Diagnostic assessment methods, devices, electronic equipment, and computer-readable storage media

By generating electronic medical record reports and evaluating candidate treatment plans in conjunction with treatment guidelines, the problem of lack of guidance for young doctors in second- and third-tier cities has been solved, achieving the effect of rapidly improving treatment skills and the accuracy of treatment plans.

CN115631848BActive Publication Date: 2026-11-17ZHEJIANG HAIXINZHIHUI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211290314.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-20
Publication Date
2026-11-17
Estimated Expiration
2042-10-20

AI Technical Summary

Technical Problem

Young doctors in second- and third-tier cities lack high-level expert guidance and the latest treatment technologies, making it difficult for them to quickly accumulate clinical experience, resulting in slow growth in their medical skills.

Method used

Based on the medical record data of different types of patients, electronic medical record reports are automatically generated, and candidate treatment plans are generated in conjunction with the Chinese Society of Clinical Oncology's treatment guidelines, and evaluated with reference to the experience of top experts in the industry.

Benefits of technology

To improve the treatment skills and accuracy of treatment plans of young doctors, precise electronic medical record reports are generated by simulating real medical record data, thereby rapidly enhancing doctors' diagnostic and treatment skills.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115631848B_ABST
    Figure CN115631848B_ABST
Patent Text Reader

Abstract

This application provides a diagnostic assessment method, apparatus, electronic device, and computer-readable storage medium. The method includes: acquiring key information of a desired electronic medical record (EMR) report; matching an EMR report template based on the key information; determining a target EMR report based on the matched EMR report template and medical record information; receiving candidate treatment plans determined based on the target EMR report; and evaluating the candidate treatment plans based on the differences between the candidate treatment plans and the target treatment plan corresponding to the target EMR report. The diagnostic assessment method provided in this application can automatically generate EMR reports based on medical record data of different types of patients; determine target treatment plans with different recommendation levels for the EMR reports; and evaluate the candidate treatment plans after obtaining them.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of medical decision support technology, and in particular to a diagnostic assessment method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, in the medical field, most second- and third-tier cities have relatively scarce medical resources compared to first-tier cities. Young doctors not only rarely have the opportunity to receive professional and standardized guidance from high-level experts in the field, but they also cannot access the latest treatment technologies and plans in a timely manner, and cannot be exposed to different types and diverse clinical cases in a short period of time. Young doctors lack clinical experience and cannot obtain systematic and real-world clinical treatment learning and training. They can only rely on clinical treatment time to slowly accumulate diagnostic and treatment experience and improve their medical skills. Coupled with unfamiliarity with treatment guidelines, their growth is relatively slow.

[0003] Therefore, it is necessary to implement an electronic medical record report that is automatically generated based on the medical record data of different types of patients and combined with the Chinese Society of Clinical Oncology's treatment guidelines. After the doctor determines the candidate treatment plan, the doctor can evaluate the candidate treatment plan by referring to and absorbing the treatment experience of top experts in the industry. Summary of the Invention

[0004] This application provides a diagnostic assessment method, apparatus, electronic device, and computer-readable storage medium, which can automatically generate electronic medical record reports based on medical record data of different types of patients; determine target treatment plans with different recommendation levels based on the electronic medical record reports; and evaluate the candidate treatment plans after obtaining the determined candidate treatment plans.

[0005] The technical solution of this application embodiment is implemented as follows: In a first aspect, embodiments of this application provide a diagnostic assessment method, including: Obtain the key information for the expected electronic medical record report; Match electronic medical record report templates based on the aforementioned key information; Based on the matched electronic medical record report template and medical record information, the target electronic medical record report is determined; Receive candidate treatment plans determined based on the target electronic medical record report; The candidate treatment plan is evaluated based on the differences between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report.

[0006] In the above scheme, the step of matching the electronic medical record report template based on the key information includes: Generate different types of electronic medical record report templates based on the original medical record data; The key information of the expected electronic medical record report is matched with the electronic medical record report template to obtain the matched electronic medical record report template.

[0007] In the above scheme, the raw data includes: medical record data collected in the cloud and medical record data simulated offline.

[0008] In the above scheme, generating different types of electronic medical record report templates based on the original medical record data includes: Based on the key information of each original medical record data, determine the original medical record data corresponding to each type of key information; The original medical record data corresponding to each type of key information is structured and key indicator factors are extracted. Based on the aforementioned key indicator factors, a key indicator factor library shall be established. Based on the dependencies between the key indicator factors, a key indicator factor dependency pool is established. Based on the key indicator factor library and the key indicator factor dependency relationship pool, the electronic medical record report template corresponding to the key information is obtained.

[0009] In the above scheme, determining the target electronic medical record report based on the matched electronic medical record report template and medical record information includes: If the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template, then the electronic medical record report template shall be modified. The target electronic medical record report is obtained by filling in the medical record information based on the modified electronic medical record report template.

[0010] In the above scheme, if the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template, the electronic medical record report template is modified, including: If the electronic medical record report template contains key indicator factors that do not conform to the medical record information, then the key indicator factors that do not conform to the information are modified to obtain the modified electronic medical record report template. If the matched electronic medical record report template is missing key indicator factors of the current medical record information, then the missing key indicator factors are added to obtain the modified electronic medical record report template.

[0011] In the above scheme, after filling in the medical record information based on the modified electronic medical record report template to obtain the target electronic medical record report, the method further includes: Based on the key indicator factors in the target electronic medical record report, the key indicator information database and the corresponding key indicator information dependency pool corresponding to the electronic medical record report template are updated.

[0012] In the above scheme, the evaluation of the candidate treatment plan based on the recommendation level of the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report includes: Based on the key indicator factors in the target electronic medical record report, determine the target treatment plan; Based on the evidence supporting each target treatment plan, the recommendation level for each target treatment plan is determined; If the candidate treatment plan is among the target treatment plans, then a first treatment plan corresponding to the candidate treatment plan is determined in the target treatment plan, and the candidate treatment plan is evaluated based on the recommendation level of the first treatment plan; If the candidate treatment plan is not among the target treatment plans, then the candidate treatment plan will be evaluated as unqualified.

[0013] In the above scheme, the evidence supporting each recommended treatment plan includes: The treatment plan shall be based on at least one of the following: the completeness of the clinical trial design, the degree of expert consensus, patient factors, the guidelines of the Chinese Society of Clinical Oncology, references, drug usage and dosage, contraindications and adverse reactions.

[0014] Secondly, embodiments of this application provide a diagnostic assessment device, the diagnostic assessment device comprising: The key information acquisition module is used to acquire key information from the expected electronic medical record report; An electronic medical record report matching module is used to match electronic medical record report templates based on the key information; The target electronic medical record report determination module is used to determine the target electronic medical record report based on the matched electronic medical record report template and medical record information; The candidate treatment plan receiving module is used to receive candidate treatment plans determined based on the target electronic medical record report; The candidate treatment plan evaluation module is used to evaluate the candidate treatment plan based on the differences between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report.

[0015] Thirdly, embodiments of this application provide an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the diagnostic evaluation method provided in embodiments of this application.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium, the storage medium including a set of computer-executable instructions, which, when executed, are used to perform the diagnostic evaluation method provided in embodiments of this application.

[0017] The diagnostic assessment method provided in this application involves: acquiring key information of a anticipated electronic medical record (EMR) report; matching an EMR report template based on the key information; determining a target EMR report based on the matched EMR report template and medical record information; receiving candidate treatment plans determined based on the target EMR report; and evaluating the candidate treatment plans based on the recommendation level of the target treatment plan corresponding to the target EMR report. This diagnostic assessment method can generate target EMR reports based on different types of medical record data; obtain target treatment plans with different recommendation levels for the target EMR report; and evaluate candidate treatment plans based on the target treatment plan, thereby improving the treatment level of trainees. Attached Figure Description

[0018] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this application. Wherein: Figure 1 This is a schematic diagram of an optional processing flow of the diagnostic assessment method provided in the embodiments of this application; Figure 2 This is a schematic diagram of an optional processing flow for generating an electronic medical record report template, provided in an embodiment of this application. Figure 3 This is a schematic diagram of an optional decision tree workflow provided in an embodiment of this application; Figure 4 This is a schematic diagram of an optional system structure of the diagnostic assessment system provided in this application embodiment; Figure 5 This is a schematic diagram of an optional structure of the diagnostic assessment device provided in the embodiments of this application; Figure 6 This is a schematic block diagram of an optional electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] In the following description, the terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first" and "second" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0023] The following describes a diagnostic assessment method provided by an embodiment of this application. (See also...) Figure 1 , Figure 1 This is a schematic diagram of an optional processing flow of the diagnostic assessment method provided in the embodiments of this application. The following will be combined with... Figure 1 The steps S101-S105 shown are combined with Figures 2-3 Please provide an explanation.

[0024] Step S101: Obtain the key information of the expected electronic medical record report.

[0025] In some embodiments, key information in the anticipated electronic medical record report includes cancer type and disease stage. Disease stage includes early stage, neoadjuvant chemotherapy, post-operative, adjuvant chemotherapy, advanced stage (line 1 / 2 / 3 / 4), etc.

[0026] Step S102: Match the electronic medical record report template based on the key information.

[0027] In some embodiments, different types of electronic medical record report templates can be generated based on the original medical record data. The processing flow for generating different types of electronic medical record report templates is as follows: Figure 2 Steps 201-203 are shown in the illustration.

[0028] Step 201: Based on the key information of each original medical record data, determine the key indicator factors corresponding to each type of key information.

[0029] In some embodiments, the raw data includes medical record data collected in the cloud and offline simulated medical record data. Using cloud-collected medical record data overcomes the problem of independent systems and limited data sharing between hospitals, while using offline simulated medical record data enriches the overall medical record database. The cloud-collected medical record data can be processed into structured data in a unified format using methods such as OCR (Optical Character Recognition). The offline simulated medical record data can be generated through user input.

[0030] In some embodiments, based on the key information corresponding to each type of original medical record data, the original medical record data corresponding to each type of key information can be determined, and the original medical record data corresponding to each type of key information can be structured to extract key indicator factors. The key information includes cancer type and disease stage. For the same cancer type at the same disease stage, key indicator factors are extracted from the original medical record data based on the key indicator factors for cancer type and disease stage corresponding to the Chinese Society of Clinical Oncology (CSCO) guidelines.

[0031] As an example, if the key information corresponding to the original medical record data is early-stage colorectal cancer, based on the CSCO treatment guidelines, key indicator factors include: age, gender, clinical stage, pathological stage, primary lesion location, primary lesion size, number of primary lesions, whether the lesion is resectable, source of pathological specimen, radical surgical method, depth of lesion invasion, number of positive / submitted lymph nodes, vascular invasion, nerve invasion, surgical margin, histological type, histological grade, immunohistochemistry (MMR, MSI, RAS, BRAF, PD-L TPS, ERB-B2 mutation, TMB), details of preoperative treatment, whether adjuvant therapy was used, whether chemotherapy was used, first / second / third-line regimen, best efficacy assessment, whether the disease has progressed, TTP, etc. Key indicator factors can be extracted from the corresponding original medical record data based on these key indicator factors.

[0032] Step 202: Based on key indicator factors, establish a key indicator factor library; based on the dependencies between key indicator factors, establish a key indicator factor dependency pool.

[0033] In some embodiments, a key indicator factor library can be established for key indicator factors in the original medical record data corresponding to each type of key information.

[0034] As an example, if the key information is advanced second-line treatment for triple-negative breast cancer, then the original medical record data of the patient with advanced second-line triple-negative breast cancer to be treated can be used to extract the corresponding key indicator factors based on the CSCO treatment guidelines. These key indicator factors include, but are not limited to, age, gender, pathological stage, molecular pathology, surgical plan, neoadjuvant regimen, number of positive / submitted lymph nodes, postoperative treatment, and efficacy evaluation. The key indicator factors extracted from the corresponding original medical record data can be uniformly organized into a key factor library.

[0035] In some embodiments, based on the dependencies between key indicator factors in the CSCO treatment guidelines, a key indicator factor dependency pool can be established for the key indicator factors in the original medical record data corresponding to each type of key information, and key indicator factors with dependencies and linkages can be maintained.

[0036] As an example, if the key information is advanced triple-negative breast cancer in second-line treatment, then the relationships between key indicator factors can be determined based on the original medical record data of the current patient with advanced triple-negative breast cancer in second-line treatment, according to the CSCO treatment guidelines. Triple negative -> human epidermal growth factor receptor 2 is negative (her2-), estrogen receptor is negative (er-), and progesterone receptor is negative (pr-). Pathological staging -> Primary lesion large and positive / number of lymph nodes submitted for examination and site of metastasis; Second-line plan First-line solution Postoperative treatment plan Neoadjuvant therapy Treatment efficacy assessment.

[0037] The explanations of the above terms and symbols are shown in the table below:

[0038] Step 203: Generate the corresponding electronic medical record report template based on the key indicator factor library and the key indicator factor dependency pool.

[0039] In some embodiments, corresponding electronic medical record report templates can be generated for each type of key information, based on the key indicator factor library and key indicator factor dependency pool.

[0040] Since different key information corresponds to different electronic medical record (EMR) report templates, the key information of the expected EMR report can be matched with the key information corresponding to the EMR report template to obtain a matched EMR template.

[0041] Step S103: Based on the matched electronic medical record report template and medical record information, determine the target electronic medical record report.

[0042] In some embodiments, if the key indicator factors in the medical record information do not match the key indicator factors in the matched electronic medical record report template, the matched electronic medical record report template needs to be modified. Based on the modified electronic medical record report template, the current medical record information is entered to obtain the target electronic medical record report.

[0043] The medical record information can be real patients' cancer clinical data or simulated cancer clinical data.

[0044] Modifying the electronic medical record report template includes: if the matched electronic medical record report template contains key indicator factors that do not conform to the current medical record information, then modify the key indicator factors that do not conform to the current medical record information to obtain the modified electronic medical record report template; if the matched electronic medical record report template is missing key indicator factors of the current medical record information, then add the missing key indicator factors to obtain the modified electronic medical record report template.

[0045] In some embodiments, the key indicator information database and key indicator information dependency pool corresponding to the electronic medical record report template are updated based on the key indicator factors in the target electronic medical record report.

[0046] By updating and maintaining the key indicator factor library and the key indicator information dependency pool, the accuracy of the generated electronic medical record report templates is ensured, regardless of whether they are based on real patient medical record data or simulated patient medical record data.

[0047] Step S104: Receive the candidate treatment plan determined based on the target electronic medical record report.

[0048] In some embodiments, target treatment plans with different recommendation levels can be generated based on the target electronic medical record report. Three plans with different recommendation levels are selected from these plans, and an incorrect plan is added as an option in the question. One of the options selected by the trainee from the question is then designated as a candidate treatment plan.

[0049] Step S105: Evaluate the candidate treatment plan based on the difference between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report.

[0050] In some embodiments, the evaluation rule is as follows: the three options selected in the target treatment plan are ranked in descending order of recommendation level as 100, 90 and 80 points, and the option of the incorrect plan is determined to be 0 points.

[0051] If the trainee selects a candidate treatment plan that is included in the target treatment plan, the candidate treatment plan will be scored based on the recommendation level of the target treatment plan and the corresponding ratings in the three options. If the trainee selects a candidate treatment plan that is not included in the target treatment plan, and the trainee selects an incorrect option with a score of 0, the candidate treatment plan will be evaluated as having a score of 0, i.e., it is unqualified. Furthermore, trainees can click on the options to view the supporting evidence and other information for that plan, facilitating learning.

[0052] The target treatment plan can be derived from a decision tree system based on the clinical experience of top domestic experts and the CSCO treatment guidelines. Supporting evidence includes one or more of the following: the completeness of the clinical trial design of the treatment plan, the degree of expert consensus, patient factors, the views of the Chinese Society of Clinical Oncology treatment guidelines, references, drug usage and dosage, contraindications, and adverse reactions.

[0053] By referencing and drawing upon the treatment experience of leading experts in the field who provide evidence supporting the treatment plan, trainees can quickly improve their diagnostic and treatment skills.

[0054] The workflow of decision trees is as follows: Figure 3 As shown. The decision tree system can rely on the CSCO (China Society of Clinical Oncology) guidelines to provide standardized recommended treatment plans for specific symptom types corresponding to target electronic medical record reports. Figure 3 In the decision tree, the root node corresponds to the cancer type and the version number of the CSCO treatment guidelines, the non-leaf nodes are the key indicator factors corresponding to the target electronic medical record report, and the leaf nodes are the recommended treatment plans for the specific symptoms corresponding to each target electronic medical record report.

[0055] like Figure 3 As shown, taking second-line treatment of advanced triple-negative breast cancer as an example, the root node is the 2022 CSCO Breast Cancer Guidelines, indicating that the cancer type is breast cancer and the version number of the CSCO guidelines is 2022. The target electronic medical record report contains key indicator factors such as HER2, ER, PR, pTNM, first-line treatment regimen, and efficacy assessment. These key indicator factors are fed into the decision tree to match the corresponding nodes. Finally, the decision tree will route to a leaf node, which is the recommended treatment plan for second-line treatment of advanced triple-negative breast cancer. For example, recommended treatment plans for advanced triple-negative breast cancer include albumin-bound paclitaxel (1A), docetaxel (2A), and etoposide (2B).

[0056] The workflow of the diagnostic assessment system provided in the embodiments of this application is described below. See also... Figure 4 , Figure 4 This is an optional system structure diagram of the diagnostic assessment system 400 provided in the embodiments of this application.

[0057] In some embodiments, the diagnostic assessment system 400 includes an information input unit 401, an electronic medical record report generation unit 402, a decision processing unit 403, and a scoring unit 404.

[0058] In some embodiments, the information input unit 401 is used to input key information for the expected electronic medical record report. The information input unit can input key information or select corresponding key information through options. The key information includes information such as cancer type and disease stage, with disease stages including: early stage, neoadjuvant chemotherapy, post-operative, adjuvant chemotherapy, and advanced stage 1 / 2 / 3 / 4 lines of treatment.

[0059] In some embodiments, the electronic medical record report generation unit 402 is used to match the key information obtained by the information input unit 401 with the electronic medical record report template in the electronic medical record report generation unit 402 to obtain a matched electronic medical record report template. Based on the matched electronic medical record report template and medical record information, a target electronic medical record report is determined.

[0060] In some embodiments, the electronic medical record report generation unit 402 is further configured to generate an electronic medical record report template. Based on the key information of each original medical record data, the electronic medical record report generation unit 402 determines the original medical record data corresponding to each type of key information, performs structured processing on the original medical record data corresponding to each type of key information, and extracts key indicator factors. Based on the key indicator factors corresponding to each type of key information, a key indicator factor library is established; based on the dependencies between the key indicator factors corresponding to each type of key information, a key indicator factor dependency relationship pool is established. Based on the key indicator factor library and the key indicator factor dependency relationship pool, an electronic medical record report template corresponding to each type of key information is obtained.

[0061] In some embodiments, the electronic medical record report generation unit 402 is further configured to, when determining a target electronic medical record report based on a matched electronic medical record report template and medical record information, modify the electronic medical record report template if the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template. The modified electronic medical record report template is then used to fill in the medical record information to obtain the target electronic medical record report. Modifying the electronic medical record report template includes: if the electronic medical record report template contains key indicator factors that do not match the medical record information, modifying the non-matching key indicator factors to obtain a modified electronic medical record report template; if the electronic medical record report template lacks key indicator factors for the current medical record information, adding the missing key indicator factors to obtain a modified electronic medical record report template.

[0062] In some embodiments, the electronic medical record report generation unit 402 is further configured to: after filling in medical record information based on the modified electronic medical record report template to obtain a target electronic medical record report, update the key indicator information database corresponding to the electronic medical record report template and the corresponding key indicator information dependency relationship pool based on the key indicator factors in the target electronic medical record report.

[0063] In some embodiments, the decision processing unit 403 is used to determine the target treatment plan corresponding to the target electronic medical record report and the evidence support for each target treatment plan based on the key indicator factors corresponding to the target electronic medical record report, based on the decision tree system and the CSCO treatment guidelines; and to determine the recommendation level of each target treatment plan based on the evidence support for each target treatment plan.

[0064] In some embodiments, the scoring unit 404 is used to develop assessment questions based on the target treatment plan. The assessment question options include selecting three plans with different recommendation levels from the target treatment plan generated by the decision processing unit 403, and one incorrect recommendation plan. The three plans with different recommendation levels can be scored from highest to lowest as 100 points, 90 points, and 80 points, respectively, while the incorrect recommendation plan receives a score of 0 points. The assessment is based on the scores corresponding to the candidate treatment plans selected by the trainee.

[0065] In some embodiments, the scoring unit 404 is also used to view the evidence support corresponding to each option in the assessment question, so as to facilitate doctors to make comparative learning.

[0066] Figure 5 This is a schematic diagram of an optional device structure for the diagnostic assessment apparatus provided in an embodiment of this application. The diagnostic assessment apparatus 500 includes a key information acquisition module 501, an electronic medical record report matching module 502, a target electronic medical record report determination module 503, a candidate treatment plan receiving module 504, and a candidate treatment plan evaluation module 505. The key information acquisition module 501 is used to acquire key information of the expected electronic medical record report; Electronic medical record report matching module 502 is used to match electronic medical record report templates based on the key information; The target electronic medical record report determination module 503 is used to determine the target electronic medical record report based on the matched electronic medical record report template and medical record information; The candidate treatment plan receiving module 504 is used to receive candidate treatment plans determined based on the target electronic medical record report; The candidate treatment plan evaluation module 505 is used to evaluate the candidate treatment plan based on the differences between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report.

[0067] In some embodiments, the electronic medical record report matching module 502 is used to: generate different types of electronic medical record report templates based on the original medical record data; and match the key information of the expected electronic medical record report with the electronic medical record report templates to obtain a matched electronic medical record report template. The key information of the expected electronic medical record report includes: cancer type and disease stage.

[0068] In some embodiments, the electronic medical record report matching module 502 is further configured to: determine the original medical record data corresponding to each type of key information based on the key information of each original medical record data; perform structured processing on the original medical record data corresponding to each type of key information to extract key indicator factors; establish a key indicator factor library based on the key indicator factors; establish a key indicator factor dependency pool based on the dependencies between the key indicator factors; and obtain the electronic medical record report template corresponding to the key information based on the key indicator factor library and the key indicator factor dependency pool. The key information of the original medical record data includes: cancer type and disease stage.

[0069] In some embodiments, the target electronic medical record report determination module 503 is used to: modify the electronic medical record report template if the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template; and fill in the medical record information based on the modified electronic medical record report template to obtain the target electronic medical record report.

[0070] In some embodiments, the target electronic medical record report determination module 503 is further configured to: if there are key indicator factors in the electronic medical record report template that do not conform to the medical record information, modify the key indicator factors that do not conform to the medical record information to obtain the modified electronic medical record report template; if the matched electronic medical record report template lacks key indicator factors of the current medical record information, add the missing key indicator factors to obtain the modified electronic medical record report template.

[0071] In some embodiments, the target electronic medical record report determination module 503 is further configured to: update the key indicator information database and the corresponding key indicator information dependency pool corresponding to the electronic medical record report template based on the key indicator factors in the target electronic medical record report.

[0072] In some embodiments, the candidate treatment plan evaluation module 505 is used to: determine the target treatment plan based on key indicator factors in the target electronic medical record report; determine the recommendation level of each target treatment plan based on the evidence support corresponding to each target treatment plan; if the candidate treatment plan is in the target treatment plan, then determine the first plan corresponding to the candidate treatment plan in the target treatment plan, and evaluate the candidate treatment plan based on the recommendation level of the first plan; if the candidate treatment plan is not in the target treatment plan, then evaluate the candidate treatment plan as unqualified; wherein, the evidence support corresponding to each target treatment plan includes at least one of the following: the degree of perfection of the clinical trial design of the treatment plan, the degree of expert consensus, patient factors, the views of the Chinese Society of Clinical Oncology treatment guidelines, references, drug usage and dosage, contraindications and adverse reactions.

[0073] It should be noted that the diagnostic evaluation device of this application embodiment is similar to the diagnostic evaluation method embodiment described above, and has similar beneficial effects as the method embodiment, therefore, it will not be described in detail. For any technical details not covered in the diagnostic evaluation device provided in this application embodiment, please refer to... Figures 1 to 4 The meaning is understood in accordance with the description of any of the accompanying drawings.

[0074] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device 600 is used to implement the diagnostic assessment method of the embodiments of the present disclosure. In some alternative embodiments, the electronic device 600 can implement the diagnostic assessment method provided in the embodiments of this application by running a computer program. For example, the computer program can be a software module in an operating system; it can be a native application (APP), i.e., a program that needs to be installed in the operating system to run; it can also be a small program, i.e., a program that only needs to be downloaded to a browser environment to run; or it can be a small program that can be embedded in any APP. In summary, the above-mentioned computer program can be any form of application, module, or plugin.

[0075] In practical applications, electronic device 600 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Cloud technology refers to a hosting technology that unifies hardware, software, and network resources within a wide area network (WAN) or local area network (LAN) to achieve data computation, storage, processing, and sharing. Electronic device 600 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smart TV, smartwatch, etc., but is not limited to these.

[0076] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, in-vehicle terminals, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0077] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0078] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0079] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as diagnostic evaluation methods. For example, in some alternative embodiments, the diagnostic evaluation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some alternative embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the diagnostic evaluation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured as a diagnostic evaluation method by any other suitable means (e.g., by means of firmware).

[0080] This application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored and, when executed by a processor, will cause the processor to execute the diagnostic evaluation method provided in this application.

[0081] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0082] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0083] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0084] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0086] It should be understood that in the various embodiments of this application, the sequence number of each implementation process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0087] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A method of diagnostic assessment, characterized by, The method includes: Obtain the key information for the expected electronic medical record report; Match electronic medical record report templates based on the aforementioned key information; Based on the matched electronic medical record report template and medical record information, the target electronic medical record report is determined; Receive candidate treatment plans determined based on the target electronic medical record report; The candidate treatment plan is evaluated based on the differences between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report; The process of matching electronic medical record report templates based on the key information includes: Based on the original medical record data, generate different types of electronic medical record report templates; The key information of the expected electronic medical record report is matched with the electronic medical record report template to obtain the matched electronic medical record report template. The process of generating different types of electronic medical record report templates based on original medical record data includes: Based on the key information of each original medical record data, determine the original medical record data corresponding to each type of key information; The original medical record data corresponding to each type of key information is structured and key indicator factors are extracted. Based on the aforementioned key indicator factors, a key indicator factor library shall be established. Based on the dependencies between the key indicator factors, a key indicator factor dependency pool is established. Based on the key indicator factor library and the key indicator factor dependency relationship pool, the electronic medical record report template corresponding to the key information is obtained. The process of determining the target electronic medical record report based on the matched electronic medical record report template and medical record information includes: If the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template, then the electronic medical record report template shall be modified. The target electronic medical record report is obtained by filling in the medical record information based on the modified electronic medical record report template; if the key indicator factors in the medical record information do not match the key indicator factors in the electronic medical record report template, the electronic medical record report template is modified, including: If the electronic medical record report template contains key indicator factors that do not conform to the medical record information, then the key indicator factors that do not conform to the information are modified to obtain the modified electronic medical record report template. If the matched electronic medical record report template is missing key indicator factors of the current medical record information, then the missing key indicator factors are added to obtain the modified electronic medical record report template. After filling in the medical record information based on the modified electronic medical record report template to obtain the target electronic medical record report, the process further includes: Based on the key indicator factors in the target electronic medical record report, the key indicator information database and the corresponding key indicator information dependency pool corresponding to the electronic medical record report template are updated. The evaluation of the candidate treatment plan based on the difference between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report includes: Based on the key indicator factors in the target electronic medical record report, determine the target treatment plan; Based on the evidence supporting each target treatment plan, the recommendation level for each target treatment plan is determined; If the candidate treatment plan is among the target treatment plans, then a first treatment plan corresponding to the candidate treatment plan is determined in the target treatment plan, and the candidate treatment plan is evaluated based on the recommendation level of the first treatment plan; If the candidate treatment plan is not among the target treatment plans, then the candidate treatment plan will be evaluated as unqualified.

2. The method of claim 1, wherein, The raw data includes: medical record data collected in the cloud and medical record data simulated offline.

3. The method of claim 1, wherein, The evidence supporting each target treatment plan includes: The treatment plan shall include at least one of the following: the completeness of the clinical trial design, the degree of expert consensus, patient factors, the views of the Chinese Society of Clinical Oncology's treatment guidelines, references, drug usage and dosage, contraindications, and adverse reactions.

4. A diagnostic evaluation device for performing the method of any one of claims 1 to 3, characterized by The device includes: The key information acquisition module is used to acquire key information from the expected electronic medical record report; An electronic medical record report matching module is used to match electronic medical record report templates based on the key information; The target electronic medical record report determination module is used to determine the target electronic medical record report based on the matched electronic medical record report template and medical record information; The candidate treatment plan receiving module is used to receive candidate treatment plans determined based on the target electronic medical record report; The candidate treatment plan evaluation module is used to evaluate the candidate treatment plan based on the differences between the candidate treatment plan and the target treatment plan corresponding to the target electronic medical record report.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The storage medium includes a set of computer-executable instructions, which, when executed, are used to perform the diagnostic assessment method according to any one of claims 1-3.