CN111223572A - Method for evaluating degree of correlation between treatment scheme effect and specific patient population - Google Patents
Method for evaluating degree of correlation between treatment scheme effect and specific patient population Download PDFInfo
- Publication number
- CN111223572A CN111223572A CN202010058339.2A CN202010058339A CN111223572A CN 111223572 A CN111223572 A CN 111223572A CN 202010058339 A CN202010058339 A CN 202010058339A CN 111223572 A CN111223572 A CN 111223572A
- Authority
- CN
- China
- Prior art keywords
- group
- survival
- patients
- survival rate
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the field of relevancy evaluation, and particularly discloses a method for evaluating relevancy of treatment scheme effects and specific patients. The evaluation method comprises the following steps: dividing patients into N groups, adopting different intervention treatment measures for each group, and respectively listing the survival time of each group of patients; solving the survival rate of each group, and finding out a group with the highest survival rate at the M time point; recording the intervention measures of the group with the highest survival rate, forming an expanded group, and generating a survival distribution map of the expanded group; intercepting the second half part of the survival rate obviously beginning to increase in the survival distribution map, listing the survival time of the intercepted section of the expanded group and the characteristic values of all patients, finding out the characteristic values commonly owned by the patients, and further determining the optimal treatment method of the disease patients with the specific characteristic values. The invention makes full use of the disease treatment data, accurately analyzes different specific measures and effects to obtain better intervention measures of the disease under different characterization states, thereby improving the cure rate of the disease.
Description
(I) technical field
The invention relates to the field of relevancy evaluation, in particular to a method for evaluating relevancy between treatment scheme effects and specific patients.
(II) background of the invention
With the continuous emergence of a plurality of new therapeutic drugs and therapeutic methods in recent years, the survival time of a specific patient group is greatly prolonged once the specific patient group receives the treatment suitable for the patient. How to utilize clinical data and a convenient method to help a specific patient group to find a treatment scheme suitable for the patient can benefit many patients and is also one direction for effective utilization and development of future big data.
In the direction of research on correlation, only comparison of multiple treatment effects for a certain disease or comparison of effects of a certain treatment scheme for multiple disease conditions is performed from a medical perspective, and evaluation of the correlation lacks systematic method tools, particularly research on the general method for correlation of treatment effects with a specific patient population.
Disclosure of the invention
In order to make up for the defects of the prior art, the invention provides the evaluation method of the relevance between the treatment scheme effect and the specific patient, which has the advantages of full data utilization, accurate analysis and high utilization value.
The invention is realized by the following technical scheme:
a method for assessing the relevance of the effect of a treatment regimen to a particular patient, comprising the steps of:
(1) dividing patients with the same disease into N groups, adopting different intervention treatment measures in each group, and respectively listing the survival time of each group of patients;
(2) solving the survival rate of each group, and finding out a group with the highest survival rate at the M time point;
(3) recording the intervention measures of the group with the highest survival rate, collecting or gathering more cases under the intervention measures to form an expanded group, listing the survival time of patients in the expanded group, and generating a survival distribution map of the expanded group;
(4) intercepting the second half part of the survival rate in the survival distribution graph which obviously begins to increase, and listing the survival time of the interception section of the expansion group;
(5) listing the characteristic values of all patients in the enlarged group intercepting segment, numbering the characteristic codes of the patients, calculating the occurrence frequency of each characteristic code, finding out the characteristic code with the occurrence frequency of 1 or the highest occurrence frequency, namely the characteristic code commonly owned by the patients or the code most frequently possessed by the patients, and then determining the optimal treatment method of the disease patient with the specific characteristic value.
The invention analyzes different intervention treatment measures of the same disease, analyzes the intervention measure with better effect by calculating survival rate, fills and expands data, digitalizes the characteristics of the patient, and finally obtains the optimal treatment method of the disease patient with corresponding characteristic value, so as to scientifically adjust and treat according to the characteristics of the patient.
The more preferable technical scheme of the invention is as follows:
in the step (2), the survival rate is calculated by, in the case of M time points in total, the number of survival cases in the mth period = the number of initial cases in the mth period-the number of effective cases in the mth period, and the survival probability in the mth period = the number of survival cases in the mth period/the number of initial cases in the mth period, and then the survival rate in the mth period = the survival rate in the M-1 th period × the survival probability in the mth period.
In the step (3), the survival distribution map of the expanded group is generated by using EXCEL with the patient number as the horizontal axis and the survival time as the vertical axis.
In the step (5), the method for calculating the occurrence frequency of the feature code comprises the following steps: the frequency of occurrence of the feature code = the number of occurrences of the feature code/total number of patients in the enlarged group truncation.
A population of patients sensitive to a particular intervention is selected, and the optimal treatment for that type of patient is determined to be the particular intervention.
The invention makes full use of the existing disease treatment data, accurately analyzes different specific measures and effects to obtain the optimal intervention measures of the diseases under different characterization states, further improves the cure rate of the diseases, and is suitable for wide popularization and application.
(IV) description of the drawings
The invention will be further described with reference to the accompanying drawings.
FIG. 1 is a graph showing the survival distribution of an expanded group of the present invention.
(V) detailed description of the preferred embodiments
In order to more fully understand the technical contents of the present invention, the technical solutions of the present invention will be further described and illustrated with reference to the following specific embodiments.
Example (b):
the total number of the lung cancer patient group files is 2, the intervention measure adopted by the patient group 1 is western medicine A treatment, and the intervention measure adopted by the patient group 2 is traditional Chinese medicine B treatment. The information of survival time, treatment mode, lung cancer type and the like in the file can be retrieved. It is desirable to find valuable information therefrom, particularly information on effective treatments or optimal treatment regimens for different lung cancer patients, as described below.
Step one, the survival time of 2 patients is listed as shown in table 1 and table 2 (note: + indicates invalid data or deleted data).
TABLE 1 survival time (month) for patient group 1
TABLE 2 survival time (month) for patient group 2
And step two, calculating the survival rate of each group as shown in tables 3 and 4 (note: + represents invalid data or deletion data, so that the death number of the patient with + mark is not counted when the survival probability is calculated).
Table 3 survival rate of patient group 1
Table 4 survival rate of patient group 2
The 46-month survival rate of group 1 was 0.13, and the 46-month survival rate of group 2 was 0.125. Therefore, the group with the highest survival rate at the 46 month time point was group 1, and the intervention measure adopted in group 1 was western medicine a.
Step three, recording the intervention measures adopted by the patient group 1 as western medicine A treatment, collecting cases under the intervention measures in a file to form an expanded group, and listing the survival time of the patients in the expanded group, as shown in table 5.
TABLE 5 extended survival time (month)
The survival profile of the expanded group was generated using EXCELL (see FIG. 1).
Step four, intercepting the latter half part of the distribution graph, in which the survival rate obviously begins to increase, and listing the survival time of the intercepted segment of the expanded group, as shown in table 6.
TABLE 6 Life time of the extended group intercept segment (moon)
Step five, listing the characteristic values of all patients in the intercepted segment of the enlarged group, and numbering the characteristic codes of the patients, as shown in table 7.
The characteristic values of this group of patients are summarized below, in letters, and the patient characteristics represented by each letter are as follows: a small cell lung cancer, B non-small cell lung cancer, C cystic adenoid cancer, D before receiving radiotherapy, E before receiving chemotherapy, and F before receiving targeted drug therapy.
TABLE 7 eigenvalues of the extended group intercept segment
Calculating the occurrence frequency of each feature value, wherein the occurrence frequency of the feature code = the occurrence frequency of the feature code/the total number of patients in the enlarged group truncation section.
The occurrence frequency of the characteristic value B is 1, the occurrence frequency is the highest, and then the patients sensitive and effective to the intervention measure have the common characteristic code B, namely the patients sensitive and effective to the intervention measure which is treated by the western medicine A are all non-small cell lung cancer patients. The effective intervention measures of the Western medicine A for the non-small cell lung cancer patient are obtained through the algorithm.
The technical contents of the present invention are further described by way of examples only so as to facilitate understanding of the present invention for those skilled in the art, but the present invention is not limited thereto, and any technical extension or re-creation based on the present invention is protected by the present invention.
Claims (5)
1. A method for assessing the degree to which a treatment regimen effect is correlated with a specific patient, comprising the steps of: (1) dividing patients with the same disease into N groups, adopting different intervention treatment measures in each group, and respectively listing the survival time of each group of patients; (2) solving the survival rate of each group, and finding out a group with the highest survival rate at the M time point; (3) recording the intervention measures of the group with the highest survival rate, collecting or gathering more cases under the intervention measures to form an expanded group, listing the survival time of patients in the expanded group, and generating a survival distribution map of the expanded group; (4) intercepting the second half part of the survival rate in the survival distribution graph which obviously begins to increase, and listing the survival time of the interception section of the expansion group; (5) listing the characteristic values of all patients in the enlarged group intercepting segment, numbering the characteristic codes of the patients, calculating the occurrence frequency of each characteristic code, finding out the characteristic code with the occurrence frequency of 1 or the highest occurrence frequency, namely the characteristic code commonly owned by the patients or the code most frequently possessed by the patients, and then determining the optimal treatment method of the disease patient with the specific characteristic value.
2. The method of claim 1 for assessing the relevance of the effect of a treatment regimen to a particular patient, wherein: in the step (2), the survival rate is calculated by, in the case of M time points in total, the number of survival cases in the mth period = the number of initial cases in the mth period-the number of effective cases in the mth period, and the survival probability in the mth period = the number of survival cases in the mth period/the number of initial cases in the mth period, and then the survival rate in the mth period = the survival rate in the M-1 th period × the survival probability in the mth period.
3. The method of claim 1 for assessing the relevance of the effect of a treatment regimen to a particular patient, wherein: in the step (3), the survival distribution map of the expanded group is generated by using EXCEL with the patient number as the horizontal axis and the survival time of the survival case as the vertical axis.
4. The method of claim 1 for assessing the relevance of the effect of a treatment regimen to a particular patient, wherein: in step (5), the frequency of occurrence of the feature code = the number of occurrences of the feature code/total number of patients in the enlarged group truncation section.
5. The method of claim 1 for assessing the relevance of the effect of a treatment regimen to a particular patient, wherein: in step (5), a patient population sensitive to a specific intervention measure is selected, and the optimal treatment method for the patient is determined to be the specific intervention measure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058339.2A CN111223572B (en) | 2020-01-19 | 2020-01-19 | Method for evaluating degree of correlation between treatment scheme effect and specific patient population |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058339.2A CN111223572B (en) | 2020-01-19 | 2020-01-19 | Method for evaluating degree of correlation between treatment scheme effect and specific patient population |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111223572A true CN111223572A (en) | 2020-06-02 |
| CN111223572B CN111223572B (en) | 2022-06-24 |
Family
ID=70827200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010058339.2A Active CN111223572B (en) | 2020-01-19 | 2020-01-19 | Method for evaluating degree of correlation between treatment scheme effect and specific patient population |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223572B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325502A1 (en) * | 2012-06-05 | 2013-12-05 | Ari Robicsek | System and method for providing syndrome-specific, weighted-incidence treatment regimen recommendations |
| CN108573751A (en) * | 2017-03-08 | 2018-09-25 | 深圳大森智能科技有限公司 | The method of inspection and device of therapeutic effect |
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
-
2020
- 2020-01-19 CN CN202010058339.2A patent/CN111223572B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325502A1 (en) * | 2012-06-05 | 2013-12-05 | Ari Robicsek | System and method for providing syndrome-specific, weighted-incidence treatment regimen recommendations |
| CN108573751A (en) * | 2017-03-08 | 2018-09-25 | 深圳大森智能科技有限公司 | The method of inspection and device of therapeutic effect |
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111223572B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Maronna et al. | Multivariate clustering procedures with variable metrics | |
| US20130254202A1 (en) | Parallelization of synthetic events with genetic surprisal data representing a genetic sequence of an organism | |
| Rani et al. | Microarray cancer gene feature selection using spider monkey optimization algorithm and cancer classification using SVM | |
| Díaz et al. | Analysis of gene expression in the developing mouse retina | |
| Abreu et al. | Overall survival prediction for women breast cancer using ensemble methods and incomplete clinical data | |
| Torres-Espín et al. | Topological network analysis of patient similarity for precision management of acute blood pressure in spinal cord injury | |
| CN112768029A (en) | Combined medication recommendation device, method and medium based on single cell sequencing | |
| CN111223572B (en) | Method for evaluating degree of correlation between treatment scheme effect and specific patient population | |
| Bandyopadhyay et al. | Analyzing miRNA co-expression networks to explore TF-miRNA regulation | |
| Mak et al. | Indel seeds for homology search | |
| Daoud et al. | Epigenetic and genomic profiling of chordoid meningioma: implications for clinical management | |
| CN116917733A (en) | Multiple-set of learning methods for precision medicine | |
| Rajasekaran et al. | The efficient computation of position-specific match scores with the fast Fourier transform | |
| Pal et al. | Identifying relevant group of miRNAs in cancer using fuzzy mutual information | |
| Berger et al. | A classification tree approach for the modeling of competing risks in discrete time | |
| KR101394339B1 (en) | System and method for processing genome sequence in consideration of seed length | |
| CN115691751A (en) | Traditional Chinese medicine prescription screening method and system based on diagnosis and treatment experience and intelligent learning | |
| Gossmann et al. | A sparse regression method for group-wise feature selection with false discovery rate control | |
| de Armas et al. | K-mer Mapping and de Bruijn graphs: the case for velvet fragment assembly | |
| CN112820417A (en) | Transcriptomics-based prostate cancer drug combination prediction method | |
| CN109754843A (en) | A kind of method and device detecting genome small fragment insertion and deletion | |
| Ishida et al. | Fully incremental LCS computation | |
| CN111192639A (en) | Complex network-based tumor metastasis key gene retrieval method | |
| KR102594143B1 (en) | A method and System for sorting group being predicted to have remarkable anticancer treatment response using CA-125 before and after the first neoadjuvant chemotherapy, and for predicting whether interval debulking surgery in the sorted group | |
| Singh | A novel algorithm to preprocess cancerous gene expression dataset for efficient gene selection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |