CN115083613B - Digital twin-based clinical trial method, system, device and storage medium - Google Patents
Digital twin-based clinical trial method, system, device and storage medium Download PDFInfo
- Publication number
- CN115083613B CN115083613B CN202210575554.9A CN202210575554A CN115083613B CN 115083613 B CN115083613 B CN 115083613B CN 202210575554 A CN202210575554 A CN 202210575554A CN 115083613 B CN115083613 B CN 115083613B
- Authority
- CN
- China
- Prior art keywords
- index
- data
- test
- time
- subjects
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 152
- 238000011161 development Methods 0.000 claims description 46
- 238000012216 screening Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 12
- 239000003814 drug Substances 0.000 claims description 8
- 229940079593 drug Drugs 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000007717 exclusion Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000007115 recruitment Effects 0.000 abstract description 17
- 238000010998 test method Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 239000000902 placebo Substances 0.000 abstract description 5
- 229940068196 placebo Drugs 0.000 abstract description 5
- 230000008859 change Effects 0.000 abstract description 4
- 238000002474 experimental method Methods 0.000 abstract description 3
- 238000011282 treatment Methods 0.000 description 10
- 206010028980 Neoplasm Diseases 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 206010027476 Metastases Diseases 0.000 description 5
- 230000009401 metastasis Effects 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000004083 survival effect Effects 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 206010008479 Chest Pain Diseases 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 2
- 108010054147 Hemoglobins Proteins 0.000 description 2
- 208000000616 Hemoptysis Diseases 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000259 anti-tumor effect Effects 0.000 description 2
- 238000003556 assay Methods 0.000 description 2
- 208000006673 asthma Diseases 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 2
- 208000028659 discharge Diseases 0.000 description 2
- 210000004185 liver Anatomy 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 102000007644 Colony-Stimulating Factors Human genes 0.000 description 1
- 108010071942 Colony-Stimulating Factors Proteins 0.000 description 1
- 108010017080 Granulocyte Colony-Stimulating Factor Proteins 0.000 description 1
- 102000004269 Granulocyte Colony-Stimulating Factor Human genes 0.000 description 1
- 102000004457 Granulocyte-Macrophage Colony-Stimulating Factor Human genes 0.000 description 1
- 108010017213 Granulocyte-Macrophage Colony-Stimulating Factor Proteins 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000001185 bone marrow Anatomy 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 229940047120 colony stimulating factors Drugs 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 229940109239 creatinine Drugs 0.000 description 1
- 230000002380 cytological effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002565 electrocardiography Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 210000003714 granulocyte Anatomy 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 201000007270 liver cancer Diseases 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 229910001092 metal group alloy Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 210000000440 neutrophil Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000000849 parathyroid Effects 0.000 description 1
- 230000036314 physical performance Effects 0.000 description 1
- 239000013641 positive control Substances 0.000 description 1
- 238000009597 pregnancy test Methods 0.000 description 1
- 210000002966 serum Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000001685 thyroid gland Anatomy 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a digital twin-based clinical test method, a system, equipment and a storage medium, wherein the method is characterized in that data of potential subjects are mined, a digital twin model is built according to the data, then data of real subjects are input into the digital twin model, virtual subjects corresponding to the real subjects one by one can be created, and then the virtual subjects are used as a control group for clinical test. The method disclosed by the invention can change the unknown-unknown state of the subject recruitment in the prior art into the known-unknown state, so that the progress of clinical experiments is accelerated, the recruitment quantity of the subjects is reduced, and the recruitment efficiency of the subjects is greatly improved. On the other hand, the invention utilizes the digital twin technology, generates a virtual subject by analyzing and simulating real data, can replace a placebo control group, and solves the problems of high test cost, difficult recruitment of subjects, low test efficiency and the like.
Description
Technical Field
The invention relates to the technical field of clinical trials, in particular to a digital twin-based clinical trial method, digital twin-based clinical trial equipment and digital twin-based clinical trial storage medium.
Background
Currently, there are two main channels for subject recruitment during clinical trials: firstly, the patients are recruited by main researchers (such as department owners) of hospitals based on own stock groups, but the number of the recruited subjects in the mode is difficult to reach the test requirement; secondly, through social recruitment channels such as WeChat, microblog, advertisement posting and the like, but the mode lacks accurate grasp of target people, is developed based on a communication network completely, and has low efficiency.
During the clinical trial, the control group needs to be established and the balance between the experimental and control groups maintained is the primary means of eliminating confounding factors, so that during the trial, the subjects also need to be enrolled as either placebo or positive control groups.
However, the recruitment of the control group in the traditional test process generally needs to recruit real patients, which not only increases the recruitment quantity exponentially, but also increases the economic cost and labor cost when the number of real subjects to be recruited for one test project is large, such as advertising cost and labor for recruiting propaganda, and also slows down the test process and reduces the efficiency because the time required for recruiting enough patients is uncertain.
Disclosure of Invention
The embodiment of the invention provides a digital twinning-based clinical test method, a digital twinning-based clinical test system, digital twinning-based clinical test equipment and a digital twinning-based clinical test storage medium, which at least solve the problems that a sufficient number of clinical tests are difficult to recruit for test comparison and the cost of recruiting real patients is high.
In a first aspect, embodiments of the present invention provide a digital twinning-based clinical trial method, the method comprising:
Acquiring search conditions, matching the electronic medical record system of the hospital according to the search conditions, and screening potential subjects conforming to the search conditions;
Acquiring test indexes of the clinical test scheme, and carrying out data retrieval on all potential subjects according to the test indexes to acquire first index data;
Sequencing the first index data according to the time dimension, and performing data processing on the sequenced first index data to obtain a test data sequence;
Constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the common patient does not receive a test treatment scheme;
and acquiring second index data of the real subjects, and inputting the second index data of each real subject into the index development model to form a virtual subject, wherein the virtual subject is used as a control group of the clinical test scheme.
Further, the acquiring search conditions includes:
acquiring screening conditions of a clinical test scheme, and converting the screening conditions described by using characters into search conditions capable of being assembled in a structuring way; the screening conditions include inclusion conditions and exclusion conditions.
Further, the matching the electronic medical record system of the hospital according to the search condition, and screening out potential subjects meeting the search condition comprises:
Comparing the data of all the historical diagnosis patients in the electronic medical record system of the hospital according to the retrieval conditions, and matching the historical diagnosis patients meeting the retrieval conditions as the potential subjects; or alternatively
And monitoring the data in the electronic medical record system in real time, judging whether the data of the newly added patients meet the retrieval conditions or not when the newly added patients in the electronic medical record system, and automatically sending prompt information to researchers if the data of the newly added patients meet the retrieval conditions.
Further, the test indicators include one or more of a outcome indicator, a test indicator, and an assessment scale in the clinical trial regimen;
the acquiring the first index data includes:
and extracting medical record data of the potential subjects from the electronic medical record system, searching the medical record data according to the test indexes, and obtaining time and index values corresponding to each test index to form the first index data.
Further, the sorting the first index data according to the time dimension, and performing data processing on the sorted first index data to obtain a test data sequence, including:
Extracting the primary morbidity time, the primary visit time or the primary medication time of each potential subject from the first index data, and converting the primary morbidity time, the primary visit time or the primary medication time into the initial state time in a unified format;
Converting index values of the same test index in the first index data into values in a unified format;
time alignment is carried out on the first index data with unified formats according to the initial state time;
Constructing an index value of the same test index of all potential subjects into a discrete data point set of a time period-index value as a test data sequence according to a time interval, wherein the time interval is a time difference between a sampling time corresponding to each index value and the initial state time.
Further, the converting the index value of the same test index in the first index data into a value in a unified format includes:
If the result corresponding to the test index is described by adopting the text, converting the result described by adopting the text into a computable numerical value according to a preset conversion rule.
In some of these embodiments, the method further comprises:
inputting second index data of a real subject with preset proportion into the index development model, and obtaining a predictive index value;
acquiring a real index value of the real subjects in the preset proportion, wherein the real index value corresponds to the predicted index value time;
verifying the predictive index value according to the real index value, and obtaining a verification result;
and optimizing or adjusting the index development model according to the verification result.
In a second aspect, embodiments of the present invention provide a digital twinning-based clinical trial system comprising:
the data screening module is used for acquiring search conditions, searching and monitoring the electronic medical record system of the hospital according to the search conditions, and screening potential subjects conforming to the search conditions;
the data collection module is used for obtaining test indexes of the clinical test scheme, and carrying out data retrieval on all potential subjects according to the test indexes to obtain first index data; and is used for obtaining the second index data of the real subject;
the data processing module is used for carrying out data processing on the first index data and sequencing the subject data according to the time dimension to obtain a test data sequence;
the model construction module is used for constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the common patient does not receive a test treatment scheme; inputting second index data of each real subject into the index development model to form a virtual subject, wherein the virtual subject is used as a control group of the clinical test scheme.
In a third aspect, embodiments of the present invention provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform a digital twinning-based clinical trial method as described in any of the embodiments above.
In a third aspect, embodiments of the present invention provide a storage medium having a computer program stored therein, wherein the computer program is configured to perform the digital twin based clinical trial method of any of the embodiments described above when run.
Compared with the related art, the digital twin-based clinical test method provided by the embodiment of the invention realizes the mining and analysis of the existing data, namely mining the data of potential subjects, constructing a digital twin model according to the data, inputting the data of real subjects into the digital twin model, namely creating virtual subjects which are in one-to-one correspondence with the real subjects (experimental groups), and carrying out clinical test by taking the virtual subjects as control groups. The method disclosed by the invention can change the unknown-unknown state of the subject recruitment in the prior art into the known-unknown state, so that the progress of clinical experiments is accelerated, the recruitment quantity of the subjects is reduced, and the recruitment efficiency of the subjects is greatly improved. On the other hand, the invention utilizes the digital twin technology to generate the virtual subjects with the same basic characteristics as the real subjects by analyzing and simulating the real data, can replace a placebo control group, and solves the problems of difficulty in recruiting enough real patients, high recruitment cost, low test efficiency and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of a digital twinning-based clinical trial method according to one embodiment of the invention;
FIG. 2 is a plot of "time-value" discrete data points of ALT, AST in accordance with one embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the invention.
Detailed Description
The present invention will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present invention without making any inventive effort, are intended to fall within the scope of the present invention. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the invention can be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "a," "an," "the," and similar referents in the context of the invention are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in connection with the present invention are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means greater than or equal to two. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
An embodiment of the present invention provides a digital twin-based clinical trial method, the implementation of which includes the steps of:
step S1, acquiring search conditions, searching and monitoring the electronic medical record system of the hospital according to the search conditions, and screening potential subjects meeting the search conditions. In particular, prior to conducting a clinical trial, a clinical trial plan, i.e., a trial plan, is typically formulated by a researcher or project sponsor, and the trial plan is typically described in terms of text or form. Therefore, in the execution process of the test method, all data of the clinical test scheme are firstly obtained, then the screening conditions are extracted from the data, and after the screening conditions of the clinical test scheme are obtained, the screening conditions in the form of characters or tables are converted into search conditions capable of being assembled in a structuring mode. The invention generally adopts full text retrieval methods such as elastic search/Sonar and the like, and utilizes SQL sentences or semantic retrieval technology based on natural language processing to complete structured retrieval.
In this embodiment, the screening conditions include an inclusion condition (inclusion group condition) and an exclusion condition, wherein the inclusion condition is used to determine which historical patients can be treated as potential subjects; the exclusion criteria are used to determine which historical visit patients cannot be potential subjects. All the historical patients meeting the requirements can be screened out through the inclusion condition, and then the crowd incapable of carrying out clinical tests is removed from the historical patients meeting the inclusion condition according to the exclusion condition, so that potential subjects required by the invention are obtained, and the specific screening process is as follows.
Specifically, the data of all the historical patients in the electronic medical record system of the hospital can be compared according to the retrieval conditions, and the historical patients meeting the retrieval conditions are matched to be potential subjects. After all patient data in the system are compared, the retrieval conditions of the embodiment are used for continuously monitoring the data in the electronic medical record system in real time, when a patient for treatment is newly added in the electronic medical record system, a doctor fills in electronic medical record information which basically contains retrieval information required by a test, for example, gender/age generally appears in basic information of the patient; the admission/discharge diagnostic information is presented in a patient medical record or case; the imaging information appears in the examination report; the test information is presented in an assay report. Then judging whether the data of the newly added patient meets the retrieval conditions of the clinical test scheme or not through the retrieval conditions of the embodiment, if so, automatically sending prompt information to a researcher, and after receiving the prompt, the researcher can select whether to collect the medical record data of the patient according to the needs of the researcher and the judgment, and taking the patient as a potential subject.
And S2, acquiring test indexes of a clinical test scheme, and carrying out data retrieval on all potential subjects according to the test indexes to acquire first index data.
Specifically, after a sufficient number of potential subjects are retrieved, the data required for the present test protocol needs to be extracted from the medical record data of these potential subjects, and for example, the test indicators of the present embodiment include one or more of the outcome indicators (such as imaging progress, survival period, no-progress survival period, etc.), test indicators, and rating scales in the clinical test protocol. The test index of this example was also extracted from the clinical trial protocol.
After determining the test index, the data corresponding to each test index can be extracted from the medical record data of the potential subjects, and the data form first index data. Specifically, medical record data of a potential subject is extracted from the electronic medical record system, the medical record data is retrieved according to test indexes, and time and index values corresponding to each test index are obtained to form first index data.
And step S3, sorting the first index data according to the time dimension, and performing data processing on the sorted first index data to obtain a test data sequence.
Specifically, after the first index data is retrieved, the first index data is expanded in a time dimension to form discrete data points with an abscissa of "time-index value". Because the data time points of the potential subjects are all completely different, further processing, such as time alignment, is needed to be performed on the sorted first index data, more specifically, the primary morbidity time, the primary visit time or the primary medication time of each potential subject is extracted from the first index data, and is converted into the initial state time (set as t 0) of a unified format; then converting index values corresponding to each test index of all potential subjects into values in a unified format; and finally, performing time alignment on the first index data according to the first morbidity time, the first visit time or the first medication time of index values of the same test index of all potential subjects, and constructing a discrete data point set of a time period-index value as a test data sequence according to a time interval, wherein the time interval is a time difference between the sampling time corresponding to each index value and the initial state time. In another embodiment of the present invention, the first index data may be aligned first, and then the index values of the same test index in the first index data may be converted into values in a uniform format.
In another embodiment of the present invention, the first index data may be time aligned, and then the index values in different formats may be converted; or if the result corresponding to the test index is described by text, converting the result described by text into a computable numerical value according to a preset conversion rule, for example, converting the index value of the text description of 'tumor unchanged, tumor enlarged, tumor cell metastasis and the like' into the computable numerical grade types of 'level 1, level2 and level 3', and reconstructing the experimental data sequence of 'time period-index value' according to the converted index value.
And S4, constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the clinical test scheme treatment is not carried out, and generally, the relatively visual and simple data can directly adopt a time sequence algorithm, the relatively complex data can be simulated by adopting an unsupervised algorithm such as a Boltzmann machine, and the like, and the different algorithms can be adopted in combination with the actual condition for obtaining an accurate model for different data types. The index development model of the embodiment not only can embody the current physical state of the patient, but also can predict the physical state of the patient at a certain moment. In the embodiment of the invention, the test data sequence of each test index can construct an index development model, i.e. the number of index development models is the same as the number of items of the test index.
And S5, acquiring second index data of the real subjects, inputting the second index data of each real subject into an index development model to form a virtual subject, wherein the virtual subject is used as a control group of a clinical test scheme. After recruiting to the real subjects, it is also necessary to extract an index value corresponding to each test index from the medical record data of the real subjects, and then input the index value of each test index as t0 of the corresponding index development model, i.e. simulate virtual subjects, and each real subject simulate corresponding virtual subjects, so that the number of real subjects is the same as the number of virtual subjects in this embodiment.
The virtual subjects of the embodiments of the present invention were used as a control group for the clinical trial protocol, i.e., not treated according to the treatment method in the clinical trial protocol; whereas real subjects as experimental groups need to be treated according to the treatment regimen. During the treatment of a real subject, a researcher acquires real test data of the next stage (t 1) according to a specified time; meanwhile, as the simulation subject, the virtual subject also changes with time, and can output control test data (i.e. prediction data) at time t 1. And then, researchers can analyze and summarize according to the real test data and the control test data to obtain the treatment effect of the clinical test scheme.
In one embodiment of the invention, if the text of the screening condition of a certain clinical trial regimen is expressed as "unlimited in sex", the age is equal to or more than 18 years old; patients with solid malignant tumors identified by histological or cytological examination; three-level hospital radiographic evidence (e.g., X-ray examination, computed tomography CT, MRI, positron emission computed tomography PETCT) recorded over the first 3 months demonstrates at least 1 bone metastasis; … …; has enough organ function and meets the following laboratory examination standard (no transfusion is carried out in 2 weeks before the random, no colony stimulating factors such as G-CSF, GM-CSF and the like are used in 1 week): the neutrophil count is more than or equal to 1.5X109/L, the platelet is more than or equal to 75X 109/L, and the hemoglobin is more than or equal to 80g/L; ALT and AST are less than or equal to 3.0 xULN or less than or equal to 5.0 xULN (liver metastasis or primary liver cancer); serum creatinine clearance (CrCL) is not less than 30ml/min (calculated by the Cockcroft-Gault formula, appendix 1), if other antitumor treatments are combined, the bone marrow and liver and kidney functions need to reach other antitumor treatment standards; ECOG physical performance score 0-2; … …'
After the content of the screening conditions is obtained, firstly, disassembling the group entering conditions and the eliminating conditions in the clinical test scheme, and converting the text description into search conditions capable of being structurally assembled, wherein the search conditions are as follows: sex = male or female; age is more than or equal to 18; discharge diagnosis includes "malignancy"; the imaging description includes "bone metastasis"; … …; the count of the neutral granulocytes is more than or equal to 1.5X109/L AND platelet is more than or equal to 75X 109/L AND hemoglobin is more than or equal to 80g/L AND ALT is less than or equal to 3.0XULN AND AST is less than or equal to 3.0XULN; ECOG >0AND ECOG <2; … ….
After the screening conditions are structured and assembled, the data in the current hospital history patients are searched according to the search conditions, potential crowds meeting the conditions are matched, and the method adopted for searching the subjects according to the conditions can be full-text search such as elastic search/Sonar or structured search finished by utilizing SQL sentences or semantic search technology based on natural language processing. On the other hand, the retrieval condition of the potential subject population can monitor newly admitted patients in real time through the electronic medical record system, and the retrieval condition is automatically prompted when the patients meeting the condition appear. For example, when a new patient is admitted, the doctor fills in electronic medical record information, which basically includes the above search information: gender/age typically appears in the patient profile; diagnosis occurs in the patient medical record; imaging occurs in the exam report; the test information is presented in an assay report.
And then, extracting test indexes from the clinical test scheme, searching the subjects according to main ending indexes (such as imaging progress, life cycle, no-progress life cycle and the like), basic sign data, main inspection indexes or other evaluation scales in the test indexes, and collecting related data to form first index data. Such as: objective remission rate, which is the proportion of patients whose tumor volume is reduced to reach a predetermined value (x) and can maintain minimum time limit requirements; total survival (OS), which is the time from the onset of randomization to the death of the patient for various reasons; … …. These two test indicators were structured as "imaging exam report: tumor volume < x); total lifetime (OS): death date-date of first administration; … …% by weight of a metal alloy.
The retrieved subject data (first index data: base sign data, inspection test data, etc.) is then expanded in the time dimension to form (time-value) discrete data points, as shown in fig. 2, fig. 2 being specific values of ALT and AST in the first index data of potential subject a. The corresponding results of some test indexes need to be converted, the types of text descriptions (such as tumor enlargement and the like) are converted into numerical grade types which can be calculated, and discrete data points of time period-value are reconstructed. For example, the condition of a subject is described as: the patients before half month again show chest distress and asthma, the symptoms are obviously aggravated before, no fever and hemoptysis are caused, and the symptoms can be converted into: chest distress of "2", asthma of "2", fever of "0", hemoptysis of "0". Thus, the condition can be converted into a numerical value that can be analyzed.
In this example, since the data time points of the subjects are all completely different, this example sets the initial onset time or initial administration time of the potential subject to t0, and performs time alignment according to t0, and re-forms (period-value) data points at time intervals. Referring to table 1, table 2, assume that the first onset date of a is 5 months 20 days 2020; assuming that the first date of onset of another potential subject B is 2021, 2 months, 1 day, the ALT/AST data and time intervals for subjects a and B are shown in fig. 3. Table 1:
| Date | 2020-6-1 | 2020-6-20 | 2020-7-10 | 2020-7-30 | 2020-8-20 | 2020-9-10 | 2020-9-30 |
| ALT | 6.0 | 4.7 | 5.6 | 6.4 | 4.1 | 3.2 | 2.6 |
| AST | 5.5 | 6.3 | 8.2 | 6.6 | 5.3 | 4.1 | 3.2 |
| Space sky | 12 | 31 | 51 | 71 | 92 | 113 | 133 |
Table 2:
| Date | 2021-3-15 | 2021-5-2 | 2021-7-8 | 2021-8-20 | 2021-10-10 | 2021-12-3 |
| ALT | 6.0 | 4.7 | 5.6 | 4.1 | 3.2 | 2.6 |
| AST | 5.5 | 6.3 | 8.2 | 5.3 | 4.1 | 3.2 |
| Space sky | 42 | 90 | 157 | 200 | 251 | 305 |
After the first index data is ordered according to the time dimension, performing data processing on the ordered first index data to obtain a test data sequence (shown in table 3), wherein the test data sequence of table 3 is obtained by assembling the data of table 1 and table 2 based on time intervals.
Table 3:
| Date | 12 | 31 | 42 | 51 | 71 | 90 | 92 | 113 | 133 | 157 | 200 | 251 | 305 |
| ALT | 6.0 | 4.7 | 6.0 | 5.6 | 6.4 | 4.7 | 4.1 | 3.2 | 2.6 | 5.6 | 4.1 | 3.2 | 2.6 |
| AST | 5.5 | 6.3 | 5.5 | 8.2 | 6.6 | 6.3 | 5.3 | 4.1 | 3.2 | 8.2 | 5.3 | 4.1 | 3.2 |
Then, a time series prediction model is required to be constructed according to discrete data of all subject groups, and the data of the table 3 is taken as an example to construct an index development model in the embodiment, wherein two first index data of the table 3 are fitted mainly through an unsupervised algorithm such as a time series algorithm and a boltzmann machine, so that two time series data simulations (index development models) of ALT and AST are formed: y ALT＝f(xt0)、yAST＝f(xt0).
When the real subjects are recruited, screening period data (second index data) of the real subjects are collected first, the screening period data of the real subjects are input into a corresponding model as t0 data, and for example, ALT data are input into an ALT model.
In this example, various test examinations such as vital signs, physical examinations, 12-lead electrocardiography, ECOG score, oral examination, thyroid examination, parathyroid function examination, virology screening, hematology examination, blood biochemistry and electrolytes, urine examination, pregnancy test and coagulation function examination, imaging examination (tumor bone metastasis) and the like are performed on a real subject, and these test items are determined according to the requirements of clinical test protocols. During the screening period of the clinical trial, the real subjects will perform the above examination tests, and the examination results are the data of each index development model t0, and then the data of the next stage are predicted according to the model.
And then carrying out digital twin on the data obtained by the examination and inspection of 90% of real subjects, generating control data of a digital twin group, and generating data of virtual subjects in a large scale according to the requirements of clinical test projects. If the model is changed, the subsequent 10% of real subjects are taken as verification groups for verification and tuning, i.e. assuming a total of 100, 10 for the first verification group, 9 for the second verification group, 8 for the third verification group, … ….
In this embodiment, the data table is formed by predicting specific values of each test finger of the time of the next time period t1 through each index development model, as shown in table 4.
Table 4:
| Project | Screening period | Test period D1 | Test period D2 | Test period DN | |
| ... | ... | ||||
| ALT | 7.4 | =F (7.4)/such as=6.5 | ＝f(6.5) | ... | ＝f(XDN-1) |
| AST | 6.8 | =F 2 (6.8)/e.g. =6.3 | ＝f2(6.3) | ... | ＝f2(XDN-1) |
| ... |
In another embodiment of the present invention, the digital twin-based clinical trial method of the present embodiment further requires optimization of the index development model. Specifically, among all the enrolled real subjects, a certain proportion (preset proportion) of subjects was taken as a verification group to verify the index development model.
Assuming that the preset proportion is 10%, first second index data of the first 10% of real subjects are extracted, then the second index data are input into each index development model as initial values (at time t 0), and then the change of test indexes of the 10% of real subjects at time t1 (time in future) is predicted through the index development models, namely, a prediction index value is obtained. On the other hand, the actual index value of the 10% of the actual subjects corresponding to the predicted index value time, that is, after a certain period of time (corresponding to time t 1), is obtained, and the test examination is performed on the subjects, so that specific values of the respective test indexes of the actual subjects are obtained. Verifying the predicted index value according to the real index value, and obtaining a verification result; and finally, optimizing or adjusting the index development model according to the verification result.
In the embodiment of the invention, if the predicted index value of a certain test index is different from the real index value and the difference is greater than a first preset threshold value, an index development model of the certain test index needs to be reconstructed; if the predictive index value of a certain test index is different from the real index value and the difference is larger than a second preset threshold value, optimizing and adjusting the index development model according to the real index value, for example, only modifying a certain coefficient in the model; if the predicted index value of a certain test index is basically not different from the true index value (namely, the difference is smaller than a second preset threshold value), the index development model is unchanged.
For example, the first 10% of real subjects enrolled were used as the validation set to tune the individual index development model. The 10% of subjects in the validation group can obtain real test data because they actually participated in the clinical trial. A real subject of a validation group as 1 can obtain real data as in table 5 through a real test.
Table 5:
| Project | Screening period | Test period D1 | Test period D2 | Test period DN | |
| ... | ... | ||||
| ALT | 7.4 | 7.2 | 6.8 | ... | 4.8 |
| AST | 6.8 | 6.6 | 5.6 | ... | 4.5 |
| ... |
And then comparing and analyzing the real data in the table 5 with the data simulated in the table 4, calculating delta of the real data and the simulated data in each test period Dn, calculating sigma, and simultaneously obtaining the P value, the R value and the F1 of each model, thereby evaluating the model.
In clinical tests, the digital twin-based clinical test method realizes the mining and analysis of the existing data, namely mining the data of potential subjects, constructing a digital twin model according to the data, inputting the data of real subjects into the digital model, creating virtual subjects which are in one-to-one correspondence with the real subjects (experimental groups), and carrying out clinical tests by taking the virtual subjects as a control group. The method disclosed by the invention can change the unknown-unknown state of the subject recruitment in the prior art into the known-unknown state, so that the progress of clinical experiments is accelerated, the recruitment quantity of the subjects is reduced, and the recruitment efficiency of the subjects is greatly improved. On the other hand, the actual patients need to be recruited as placebo control group during the course of the traditional clinical trial, which not only doubles the number of recruitments, but also increases the cost of the trial. The invention utilizes the digital twin technology to generate the virtual subjects by analyzing and simulating the real data, can basically replace a placebo control group, and solves the problems of high test cost, difficult recruitment of subjects, low test efficiency and the like.
In one embodiment of the present invention, a digital twinning-based clinical trial system is provided that includes a data screening module, a data collection module, a data processing module, and a model building module.
The data screening module is used for acquiring the retrieval conditions, searching and monitoring the electronic medical record system of the hospital according to the retrieval conditions, and screening potential subjects meeting the retrieval conditions. And the data collection module is used for acquiring test indexes of the clinical test scheme, and carrying out data retrieval on all potential subjects according to the test indexes to acquire first index data. And is used for obtaining the second index data of the real subject; the data processing module is used for carrying out data processing on the first index data and sequencing the subject data according to the time dimension to obtain a test data sequence. The model construction module is used for constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the common patient does not receive the test treatment scheme; the second index data of each real subject is input into the index development model to form a virtual subject, and the virtual subject is used as a control group of a clinical test scheme.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
In addition, in combination with the digital twin-based clinical trial method in the above embodiment, the embodiment of the present invention may be implemented by providing a storage medium. The storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements any of the digital twinning-based clinical trial methods of the above embodiments.
An embodiment of the present invention further provides an electronic device, which may be a terminal. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a digital twinning-based clinical trial method. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the electronic equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
In one embodiment, fig. 3 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, an electronic device, which may be a server, is provided, and an internal structure diagram thereof may be as shown in fig. 3. The electronic device includes a processor, a network interface, an internal memory, and a non-volatile memory connected by an internal bus, where the non-volatile memory stores an operating system, computer programs, and a database. The processor is used for providing computing and control capability, the network interface is used for communicating with an external terminal through network connection, the internal memory is used for providing environment for the operation of an operating system and a computer program, the computer program is executed by the processor to realize a digital twin-based clinical test method, and the database is used for storing data.
It will be appreciated by those skilled in the art that the structure shown in fig. 3 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the electronic device to which the present inventive arrangements are applied, and that a particular electronic device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be understood by those skilled in the art that the technical features of the above-described embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above-described embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. A digital twinning-based clinical trial method, the method comprising:
Acquiring search conditions, matching the electronic medical record system of the hospital according to the search conditions, and screening potential subjects conforming to the search conditions;
Acquiring a preset test index, and performing data retrieval on all potential subjects according to the test index to acquire first index data;
Sequencing the first index data according to the time dimension, and performing data processing on the sequenced first index data to obtain a test data sequence;
Constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the common patient does not accept a clinical test scheme;
Acquiring second index data of a real subject, and inputting the second index data of each real subject into the index development model to form a virtual subject, wherein the virtual subject is used as a control group of the clinical test scheme;
Wherein the test index comprises one or more of a outcome index, a test index and an evaluation scale in the clinical test protocol;
the acquiring the first index data includes:
Extracting medical record data of the potential subjects from the electronic medical record system, searching the medical record data according to the test indexes, and obtaining time and index values corresponding to each test index to form the first index data;
the step of sorting the first index data according to the time dimension and performing data processing on the sorted first index data to obtain a test data sequence comprises the following steps:
Extracting the primary morbidity time, the primary visit time or the primary medication time of each potential subject from the first index data, and converting the primary morbidity time, the primary visit time or the primary medication time into the initial state time in a unified format;
Converting index values of the same test index in the first index data into values in a unified format;
time alignment is carried out on the first index data with unified formats according to the initial state time;
Constructing an index value of the same test index of all potential subjects into a discrete data point set of a time period-index value as a test data sequence according to a time interval, wherein the time interval is a time difference between a sampling time corresponding to each index value and the initial state time.
2. The method of claim 1, wherein the acquiring search criteria comprises:
acquiring screening conditions of a clinical test scheme, and converting the screening conditions described by using characters into search conditions capable of being assembled in a structuring way; the screening conditions include inclusion conditions and exclusion conditions.
3. The method according to claim 2, wherein the method further comprises:
and monitoring the data in the electronic medical record system in real time, judging whether the data of the newly added patients meet the retrieval conditions or not when the newly added patients in the electronic medical record system, and automatically sending prompt information to researchers if the data of the newly added patients meet the retrieval conditions.
4. The method of claim 1, wherein converting the index value of the same test index in the first index data into a value in a uniform format comprises:
If the result corresponding to the test index is described by adopting the text, converting the result described by adopting the text into a computable numerical value according to a preset conversion rule.
5. The method according to claim 1, wherein the method further comprises:
inputting second index data of a real subject with preset proportion into the index development model, and obtaining a predictive index value;
acquiring a real index value of the real subjects in the preset proportion, wherein the real index value corresponds to the predicted index value time;
verifying the predictive index value according to the real index value, and obtaining a verification result;
And optimizing the index development model according to the verification result.
6. A digital twinning-based clinical trial system, comprising:
The data screening module is used for acquiring search conditions, matching the electronic medical record system of the hospital according to the search conditions, and screening potential subjects conforming to the search conditions;
the data collection module is used for acquiring preset test indexes, and carrying out data retrieval on all potential subjects according to the test indexes to acquire first index data; and is used for obtaining the second index data of the real subject;
the data processing module is used for carrying out data processing on the first index data and sequencing the subject data according to the time dimension to obtain a test data sequence;
The model construction module is used for constructing an index development model of the common patient according to the test data sequence, wherein the index development model represents the physical development condition of the common patient under the condition that the common patient does not accept a clinical test scheme; inputting second index data of each real subject into the index development model to form a virtual subject, wherein the virtual subject is used as a control group of the clinical test scheme;
Wherein the test index comprises one or more of a outcome index, a test index and an evaluation scale in the clinical test protocol;
the acquiring the first index data includes:
Extracting medical record data of the potential subjects from the electronic medical record system, searching the medical record data according to the test indexes, and obtaining time and index values corresponding to each test index to form the first index data;
the step of sorting the first index data according to the time dimension and performing data processing on the sorted first index data to obtain a test data sequence comprises the following steps:
Extracting the primary morbidity time, the primary visit time or the primary medication time of each potential subject from the first index data, and converting the primary morbidity time, the primary visit time or the primary medication time into the initial state time in a unified format;
Converting index values of the same test index in the first index data into values in a unified format;
time alignment is carried out on the first index data with unified formats according to the initial state time;
Constructing an index value of the same test index of all potential subjects into a discrete data point set of a time period-index value as a test data sequence according to a time interval, wherein the time interval is a time difference between a sampling time corresponding to each index value and the initial state time.
7. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the digital twinning-based clinical trial method of any one of claims 1 to 5.
8. A storage medium having a computer program stored therein, wherein the computer program is configured to perform the digital twinning-based clinical trial method of any one of claims 1 to 5 when run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210575554.9A CN115083613B (en) | 2022-05-24 | 2022-05-24 | Digital twin-based clinical trial method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210575554.9A CN115083613B (en) | 2022-05-24 | 2022-05-24 | Digital twin-based clinical trial method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115083613A CN115083613A (en) | 2022-09-20 |
| CN115083613B true CN115083613B (en) | 2024-09-24 |
Family
ID=83248972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210575554.9A Active CN115083613B (en) | 2022-05-24 | 2022-05-24 | Digital twin-based clinical trial method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115083613B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428477A (en) * | 2018-03-30 | 2018-08-21 | 北京航空航天大学 | Construction method and cloud medical system based on the twinborn cloud surgery simulation platform of number |
| CN110415772A (en) * | 2019-07-31 | 2019-11-05 | 曹茂华 | Clinical test patient enrolment and case Rapid matching system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1844416A2 (en) * | 2005-02-04 | 2007-10-17 | Entelos, Inc. | Method for defining virtual patient populations |
| US20210225513A1 (en) * | 2020-01-22 | 2021-07-22 | XY.Health Inc. | Method to Create Digital Twins and use the Same for Causal Associations |
-
2022
- 2022-05-24 CN CN202210575554.9A patent/CN115083613B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428477A (en) * | 2018-03-30 | 2018-08-21 | 北京航空航天大学 | Construction method and cloud medical system based on the twinborn cloud surgery simulation platform of number |
| CN110415772A (en) * | 2019-07-31 | 2019-11-05 | 曹茂华 | Clinical test patient enrolment and case Rapid matching system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115083613A (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102165453B (en) | For merging the clinical system and method being calculated machine auxiliary diagnosis with characteristics of image | |
| US20060173663A1 (en) | Methods, system, and computer program products for developing and using predictive models for predicting a plurality of medical outcomes, for evaluating intervention strategies, and for simultaneously validating biomarker causality | |
| CN112309576A (en) | Colorectal cancer survival period prediction method based on deep learning CT (computed tomography) image omics | |
| CN112530535B (en) | Method and device for establishing disease-specific disease queue based on health medical big data | |
| CN114818720B (en) | Special disease data set construction method and device, electronic equipment and storage medium | |
| CN115099331A (en) | Auxiliary diagnosis system for malignant pleural effusion based on interpretable machine learning algorithm | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN113555077A (en) | Suspected infectious disease prediction method and device | |
| Benndorf et al. | Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon | |
| CN111524570B (en) | Ultrasonic follow-up patient screening method based on machine learning | |
| Bozhenko et al. | Application of data preprocessing in medical research | |
| CN109102845B (en) | Medical document auditing method, device, computer equipment and storage medium | |
| Beaulieu-Jones et al. | Learning contextual hierarchical structure of medical concepts with poincairé embeddings to clarify phenotypes | |
| CN115083613B (en) | Digital twin-based clinical trial method, system, device and storage medium | |
| CN111599427B (en) | Recommendation method and device for unified diagnosis, electronic equipment and storage medium | |
| RU2723674C1 (en) | Method for prediction of diagnosis based on data processing containing medical knowledge | |
| Schiappa et al. | Validation of RUBY for breast cancer knowledge extraction from a large French electronic medical record system | |
| Ieva et al. | Dynamic clustering of hazard functions: an application to disease progression in chronic heart failure | |
| Heryawan et al. | Deep learning and machine learning model comparison for diagnosis detection from medical records | |
| Al Shehri et al. | A smart pain management system using big data computing | |
| Wang et al. | Using Large Language Models for Efficient Cancer Registry Coding in the Real Hospital Setting: A Feasibility Study | |
| Kleiman et al. | High-throughput machine learning from electronic health records | |
| Elalfi et al. | A. Novel Intelligent System for Diagnosing some of Humans' Respiratory System Diseases | |
| CN119049731A (en) | Lung cancer patient screening method, device, terminal and medium based on deep learning model | |
| Naglah et al. | Correlation of glomerular histomorphometry changes with spatially resolved transcriptomic profiles in diabetic nephropathy |
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 |