CN110349681A - Drug combination recommended method, system and device for non-small cell lung cancer - Google Patents
Drug combination recommended method, system and device for non-small cell lung cancer Download PDFInfo
- Publication number
- CN110349681A CN110349681A CN201910627043.5A CN201910627043A CN110349681A CN 110349681 A CN110349681 A CN 110349681A CN 201910627043 A CN201910627043 A CN 201910627043A CN 110349681 A CN110349681 A CN 110349681A
- Authority
- CN
- China
- Prior art keywords
- drug
- cell lung
- probability
- lung cancer
- small cell
- 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
- 208000002154 non-small cell lung carcinoma Diseases 0.000 title claims abstract description 81
- 208000029729 tumor suppressor gene on chromosome 11 Diseases 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000000890 drug combination Substances 0.000 title claims abstract description 30
- 239000003814 drug Substances 0.000 claims abstract description 179
- 229940079593 drug Drugs 0.000 claims abstract description 157
- 230000001225 therapeutic effect Effects 0.000 claims abstract description 22
- 238000003745 diagnosis Methods 0.000 claims abstract description 19
- 238000013461 design Methods 0.000 claims abstract description 18
- 238000002651 drug therapy Methods 0.000 claims abstract description 6
- 230000000694 effects Effects 0.000 claims description 21
- 101000623901 Homo sapiens Mucin-16 Proteins 0.000 claims description 14
- 102100023123 Mucin-16 Human genes 0.000 claims description 14
- 239000008194 pharmaceutical composition Substances 0.000 claims description 12
- 238000002560 therapeutic procedure Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 239000012634 fragment Substances 0.000 claims description 7
- 206010058467 Lung neoplasm malignant Diseases 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 6
- 201000005202 lung cancer Diseases 0.000 claims description 6
- 208000020816 lung neoplasm Diseases 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 3
- 108010066302 Keratin-19 Proteins 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 102100033420 Keratin, type I cytoskeletal 19 Human genes 0.000 claims 2
- 229940000425 combination drug Drugs 0.000 abstract 1
- 230000001737 promoting effect Effects 0.000 abstract 1
- 210000004072 lung Anatomy 0.000 description 16
- 208000000649 small cell carcinoma Diseases 0.000 description 14
- 238000004458 analytical method Methods 0.000 description 11
- 210000004027 cell Anatomy 0.000 description 11
- 102100025475 Carcinoembryonic antigen-related cell adhesion molecule 5 Human genes 0.000 description 10
- 101000914324 Homo sapiens Carcinoembryonic antigen-related cell adhesion molecule 5 Proteins 0.000 description 9
- 101000914321 Homo sapiens Carcinoembryonic antigen-related cell adhesion molecule 7 Proteins 0.000 description 9
- 101000617725 Homo sapiens Pregnancy-specific beta-1-glycoprotein 2 Proteins 0.000 description 9
- 206010028980 Neoplasm Diseases 0.000 description 7
- 108010036226 antigen CYFRA21.1 Proteins 0.000 description 7
- 201000011510 cancer Diseases 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 101150040459 RAS gene Proteins 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 102000004169 proteins and genes Human genes 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 210000002966 serum Anatomy 0.000 description 3
- 208000010507 Adenocarcinoma of Lung Diseases 0.000 description 2
- 206010064571 Gene mutation Diseases 0.000 description 2
- 239000005551 L01XE03 - Erlotinib Substances 0.000 description 2
- 239000002146 L01XE16 - Crizotinib Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 2
- 239000003560 cancer drug Substances 0.000 description 2
- 229960005061 crizotinib Drugs 0.000 description 2
- KTEIFNKAUNYNJU-GFCCVEGCSA-N crizotinib Chemical compound O([C@H](C)C=1C(=C(F)C=CC=1Cl)Cl)C(C(=NC=1)N)=CC=1C(=C1)C=NN1C1CCNCC1 KTEIFNKAUNYNJU-GFCCVEGCSA-N 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 229960001433 erlotinib Drugs 0.000 description 2
- AAKJLRGGTJKAMG-UHFFFAOYSA-N erlotinib Chemical compound C=12C=C(OCCOC)C(OCCOC)=CC2=NC=NC=1NC1=CC=CC(C#C)=C1 AAKJLRGGTJKAMG-UHFFFAOYSA-N 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000002483 medication Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 108010022366 Carcinoembryonic Antigen Proteins 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000002965 ELISA Methods 0.000 description 1
- 101000686031 Homo sapiens Proto-oncogene tyrosine-protein kinase ROS Proteins 0.000 description 1
- 102000018317 Keratin-19 Human genes 0.000 description 1
- 102100023347 Proto-oncogene tyrosine-protein kinase ROS Human genes 0.000 description 1
- 101150035397 Ros1 gene Proteins 0.000 description 1
- 206010040102 Seroma Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000000427 antigen Substances 0.000 description 1
- 102000036639 antigens Human genes 0.000 description 1
- 108091007433 antigens Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003115 biocidal effect Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000002648 combination therapy Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011268 retreatment Methods 0.000 description 1
- 208000000587 small cell lung carcinoma Diseases 0.000 description 1
- 238000002626 targeted therapy Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 150000003722 vitamin derivatives Chemical class 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
- 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
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Toxicology (AREA)
- Pharmacology & Pharmacy (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention provides a kind of drug combination recommended method, system and devices for non-small cell lung cancer, comprising: relevant parameter of the selection about non-small cell lung cancer；Diagnostic parameters model is constructed, relevant parameter input Diagnostic parameters model is obtained into Diagnostic parameters value；According to judging that Diagnostic parameters obtains the decision probability of drug combination, is analyzed to obtain by decision probability of the joint probability method to combination medicine and different pharmaceutical is evaluated in combination；Medication combined suggested design is obtained according to evaluating in combination for different pharmaceutical.The present invention can recommend applicable scheme of combination drug therapy by the relevant parameter of acquisition, give decision scheme to reduce diagnosis duration, promoting therapeutic effect.
Description
Technical field
The invention belongs to a kind of medical treatment, big data, machine learning and decision data fields, are specifically related to one kind be used for
Drug combination recommended method, system and the device of non-small cell lung cancer.
Background technique
In many developing countries, due to limited medical resource, the medical technology of backwardness and the huge size of population it
Between contradiction, the problems such as causing medical resource distribution uneven, Expensive and hard to visit doctors.In practice, it is diagnosed by various inspections
Disease is a cumbersome task.And with the development of information technology, more and more technologies are applied in medical system, significantly
The burden of ground mitigation doctors.Wherein, intelligent medical system can not only help the analysis and diagnosis of doctor's progress state of an illness, moreover it is possible to
It is enough effectively to shorten Diagnostic Time and reduce misdiagnosis rate.It can be between hospital, doctor, patient and its relatives in real time by internet
Ground transmits data, quickly and efficiently can not only provide medical information for patient and its relatives, moreover it is possible to promote between doctor and patient
Communication, efficiently reduce the contradiction between doctor-patient relationship.
For non-small cell lung cancer the state of an illness exist diagnosis time-consuming, there are mistaken diagnosis, therapeutic effect is poor the problems such as.It is now logical
Often to be treated by the way of targeted therapy, and the therapeutic effect of single medicine is often poor, Cocktail treatment again not
Has specific aim.
Summary of the invention
Present invention firstly provides a kind of drug combination recommended methods for non-small cell lung cancer, comprising the following steps:
Select the relevant parameter about non-small cell lung cancer.
Diagnostic parameters model is constructed, relevant parameter input Diagnostic parameters model is obtained into Diagnostic parameters value.
According to judging that Diagnostic parameters obtains the decision probability of drug combination, by joint probability method to the decision of drug combination
Probability is analyzed to obtain and different pharmaceutical is evaluated in combination.
Medication combined suggested design is obtained according to evaluating in combination for different pharmaceutical.
Preferably, the probability for judging therapy target after Diagnostic parameters value by following steps is obtained:
Judge critical section locating for Diagnostic parameters value, obtains the state of an illness stage of non-small cell lung cancer；
Target spot Probabilistic Decision-making weight is set, target spot probability is judged according to state of an illness stage and target spot Probabilistic Decision-making weight.
Preferably, Diagnostic parameters model are as follows:
Wherein, VNSL_CYF(t)、VNSL_CEA(t)、VNSL_CAIt (t) is respectively three kinds of relevant parameters, VNSL_CYFIt (t) is cell angle
The soluble fragments of protein 19, VNSL_CEAIt (t) is S-CEA, VNSL_CAFor cancer antigen -125；δi、δjAnd δjkTo influence
The factor, and δi+δj+δk=1；WithIt is the past 5 years
Determining range.
Preferably, according to judging that Diagnostic parameters obtains combination medicine decision probability, by joint probability method to combination medicine
Decision probability analyzed to obtain different pharmaceutical is evaluated in combination the following steps are included:
Parameter p (drug (k)) is set by the decision probability of preceding k kind drug, p (drug's (k)) is expressed as follows:
Wherein, VNSL_par(t+1) it is to obtain Diagnostic parameters at the t+1 moment using after drug k, is p (drug (k)) weight
The decision probability of major parameter, parameter is as follows:
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell
The invalid or state of an illness of lung-cancer medicament treatment does not deteriorate；If 0≤p (drug (k))≤χ, after using drug k, major parameter
Weight have dropped；The parameter declaration drug k of normal weights is effective for treatment non-small cell lung cancer；If Then illustrate obvious using medication effect after drug k, and the weight of its major parameter is normal,
It no longer needs to take drugs；
Using the information of the drug set of drug (k), training set D is set, and sets relevant parameter in the optimal general of t moment
Rate is ω (t):
ω(t)≡P(VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ)；
Pharmaceutical composition probability after selection therapeutic scheme is arranged is as follows:
When the time is t, by calculating Pω(D) weight, the change of the possible Diagnostic parameters value of the united probability of different pharmaceutical,
That is:
When the time is t+1, medication combined probability is ω (t+1).
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment
, then recommending ω (t) therapeutic scheme is medication combined suggested design；If having one group after any time t is the drug connection for being N the time
Treatment record is closed, and there are ω (t) >=ω (t+N), is then optimal the drug that treatment non-small cell lung cancer effect is t moment
Combined treatment is medication combined suggested design.
Above-mentioned method is relied on, present aspect additionally provides a kind of drug combination recommendation system for non-small cell lung cancer
System, comprises the following modules:
First module, for selecting the relevant parameter about non-small cell lung cancer；
Second module is obtained for constructing Diagnostic parameters model, and for relevant parameter to be inputted Diagnostic parameters model
Diagnostic parameters value；
Third module, for according to judging that Diagnostic parameters obtains combination medicine decision probability, and for general by joint
Rate method is analyzed to obtain and different pharmaceutical is evaluated in combination to combination medicine decision probability；
4th module evaluates different pharmaceutical in combination for basis and obtains medication combined suggested design.
Preferably, the second module obtains the probability after Diagnostic parameters value by judging therapy target with lower module:
5th module obtains the state of an illness stage of non-small cell lung cancer for judging critical section locating for Diagnostic parameters value；
6th module is sentenced for target spot Probabilistic Decision-making weight to be arranged according to state of an illness stage and target spot Probabilistic Decision-making weight
Disconnected target spot probability.
Preferably, the Diagnostic parameters model in the second module are as follows:
Wherein, VNSL_CYF(t)、VNSL_CEA(t)、VNSL_CAIt (t) is respectively three kinds of relevant parameters, VNSL_CYFIt (t) is cell angle
The soluble fragments of protein 19, VNSL_CEAIt (t) is S-CEA, VNSL_CAIt (t) is cancer antigen -125；δi、δjAnd δjkFor shadow
Ring the factor, and δi+δj+δk=1；WithFor the past 5
The range that year determines.
Preferably, third module is used for according to judging that Diagnostic parameters obtains combination medicine decision probability, and passes through connection
It includes with lower unit that conjunction probabilistic method is analyzed to obtain and different pharmaceutical is evaluated in combination to combination medicine decision probability:
First unit, for setting the decision probability of preceding k kind drug to parameter p (drug (k)), the table of p (drug (k))
Show as follows:
Wherein, VNSL_par(t+1) it is to obtain Diagnostic parameters at the t+1 moment using after drug k, is p (drug (k)) weight
The decision probability of major parameter, parameter is as follows:
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell
The invalid or state of an illness of lung-cancer medicament treatment does not deteriorate；If 0≤p (drug (k))≤χ, after using drug k, major parameter
Weight have dropped；The parameter declaration drug k of normal weights is effective for treatment non-small cell lung cancer；If Then illustrate obvious using medication effect after drug k, and the weight of its major parameter is normal,
It no longer needs to take drugs；
Training set D is arranged for the information of the drug set using drug (k) in second unit, and sets relevant parameter and exist
The optimum probability of t moment is ω (t):
ω(t)≡P(VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ)；
Third unit is as follows for the pharmaceutical composition probability after selecting therapeutic scheme to be arranged:
When the time is t, by calculating Pω(D) weight, the change of the possible Diagnostic parameters value of the united probability of different pharmaceutical,
That is:
When the time is t+1, medication combined probability is ω (t+1).
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment
, then recommending ω (t) therapeutic scheme is medication combined suggested design；If having one group after any time t is the drug connection for being N the time
Treatment record is closed, and there are ω (t) >=ω (t+N), is then optimal the drug that treatment non-small cell lung cancer effect is t moment
Combined treatment is medication combined suggested design.
Above-mentioned method is relied on, present aspect additionally provides the another drug combination for non-small cell lung cancer and recommends dress
It sets, including memory and processor；
Memory, for storing computer program；
Processor, for when a computer program is executed, realize as claim 1-4 it is any be used for non-small cell lung cancer
Drug combination recommended method.
The beneficial effects of the present invention are:
Present aspect can recommend applicable combination medicine by the relevant parameter of acquisition, for reduce diagnosis duration,
It promotes therapeutic effect and gives decision scheme.
Detailed description of the invention
Fig. 1 is the drug therapy and decision process to Patients with Non-small-cell Lung.
Fig. 2 is the corresponding drug figure of different target spots.
Fig. 3 is three hospital's data collected in embodiment.
Fig. 4 is the mean apparent of the CYFRA-21-1 of the patient of nearly 5 Nian Laisanjia hospital in embodiment.
Fig. 5 is the mean apparent of the CEA of the patient of nearly 5 Nian Laisanjia hospital in embodiment.
Fig. 6 is the mean apparent of the CA-125 of the patient of nearly 5 Nian Laisanjia hospital in embodiment.
Fig. 7 is in embodiment, the Diagnostic parameters value and the state of an illness of nearly five Nian Laisanjia hospital range by stages.
Fig. 8 is the Diagnostic parameters value of 30 Patients with Non-small-cell Lung in embodiment.
Fig. 9 is the analysis (χ=3.0, ψ=0.4) that medication is persistently selected in embodiment.
Figure 10 is the analysis (χ=6.0, ψ=0.2) that medication is persistently selected in embodiment.
Figure 11 is the analysis (χ=1.0, ψ=0.6) that medication is persistently selected in embodiment.
Figure 12 is the accuracy of diagnosis aid system in embodiment.
Specific embodiment
Embodiment 1:
Referring to Fig. 1, the contents of the present invention include providing a kind of drug combination recommended method for non-small cell lung cancer,
The following steps are included:
S1: relevant parameter of the selection about non-small cell lung cancer.
In non-small cell lung cancer, blood serum tumor markers are mainly generated by tumour cell, and in healthy population, tool
Body value is always in the normal range.However, especially suffering from the patient of advanced cancer, seroma in malignant tumor patient
The level of tumor markers is negatively correlated with life span.Wherein, with the Cancer-Related blood serum tumor markers of non-small cell lung, including
The soluble fragments (soluble fragment of cytokeratin-19, CYFAR21-1) of Cyfra21-1, serum cancer
Embryonal antigen (carcinoembryonic antigen, CEA), cancer antigen -125 (CA-125), these three markers are recognized always
For the prediction index for being non-small cell lung cancer.Non-small cell lung cancer and these three markers in view of 95% or more have apparent
Correlation, the value for calculating these three markers is convenient to Patients with Non-small-cell Lung progress entry evaluation, to select in next step
Effective therapeutic scheme.CYFRA21-1, CEA and CA-125 are set main relevant parameter by the present embodiment, because these three
Relevant parameter can by PET-CT scan be quickly detected from Lai.
S2: relevant parameter input Diagnostic parameters model is obtained Diagnostic parameters value by building Diagnostic parameters model.
The division in non-small cell lung cancer stage generallys use the parameter value of a variety of machine scans, come determine patient the state of an illness and
Stage.One Diagnostic parameters value V is setNSL_par(t), it indicates by relevant parameter and judges that data are examined what t moment was calculated
Disconnected value.Diagnostic parameters value VNSL_parIt (t) include following three parts, and by these three parts, i.e. CYFAR21-1, CEA, CA-
125 value is respectively labeled as VNsL_CYF(t)、VNsL_CEA(t)、VNsL_CA(t).Diagnostic parameters value VNSL_par(t) can be expressed as
Under.
Wherein, δi、δjAnd δjkFor impact factor, and δi+δj+δk=1；
WithFor past 5 years determining range.In addition, the value of CYFRA21-1, CEA and CA-125, average age
It is determined with the range of normal parameter values.
S3: the division in non-small cell lung cancer stage and the judgement of therapy target.
ε (si) it is defined as threshold value, wherein i=1,2,3,4.It can be by VNSL_par(t) four different critical zones are divided
Between, Diagnostic parameters value meets ε (si)≤VNSL_par(t)≤ε(si+1).By above definition, that is, it can determine whether non-small cell lung cancer
The state of an illness stage locating for patient.This four different critical sections are illustrated in Fig. 1.
For each stage of non-small cell lung cancer, it includes therapy target it is as follows:
Stage 1: the mutation of EGF-R ELISA (EGFR) accounts for the 40% of non-small cell lung cancer；RAS in adenocarcinoma of lung
Gene mutation accounts for about the 30% of non-small cell lung cancer.
The mutation of stage 2:EGFR accounts for the 15% of non-small cell lung cancer；RAS gene mutation accounts for about non-small cell lung in adenocarcinoma of lung
The 38% of cancer；EML4-ALK fusion accounts for the 25% of non-small cell lung cancer.
Stage 3:EML4-ALK fusion accounts for the 43% of non-small cell lung cancer；C-MET amplification accounts for non-small cell lung cancer
41%；Gene Fusion accounts for the 12% of non-small cell lung cancer.
The amplification of stage 4:C-MET accounts for the 28% of non-small cell lung cancer；ROS1 Gene Fusion accounts for the 56% of non-small cell lung cancer.
Drug corresponding to each therapy target is all different, and Fig. 2 is the corresponding drug figure of different target spots.
During diagnosing non-small cell lung cancer, a possibility that each target spot probability can be measured, and target spot and trouble
The stage that person is in disease is related.Meanwhile three kinds of relevant parameters in type and non-small cell lung cancer each stage of disease have
Association.Therefore, in order to assess the probability P of target spotTherapeutic, the major parameter of disease stage and Probabilistic Decision-making weight can be passed through
Node diagnoses.For this purpose, we can obtain target spot probability P by following judgementTherapeutic。
PTherapeutic(Tk)=P (Tk| Stage=i, VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ) (2)
Wherein, TkFor the type of point, i is the stage of small cell carcinoma of lung, and α, beta, gamma is the marker of three kinds of relevant parameters.I
Can be calculated by joint probability method non-small cell lung cancer each stage target spot probability.
S4: according to judging that Diagnostic parameters obtains the decision probability of drug combination, by joint probability method to drug combination
Decision probability is analyzed to obtain and different pharmaceutical is evaluated in combination.
The different phase of non-small cell carcinoma is calculated by Probabilistic Decision-making, wherein different phase is there may be multiple target spots,
And these target spots can be used for the selection of therapeutic scheme.Therefore, we use number for the main chart and drug of drug therapy
According to collection design a kind of decision-making technique.
Fig. 2 illustrates the decision of one group of drug therapy.In decision process, record selection uses each of which kind of method
The classification of target spot.In Fig. 2, we construct a decision set, which includes depositing for all kinds of medical records and target spot
Store up type, the form of expression for such as storing a kind of drug as system (chair type).The representation of the data set is as follows:
Data set 1:RGFR { gefeitinib (chair), erlotinib (chair) }
Data set 2:RAS { selmetinib (chair), alecitinib (chair) }
Data set 3:MELA4-ALK { alecitinib (chair), gefeitinib (chair) }
Data set 4:ROS1 { alecitinib (chair), crizotinib (chair), cretinib (chair) }
Data set 5:C-MET { gefeitinib (chair), erlotinib (chair), crizotinib (chair) }
The collection system of each similar drug provides Retreatment possibility for patient and improves the therapeutic scheme of medication efficiency.
The evaluation of treated with combined medication scheme.
Parameter p (drug (k)) is set by the decision probability of preceding k kind drug, p (drug's (k)) is expressed as follows:
Wherein, VNSL_parIt (t+1) is using obtaining the weight of major parameter after drug k.Finally according to formula (1)-(3)
The Parameter Decision Making probability of preceding k kind drug is as follows.
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell
The invalid or state of an illness of lung-cancer medicament treatment does not deteriorate；
If 0≤p (drug (k))≤χ, using after drug k, the weight of major parameter is had dropped；The ginseng of normal weights
Scolding bright drug k is effective for treatment non-small cell lung cancer；
IfThen illustrate, and its major parameter obvious using medication effect after drug k
Weight it is normal, it is no longer necessary to take drugs.
In many developing countries, patient needs to take a variety of containing antibiotic, vitamin and other drugs.For suffering from
For person, the effect of these drugs is independent and necessary.Therefore, during treating non-small cell lung cancer, a variety of drugs
Combination therapy facilitate improve non-small cell lung cancer main relevant parameters data.We, which can calculate, all kinds of uses medicinal strip
Joint probability distribution under part is as follows:
The evaluation that we can combine different medications by joint probability method, so as to improve the non-small cell lung of patient
The data of the main relevant parameters of cancer.
The iteration of treated with combined medication scheme optimizes:
Such as drug (1) is used during data collection, the letter of the drug set of drug (1) ..., drug (k)
Breath, is arranged a training set D.Three kinds of relevant parameters are set in the optimum probability of t moment as ω (t).
ω(t)≡P(VNsL_CYF(t)=α, VNsL_CEA(t)=β, VNSL_CA(t)=γ) (5)
Pharmaceutical composition probability after selection therapeutic scheme is arranged is as follows:
When the time is t, by calculating Pω(D) weight, the probability of the therapeutic scheme of patient may cause three kinds of diagnosis ginsengs
The change of numerical value, it may be assumed that
When the time is t+1, optimal medication probability is ω (t+1).
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment
, then recommend ω (t) therapeutic scheme.
If have after any time t one group be the treated with combined medication record of N the time, and there are ω (t) >=ω (t+N),
Then it is optimal the treated with combined medication scheme that treatment non-small cell lung cancer effect is t moment.
S5: medication combined suggested design is obtained according to evaluating in combination for different pharmaceutical.
Above-mentioned method is relied on, present aspect additionally provides a kind of drug combination recommendation system for non-small cell lung cancer
System, comprises the following modules:
First module, for selecting the relevant parameter about non-small cell lung cancer；
Second module is obtained for constructing Diagnostic parameters model, and for relevant parameter to be inputted Diagnostic parameters model
Diagnostic parameters value；
Third module, for according to judging that Diagnostic parameters obtains the decision probability of drug combination, and for passing through joint
Probabilistic method is analyzed to obtain and different pharmaceutical is evaluated in combination to the decision probability of drug combination；
4th module evaluates different pharmaceutical in combination for basis and obtains medication combined suggested design.
Preferably, the second module obtains the probability after Diagnostic parameters value by judging therapy target with lower module:
5th module obtains the state of an illness stage of non-small cell lung cancer for judging critical section locating for Diagnostic parameters value；
6th module is sentenced for target spot Probabilistic Decision-making weight to be arranged according to state of an illness stage and target spot Probabilistic Decision-making weight
Disconnected target spot probability.
Preferably, the Diagnostic parameters model in the second module are as follows:
Wherein, VNSL_CYF(t)、VNSL_CEA(t)、VNSL_CAIt (t) is respectively three kinds of relevant parameters, VNSL_CYFIt (t) is cell angle
The soluble fragments of protein 19, VNSL_CEAIt (t) is S-CEA, VNSL_CAIt (t) is cancer antigen -125；δi、δjAnd δjkFor shadow
Ring the factor, and δi+δj+δk=1；WithFor the past 5
The range that year determines.
Preferably, third module is used for according to judging that Diagnostic parameters obtains combination medicine decision probability, and passes through connection
It includes with lower unit that conjunction probabilistic method is analyzed to obtain and different pharmaceutical is evaluated in combination to combination medicine decision probability:
First unit, for setting the decision probability of preceding k kind drug to parameter p (drug (k)), the table of p (drug (k))
Show as follows:
Wherein, VNSL_par(t+1) it is to obtain Diagnostic parameters at the t+1 moment using after drug k, is p (drug (k)) weight
The decision probability of major parameter, parameter is as follows:
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell
The invalid or state of an illness of lung-cancer medicament treatment does not deteriorate；If 0≤p (drug (k))≤χ, after using drug k, major parameter
Weight have dropped；The parameter declaration drug k of normal weights is effective for treatment non-small cell lung cancer；If Then illustrate obvious using medication effect after drug k, and the weight of its major parameter is normal,
It no longer needs to take drugs；
Training set D is arranged for the information of the drug set using drug (k) in second unit, and sets relevant parameter and exist
The optimum probability of t moment is ω (t):
ω(t)≡P(VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ)；
Third unit is as follows for the pharmaceutical composition probability after selecting therapeutic scheme to be arranged:
When the time is t, by calculating Pω(D) weight, the change of the possible Diagnostic parameters value of the united probability of different pharmaceutical,
That is:
When the time is t+1, medication combined probability is ω (t+1).
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment
, then recommending ω (t) therapeutic scheme is medication combined suggested design；If having one group after any time t is the drug connection for being N the time
Treatment record is closed, and there are ω (t) >=ω (t+N), is then optimal the drug that treatment non-small cell lung cancer effect is t moment
Combined treatment is medication combined suggested design.
Above-mentioned method is relied on, present aspect additionally provides the another drug combination for non-small cell lung cancer and recommends dress
It sets, including memory and processor；
Memory, for storing computer program；
Processor, for when a computer program is executed, realize as claim 1-4 it is any be used for non-small cell lung cancer
Drug combination recommended method.
Embodiment 2:
In the present embodiment, used medical data is all from three first-class hospitals, institute of China, be respectively Xiang Ya hospital,
Refined second hospital in Hunan, Xiang Ya third hospital.
Table 1, which is illustrated, acquires medical system used in data by this three hospitals.
The medical data of this three hospitals passes through medical data center and is transmitted and exchanged.Medical data central data
From the data of different department, the data such as diagnosis, case, operation, nursing care plan and the medicament selection of patient, and carry out
Classification, provides comprehensive information for doctor, nurse and patient.The table also shows this three hospitals from 2002 to 2015 year
All patients data record, these data can be used for the identification and statistic of classification of information, to be formed in medical data
The heart.
Fig. 3 illustrates the data collection situation of this three hospitals.In 15 years, this three hospitalize patients totally 789675
People generates totally 5287413 parts of effective electronic health record.The doctor of this three hospitals sends 112561 parts of diagnosis report, clinic is examined
Disconnected 1427790 parts of report.
In these medical systems, HIS is hospital information system (Hospital Information System), and EMR is
Electronic health record (Electronic Medical Record), LIS are laboratory information system (Laboratory
Information System), RIS is radiology information system (Radiology Information System), and PACS is
Picture archiving and communication system (Picture Archiving and Communication System).These data record energy
Enough help doctor to typical case carry out clinical analysis and research, by big data medical information system carry out decision and with
Probability analysis is as Research foundation.
39483216 parts of data informations about non-small cell lung cancer big data by being stored in medical laboratory carry out
Analysis.Wherein, it shares 93218 articles to have recorded from different department and different classes of operative treatment, using different hands
Art shares 40631 articles and has recorded information and attribute that doctor selects drug, it is ensured that use doctor to improve success rate of operation
Institute's medication management data environment it is convenient.
Table 2 illustrates three kinds of normal relevant parameter ranges of non-small cell lung cancer；Table 3 is the diagnosis of non-small cell lung cancer
Parameter is used to the case where dividing the state of an illness stage.
The normal relevant parameter range of three kinds of 2 non-small cell lung cancer of table
The Diagnostic parameters of 3 non-small cell lung cancer of table is used to the case where dividing the state of an illness stage
Fig. 4 for three hospitals patient over nearly 5 years CYFRA-21-1 mean apparent situation, it can be seen that CYFRA-21-1's
Normal range (NR) is between 0 to 1.8.5 sampling results mean apparents of non-small cell lung cancer are all larger than normal value, and average more than
35, CYFRA-21-1 nearly 5 years for showing Patients with Non-small-cell Lung are in abnormality.
Fig. 5 illustrates the mean apparent of the CEA of the patient of nearly 5 Nian Laisanjia hospital, it can be seen that the normal range (NR) of CEA exists
Between 0 to 5.0.The mean apparent of the sampling results of Patients with Non-small-cell Lung is greater than normal value, and CEA mean apparent is normal value
16 times, average more than 80, CEA nearly 5 years for showing Patients with Non-small-cell Lung are in abnormality.
Fig. 6 illustrates the mean apparent of the CA-125 of the patient of nearly 5 Nian Laisanjia hospital, it can be seen that CA-125's is normal
Range is between 0 to 35.0.The mean apparent of the sampling results of Patients with Non-small-cell Lung is greater than normal value, and CA-125 is averaged table
Now it is 5 times of normal value, has been more than average value, CA-125 nearly 5 years for showing Patients with Non-small-cell Lung are in abnormal shape
State.
Diagnostic parameters value V can be calculated by the analysis to patient's Diagnostic parameters, and using formula (2)NSL_par(t)。
Assuming that three relevant parameters in judgement non-small cell lung cancer stage, are divided into phase by the related diagnostic parameter of patient's equal weight
Same weight, and as shown in fig. 6, patient's Diagnostic parameters value with higher.
According to the available diagnosis Analysis of Policy Making in nearly 5 years of calculating of formula (2).In the whole process, three correlations
Parameter is set as identical weight factor, i.e.,To which we can calculate three patient in hospital not
With Diagnostic parameters value.
As shown in fig. 6, by the statistical data of 2011 to 2015 years nearest 5 years Patients with Non-small-cell Lung, including use
The diagnosed case of the second stage of decision, in these data, numerical value in 2011 is 80.71.Diagnostic parameters average value in 2012 is
93.85 increasing by 13.68%.In 2013, the Diagnostic parameters average value of the Patients with Non-small-cell Lung of this three hospitals was
124.32.In addition, the growth rate of non-small cell lung cancer three phases in 2012 is 32.6%.It is non-small 2014 and 2015
The Diagnostic parameters average value of cell lung cancer patients falls to 96.12 and 91.12 respectively.
From table 3 it is observed that the case of non-small cell lung cancer is in second stage mostly in nearly research in 5 years.It is logical
The analysis to a large amount of decision data, especially Patients with Non-small-cell Lung are crossed, hospital and doctor have been that patient carries out medication
And the prior preparation for the treatment of, the storage for the second class disease medicament provide good reference.
Table 4 lists the sample set of diagnosis process and decision parameters of 30 patients after hospital admission.
The sample set of diagnosis process and decision parameters after table 4 is medical
The sensitivity of system is related to effectively regulating and controlling, multiple patient datas sample under improvement and mixed mode, these are right
Decision process mechanism is advantageous, coverage area is wider and analyzes speed faster.Therefore, these are all necessary.Meanwhile according to formula
(4) in-(10), we, which can analyze, judges each therapy target and automatic recommendation drug, as shown in Figure 8.
Fig. 8 presents the record of nearly 30 Patients with Non-small-cell Lung and the mechanism of decision.Utilize the data of system introducing
Collection can quickly analyze patient's decision data of each sampled point, to quickly distinguish the stage of Patients with Non-small-cell Lung.
Fig. 9-11 presents the effect in different probability state modulator and persistently selecting medication.In these figures, when χ=
When 3.0, ψ=0.4, decision node is 7 by continuously putting the set formed, is divided into 1-5,6-9 and 11-15 three phases.This
Outside, under medication mode of the same race, long-continued clinical stages, shows that these medications can improve the steady of non-small cell lung cancer
It is qualitative.As χ=6.0, ψ=0.2, which shares five groups of drugs.Then, as χ=3.0, ψ=0.4, the spirit of system
Sensitivity is reduced with the reduction of Tactic selection.As χ=1.0, ψ=0.6, only 4 groups of drug control node collection 11-15 it
Between be in chronic steady state.After being adjusted to probability control parameter, the sensitivity of system reflects drug decision
Effect.
It, can be to different regions, different age people and probability by the control and adjustment to system mode probability parameter
Diagnosis, drug recommend analysis to work, and may advantageously facilitate the early diagnosis of non-small cell lung cancer.Each stage of system recommendation
Medication has preferable improvement.
Figure 12 shows the accuracy of diagnosis aid system.From data history, we wonder whether a patient has
With non-small cell lung cancer.From data, the diagnosis of doctor is very accurately.The diagnosis of doctor is in small sample (100-
500) precision is up to 97%, and (more than 1000), accuracy rate has also reached 88% in big data sample.
The diagnosis aid system is not accurate enough in small sample, and accuracy rate is only 43%-59%.If without enough instructions
Practice storage originally in the database, then the diagnostic result of the system can not play help to doctor.Using a large amount of samples
Be trained in this, accuracy rate is consequently increased, when diagnostic data reaches 5000 or more, accuracy rate be increased to 80% with
On.
Although the present invention is disclosed as above with preferred embodiment, however, it is not intended to limit the invention.It is any to be familiar with ability
The technical staff in domain, without deviating from the scope of the technical scheme of the present invention, all using the technology contents pair of the disclosure above
Technical solution of the present invention makes many possible changes and modifications or equivalent example modified to equivalent change.Therefore, all
Without departing from the content of technical solution of the present invention, according to the present invention technical spirit any simple modification made to the above embodiment,
Equivalent variations and modification, all shall fall within the protection scope of the technical scheme of the invention.
Claims (9)
1. being used for the drug combination recommended method of non-small cell lung cancer, characterized in that the following steps are included:
Select the relevant parameter about non-small cell lung cancer；
Diagnostic parameters model is constructed, the relevant parameter is inputted into the Diagnostic parameters model and obtains Diagnostic parameters value；
According to judging that the Diagnostic parameters obtains the decision probability of drug combination, by joint probability method to the decision of drug combination
Probability is analyzed to obtain and different pharmaceutical is evaluated in combination；
Medication combined suggested design is obtained according to evaluating in combination for different pharmaceutical.
2. being used for the drug combination recommended method of non-small cell lung cancer as described in claim 1, characterized in that obtain described examine
The probability of therapy target is judged after disconnected parameter value by following steps:
Judge critical section locating for the Diagnostic parameters value, obtains the state of an illness stage of non-small cell lung cancer；
Target spot Probabilistic Decision-making weight is set, judges that target spot is general according to the state of an illness stage and the target spot Probabilistic Decision-making weight
Rate.
3. being used for the drug combination recommended method of non-small cell lung cancer as described in claim 1, characterized in that the diagnosis ginseng
Exponential model are as follows:
Wherein, VNSL_CYF(t)、VNSL_CEA(t)、VNSL_CAIt (t) is respectively three kinds of relevant parameters, VNSL_CYFIt (t) is cytokeratin
19 soluble fragments, VNSL_CEAIt (t) is S-CEA, VNSL_CAIt (t) is cancer antigen -125；δi、δjAnd δjkFor influence because
Son, and δi+δj+δk=1；WithIt is true for past 5 years
Fixed range.
4. being used for the drug combination recommended method of non-small cell lung cancer as described in claim 1, characterized in that according to judging
It states Diagnostic parameters and obtains the decision probability of drug combination, analyze by decision probability of the joint probability method to drug combination
To being evaluated in combination for different pharmaceutical the following steps are included:
Parameter p (drug (k)) is set by the decision probability of preceding k kind drug, p (drug's (k)) is expressed as follows:
Wherein, VNSL_par(t+1) it is to obtain Diagnostic parameters at the t+1 moment using after drug k, is the main of p (drug (k)) weight
The decision probability of parameter, parameter is as follows:
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell lung cancer
The invalid or state of an illness of drug therapy does not deteriorate；If 0≤p (drug (k))≤χ, after using drug k, the power of major parameter
It has dropped again；The parameter declaration drug k of normal weights is effective for treatment non-small cell lung cancer；If 0≤p (drug (k))
≤Then illustrate obvious using medication effect after drug k, and the weight of its major parameter is normal, it is no longer necessary to take medicine
Object；
Using the information of the drug set of drug (k), training set D is set, and sets the relevant parameter in the optimal general of t moment
Rate is ω (t):
ω(t)≡P(VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ)；
Pharmaceutical composition probability after selection therapeutic scheme is arranged is as follows:
When the time is t, by calculating Pω(D) weight, the change of the possible Diagnostic parameters value of the united probability of different pharmaceutical,
That is:
When the time is t+1, medication combined probability is ω (t+1)
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment,
Then recommending ω (t) therapeutic scheme is medication combined suggested design；If having one group after any time t is be N the time medication combined
Treatment record, and there are ω (t) >=ω (t+N), then it is optimal the drug connection that treatment non-small cell lung cancer effect is t moment
Conjunction therapeutic scheme is medication combined suggested design.
5. being used for the drug combination recommender system of non-small cell lung cancer, characterized in that comprise the following modules:
First module, for selecting the relevant parameter about non-small cell lung cancer；
Second module, for constructing Diagnostic parameters model, and for the relevant parameter to be inputted the Diagnostic parameters model
Obtain Diagnostic parameters value；
Third module, for according to judging that the Diagnostic parameters obtains combination medicine decision probability, and for general by joint
Rate method is analyzed to obtain and different pharmaceutical is evaluated in combination to combination medicine decision probability；
4th module evaluates different pharmaceutical in combination for basis and obtains medication combined suggested design.
6. being used for the drug combination recommender system of non-small cell lung cancer as claimed in claim 5, characterized in that second mould
Block obtains the probability after the Diagnostic parameters value by judging therapy target with lower module:
5th module obtains the state of an illness stage of non-small cell lung cancer for judging critical section locating for the Diagnostic parameters value；
6th module is weighed for target spot Probabilistic Decision-making weight to be arranged according to the state of an illness stage and the target spot Probabilistic Decision-making
Major punishment is broken target spot probability.
7. being used for the drug combination recommender system of non-small cell lung cancer as claimed in claim 5, characterized in that second mould
The Diagnostic parameters model in block are as follows:
Wherein, VNSL_CYF(t)、VNSL_CEA(t)、VNSL_CAIt (t) is respectively three kinds of relevant parameters, VNSL_CYFIt (t) is cytokeratin
19 soluble fragments, VNSL_CEAIt (t) is S-CEA, VNSL_CAIt (t) is cancer antigen -125；δi、δjAnd δjkFor influence because
Son, and δi+δj+δk=1；WithIt is true for past 5 years
Fixed range.
8. being used for the drug combination recommender system of non-small cell lung cancer as claimed in claim 5, characterized in that third module is used
According to judging that the Diagnostic parameters obtains combination medicine decision probability, and it is general to combination medicine decision by joint probability method
It includes with lower unit that rate, which is analyzed to obtain and different pharmaceutical is evaluated in combination:
First unit, for setting the decision probability of preceding k kind drug to parameter p (drug (k)), the expression of p (drug (k)) is such as
Under:
Wherein, VNSL_par(t+1) it is to obtain Diagnostic parameters at the t+1 moment using after drug k, is the main of p (drug (k)) weight
The decision probability of parameter, parameter is as follows:
If p (drug (k)) >=χ, using after drug k, the weight of major parameter does not decline, and is due to non-small cell lung cancer
The invalid or state of an illness of drug therapy does not deteriorate；If 0≤p (drug (k))≤χ, after using drug k, the power of major parameter
It has dropped again；The parameter declaration drug k of normal weights is effective for treatment non-small cell lung cancer；If 0≤p (drug (k))
≤Then illustrate obvious using medication effect after drug k, and the weight of its major parameter is normal, it is no longer necessary to take
Drug；
Training set D is arranged for the information of the drug set using drug (k) in second unit, and sets the relevant parameter and exist
The optimum probability of t moment is ω (t):
ω(t)≡P(VNSL_CYF(t)=α, VNSL_CEA(t)=β, VNSL_CA(t)=γ)；
Third unit is as follows for the pharmaceutical composition probability after selecting therapeutic scheme to be arranged:
When the time is t, by calculating Pω(D) weight, the united probability of different pharmaceutical may cause the Diagnostic parameters value
Change, it may be assumed that
When the time is t+1, medication combined probability is ω (t+1)
If at any time when t, there are ω (t) >=ω (t+1), i.e. the effect of the pharmaceutical composition of t moment is better than the t+1 moment,
Then recommending ω (t) therapeutic scheme is medication combined suggested design；If having one group after any time t is be N the time medication combined
Treatment record, and there are ω (t) >=ω (t+N), then it is optimal the drug connection that treatment non-small cell lung cancer effect is t moment
Conjunction therapeutic scheme is medication combined suggested design.
9. being used for the drug combination recommendation apparatus of non-small cell lung cancer, characterized in that including memory and processor；
The memory, for storing computer program；
The processor, for when loaded and executed, realize as described in claim 1-4 is any be used for it is non-small
The medication combined recommended method of cell lung cancer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910627043.5A CN110349681A (en) | 2019-07-11 | 2019-07-11 | Drug combination recommended method, system and device for non-small cell lung cancer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910627043.5A CN110349681A (en) | 2019-07-11 | 2019-07-11 | Drug combination recommended method, system and device for non-small cell lung cancer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110349681A true CN110349681A (en) | 2019-10-18 |
Family
ID=68174940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910627043.5A Pending CN110349681A (en) | 2019-07-11 | 2019-07-11 | Drug combination recommended method, system and device for non-small cell lung cancer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349681A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696678A (en) * | 2020-06-15 | 2020-09-22 | 中南大学 | Deep learning-based medication decision method and system |
| CN115862804A (en) * | 2022-11-25 | 2023-03-28 | 成都诺医德医学检验实验室有限公司 | Method and device for recommending combined medication of double medicines |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109061164A (en) * | 2018-08-21 | 2018-12-21 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | For the composite marker object of Diagnosis of Non-Small Cell Lung and its application |
-
2019
- 2019-07-11 CN CN201910627043.5A patent/CN110349681A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109061164A (en) * | 2018-08-21 | 2018-12-21 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | For the composite marker object of Diagnosis of Non-Small Cell Lung and its application |
Non-Patent Citations (1)
| Title |
|---|
| JIAWU: "Data Decision and Drug Therapy Based on Non-Small Cell Lung Cancer in a Big Data Medical System in Developing Countries", 《SYMMETRY》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696678A (en) * | 2020-06-15 | 2020-09-22 | 中南大学 | Deep learning-based medication decision method and system |
| CN115862804A (en) * | 2022-11-25 | 2023-03-28 | 成都诺医德医学检验实验室有限公司 | Method and device for recommending combined medication of double medicines |
| CN115862804B (en) * | 2022-11-25 | 2023-12-19 | 成都诺医德医学检验实验室有限公司 | Method and device for recommending combined drug for combination of two drugs |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Siddiqui et al. | Comparison of MR/ultrasound fusion–guided biopsy with ultrasound-guided biopsy for the diagnosis of prostate cancer | |
| Dercle et al. | Early readout on overall survival of patients with melanoma treated with immunotherapy using a novel imaging analysis | |
| Lambin et al. | Predicting outcomes in radiation oncology—multifactorial decision support systems | |
| Wei et al. | Understanding artificial neural networks and exploring their potential applications for the practicing urologist | |
| Bangma et al. | Active surveillance for low-risk prostate cancer | |
| US8929625B2 (en) | Method and device for side-effect prognosis and monitoring | |
| US20090234627A1 (en) | Modeling lung cancer survival probability after or side-effects from therapy | |
| CN102652317A (en) | Diagnostic techniques for continuous storage and joint analysis of both image and non-image medical data | |
| US8874378B2 (en) | System and method for targeting relevant research activity in response to angiogenic regulator analyses | |
| Agur et al. | Personalizing oncology treatments by predicting drug efficacy, side‐effects, and improved therapy: mathematics, statistics, and their integration | |
| Olson et al. | Treatment with stereotactic ablative radiotherapy for up to 5 oligometastases in patients with cancer: primary toxic effect results of the nonrandomized phase 2 SABR-5 clinical trial | |
| US20150046465A1 (en) | System and method for targeting relevant research activity in response to diagnostic marker analyses | |
| Saleem et al. | Textural features of 18 F-fluorodeoxyglucose positron emission tomography scanning in diagnosing aortic prosthetic graft infection | |
| CN110349681A (en) | Drug combination recommended method, system and device for non-small cell lung cancer | |
| Erb et al. | Surveillance practice patterns after curative intent therapy for stage I non-small-cell lung cancer in the Medicare population | |
| WO2006119340A2 (en) | Dynamic tumor diagnostic and treatment system | |
| Wang et al. | Comparison and screening of different risk assessment models for deep vein thrombosis in patients with solid tumors | |
| US20220015698A1 (en) | Method of identifying tumor drug resistance during treatment | |
| WO2009148803A2 (en) | Methods and systems for integrated health systems | |
| Rawat et al. | Digital Clinical Diagnostic System for Lung Cancer Detection | |
| Zhang et al. | The application of artificial intelligence in lung cancer: a narrative review | |
| Jagsi et al. | Radiotherapy use and incidence of locoregional recurrence in patients with favorable-risk, node-positive breast cancer enrolled in the SWOG S1007 trial | |
| Booth et al. | Machine learning and glioblastoma: treatment response monitoring biomarkers in 2021 | |
| CN115346637A (en) | Method and system for recommending tumor targeted drugs | |
| Gezer et al. | CT-derived body composition associated with lung cancer recurrence after surgery |
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: 20191018 |