CN115878893A

CN115878893A - Clinical test item recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN115878893A
Application number: CN202211565843.7A
Authority: CN
Inventors: 刘荣兵; 王永明; 王育清
Original assignee: Zhejiang Taimei Medical Technology Co Ltd
Current assignee: Zhejiang Taimei Medical Technology Co Ltd
Priority date: 2022-12-07
Filing date: 2022-12-07
Publication date: 2023-03-31

Abstract

The application discloses a method and a device for recommending clinical test items, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an entry and exit standard text of a clinical test item, and extracting entry and exit standard data, wherein the entry and exit standard data comprises entities, attributes and entity-attribute corresponding relations; displaying the entry and discharge standard data to a rule configuration interface; generating an entry and exit rule in response to a rule configuration operation on a rule configuration interface; and recommending clinical test items for the subjects based on the matching results of the inclusion and exclusion rules and the disease course information of the subjects. The method can efficiently recommend suitable clinical test items for the testee, and improves the recommendation accuracy because of not depending on excessive manual comparison.

Description

Clinical test item recommendation method and device, electronic equipment and storage medium

Technical Field

The application belongs to the technical field of computer data processing, and particularly relates to a method and a device for recommending clinical test items, electronic equipment and a storage medium.

Background

In recent years, more and more patients actively seek out clinical trial items to participate, but in the face of the large number of trial items on the market, it is difficult for patients to judge which clinical trials can participate. Therefore, a professional responsible for clinical trial recruitment is born in the industry, and the recruiter sorts patient data after obtaining the authorization of the patient, compares the data with the inclusion standard of the clinical trial item, and judges whether the patient meets the requirement of the clinical trial item according to the comparison result. However, the patient data is of various types and large in data volume, so that the efficiency of recruiting a specialist to recommend a clinical test item to a patient is low, and the patient is prone to errors.

The information disclosed in this background section is only for enhancement of understanding of the general background of the application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

Disclosure of Invention

The application aims to provide a method for recommending clinical test items, which is used for solving the problems that the efficiency of recruiters for recommending the clinical test items is low and mistakes are easy to make.

In order to achieve the above object, the present application provides a method for recommending clinical trial items, the method comprising:

acquiring an entry and exit standard text of a clinical test item, and extracting entry and exit standard data, wherein the entry and exit standard data comprises entities, attributes and entity-attribute corresponding relations;

displaying the entry and discharge standard data to a rule configuration interface;

responding to the rule configuration operation of the rule configuration interface, and generating an entry and exit rule;

and recommending clinical test items for the subjects based on the matching results of the inclusion and exclusion rules and the disease course information of the subjects.

In one embodiment, displaying the inclusion and exclusion standard data to a rule configuration interface specifically includes:

based on the entity-attribute corresponding relation, assembling the entity and the attribute into a template rule by using a logical operation relation, and displaying the template rule to a rule configuration interface;

responding to the rule configuration operation of the rule configuration interface, and generating an entry and emission rule, wherein the entry and emission rule specifically comprises the following steps:

and responding to the rule configuration operation of the template rule in the rule configuration interface to generate the entry and discharge rule.

In one embodiment, the template rules include at least two rules;

and generating the entry and discharge rule in response to the configuration operation of the same intra-rule information and/or the logic operation relation among the rules in the template rule.

In an embodiment, the configuring operation of information in the same rule in the template rule specifically includes:

and carrying out configuration operation on entities and/or attributes and/or entity-attribute logical operation relations in the same rule in the template rule.

In one embodiment, the method further comprises:

displaying an entry matching field configuration interface, wherein the entry matching field configuration interface comprises subject data type information and associated field information corresponding to the rule field;

generating entry matching field information in response to configuration operations on the subject data type information and/or the associated field information in the entry matching field configuration interface;

and screening the disease course information of the subject from the data of the subject based on the inclusion matching field information.

In one embodiment, the method further comprises:

respectively configuring the entry and exit rules for at least two clinical test projects;

calculating the number of the disease course information of the subject passing through the inclusion rules in the at least two clinical test items so as to determine the matching degree of the subject and the at least two clinical test items;

and displaying the matching results of the subjects and the at least two clinical test items to a recommendation interface based on the matching degree.

In one embodiment, the ranking rules include a primary rule having a first weight, a reference rule having a second weight;

the method further comprises the following steps:

determining the inclusion rule of the clinical test item passed by the disease course information of the subject so as to calculate a main rule accumulated weight and a reference rule accumulated weight;

calculating whether the proportion of the reference rule accumulative weight to the main rule accumulative weight exceeds a preset value; if so,

determining the sum of the main rule accumulated weight and the reference rule accumulated weight as the matching degree of the subject and the clinical test item; if not, the user can not select the specific application,

and accumulating the weight of the main rule, and determining the matching degree of the subject and the clinical test item.

In one embodiment, the primary rule cumulative weight is expressed as:

wherein alpha is a first weight, S1 is the main rule number of clinical test items passed by the disease course information of the subject, and S is the inclusion rule number of the clinical test items;

the reference rule cumulative weight is expressed as:

wherein β is the second weight, S2 is the reference rule number of the clinical trial item through which the subject course information passes, and S is the inclusion rule number of the clinical trial item.

In one embodiment, the method further comprises:

identifying subject data from the subject profile text based on optical character recognition;

after the data of the subject is classified and deduplicated, the data value type in the data is identified so as to extract the disease course information of the subject.

In one embodiment, the method further comprises:

displaying the course information of the subject to a course information editing interface;

and matching the inclusion rules with the disease course information of the subject in response to the rule configuration operation of the rule configuration interface and/or the disease course information editing operation of the disease course information editing interface.

In one embodiment, the method further comprises:

and displaying the matching result of the inclusion rule and the disease course information of the subject to a recommendation interface, wherein the recommendation interface comprises the matching degree information and/or the matching result information of the subject and the clinical test items.

In one embodiment, the method further comprises:

and responding to the matching detail viewing operation of the recommendation interface, and displaying the matching results of the inclusion and exclusion rules and the corresponding disease course information of the testees one by one.

The present application further provides a clinical trial item recommendation device, including:

the extraction module is used for acquiring the entry and exit standard text of the clinical test item and extracting entry and exit standard data, wherein the entry and exit standard data comprises entities, attributes and entity-attribute corresponding relations;

the display module is used for displaying the entry and discharge standard data to a rule configuration interface;

the rule generating module is used for responding to the rule configuration operation of the rule configuration interface and generating an entry and exit rule;

and the recommending module is used for recommending clinical test items for the testee based on the matching result of the inclusion rule and the disease course information of the testee.

The present application further provides an electronic device, including:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method of recommending clinical trial items as described above.

The present application also provides a machine-readable storage medium having stored thereon executable instructions that, when executed, cause the machine to perform the method of recommending clinical trial items as described above.

Compared with the prior art, according to the recommendation method of the clinical test items, the inclusion standard data are extracted based on the inclusion standard text and are displayed to the rule configuration interface in a visual mode so that an operator can execute rule configuration operation and generate the inclusion rule, the appropriate clinical test items can be efficiently recommended for the testee based on the matching result of the inclusion rule and the course information of the testee, and the accuracy of recommending the clinical test items is improved because excessive manual comparison is not relied.

In another aspect, based on the subject data text uploaded by the subject, the subject data is identified through OCR, and the subject course information is extracted after classification and de-duplication, so that an operator can perform the course information editing operation on a visualized course information editing interface, thereby avoiding the deficiency or error of the course information of important subjects and further ensuring the accuracy of clinical test project recommendation.

Drawings

FIG. 1 is a schematic view of a scenario in which the recommendation method for clinical trial items is applied;

FIG. 2 is a flow chart of a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an inclusion criteria data interface in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a rule configuration interface in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 5 is a schematic diagram of an entry matching field configuration interface in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a disease course information editing interface in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 7 is a schematic diagram illustrating a triggering process of matching test items in a method for recommending clinical test items according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a recommendation interface in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 9 is a schematic diagram of a recommendation interface showing details of recommended items in a method for recommending clinical trial items according to an embodiment of the present application;

FIG. 10 is a block diagram of a clinical trial item recommender according to an embodiment of the present application;

FIG. 11 is a hardware block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application will be described in detail below with reference to embodiments shown in the drawings. The embodiments are not intended to limit the present disclosure, and structural, methodological, or functional changes made by those skilled in the art according to the embodiments are included in the scope of the present disclosure.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Moreover, the terms "comprises," "comprising," and "corresponding" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the application relates to a natural language processing technology, and the natural language processing is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like. In embodiments of the present application, it relates primarily to extracting entities from text, and relationships between entities.

Clinical trials of drugs refer to systematic study of drugs in humans to determine the efficacy and safety of drugs. The clinical test stages of the medicine are divided into phase I, phase II, phase III clinical tests and phase IV clinical tests. Phase I is mainly related to preliminary clinical pharmacology and human safety evaluation tests. Phase II is understood to be the initial stage of treatment, which is primarily related to the initial assessment of the therapeutic effect and safety of the drug on the patient with the target indication, and also provides the basis for the design of phase III clinical trial studies and the determination of the dosage regimen for administration. Stage III can be understood as a treatment effect confirmation stage, and is mainly used for further verifying the treatment effect and safety of the medicament on a target indication patient, evaluating the relationship between benefit and risk and finally providing a sufficient basis for the examination of a medicament registration application. The stage IV is mainly a clinical trial after the drug is marketed, and after the drug is marketed, the therapeutic effect and adverse reaction of the drug under a wide range of use conditions are continuously followed to evaluate the interest and risk relationship in use in general or special populations and to improve the administration dosage and the like.

The clinical trials of different drugs correspond to different inclusion and exclusion criteria information, and specifically, the inclusion and exclusion criteria information includes inclusion and exclusion criteria information, and the factor which is allowed to participate in the clinical drug trial is the "inclusion criterion" and the factor which is not allowed to participate in the clinical drug trial is the "exclusion criterion". It should be noted that the "inclusion criteria" and "exclusion criteria" are not used to reject the subject to participate in the clinical drug trial, but to determine whether the person is appropriate to participate in the clinical drug trial to ensure the safety of the trial.

Exemplary drug trial inclusion criteria information may include: age, sex, type and stage of disease, history of treatment, other disease conditions, etc., only those patients who meet the inclusion criteria of the drug trial may participate in the clinical trial. For example, the subjects are required to have a minimum age limit of 22 years, a maximum age limit of 80 years, sex men and women, and the patients are allowed to have hepatitis B if paclitaxel-containing drugs have not been used in previous treatment, but the hepatitis B dose cannot exceed 1800IU/mL and the like; if a certain "subject A" meets these inclusion criteria, it can be screened for participation in a clinical trial of the drug.

Referring to FIG. 1, a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application is shown. The implementation environment comprises a terminal and a server. The terminal and the server perform data communication through a communication network, optionally, the communication network may be a wired network or a wireless network, and the communication network may be at least one of a local area network, a metropolitan area network, and a wide area network.

The terminal may be an electronic device for providing a sequence of access images and/or displaying quality control images, and the electronic device may be a smart phone, a tablet computer, a personal computer, or the like. Fig. 1 illustrates a computer used by a medical staff and a subject as an example of a terminal.

After acquiring the entry and discharge standard text of the clinical test item, the terminal sends the entry and discharge standard text to the server, and the server extracts entry and discharge standard data in the entry and discharge standard text; meanwhile, the other terminal can also receive the data of the testee uploaded by the testee, send the data of the testee to the server, and process the data of the testee by the server to obtain the course information of the testee. Medical personnel can check the entry and discharge standard data extracted by the server through the terminal and carry out corresponding rule configuration operation so as to generate entry and discharge rules. The server can match the disease course information of the testees according to the inclusion and exclusion rules, and recommend clinical test items for the testees.

The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Illustratively, as shown in fig. 1, after receiving the inclusion standard text and the subject data sent by the terminal, the server inputs the inclusion standard text and the subject data into a device capable of operating a recommendation method for clinical test items, so as to obtain the clinical test items recommended for the subject.

In other possible embodiments, the device capable of operating the recommendation method for clinical test items may also be deployed at the terminal side, and the terminal directly recommends clinical test items for the subject and may report the recommended clinical test items to the server (avoiding the server directly acquiring the subject data).

Referring to fig. 2, an embodiment of a method for recommending clinical trial items according to the present application is described. In this embodiment, the method includes:

s11, acquiring the inclusion and exclusion standard text of the clinical test item, and extracting the inclusion and exclusion standard data.

The inclusion criteria data may include entities, attributes, and entity-attribute correspondences. Exemplarily, the entities may be, for example: demographic information such as age, gender, etc., disease, medication, laboratory tests, scale scores, etc.; the attributes may be, for example: value range, time constraint, etc.; there is a corresponding relationship between the entity and the attribute, for example, for the entity "age", the value range is "18 to 80 years old".

The extraction of the inclusion criterion data may be based on Natural Language Processing (NLP) technology. Information Extraction (IE) is the Extraction of specific event or factual Information from natural language text to help automatically classify, extract, and reconstruct mass content. Specifically, the extraction may be performed based on a pre-trained natural language processing model, such as roberta-tiny + crf, or Trie tree, and the extraction results of different extraction manners may be verified or combined with each other, so as to improve the reliability of the extraction of the inclusion and exclusion standard data.

Before the extraction of the typesetting standard data, the typesetting standard text can be preprocessed, for example, the typesetting standard text can be segmented based on text character spacing and text line spacing, and the typesetting standard text can be divided based on punctuation marks and other sentence marks.

Illustratively, a standard text character spacing and a standard text line spacing may be preset. When the distance between two characters is detected to be larger than the standard text character distance, the two characters can be considered to belong to two paragraph texts; alternatively, when the distance between two text lines is detected to be greater than the standard text line distance, the two text lines can be considered to belong to two paragraph texts. Of course, segmentation may also combine information of text character spacing and text line spacing simultaneously to enhance the reliability of paragraph segmentation. For each segmented text, it may be for ". "and"; and the like, segmenting sentences in the text to obtain segmentation results of each clause.

The extraction of the ranking standard data can structure the unstructured ranking standard text, and in this embodiment, the extracted ranking standard data can be further subjected to standardization processing to meet the requirement of logical operation in the post-ranking rule configuration. For example, the input non-standard words may be analyzed first, and then fuzzy matching processing may be performed based on the analysis result; alternatively, a variety of literal features (e.g., segmentation features, part-of-speech features, character features, context features, glossary features, etc.) are used to model the probability distribution of non-standard words to standard words; or, a recall ordering mode in a short text matching task is used, a round of recall based on similarity (realized based on the distance in a vector space) is performed through dense semantic feature vectors of the non-standard words and the standard words, the synonyms are added through priori knowledge, and finally a discriminant model is trained for fine ordering, so that the standard words corresponding to the non-standard words are determined.

Referring collectively to FIG. 3, an inclusion criteria data interface is shown that includes structured inclusion criteria data extracted from an inclusion criteria text. The user can further perform editing operation on the ranking standard data or supplement missing field data in the ranking standard data interface.

And S12, displaying the entry and discharge standard data to a rule configuration interface.

In this embodiment, the entity and the attribute may be assembled into the template rule based on the entity-attribute correspondence relationship in a logical operation relationship, and displayed to the rule configuration interface. The logical operation relationship here may be a comparison or operation including numerical, text, and time-class data, such as ">", "=", "<", "", "includes", "distance", and the like.

Referring to fig. 4, one example of a regular configuration interface includes several entities "disease/name", "disease/duration", "drug/name", "drug/start time", "drug/bolus" and so on. The entities and the corresponding attributes are associated through logical operation relations. For example, the "maximum value" of "disease/duration" is greater than "(logical operation relationship)" 180 days "(attribute), and the" maximum value "of" drug/start time "is greater than" (logical operation relationship) "180 days" (attribute).

And S13, responding to the rule configuration operation of the rule configuration interface, and generating an entry and emission rule.

The rule configuration operation on the rule configuration interface can be for entities, attributes, logical operation relations and the like in the rule configuration interface. In this embodiment, the rule configuration operation may be a rule configuration operation on a template rule in a rule configuration interface, that is, rule adjustment or rule confirmation is performed as required on the basis of the template rule.

For the clinical trial project, the inclusion rule usually consists of a plurality of rules, which correspond to the template rule, and may also include one or more rules. Taking the template rule including at least two rules as an example, the rule configuration operation on the template rule may be a configuration operation on information in the same rule or a configuration operation on a logical operation relationship between rules.

In this embodiment, the configuration operation on the information in the same rule may be a configuration operation on an entity, and/or an attribute, and/or an entity-attribute logical operation relationship in the same rule in the template rule.

Continuing with FIG. 4, exemplarily, for rule A in the template rules: "maximum of" disease/duration "greater than" 180 days ", rule B: "maximum of" drug/start time "up to" 180 days ", rule C: the minimum value of the drug/single dose is larger than 1IU/mL, if the rules A to C are confirmed without modification and other rules are not required to be added or deleted, the rule configuration operation of the precious rule can be directly confirmed. Or, if the attribute of the rule a in the template rule needs to be modified to "200 days", the rule a may be adjusted to have a "maximum value of" disease/duration "greater than" 200 days ", and the template rule may be confirmed. Or, if the attribute maximum value of the rule a in the template rule is further limited to "300 days", a new rule D may be added: the "maximum value" of "disease/duration" is less than "300 days" and the logical operational relationship between rule a and rule D is configured as "and".

The rule configuration operation on the template rule may be, for example, an operation performed by a medical worker on a terminal, and after the configuration is completed, a server connected to the terminal generates the entry and exit rule based on the rule configuration operation of the medical worker. The visualized arrangement rule configuration mode is combined with NLP extraction of the arrangement standard data, and higher accuracy and flexibility of arrangement rule configuration can be given on the basis of reducing arrangement rule configuration time.

And S14, recommending clinical test items for the testee based on the matching result of the inclusion and exclusion rules and the disease course information of the testee.

Subject course information may include basic information about the subject, such as: disease name, subtype, sex, age, patient identification number, level of daily activity, etc.; subject medical record information can also be included, such as: accepted treatment, accepted treatment time, accepted treatment medication, treatment assay information, disease condition information, and complication information, pathology reports, CT reports, imaging reports, disease diagnosis, and the like.

The course information of the subject can be obtained from the subject data, for example, in a specific application scenario, the subject can upload the subject data through the terminal, and the server extracts the course information of the subject from the subject data after obtaining the subject data.

In this embodiment, the subject data may be identified from the subject data text based on Optical Character Recognition (OCR), and after classifying and de-duplicating the subject data, the data value type therein may be identified to extract the subject disease course information.

The optical character recognition means that aiming at print characters, the print characters are converted into an electronic file through an optical imaging device, and characters in the electronic file are converted into a text format through recognition software. Subject data in the embodiments of the present application refers to electronic subject data reports that have been converted to be computer readable using an imaging device. Exemplarily, the imaging device may be a scanner, a digital camera, a mobile terminal with a camera function, etc., and the format of the subject data may be PDF, JPG, PNG, BMP, etc.

The subject data uploaded by the subject can be of various types, such as discharge records, admission records, immunohistochemical reports and the like, and after OCR recognition, the obtained subject data can be classified and deduplicated, and the data value type can be judged. In this embodiment, for example, the subject data may be divided into text, numbers, time, etc. so as to extract the course information of the subject in the subject data by using NLP.

Exemplarily, the optical character recognition here may be based on the CRNN network model; the course information of the subject can also be extracted based on roberta-tiny + crf, or Trie tree, etc.

In some embodiments, given the diversity of subject profiles, certain fields in certain types of subject profiles are not expected to match inclusion rules as subject course information. For example, the usual imaging examinations for breast disease include ultrasound and molybdenum targets, and both of these examinations may present BI-RADS ranking results on the report. However, in some rule-of-inclusion matching, it is expected that only BI-RADS ranking results in the molybdenum target examination report will be determined as subject course information, given the relative reliability of the molybdenum target examination.

In such an embodiment, in conjunction with fig. 5, the server may further present an inclusion matching field configuration interface including subject profile type information and associated field information corresponding to the rule fields. The user can carry out configuration operation on the type information and/or the associated field information of the subject data in the entry matching field configuration interface. In response to the above configuration operation by the user, the server may generate ranking matching field information and screen the subject's course information from the subject data based on the ranking matching field information.

For example, for the rule field "disease", the corresponding data type is "medical record-discharge record", "medical record-outpatient record", "medical record-admission record", "medical record-medical case", … … "medical record detection-genetic detection report", and the corresponding associated field is "disease-name", "disease-type", "patient information table-self-describing disease name", and "patient information table-AI analysis disease name". Here, the rule field "disease" and the corresponding information of the configured data type and the associated field can be regarded as "inclusion matching field information", which restricts the source of the course information of the subject, so that the recommendation of the clinical test item is more reliable.

The matching result of the disease course information of the subject and the inclusion rule of a certain clinical test item can be a matching degree comprising the disease course information and the certain clinical test item, or a conclusion whether the subject can be selected in the clinical test item is directly given according to a preset standard threshold value of the matching degree. For example, when the threshold of the matching degree criterion is set to 90%, that is, the matching degree between the disease course information of the subject and the inclusion rule is greater than or equal to 90%, it is determined that the subject can be selected in the clinical trial item, otherwise, the subject is determined to be undetermined or can not be selected in the clinical trial item. Or, if the disease course information of the subject meets a certain exclusion standard information in the inclusion rule, the subject can be directly judged not to be selected into the corresponding clinical test item.

In one embodiment, the degree of matching of the subject to the clinical trial may be determined by the number of inclusion rules in the clinical trial based on the subject's course information. For example, if a clinical trial item includes 10 entry rules and the course information of the subject passes through 6 entry rules, the matching degree between the subject and the clinical trial item is 60%.

In another embodiment, the ranking rules may further include a primary rule and a reference rule, and the primary rule is preset to have a first weight, and the reference rule is preset to have a second weight. And calculating the accumulated weight of the main rule and the accumulated weight of the reference rule by determining the inclusion rule of the clinical test item passed by the disease course information of the subject.

The reference rules in the inclusion rules may be, for example, some indicators that are not stable over time or that are not primarily considered by the current clinical trial project. For example, in some non-tumor clinical trial groups, the patient's ECOG score may only need to be taken as a reference; for another example, for clinical trials of stage I tumors, the primary objective is to assess safety, whether there is a measurable lesion may be used as a reference rather than an essential indicator.

In this embodiment, the second weight of the reference rule may be set to be smaller than the first weight of the main rule, and whether the ratio of the reference rule cumulative weight to the main rule cumulative weight exceeds a preset value is calculated, if so, the sum of the main rule cumulative weight and the reference rule cumulative weight is determined as the matching degree of the subject and the clinical test item; if not, directly accumulating the weight of the main rule, and determining the weight as the matching degree of the subject and the clinical test item. Thus, in the calculation of the degree of matching between the subject and the clinical trial items, the main rule and the reference rule are comprehensively considered, the influence of the reference rule is regulated and controlled by the preset weight, and the degree of matching is calculated by taking into account the influence of the reference rule only when the cumulative influence of the reference rule exceeds a certain degree.

Exemplarily, the primary rule cumulative weight is expressed as:

wherein alpha is a first weight, S1 is the main rule number of clinical test items passed by the course information of the subject, and S is the inclusion rule number of the clinical test items;

the reference rule cumulative weight is expressed as:

The disease course information of the subject meets the inclusion and exclusion rules of a certain clinical test item, namely the condition representing the subject meets the inclusion and exclusion requirements of the clinical test item. In some application scenarios, the enrollment invitation may also be sent directly to the enrollment-eligible subject and await subject confirmation.

With reference to fig. 6, in this embodiment, after the subject uploads the subject data text through the terminal, the server may further display the generated subject course information to the course information editing interface, and the subject may edit the course information editing interface on the corresponding terminal.

The visual disease course information editing interface facing the subject is beneficial for the subject to confirm the accuracy and the integrity of the disease course information of the subject. Similarly, the editing may be confirmation or adjustment of the course information of the subject in the course information editing interface by the subject.

Illustratively, in the course information editing interface, the data value of the subject's immunohistochemistry index "Ki-67 (degree of tumor cell proliferation)" is "60%", and the subject may modify the data value, for example, to "55%"; meanwhile, the immunohistochemical indexes 'ER (estrogen receptor)' and 'PR (progestogen receptor)' of the subject are absent in the course information editing interface, and the subject can supplement the corresponding immunohistochemical indexes 'ER' to be 'negative' and 'PR' to be 'negative'.

For some neoplastic diseases, the immunohistochemical indicators described above indicate that the subject may not benefit from the corresponding endocrine treatment. Thus, the lack of this immunohistochemical index would result in the loss of critical subject course information, thereby rendering the recommendation of clinical trial items unreliable. The adverse possibility can be reduced by displaying the course information of the subject to a course information editing interface and confirming or improving the course information by the subject or other credible personnel.

With reference to fig. 7, in the above embodiment of the present application, the server may match the inclusion rule with the subject course information in response to the rule configuration operation on the rule configuration interface and/or the course information editing operation on the course information editing interface. And the server can also display the matching result of the inclusion rule and the disease course information of the subject to a recommendation interface. Wherein, the recommendation interface comprises the matching degree information and/or the matching result information of the subject and the clinical test items.

In some other application scenarios, the above-mentioned inclusion and exclusion rules may also be issued to a plurality of clinical trial groups, and these clinical trial groups may respectively include a plurality of pieces of collected subject course information. After the inclusion and exclusion rule is issued to the clinical trial group, the information of the disease course of a plurality of subjects can be matched with the inclusion and exclusion rule respectively, so that suitable subjects can be screened out.

In the scenario where subjects self-screen clinical trial programs, more than one clinical trial program may be currently recruited. Correspondingly, the inclusion rule can be configured for at least two clinical test items, and the number of the subject disease course information passing through the inclusion rule in the at least two clinical test items is calculated to determine the matching degree of the subject and the at least two clinical test items. In this scenario, the matching results of the subject and the at least two clinical trial items may be presented to the recommendation interface based on the matching degree.

Referring to FIG. 8 in conjunction, in one illustrated recommendation interface, three recommendation items are presented. According to the sequence of the matching degrees from high to low, the matching degrees of the subject and the three recommended items are respectively '100%', '33%', and '0', and the corresponding matching results are 'selected', 'undetermined', and 'undetermined'. For a recommended item with a matching degree of "100%", the subject may be invited to directly access the group; and for each recommended item, the matching detail checking operation can be carried out on the recommendation interface.

With reference to fig. 9, the server may view the matching details of the recommended interface, and display the matching results of the inclusion and exclusion rules and the corresponding subject course information item by item. For example, after performing a matching detail checking operation on the recommended item with the matching degree of "33%", a rule (1) is exhibited on the recommendation interface: "disease/treatment medication" includes any of: amoxicillin, penicillin ", rule (2): "is equal to any one of: image [ includes any of: punctate calcification of coronary arteries [ n ]: 10 days; h ]; or any one of: left lung portal enlargement lymph node ", rule (3): "disease/said data equals either: discharge records, outpatient records, admission records, solid tumor pathology reports, genetic testing reports (biopsy), immunohistochemistry, biopsy (stained color), biopsy (unstained white), hematologic disease case reports, hematology, liver function, stomach function, coagulation function, pancreatic function (lipase, amylase), urinary routine, fecal routine, blood pregnancy, infectious disease examination, thyroid function, glycated hemoglobin, electrolyte repertoire, fasting plasma glucose [ disease, name do not: cold; "A", "B", "C", and "C". The subject course information corresponding to rule (1) is "disease/name: stomach cancer; disease/therapeutic drugs: amoxicillin ", in accordance with rule (1); the disease course information of the subject corresponding to the rule (2) is 'missing', and the subject does not accord with the rule (2); the subject course information corresponding to rule (3) is "disease/name: gastric cancer; disease/therapeutic drugs: amoxicillin ", does not comply with rule (3), i.e. the subject's course information complies with 1 out of 3 rules.

Referring to fig. 10, an embodiment of the apparatus for recommending clinical trial items according to the present application will be described. In this embodiment, the recommendation device for clinical trial items includes an extraction module 21, a presentation module 22, a rule generation module 23, and a recommendation module 24.

The extraction module 21 is configured to obtain an entry and exit standard text of a clinical test item, and extract entry and exit standard data, where the entry and exit standard data includes an entity, an attribute, and an entity-attribute correspondence; the display module 22 is configured to display the entry and exit standard data to a rule configuration interface; the rule generating module 23 is configured to generate an entry and exit rule in response to a rule configuration operation on the rule configuration interface; the recommending module 24 is used for recommending clinical test items for the subject based on the matching result of the inclusion rule and the disease course information of the subject.

In an embodiment, the display module 22 is specifically configured to assemble the entities and the attributes into a template rule according to a logical operation relationship based on the entity-attribute correspondence relationship, and display the template rule to a rule configuration interface; the rule generating module 23 is specifically configured to generate an entry and exit rule in response to a rule configuration operation on a template rule in the rule configuration interface.

In one embodiment, the template rules include at least two rules; the rule generating module 23 is specifically configured to generate an entry and exit rule in response to a configuration operation on the same intra-rule information and/or a logical operation relationship between rules in the template rule.

In an embodiment, the configuring operation on the information in the same rule in the template rule specifically includes configuring operation on an entity and/or an attribute and/or an entity-attribute logical operation relationship in the same rule in the template rule.

In one embodiment, the recommendation apparatus for clinical trial items further comprises a recognition module 25 for recognizing the subject data from the subject profile text based on optical character recognition; after the data classification and the de-duplication of the subjects, the data value types in the data classification and the de-duplication are identified so as to extract the disease course information of the subjects.

In one embodiment, the display module 22 is further configured to display the course information of the subject to a course information editing interface; the recommending module 24 is further configured to match the inclusion rule with the subject course information in response to a rule configuration operation on the rule configuration interface and/or a course information editing operation on the course information editing interface.

In one embodiment, the presentation module 22 is further configured to present the matching result of the inclusion rule and the disease course information of the subject to a recommendation interface, where the recommendation interface includes the matching degree information and/or the matching result information of the subject and the clinical test item.

In one embodiment, the display module 22 is further configured to display the matching result of the inclusion rule and the corresponding subject course information item by item in response to the matching detail viewing operation on the recommendation interface.

The recommendation method of the clinical trial items according to the embodiment of the present specification is described above with reference to fig. 1 to 9. The details mentioned in the above description of the method embodiments are also applicable to the clinical trial item recommendation apparatus of the embodiments of the present specification. The above recommendation apparatus for clinical trial items may be implemented by hardware, or may be implemented by software, or a combination of hardware and software.

Fig. 11 shows a hardware configuration diagram of an electronic device according to an embodiment of the present specification. As shown in fig. 11, the electronic device 30 may include at least one processor 31, a storage 32 (e.g., a non-volatile storage), a memory 33, and a communication interface 34, and the at least one processor 31, the storage 32, the memory 33, and the communication interface 34 are connected together via an internal bus 35. The at least one processor 31 executes at least one computer readable instruction stored or encoded in the memory 32.

It should be understood that the computer-executable instructions stored in the memory 32, when executed, cause the at least one processor 31 to perform the various operations and functions described above in connection with fig. 1-7 in the various embodiments of the present description.

In embodiments of the present description, the electronic device 30 may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile electronic devices, smart phones, tablet computers, cellular phones, personal Digital Assistants (PDAs), handsets, messaging devices, wearable electronic devices, consumer electronic devices, and the like.

According to one embodiment, a program product, such as a machine-readable medium, is provided. A machine-readable medium may have instructions (i.e., elements described above as being implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 1-7 in the various embodiments of the present specification. Specifically, a system or apparatus may be provided which is provided with a readable storage medium on which software program code implementing the functions of any of the above embodiments is stored, and causes a computer or processor of the system or apparatus to read out and execute instructions stored in the readable storage medium.

In this case, the program code itself read from the readable medium can realize the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of this specification.

Examples of the readable storage medium include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or from the cloud via a communications network.

It will be understood by those skilled in the art that various changes and modifications may be made in the above-disclosed embodiments without departing from the spirit of the invention. Accordingly, the scope of the present description should be limited only by the attached claims.

It should be noted that not all steps and units in the above flows and system structure diagrams are necessary, and some steps or units may be omitted according to actual needs. The execution order of the steps is not fixed, and can be determined as required. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients separately, or some units may be implemented by some components in multiple independent devices together.

In the above embodiments, the hardware units or modules may be implemented mechanically or electrically. For example, a hardware unit, module or processor may comprise permanently dedicated circuitry or logic (such as a dedicated processor, FPGA or ASIC) to perform the corresponding operations. The hardware elements or processors may also comprise programmable logic or circuitry (e.g., a general-purpose processor or other programmable processor) that may be temporarily configured by software to perform corresponding operations. The specific implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.

The detailed description set forth above in connection with the appended drawings describes exemplary embodiments but does not represent all embodiments that may be practiced or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for recommending clinical trial items, the method comprising:

2. The method for recommending clinical trial items according to claim 1, wherein presenting the inclusion criteria data to a rule configuration interface specifically comprises:

responding to the rule configuration operation of the rule configuration interface, and generating an entry and exclusion rule, specifically comprising:

3. The method of recommending clinical trial items according to claim 2, wherein said template rule comprises at least two rules;

4. The method for recommending clinical trial items according to claim 3, wherein the operation of configuring the information in the same rule in the template rule specifically includes:

5. The method for recommending clinical trial items according to claim 1, further comprising:

6. The method for recommending clinical trial items according to claim 1, further comprising:

7. The method of recommending clinical trial items according to claim 1, wherein said inclusion rule comprises a primary rule having a first weight, a reference rule having a second weight;

the method further comprises the following steps:

8. The method of recommending clinical trial items according to claim 1, wherein said primary rule cumulative weight is expressed as:

the reference rule cumulative weight is expressed as:

wherein β is a second weight, S2 is a reference rule number of a clinical trial item through which the subject course information passes, and S is an inclusion rule number of the clinical trial item.

9. An apparatus for recommending clinical trial items, comprising:

10. An electronic device, comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of recommending clinical trial items according to any of claims 1 to 8.

11. A machine readable storage medium storing executable instructions that when executed cause the machine to perform a method of recommending clinical trial items as claimed in any one of claims 1 to 8.