CN110322946B - Optimal medication granularity calculation device based on multi-granularity decision model - Google Patents
Optimal medication granularity calculation device based on multi-granularity decision model Download PDFInfo
- Publication number
- CN110322946B CN110322946B CN201910625179.2A CN201910625179A CN110322946B CN 110322946 B CN110322946 B CN 110322946B CN 201910625179 A CN201910625179 A CN 201910625179A CN 110322946 B CN110322946 B CN 110322946B
- Authority
- CN
- China
- Prior art keywords
- granularity
- medication
- layer
- decision model
- patient
- 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.)
- Active
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
The invention discloses a method for calculating optimal medication granularity based on a multi-granularity decision model, which comprises the following specific steps of: a: constructing a multi-granularity-level medicament granularity decision model by taking different granularity levels for medicament dosage; b: if the cancer patient is stage I or stage II patient, entering step C; if the patients are stage III and stage IV patients, entering step F; c: if the number of the patient data is less than or equal to 5000, entering the step D; e, entering the step E for more than 5000 pieces; d: calculating the global optimal drug granularity by using a coordination method; e: calculating the global optimal medication granularity by using a tree structure method; f: if the number of the patient data is less than or equal to 1000, entering the step G; step H is carried out when the number of the strips is more than 1000; g: calculating local optimal drug granularity by using a serial method; h: and calculating the local optimal medication granularity by using a parallel method. The invention can provide an automatic auxiliary tool for doctors to select anticancer drugs.
Description
Technical Field
The invention relates to a method for selecting and optimizing medication granularity, in particular to a method for calculating optimal medication granularity based on a multi-granularity decision model.
Background
At present, along with the aggravation of environmental pollution and the aggravation of competitive pressure, the incidence rate of some diseases tends to increase, and the situation is more and more valued by people. Recent statistics show that: 1810 of ten thousand new cancer cases, Asia accounts for about 50% of the total number of cancers worldwide; of 960 ten thousand cancer deaths, asia accounts for approximately 60% of the total cancer deaths worldwide. There are 400 million new cases of cancer each year in China, and many people are afflicted with cancer.
Under the background of new Chinese medical improvement, intelligent medical treatment is going to live in the lives of common people. The intelligent medical treatment is a medical service mode taking patient data as a center, and records all behaviors and diagnosis and treatment data of a patient in a hospital. The key task of current research is to reasonably utilize collected medical data and provide an effective solution for diagnosing the disease condition.
Currently, there are many kinds of cancer drugs, for example, 1187 common drugs for lung cancer, 754 common drugs for stomach cancer, 503 common drugs for colon cancer, and the like. Indirectly shows that the current medical level is limited, no specific medicine is available for cancer, only a plurality of medicines can be tried, improper medication can not improve the disease condition, a large amount of money is spent, precious time of a patient is wasted, the disease condition is delayed, and the optimal treatment opportunity is missed. The multi-granularity decision model is proposed for the selection of the medication granularity of the cancer drugs, and if the previous patient medication data can provide effective medication basis for the current patient, the significance for the recovery of the patient's condition is extraordinary.
Disclosure of Invention
The invention aims to provide a method for calculating the optimal medication granularity based on a multi-granularity decision model, which can convert the problem of selecting the medication granularity of a cancer patient into the problem of selecting the optimal granularity by the multi-granularity decision model, optimize the method for calculating the optimal medication granularity, provide an effective medication basis for the current patient according to the previous medication data of the patient, and provide an automatic auxiliary tool for a doctor to select an anti-cancer drug.
The invention adopts the following technical scheme:
a method for calculating optimal medication granularity based on a multi-granularity decision model comprises the following specific steps:
a: on the basis of the single-granularity-level medication granularity decision model, a multi-granularity-level medication granularity decision model is constructed in a medication system of a cancer patient by taking different granularity levels for the medication dosage of the medicament; then entering the step B;
b: judging the severity of the cancer patient, selecting the globally optimal drug granularity if the cancer patient is a stage I patient and a stage II patient, and entering the step C; if the cancer patient is a stage III patient or a stage IV patient, selecting local optimal drug granularity, and entering a step F;
c: judging according to the number of the patient data, and entering the step D if the number of the patient data is less than or equal to 5000; if the number of newly added patient data is larger than 5000, entering the step E; wherein the patient data comprises an object O, a condition attribute P and a decision attribute d;
d: calculating the global optimal drug granularity by using a coordination method;
e: calculating the global optimal medication granularity by using a tree structure method;
f: judging according to the number of the patient data, and entering the step G if the number of the patient data is less than or equal to 1000; if the number of pieces of patient data is more than 1000, entering step H;
g: calculating local optimal drug granularity by using a serial method;
h: and calculating the local optimal medication granularity by using a parallel method.
In the step A:
the single-granularity-level medication granularity decision model is a binary set S ═ (O, PU { d }); wherein O is a group of cancer patients, and O ═ x is used 1 ，x 2 ，…，x n Denotes wherein x 1 Is patient 1, x 2 Patient 2, and so on, x n Is patient n; p is a condition attribute and comprises the basic condition and the dosage of the patient, and P is { a ═ a 1 ，a 2 ，…，a n The decision attribute d represents the treatment effect of the medicine and is represented by Y or N, Y represents the treatment effectiveness, and N represents the treatment ineffectiveness;
in the single-granularity-level medication granularity decision model S ═ (O, Pu { d }), a multi-granularity-level medication granularity decision model S is obtained by taking different observed values for the drug dosage in the condition attribute set P k ＝(O，P k U { d }), where k represents the number of layers, including all the granularity layers that can be constructed(ii) a The granularity layer number constructed by the multi-granularity-layer medicine granularity decision model is I, the multi-granularity-layer medicine granularity decision model is constructed layer by layer from fine granularity to coarse granularity, and an object O is { x ═ x 1 ，x 2 ，…，x n H, attribute set of each layer is recorded as
1≤k≤I，
Respectively representing the 1 st condition attribute, the 2 nd condition attribute, … and the mth condition attribute in the k-th layer medication granularity decision model.
In the multi-granularity-level medication granularity decision model constructed in the step a, the condition attribute P includes the basic condition and the dosage of the patient, and P ═ a 1 ，a 2 ，…，a 10 The disease severity, sex, age, drug A, drug B, drug C, drug D, drug E, drug F and drug G in sequence; the number k of layers of the multi-granularity-layer medicine-use granularity decision model is 3, and when the medicine amount of a patient is expressed by tablets or granules, a first-layer medicine-use granularity decision model S is obtained 1 ＝(O，P 1 U { d }); when the medicine dosage of the patient is represented by a box or a bottle, a second layer medicine dosage decision model S is obtained 2 ＝(O，P 2 U { d }); when the drug dosage of the patient is expressed by the course of treatment, a third layer of drug dosage granularity decision model S is obtained 3 ＝(O，P 3 ∪{d})。
The step D comprises the following specific steps:
d1: medication granularity decision model S at multiple granularity levels k ＝(O，P k Each layer of U { d }) divides each object according to condition attribute, and sets object x 1 Each condition attribute of
And object x 2 Each condition attribute of (2)
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class by analogy, recording the division result and obtaining a set of the division result of each layer, and marking as R O ；
D2: medication granularity decision model S at multiple granularity levels k ＝(O，P k Each layer of U { d }) divides each object according to decision attributes, and sets object x 1 、x 2 And x 3 Is effective, and subject x 4 And x 5 If the drug treatment is not effective, dividing the disease according to decision attributes and dividing x 1 、x 2 And x 3 Is divided into one class, x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result to obtain the set of all objects divided on each layer, and recording as R r ；
D3: comparing the division results R O And a division result R r If, if
Judging that the decision model of the layer is harmonious; if it is not
Judging that the decision model of the layer is uncoordinated; the upper layer of the first uncoordinated granularity layer is the global optimal medication granularity; r O Representing a set of objects divided by attributes, R r Representing the set of subjects divided by the effect of the medication.
The step E comprises the following specific steps:
solving global optimum granularity by using a tree structure, converting the multi-granularity-level medication granularity decision model obtained in the step A into a tree storage, and using a multi-granularity-level medication granularity decision model S k ＝(O，P k In U { d }), each layer of decision model of the multi-granularity-level drug-using granularity decision model is a forest formed by a plurality of trees, each layer of the tree represents each condition attribute, an object O and a decision attribute d are stored below a leaf node, and whether the decision model in the layer is coordinated or not is judged according to the consistency of the decision attributes d below the same leaf nodeThe upper layer of the inconsistent granularity layers appearing for the first time is the global optimal medication granularity.
The step G comprises the following specific steps:
g1: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each level of U { d }), each object is divided according to conditional attributes, and an object x is assumed to be 1 Each attribute of (2)
And object x 2 Each attribute of (2)
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class, repeating the above steps, recording the division results and obtaining the set of the division results of each object, and recording the set as
Namely, the result of dividing the object x on the k-th layer medication granularity decision model according to the condition attribute P;
g2: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each layer of U { x }), each object is divided according to decision attributes, and an object x is assumed to be 1 And x 2 Is effective, and subject x 3 ，x 4 And x 5 If the drug treatment is not effective, the decision attribute is divided, and x is divided 1 And x 2 Is divided into one class, x 3 ，x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result and obtaining the set of each object, and marking as [ x ]] d I.e. the result of the partitioning of the object x by the decision attribute d;
g3: comparing the set [ x ] of each object x in the step 2] d Whether the set of the objects x in the step 1 is included
If it is
Judging that the decision model of the layer where the object x is located is coordinated; if it is
Judging that the decision model of the layer where the object x is located is uncoordinated; the top layer of the first-occurring uncoordinated granularity layer is the locally optimal medication granularity of the object x, i.e. the
And is provided with
When, the k-th layer granularity is the locally optimal medication granularity for subject x; and thus a set of locally optimal medication granularities for all subjects.
In the step H, the plurality of pieces of patient data are averagely divided into N groups according to the number N of cores of the processor of the computer used, and then the N cores of the processor of the computer used respectively calculate a corresponding group of patient data according to the method described in the step G, thereby finally obtaining a set of local optimal medication granularity of all the objects.
The invention solves the problem of drug selection of cancer patients by utilizing a multi-granularity decision model; aiming at different conditions, two methods for calculating the global optimal drug granularity are provided, and the global optimal drug granularity is selected in a multi-granularity decision model established for stage I and stage II patients by analyzing the disease severity of cancer patients; selecting local optimal drug granularity in a multi-granularity decision model established for patients in stages III and IV; meanwhile, under the condition that the number of newly added patient data is more than 5000, the method for solving the global optimal medication granularity by selecting the tree structure improves the time efficiency; the process of selecting the local optimal drug granularity is performed in parallel, so that the problem of overlong time is solved, and nearly half of the time is saved.
For the selection of anti-cancer drugs, doctors generally have a certain misdiagnosis rate based on the existing experience, which not only causes the waste of time and money of patients, but also delays the illness state. Based on a multi-granularity decision model, two methods for selecting the globally optimal granularity are provided, a specific algorithm is provided, and the process of selecting the locally optimal granularity is performed in parallel. The results show that: under the condition that the data volume of a newly added patient is larger than 5000, the method for selecting the global optimal granularity by the tree structure has great advantage over a coordinated method in time performance, the time for selecting the local optimal granularity in parallel is about half of the time for selecting the anti-cancer drugs in series, and an automatic auxiliary tool is provided for a doctor to select the anti-cancer drugs.
Drawings
FIG. 1 is a schematic diagram of a first-level medication granularity decision model generated by the present invention;
FIG. 2 is a schematic diagram of a second layer medication granularity decision model generated by the present invention;
FIG. 3 is a schematic diagram of a third layer medication granularity decision model generated by the present invention;
fig. 4 is a schematic diagram illustrating patient data decision making according to the present invention;
FIG. 5 is a schematic diagram illustrating a tree structure constructed in accordance with the present invention;
FIG. 6 is a schematic diagram of the time comparison of the optimal granularity of the computing system using the tree structure method and the coordination method, respectively;
FIG. 7 is a schematic diagram of the temporal comparison of the locally optimal granularity calculated using the serial method and the parallel method, respectively;
FIG. 8 is a graph of local optimal granularity versus time alignment calculated using a serial method and a parallel method;
FIG. 9 is a schematic flow chart of the present invention.
Detailed Description
The invention is described in detail below with reference to the following figures and examples:
as shown in fig. 1 to fig. 9, the method for calculating the optimal medication granularity based on the multi-granularity decision model according to the present invention includes the following steps:
a: on the basis of the single-granularity-level medication granularity decision model, a multi-granularity-level medication granularity decision model is constructed in a medication system of a cancer patient by taking different granularity levels for the medication dosage of the medicament; then entering the step B;
since there are more than one thousand anticancer drug preparations on the market, the selection of the drugs by doctors can only be based on the existing knowledge and experience, and the automatic auxiliary tool is lacked. The medicine granularity selection problem of the cancer patient can be abstracted to be the problem of selecting the optimal granularity by a multi-granularity decision model, and the medicine granularity decision models with different granularity levels can be obtained by taking different observed values of the medicine dosage of the cancer patient.
The single granularity level medication granularity decision model constructed in the invention is a binary set S ═ (O, P { d }); wherein O is a target, and is a set of cancer patients, and O ═ x can be used 1 ，x 2 ，…，x n Denotes wherein x 1 Is patient 1, x 2 Patient 2, and so on; p ═ a 1 ，a 2 ，…，a n And d represents different condition attributes, wherein the decision attribute d represents the treatment effect of the medicine and is represented by Y or N, Y represents the treatment effectiveness, and N represents the treatment ineffectiveness.
In the single-granularity-level medication granularity decision model S ═ (O, Pu { d }), a multi-granularity-level medication granularity decision model S is obtained by taking different observed values for the drug dosage in the condition attribute set P k ＝(P，P k U { d }), wherein k represents the number of layers and contains all the granularity layers which can be constructed; the number of granularity layers constructed by the multi-granularity-layer medicine granularity decision model is I, the multi-granularity-layer medicine granularity decision model is constructed layer by layer from fine granularity to coarse granularity, and an object O is { x ═ x 1 ，x 2 ，…，x n }, the attribute set of each layer is noted as
1≤k≤I，
Respectively representing the 1 st condition attribute, the 2 nd condition attribute, … and the mth condition attribute in the k-th layer medication granularity decision model.
In this embodiment, in the multi-granularity-level medication granularity decision model constructed in step a, the condition isThe attribute P comprises the basic condition and the dosage of the patient, and P is { a } 1 ，a 2 ，…，a 10 The severity of the disease, sex, age, drug A, drug B, drug C, drug D, drug E, drug F and drug G in sequence; the number k of layers of the multi-granularity-layer medicine granularity decision model is 3; when the dosage of the patient is expressed by the minimum unit, namely a tablet or a granule, a first-layer medicine granularity decision model S can be obtained 1 ＝(O，P 1 U { d }), as shown in fig. 1. When the dosage of the medicine of the patient is represented by a box or a bottle, a second layer of medicine granularity decision model S can be obtained 2 ＝(O，P 2 U { d }), as shown in fig. 2. When the drug dosage of a patient is expressed by a treatment course, a third-layer drug dosage granularity decision model S can be obtained 3 ＝(O，P 3 U { d }), as shown in fig. 3.
Setting the number of granularity layers constructed by a multi-granularity-layer medicine granularity decision model as I, constructing layer by layer from fine granularity to coarse granularity, and setting an object O as { x ═ x 1 ，x 2 ，…，x n }, the attribute set of each layer is noted as
1≤k≤I，
Respectively representing the 1 st condition attribute, the 2 nd condition attribute, … and the mth condition attribute in the k-th medicament granularity decision model, namely obtaining the medicament granularity decision model S with multiple granularity levels k ＝(O，P k ∪{d})。
B: judging the severity of the cancer patient, selecting the globally optimal drug granularity if the cancer patient is a stage I patient and a stage II patient, and entering the step C; if the cancer patient is a stage III patient or a stage IV patient, selecting local optimal drug granularity, and entering the step F;
c: judging according to the number of the patient data, and entering the step D if the number of the patient data is less than or equal to 5000; if the number of newly added patient data is larger than 5000, entering the step E; wherein the patient data comprises an object O, a condition attribute P and a decision attribute d;
d: calculating the global optimal drug granularity by using a coordination method;
d1: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each level of U { d }), each object is divided according to conditional attributes, and an object x is assumed to be 1 Each condition attribute of
And object x 2 Each condition attribute of
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class by analogy, recording the division result and obtaining a set of the division result of each layer, and marking as R O 。
D2: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each layer of U { d }), each object is divided according to decision attributes, and an object x is assumed to be 1 、x 2 And x 3 Is effective, and subject x 4 And x 5 If the drug treatment is not effective, the decision attribute is divided, and x is divided 1 、x 2 And x 3 Is divided into one class, x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result to obtain the set of all objects divided on each layer, and recording as R r 。
D3: comparing the division results R O And a division result R r If, if
Judging that the decision model of the layer is harmonious; if it is not
Judging that the decision model of the layer is uncoordinated; the upper layer of the first uncoordinated granularity layer is the global optimal medication granularity; r O Representing a set of objects divided by attributes, R r Representing division of objects by effect of medicationThe resulting set.
In summary, in steps D1 to D3, the decision model S of medication granularity is at multiple granularity levels k ＝(O，P k U { d }), if
The decision model of the layer of the multi-granularity-level medication granularity decision model is coordinated, otherwise, the decision model of the layer of the multi-granularity-level medication granularity decision model is uncoordinated, and the global optimal medication granularity is determined according to the uncoordinated decision model.
E: and calculating the global optimal medication granularity by using a tree structure method.
Solving global optimum granularity by using a tree structure, converting the multi-granularity-level medication granularity decision model obtained in the step A into tree storage, wherein the conversion process is as shown in figures 4 to 5, and the multi-granularity-level medication granularity decision model S shown in figure 4 k ＝(O，P k U { d }), there are 5 objects in O, each being x 1 、x 2 、x 3 、x 4 And x 5 (ii) a The conditional attribute is a 1 ，a 2 And a 3 The decision attribute is denoted by d.
Observing the tree structure of fig. 5 yields: each layer of the constructed multi-granularity-level medication granularity decision model is a forest consisting of a plurality of trees, and the tree form selection method and the coordination method are different in that the division result and the coordination can be obtained at the same time, so that a large amount of time is saved. Each layer of the tree represents each condition attribute, which is a condition attribute a from top to bottom in sequence 1 ，a 2 And a 3 Stored below the leaf node is object O and decision attribute d. And judging whether the decision model at the layer is coordinated or not according to the consistency of the decision attribute d below the same leaf node, wherein the upper layer of the layer with uncoordinated granularity for the first time is the global optimal medication granularity.
In view of the fact that patient data belongs to the type of continuous growth, the invention mainly discusses that the condition attribute is unchanged, and the global optimal granularity is selected under the condition that the object grows in batches. On the basis of the existing patient data, data are added in batches, a method for calculating the globally optimal medication granularity by coordination in the step D and a method for calculating the globally optimal medication granularity by a tree structure method in the step E are respectively used, and the result in time performance is shown in fig. 6.
The results show that: when the calculation results of the two algorithms are consistent, the time used by the two methods for solving the global optimal granularity is increased along with the increase of the objects. When the number of the objects is increased to 5000, the time difference of the two methods is only about 1 second, but when the number of the objects is increased to be larger than 5000 and is larger, the advantage of the tree structure method is displayed in the aspect of time performance. This saves a lot of valuable time for selecting the granularity of medication for cancer patients.
F: judging according to the number of the patient data, and entering the step G if the number of the patient data is less than or equal to 1000; if the number of pieces of patient data is more than 1000, entering step H;
g: calculating local optimal drug granularity by using a serial method:
g1: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each level of U { d }), each object is divided according to conditional attributes, and an object x is assumed to be 1 Each attribute of (2)
And object x 2 Each attribute of (2)
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class, repeating the above steps, recording the division results and obtaining the set of the division results of each object, and recording the set as
Namely, the result of the division of the object x on the k-th layer medication granularity decision model according to the condition attribute P.
G2: medication granularity decision model S at multiple granularity levels k ＝(O，P k Each layer of U { d }), each layerThe individual objects are divided according to decision attributes, assuming object x 1 And x 2 Is effective, and subject x 3 ，x 4 And x 5 If the drug treatment is not effective, the decision attribute is divided, and x is divided 1 And x 2 Is divided into one class, x 3 ，x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result and obtaining the set of each object, and marking as [ x ]] d I.e. the result of the partitioning of the object x by the decision attribute d.
G3: comparing the set [ x ] of each object x in the step 2] d Whether the set of the objects x in the step 1 is included
If it is
Judging that the decision model of the layer where the object x is located is coordinated; if it is
Judging that the decision model of the layer where the object x is located is uncoordinated; the layer above the first inconsistent granularity layer is the local optimal granularity of the object x, i.e. the first inconsistent granularity layer
And is
When, the k-th layer granularity is the locally optimal medication granularity for subject x; and thus a set of locally optimal medication granularities for all subjects.
In summary, in steps G1 to G3, the locally optimal medication granularity, i.e., the medication granularity decision model S at multiple granularity levels, is selected according to the coordination of each object k ＝(O，P k In U { d }), given k, 1. ltoreq. k.ltoreq.I for x ∈ O, if
And is
That is, the decision model of the kth layer where the object x is located is coordinated and the decision model of the (k + 1) th layer is uncoordinated, it is determined that the kth layer granularity is the local optimal medication granularity related to the object x, and thus a set of the local optimal medication granularities of all the objects is obtained.
H: calculating local optimal drug granularity by using a parallel method;
and D, averagely dividing the plurality of pieces of patient data into N groups according to the number N of the cores of the processor of the used computer, then respectively calculating a corresponding group of patient data by the N cores of the processor of the used computer according to the method in the step G, and finally obtaining a local optimal medication granularity set of all the objects. For example, if the number of cores of the processor of the computer used is 4, the plurality of pieces of patient data are averagely divided into 4 groups, and then the 4 cores of the processor of the computer used respectively calculate a corresponding group of patient data according to the method described in step G, that is, each core of the processor of the computer respectively calculates a corresponding group of patient data.
The number of the objects is sequentially increased, and the local optimal granularity of the newly-increased objects is respectively solved by using the step G and the step H, and the result shows that the time consumed by the step G and the step H for solving the local optimal granularity is increased along with the increase of the number of the objects. However, in general, the time taken to calculate the local optimum granularity in step H is saved by about half the time compared with the calculation in step G, and the larger the number of objects added, the more time is saved, as shown in fig. 7.
As shown in fig. 8: when the number of the objects which are increased in batches is 1000, the time for solving the local optimal granularity in the step G is not long, so the effect of the step H is not obvious, but the more the objects which are increased in batches are, the more the time for solving the local optimal granularity in the step G is, the more obvious the effect of the step H is, the time for solving the local optimal granularity in the step H is about half of the time for solving the local optimal granularity in the step G, and the time can be obtained.
The invention solves the problem of drug selection of cancer patients by utilizing a multi-granularity decision model; aiming at different conditions, two methods for calculating the global optimal drug granularity are provided, and the global optimal drug granularity is selected in a multi-granularity decision model established for stage I and stage II patients by analyzing the disease severity of cancer patients; selecting local optimal drug granularity in a multi-granularity decision model established for patients in stages III and IV; meanwhile, under the condition that the number of newly added patient data is more than 5000, the method for solving the global optimal medication granularity by selecting the tree structure improves the time efficiency; the process of selecting the local optimal drug granularity is performed in parallel, so that the problem of overlong time is solved, and nearly half of the time is saved.
For the selection of anti-cancer drugs, doctors generally have a certain misdiagnosis rate based on the existing experience, which not only causes the waste of time and money of patients, but also delays the illness state. Based on a multi-granularity decision model, two methods for selecting the globally optimal granularity are provided, a specific algorithm is provided, and the process of selecting the locally optimal granularity is performed in parallel. The results show that: under the condition that the data volume of a newly added patient is larger than 5000, the method for selecting the global optimal granularity by the tree structure has great advantage over a coordinated method in time performance, the time for selecting the local optimal granularity in parallel is about half of the time for selecting the anti-cancer drugs in series, and an automatic auxiliary tool is provided for a doctor to select the anti-cancer drugs.
Claims (4)
1. An optimal medication granularity calculation device based on a multi-granularity decision model is characterized in that: comprises a processor and a memory; the memory has a computer program stored therein, and the computer program, when executed by the processor, performs the following steps:
a: on the basis of the single-granularity-level medication granularity decision model, a multi-granularity-level medication granularity decision model is constructed in a medication system of a cancer patient by taking different granularity levels for the medication dosage of the medicament; then entering the step B;
in the step a, the single-granularity-level medication granularity decision model is a tuple S ═ (O, P ═ d }); wherein O is a group of cancer patients, and O ═ x is used 1 ，x 2 ，...，x n Denotes wherein x 1 Is patient 1, x 2 Patient 2, and so on, x n Is patient n; p is a condition attribute and comprises the basic condition and the dosage of the patient, and P is { a ═ a 1 ，a 2 ，...，a n The decision attribute d represents the treatment effect of the medicine and is represented by Y or N, Y represents the treatment effectiveness, and N represents the treatment ineffectiveness;
in the step a, in the constructed multi-granularity-level medication granularity decision model, the condition attribute P includes the basic condition and the dosage of the patient, and P ═ a 1 ，a 2 ，...，a 10 The disease severity, sex, age, drug A, drug B, drug C, drug D, drug E, drug F and drug G in sequence; the number k of layers of the multi-granularity-layer medicine-use granularity decision model is 3, and when the medicine amount of a patient is expressed by tablets or granules, a first-layer medicine-use granularity decision model S is obtained 1 ＝(O，P 1 U { d }); when the medicine dosage of the patient is represented by a box or a bottle, a second layer medicine dosage decision model S is obtained 2 ＝(O，P 2 U { d }); when the drug dosage of the patient is expressed by the course of treatment, a third layer of drug dosage granularity decision model S is obtained 3 ＝(O，P 3 ∪{d})；
In the single-granularity-level medication granularity decision model S ═ (O, Pu { d }), a multi-granularity-level medication granularity decision model S is obtained by taking different observed values for the drug dosage in the condition attribute set P k ＝(O，P k U { d }), wherein k represents the number of layers and contains all the granularity layers which can be constructed; the number of granularity layers constructed by the multi-granularity-layer medicine granularity decision model is I, the multi-granularity-layer medicine granularity decision model is constructed layer by layer from fine granularity to coarse granularity, and an object O is { x ═ x 1 ，x 2 ，...，x n H, attribute set of each layer is recorded as
Respectively representing the 1 st condition attribute, the 2 nd condition attribute, … and the mth condition attribute in the k-th layer medication granularity decision model;
b: judging the severity of the cancer patient, selecting the globally optimal drug granularity if the cancer patient is a stage I patient and a stage II patient, and entering the step C; if the cancer patient is a patient in stage III and stage IV, selecting local optimal drug granularity, and entering step F;
c: judging according to the number of the patient data, and entering the step D if the number of the patient data is less than or equal to 5000; if the number of newly added patient data is larger than 5000, entering the step E; wherein the patient data comprises an object O, a condition attribute P and a decision attribute d;
d: calculating the global optimal drug granularity by using a coordination method;
e: calculating the global optimal medication granularity by using a tree structure method;
the step E comprises the following specific steps:
solving the global optimum granularity by using a tree structure, converting the multi-granularity-level medication granularity decision model obtained in the step A into a tree storage, and using the multi-granularity-level medication granularity decision model S k ＝(O，P k In U { d }), each layer of a multi-granularity-level drug granularity decision model is a forest consisting of a plurality of trees, each layer of the tree represents each condition attribute, an object O and a decision attribute d are stored below leaf nodes, whether the decision model in the layer is coordinated or not is judged according to the consistency of the decision attribute d below the same leaf node, and the upper layer of the first-appearing uncoordinated granularity layer is the globally optimal drug granularity;
f: judging according to the number of the patient data, and entering the step G if the number of the patient data is less than or equal to 1000; if the number of pieces of patient data is more than 1000, entering step H;
g: calculating local optimal drug granularity by using a serial method;
h: and calculating the local optimal medication granularity by using a parallel method.
2. The device for calculating optimal medication granularity based on the multi-granularity decision model as claimed in claim 1, wherein the step D comprises the following specific steps:
d1: medication granularity decision model S at multiple granularity levels k ＝(O，P k Each layer of U { d }) divides each object according to condition attribute, and sets object x 1 Each condition attribute of
And object x 2 Each condition attribute of
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class by analogy, recording the division result and obtaining a set of the division result of each layer, and marking as R O ；
D2: medication granularity decision model S at multiple granularity levels k ＝(O，P k Each layer of U { d }) divides each object according to decision attributes, and sets object x 1 、x 2 And x 3 Is effective, and subject x 4 And x 5 If the drug treatment is not effective, the decision attribute is divided, and x is divided 1 、x 2 And x 3 Is divided into one class, x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result to obtain the set of all objects divided on each layer, and recording as R r ；
D3: comparing the division results R O And a division result R r If, if
Judging that the decision model of the layer is harmonious; if it is not
Judging that the decision model of the layer is uncoordinated; the upper layer of the first uncoordinated granularity layer is the global optimal medication granularity; r O Representing a set of objects divided by attributes, R r Representing the set of subjects divided by the effect of the medication.
3. The device for calculating optimal medication granularity based on the multi-granularity decision model as claimed in claim 1, wherein the step G comprises the following specific steps:
g1: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each level of U { d }), each object is divided according to conditional attributes, and an object x is assumed to be 1 Each attribute of (2)
And object x 2 Each attribute of (2)
The one-to-one correspondence is the same, then x is 1 And x 2 Dividing into one class, repeating the above steps, recording the division results and obtaining the set of the division results of each object, and recording the set as
Namely, the result of dividing the object x on the k-th layer medication granularity decision model according to the condition attribute P;
g2: medication granularity decision model S at multiple granularity levels k ＝(O，P k At each layer of U { d }), each object is divided according to decision attributes, and an object x is assumed to be 1 And x 2 Is effective, and subject x 3 ，x 4 And x 5 If the drug treatment is not effective, dividing the disease according to decision attributes and dividing x 1 And x 2 Is divided into one class, x 3 ，x 4 And x 5 Dividing into one class, repeating the above steps, recording the division result and obtaining the set of each object, and marking as [ x ]] d I.e. the result of the partitioning of the object x by the decision attribute d;
g3: comparing the set [ x ] of each object x in the step 2] d Whether the set of the objects x in the step 1 is included
If it is
Judging that the decision model of the layer where the object x is located is coordinated; if it is
Judging that the decision model of the layer where the object x is located is uncoordinated; the top layer of the first-occurring uncoordinated granularity layer is the locally optimal medication granularity of the object x, i.e. the
Eyes of a user
When, the k-th layer granularity is the locally optimal medication granularity for subject x; and thus a set of locally optimal medication granularities for all subjects.
4. The device for calculating optimal medication granularity based on a multi-granularity decision model according to claim 3, wherein in the step H, the plurality of pieces of patient data are averagely divided into N groups according to the number N of cores of the processor of the computer, then the N cores of the processor of the computer calculate a corresponding group of patient data respectively according to the method in the step G, and finally the set of local optimal medication granularity of all the objects is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910625179.2A CN110322946B (en) | 2019-07-11 | 2019-07-11 | Optimal medication granularity calculation device based on multi-granularity decision model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910625179.2A CN110322946B (en) | 2019-07-11 | 2019-07-11 | Optimal medication granularity calculation device based on multi-granularity decision model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110322946A CN110322946A (en) | 2019-10-11 |
| CN110322946B true CN110322946B (en) | 2022-09-16 |
Family
ID=68121971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910625179.2A Active CN110322946B (en) | 2019-07-11 | 2019-07-11 | Optimal medication granularity calculation device based on multi-granularity decision model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110322946B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336791A (en) * | 2013-06-06 | 2013-10-02 | 湖州师范学院 | Hadoop-based fast rough set attribute reduction method |
| CN107679368A (en) * | 2017-09-11 | 2018-02-09 | 宁夏医科大学 | PET/CT high dimensional feature level systems of selection based on genetic algorithm and varied precision rough set |
| CN109542949A (en) * | 2018-11-07 | 2019-03-29 | 太原理工大学 | A kind of decision information system knowledge acquisition method based on type vector |
| CN109859815A (en) * | 2019-01-24 | 2019-06-07 | 西安交通大学 | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004025393A2 (en) * | 2002-09-16 | 2004-03-25 | Optimata, Ltd. | An interactive technique for optimizing drug development from the pre-clinical phases through phase-iv |
| US20140372158A1 (en) * | 2013-06-12 | 2014-12-18 | Fair Isaac Corporation | Determining Optimal Decision Trees |
-
2019
- 2019-07-11 CN CN201910625179.2A patent/CN110322946B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336791A (en) * | 2013-06-06 | 2013-10-02 | 湖州师范学院 | Hadoop-based fast rough set attribute reduction method |
| CN107679368A (en) * | 2017-09-11 | 2018-02-09 | 宁夏医科大学 | PET/CT high dimensional feature level systems of selection based on genetic algorithm and varied precision rough set |
| CN109542949A (en) * | 2018-11-07 | 2019-03-29 | 太原理工大学 | A kind of decision information system knowledge acquisition method based on type vector |
| CN109859815A (en) * | 2019-01-24 | 2019-06-07 | 西安交通大学 | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system |
Non-Patent Citations (3)
| Title |
|---|
| Monotonic uncertainty measures for attribute reduction in probabilistic rough set model;Guoyin Wang et al;《International Journal of Approximate Reasoning》;20151231;全文 * |
| 多粒度决策系统属性约简的最优粒度选择;史进玲等;《计算机科学》;20180228;全文 * |
| 广义多尺度决策系统的局部最优粒度选择;顾沈明等;《山东大学学报(理学版)》;20180831;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110322946A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guidi et al. | A machine learning system to improve heart failure patient assistance | |
| WO2017152802A1 (en) | Intelligent system and method for converting textual medical report into structured data | |
| Banu et al. | Disease predicting system using data mining techniques | |
| CN102682210B (en) | Self-adaptive frog cluster evolutionary tree designing method used for electronic medical record attribute reduction | |
| CN101911077A (en) | Method and apparatus for refining similar case search | |
| CN106228023A (en) | A kind of clinical path method for digging based on body and topic model | |
| CN106682213A (en) | Internet-of-things task customizing method and system based on Hadoop platform | |
| Kayyum et al. | Data analysis on myocardial infarction with the help of machine learning algorithms considering distinctive or non-distinctive features | |
| CN109394188A (en) | A kind of adnormal respiration detection method, device and equipment based on heart rate variability | |
| CN106227820B (en) | A kind of construction method of Basic Theories of Chinese Medicine knowledge picture library | |
| CN117216131B (en) | Traditional Chinese medicine data management system based on data retrieval | |
| CN109961018A (en) | Electroencephalogramsignal signal analysis method, system and terminal device | |
| CN111477295B (en) | Traditional Chinese medicine formula recommendation method and system based on latent semantic model | |
| CN110322946B (en) | Optimal medication granularity calculation device based on multi-granularity decision model | |
| Alturki et al. | Predictors of readmissions and length of stay for diabetes related patients | |
| Devi et al. | Coronary Artery Disease prediction using Machine Learning Techniques | |
| CN115985503B (en) | Cancer prediction system based on ensemble learning | |
| Wang et al. | Pay attention and watch temporal correlation: a novel 1-D convolutional neural network for ECG record classification | |
| CN110364265B (en) | Data value generation and implementation method based on health data bank | |
| Li et al. | TCM constitution analysis method based on parallel FP-growth algorithm in hadoop framework | |
| Uma et al. | Stacked feature selection and C5. 0 classification model with Tsallis entropy for medical dataset | |
| Sharma et al. | A Literature Survey on Data Mining Techniques to Predict Lifestyle Diseases | |
| Kamruzzaman et al. | A Structured Method For Predicting Liver Disease Using Machine Learning Techniques & Improvements In Correctness | |
| Alsalamah | Heart Diseases Diagnosis Using Artificial Neural Networks | |
| CN117831640B (en) | Medical industry digital twin platform based on super calculation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |