CN109994205A - Disability-adjusted life expectancy prediction technique, electronic device and storage medium - Google Patents
Disability-adjusted life expectancy prediction technique, electronic device and storage medium Download PDFInfo
- Publication number
- CN109994205A CN109994205A CN201910133312.2A CN201910133312A CN109994205A CN 109994205 A CN109994205 A CN 109994205A CN 201910133312 A CN201910133312 A CN 201910133312A CN 109994205 A CN109994205 A CN 109994205A
- Authority
- CN
- China
- Prior art keywords
- group
- age
- disability
- death
- life expectancy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000036541 health Effects 0.000 claims abstract description 63
- 230000004083 survival effect Effects 0.000 claims abstract description 31
- 150000001875 compounds Chemical class 0.000 claims abstract description 9
- 201000010099 disease Diseases 0.000 claims description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 16
- 230000003862 health status Effects 0.000 claims description 7
- 239000002131 composite material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 8
- 239000013598 vector Substances 0.000 description 13
- 238000013459 approach Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 208000017667 Chronic Disease Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to data processing techniques, there is provided a kind of disability-adjusted life expectancy prediction technique, comprising: collecting sample obtains sample information, the sample information includes sample identification symbol, age and survival or death, and the sample identification symbol includes one or more in name, certificate number and cell-phone number；Sample is grouped according to the sequence of age bracket from small to large；Establish life table, the life table includes the probability of death of each age group, remains number, the Survival person-year of each age group and the total person-time of existence on table, the probability of death acquisition that number and previous age bracket are remained on table of the number according to previous age bracket is remained on the table of one age bracket, the Survival person-year is the compound measuring index of number and time；According to the total person-time of existence of each group of life table divided by the health life expectancy in life expectancy for remaining number acquisition each group on each group table.The present invention also provides a kind of electronic device and storage mediums.The disability-adjusted life expectancy of Accurate Prediction each age group of the present invention.
Description
Technical field
The present invention relates to technical field of data processing, more specifically, are related to a kind of disability-adjusted life expectancy prediction technique, electricity
Sub-device and storage medium.
Background technique
During the measuring and calculating of traditional health life expectancy, fitness assessment is carried out often by the way of questionnaire survey to individual
Come whether subjective judgement individual can't take care of oneself, i.e., whether disables, it is personal whether healthy to judge, but questionnaire survey is normal
Unbalanced in the presence of sampling, sample size is small and subjective judgement causes the result calculated to generate deviation.
Summary of the invention
In view of the above problems, the object of the present invention is to provide a kind of the strong of the disability-adjusted life expectancy of Accurate Prediction each age group
Health life expectancy prediction technique, electronic device and storage medium.
To achieve the goals above, the present invention provides a kind of electronic device, and the electronic device includes memory and processing
Device includes disability-adjusted life expectancy Prediction program in the memory, and the disability-adjusted life expectancy Prediction program is by the processor
Following steps are realized when execution:
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death,
The sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the life that number, each age group are remained on table
It deposits person-time and total person-time that survives, is remained on the table of one age bracket and remain people on table of the number according to previous age bracket
Several and previous age bracket probability of death obtains, and the Survival person-year is the compound measuring index of number and time；
According to the total person-time of existence of each group of life table divided by the Health needs for remaining number acquisition each group on each group table
Service life.
In addition, to achieve the goals above, the present invention also provides a kind of disability-adjusted life expectancy prediction techniques, comprising:
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death,
The sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the life that number, each age group are remained on table
Deposit person-time and the total person-time of surviving, remained on the table of an age bracket remained on table of the number according to previous age bracket number and
The probability of death of previous age bracket obtains according to the following formula (1), and the Survival person-year is the compound measuring index of number and time,
(2) obtain according to the following formula, and the total person-time of existence obtains according to the following formula (3),
lx+1=lx(1-qx) (1)
Lx=(alx+blx+1)/2 (2)
Wherein, lxNumber, q are remained on table for xth groupxFor the probability of death of xth group, a is the age segment length of xth group,
B is the age segment length of (x+1)th group, LxFor the Survival person-year of xth group, TxFor the total person-time of existence of xth group, xth group is indicated
Or more the population of each age group can also survive person-time's summation, x=1 ..., m, m is total group of number of sample, l1For setting value
Or for acquisition the first age bracket at the end of remain number；
The health life expectancy in life expectancy of each group is obtained by following formula (4) according to the total person-time of the existence of each group of life table
ex=Tx/lx (4)
Wherein, exFor the health life expectancy in life expectancy of xth group.
Preferably, described according to the sequence of age bracket from small to large includes: according to Dan Sui to the method that sample is grouped
Group is grouped sample, using every one-year-old crowd as a group.
Further, it is preferable that the life table includes: x ': the age；lx′: number is remained, fingering enters x ' years old number；
dx′: death toll on table refers to and lived by x ' years old, but not yet lives to x '+1 year old and the number die；mx′: the death rate refers to x ' year
Average mortality of the age population in 1 year；Qx ': probability of death refers in full x ' years old people living, dead before reaching x '+1 year old
The ratio gone；Lx′: the average survival time person-time refers to the product of number and time-to-live, is the composite index of number and time；Tx′:
Survive total person-time, refers to that the population of x ' years old or more each age group can also survive person-time's summation；ex′: the average expected life-span refers to
It lives into the population of x ', it is every to survive how many year for each person, wherein dx′=lx′*qx′。
Further still, it is preferred that the probability of death is obtained according to the population of the previous year, or according to from calculating the time
The population of the previous year obtains, or is obtained according to population several years ago,
qx=Dx/PAt the beginning of x
Wherein, DxFor the death toll or the several years ago corresponding age bracket of xth group of the previous year xth group corresponding age bracket
Mean Death number, PAt the beginning of xFor the population of the corresponding age bracket of xth group at the beginning of the previous year or several years ago beginning of the year xth group corresponding year
The average population of age section.
Preferably, the probability of death is obtained according to the equivalent death rate, and the probability of death is obtained according to the equivalent death rate
Method include:
The population of the population at the beginning of the year and year end is averaged, average population P is obtainedx；
Pass through dead population using the average population and obtain the equivalent death rate according to the following formula (5),
mx=Dx/Px(5)；
Probability of death is obtained by following formula (6) according to the equivalent death rate,
Moreover it is preferred that the collecting sample step further include:
The electronic health record case data for acquiring each sample carry out health evaluating using the disease information in electronic health record, obtain
The personal health condition for obtaining each sample carries out a point group to sample according to each sample health status, obtains different crowd.
Further, it is preferable that the crowd includes disability service life crowd, disability service life crowd and slow sick service life crowd.
Further still, it is preferred that carrying out health to the disability service life crowd, disability service life crowd and slow sick service life crowd
Life expectancy prediction method include:
It is divided into the level Four cause of the death according to kinds of Diseases, predicts the disability-adjusted life expectancy of each age group of the causes of the death at different levels；
According to disability ranking score group, the disability-adjusted life expectancy of each age group of each disability grade is predicted；
A point group is carried out according to slow disease class, predicts the disability-adjusted life expectancy of each age group of each slow disease class.
In addition, to achieve the goals above, the present invention also provides a kind of computer readable storage medium, the computer can
It reads in storage medium to include disability-adjusted life expectancy Prediction program, when the disability-adjusted life expectancy Prediction program is executed by processor,
The step of realizing above-mentioned disability-adjusted life expectancy prediction technique.
Disability-adjusted life expectancy prediction technique, electronic device and computer readable storage medium of the present invention are to each age group
It is grouped, constructs life table, and according to remaining number, Survival person-year and life on the probability of death of each age group, table
The health life expectancy in life expectancy that total person-time predicts each group is deposited, objective fact, the disability-adjusted life expectancy of Accurate Prediction each age group are based on.
Detailed description of the invention
Fig. 1 is the application environment schematic diagram of disability-adjusted life expectancy prediction technique preferred embodiment of the present invention；
Fig. 2 is the module diagram of disability-adjusted life expectancy Prediction program preferred embodiment in Fig. 1；
Fig. 3 is the flow chart of disability-adjusted life expectancy prediction technique preferred embodiment of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Hereinafter, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The present invention provides a kind of disability-adjusted life expectancy prediction technique, is applied to a kind of electronic device 1.Shown in referring to Fig.1, it is
The application environment schematic diagram of disability-adjusted life expectancy prediction technique preferred embodiment of the present invention.
In the present embodiment, electronic device 1 can be server, mobile phone, tablet computer, portable computer, desktop meter
Calculation machine etc. has the client terminals of calculation function.
Memory 11 includes the readable storage medium storing program for executing of at least one type.The readable storage medium storing program for executing of at least one type
It can be the non-volatile memory medium of such as flash memory, hard disk, multimedia card, card-type memory.In some embodiments, described can
Reading storage medium can be the internal storage unit of the electronic device 1, such as the hard disk of the electronic device 1.In other realities
It applies in example, the readable storage medium storing program for executing is also possible to the external memory of the electronic device 1, such as on the electronic device 1
The plug-in type hard disk of outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD)
Card, flash card (Flash Card) etc..
In the present embodiment, the readable storage medium storing program for executing of the memory 11 is installed on the electronic device commonly used in storage
1 disability-adjusted life expectancy Prediction program 10 etc..The memory 11, which can be also used for temporarily storing, have been exported or will
The data of output.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, program code or processing data for being stored in run memory 11, example
Such as execute disability-adjusted life expectancy Prediction program 10.
Network interface 13 optionally may include standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the electronic device 1 and other electronic clients.
Communication bus 14 is for realizing the connection communication between these components.
Fig. 1 illustrates only the electronic device 1 with component 11-14, it should be understood that being not required for implementing all show
Component out, the implementation that can be substituted is more or less component.
Optionally, which can also include user interface, and user interface may include input unit such as keyboard
(Keyboard), speech input device such as microphone (microphone) etc. has the client of speech identifying function, voice
Output device such as sound equipment, earphone etc., optionally user interface can also include standard wireline interface and wireless interface.
Optionally, which can also include display, and display is referred to as display screen or display unit.
It can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and organic light emission in some embodiments
Diode (Organic Light-Emitting Diode, OLED) touches device etc..Display is for showing in the electronic apparatus 1
The information of processing and for showing visual user interface.
Optionally, which further includes touch sensor.It is touched provided by the touch sensor for user
The region for touching operation is known as touch area.In addition, touch sensor described here can be resistive touch sensor, capacitor
Formula touch sensor etc..Moreover, the touch sensor not only includes the touch sensor of contact, proximity may also comprise
Touch sensor etc..In addition, the touch sensor can be single sensor, or such as multiple biographies of array arrangement
Sensor.
Optionally, which can also include logic gates, and sensor, voicefrequency circuit etc. are no longer superfluous herein
It states.
In Installation practice shown in Fig. 1, as may include in a kind of memory 11 of computer storage medium behaviour
Make system and disability-adjusted life expectancy Prediction program 10；Processor 12 executes the disability-adjusted life expectancy prediction stored in memory 11
Following steps are realized when program 10:
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death,
The sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the life that number, each age group are remained on table
Deposit person-time and the total person-time of surviving, remained on the table of an age bracket remained on table of the number according to previous age bracket number and
The probability of death of previous age bracket obtains according to the following formula (1), and the Survival person-year is the compound measuring index of number and time,
(2) obtain according to the following formula, and the total person-time of existence obtains according to the following formula (3),
lx+1=lx(1-qx) (1)
Lx=(alx+blx+1)/2 (2)
Wherein, lxNumber, q are remained on table for xth groupxFor the probability of death of xth group, a is the age segment length of xth group,
B is the age segment length of (x+1)th group, LxFor the Survival person-year of xth group, TxFor the total person-time of existence of xth group, xth group is indicated
Or more the population of each age group can also survive person-time's summation, x=1 ..., m, m is total group of number of sample, l1For setting value
Or for acquisition the first age bracket at the end of remain number；
The health life expectancy in life expectancy of each group is obtained by following formula (4) according to the total person-time of the existence of each group of life table
ex=Tx/lx (4)
Wherein, exFor the health life expectancy in life expectancy of xth group.
In other embodiments, the disability-adjusted life expectancy Prediction program 10 can also be divided into one or more mould
Block, one or more module are stored in memory 11, and are executed by processor 12, to complete the present invention.Institute of the present invention
The module of title is the series of computation machine program instruction section for referring to complete specific function.It is health in Fig. 1 referring to shown in Fig. 2
The functional block diagram of 10 preferred embodiment of life expectancy Prediction program.The disability-adjusted life expectancy Prediction program 10 is according to backstage
Application program carries out the dynamic configuration of official documents and correspondence in front end, can be divided into:
Acquisition module 110, collecting sample, obtain sample information, the sample information include sample identification symbol, the age and
Survival is dead；
Grouping module 120 is grouped sample according to the sequence of age bracket from small to large；
Life table constructs module 130, establishes life table, the life table include the probability of death of each age group, on table still
Deposit number, the Survival person-year of each age group and the total person-time of existence；
Prediction module 140 obtains respectively according to the total person-time of the existence of each group of life table divided by number is remained on each group table
The health life expectancy in life expectancy of group.
Preferably, the grouping module 120 is grouped sample according to single year old group, using every one-year-old crowd as a group
Body.
Preferably, the acquisition module 110 acquires the electronic health record case data of each sample as sample, the prediction mould
Block 140 carries out health evaluating using the disease information in electronic health record, obtains the personal health condition of each sample, and the health is pre-
Phase life prediction program 10 further include: grouping module (not shown) carries out a point group to sample according to each sample health status, obtains
Crowd described in each sample；Module 130 is constructed by grouping module 120, life table and prediction module 140 predicts the health of each crowd
Life expectancy.
In addition, the present invention also provides a kind of disability-adjusted life expectancy prediction techniques.It is pre- for present invention health referring to shown in Fig. 3
The flow chart of phase life-span prediction method preferred embodiment.This method can be executed by device, the device can by software and/
Or hardware realization.
In the present embodiment, disability-adjusted life expectancy prediction technique carries out official documents and correspondence in front end according to the application program on backstage
Dynamic configuration, comprising:
Step S1, collecting sample obtain sample information, and the sample information includes sample identification symbol, age and survival
Or it is dead, the sample identification symbol includes a kind of or more in name, certificate number (identity card, medical insurance number, passport etc.) and cell-phone number
Kind, for example, can from the database or/and website of hospital or/and insurance company or/and government department collecting sample；
Step S2 is grouped sample according to the sequence of age bracket from small to large；
Step S3, establishes life table, and the life table includes the probability of death of each age group, remains number, each year on table
The Survival person-year of age section and total person-time that survives, remain number according to the table of previous age bracket on the table of one age bracket
On remain the probability of death of number and previous age bracket and obtain according to the following formula (1), the Survival person-year is number and time
Compound measuring index, (2) obtain according to the following formula, and the total person-time of existence obtains according to the following formula (3),
lx+1=lx(1-dx) (1)
Lx=(alx+blx+1)/2 (2)
Wherein, lxNumber, q are remained on table for xth groupxFor the probability of death of xth group, a is the age segment length of xth group,
B is the age segment length of (x+1)th group, LxFor the Survival person-year of xth group, TxFor the total person-time of existence of xth group, xth group is indicated
Or more the population of each age group can also survive person-time's summation, x=1 ..., m, m is total group of number of sample, l1For setting value
Or for acquisition the first age bracket at the end of remain number, for example, dividing crowd, i.e. 0-4 years old group, 5-9 years old according to 5 years old group
Group ..., 95-99 years old group etc., 0-4 year old group be the 1st group, l1It can be setting value, first group for being also possible to acquire was more than 4 years old
The number remained；
Step S4 obtains the Health needs longevity of each group according to the total person-time of the existence of each group of life table by following formula (4)
Life
ex=Tx/lx (4)
Wherein, exFor the health life expectancy in life expectancy of xth group.
In one alternate embodiment, in step s 2, in order to calculate 0 years old disability-adjusted life expectancy, according to single year old group to sample
Originally be grouped, using every one-year-old crowd as a group, i.e., by sample be divided into 0 years old group, 1 years old group, 2 years old group ..., 100 years old
Group etc., increases sample size.
Preferably, in step s3, life table includes: x ': the age；lx′: number is remained, fingering enters x ' years old number；
dx′: death toll on table refers to and lived by x ' years old, but not yet lives to x '+1 year old and the number die；mx′: the death rate refers to x ' year
Average mortality of the age population in 1 year；qx′: probability of death refers in full x ' years old people living, dead before reaching x '+1 year old
The ratio gone；Lx′: the average survival time person-time refers to the product of number and time-to-live, is the composite index of number and time；Tx′:
Survive total person-time, refers to that the population of x ' years old or more each age group can also survive person-time's summation；ex′: the average expected life-span refers to
It lives into the population of x ', it is every to survive how many year for each person, wherein dx′=lx′*qx′, when according to single year old group to sample carry out
When grouping, x and x '+1 are corresponding, that is to say, that it is the 1st group that 0 years old corresponding, and it is the 2nd group that 1 years old corresponding.
Probability of death of the present invention can be obtained according to the population of the previous year, can also be according to before from calculating the time
1 year population obtains, and can also be obtained according to the population of preceding setting year (such as first 5 years), for example, directly using XX
The death toll at each age divided by XX at the beginning of correspond to the population at age, corresponding probability of death of each age, q can be obtainedx=
Dx/PAt the beginning of xWherein, DxFor the death toll of the corresponding age bracket of XX xth group, PAt the beginning of xThe corresponding age bracket of xth group at the beginning of for XX
Population.
Preferably, probability of death is obtained according to the equivalent death rate, specifically: will be averaged at the beginning of XX with the population at year end
Value, can be obtained the average population P of XXx；Dead population obtains the equivalent death rate i.e. divided by average population: mx=Dx/
Px；It is calculated according to the relationship that the calculation formula of the death rate obtains the death rate and probability of death:
In a preferred embodiment of the invention, in step sl, the electronic health record case data for acquiring each sample, make
Health evaluating is carried out with the disease information in electronic health record, obtains the personal health condition of each sample, according to each sample health shape
Condition carries out a point group to sample, obtains the affiliated crowd of each sample, is predicted using the health forecast life approach of the various embodiments described above each
The disability-adjusted life expectancy of crowd.
Preferably, the crowd includes disability service life crowd, disability service life crowd and slow sick service life crowd, is directed to loses respectively
Energy service life crowd, disability service life crowd and slow sick service life crowd carry out disability-adjusted life expectancy prediction, for example, for being the energy service life,
It is divided into the level Four cause of the death according to kinds of Diseases, the health of each age group of the causes of the death at different levels is predicted using above-mentioned health forecast life approach
Life expectancy for another example predicts each age of each disability grade according to disability ranking score group using above-mentioned health forecast life approach
The disability-adjusted life expectancy of section carries out a point group according to slow disease class for another example, predicts each slow disease using above-mentioned health forecast life approach
The disability-adjusted life expectancy of each age group of type.
In above preferred embodiment, using crowd's electronic health record case data, avoid in the sampling process of questionnaire survey
The deviation of generation.The health evaluating method of electronic health record case data is based on objective fact, avoids the subjectivity in questionnaire survey
Result error caused by judging.Calculated based on the true medical record data of case, saves the manpower and material resources of questionnaire survey generation.
The various embodiments described above are equally practically applicable to after carrying out point group according to gender, area, level of consumption etc., divide each group after group
Disability-adjusted life expectancy.
In one particular embodiment of the present invention, predict that a certain area is a certain using health forecast life approach of the present invention
The disability-adjusted life expectancy of crowd under calendar year, comprising:
Step 1, single year old group population of the year end calendar year and the single year old group death rate are counted；
Step 2, group life expectancy budget in single year old is carried out using life table, the life table is the year according to specific crowd
The age group death rate compiles a kind of statistical form come, and the basic data of life table establishment is the average population of each age (section)
With practical dead population；
Step 3, this area's population electronic health record case data are acquired, carry out health using the disease information in electronic health record
It assesses, judges whether individual is healthy for disability, disability, slow sick 3 kinds of paths respectively, such as the following table 1 is enumerated for the disability service life
4 grades of causes of the death, can classify according to the level Four cause of the death
Table 1
The following table 2 gives the example of chronic disease, can classify according to the major class of chronic disease
Table 2
According to personal insurance disability judgment criteria, the mapping relations between disease and disability are found out, mapping relations are passed through
Find out disability crowd；
Step 4, it in conjunction with personal health condition, using life table, calculates separately for disability service life, disability service life and slow disease
The population health life expectancy in service life, when calculating disability-adjusted life expectancy using life table, wherein the death rate etc. in life table
Imitate in the ratio to lose one's health, i.e. health status converts, both include death toll, also include be converted by health it is unhealthy
Number accounts for the ratio of total number of persons, for example, in healthy judgment criteria, using people whether suffer from chronic disease as whether health according to
According to death rate mxEqual to dead population divided by average population, it may be assumed that
mx=Dx/Px
When calculating life expectancy, i.e., calculated using the death rate.And when calculating health life expectancy in life expectancy, in addition to considering
The death of population is also taken into account health status to get equivalent to one by the unhealthy number for being converted into health status
The death rate, for calculating disability-adjusted life expectancy, the equivalent death rate is equal to the sum of death toll and number of the infected divided by average population
Number；l0It points out raw number, is usually initialized as 100000 people, according to the death toll of each age bracket, recurrence calculation backward:
First according to 0 years old probability of death q0, calculate death toll d on 0 years old table0: d0=l0*q0, secondly according to dead on 0 years old table
Number d0Number l is remained with remaining within 0 years old number and calculating 1 years old1: l1=l0-d0, last recurrence calculation obtains on the table at each age
Death toll and remain number: dx′=lx′*qx′, lx′+1=lx′-dx′；Survival person-year Lx′It is the compound metering of number and time
Index is the product of number and time-to-live, each 1 year=2 man-year of work of 2 years=2 people for example, 1 people lives, the existence people of age x '
Year calculates according to the following formula: Lx′=(lx′+lx′+1)/2；Survive total person-time Tx′, refer to the population of x ' years old or more each age group also
Can survive person-time's summation, calculate according to the following formula:
Wherein m ' is max age；The health life expectancy in life expectancy e of age x 'x′Person-time T total equal to the existence of age x 'x′Divided by age x '
Remain number lx′, it may be assumed that ex′=Tx′/lx′。
In an alternate embodiment of the present invention where, term vector is converted by the sentence in case history, according between term vector
Similitude case history is clustered, to obtain each multi-class classification, the population health for obtaining each age group of each classification is expected
Service life, specifically:
Electronic health record text nature sentence is segmented, the term vector of case text is obtained；
Term vector is encoded using encoder, such as one-hot coding；
According to the similarity (for example, cosine similarity) of the coding of each term vector, the similarity between each term vector is obtained,
Can be according to the mean value of the similarity between term vectors multiple between case history as the similarity between case history, it can also be using maximum
Or the similarity between minimum term vector is as the similarity between case history, it is also an option that keyword (such as belong in case history
In chronic disease table, disabled grade is highest, and the highest word of service life grade that disables is as keyword) corresponding term vector it is similar
Degree is as the similarity between case；
Case history is clustered using clustering algorithm according to the similarity between case history.
Preferably, the encoder uses LSTM model,
it=σ (Wxixt+Whiht-1+Wcict-1+bi)
it=(1-it)⊙ct-1+it⊙tanh(Wxcxt+Whcht-1+bc)
ot=σ (Wxoxt+Whoht-1+Wcoct+bo)
it=ot⊙tanh(ct)
Wherein, σ is the sigmoid function by element, and ⊙ is by element multiplication, and tanh is hyperbolic tangent function, it, ct,
ot, htThe input gate parameter of t moment is respectively represented, state parameter (exports recall info), out gate parameter, hidden layer output valve,
xtIt is the word vector that t moment is input to model, WxiIndicate the input gate selection weight of the word vector, WhiIndicate input gate and
Selection weight between hidden layer, WciIndicate the selection weight of input gate output recall info, WxcIndicate the defeated of the word vector
The selection weight of recall info out, WhcIndicate the selection weight of the output recall info of hidden layer, WxoIndicate the word vector
Out gate selects weight, WhoIndicate the selection weight between hidden layer and out gate, WcoIndicate the output memory of the out gate
The selection weight of information, bi、bcAnd b0The bias term for respectively indicating input gate, exporting recall info and out gate.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
In include disability-adjusted life expectancy Prediction program, following step is realized when the disability-adjusted life expectancy Prediction program is executed by processor
It is rapid:
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death,
The sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the life that number, each age group are remained on table
It deposits person-time and total person-time that survives, is remained on the table of one age bracket and remain people on table of the number according to previous age bracket
Several and previous age bracket probability of death obtains, and the Survival person-year is the compound measuring index of number and time；
According to the total person-time of existence of each group of life table divided by the Health needs for remaining number acquisition each group on each group table
Service life.
The specific embodiment of the computer readable storage medium of the present invention and above-mentioned disability-adjusted life expectancy prediction technique, electricity
The specific embodiment of sub-device is roughly the same, and details are not described herein.
Disability-adjusted life expectancy prediction technique, electronic device and computer readable storage medium of the present invention are based on case
Population health life expectancy counts the health status of crowd by the health evaluating of case, and the health for providing each age group is expected
In the service life, for example, dividing crowd using single year old group, what is obtained is that healthy can survive in expection future of the current year per one-year-old crowd
Year.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.Pass through above embodiment party
The description of formula, it is required general that those skilled in the art can be understood that above-described embodiment method can add by software
The mode of hardware platform is realized, naturally it is also possible to which by hardware, but in many cases, the former is more preferably embodiment.It is based on
Such understanding, substantially the part that contributes to existing technology can be with software product in other words for technical solution of the present invention
Form embody, which is stored in a storage medium (such as ROM/RAM, magnetic disk, light as described above
Disk) in, including some instructions are used so that a client terminals (can be mobile phone, computer, server or network visitor
Family end etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of disability-adjusted life expectancy prediction technique characterized by comprising
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death, described
Sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the existence people that number, each age group are remained on table
Year and the total person-time of surviving remain on the table of one age bracket and remain number and previous on table of the number according to previous age bracket
The probability of death of age bracket obtains according to the following formula (1), and the Survival person-year is the compound measuring index of number and time, according to
Following formula (2) obtains, and the total person-time of existence obtains according to the following formula (3),
lx+1=lx(1-qx)(1)
Lx=(alx+blx+1)/2(2)
Wherein, lxNumber, q are remained on table for xth groupxFor the probability of death of xth group, a is the age segment length of xth group, and b is
The age segment length of (x+1)th group, LxFor the Survival person-year of xth group, TxFor the total person-time of existence of xth group, indicate xth group and
The population of above each age group can also survive person-time's summation, x=1 ..., m, and m is total group of number of sample, l1For setting value or
For acquisition the first age bracket at the end of remain number；
The health life expectancy in life expectancy of each group is obtained by following formula (4) according to the total person-time of the existence of each group of life table
ex=Tx/lx(4)
Wherein, exFor the health life expectancy in life expectancy of xth group.
2. disability-adjusted life expectancy prediction technique according to claim 1, which is characterized in that it is described according to age bracket from it is small to
Big sequence includes: to be grouped according to single year old group to sample to the method that sample is grouped, using every one-year-old crowd as one
A group.
3. disability-adjusted life expectancy prediction technique according to claim 2, which is characterized in that the life table includes: x ': year
Age；lx′: number is remained, fingering enters x ' years old number；dx′: death toll on table refers to and lived by x ' years old, but it is not yet living to x '+
1 year old and the number die；mx′: the death rate refers to average mortality of the x ' age population in 1 year；qx′: probability of death refers to
Work is expired in x ' years old people, the ratio die before reaching x '+1 year old；Lx′: the average survival time person-time refers to number and time-to-live
Product, be the composite index of number and time；Tx′: survive total person-time, refers to that the population of x ' years old or more each age group can also
Survival person-time's summation；ex′: the average expected life-span refers to and lives into the population of x ', every to survive how many year for each person, wherein
dx′=lx′*qx′。
4. disability-adjusted life expectancy prediction technique according to claim 3, which is characterized in that the probability of death is according to previous
The population in year obtains, or is obtained according to the population of the previous year from calculating the time, or according to the population of preceding setting year
It obtains,
qx=Dx/PAt the beginning of x
Wherein, DxFor the previous year xth group corresponding age bracket death toll or several years ago the corresponding age bracket of xth group is averaged
Death toll, PAt the beginning of xFor the population of the corresponding age bracket of xth group at the beginning of the previous year or several years ago corresponding age bracket of beginning of the year xth group
Average population.
5. disability-adjusted life expectancy prediction technique according to claim 3, which is characterized in that the probability of death is according to equivalent
The death rate obtains, and the probability of death includes: according to the method that the equivalent death rate obtains
The population of the population at the beginning of the year and year end is averaged, average population P is obtainedx；
Pass through dead population using the average population and obtain the equivalent death rate according to the following formula (5),
mx=Dx/Px(5)；
Probability of death is obtained by following formula (6) according to the equivalent death rate,
6. disability-adjusted life expectancy prediction technique described in any claim in -5 according to claim 1, which is characterized in that described
Collecting sample step further include:
The electronic health record case data for acquiring each sample carry out health evaluating using the disease information in electronic health record, obtain each
The personal health condition of sample carries out a point group to sample according to each sample health status, obtains the affiliated crowd of each sample.
7. disability-adjusted life expectancy prediction technique according to claim 6, which is characterized in that the crowd includes: the disability longevity
Life crowd, disability service life crowd and slow sick service life crowd.
8. disability-adjusted life expectancy prediction technique according to claim 7, which is characterized in that the disability service life crowd,
Disability service life crowd and the method that sick service life crowd carries out disability-adjusted life expectancy prediction slowly include:
It is divided into the level Four cause of the death according to kinds of Diseases, predicts the disability-adjusted life expectancy of each age group of the causes of the death at different levels；
According to disability ranking score group, the disability-adjusted life expectancy of each age group of each disability grade is predicted；
A point group is carried out according to slow disease class, predicts the disability-adjusted life expectancy of each age group of each slow disease class.
9. a kind of electronic device, which is characterized in that store the unsoundness expected longevity including memory and processor, in the memory
Prediction program is ordered, the disability-adjusted life expectancy Prediction program realizes following steps when being executed by the processor:
Collecting sample, obtains sample information, and the sample information includes sample identification symbol, age and survival or death, described
Sample identification symbol includes one or more in name, certificate number and cell-phone number；
Sample is grouped according to the sequence of age bracket from small to large；
Establish life table, the life table includes the probability of death of each age group, the existence people that number, each age group are remained on table
Year and the total person-time of surviving remain on the table of one age bracket and remain number and previous on table of the number according to previous age bracket
The probability of death of age bracket obtains according to the following formula (1), and the Survival person-year is the compound measuring index of number and time, according to
Following formula (2) obtains, and the total person-time of existence obtains according to the following formula (3),
lx+1=lx(1-qx)(1)
Lx=(alx+blx+1)/2(2)
Wherein, lxNumber, q are remained on table for xth groupxFor the probability of death of xth group, a is the age segment length of xth group, and b is
The age segment length of (x+1)th group, LxFor the Survival person-year of xth group, TxFor the total person-time of existence of xth group, indicate xth group and
The population of above each age group can also survive person-time's summation, x=1 ..., m, and m is total group of number of sample, l1For setting value or
For acquisition the first age bracket at the end of remain number；
The health life expectancy in life expectancy of each group is obtained by following formula (4) according to the total person-time of the existence of each group of life table
ex=Tx/lx(4)
Wherein, exFor the health life expectancy in life expectancy of xth group.
10. a kind of computer readable storage medium, which is characterized in that include that unsoundness is pre- in the computer readable storage medium
Phase life prediction program when the disability-adjusted life expectancy Prediction program is executed by processor, is realized as appointed in claim 1 to 8
The step of disability-adjusted life expectancy prediction technique described in one claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910133312.2A CN109994205A (en) | 2019-02-22 | 2019-02-22 | Disability-adjusted life expectancy prediction technique, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910133312.2A CN109994205A (en) | 2019-02-22 | 2019-02-22 | Disability-adjusted life expectancy prediction technique, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109994205A true CN109994205A (en) | 2019-07-09 |
Family
ID=67130312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910133312.2A Pending CN109994205A (en) | 2019-02-22 | 2019-02-22 | Disability-adjusted life expectancy prediction technique, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109994205A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113555120A (en) * | 2021-07-26 | 2021-10-26 | 医渡云（北京）技术有限公司 | Biological state analysis method and device, storage medium, and electronic device |
| CN114638524A (en) * | 2022-03-28 | 2022-06-17 | 哈尔滨商业大学 | Intelligent endowment integrated service center information statistical method |
| CN114974403A (en) * | 2022-04-13 | 2022-08-30 | 北京邮电大学 | Method for predicting survival probability and related equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016077727A1 (en) * | 2014-11-14 | 2016-05-19 | Sudano Joseph John | Method and apparatus for performing health risk assessment |
| CN109346173A (en) * | 2018-10-23 | 2019-02-15 | 上海市疾病预防控制中心 | The system and method for realization health life expectancy in life expectancy operational analysis function based on hygiene medical treatment big data |
-
2019
- 2019-02-22 CN CN201910133312.2A patent/CN109994205A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016077727A1 (en) * | 2014-11-14 | 2016-05-19 | Sudano Joseph John | Method and apparatus for performing health risk assessment |
| CN109346173A (en) * | 2018-10-23 | 2019-02-15 | 上海市疾病预防控制中心 | The system and method for realization health life expectancy in life expectancy operational analysis function based on hygiene medical treatment big data |
Non-Patent Citations (3)
| Title |
|---|
| 李强等: "多状态生命表法在老年人健康预期寿命研究中的应用", 《中国人口科学》 * |
| 王呼生 等: "《医学计算机信息应用》", 31 July 2018, 中国铁道出版社 * |
| 米歇尔·刘易斯-伯克 等: "《社会科学研究方法百科全书 第2卷》", 31 August 2017, 重庆大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113555120A (en) * | 2021-07-26 | 2021-10-26 | 医渡云（北京）技术有限公司 | Biological state analysis method and device, storage medium, and electronic device |
| CN113555120B (en) * | 2021-07-26 | 2022-10-11 | 医渡云（北京）技术有限公司 | Biological state analysis method and device, storage medium, and electronic device |
| CN114638524A (en) * | 2022-03-28 | 2022-06-17 | 哈尔滨商业大学 | Intelligent endowment integrated service center information statistical method |
| CN114974403A (en) * | 2022-04-13 | 2022-08-30 | 北京邮电大学 | Method for predicting survival probability and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ansarullah et al. | Significance of Visible Non‐Invasive Risk Attributes for the Initial Prediction of Heart Disease Using Different Machine Learning Techniques | |
| Azmi et al. | A systematic review on machine learning approaches for cardiovascular disease prediction using medical big data | |
| Ozcift | SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease | |
| Song et al. | A comparative study of dimensionality reduction techniques to enhance trace clustering performances | |
| Mandal et al. | New machine-learning algorithms for prediction of Parkinson's disease | |
| Ma et al. | Combining multiple markers for classification using ROC | |
| WO2020248847A1 (en) | Smart heart disease detection method and device, and computer readable storage medium | |
| CN109994205A (en) | Disability-adjusted life expectancy prediction technique, electronic device and storage medium | |
| Bartolucci et al. | A latent Markov model for detecting patterns of criminal activity | |
| Xie et al. | Analyzing health insurance claims on different timescales to predict days in hospital | |
| US11317870B1 (en) | System and method for health assessment on smartphones | |
| CA3110455A1 (en) | Visualization of social determinants of health | |
| Ben-Assuli et al. | Analysing repeated hospital readmissions using data mining techniques | |
| Gallardo et al. | A simplified estimation procedure based on the EM algorithm for the power series cure rate model | |
| CN113284627A (en) | Medication recommendation method based on patient characterization learning | |
| Ahmad | Mining health data for breast cancer diagnosis using machine learning | |
| Hakizimana et al. | A hybrid based classification and regression model for predicting diseases outbreak in datasets | |
| van der Steen et al. | Calibrating parameters for microsimulation disease models: a review and comparison of different goodness-of-fit criteria | |
| Nguyen et al. | Estimating county health indices using graph neural networks | |
| Tran et al. | Mortality prediction of patients with cardiovascular disease using medical claims data under artificial intelligence architectures: validation study | |
| Uddin et al. | Machine Learning-Based Chronic Kidney Cancer Prediction Application: A Predictive Analytics Approach | |
| CN113990506A (en) | Health state evaluation method and device, storage medium and computer system | |
| Bjarndóttir et al. | The history and modern applications of insurance claims data in healthcare research | |
| Uddin et al. | Intelligent type 2 diabetes risk prediction from administrative claim data | |
| Gu et al. | Modeling the length-of-stay of patients with geriatric diseases or alcohol use disorder using phase-type distributions with covariates |
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: 20190709 |