CN113270190A - Doctor decision-making method based on UPHFPR consistency iterative algorithm - Google Patents
Doctor decision-making method based on UPHFPR consistency iterative algorithm Download PDFInfo
- Publication number
- CN113270190A CN113270190A CN202110668237.7A CN202110668237A CN113270190A CN 113270190 A CN113270190 A CN 113270190A CN 202110668237 A CN202110668237 A CN 202110668237A CN 113270190 A CN113270190 A CN 113270190A
- Authority
- CN
- China
- Prior art keywords
- matrix
- doctor
- uphfpr
- phfpr
- aggregated
- 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
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a doctor decision-making method based on a UPHFPR consistency iterative algorithm. The method comprises the following steps: constructing a UPHFPR matrix of each doctor according to the symptom set of the patient, establishing an objective function for acquiring element probability and weight in the UPHFPR matrix of the doctor, and calculating the occurrence probability and priority of the elements in the UPHFPR matrix of each doctor; after judging that the UPHFPR matrix of each doctor meets the condition of acceptable expected consistency, obtaining the PHFPR matrix of each doctor according to the occurrence probability of elements in the UPHFPR matrix of each doctor; aggregating PHFPR matrixes of K doctors by using a WUPHPPAR aggregation operator to obtain an aggregated PHFPR matrix, and calculating the ordering weight of the aggregated PHFPR matrix; and when the aggregated PHFPR matrix is judged to meet the condition of acceptable expected consistency, selecting the diagnosis result with the maximum weight value as the final diagnosis result of the patient according to the sorting weight of the aggregated PHFPR matrix. The invention uses UPHFPR decision method to fuse the diagnosis opinions of the doctor, and helps the doctor select accurate diagnosis result.
Description
Technical Field
The invention relates to the technical field of doctor clinical decision, in particular to a doctor decision method based on UPHFPR (Uncertain probability hesitation fuzzy preference relationship) consistency iterative algorithm.
Background
In the field of clinical decision making, disease diagnosis has become one of the more complex decision making problems. Doctors may not be able to make a diagnosis in the disease diagnosis process due to uncertain information, subjective reasons of the doctors, and the like, and the final diagnosis result needs to be given by combining opinions of different doctors.
In the modern disease diagnosis process, since medical data presents characteristics of large scale and rapid growth, doctors often need to extract valuable information from a plurality of complex information when expressing diagnosis opinions. In addition, disease diagnosis requires analysis of many symptoms, and it often takes a long time for a doctor to give a final diagnosis result. If analysis of some symptoms is ignored in the process, misdiagnosis may result.
In the prior art, a method for solving misdiagnosis in the diagnosis process of a doctor comprises the following steps of; because fuzzy sets can better characterize uncertainty in decision making, fuzzy mathematics are combined with disease diagnosis, and decision information of doctors is characterized by using a Hesitation Fuzzy Set (HFS) or a Probabilistic Hesitation Fuzzy Set (PHFS).
The method for solving the misdiagnosis in the diagnosis process of the doctor in the prior art has the following defects: in practical applications of HFS or PHFS, it may be difficult for a physician to accurately and sufficiently provide the occurrence probability of an element, and at this time, neither the hesitation ambiguity nor the probability hesitation ambiguity can effectively characterize the information provided by the physician.
Disclosure of Invention
The invention provides a doctor decision method based on a UPHFPR consistency iterative algorithm, which is used for helping a doctor to select an accurate diagnosis result.
In order to achieve the purpose, the invention adopts the following technical scheme.
A doctor decision method based on a UPHFPR consistency iterative algorithm comprises the following steps:
constructing an uncertain probability hesitation fuzzy preference relation UPHFPR matrix of each doctor according to the symptom set of the patient, and establishing an objective function for acquiring element probability and weight in the UPHFPR matrix of the doctor;
calculating the occurrence probability and the priority of elements in the UPHFPR matrix of each doctor according to the objective function of the calculation model;
after judging that the UPHFPR matrix of each doctor meets the condition of acceptable expected consistency according to the occurrence probability and the priority weight of the elements in the UPHFPR matrix of each doctor, obtaining the PHFPR matrix of the hesitation fuzzy preference relation of the determination probability of each doctor according to the occurrence probability of the elements in the UPHFPR matrix of each doctor;
aggregating PHFPR matrixes of K doctors by using a WUPHPPR aggregation operator according to the priority weight of the PHFPR matrixes of each doctor to obtain an aggregated PHFPR matrix, and calculating the sequencing weight of the aggregated PHFPR matrix;
and when the aggregated PHFPR matrix meets the condition of acceptable expected consistency according to the sorting weight of the aggregated PHFPR matrix, selecting the diagnosis result with the maximum weight value as the final diagnosis result of the patient according to the sorting weight of the aggregated PHFPR matrix.
Preferably, the building of the UPHFPR matrix of each doctor according to the patient symptom set and the building of the objective function for obtaining the element probability and the weight in the UPHFPR matrix of the doctor include:
constructing UPHFPR matrices for K doctors from the patient symptom set, taking the doctor-to-patient diagnostic scheme as the row and column elements of the UPHFPR matrix U for the doctor, namely:
is an element in the UPHFPR matrix of the doctor, k denotes the number of doctors, lkTo representThe number of middle elements, i and j, represents the number of doctor's diagnosis plans;
establishing a calculation model of the UPHFPR matrix probability of the doctor by using a method for obtaining the UPHFPR probability of the doctor by improving the expected consistency, wherein the model is a multi-target planning problem, and an objective function of the model is as follows:
wherein the positive deviation variableNegative deviation variable Representation of UPHFEExpected value of (a), xij,lRepresents gammaij,lProbability of occurrence of partially or completely unknown information, wiAnd wjIs the priority weight of U.
Preferably, the calculating the occurrence probability and the priority of the elements in the UPHFPR matrix of each doctor according to the objective function of the calculation model includes:
obtaining the objective function of the UPHFPR matrix of each doctor according to the UPHFPR matrix of each doctor by using a formula 1, calculating the multi-objective optimization problem of the objective function of the UPHFPR matrix of each doctor by using an MATLAB tool, and solving the occurrence probability of elements in the UPHFPR matrix of each doctorAnd priority weight
Preferably, after judging that the UPHFPR matrix of each doctor satisfies the condition of acceptable expected consistency according to the occurrence probability and the priority weight of the elements in the UPHFPR matrix of each doctor, the method includes:
calculating U using equation (3)kCI value of (1):
if CI is less than or equal to zeta (i, j is 1,2, …, n) and ξ is a set threshold value, judging that the UPHFPR matrix of the doctor meets the condition of acceptable expected consistency;
if CI is present>ξ, judging that the UPHFPR matrix of the doctor does not meet the condition of acceptable expected consistency, calculating the corrected UPHFPR matrix of each doctor by using an improved consistency iterative algorithm, and calculating the corrected UPHFPR matrix U of each doctor by using a formula (1) againkProbability of occurrence of middle elementAnd a priority weight until the revised UPHFPR matrix for each doctor meets the acceptable expected consistency condition.
Preferably, said calculating the modified UPHFPR matrix for each doctor using an improved consistency iterative algorithm comprises:
UPHFPR matrix U according to doctorkPositive deviation variable ofNegative deviation variable of sumUsing formulasCalculating the maximum deviation dmax;
According to the maximum deviation dmaxTwo cases are discussed:
if it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
If it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
Preferably, the obtaining of the PHFPR matrix of the fuzzy preference relationship of the determination probability of each doctor according to the occurrence probability of the element in the UPHFPR matrix of each doctor includes:
UPHFPR matrix U of each doctor obtained by the calculation of the formula (1)kIs filled in the UPHFPR matrix U of each doctorkWherein i, j ═ 1,2, …, n; k is 1,2, …, K;the complete UPHFPR matrix of K physicians, i.e., the PHFPR matrix of K physicians, is obtained.
Preferably, the aggregating the PHFPR matrices of K doctors by using the WUPHFPRA aggregation operator according to the priority weight of the PHFPR matrices of each doctor to obtain an aggregated PHFPR matrix, and calculating the ranking weight of the aggregated PHFPR matrix, includes:
according to the priority of PHFPR matrix of each doctorAggregating PHFPR matrixes of K doctors by using a WUPHPPAR aggregation operator to obtain an aggregated PHFPR matrix
Suppose thatIs UPHFPR for K doctors, with the weight vector Q ═ Q1,q2,…,qK) And satisfyThen the WUPHPPRA aggregation operatorIs defined as:
wiThe ranking weight of the aggregated UPHFPR matrix U is the ranking weight of the K doctors to the diagnosis scheme.
Preferably, after the aggregated PHFPR matrix is judged to satisfy the condition of acceptable expected consistency according to the ranking weight of the aggregated PHFPR matrix, selecting the diagnosis result with the largest weight value according to the ranking weight of the aggregated PHFPR matrix as the final diagnosis result of the patient, including:
If CI ≦ ξ (i, j ═ 1,2, …, n), the aggregated PHFPR matrix is confirmedSatisfying the condition of acceptable expected consistency, and obtaining the aggregated PHFPR matrix Is weighted by the rank wiSelecting the diagnosis result with the maximum weight value as the final diagnosis result of the patient;
if CI is present>ξ (i, j ═ 1,2, …, n), the aggregated PHFPR matrix is confirmedNot meeting the condition of acceptable expected consistency, calculating a modified PHFPR matrix U by using an improved consistency iterative algorithm, and calculating the modified PHFPR matrix U of each doctor by using the formula (1) againkUntil the modified PHFPR matrix for each doctor meets the condition of acceptable desired consistency.
According to the technical scheme provided by the embodiment of the invention, the UPHFPR decision method is used for fusing the diagnosis opinions of the doctor, so that the doctor is helped to select an accurate diagnosis result.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a processing flow chart of a doctor decision method based on a UPHFPR consistency iterative algorithm according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
Aiming at the problems, the UPHFPR is introduced, the problem of consistency of additive expectation of the UPHFPR is researched, the probability of occurrence of a diagnosis result is calculated by constructing an optimized model, and finally a decision model based on a consistency iterative algorithm is established, and the probability of elements in the decision model and a sequencing weight vector of the diagnosis result are calculated, so that an accurate diagnosis result is obtained.
The doctor decision method based on the UPHFPR consistency iterative algorithm effectively expresses information provided by a doctor by using an uncertain probability hesitation fuzzy set, calculates uncertain probability and priority weight, analyzes expected consistency or acceptable expected consistency of a UPHFPR matrix of the doctor, aggregates the UPHFPR matrix of the doctor after the expected consistency is met, and finally calculates the priority weight of the aggregated matrix, thereby helping the doctor to select an accurate diagnosis scheme.
The processing flow of the doctor decision method based on the UPHFPR consistency iterative algorithm provided by the embodiment of the invention is shown in FIG. 1, and comprises the following processing steps;
step S1: and establishing an objective function for acquiring element probability and weight in the UPHFPR matrix of the doctor.
The doctor-to-patient diagnostic scheme is taken as the row and column elements of the UPHFPR matrix U for the doctor.
Such asMeaning that doctor U considers the diagnosis protocol 180% better than diagnosis protocol 2, and the occurrence probability of this event is 50%; the diagnosis scheme is 190% better than the diagnosis scheme 2, and the occurrence probability of the event is uncertain; the diagnostic protocol is 130% better than diagnostic protocol 2, and the probability of this event occurrence is uncertain.
For the UPHFPR matrix of the doctor, the key problem is the calculation of the probability of occurrence of elements and the improvement of the consistency level of the matrix. To address this problem, embodiments of the present invention use a method of increasing the probability of obtaining the doctor UPHFPR of the desired consistency. The embodiment of the invention establishes a calculation model of element probability and weight in a UPHFPR matrix of a doctor, wherein the model is a multi-target planning problem, and the target function is as follows:
Representation of UPHFEExpected value of (a), xij,lRepresents gammaij,lProbability of occurrence of partially or completely unknown information, wiAnd wjIs the priority weight of U.
Is an element in the UPHFPR matrix of the doctor, k denotes the number of doctors, lkTo representThe number of elements in (a) and (j) represents the number of doctor's diagnosis plans.
UPHFPR matrix U of the doctor in this stepkBecause the uncertain probability is hesitant to obscure the preference relation matrix, the uncertain probability is incomplete, and the occurrence probability of some elements in the matrix is uncertain。
Step S3: calculate UPHFPR matrix U for the Kth doctor using equation (1)kProbability of occurrence ofAnd element UkPriority ofAnd a positive deviation variableNegative deviation variable of sum
Obtaining an objective function of a specific doctor by using a formula 1 according to UPHFPR matrixes of different doctors, calculating a multi-objective optimization problem by using an MATLAB tool, and solving the occurrence probabilityAnd priority weight
calculating U using equation (3)kThe CI (consistency index) value of (c),
if CI ≦ ξ (i, j ═ 1,2, …, n), proceed to the next step S5; otherwise, the modified doctor UPHFPR matrix is calculated using the improved consistency iterative algorithm, and the process returns to step S3.
Before the aggregation of the UPHFPR matrix of doctors, each UPHFPR matrix of doctors has a CI (consistency index) value; all physicians' UPHFPR matrices will also correspond to a CI value when aggregated.
Calculating the UPHFPR matrix of the modified doctor by using the improved consistency iterative algorithm comprises the following steps:
UPHFPR matrix U according to doctorkPositive deviation variable ofNegative deviation variable of sumUsing formulasCalculating the maximum deviation dmax。
The maximum deviation d is obtainedmaxTwo cases are discussed:
if it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
If it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
Based on the modified elementsObtaining a corrected UPHFEThe upper triangular element of the uncertain probability fuzzy preference relation has additive expectation consistency, and the lower triangular element also has additive expectation consistency, so the method is based onxqp,l=xpq,lObtaining UPHFEFurther, the UPHFPR of the doctor after the correction is constructedThe iteration continues back to step S3.
The acceptable expected consistency of the uphpr of the doctor can be set according to different application scenes and requirements, for example, if CI is 0, the uphpr of the doctor meets the expected consistency; if CI is less than or equal to 0.01, the confidence level of the doctor's UPHFPR expected consistency is 99%; if CI is less than or equal to 0.02, the confidence level of the doctor's UPHFPR expected consistency is 98%; if CI ≦ 0.05, the confidence level of the doctor's UPHFPR expected consistency is 95%. Generally, if CI ≦ 0.05, the desired consistency of UPHFPR for the doctor is acceptable.
Step S5: from step S3, we calculate UkProbability of occurrence ofWherein i, j is 1,2, …, n; k is 1,2, …, K;the complete UPHFPR matrix of K physicians, i.e., the PHFPR matrix of K physicians, can be obtained.
K doctors UPHFPR matrix constructed by the inventionIn the method, the occurrence probability of some elements is uncertain, and the occurrence probability of the elements is obtained through the calculation of formula (1), and thenThe substitution into a specific value will obtain a complete UPHFPR matrix, which is also called PHFPRUPHFPPR (probabilistic fuzzy preference relationship, deterministic probability hesitation) matrix of the doctor.
Then, according to a given weight matrix W, using a WUPHPPAR aggregation operator to aggregate PHFPR matrixes of K doctors to obtain an aggregated PHFPR matrix
The WUPHFPRA aggregation operator in the practice of the present invention uses the following definitions: suppose thatPHFPR for K doctors, with weight vector Q ═ Q1,q2,…,qK) And satisfyThen WUPHFRA polymerizesThe cost-effective definition is:
step S6: calculating the aggregated PHFPR matrix again using equation (1)Is weighted by the rank wi。
wiThe method is the ranking weight of the aggregated PHFPR matrix U, is used for selecting a more accurate diagnosis scheme, and combines the ranking weights of K doctors on the diagnosis scheme.
Step S7: analysis ofAnd calculates the CI value of the aggregated PHFPR matrix U using equation (4).
If CI ≦ ξ (i, j ═ 1,2, …, n), then it is confirmed that the appropriate ordering weight w is obtainedi(i ═ 1,2, …, n), the next step S8 is performed;
if CI is present>ξ (i, j ═ 1,2, …, n), the aggregated PHFPR matrix is confirmedNot meeting the condition of acceptable expected consistency, calculating a modified PHFPR matrix U by using an improved consistency iterative algorithm,and re-use formula (1) to calculate the modified PHFPR matrix U for each doctorkUntil the modified PHFPR matrix of each doctor meets the condition of acceptable expected consistency.
Step S8: and selecting an accurate doctor diagnosis result according to a rule that the weighted value is larger and the working target is better. According to the PHFPR matrix after aggregation Is weighted by the rank wiChoose the weight w with the maximumiAnd (i-1, 2, …, n) as the final diagnosis result of the patient.
In conclusion, the uncertain probability hesitation fuzzy set and uncertain probability hesitation fuzzy preference relation are introduced, the additive expectation consistency problem of UPHFPR is researched, the probability of the occurrence of the diagnosis result is calculated by constructing an optimization model, finally, a decision model based on a consistency iterative algorithm is established, the probability of elements in the decision model and the sequencing weight vector of the diagnosis result are calculated, and therefore the accurate diagnosis result is obtained.
In order to enable a decision maker (doctor) to express decision information more accurately, the invention introduces the uncertain information in the decision process of the hesitation fuzzy set of uncertain probability. The invention applies the consistency of additive expectation to UPHFPR, so that the diagnosis result obtained by a doctor is more reasonable and reliable.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A doctor decision method based on a UPHFPR consistency iterative algorithm is characterized by comprising the following steps:
constructing an uncertain probability hesitation fuzzy preference relation UPHFPR matrix of each doctor according to the symptom set of the patient, and establishing an objective function for acquiring element probability and weight in the UPHFPR matrix of the doctor;
calculating the occurrence probability and the priority of elements in the UPHFPR matrix of each doctor according to the objective function of the calculation model;
after judging that the UPHFPR matrix of each doctor meets the condition of acceptable expected consistency according to the occurrence probability and the priority weight of the elements in the UPHFPR matrix of each doctor, obtaining the PHFPR matrix of the hesitation fuzzy preference relation of the determination probability of each doctor according to the occurrence probability of the elements in the UPHFPR matrix of each doctor;
aggregating PHFPR matrixes of K doctors by using a WUPHPPR aggregation operator according to the priority weight of the PHFPR matrixes of each doctor to obtain an aggregated PHFPR matrix, and calculating the sequencing weight of the aggregated PHFPR matrix;
and when the aggregated PHFPR matrix meets the condition of acceptable expected consistency according to the sorting weight of the aggregated PHFPR matrix, selecting the diagnosis result with the maximum weight value as the final diagnosis result of the patient according to the sorting weight of the aggregated PHFPR matrix.
2. The method according to claim 1, wherein said constructing a UPHFPR matrix for each physician according to the patient symptom set, and establishing an objective function for obtaining element probabilities and weights in the UPHFPR matrix of the physician comprises:
constructing UPHFPR matrices for K doctors from the patient symptom set, taking the doctor-to-patient diagnostic scheme as the row and column elements of the UPHFPR matrix U for the doctor, namely:
is an element in the UPHFPR matrix of the doctor, k denotes the number of doctors, lkTo representThe number of middle elements, i and j, represents the number of doctor's diagnosis plans;
establishing a calculation model of the UPHFPR matrix probability of the doctor by using a method for obtaining the UPHFPR probability of the doctor by improving the expected consistency, wherein the model is a multi-target planning problem, and an objective function of the model is as follows:
3. The method according to claim 1, wherein said calculating the occurrence probability and priority of the elements in the UPHFPR matrix of each doctor according to the objective function of the calculation model comprises:
obtaining the objective function of the UPHFPR matrix of each doctor according to the UPHFPR matrix of each doctor by using a formula 1, calculating the multi-objective optimization problem of the objective function of the UPHFPR matrix of each doctor by using an MATLAB tool, and solving the occurrence probability of elements in the UPHFPR matrix of each doctorAnd priority weight
4. The method according to claim 1, wherein said determining that the UPHFPR matrix of each doctor satisfies the condition of acceptable expected consistency according to the occurrence probability and priority weight of the elements in the UPHFPR matrix of each doctor comprises:
calculating U using equation (3)kCI value of (1):
if CI is less than or equal to zeta (i, j is 1,2, …, n) and ξ is a set threshold value, judging that the UPHFPR matrix of the doctor meets the condition of acceptable expected consistency;
if CI is present>ξ, judging that the UPHFPR matrix of the doctor does not meet the condition of acceptable expected consistency, calculating the corrected UPHFPR matrix of each doctor by using an improved consistency iterative algorithm, and calculating the corrected UPHFPR matrix U of each doctor by using a formula (1) againkProbability of occurrence of middle elementAnd a priority weight until the revised UPHFPR matrix for each doctor meets the acceptable expected consistency condition.
5. The method according to claim 4, wherein said calculating the modified UPHFPR matrix for each doctor using an improved consistency iterative algorithm comprises:
UPHFPR matrix U according to doctorkPositive deviation variable ofNegative deviation variable of sumUsing formulasCalculating the maximum deviation dmax;
According to the maximum deviation dmaxTwo cases are discussed:
if it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
If it is notWherein p is 1,2, …, n-1; q is 2,3, …, n; q > p, according toCalculating the corrected elementsWherein
6. The method according to claim 4 or 5, wherein the obtaining of the PHFPR matrix of the individual doctor's deterministic probability hesitation fuzzy preference relationship based on the occurrence probability of the elements in the UPHFPR matrix of the individual doctor comprises:
7. The method as claimed in claim 6, wherein the aggregating PHFPR matrixes of K doctors by using a WUPHPPR aggregation operator according to the priority of PHFPR matrixes of each doctor to obtain an aggregated PHFPR matrix, and calculating the ranking weight of the aggregated PHFPR matrix, comprises:
according to eachPriority weighting of physician's PHFPR matrixAggregating PHFPR matrixes of K doctors by using a WUPHPPAR aggregation operator to obtain an aggregated PHFPR matrix
Suppose thatIs UPHFPR for K doctors, with the weight vector Q ═ Q1,q2,…,qK) And satisfyThe definition of the WUPHFPRA aggregation operator is:
wiThe ranking weight of the aggregated UPHFPR matrix U is the ranking weight of the K doctors to the diagnosis scheme.
8. The method of claim 7, wherein selecting the diagnosis result with the largest weight value as the final diagnosis result of the patient according to the sorting weight of the aggregated PHFPR matrix after the aggregated PHFPR matrix is judged to satisfy the condition of acceptable expected consistency according to the sorting weight of the aggregated PHFPR matrix comprises:
If CI ≦ ξ (i, j ═ 1,2, …, n), the aggregated PHFPR matrix is confirmedSatisfying the condition of acceptable expected consistency, and obtaining the aggregated PHFPR matrix Is weighted by the rank wiSelecting the diagnosis result with the maximum weight value as the final diagnosis result of the patient;
if CI is present>ζ (i, j ═ 1,2, …, n), the aggregated PHFPR matrix is confirmedNot meeting the condition of acceptable expected consistency, calculating a modified PHFPR matrix U by using an improved consistency iterative algorithm, and reusing the commonEquation (1) calculates the modified PHFPR matrix U for each doctorkUntil the modified PHFPR matrix for each doctor meets the condition of acceptable desired consistency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110668237.7A CN113270190A (en) | 2021-06-16 | 2021-06-16 | Doctor decision-making method based on UPHFPR consistency iterative algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110668237.7A CN113270190A (en) | 2021-06-16 | 2021-06-16 | Doctor decision-making method based on UPHFPR consistency iterative algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113270190A true CN113270190A (en) | 2021-08-17 |
Family
ID=77235172
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110668237.7A Pending CN113270190A (en) | 2021-06-16 | 2021-06-16 | Doctor decision-making method based on UPHFPR consistency iterative algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113270190A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122195A (en) * | 2017-05-08 | 2017-09-01 | 云南大学 | The software non-functional requirement evaluation method of subjective and objective fusion |
CN109086470A (en) * | 2018-04-08 | 2018-12-25 | 北京建筑大学 | A kind of method for diagnosing faults based on fuzzy preference relation and D-S evidence theory |
-
2021
- 2021-06-16 CN CN202110668237.7A patent/CN113270190A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122195A (en) * | 2017-05-08 | 2017-09-01 | 云南大学 | The software non-functional requirement evaluation method of subjective and objective fusion |
CN109086470A (en) * | 2018-04-08 | 2018-12-25 | 北京建筑大学 | A kind of method for diagnosing faults based on fuzzy preference relation and D-S evidence theory |
Non-Patent Citations (1)
Title |
---|
WEI ZHOU 等: "Group consistency and group decision making under uncertain probabilistic hesitant fuzzy preference environment", 《INFORMATION SCIENCES》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110147450B (en) | Knowledge complementing method and device for knowledge graph | |
Delignette-Muller et al. | fitdistrplus: An R package for fitting distributions | |
CN107070704A (en) | A kind of Trusted Web services combined optimization method based on QoS | |
CN113379042B (en) | Business prediction model training method and device for protecting data privacy | |
CN110111885B (en) | Attribute prediction method, attribute prediction device, computer equipment and computer readable storage medium | |
CN114611384A (en) | Medical knowledge graph node importance evaluation method based on graph neural network | |
CN117370565A (en) | Information retrieval method and system | |
CN116598012A (en) | Chronic disease medical care method and system based on federal learning value evaluation | |
CN111832817A (en) | Small world echo state network time sequence prediction method based on MCP penalty function | |
CN107026755B (en) | A kind of service recommendation method based on sequence study | |
CN111292322A (en) | Medical image processing method, device, equipment and storage medium | |
CN106874668B (en) | Medication analysis method based on full memory event sequence mining model | |
CN113270190A (en) | Doctor decision-making method based on UPHFPR consistency iterative algorithm | |
CN113035348A (en) | Diabetes diagnosis method based on GRU feature fusion | |
Amini et al. | A fuzzy MADM method for uncertain attributes using ranking distribution | |
US8700541B2 (en) | Modeling method of neuro-fuzzy system | |
CN116630347A (en) | Blood vessel segmentation method and device for retina fundus image | |
CN115392582A (en) | Crop yield prediction method based on incremental fuzzy rough set attribute reduction | |
US20230334360A1 (en) | Model-independent feature selection | |
CN115295115A (en) | Sodium valproate blood concentration prediction method and device based on deep learning | |
JP7207128B2 (en) | Forecasting Systems, Forecasting Methods, and Forecasting Programs | |
CN112735596A (en) | Similar patient determination method and device, electronic equipment and storage medium | |
CN116936048B (en) | Federal learning hospital selection method, device and storage medium for heterogeneous medical information | |
CN113094497B (en) | Electronic health record recommendation method and shared edge computing platform | |
CN117557870B (en) | Classification model training method and system based on federal learning client selection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210817 |
|
RJ01 | Rejection of invention patent application after publication |