Workload quantification method and device for image report, and storage medium

Abstract

The invention discloses a workload quantification method and device for an image report and a storage medium, and the method comprises the steps: obtaining a target image report corresponding to a patient, and extracting a plurality of first key features in the text content of the target image report through an NLP model; coding each first key feature by using a preset coding rule, and determining a plurality of feature codes corresponding to each first key feature and a plurality of coding values corresponding to each feature code; generating a corresponding first data set based on the plurality of feature codes and the plurality of coded values; and inputting the first data set into a preset workload prediction model, and determining the workload corresponding to the target image report. The technical effects of truly reflecting the workload when the doctor fills the diagnosis report based on the target image report and improving the work enthusiasm of the doctor are achieved.

Description

Technical Field

[0001] The present application relates to the field of medical diagnosis technology, and in particular to a method, device and storage medium for quantifying the diagnostic workload of imaging reports. Background Art

[0002] As medical imaging becomes an indispensable part of modern healthcare, the workload doctors face in completing diagnostic reports based on imaging reports is increasing. Accurately and effectively assessing doctors' workload is crucial for improving their work enthusiasm. Traditionally, doctors' workload is quantified by assigning a score to each examination item. However, the time it takes to complete a diagnostic report based on an imaging report varies. Specifically, more complex imaging reports take longer, while simpler reports take less time. Therefore, using traditional methods to quantify the workload of doctors completing diagnostic reports based on imaging reports fails to truly reflect the workload.

[0003] For example, for patients with more complicated conditions, the imaging report contains more descriptions of their condition, and doctors need to spend a longer time filling out the diagnosis report based on the imaging report. Therefore, if traditional quantitative methods are used to evaluate the doctor's workload, it will be biased.

[0004] Publication number CN117689242A, titled "Verification Service Work Quantification Method, Apparatus, Electronic Device, and Storage Medium." The method includes: obtaining a dataset including current basic data, current accounting boundaries, and monitoring data of an object to be verified, where the object to be verified includes at least one accounting entity; determining the workload corresponding to the current basic data and current accounting boundaries of each accounting entity based on a pre-established mapping relationship between basic data, accounting boundaries, and workload, as a first workload for each accounting entity; determining a second workload for each accounting entity based on the monitoring data of each accounting entity using a preset accounting algorithm; and obtaining a quantified result based on the first and second workloads of each accounting entity.

[0005] Publication number CN116227972A, titled "A Quantitative Evaluation Method for Science and Technology Special Envoys Based on a Cloud Platform," includes the following steps: S1. Constructing an evaluation index system for science and technology special envoys. Based on cloud platform data, the evaluation factors in the evaluation index system are standardized and scored to obtain standardized scores for the evaluation factors. S2. Using the analytic hierarchy process and entropy weight method, the weight coefficients of the evaluation factors are determined, and a quantitative evaluation model for science and technology special envoys' work is established.

[0006] There is currently no effective solution to the technical problem in the above-mentioned prior art that the traditional workload quantification method of filling out diagnostic reports based on imaging reports cannot truly reflect the workload of doctors, and thus cannot further improve the work enthusiasm of doctors. Summary of the Invention

[0007] The embodiments of the present disclosure provide a method, device and storage medium for quantifying the workload of imaging reports, so as to at least solve the technical problem in the prior art that the traditional workload quantification method of filling out diagnostic reports based on imaging reports cannot truly reflect the workload of doctors, and thus cannot further improve the work enthusiasm of doctors.

[0008] According to one aspect of an embodiment of the present disclosure, a method for quantifying the workload of an imaging report is provided, comprising: obtaining a target imaging report corresponding to a patient, and extracting a plurality of first key features from the text content of the target imaging report using an NLP model, wherein the plurality of first key features include examination items, the number of included parts, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is a trauma, and whether there is a historical examination; encoding each first key feature separately using a preset coding rule, and determining a plurality of feature codes corresponding to each first key feature and a plurality of coding values ​​corresponding to each feature code, wherein the coding rule includes a key feature code and a coding value; generating a corresponding first data set based on the plurality of feature codes and the plurality of coding values; and inputting the first data set into a preset workload prediction model, and determining the workload corresponding to the target imaging report.

[0009] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0010] According to another aspect of an embodiment of the present disclosure, a workload quantification device for an imaging report is also provided, including: a first feature extraction module, used to obtain a target imaging report corresponding to a patient, and use an NLP model to extract multiple first key features in the text content of the target imaging report, wherein the multiple first key features include examination items, the number of parts included, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is a trauma, and whether there is a historical examination; an encoding module, used to encode each first key feature respectively using a preset encoding rule, and determine multiple feature codes corresponding to each first key feature and multiple coding values ​​corresponding to each feature code, wherein the encoding rule includes a key feature code and a coding value; a first data set generation module, used to generate a corresponding first data set based on the multiple feature codes and the multiple coding values; and a workload determination module, used to input the first data set into a preset workload prediction model, and determine the workload corresponding to the target imaging report.

[0011] According to another aspect of an embodiment of the present disclosure, a workload quantification device for an imaging report is also provided, comprising: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: obtaining a target imaging report corresponding to a patient, and extracting multiple first key features in the text content of the target imaging report using an NLP model, wherein the multiple first key features include examination items, the number of parts included, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is a trauma, and whether there is a historical examination; encoding each first key feature separately using a preset coding rule, and determining multiple feature codes corresponding to each first key feature and multiple coding values ​​corresponding to each feature code, wherein the coding rule includes a key feature code and a coding value; generating a corresponding first data set based on the multiple feature codes and the multiple coding values; and inputting the first data set into a preset workload prediction model, and determining the workload corresponding to the target imaging report.

[0012] The present application provides a method for quantifying the workload of an imaging report. First, the processor obtains a target imaging report corresponding to the patient, and uses an NLP model to extract multiple first key features in the text content of the target imaging report. Then, the processor encodes each first key feature respectively using a preset encoding rule, and determines multiple feature codes corresponding to each first key feature and multiple coding values ​​corresponding to each feature code. Furthermore, the processor generates a corresponding first data set based on the multiple feature codes and the multiple coding values. Finally, the processor inputs the first data set into a preset workload prediction model and determines the workload corresponding to the target imaging report.

[0013] Referring to the above content, it can be seen that since this application first uses the NLP model to extract multiple first key features that may affect the doctor's workload from the text content of the target imaging report, and uses pre-set encoding rules to encode each first key feature separately, therefore, unlike the existing technology, this application quantifies the degree of impact of different key features on the doctor's workload, thereby significantly distinguishing the workload consumed by the doctor when filling out the diagnosis report based on each key feature of the target imaging report.

[0014] Furthermore, since the generated first data set contains feature codes and code values ​​corresponding to each first key feature, when the first data set is input into a pre-set workload prediction model, the workload prediction model can truly reflect the workload of the doctor in filling out the diagnostic report based on the target imaging report in a visual form.

[0015] This achieves the technical effect of truly reflecting the workload of doctors when filling out diagnostic reports based on target imaging reports, and further enhancing their work enthusiasm. This solves the technical problem in the prior art that traditional workload quantification methods based on imaging reports fail to truly reflect doctors' workload and thus fail to further enhance their work enthusiasm. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings: Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to embodiment 1 of the present application; Figure 2 is a schematic diagram of the workload quantification system for imaging reporting according to Example 1 of the present application; Figure 3 is a flow chart of the method for quantifying the workload of imaging reports according to Example 1 of the present application; Figure 4 is a schematic diagram of the anatomical structure according to Example 1 of the present application; Figure 5 is a schematic diagram of a target imaging report corresponding to a patient and corresponding critical value keywords according to Example 1 of the present application; Figure 6 is a schematic diagram of the interface for critical value management according to Example 1 of the present application; Figure 7 is a schematic diagram of a workload quantification device for image reporting according to Example 2 of the present application; Figure 82 is a schematic diagram of a workload quantification device for image reporting according to Example 3 of the present application. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0018] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] Example 1 According to this embodiment, an embodiment of a method for quantifying the workload of image reporting is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0020] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 The following is a hardware block diagram of a computing device for implementing a workload quantification method for needle image reporting. Figure 1 As shown, a computing device may include one or more processors (the processor may include, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA) or other processing device), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, transmission device, and input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. Those skilled in the art will understand that Figure 1The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0021] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computing device. As discussed in the embodiments of the present disclosure, the data processing circuitry functions as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0022] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the workload quantification method of image reporting in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the workload quantification method of image reporting of the above-mentioned application. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0023] The transmission device is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by a communications provider of the computing device. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0024] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computing device.

[0025] It should be noted that, in some optional embodiments, the above Figure 1The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0026] Figure 2 Schematic diagram of the workload quantification system of the image report according to this embodiment. Figure 2 As shown, the system includes: a terminal device 100 and a processor 200. A doctor uploads a patient's target imaging report to the processor 200 via the terminal device 100. Upon receiving the target imaging report corresponding to the patient, the processor 200 first uses an NLP model to extract multiple first key features from the text content of the target imaging report. Each first key feature is then encoded using pre-set encoding rules to generate a corresponding first data set. Finally, the first data set is input into a pre-set workload prediction model to determine the workload required for the doctor to complete a diagnostic report based on the target imaging report.

[0027] Furthermore, when the processor 200 determines the workload required for the doctor to fill out the diagnosis report based on the target imaging report, the processor 200 sends the determined workload to the terminal device 100. Thus, the terminal device 100 can display the determined workload to the doctor in a visual form.

[0028] It should be noted that the terminal device 100 and the processor 200 in the system can both be applicable to the hardware structure described above.

[0029] Under the above operating environment, according to the first aspect of this embodiment, a method for quantifying the workload of image reporting is provided. The method comprises: Figure 2 The processor 200 shown in FIG. Figure 3 A schematic diagram of the process is shown in FIG. Figure 3 As shown, the method includes: S302: Obtain a target imaging report corresponding to the patient, and extract multiple first key features from the text content of the target imaging report using an NLP model, where the multiple first key features include examination items, the number of included sites, the number of positive sites, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is traumatic, and whether there is a history of examinations; S304: Encode each first key feature using a preset encoding rule, and determine a plurality of feature codes corresponding to each first key feature and a plurality of code values ​​corresponding to each feature code, wherein the encoding rule includes the key feature code and the code value; S306: Generate a corresponding first data set based on the multiple feature codes and the multiple code values; and S308: Input the first data set into a preset workload prediction model, and determine the workload corresponding to the target image report.

[0030] Specifically, the processor 200 first obtains a target imaging report corresponding to the patient through the terminal device 100 and uses the NLP model to extract multiple first key features from the text content of the target imaging report (S302). In this embodiment, the target imaging report may be, for example, a medical imaging report, and the medical image includes both text content and radiographic images. The text content should meet the basic requirements of a medical imaging report and include at least the following aspects: patient gender, patient age, examination site, examination equipment type, examination findings, diagnostic impression, and examination submission information.

[0031] The text content of the target image report is exemplified as follows: "Gender: Female, Age: 7 years old, Examination site: Chest, Examination equipment: CT

[0032] Examination findings: The thorax is roughly symmetrical on both sides, with clear bronchial vessels in both lungs. Strip-like high-density shadows are visible in the middle lobe of the left lung, with a relatively uniform density. No enlarged lymph nodes are found in the bilateral hilum and mediastinum. The mediastinum does not show any widening and is centrally located without displacement. No abnormalities are found in the heart or major blood vessels, and no pleural effusion is found on either side. No obvious abnormalities are found in the bone and soft tissue structures of the thorax within the scanning range. The cerebral hemispheres are symmetrical on both sides, with spots and patchy low-density lesions in the center of the hemispheres, corona radiata, and basal ganglia. Some lesions have clear boundaries, some have blurred boundaries, and some have a watery density. There is no obvious expansion of the ventricular system, no widening of the cerebral sulci, cerebral columns, or cisterns, no displacement of the midline structures, and no abnormal density shadows in the brainstem or cerebellum. No abnormal changes are found in the skull bones.

[0033] Diagnostic Impression: The patient presented with right middle lobe atelectasis of unknown etiology, recommending enhanced CT or bronchoscopy for further examination. Multiple ischemic lesions were found bilaterally in the centrum semiovale, corona radiata, and basilar segments, as well as senile cerebral infarction. The corpus cavernosum was normal.

[0034] Inspection information: Patient Origin: Outpatient; Application Department: Internal Medicine; Application Number: YY20240912; Emergency: No; Trauma: Yes; Follow-up: Yes; Condition Description: Chest tightness and nausea. Thus, when the processor 200 obtains a target imaging report corresponding to a patient, the target imaging report is input into a general NLP model, and the NLP model is used to extract the entity content of each sentence of the imaging report in the text content of the target imaging report. The entity content includes entities and relationships between entities. Examples of entities include: lung, hilum, trachea, kidney, liver, etc. Examples of relationships between entities include: positional relationships, sign descriptions, and qualitative relationships. Positional relationships include location and location. Sign descriptions include location and positive / negative signs. Qualitative relationships include qualitative terms and signs.

[0035] Table 1 shows the entity types.

[0036] Table 1

[0037] Table 1 shows the entity type, its English representation, its description, and its corresponding example. For example, the entity type is a part entity, and its corresponding English representation is nsf. Part entities are used to indicate anatomical parts of the body, and entity types can include brain, thoracic vertebrae, lungs, and blood vessels.

[0038] Table 2 shows the entity relationships.

[0039] Table 2

[0040] Table 2 above shows entity relationships, their corresponding antecedents, their corresponding posterior entities, and corresponding examples. The positive and negative sign relationships shown in Table 2 describe a part. For example, the entity relationship is a position relationship, the antecedent entity is a position entity (ntcb), the posterior entity is a position entity (nsf), and the entity relationship can be, for example, "left side" or "thorax."

[0041] Furthermore, the processor 200 may determine the masculinity of the current description sentence based on the qualitative relationship and the positive sign relationship shown in Table 2. Table 3 shows a method for determining the masculinity of the description sentence.

[0042] Table 3

[0043] As shown in Table 3, the masculine / feminine nature of a description statement is determined by: whether the description statement contains masculine signs, whether the description statement contains a qualitative relationship, and the masculine / feminine nature of the description statement. For example, if the description statement contains masculine signs but no qualitative relationship, the description statement is masculine.

[0044] The processor 200 then determines the positive level (L0-L5) of the current lesion based on the configured levels of positive signs. L0 indicates negative, and L1-L5 indicate positive. A higher level indicates a more severe disease. For example, "pulmonary calcification" is L2, and "lung cancer" is L5.

[0045] Figure 4 Schematic diagram of the anatomical structure according to the embodiment of the present application. Figure 4 As shown, the anatomical structure includes the head, neck, and chest. The chest includes the lungs. The lungs include pulmonary lobules, lung fields, lungs, and the pulmonary valve. Thus, the processor 200 can confirm the examination scope of the imaging report by combining the region entity with the anatomical structure. In other words, several major regions are diagnosed, such as "lung-chest" and "liver-abdomen."

[0046] The processor 200 can also determine how many positive sites are in the report based on the positive sentences. In addition, the processor 200 can also determine the number of lesion measurements based on the description of the lesion. The processor 200 can also confirm whether the report is an emergency, whether it is a trauma, and whether there is a history of examination based on the inspection information of the report.

[0047] Thus, through the above method, the processor 200 can use the NLP model to determine multiple first key features. Among them, the selection of the first key feature should be able to reflect the text content characteristics of the target imaging report and the time invested by the doctor in filling out the diagnostic report based on the target imaging report. And among them, the first key feature includes: examination items, the number of parts included, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is traumatic, and whether there is a historical examination, etc. It is worth noting that the above is just an example of the type of the first key feature, and the actual situation is not limited to this.

[0048] Table 4 shows the first key features corresponding to the target image report.

[0049] Table 4

[0050] For example, the text content of the target imaging report includes "A scan from the apex of both lungs to the lower edge of the pubic symphysis showed: increased translucency in both lungs, linear high-density shadows and calcifications in the right upper lobe and both lower lobes, regular distribution of lung texture, clear hilar structure, unobstructed trachea, no mediastinal displacement, and enlarged lymph nodes." After inputting the above text content into the NLP model, the content shown in Table 4 can be output. Therefore, after determining the content of Table 4, the processor 200 can further determine the first key feature corresponding to the text content of the target imaging report.

[0051] For example, when the processor 200 obtains the target image report in the above example, the target image report is input into the NLP model, and the processor 200 determines "Examination items: CT chest; Number of parts included: 8; Number of positive parts: 3; Number of lesions: 2; Number of lesion measurements: 1; Positive level: L4; Whether it is an emergency: 1 (yes); Whether it is a trauma: 0 (not a trauma); Whether there is a historical examination: 0 (no historical examination)" according to the output results of the NLP model.

[0052] When the processor 200 determines multiple first key features in the target image report, it encodes each first key feature using a preset encoding rule and determines multiple feature codes corresponding to each first key feature and multiple code values ​​corresponding to each feature code (S304). The preset encoding rule may be, for example, a coding table, and the coding table includes a number, a key feature name, a key feature code, a code value, and a feature description.

[0053] Table 5 shows the encoding rules.

[0054] Table 5

[0055] Referring to Table 5 above, the number of parts included is used to indicate which parts are diagnosed in the target imaging report. For example, when the value is 3, it means that 3 parts of the patient are diagnosed in the target imaging report.

[0056] The number of positive sites is used to indicate which of the diagnosed sites are diseased. For example, when the value is 3, it means that three sites of the patient are diseased.

[0057] The number of lesions is used to indicate how many lesions are diagnosed in the target imaging report. For example, when the value is 1, it means that one lesion is diagnosed.

[0058] The lesion measurement number is used to indicate how many lesions were measured in the target imaging report. For example, when the value is 3, it means that 3 lesions were measured.

[0059] The positive grade is used to indicate the severity of the lesion, where 0 indicates no disease, 1 indicates mild, 2 indicates milder, 3 indicates moderate, 4 indicates more severe, and 5 indicates severe.

[0060] Whether it is an emergency report is used to indicate whether the target imaging report is an emergency report. 0 indicates that it is not an emergency report, and 1 indicates that it is an emergency report.

[0061] Trauma indicates whether the target image report is a trauma report, where 0 indicates it is not a trauma report and 1 indicates it is a trauma report.

[0062] Whether there are historical checks is used to indicate whether there are historical checks that need to be compared. 0 indicates no historical checks need to be compared, and 1 indicates that there are historical checks that need to be compared.

[0063] For example, the processor 200 determines the multiple coding features of the target image report in the above example and the coding values ​​corresponding to each coding feature according to the pre-set coding rules: "Examination items (jcxm): CT chest—0105; Number of parts included (bwzl): 8—8; Number of positive parts (yxbw): 3—3; Number of lesions (bzsl): 2—2; Number of lesion measurements (bzcl): 1—1; Positive grade (yxdj): L4—4; Whether it is an emergency (jz): 1 (yes)—1; Whether it is trauma (ws): 0 (not trauma)—0; Whether there is a historical examination (lsjc): 0 (no historical examination)—0".

[0064] The processor 200 then generates a corresponding first data set based on the determined multiple coding features and the coding values ​​corresponding to each coding feature (S306). For example, the processor 200 generates the first data set X={jcxm:0105;bwzl:8;yxbw:3;bzsl:2;bzcl:1;yxdj:4;jz:1;ws:0;lsjc:0}.

[0065] Finally, processor 200 inputs the first dataset into a pre-set workload prediction model and determines the workload corresponding to the target imaging report (S308). The workload prediction model may be, for example, a random forest model. When processor 200 inputs the first dataset into the trained random forest model, the random forest model can predict the time (i.e., workload) required for the doctor to complete the diagnostic report based on the target imaging report.

[0066] For example, the processor 200 inputs the first data set in the above example into the workload prediction model, so that the workload prediction model outputs Y = 18. Here, Y is used to indicate the time taken by the doctor to diagnose the target imaging report.

[0067] As described in the background, the traditional method of quantifying physician workload assigns a score to each examination item. However, the time it takes for a physician to complete a diagnostic report based on an imaging report varies. Specifically, more complex imaging reports take longer, while simpler reports take less time. Therefore, using traditional methods to quantify the workload of physicians completing diagnostic reports based on imaging reports fails to truly reflect the physician's workload.

[0068] In view of this, the present application provides a method for quantifying the workload of imaging reports. Referring to the above-mentioned content, it can be seen that since the present application first uses the NLP model to extract multiple first key features that may affect the workload of doctors from the text content of the target imaging report, and uses the pre-set encoding rules to encode each first key feature respectively, therefore, unlike the prior art, the present application quantifies the degree of influence of different key features on the workload of doctors, thereby significantly distinguishing the workload consumed by doctors when filling out each key feature of the diagnostic report based on the target imaging report.

[0069] Furthermore, since the generated first data set contains feature codes and code values ​​corresponding to each first key feature, when the first data set is input into a pre-set workload prediction model, the workload prediction model can truly reflect the workload of the doctor in filling out the diagnostic report based on the target imaging report in a visual form.

[0070] This achieves the technical effect of truly reflecting the workload of doctors when filling out diagnostic reports based on imaging reports, and further enhancing their work enthusiasm. This solves the technical problem in the prior art that traditional workload quantification methods based on imaging reports fail to truly reflect doctors' workload and thus fail to further enhance their work enthusiasm.

[0071] Optionally, it also includes: constructing a workload prediction model and training the workload prediction model. Further optionally, the operations of constructing a workload prediction model and training the workload prediction model include: determining input samples for training the workload prediction model; determining output samples for training the workload prediction model; and using the input samples and output samples to train the workload prediction model. Further optionally, the operations of using the input samples and output samples to train the workload prediction model include: collecting multiple image report samples, and using the NLP model to extract multiple second key features of each image report sample; using pre-set encoding rules to encode each second key feature, and generating corresponding multiple second data sets; determining the workload corresponding to each image report sample; and using the multiple second data sets as input samples and the workload corresponding to each image report sample as output samples, and training the workload prediction model.

[0072] Specifically, before the processor 200 uses the workload prediction model to determine the workload required for the doctor to fill out the diagnosis report based on the target imaging report, it is also necessary to pre-build the workload prediction model and train the workload prediction model.

[0073] First, the processor 200 builds a workload prediction model, wherein the processor 200 can, for example, use the RandomForestRegressor class provided by the Scikit-learn library to build a random forest model.

[0074] Then, the processor 200 randomly obtains multiple image report samples from the database The database may include, for example, pre-stored historical image reports. Further, the processor 200 extracts each image report sample using the NLP model. For example, the processor 200 uses the NLP model to extract the image report sample Multiple second key features in , the processor 200 uses the NLP model to extract the image report sample Multiple second key features in , the processor 200 uses the NLP model to extract the image report sample Multiple second key features in , ..., the processor 200 uses the NLP model to extract the image report sample Multiple second key features in .

[0075] The processor 200 then uses the encoding rules shown in Table 5 to encode each image report sample. Encode multiple second key features in and generate corresponding multiple second data sets For example, the processor 200 reports a sample image. Encode multiple second key features in and generate a second data set ; Processor 200 reports sample images Encode multiple second key features in and generate a second data set ; Processor 200 reports sample images Encode multiple second key features in and generate a second data set ; ...; Processor 200 reports sample images Encode multiple second key features in and generate a second data set .

[0076] Then, the processor 200 determines the image report samples For example, the processor 200 determines that the doctor The workload required to fill out the diagnostic report is , the processor 200 determines that the doctor based on the image report sample The workload required to fill out the diagnostic report is , the processor 200 determines that the doctor based on the image report sample The workload required to fill out the diagnostic report is , ..., the processor 200 determines that the doctor based on the image report sample The workload required to fill out the diagnostic report is .

[0077] Finally, the processor 200 converts the plurality of second data sets into As input samples, and the workload corresponding to each image report sample As output samples, the workload prediction model is trained. and workload Correspondingly, the second data set and workload Correspondingly, the second data set and workload Corresponding to,..., the second data set and workload correspond.

[0078] Among them, for a given sample (i.e., the second data set ), the prediction results of the random forest model (i.e., workload ) is the average of all individual decision tree predictions:

[0079] in, Represents the prediction result of the random forest model, u represents the number of decision trees, and u=1~U, Represents the prediction result of the decision tree.

[0080] Random forest is an ensemble machine learning method that improves prediction accuracy and controls overfitting by building multiple decision trees and averaging their predictions. First, random forest extracts samples from the original dataset using replacement sampling to create several training subsets. This ensures that the data inputs to each model are distinct, enhancing data diversity, improving feature space resolution, and forming more precise and smooth decision boundaries.

[0081] When splitting a node, instead of considering all features, a randomly selected subset of features is evaluated. Typically, the number of features selected is the square root or logarithm of the total number of features. This approach not only speeds up the search but also increases the nonlinearity of the model, making the decision boundary more complex and effective. During training, decision trees use specific evaluation criteria (such as information gain and Gini impurity) to determine the optimal split point. Different decision trees, based on different samples and feature subsets, generate different splitting rules, thus reducing the bias of individual models. Finally, by integrating the results of multiple decision trees, random forests reduce the variance of individual trees, improve the model's predictive performance on unseen data, and achieve stronger representational capabilities and better generalization results than a single decision tree.

[0082] It's worth noting that processor 200 can adjust the number of decision trees in the random forest, the feature selection method, and how each tree is grown based on the changes in the loss and accuracy of the training random forest. The selection of these parameters directly affects the behavior of the model and therefore requires careful evaluation, analysis, and adjustment. The random forest model analyzes the samples in the training set and their corresponding target variable values, gradually building multiple decision trees and performing feature selection and partitioning on each decision tree.

[0083] In this embodiment, for example, a test set for testing the random forest model can also be set. Therefore, after the random forest model training is completed, the processor 200 uses the samples in the test set to test the random forest model. For the random forest model, it averages or weighted averages the prediction results of each decision tree to obtain the final prediction value. Then, the processor 200 compares these predicted results with the actual target variable value to evaluate the performance of the random forest model. In order to more accurately measure the performance of the model, accuracy evaluation indicators such as mean square error (MSE), mean absolute error (MAE) and / or determination coefficient R2 are calculated, and the optimal model result is selected based on the results.

[0084] Preferably, in this embodiment, the decision trees in the trained random forest model can be screened using principal component analysis (PCA). Precision evaluation indicators such as mean square error (MSE), mean absolute error (MAE), and / or coefficient of determination (R2) can then be used to further determine the optimal model result from the screened decision trees.

[0085] Specifically, in this embodiment, it is assumed that the trained decision tree in the random forest model has n Define vector X =[ x 1, x 2, ..., x n ]T .in, x j For the same sample, j The working hours predicted by a decision tree.

[0086] Thus, for the test set m samples, and input them into n A decision tree can be obtained m The first decision tree vector { X 1, X 2, ..., X m}.in, X i =[ x i,1 , x i,2 , ..., x i,n ] T . And among them x i,j Indicates that the i Sample input j The predicted working hours by the decision tree. X 1, X 2, ..., X m ] Construct the following first decision tree matrix:

[0087] In generating the first decision tree matrix [ X 1, X 2, ..., X m ], the processor 200 processes the first decision tree matrix [ X 1, X 2, ..., X m ] is normalized to generate a second decision tree matrix. The specific calculation formula for normalizing the first decision tree matrix is ​​as follows:

[0088] in, i =1~m. j =1~n. And among them, Represents the element value in the second decision tree matrix after normalization. Represents the element value in the first decision tree matrix without normalization. Represents the average of the first decision tree vectors in the first decision tree matrix, where the first decision tree vector is X i , and i=1~m. Represents the variance of each first decision tree vector.

[0089] The specific calculation formula for the average value of each first decision tree vector is as follows:

[0090] Among them, j=1~n.

[0091] The specific calculation formula for the variance of each first decision tree vector is as follows:

[0092] Among them, j=1~n.

[0093] Thus, the processor 200 calculates the value of the element in the second decision tree matrix after normalization. , the second decision tree matrix can be determined .in, .

[0094] Afterwards, when the processor 200 determines the second decision tree matrix, it can calculate the corresponding sample correlation matrix based on the second decision tree matrix. The specific calculation formula is as follows:

[0095] Where R represents the sample correlation matrix and Y represents the second decision tree matrix.

[0096] Furthermore, the processor 200 performs eigendecomposition on the sample correlation matrix R and determines a plurality of first eigenvalues. The specific calculation formula is as follows:

[0097] Where R represents the sample correlation matrix, I represents the identity matrix, and λ represents the first eigenvalue.

[0098] Thus, the processor 200 can calculate the n first eigenvalues ​​λ1, λ2, ..., λ of the sample correlation matrix R based on the above formula. n . And among them, λ1≥λ2≥...≥λ n .

[0099] Then, when the processor 200 determines the n first eigenvalues ​​of the sample correlation matrix R, it further determines the number of first eigenvalues ​​whose variance contribution rate reaches a preset threshold, and determines a plurality of second eigenvalues ​​k. The specific calculation formula is as follows:

[0100] in, represents the variance contribution rate of the kth first eigenvalue among multiple first eigenvalues, represents the sum of the n first eigenvalues, Indicates the variance contribution rate.

[0101]

[0102] in, represents the sum of the variance contributions of the k first eigenvalues, represents the sum of the k first eigenvalues, represents the sum of the n first eigenvalues.

[0103] Furthermore, the processor 200 determines the number of variance contribution rates of the plurality of first eigenvalues ​​that reaches a preset threshold, and based on the determined number, determines a plurality of second eigenvalues. It is worth noting that the preset threshold is a threshold set by the operator based on actual conditions, usually 70% to 80%. In this embodiment, the preset threshold is 70%. Thus, since it has been mentioned in the above content that λ1≥λ2≥...≥λ n Therefore, when the sum of the variance contribution rates of the k first eigenvalues ​​is greater than or equal to the preset value, the value of k can be determined, and multiple second eigenvalues ​​λ1, λ2, ..., λ k .

[0104] That is, the processor 200 can determine to select k decision trees from n decision trees, and these k decision trees are the decision trees after redundancy removal. Furthermore, when the processor 200 determines k decision trees, it then uses accuracy evaluation indicators such as mean square error (MSE), mean absolute error (MAE), and / or coefficient of determination R2 to select decision trees with higher accuracy from the decision trees after redundancy removal, thereby achieving the technical effect of reducing redundant calculations and improving calculation accuracy.

[0105] Therefore, according to the first aspect of this embodiment, the technical effect of truly reflecting the workload of doctors when filling out diagnostic reports based on imaging reports and further enhancing the work enthusiasm of doctors is achieved.

[0106] In addition, critical value keywords are also set in the target image report, and the processor 200 can prompt the doctor to focus on the critical value keywords through the terminal device 100 based on the critical value keywords. Among them, the doctor can set the critical value keywords that need to be prompted in the application platform. For example, Figure 5 Schematic diagram of target image report corresponding to a patient and corresponding critical value keywords according to an embodiment of the present application. Figure 5The display shows the examination findings, report conclusions, and critical values. Among the findings: bilateral symmetry of the thorax, with the trachea and mediastinum centered. Patchy translucent shadows are visible bilaterally within the chest cavity, with compression of the lung margins (approximately 75% for the right lung and less than 10% for the left lung). Bilateral pleural thickening is present, and bilateral lung translucency is decreased.

[0107] The report conclusions include: 1. Bilateral pneumothorax, with right lung compression approximately 75% and left lung compression less than 10%, and decreased lung translucency. Please consider clinical considerations. 2. Bilateral pleural thickening.

[0108] Critical values ​​include: Compression. Among them, the examination findings include 2 "compressions" and the report conclusion includes 1 "compression".

[0109] Furthermore, Figure 6 Schematic diagram of the interface of critical value management according to the embodiment of the present application. Figure 6 As shown, the main menu of the data platform includes: Error Report Log, BPR Management, Part Conflict Whitelist, NER Hot Update, REF Hot Update, Critical Value Management, and Positive Level Management. The critical value management interface includes: critical value sequence number, critical value abbreviation, critical value description, part word in short sentence, short sentence symptom word, report keyword, and device type.

[0110] For example, the critical value corresponding to the serial number "3" is "brain herniation", and the description corresponding to "brain herniation" is "brain herniation". Midline structure displacement>1.0cm", there is no location word in the short sentence, the symptom word in the short sentence is "brain herniation", there are no keywords in the report, and there is no device type.

[0111] In addition, reference Figure 6 As shown, doctors can click "Add" on this interface to customize the critical value keywords that need to be submitted, thereby ensuring that doctors can receive prompts in a timely manner when filling out the diagnosis report based on the target imaging report.

[0112] In addition, reference Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0113] Therefore, according to this embodiment, the technical effect of being able to truly reflect the workload of doctors when filling out diagnosis reports based on imaging reports and further enhance the work enthusiasm of doctors is achieved.

[0114] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0115] Through the description of the above embodiments, those skilled in the art will clearly understand that the methods according to the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0116] Example 2 Figure 7 FIG. 7 shows a device 700 for quantifying workload of an image report according to this embodiment, which corresponds to the method according to embodiment 1. Figure 7 As shown, the device 700 includes: a first feature extraction module 710, which is used to obtain a target imaging report corresponding to the patient, and use an NLP model to extract multiple first key features in the text content of the target imaging report, wherein the multiple first key features include examination items, the number of parts included, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is trauma, and whether there is a historical examination; an encoding module 720, which is used to encode each first key feature respectively using a preset encoding rule, and determine multiple feature codes corresponding to each first key feature and multiple coding values ​​corresponding to each feature code, wherein the encoding rule includes a key feature code and a coding value; a first data set generation module 730, which is used to generate a corresponding first data set based on multiple feature codes and multiple coding values; and a workload determination module 740, which is used to input the first data set into a preset workload prediction model and determine the workload corresponding to the target imaging report.

[0117] Optionally, the apparatus 700 further includes: a model training module, configured to construct a workload prediction model and train the workload prediction model.

[0118] Optionally, the model training module includes: an input sample determination module for determining input samples for training the workload prediction model; an output sample determination module for determining output samples for training the workload prediction model; and a model training submodule for training the workload prediction model using input samples and output samples.

[0119] Optionally, the model training submodule includes: a second key feature extraction module, which is used to collect multiple imaging report samples and use the NLP model to extract multiple second key features of each imaging report sample; a second data set generation module, which is used to encode each second key feature respectively using pre-set encoding rules and generate corresponding multiple second data sets; a workload determination module, which is used to determine the workload of diagnosing each imaging report sample; and a model training submodule, which is used to take the multiple second data sets as input samples, the workload corresponding to each imaging report sample as output sample, and train the workload prediction model.

[0120] Therefore, according to this embodiment, a technical effect is achieved that can truly reflect the workload of doctors when filling out diagnosis reports based on imaging reports, and further enhance the work enthusiasm of doctors.

[0121] Example 3 Figure 8 FIG. 8 shows a device 800 for quantifying workload of an image report according to this embodiment, which corresponds to the method according to embodiment 1. Figure 8 As shown, the device 800 includes: a processor 810; and a memory 820, which is connected to the processor 810 and is used to provide the processor 810 with instructions for processing the following processing steps: obtaining a target imaging report corresponding to the patient, and using an NLP model to extract multiple first key features in the text content of the target imaging report, wherein the multiple first key features include examination items, the number of parts included, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is trauma, and whether there is a historical examination; using a preset coding rule to encode each first key feature respectively, and determine multiple feature codes corresponding to each first key feature and multiple coding values ​​corresponding to each feature code, wherein the coding rule includes a key feature code and a coding value; generating a corresponding first data set based on the multiple feature codes and the multiple coding values; and inputting the first data set into a preset workload prediction model, and determining the workload corresponding to the target imaging report.

[0122] Optionally, the apparatus 800 further includes: constructing a workload prediction model, and training the workload prediction model.

[0123] Optionally, the operations of constructing a workload prediction model and training the workload prediction model include: determining input samples for training the workload prediction model; determining output samples for training the workload prediction model; and training the workload prediction model using the input samples and the output samples.

[0124] Optionally, the operation of training the workload prediction model using input samples and output samples includes: collecting multiple imaging report samples, and extracting multiple second key features of each imaging report sample using an NLP model; encoding each second key feature separately using pre-set encoding rules, and generating corresponding multiple second data sets; determining the workload of diagnosing each imaging report sample; and using multiple second data sets as input samples, and the workload corresponding to each imaging report sample as output samples, and training the workload prediction model.

[0125] Therefore, according to this embodiment, a technical effect is achieved that can truly reflect the workload of doctors when filling out diagnosis reports based on imaging reports, and further enhance the work enthusiasm of doctors.

[0126] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0127] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0131] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0132] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for quantifying workload of image reporting, characterized in that: include: Obtain a target imaging report corresponding to the patient, and extract a plurality of first key features in the text content of the target imaging report using an NLP model, wherein the plurality of first key features include examination items, the number of included parts, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is trauma, and whether there is a historical examination; Encode each first key feature respectively using a preset encoding rule, and determine a plurality of feature codes corresponding to each first key feature and a plurality of encoding values ​​corresponding to each feature code, wherein the encoding rule includes a key feature code and an encoding value; Based on the plurality of feature codes and the plurality of code values, generating a corresponding first data set; as well as The first data set is input into a preset workload prediction model, and the workload corresponding to the target image report is determined.

2. The method according to claim 1, characterized in that Also includes: Constructing the workload prediction model and training the workload prediction model.

3. The method according to claim 2, characterized in that The operations of constructing the workload prediction model and training the workload prediction model include: Determining input samples for training the workload prediction model; Determining output samples for training the workload prediction model; and The workload prediction model is trained using the input samples and the output samples.

4. The method according to claim 3, characterized in that The operation of training the workload prediction model using the input sample and the output sample includes: Acquire multiple imaging report samples, and extract multiple second key features from each imaging report sample using the NLP model; Encode each second key feature using a preset encoding rule, and generate a corresponding plurality of second data sets; Determining the workload corresponding to each of the image report samples; and The multiple second data sets are used as the input samples, the workload corresponding to each image report sample is used as the output sample, and the workload prediction model is trained.

5. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 4.

6. A device for quantifying workload of image reporting, characterized in that: include: a first feature extraction module, configured to obtain a target imaging report corresponding to the patient, and extract a plurality of first key features from the text content of the target imaging report using an NLP model, wherein the plurality of first key features include examination items, the number of included parts, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is a trauma, and whether there is a historical examination; An encoding module, used to encode each first key feature respectively using a preset encoding rule, and determine a plurality of feature codes corresponding to each first key feature and a plurality of encoding values ​​corresponding to each feature code, wherein the encoding rule includes a key feature code and an encoding value; A first data set generating module, configured to generate a corresponding first data set based on the plurality of feature codes and the plurality of code values; as well as A workload determination module is used to input the first data set into a preset workload prediction model and determine the workload corresponding to the target image report.

7. The device according to claim 6, characterized in that The device also includes: a model training module, which is used to construct the workload prediction model and train the workload prediction model.

8. The device according to claim 7, characterized in that The model training module includes: An input sample determination module, used to determine input samples for training the workload prediction model; an output sample determination module, used to determine output samples for training the workload prediction model; and The model training submodule is used to train the workload prediction model using the input samples and the output samples.

9. The device according to claim 8, characterized in that The model training submodule includes: A second key feature extraction module, used to obtain multiple image report samples, and extract multiple second key features of each image report sample using the NLP model; A second data set generation module, used to encode each second key feature respectively using a preset encoding rule, and generate a corresponding plurality of second data sets; A workload determination module, configured to determine the workload corresponding to each of the image report samples; and The model training submodule is used to use the multiple second data sets as the input samples, use the workload corresponding to each image report sample as the output sample, and train the workload prediction model.

10. A device for quantifying workload of image reporting, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Obtain a target imaging report corresponding to the patient, and extract a plurality of first key features in the text content of the target imaging report using an NLP model, wherein the plurality of first key features include examination items, the number of included parts, the number of positive parts, the number of lesions, the number of lesion measurements, the positive grade, whether it is an emergency, whether it is trauma, and whether there is a historical examination; Encode each first key feature respectively using a preset encoding rule, and determine a plurality of feature codes corresponding to each first key feature and a plurality of encoding values ​​corresponding to each feature code, wherein the encoding rule includes a key feature code and an encoding value; Based on the plurality of feature codes and the plurality of code values, generating a corresponding first data set; as well as The first data set is input into a preset workload prediction model, and the workload corresponding to the target image report is determined.

Images