- 230000002265 prevention Effects 0.000 claims description 11
- 108090000623 proteins and genes Proteins 0.000 claims description 7
- 230000037396 body weight Effects 0.000 claims description 5
- 230000007211 cardiovascular event Effects 0.000 claims description 5
- 230000003001 depressive effect Effects 0.000 claims description 5
- 235000006694 eating habits Nutrition 0.000 claims description 5
- 208000024891 symptom Diseases 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 33
- 206010020772 Hypertension Diseases 0.000 description 63
- 230000036772 blood pressure Effects 0.000 description 37
- 239000008280 blood Substances 0.000 description 29
- 210000004369 blood Anatomy 0.000 description 29
- 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 description 15
- 229910052708 sodium Inorganic materials 0.000 description 15
- 239000011734 sodium Substances 0.000 description 15
- 235000021023 sodium intake Nutrition 0.000 description 15
- 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 13
- 239000008103 glucose Substances 0.000 description 13
- 230000000391 smoking effect Effects 0.000 description 13
- 238000012502 risk assessment Methods 0.000 description 11
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 9
- 201000005202 lung cancer Diseases 0.000 description 9
- 208000020816 lung neoplasm Diseases 0.000 description 9
- 239000000428 dust Substances 0.000 description 6
- 230000000977 initiatory effect Effects 0.000 description 5
- 235000005911 diet Nutrition 0.000 description 4
- 230000037213 diet Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 210000001124 body fluid Anatomy 0.000 description 3
- 239000010839 body fluid Substances 0.000 description 3
- 239000003245 coal Substances 0.000 description 3
- 230000035622 drinking Effects 0.000 description 3
- 235000005686 eating Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 201000001421 hyperglycemia Diseases 0.000 description 3
- 210000004072 lung Anatomy 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 201000001320 Atherosclerosis Diseases 0.000 description 1
- 206010003658 Atrial Fibrillation Diseases 0.000 description 1
- 206010061216 Infarction Diseases 0.000 description 1
- 208000001145 Metabolic Syndrome Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000007574 infarction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention discloses a kind of individualized disease risk class analysis method based on regular factor, including：According to medical information and big data information, set up regular factor logical table and adjusted in real time according to the renewal of medical information and/or big data information；Obtain personal information；Filter out the personalized factor and its weights is set, personal label is obtained to the sequence of the personalized factor according to weights, personal label includes initial ailment group, and initial ailment group includes at least one disease name and the corresponding risk class of disease name；Personal fresh information is obtained, and personal renewal label is obtained according to personal fresh information, individual, which updates label, to be included updating disease group, and renewal disease group includes at least one disease name and the corresponding risk class of disease name；When updating disease group and initial ailment group including same disease name, updating disease group includes the variation tendency of the same disease name.The method that the present invention is provided, with higher personalization and real-time, accuracy rate is higher.
Description
Technical field
The present invention relates to disease risks analysis technical field, more particularly, to a kind of personalization based on regular factor
Disease risks grade analysis method.
Background technology
With the development of the social economy, the diet structure of people and habits and customs there occurs huge change, people are to disease
Disease and health problem are also increasingly paid attention to.
According to the research report of the World Health Organization, the disease of the mankind 1/3 can be avoided by prevention and health care, 1/3
Disease early detection can be effectively controlled, and 1/3 disease can improve therapeutic effect by effective communication.For disease,
Treatment is not unique approach, effectively prevents, controls disease and lift the efficiency of disease treatment to be only the mankind by health control
Healthy is basic.
It is the important means of prevention from suffering from the diseases, still, existing disease to the risk assessment of disease for prevention from suffering from the diseases
Methods of risk assessment, typically a certain to some specific crowds trouble or some diseases, which are provided, compared with other crowds there is excessive risk to comment
Estimate conclusion, but personal disease risks assessed and are inaccurate, the conclusion of disease risks assessment can not be adjusted in real time,
I.e.：Existing disease risks appraisal procedure is personalized and real-time is poor.
Therefore, in view of the above-mentioned problems, the present invention proposes a kind of individualized disease risk class point based on regular factor
Analysis method, with higher personalization and real-time.
The content of the invention
In view of this, the invention provides a kind of individualized disease risk class analysis method based on regular factor, tool
There are higher personalization and real-time, and accuracy rate is higher.
In order to solve the above-mentioned technical problem, the present invention has following technical scheme：A kind of personalized disease based on regular factor
Sick risk class analysis method, including：
According to medical information and big data information, regular factor logical table is set up, the regular factor logical table, including：
The threshold value of disease name, regular factor and the regular factor, a kind of disease name is entered with least one regular factor
Row association, the direct correlation is divided into direct 1 grade of association, direct 2 grades of associations and associated with direct 3 grades, and the indirect association is divided into
Indirect 1 grade of association, indirect 2 grades of associations are associated with indirect 3 grades, and the relevance grades of 1 grade of association are higher than association of two grades of associations etc.
Level is higher than the relevance grades that three-level is associated；
Wherein, the regular factor logical table is carried out according to the renewal of the medical information and/or the big data information
Adjustment in real time；
Acquisition personal information, the personal information, including：The regular factor and the regular factor clinical value and/or
Main suit is worth, wherein, the clinical value is worth the actual value as the regular factor better than the main suit；
The personal information is contrasted with the regular factor logical table, the actual value is filtered out and deviates the threshold
The regular factor of value is more than between the disease name as the personalized factor according to the disease name direct correlation
Connect association, advanced correlation and be more than rudimentary association and the actual value deviation threshold value more at most bigger principle of weights, if
The weights of the personalized factor are put, and the personalized factor is ranked up according to the weights, personal label, institute is obtained
Personal label is stated, including：Initial ailment group, the initial ailment group includes at least one disease name and disease name
Claim corresponding risk class, the risk class, including：Senior risk, intermediate risk and rudimentary risk；
Wherein, the personal label, according to the renewal of the regular factor logical table and/or the personal information more
Newly, the personal label after renewal, including：Disease group is updated, the renewal disease group includes at least one disease name
Title risk class corresponding with the disease name, the risk class, including：Senior risk, intermediate risk and rudimentary risk；
When the renewal disease group includes the same disease name with the initial ailment group, the renewal disease
Group, including：The variation tendency of the same disease name.
Further, the personal information, in addition to：The disease name；The initial ailment group, including：Described
The disease name in people's information.
Further, the medical information, including：Fo Minghan cardiovascular events risk evaluation model, TIMI Rating Models,
Hamilton depressive scale, diabetes mellitus in China guideline of prevention and treatment.
Further, the big data information, including：The personal information updated.
Further, the big data information, including：The personal information Added User.
Further, the regular factor, including：Sex, age, height, body weight, habits and customs, eating habit, disease
Shape, exercise habit, medical history, family history, sign, lab index.
Further, the regular factor, in addition to：Gene information.
Further, the regular factor, including：The long-term factor and the short-term factor, the weights of the long-term factor are more than
The weights of the short-term factor.
Further, this method also includes：The personalized factor set of acquisition is combined to the personalized factor, will be described
Personalized factor set is ranked up according to risk class from high to low.
Further, this method also includes：The disease name is set up and associated, at least one disease name with it is another
The degree of association of disease name described in one is higher, then at least one disease name triggers the risk of another disease name to get over
It is high.
Compared with prior art, the individualized disease risk class analysis method described herein based on regular factor,
Realize following beneficial effect：
(1) the individualized disease risk class analysis method based on regular factor that provides of the present invention, being capable of basis in time
The medical information and/or big data information of renewal are adjusted to regular factor logical table, and when personal information updates, it is individual
People's label can also update, i.e.,：The result that disease risks are assessed be renewal with regular factor logical table and/or personal information and
Adjust at any time, therefore, the result that disease risks are assessed is more accurate and with real-time；
(2) this method is to be directed to personal information, the personalized factor is filtered out from the regular factor of personal information, then pass through
Weights are set to the personalized factor and weights are ranked up, disease risks is realized and is estimated, personalization level is high；
(3) this method adds the risk assessment to personalized factor set so as to the assessments of personal disease risks more
To be accurate；
(4) this method is associated by being set up to disease name, and the disease that patient may trigger can be estimated, and is improved
The degree of accuracy assessed patient disease risk.
Certainly, implement the present invention any product must not specific needs simultaneously reach all the above technique effect.
By referring to the drawings to the detailed description of the exemplary embodiment of the present invention, further feature of the invention and its
Advantage will be made apparent from.
Brief description of the drawings
Accompanying drawing described herein is used for providing further understanding of the present application, constitutes the part of the application, this Shen
Schematic description and description please is used to explain the application, does not constitute the improper restriction to the application.In the accompanying drawings：
Fig. 1 be the embodiment of the present invention 1 in the individualized disease risk class analysis method based on regular factor flow
Figure；
Fig. 2 is the flow chart for obtaining personal label in the embodiment 1 in the present invention；
Fig. 3 be the embodiment of the present invention 2 in the individualized disease risk class analysis method based on regular factor flow
Figure；
Fig. 4 is the flow chart that the present invention is the personal label of acquisition in the embodiment 2 in the present invention；
Fig. 5 be the embodiment of the present invention 3 in the individualized disease risk class analysis method based on regular factor flow
Figure；
Fig. 6 is the flow chart for obtaining personal label in the embodiment 3 in the present invention.
Embodiment
The various exemplary embodiments of the present invention are described in detail now with reference to accompanying drawing.It should be noted that：Unless had in addition
Body illustrates that the part and the positioned opposite of step, numerical expression and numerical value otherwise illustrated in these embodiments does not limit this
The scope of invention.
The description only actually at least one exemplary embodiment is illustrative below, never as to the present invention
And its any limitation applied or used.
It may be not discussed in detail for technology, method and apparatus known to person of ordinary skill in the relevant, but suitable
In the case of, the technology, method and apparatus should be considered as a part for specification.
In shown here and discussion all examples, any occurrence should be construed as merely exemplary, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent accompanying drawing in individual accompanying drawing.
Embodiment 1
A kind of individualized disease risk class analysis method based on regular factor is present embodiments provided, as shown in figure 1,
This method includes：
Step 101：Set up regular factor logical table
According to medical information and big data information, regular factor logical table is set up, the regular factor logical table, including：
The threshold value of disease name, regular factor and the regular factor, a kind of disease name is entered with least one regular factor
Row association, the direct correlation is divided into direct 1 grade of association, direct 2 grades of associations and associated with direct 3 grades, and the indirect association is divided into
Indirect 1 grade of association, indirect 2 grades of associations are associated with indirect 3 grades, and the relevance grades of 1 grade of association are higher than association of two grades of associations etc.
Level is higher than the relevance grades that three-level is associated；Wherein, the regular factor logical table is according to the medical information and/or the big number
It is believed that the renewal of breath is adjusted in real time.
Step 102：Obtain personal information
Acquisition personal information, the personal information, including：The regular factor and the regular factor clinical value and/or
Main suit is worth, wherein, the clinical value is worth the actual value as the regular factor better than the main suit.
Step 103：Obtain personal label
Specifically, as shown in Fig. 2 step 103 is specifically included：
Step 1031：The personalized factor of screening
The personal information is contrasted with the regular factor logical table, the actual value is filtered out and deviates the threshold
The regular factor of value is used as the personalized factor.
Step 1032：Weights and sequence are set
It is more than according to the disease name direct correlation with the disease name indirect association, advanced correlation more than rudimentary
Association and the actual value deviate the threshold value more at most bigger principle of weights, set the weights of the personalized factor,
And the personalized factor is ranked up according to the weights,
Step 1033：The personal label of generation
The personal label of acquisition, the personal label, including：Initial ailment group, the initial ailment group includes at least one
The disease name and the corresponding risk class of the disease name, the risk class, including：Senior risk, intermediate risk
With rudimentary risk.
Step 104：More new individual label
The personal label, updates according to the renewal of the regular factor logical table and/or the personal information, updates
The personal label afterwards, including：Disease group is updated, the renewal disease group includes at least one disease name and described
The corresponding risk class of disease name, the risk class, including：Senior risk, intermediate risk and rudimentary risk；It is described to update
When disease group includes the same disease name with the initial ailment group, the renewal disease group, including：The same institute
State the variation tendency of disease name.
In the present embodiment, described medical information, what the including but not limited to current whole world was confirmed and used extensively
Health model, disease model, life quality model and authoritative guide document, for example：Fo Minghan cardiovascular event risk assessment
Model, TIMI Rating Models, Hamilton depressive scale, diabetes mellitus in China guideline of prevention and treatment etc..
In the present embodiment, described regular factor derives from the medical information, for example：Sex, age, height, body
Weight, habits and customs, eating habit, symptom, exercise habit, medical history, family history, sign, lab index etc..
For carrying out the patient that blood, other body fluid or cell are detected to DNA, the patient is resulted in
The gene information of certain disease may be suffered from, therefore, gene information can also be used as the regular factor for assessing disease risks grade.
The contingency table of the disease name of table 1. and regular factor
Table 1 gives the association situation of the regular factor of hypertension and diabetes, is illustrated by taking hypertension as an example：High blood
Pressure (disease name) is direct 1 grade with blood pressure (regular factor) and associated that being direct 2 grades with blood glucose (regular factor) associates, with blood
Fat (regular factor) is direct 3 grades of associations；Hypertension (disease name) is indirect 1 grade with family history (regular factor) and associates, with
BMI (regular factor) is indirect 2 grades of associations, is indirect 3 grades with sodium intake (regular factor) and associates, wherein BMI refers to Body
Mass Index, i.e.,：Body-mass index.In the setting of weights, the weights with the regular factor of disease name direct correlation
More than the weights with the regular factor of disease name indirect association；The weights of advanced correlation are more than the weights of rudimentary association, i.e.,：Directly
Connect the weights of 1 grade of association>The weights of direct 2 grades of associations>The weights of direct 3 grades of associations；The weights of indirect 1 grade of association>Indirect 2 grades
The weights of association>The weights of indirect 3 grades of associations.
The regular factor logical table of table 2.
The regular factor logical table of hypertension and diabetes is shown in table 2, is illustrated with hypertension：
User A input information be：Blood pressure (125), blood glucose (5.2), blood fat (1.56), family history (hypertension), BMI
(20), sodium intake (12), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user A personalization
The factor is：Blood pressure, blood fat and family history, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A
The personalized factor weights：Blood pressure [0.2], family history [0.1], the ranking results of the user A personalized factor are：Blood pressure>
Family history.The weights sum m of every personalization factor value is 0.3, is determined as the intermediate risk of hypertension.
User B input information be：Blood pressure (150), blood glucose (5.2), blood fat (1.56), family history (nothing), BMI
(22.6), sodium intake (6), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user B individual character
Changing the factor is：Blood pressure and sodium intake, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A's
The weights of the personalized factor：Blood pressure [0.5], sodium take in [0.2], and the ranking results of the user B personalized factor are：Blood pressure>Sodium
Intake；The weights sum m of every personalization factor value is 0.7, is determined as the senior risk of hypertension.
Contrast user A and user B：Although user A has family history of hypertension, user A blood pressure (125) is not high
Go out normal value a lot, and the amount control that sodium is taken in diet, in the scope of low-risk, the risk class of hypertension is intermediate wind
Danger；And although user B is without family history of hypertension, pressure value is up to 150, and the sodium of long-term excess intake, high
The risk class of blood pressure is senior risk.It can be seen by the assessment result of above-mentioned user A and user B risk of hypertension grade
Go out, the personalized factor of each user is different, and the weights of the personalized factor are also different, the weights of the personalized factor are set
Putting is determined by multiple standards such as relevance grades, directly/indirect association and the degree for deviateing threshold value, is a synthesis
Result, therefore the setting of weights is more accurate, and meets the situation of individual, and personalization level is higher.
It should be appreciated that the disease name in personality label can suffered from the disease or potential disease, the present invention is not only to
The risk class suffered from the disease is estimated, and the risk to potential disease is also estimated, and the risk class of potential disease is assessed
There is important directive significance to prevention from suffering from the diseases.
It should be noted that the regular factor logical table in the present invention includes common disease and associated with disease
Regular factor, table 2 illustrate only two kinds of diseases of hypertension therein and diabetes, simply exemplary illustration, be not used to limit
Disease name and the species of regular factor that regular factor logical table processed is included.
The big data information, including：The personal information Added User and the personal information updated.When using we
When method increases the user that disease risks are estimated, the information of statistics can also increase, the degree of accuracy to the assessment of this method
Lifted.For example：Influence of the smoking to lung is very big, smoking (regular factor) and lung cancer (disease name) direct correlation, but
It is that daily smoking capacity is different, the risk for suffering from lung cancer is different, and medical information does not provide smoking capacity and lung cancer to this
The corresponding relation of risk, in this regard, this method is estimated using big data information, when the radix (customer volume) of big data information
When different, the degree of accuracy of assessment is also different, and the radix of big data information is bigger, and the degree of accuracy is higher.When the personal information updates
Afterwards, the assessment result of disease risks is it can also happen that change, such as：Initial ailment group in user C personal label includes height
After blood pressure, but user C personal information renewal, pressure value tends to be normal in user C personal information, and blood glucose has been raised,
Therefore, updating disease group includes：Risk of hypertension is reduced, and tends to be normal；With the risk for suffering from hyperglycaemia.
Obtained for the first time after personal information by disease it should be noted that the initial ailment group in the present invention is not only
Obtained after risk assessment, and refer to before the regular factor logical table each time and/or personal information renewal
Included disease group in people's label, i.e.,：After the regular factor logical table next time and/or the personal information update,
The renewal disease group before will be used as initial ailment group.
In the present embodiment, the personal information, in addition to：The disease name, the initial ailment group, including：Institute
State the disease name in personal information.For example：Write exactly in the personal information of someone with diabetes, then to this
When patient carries out disease risks assessment, diabetes are added into initial ailment group automatically, and by diabetes and the patient and diabetes
The related personalized factor needs the personalized factor of long-term monitoring as the patient.
In the present embodiment, the regular factor is divided into the long-term factor and the short-term factor.Someone hangs up one's hat in humidity
In environment, coal miner long-term work in the environment containing a large amount of dust, member's eating cure food of some family, for a long time
Sodium excess intake；These environmental factors or habits and customs are generally all worked to human body for a long time, therefore, humidity, dust, sodium
Excess intake is the long-term factor.Someone makes drunk due to having participated in classmate's party, drinks for being occasional for the people
Situation, only can be worked in one day after drinking or several days, therefore, drink for being the short-term factor for this people.
When being estimated, the weights of the long-term factor are higher than the weights of the short-term factor.
The individualized disease risk class analysis method based on regular factor that the present embodiment is provided, can be in time according to more
New medical information and/or big data information is adjusted to regular factor logical table, and when personal information updates, it is personal
Label can also update, i.e.,：The result that disease risks are assessed be renewal with regular factor logical table and/or personal information and with
When adjust, therefore, the result that disease risks are assessed is more accurate and with real-time；This method is to be directed to personal information, from
The personalized factor is filtered out in the regular factor of personal information, then by setting weights to the personalized factor and weights being arranged
Sequence, realizes disease risks and is estimated, and personalization level is high.
Embodiment 2
A kind of individualized disease risk class analysis method based on regular factor is present embodiments provided, as shown in figure 3,
This method includes：
Step 201：Set up regular factor logical table
According to medical information and big data information, regular factor logical table is set up, the regular factor logical table, including：
The threshold value of disease name, regular factor and the regular factor, a kind of disease name is entered with least one regular factor
Row association, the direct correlation is divided into direct 1 grade of association, direct 2 grades of associations and associated with direct 3 grades, and the indirect association is divided into
Indirect 1 grade of association, indirect 2 grades of associations are associated with indirect 3 grades；Wherein, the regular factor logical table is according to the medical information
And/or the renewal of the big data information is adjusted in real time.
Step 202：Obtain personal information
Acquisition personal information, the personal information, including：The regular factor and the regular factor clinical value and/or
Main suit is worth, wherein, the clinical value is worth the actual value as the regular factor better than the main suit.
Step 203：Obtain personal label
Specifically, as shown in figure 4, step 203 includes：
Step 2031：The personalized factor of screening
The personal information is contrasted with the regular factor logical table, the actual value is filtered out and deviates the threshold
The regular factor of value is used as the personalized factor.
Step 2032：Weights and sequence are set
It is more than according to the disease name direct correlation with the disease name indirect association, advanced correlation more than rudimentary
The principle of association, sets the weights of the personalized factor, and the personalized factor is ranked up according to the weights,
Step 2033：Obtain personalized factor set
The personalized factor set of acquisition is combined to the personalized factor, by the personalized factor set according to by height to
Low risk class is ranked up.
Step 2034：The personal label of generation
The personal label of acquisition, the personal label, including：Initial ailment group, the initial ailment group includes at least one
The disease name and the corresponding risk class of the disease name, the risk class, including：Senior risk, intermediate risk
With rudimentary risk.
Step 204：More new individual label
The personal label, updates according to the renewal of the regular factor logical table and/or the personal information, updates
The personal label afterwards, including：Disease group is updated, the renewal disease group includes at least one disease name and described
The corresponding risk class of disease name, the risk class, including：Senior risk, intermediate risk and rudimentary risk；
When the renewal disease group includes the same disease name with the initial ailment group, the renewal disease
Group, including：The variation tendency of the same disease name.
In the present embodiment, described medical information, what the including but not limited to current whole world was confirmed and used extensively
Health model, disease model, life quality model and authoritative guide document, for example：Fo Minghan cardiovascular event risk assessment
Model, TIMI Rating Models, Hamilton depressive scale, diabetes mellitus in China guideline of prevention and treatment etc..
In the present embodiment, described regular factor derives from the medical information, for example：Sex, age, height, body
Weight, habits and customs, eating habit, symptom, exercise habit, medical history, family history, sign, lab index etc..
For carrying out the patient that blood, other body fluid or cell are detected to DNA, the patient is resulted in
The gene information of certain disease may be suffered from, therefore, gene information can also be used as the regular factor for assessing disease risks grade.
Disease name and regular factor to associate situation as shown in table 3：
The contingency table of the disease name of table 3. and regular factor
Table 3 gives the association situation of the regular factor of hypertension and diabetes, is illustrated by taking hypertension as an example：High blood
Pressure (disease name) is direct 1 grade with blood pressure (regular factor) and associated that being direct 2 grades with blood glucose (regular factor) associates, with blood
Fat (regular factor) is direct 3 grades of associations；Hypertension (disease name) is indirect 1 grade with family history (regular factor) and associates, with
BMI (regular factor) is indirect 2 grades of associations, is indirect 3 grades with sodium intake (regular factor) and associates, wherein BMI refers to Body
Mass Index, i.e.,：Body-mass index.In the setting of weights, the weights with the regular factor of disease name direct correlation
More than the weights with the regular factor of disease name indirect association；The weights of advanced correlation are more than the weights of rudimentary association, i.e.,：Directly
Connect the weights of 1 grade of association>The weights of direct 2 grades of associations>The weights of direct 3 grades of associations；The weights of indirect 1 grade of association>Indirect 2 grades
The weights of association>The weights of indirect 3 grades of associations.
The regular factor logical table of table 4.
The regular factor logical table of hypertension and diabetes is shown in table 4, is illustrated with hypertension：
User A input information be：Blood pressure (125), blood glucose (5.2), blood fat (1.56), family history (hypertension), BMI
(20), sodium intake (12), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user A personalization
The factor is：Blood pressure, blood fat and family history, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A
The personalized factor weights：Blood pressure [0.2], family history [0.1], the ranking results of the user A personalized factor are：Blood pressure>
Family history.The weights sum m of every personalization factor value is 0.3, is determined as the intermediate risk of hypertension.
User B input information be：Blood pressure (150), blood glucose (5.2), blood fat (1.56), family history (nothing), BMI
(22.6), sodium intake (6), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user B individual character
Changing the factor is：Blood pressure and sodium intake, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A's
The weights of the personalized factor：Blood pressure [0.5], sodium take in [0.2], and the ranking results of the user B personalized factor are：Blood pressure>Sodium
Intake；The weights sum m of every personalization factor value is 0.7, is determined as the senior risk of hypertension.
Contrast user A and user B：Although user A has family history of hypertension, user A blood pressure (125) is not high
Go out normal value a lot, and the amount control that sodium is taken in diet, in the scope of low-risk, the risk class of hypertension is intermediate wind
Danger；And although user B is without family history of hypertension, pressure value is up to 150, and the sodium of long-term excess intake, high
The risk class of blood pressure is senior risk.It can be seen by the assessment result of above-mentioned user A and user B risk of hypertension grade
Go out, the personalized factor of each user is different, and the weights of the personalized factor are also different, the weights of the personalized factor are set
Putting is determined by multiple standards such as relevance grades, directly/indirect association and the degree for deviateing threshold value, is a synthesis
Result, therefore the setting of weights is more accurate, and meets the situation of individual, and personalization level is higher.
It should be appreciated that the disease name in personality label can suffered from the disease or potential disease, the present invention is not only to
The risk class suffered from the disease is estimated, and the risk to potential disease is also estimated, and the risk class of potential disease is assessed
There is important directive significance to prevention from suffering from the diseases.
It should be noted that the regular factor logical table in the present invention includes common disease and associated with disease
Regular factor, table 4 illustrate only two kinds of diseases of hypertension therein and diabetes, simply exemplary illustration, be not used to limit
Disease name and the species of regular factor that regular factor logical table processed is included.
The big data information, including：The personal information Added User and the personal information updated.When using we
When method increases the user that disease risks are estimated, the information of statistics can also increase, the degree of accuracy to the assessment of this method
Lifted.For example：Influence of the smoking to lung is very big, smoking (regular factor) and lung cancer (disease name) direct correlation, but
It is that daily smoking capacity is different, the risk for suffering from lung cancer is different, and medical information does not provide smoking capacity and lung cancer to this
The corresponding relation of risk, in this regard, this method is estimated using big data information, when the radix (customer volume) of big data information
When different, the degree of accuracy of assessment is also different, and the radix of big data information is bigger, and the degree of accuracy is higher.When the personal information updates
Afterwards, the assessment result of disease risks is it can also happen that change, such as：Initial ailment group in user C personal label includes height
After blood pressure, but user C personal information renewal, pressure value tends to be normal in user C personal information, and blood glucose has been raised,
Therefore, updating disease group includes：Risk of hypertension is reduced, and tends to be normal；With the risk for suffering from hyperglycaemia.
Obtained for the first time after personal information by disease it should be noted that the initial ailment group in the present invention is not only
Obtained after risk assessment, and refer to before the regular factor logical table each time and/or personal information renewal
Included disease group in people's label, i.e.,：After the regular factor logical table next time and/or the personal information update,
The renewal disease group before will be used as initial ailment group.
In the present embodiment, the personal information, in addition to：The disease name, the initial ailment group, including：Institute
State the disease name in personal information.For example：Write exactly in the personal information of someone with diabetes, then to this
Patient carry out disease risks assessment when, automatically by diabetes add initial ailment group, and by diabetes and with the patient and sugar
The related personalized factor of urine disease needs the personalized factor of long-term monitoring as the patient.
In the present embodiment, the regular factor is divided into the long-term factor and the short-term factor.Someone hangs up one's hat in humidity
In environment, coal miner long-term work in the environment containing a large amount of dust, member's eating cure food of some family, for a long time
Sodium excess intake；These environmental factors or habits and customs are generally all worked to human body for a long time, therefore, humidity, dust, sodium
Excess intake is the long-term factor.Someone makes drunk due to having participated in classmate's party, drinks for being occasional for the people
Situation, only can be worked in one day after drinking or several days, therefore, drink for being the short-term factor for this people.
When being estimated, because the influence of long-term factor pair human body is more than the short-term factor, therefore, the weights of the long-term factor are higher than short
The weights of the phase factor.
In the present embodiment, personalized factor set by the how personalized factor set associated with a certain disease name into,
The personalized factor that personalized factor set is included is different, then the risk for suffering from certain disease is different.Table 5 gives of hypertension
The risk table of property factor set：
The risk table of the personalized factor set of the hypertension of table 5.
Show that influence of the different personalized factor sets to hypertension is different in table 5, for example：Assuming that A1 is blood pressure, B1
Be family history, C1 be blood glucose, D1 be smoking, E1 be drink, F1 is that blood fat, F2 are flu histories, then by A1＆B1＆C1＆D1＆E1＆F1
The value-at-risk that the personalized factor set of composition suffers from hypertension is apparently higher than the personalized factor being made up of A1＆B1＆C1＆D1＆E1＆F2
The value-at-risk of group, the corresponding value-at-risk of different personalized factor sets is different, and the corresponding value-at-risk of personalized factor set is higher, then
Risk class in the personal label of generation is higher.
Risk class corresponding to 35% personalized factor set is senior risk, corresponding to 35% personalized factor set
Risk class be intermediate risk, the risk class corresponding to 30% personalized factor set is rudimentary risk.Wherein：
As the corresponding value-at-risk n of personalized factor set >=0.65, then the personalized factor set corresponding disease name
Risk class is senior risk；When the corresponding value-at-risk 0.3 of personalized factor set<n<When 0.35, then the personalized factor set pair
The risk class for the disease name answered is intermediate risk；As the corresponding value-at-risk n of personalized factor set≤0.3, then the individual character
The risk class for changing the corresponding disease name of factor set is rudimentary risk.
It should be noted that in the present embodiment, although table 5 merely illustrates different personalized factor sets to hypertension
, but this is an exemplary illustration, is not limited to the combination of disease name and regular factor.
The individualized disease risk class analysis method based on regular factor that the present embodiment is provided, can be in time according to more
New medical information and/or big data information is adjusted to regular factor logical table, and when personal information updates, it is personal
Label can also update, i.e.,：The result that disease risks are assessed be renewal with regular factor logical table and/or personal information and with
When adjust, therefore, the result that disease risks are assessed is more accurate and with real-time；This method is to be directed to personal information, from
The personalized factor is filtered out in the regular factor of personal information, then by setting weights to the personalized factor and weights being arranged
Sequence, realizes disease risks and is estimated, and personalization level is high；Add the risk assessment to personalized factor set so that right
The assessment of personal disease risks is more accurate.
Embodiment 3
A kind of individualized disease risk class analysis method based on regular factor is present embodiments provided, as shown in figure 5,
This method includes：
Step 301：Set up regular factor logical table
According to medical information and big data information, regular factor logical table is set up, the regular factor logical table, including：
The threshold value of disease name, regular factor and the regular factor, a kind of disease name is entered with least one regular factor
Row association, the direct correlation is divided into direct 1 grade of association, direct 2 grades of associations and associated with direct 3 grades, and the indirect association is divided into
Indirect 1 grade of association, indirect 2 grades of associations are associated with indirect 3 grades；Wherein, the regular factor logical table is according to the medical information
And/or the renewal of the big data information is adjusted in real time.
Step 302：Obtain personal information
Acquisition personal information, the personal information, including：The regular factor and the regular factor clinical value and/or
Main suit is worth, wherein, the clinical value is worth the actual value as the regular factor better than the main suit.
Step 303：Obtain personal label
Specifically, as shown in fig. 6, step 303 is specifically included：
Step 3031：The personalized factor of screening
The personal information is contrasted with the regular factor logical table, the actual value is filtered out and deviates the threshold
The regular factor of value is used as the personalized factor.
Step 3032：Weights and sequence are set
It is more than according to the disease name direct correlation with the disease name indirect association, advanced correlation more than rudimentary
Association and the actual value deviate the threshold value more at most bigger principle of weights, set the weights of the personalized factor,
And the personalized factor is ranked up according to the weights,
Step 3033：Disease name is set up and associated
At least one disease name is associated with another disease name, at least one disease name
The degree of association with another disease name is higher, then at least one disease name triggers the wind of another disease name
Danger is higher.
Step 3034：The personal label of generation
The personal label of acquisition, the personal label, including：Initial ailment group, the initial ailment group includes at least one
The disease name and the corresponding risk class of the disease name, the risk class, including：Senior risk, intermediate risk
With rudimentary risk.
Step 304：More new individual label
The personal label, updates according to the renewal of the regular factor logical table and/or the personal information, updates
The personal label afterwards, including：Disease group is updated, the renewal disease group includes at least one disease name and described
The corresponding risk class of disease name, the risk class, including：Senior risk, intermediate risk and rudimentary risk；It is described to update
When disease group includes the same disease name with the initial ailment group, the renewal disease group, including：The same institute
State the variation tendency of disease name.
In the present embodiment, described medical information, what the including but not limited to current whole world was confirmed and used extensively
Health model, disease model, life quality model and authoritative guide document, for example：Fo Minghan cardiovascular event risk assessment
Model, TIMI Rating Models, Hamilton depressive scale, diabetes mellitus in China guideline of prevention and treatment etc..
In the present embodiment, described regular factor derives from the medical information, for example：Sex, age, height, body
Weight, habits and customs, eating habit, symptom, exercise habit, medical history, family history, sign, lab index etc..For carrying out
For crossing the individual that blood, other body fluid or cell are detected to DNA, the base of certain disease may be suffered to obtain individual
Because of information, therefore, gene information can also be used as the regular factor for assessing disease risks grade.
The contingency table of the disease name of table 6. and regular factor
Table 6 gives the association situation of the regular factor of hypertension and diabetes, is illustrated by taking hypertension as an example：High blood
Pressure (disease name) is direct 1 grade with blood pressure (regular factor) and associated that being direct 2 grades with blood glucose (regular factor) associates, with blood
Fat (regular factor) is direct 3 grades of associations；Hypertension (disease name) is indirect 1 grade with family history (regular factor) and associates, with
BMI (regular factor) is indirect 2 grades of associations, is indirect 3 grades with sodium intake (regular factor) and associates, wherein BMI refers to Body
Mass Index, i.e.,：Body-mass index.In the setting of weights, the weights with the regular factor of disease name direct correlation
More than the weights with the regular factor of disease name indirect association；The weights of advanced correlation are more than the weights of rudimentary association, i.e.,：Directly
Connect the weights of 1 grade of association>The weights of direct 2 grades of associations>The weights of direct 3 grades of associations.
The regular factor logical table of table 7.
The regular factor logical table of hypertension and diabetes is shown in table 7, is illustrated with hypertension：
User A input information be：Blood pressure (125), blood glucose (5.2), blood fat (1.56), family history (hypertension), BMI
(20), sodium intake (12), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user A personalization
The factor is：Blood pressure, blood fat and family history, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A
The personalized factor weights：Blood pressure [0.2], family history [0.1], the ranking results of the user A personalized factor are：Blood pressure>
Family history.The weights sum m of every personalization factor value is 0.3, is determined as the intermediate risk of hypertension.
User B input information be：Blood pressure (150), blood glucose (5.2), blood fat (1.56), family history (nothing), BMI
(22.6), sodium intake (6), in this regard, being contrasted by the regular factor logical table with hypertension, filters out user B individual character
Changing the factor is：Blood pressure and sodium intake, by relevance grades, directly/indirect association and the degree for deviateing threshold value, set user A's
The weights of the personalized factor：Blood pressure [0.5], sodium take in [0.2], and the ranking results of the user B personalized factor are：Blood pressure>Sodium
Intake；The weights sum m of every personalization factor value is 0.7, is determined as the senior risk of hypertension.
Contrast user A and user B：Although user A has family history of hypertension, user A blood pressure (125) is not high
Go out normal value a lot, and the amount control that sodium is taken in diet, in the scope of low-risk, the risk class of hypertension is intermediate wind
Danger；And although user B is without family history of hypertension, pressure value is up to 150, and the sodium of long-term excess intake, high
The risk class of blood pressure is senior risk.It can be seen by the assessment result of above-mentioned user A and user B risk of hypertension grade
Go out, the personalized factor of each user is different, and the weights of the personalized factor are also different, the weights of the personalized factor are set
Putting is determined by multiple standards such as relevance grades, directly/indirect association and the degree for deviateing threshold value, is a synthesis
Result, therefore the setting of weights is more accurate, and meets the situation of individual, and personalization level is higher.
It should be appreciated that the disease name in personality label can suffered from the disease or potential disease, the present invention is not only to
The risk class suffered from the disease is estimated, and the risk to potential disease is also estimated, and the risk class of potential disease is assessed
There is important directive significance to prevention from suffering from the diseases.
It should be noted that the regular factor logical table in the present invention includes common disease and associated with disease
Regular factor, table 7 illustrate only two kinds of diseases of hypertension therein and diabetes, simply exemplary illustration, be not used to limit
Disease name and the species of regular factor that regular factor logical table processed is included.
The big data information, including：The personal information Added User and the personal information updated.When using we
When method increases the user that disease risks are estimated, the information of statistics can also increase, the degree of accuracy to the assessment of this method
Lifted.For example：Influence of the smoking to lung is very big, smoking (regular factor) and lung cancer (disease name) direct correlation, but
It is that daily smoking capacity is different, the risk for suffering from lung cancer is different, and medical information does not provide smoking capacity and lung cancer to this
The corresponding relation of risk, in this regard, this method is estimated using big data information, when the radix (customer volume) of big data information
When different, the degree of accuracy of assessment is also different, and the radix of big data information is bigger, and the degree of accuracy is higher.When the personal information updates
Afterwards, the assessment result of disease risks is it can also happen that change, such as：Initial ailment group in user C personal label includes height
After blood pressure, but user C personal information renewal, pressure value tends to be normal in user C personal information, and blood glucose has been raised,
Therefore, updating disease group includes：Risk of hypertension is reduced, and tends to be normal；With the risk for suffering from hyperglycaemia.
Obtained for the first time after personal information by disease it should be noted that the initial ailment group in the present invention is not only
Obtained after risk assessment, and refer to before the regular factor logical table each time and/or personal information renewal
Included disease group in people's label, i.e.,：After the regular factor logical table next time and/or the personal information update,
The renewal disease group before will be used as initial ailment group.
In the present embodiment, the personal information, in addition to：The disease name, the initial ailment group, including：Institute
State the disease name in personal information.For example：Write exactly in the personal information of someone with diabetes, then to this
When patient carries out disease risks assessment, diabetes are added into initial ailment group automatically, and by related normal of diabetes and diabetes
The rule factor needs the personalized factor of long-term monitoring as the patient.
In the present embodiment, the regular factor is divided into the long-term factor and the short-term factor.Someone hangs up one's hat in humidity
In environment, coal miner long-term work in the environment containing a large amount of dust, member's eating cure food of some family, for a long time
Sodium excess intake；These environmental factors or habits and customs are generally all worked to human body for a long time, therefore, humidity, dust, sodium
Excess intake is the long-term factor.Someone makes drunk due to having participated in classmate's party, drinks for being occasional for the people
Situation, only can be worked in one day after drinking or several days, therefore, drink for being the short-term factor for this people.
When being estimated, the weights of the long-term factor are higher than the weights of the short-term factor.
In the present embodiment, associated, the disease of the possibility initiation by user can be commented by being set up to disease name
Estimate, table 8 gives initiation risk of the various diseases to hypertension：
Initiation risk table of the various diseases of table 8. to hypertension
Initiation risk of the various diseases to hypertension is shown in table 8, if some patient is simultaneously with diabetes ＆ brains soldier
The diseases such as middle ＆ metabolic syndromes ＆ atherosclerosis ＆ auricular fibrillation ＆ miocardial infarctions, then this patient suffer from hypertension risk
It is high, i.e.,：The combination of these diseases easily triggers hypertension；But if some patient only has flu history, then, the patient is several
The risk of hypertension is not suffered from, i.e.,：The possibility that flu does not almost trigger to hypertension.
A certain or several diseases are higher to the initiation value-at-risk w of another disease, then the trouble in the personal label generated
The risk class of another disease is higher.
For convenience of description, above-mentioned a certain or several diseases are turned into disease group, the wind corresponding to 35% disease group
Dangerous grade is senior risk, and risk class corresponding to 35% disease group is intermediate risk, corresponding to 30% disease group
Risk class is rudimentary risk.Wherein：
As the corresponding value-at-risk n of disease group >=0.65, then the risk class of the corresponding disease name of disease group is height
Level risk；When the corresponding value-at-risk 0.3 of disease group<n<When 0.35, then the risk class of the corresponding disease name of disease group is
Intermediate risk；As the corresponding value-at-risk n of disease group≤0.3, then the risk class of the corresponding disease name of disease group is low
Level risk.
The individualized disease risk class analysis method based on regular factor that the present embodiment is provided, can be in time according to more
New medical information and/or big data information is adjusted to regular factor logical table, and when personal information updates, it is personal
Label can also update, i.e.,：The result that disease risks are assessed be renewal with regular factor logical table and/or personal information and with
When adjust, therefore, the result that disease risks are assessed is more accurate and with real-time；This method is to be directed to personal information, from
The personalized factor is filtered out in the regular factor of personal information, then by setting weights to the personalized factor and weights being arranged
Sequence, realizes disease risks and is estimated, and personalization level is high；By to disease name set up associate, can be to patient can
The disease that can trigger is estimated, and improves the degree of accuracy of the assessment to the disease risks of patient.
The individualized disease risk class analysis side based on regular factor provided by above example, the application
Method has reached following beneficial effect：
(1) the individualized disease risk class analysis method based on regular factor that provides of the present invention, being capable of basis in time
The medical information and/or big data information of renewal are adjusted to regular factor logical table, and when personal information updates, it is individual
People's label can also update, i.e.,：The result that disease risks are assessed be renewal with regular factor logical table and/or personal information and
Adjust at any time, therefore, the result that disease risks are assessed is more accurate and with real-time；
(2) this method is to be directed to personal information, the personalized factor is filtered out from the regular factor of personal information, then pass through
Weights are set to the personalized factor and weights are ranked up, disease risks is realized and is estimated, personalization level is high；
(3) this method adds the risk assessment to personalized factor set so as to the assessments of personal disease risks more
To be accurate；
(4) this method is associated by being set up to disease name, the disease that the possibility of patient triggers can be estimated, carried
The degree of accuracy of the assessment of the high disease risks to patient.
Certainly, implement the present invention any product must not specific needs simultaneously reach all the above technique effect.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, device or computer program
Product.Therefore, the present invention can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.
Although some specific embodiments of the present invention are described in detail by example, the skill of this area
Art personnel are it should be understood that example above is merely to illustrate, the scope being not intended to be limiting of the invention.The skill of this area
Art personnel to above example it should be understood that can modify without departing from the scope and spirit of the present invention.This hair
Bright scope is defined by the following claims.
Claims (10)
1. a kind of individualized disease risk class analysis method based on regular factor, it is characterised in that including：
According to medical information and big data information, regular factor logical table is set up, the regular factor logical table, including：Disease
The threshold value of title, regular factor and the regular factor, a kind of disease name is closed with least one regular factor
Connection, the direct correlation is divided into direct 1 grade of association, direct 2 grades of associations and associated with direct 3 grades, and the indirect association is divided into indirect 1
Level association, indirect 2 grades of associations are associated with indirect 3 grades, and the relevance grades of 1 grade of association are higher than higher than the relevance grades of two grades of associations
The relevance grades of three-level association；
Wherein, the regular factor logical table carries out real-time according to the renewal of the medical information and/or the big data information
Adjustment；
Acquisition personal information, the personal information, including：The regular factor and the regular factor clinical value and/or main suit
Value, wherein, the clinical value is worth the actual value as the regular factor better than the main suit；
The personal information is contrasted with the regular factor logical table, the actual value is filtered out and deviates the threshold value
The regular factor is closed indirectly as the personalized factor according to being more than with the disease name direct correlation with the disease name
Connection, advanced correlation are more than rudimentary association and the actual value deviates the threshold value more at most bigger principle of weights, set institute
The weights of the personalized factor are stated, and the personalized factor is ranked up according to the weights, personal label, described is obtained
People's label, including：Initial ailment group, the initial ailment group includes at least one disease name and the disease name pair
The risk class answered, the risk class judged according to the weights sum of the personalized factor, the personalized factor
Weights sum m >=0.65, be determined as senior risk；The scope of the weights sum of the personalized factor is 0.65<m<0.3,
It is determined as intermediate risk；Weights sum m≤0.3 of the personalized factor, is determined as low-risk；
Wherein, the personal label, updates, more according to the renewal of the regular factor logical table and/or the personal information
The personal label after new, including：Disease group is updated, the renewal disease group includes at least one disease name and institute
State the corresponding risk class of disease name, the risk class, including：Senior risk, intermediate risk and rudimentary risk；
When the renewal disease group includes the same disease name with the initial ailment group, the renewal disease group, bag
Include：The variation tendency of the same disease name.
2. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The personal information, in addition to：The disease name,
The initial ailment group, including：The disease name in the personal information.
3. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The medical information, including：Fo Minghan cardiovascular events risk evaluation model, TIMI Rating Models, Hamilton depressive scale,
Diabetes mellitus in China guideline of prevention and treatment.
4. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The big data information, including：The personal information updated.
5. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The big data information, including：The personal information Added User.
6. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The regular factor, including：Sex, age, height, body weight, habits and customs, eating habit, symptom, previously exercise habit, disease
History, family history, sign, lab index.
7. the individualized disease risk class analysis method according to claim 6 based on regular factor, it is characterised in that
The regular factor, in addition to：Gene information.
8. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
The regular factor, including：The long-term factor and the short-term factor, the weights of the long-term factor are more than the power of the short-term factor
Value.
9. the individualized disease risk class analysis method according to claim 1 based on regular factor, it is characterised in that
Also include：The personalized factor set of acquisition is combined to the personalized factor, by the personalized factor set according to by height to
Low risk class is ranked up.
10. the individualized disease risk class analysis method according to claim 1 based on regular factor, its feature exists
In, in addition to：The disease name is set up and associated, at least one disease name is carried out with another disease name
Association, the degree of association of at least one disease name and another disease name is higher, then at least one disease name
Cite approvingly the risk for sending out the disease name another higher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758822.XA CN107301326A (en) | 2017-08-29 | 2017-08-29 | Individualized disease risk class analysis method based on regular factor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758822.XA CN107301326A (en) | 2017-08-29 | 2017-08-29 | Individualized disease risk class analysis method based on regular factor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107301326A true CN107301326A (en) | 2017-10-27 |
Family
ID=60132465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710758822.XA Pending CN107301326A (en) | 2017-08-29 | 2017-08-29 | Individualized disease risk class analysis method based on regular factor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107301326A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122612A (en) * | 2017-12-20 | 2018-06-05 | 姜涵予 | The foundation of database, various dimensions health risk grade determine method and device |
| WO2019196299A1 (en) * | 2018-04-09 | 2019-10-17 | 平安科技（深圳）有限公司 | Electronic device, nasopharyngeal cancer risk warning method and computer readable storage medium |
| CN110517775A (en) * | 2019-08-12 | 2019-11-29 | 上海艾莎信息科技有限公司 | Disease risks prediction technique, device, computer equipment and storage medium |
| CN110767317A (en) * | 2019-08-30 | 2020-02-07 | 贵州力创科技发展有限公司 | Cloud computing platform and method based on data mining and big data analysis |
| CN115458172A (en) * | 2022-11-11 | 2022-12-09 | 中山大学附属第一医院 | A heart risk assessment system, device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999686A (en) * | 2011-09-19 | 2013-03-27 | 上海煜策信息科技有限公司 | Health management system and implementation method thereof |
| CN105574337A (en) * | 2015-12-16 | 2016-05-11 | 上海亿保健康管理有限公司 | Health evaluation device |
| US20160224753A1 (en) * | 2015-02-02 | 2016-08-04 | Heartflow, Inc. | Systems and methods for diagnosis, risk assessment, and/or virtual treatment assessment of visceral ischemia |
| CN106355033A (en) * | 2016-09-27 | 2017-01-25 | 无锡金世纪国民体质与健康研究有限公司 | Life risk assessment system |
-
2017
- 2017-08-29 CN CN201710758822.XA patent/CN107301326A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999686A (en) * | 2011-09-19 | 2013-03-27 | 上海煜策信息科技有限公司 | Health management system and implementation method thereof |
| US20160224753A1 (en) * | 2015-02-02 | 2016-08-04 | Heartflow, Inc. | Systems and methods for diagnosis, risk assessment, and/or virtual treatment assessment of visceral ischemia |
| CN105574337A (en) * | 2015-12-16 | 2016-05-11 | 上海亿保健康管理有限公司 | Health evaluation device |
| CN106355033A (en) * | 2016-09-27 | 2017-01-25 | 无锡金世纪国民体质与健康研究有限公司 | Life risk assessment system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122612A (en) * | 2017-12-20 | 2018-06-05 | 姜涵予 | The foundation of database, various dimensions health risk grade determine method and device |
| WO2019196299A1 (en) * | 2018-04-09 | 2019-10-17 | 平安科技（深圳）有限公司 | Electronic device, nasopharyngeal cancer risk warning method and computer readable storage medium |
| CN110517775A (en) * | 2019-08-12 | 2019-11-29 | 上海艾莎信息科技有限公司 | Disease risks prediction technique, device, computer equipment and storage medium |
| CN110767317A (en) * | 2019-08-30 | 2020-02-07 | 贵州力创科技发展有限公司 | Cloud computing platform and method based on data mining and big data analysis |
| CN115458172A (en) * | 2022-11-11 | 2022-12-09 | 中山大学附属第一医院 | A heart risk assessment system, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Reichard et al. | Health disparities among adults with physical disabilities or cognitive limitations compared to individuals with no disabilities in the United States | |
| Chia et al. | Assessment of vision-related quality of life in an older population subsample: The Blue Mountains Eye Study | |
| CN107301326A (en) | Individualized disease risk class analysis method based on regular factor | |
| Jasper et al. | Determinants of diabetes knowledge in a cohort of Nigerian diabetics | |
| Varma et al. | Prevalence and causes of visual impairment and blindness in Chinese American adults: the Chinese American eye study | |
| Ross et al. | Evaluation of the Counterweight Programme for obesity management in primary care: a starting point for continuous improvement | |
| Rogers et al. | Educational differentials in US adult mortality: An examination of mediating factors | |
| Ouyang et al. | Use of quantile regression to investigate changes in the body mass index distribution of Chinese adults aged 18–60 years: a longitudinal study | |
| CN103020408A (en) | Non-pharmacological intervention method and system for health management over chronic disease | |
| Wu et al. | Real-world impact of ongoing regular exercise in overweight and obese US adults with diabetes on health care utilization and expenses | |
| Johnson et al. | Validity evidence for self-report with assistance to measure physical activity behavior in adults with intellectual disabilities | |
| Konty et al. | Context, importance, and process for creating a body mass index surveillance system to monitor childhood obesity within the New York City public school setting | |
| Touger-Decker et al. | Workplace weight loss program; comparing live and internet methods | |
| JP6161126B2 (en) | Meal guidance support device | |
| Drăgoi | The health work force migration: economic and social effects | |
| Allen et al. | Development of a diabetes mellitus knowledge resource for clinical decision support assisting primary care physicians with work-related issues | |
| Al-Arifi et al. | Assessing health literacy among hypertensive patients attending primary healthcare clinics at King Abdulaziz Medical City, Riyadh, Saudi Arabia | |
| Lee et al. | Associations of eye diseases and symptoms with self-reported physical and mental health | |
| Jung et al. | Age-specific determinants of physical activity engagement in breast cancer survivors: A Multigroup analysis | |
| Takaku | The effect of patient cost sharing on health care utilization among low-income children | |
| Manship et al. | Participant experiences of the DWELL programme: focus group findings on motivation, experiences, facilitators and barriers | |
| Hatzidimitriadou et al. | The Diabetes and WELLbeing programme: protocol of a multi-site European complex intervention study | |
| Morris et al. | Patient empowerment, eating behaviours and illness control: pre-post outcomes from DWELL delivery in UK and France | |
| Heshmati | Abstract# 1161642: Prevalence, Pathophysiology, and Management of Lean Nonalcoholic Fatty Liver Disease | |
| Blocker | Sugar high: Psychosocial factors of patients with type 2 diabetes in an integrated care setting |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171027 |