Clinical test matching method, device, equipment, medium and product

Abstract

The invention relates to the technical field of auxiliary medical treatment, and discloses a clinical test matching method, device and equipment, a medium and a product. The medical record information is input into a preset general condition matching model for traversal, the general condition matching model comprises a first preset number of general judgment conditions, and judgment tags in one-to-one correspondence with the general judgment conditions are generated; according to the discrimination label, preliminarily screening test schemes conforming to the patient, and determining a preliminary test scheme; and inputting the medical record information and the preliminary test scheme into a preset specific condition matching model for secondary screening to obtain an ultimate test scheme after secondary screening. According to the method, the accuracy of test scheme matching can be effectively improved, errors are not prone to occurring, and the recruitment efficiency of clinical test subjects can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of auxiliary medical technology, and in particular to a clinical trial matching method, device, equipment, medium and product. Background Art

[0002] In clinical trials, recruiting clinical trial subjects is a key step in completing clinical trials. In order to complete specific clinical trial projects, the research team will find and screen suitable individuals or groups to participate in the research. Whether or not subjects who meet the trial requirements and the number of trials can be recruited is an important factor affecting the progress of the trial.

[0003] The current clinical recruitment methods mainly rely on manual work. Generally, the trial information is first published on a special clinical trial registration website to attract people who actively seek to participate in clinical trials. Then, relevant personnel will compare the relevant information of the registered clinical trial population to determine whether they meet the entry conditions. This clinical recruitment method is not only inefficient, but also relies on manual work and is prone to screening errors. Summary of the invention

[0004] In view of this, the present invention provides a clinical trial matching method, device, equipment, medium and product to solve the problem that the clinical recruitment method in the prior art not only has low recruitment efficiency but is also prone to errors.

[0005] In a first aspect, the present invention provides a clinical trial matching method, the method comprising:

[0006] Acquire the patient's medical record information, where the medical record information includes multiple medical record elements and medical record element contents corresponding to the medical record elements one by one;

[0007] Inputting the medical record information into a preset general condition matching model for traversal, the general condition matching model includes a first preset number of general judgment conditions, and generating a one-to-one corresponding discrimination label for each general judgment condition;

[0008] Based on the discriminant labels, preliminarily screen the trial plans that the patients are eligible for and determine the preliminary trial plans;

[0009] The medical record information and the preliminary test plan are input into a preset specific condition matching model for secondary screening to obtain the ultimate test plan after the secondary screening, wherein the specific condition matching model includes one-to-one corresponding inclusion conditions and exclusion conditions for each test plan.

[0010] In this embodiment, the patient's medical record information is preliminarily matched according to the pre-summarized general judgment conditions, and the preliminary test plan is first screened. Then the patient's medical record information is screened again according to the inclusion and exclusion conditions of each test plan, and finally the test plan suitable for the patient is determined. Through the powerful semantic understanding ability of the large model, the general judgment conditions of the test, all the inclusion and exclusion conditions of the clinical trial are included in the evaluation criteria, which can not only effectively improve the accuracy of the test plan matching and make it less prone to errors, but also effectively improve the efficiency of recruiting subjects for clinical trials.

[0011] In an optional embodiment, the patient's medical record information is obtained by the following steps:

[0012] Obtain images of the patient's medical records;

[0013] Perform text recognition on medical record images to obtain text information in the medical record images;

[0014] Inputting text information into a preset semantic model to determine the medical record element content corresponding to the preset medical record element in the semantic model;

[0015] The text information, the preset medical record elements and the medical record element contents corresponding to the preset medical record elements are converted into structured data to obtain the medical record information.

[0016] In this embodiment, several medical record images can be identified by OCR technology, and the OCR results can be sorted into a specific format by an algorithm. After the medical record images are sorted by the OCR algorithm and the data processing algorithm, the sorted basic text information is obtained. The sorted text information is then extracted by the semantic model for the patient's treatment line number, biomarkers, indications, disease stage, and ECOG, and converted into structured data medical record information together with the text information. For any medical record image, the patient's structured information can be quickly obtained within 10 seconds for subsequent matching, which can not only quickly extract information, but also enrich the medical record information, which is conducive to improving the accuracy of subsequent matching.

[0017] In an optional implementation, inputting text information into a preset semantic model further includes:

[0018] Output the words or sentences that do not conform to the general semantic information to obtain abnormal text, which is used for text correction.

[0019] In this embodiment, this method can intelligently identify misrecognized or missed characters, words, and sentences, solving the problem that the traditional OCR recognition accuracy rate is difficult to reach 100%. Users only need to check and proofread the individually picked characters, words, and sentences, saving time and efficiency.

[0020] In an optional embodiment, the preset medical record elements include at least one of the following: tumor type, number of treatment lines, stage, immunohistochemistry information and ECOG value.

[0021] In an optional embodiment, preliminarily screening the trial regimen that the patient is eligible for based on the discriminant label and determining the preliminary trial regimen includes:

[0022] When the discrimination label corresponding to the general judgment condition is in compliance, the test scheme corresponding to the general judgment condition is removed;

[0023] When the discrimination label corresponding to the general judgment condition is not in compliance or unknown, the test plan corresponding to the general judgment condition is retained.

[0024] In this embodiment, all clinical trial schemes in the clinical trial database are preliminarily screened by using pre-set general judgment conditions, so that potential trial schemes can be screened out effectively and quickly, which is beneficial for subsequent accurate screening.

[0025] In an optional implementation, the medical record information and the preliminary test plan are input into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening, including:

[0026] Determine a first test plan in the preliminary test plans, wherein the first test plan is any test plan in the preliminary test plans;

[0027] Determine the number of lines of treatment and immunohistochemistry information in the medical records;

[0028] Determine whether the number of treatment lines and immunohistochemistry information meet the requirements of clinical trials;

[0029] After confirming that the number of treatment lines and immunohistochemistry information meet the requirements of clinical trials, determine the inclusion and exclusion conditions corresponding to the first trial plan;

[0030] Based on the inclusion criteria, exclusion criteria and medical record information, determine whether the first trial plan meets the clinical trial requirements;

[0031] If the first trial plan meets the requirements of clinical trials, the first trial plan will be determined as the final trial plan.

[0032] In this embodiment, matching based on a large model can imitate the diagnosis and treatment level of senior doctors, judge the inclusion conditions or exclusion conditions that are difficult to judge, and effectively improve the accuracy of subject recruitment.

[0033] In a second aspect, the present invention provides a clinical trial matching device, the device comprising:

[0034] An acquisition module is used to acquire the patient's medical record information, where the medical record information includes multiple medical record elements and medical record element contents corresponding to the medical record elements one by one;

[0035] A marking module, used for inputting the medical record information into a preset general condition matching model for traversal, wherein the general condition matching model includes a first preset number of general judgment conditions, and generating a one-to-one corresponding discrimination label for each general judgment condition;

[0036] The preliminary screening module is used to preliminarily screen the test plans that the patients meet based on the discrimination labels and determine the preliminary test plans;

[0037] The final screening module inputs the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening. The specific condition matching model includes the one-to-one corresponding inclusion and exclusion conditions for each test plan.

[0038] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the clinical trial matching method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the clinical trial matching method of the first aspect or any corresponding embodiment thereof.

[0040] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the clinical trial matching method of the first aspect or any corresponding embodiment thereof.

[0041] It should be noted that the clinical trial matching device, computer device and computer readable storage medium provided by the present invention correspond to the above clinical trial matching method. Therefore, for the beneficial effects of the clinical trial matching device, computer device and computer readable storage medium, please refer to the description of the corresponding beneficial effects of the clinical trial matching method above, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 is a flow chart of a clinical trial matching method according to an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of medical record information according to an embodiment of the present invention;

[0045] Figure 3 is a schematic diagram of the contents in a medical record image according to an embodiment of the present invention;

[0046] Figure 4 is a structural block diagram of a clinical trial matching device according to an embodiment of the present invention;

[0047] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0049] In related technologies, digital methods for clinical trial recruitment mostly perform natural language processing on patient information and clinical trial information, extract key information from both ends, and then match and select matching patients. However, this process requires a high accuracy rate for the structured information extracted from patient information and clinical trial information, and it is difficult to accurately match some of the inclusion and exclusion conditions of clinical trials with patient information through matching. This matching method cannot match all inclusion and exclusion conditions, resulting in low matching accuracy and prone to errors.

[0050] According to an embodiment of the present invention, an embodiment of a clinical trial matching method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, a clinical trial matching method is provided, which can be executed by a server, a terminal, a mobile terminal, etc. Figure 1 is a flow chart of a clinical trial matching method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0052] Step S101, obtaining the patient's medical record information, where the medical record information includes a plurality of medical record elements and medical record element contents corresponding to the medical record elements one by one.

[0053] Reference Figure 2 As shown, it is a schematic diagram of medical record information, wherein ECOG (Eastern Cooperative Oncology Group, a scoring system used to evaluate the physical activity and daily living ability of cancer patients), age (age), biomarker (immunohistochemistry information), diagnosis (clinical diagnosis), disease (disease type), lot (number of treatment lines), patientId (patient number), reason (disease course), sex (gender), stage (staging), and symptoms (disease symptoms) are the medical record elements in this embodiment, and each medical record element corresponds to the medical record element content in this embodiment.

[0054] Step S102, inputting the medical record information into a preset general condition matching model for traversal, wherein the general condition matching model includes a first preset number of general judgment conditions, and generating a one-to-one corresponding discrimination label for each general judgment condition.

[0055] For the inclusion and exclusion conditions of clinical trials, most of the conditions have similar requirements. In this embodiment, 20 general judgment conditions are sorted out for these. The following shows some of the 20 general judgment conditions:

[0056] (1) Whether the patient has brain metastasis or brain disease, central nervous system metastasis, cerebrovascular disease or other brain abnormalities.

[0057] (2) Whether the patient has any active infectious diseases, such as hepatitis B, hepatitis C, AIDS, syphilis, tuberculosis, etc.

[0058] (3) Has the patient undergone major surgery, radiotherapy, chemotherapy, etc. within 4 weeks of the current time? Note that minor surgeries such as puncture surgery and hemorrhoid surgery do not fall into the category of major surgery.

[0059] (4) Whether the patient has any serious heart problems, including but not limited to angina pectoris, heart failure, arrhythmia, myocardial infarction, cardiac arrhythmia, etc.

[0060] In this regard, statistics were also collected on 1,414 public clinical trial data being conducted in a tertiary hospital, and it was found that the total number of clinical trial rules was 24,644. After excluding subjective and broad clinical conditions, there were a total of 18,408 clinical trial conditions. Among these conditions, only 919 clinical trial conditions were not mapped to the 20 general judgment conditions. According to statistics, there were an average of 12.36 conditions per test condition, 9.58 general judgment conditions, accounting for 78%, and 2.78 specific conditions, accounting for 22%. In other words, the 20 general judgment conditions that were sorted out cover the vast majority of test conditions. The above 919 clinical trial conditions that have not been mapped to general conditions can be further judged as special conditions, because special conditions are exclusion criteria for clinical trials, so in the judgment of special conditions, those that meet the conditions can also be screened out, and those that do not meet the exclusion criteria will be retained.

[0061] Combined with the patient information, the general condition matching model is used to judge whether the patient meets the 20 general conditions and give a discrimination label of "meeting", "not meeting" or "unknown". If a piece of information in the medical record information can match a general judgment condition, the general judgment condition is determined to be "meeting", otherwise it is "not meeting" or "unknown".

[0062] Step S103, preliminarily screening the test plans that the patient is eligible for based on the discrimination labels, and determining the preliminary test plan.

[0063] The following is an example. Suppose that clinical trial protocol 1 requires condition a in the inclusion criteria: "the patient has no brain metastasis within 4 weeks"; clinical trial protocol 2 requires condition b in the exclusion criteria: "the patient has brain metastasis within 4 weeks". Here, both conditions a and b will be mapped to the general judgment condition: "the patient has brain metastasis". Furthermore, if the patient has brain metastasis, the general judgment condition is met. At this time, clinical trial protocols 1 and 2 should be excluded.

[0064] That is, every time a general judgment condition is met, the corresponding test plan mapped to the general judgment condition will be screened out. Finally, the patient's medical record information, the preliminary test plan that has passed the screening, and other conditions not covered by the general judgment condition can be passed to the specific condition matching model together. Other conditions may include: broad clinical conditions, such as: ethical review, whether the patient has signed an informed consent form, etc.; subjective conditions, etc.

[0065] Step S104, input the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening. The specific condition matching model includes one-to-one corresponding inclusion conditions and exclusion conditions for each test plan.

[0066] The conditions that need to be judged for each trial scheme other than the general judgment conditions are called specific conditions. In the specific condition judgment process, it can be filtered in four steps, and the number of treatment lines, immunohistochemical information, inclusion conditions, and exclusion conditions can be judged in turn. The number of treatment lines and immunohistochemical information can be judged by rule matching in the specific condition matching model, and the inclusion conditions and exclusion conditions can be judged by semantic matching in the specific condition matching model. In each judgment link, a batch of trial schemes that are not suitable for patient enrollment will be screened out. After all four links are judged, the ultimate trial scheme suitable for patient enrollment will be retained.

[0067] In this embodiment, the patient's medical record information is preliminarily matched according to the pre-summarized general judgment conditions, and the preliminary test plan is first screened. Then the patient's medical record information is screened again according to the inclusion and exclusion conditions of each test plan, and finally the test plan suitable for the patient is determined. Through the powerful semantic understanding ability of the large model, the general judgment conditions of the test, all the inclusion and exclusion conditions of the clinical trial are included in the evaluation criteria, which can not only effectively improve the accuracy of the test plan matching and make it less prone to errors, but also effectively improve the efficiency of recruiting subjects for clinical trials.

[0068] In addition, in this embodiment, based on the patient's medical record information, a one-to-one match is performed on all clinical trial titles, objectives, inclusion information, and exclusion information in the clinical trial database, and clinical trials that meet the requirements for patient inclusion are returned. The degree of compliance can be presented as quantitative indicators, which is objective.

[0069] In some optional embodiments, the patient's medical record information is obtained by the following steps:

[0070] Step a1, obtain the patient's medical record image, the content of the medical record image refers to Figure 3 shown.

[0071] Step a2: perform text recognition on the medical record image to obtain the text information in the medical record image.

[0072] Step a3, inputting the text information into a preset semantic model, and determining the medical record element content corresponding to the preset medical record element in the semantic model.

[0073] Step a4, converting the text information, the preset medical record elements and the medical record element contents corresponding to the preset medical record elements into structured data to obtain medical record information.

[0074] In this embodiment, OCR (Optical Character Recognition) technology can be used to identify all text content in the input medical record image. Specifically, it can be detected whether there are keywords such as "current medical history", "personal history", "family history", "outpatient diagnosis" and so on in the text. If so, all the content from the starting position of the keyword to the starting position of the next keyword is extracted, and the position information of the text box returned by OCR is used to add spaces when splicing text for text boxes whose starting points differ by more than 8 in the horizontal and vertical axes, so as to ensure that the information is clear and easy to understand.

[0075] After extracting the valid information from the medical record image, the semantic model determines the medical record element content corresponding to the preset medical record element of the patient. In some optional embodiments, the preset medical record element includes at least one of the following: tumor type, number of treatment lines, stage, immunohistochemical information and ECOG value. The preset medical record element preferably includes all medical record elements of tumor type, number of treatment lines, stage, immunohistochemical information and ECOG value.

[0076] Then the text information, the preset medical record elements and the medical record element contents corresponding to the preset medical record elements are converted into structured data for subsequent processing.

[0077] In this embodiment, several medical record images can be identified by OCR technology, and the OCR results can be sorted into a specific format by an algorithm. After the medical record images are sorted by the OCR algorithm and the data processing algorithm, the sorted basic text information is obtained. The sorted text information is then extracted by the semantic model for the patient's treatment line number, biomarkers, indications, disease stage, and ECOG, and converted into structured data medical record information together with the text information. For any medical record image, the patient's structured information can be quickly obtained within 10 seconds for subsequent matching, which can not only quickly extract information, but also enrich the medical record information, which is conducive to improving the accuracy of subsequent matching.

[0078] In some optional implementations, inputting text information into a preset semantic model further includes:

[0079] Output the words or sentences that do not conform to the general semantic information to obtain abnormal text, which is used for text correction.

[0080] In this embodiment, while inputting the text information into the preset semantic model to extract the medical record element content corresponding to the preset medical record element, the words or sentences that do not conform to the general semantic information can also be recognized and returned to the user for secondary confirmation. This method can intelligently identify the misrecognized or missed words, words, and sentences, solving the problem that the traditional OCR recognition accuracy rate is difficult to reach 100%. The user only needs to check and proofread the single words, words, and sentences, saving time and efficiency.

[0081] In some optional embodiments, preliminarily screening the trial regimen that the patient is eligible for based on the discriminant label and determining the preliminary trial regimen includes:

[0082] When the determination label corresponding to the general determination condition is in compliance, the test scenario corresponding to the general determination condition is removed.

[0083] When the discrimination label corresponding to the general judgment condition is not in compliance or unknown, the test plan corresponding to the general judgment condition is retained.

[0084] In this embodiment, the discrimination labels can be divided into three labels: "compliant", "non-compliant" or "unknown". Among them, if a certain information in the medical record information successfully matches a certain general judgment condition, the general judgment condition is determined to be "compliant", and the test plan corresponding to the general judgment condition is removed, otherwise the test plan corresponding to the general judgment condition is retained.

[0085] In this embodiment, all clinical trial schemes in the clinical trial database are preliminarily screened by using pre-set general judgment conditions, so that potential trial schemes can be screened out effectively and quickly, which is beneficial for subsequent accurate screening.

[0086] In some optional implementations, step S104, that is, inputting the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening, includes:

[0087] Step S1041, determining a first test plan in the preliminary test plans, wherein the first test plan is any test plan in the preliminary test plans.

[0088] Step S1042, determining the number of treatment lines and immunohistochemistry information in the medical record information.

[0089] Step S1043, determining whether the number of treatment lines and immunohistochemistry information meet the requirements of clinical trials.

[0090] Step S1044, when it is determined that the number of treatment lines and immunohistochemistry information meet the requirements of the clinical trial, determine the inclusion conditions and exclusion conditions corresponding to the first trial scheme.

[0091] Step S1045, based on the inclusion conditions, exclusion conditions and medical record information, determine whether the first trial plan meets the clinical trial requirements.

[0092] Step S1046, when the first trial plan meets the clinical trial requirements, determine the first trial plan as the final trial plan.

[0093] Specifically, after the preliminary trial plan is determined according to the general condition matching model, we can further use the specific condition matching model to first determine whether the patient's number of treatment lines and immunohistochemistry information meet the requirements of the clinical trial through rule matching; after the judgment, the inclusion conditions of the preliminary trial plan and the patient's medical record information are used as the input of the model to obtain labels of whether each condition is met or not, and filter out trial plans that do not meet the requirements; finally, the exclusion conditions of the clinical trial that meets the requirements and the patient's medical record information are used as the input of the large model again to obtain labels of whether each condition is met or not, and finally the ultimate clinical trial plan that meets the patient's enrollment is obtained.

[0094] In this embodiment, the three pieces of information, namely, the patient's tumor type, the general judgment condition label, and whether a solid tumor is selected, can be used to screen out the test plans that need to be further judged according to the specific condition matching model. After all preliminary test plans have been judged, the ultimate test plans suitable for the final patient are obtained.

[0095] In this embodiment, matching based on a large model can imitate the diagnosis and treatment level of senior doctors, judge the inclusion conditions or exclusion conditions that are difficult to judge, and effectively improve the accuracy of subject recruitment.

[0096] In this embodiment, a clinical trial matching device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0097] This embodiment provides a clinical trial matching device, such as Figure 4 As shown, the device comprises:

[0098] An acquisition module 201 is used to acquire the patient's medical record information, where the medical record information includes a plurality of medical record elements and medical record element contents corresponding to the medical record elements one by one;

[0099] The marking module 202 is used to input the medical record information into a preset general condition matching model for traversal, wherein the general condition matching model includes a first preset number of general judgment conditions, and generates a one-to-one corresponding discrimination label for each general judgment condition;

[0100] A preliminary screening module 203 is used to preliminarily screen the test plans that the patient meets based on the discrimination labels and determine the preliminary test plan;

[0101] The final screening module 204 inputs the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening, wherein the specific condition matching model includes one-to-one corresponding inclusion conditions and exclusion conditions for each test plan.

[0102] In some optional embodiments, the device further comprises:

[0103] The conversion module is used to obtain the patient's medical record image; perform text recognition on the medical record image to obtain the text information in the medical record image; input the text information into a preset semantic model to determine the medical record element content corresponding to the preset medical record element in the semantic model; convert the text information, the preset medical record element, and the medical record element content corresponding to the preset medical record element into structured data to obtain medical record information. It is also used to output words or sentences that do not conform to the general semantic information to obtain abnormal text, which is used for text correction.

[0104] In some optional implementations, the preliminary screening module 203 includes:

[0105] A removal unit, used for removing the test scheme corresponding to the general judgment condition when the discrimination label corresponding to the general judgment condition is in compliance;

[0106] The retaining unit is used to retain the test scheme corresponding to the general judgment condition when the discrimination label corresponding to the general judgment condition is not met or unknown.

[0107] In some optional embodiments, the final screening module 204 includes:

[0108] The ultimate screening unit is used to determine the first test plan in the preliminary test plans, wherein the first test plan is any test plan in the preliminary test plans; determine the number of treatment lines and immunohistochemistry information in the medical record information; determine whether the number of treatment lines and immunohistochemistry information meet the requirements of the clinical trial; when it is determined that the number of treatment lines and immunohistochemistry information meet the requirements of the clinical trial, determine the inclusion conditions and exclusion conditions corresponding to the first test plan; based on the inclusion conditions, exclusion conditions and medical record information, determine whether the first test plan meets the requirements of the clinical trial; when the first test plan meets the requirements of the clinical trial, determine the first test plan as the ultimate test plan.

[0109] The clinical trial matching device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0110] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0111] The embodiment of the present invention also provides a computer device having the above Figure 4 Clinical trial matching device shown.

[0112] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0113] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0114] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0115] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0116] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0117] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0118] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0119] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0120] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A clinical trial matching method, It is characterized in that The method comprises: Acquire the patient's medical record information, wherein the medical record information includes a plurality of medical record elements and medical record element contents corresponding to the medical record elements one by one; Inputting the medical record information into a preset general condition matching model for traversal, wherein the general condition matching model includes a first preset number of general judgment conditions, and generating a discrimination label corresponding to each of the general judgment conditions; Preliminarily screening the trial plans that the patient is eligible for based on the discrimination labels and determining a preliminary trial plan; The medical record information and the preliminary test plan are input into a preset specific condition matching model for secondary screening to obtain a final test plan after the secondary screening, wherein the specific condition matching model includes one-to-one corresponding inclusion conditions and exclusion conditions for each test plan.

2. The method according to claim 1, It is characterized in that The patient's medical record information is obtained by the following steps: Obtain images of the patient's medical records; Performing text recognition on the medical record image to obtain text information in the medical record image; Inputting the text information into a preset semantic model to determine the medical record element content corresponding to the preset medical record element in the semantic model; The text information, the preset medical record element and the medical record element content corresponding to the preset medical record element are converted into structured data to obtain the medical record information.

3. The method according to claim 2, It is characterized in that The step of inputting the text information into a preset semantic model further includes: Words or sentences that do not conform to general semantic information are output to obtain abnormal text, which is used for text correction.

4. The method according to claim 2, It is characterized in that The preset medical record elements include at least one of the following: tumor type, number of treatment lines, stage, immunohistochemistry information and ECOG value.

5. The method according to claim 1, It is characterized in that The method of preliminarily screening the test regimen that the patient is eligible for based on the discrimination label and determining the preliminary test regimen includes: When the discrimination label corresponding to the general judgment condition is in compliance, removing the test scheme corresponding to the general judgment condition; When the discrimination label corresponding to the general judgment condition is not met or is unknown, the test scheme corresponding to the general judgment condition is retained.

6. The method according to claim 4, It is characterized in that The step of inputting the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the ultimate test plan after the secondary screening includes: Determine a first test plan in the preliminary test plans, wherein the first test plan is any test plan in the preliminary test plans; Determine the number of treatment lines and immunohistochemistry information in the medical record information; Determine whether the number of treatment lines and the immunohistochemistry information meet the requirements of clinical trials; When it is determined that the number of treatment lines and the immunohistochemistry information meet the requirements of the clinical trial, determining the inclusion conditions and exclusion conditions corresponding to the first trial protocol; Based on the inclusion conditions, the exclusion conditions, and the medical record information, determining whether the first trial protocol meets the clinical trial requirements; When the first trial plan meets the requirements of the clinical trial, the first trial plan is determined as the final trial plan.

7. A clinical trial matching device, It is characterized in that The device comprises: An acquisition module, used to acquire the patient's medical record information, wherein the medical record information includes a plurality of medical record elements and medical record element contents corresponding to the medical record elements one by one; A marking module, used for inputting the medical record information into a preset general condition matching model for traversal, wherein the general condition matching model includes a first preset number of general judgment conditions, and generating a discrimination label corresponding to each of the general judgment conditions; A preliminary screening module, used to preliminarily screen the test regimens that the patient is eligible for based on the discrimination labels, and determine the preliminary test regimen; The final screening module inputs the medical record information and the preliminary test plan into a preset specific condition matching model for secondary screening to obtain the final test plan after the secondary screening, wherein the specific condition matching model includes one-to-one corresponding inclusion conditions and exclusion conditions for each test plan.

8. A computer device, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the clinical trial matching method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the clinical trial matching method according to any one of claims 1 to 6.

10. A computer program product, It is characterized in that The method comprises computer instructions for causing a computer to execute the clinical trial matching method according to any one of claims 1 to 6.

Images