Intelligent analysis method and system for medical examination data
By standardizing and intelligently analyzing medical test data, the high cost problem caused by manual classification has been solved, efficient data allocation and department matching have been achieved, and the hospital's operational efficiency has been improved.
Patent Information
- Application Number
- CN202510717629.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-30
- Publication Date
- 2025-09-16
AI Technical Summary
The existing technology of traditional Chinese medicine test data classification requires medical staff to perform manual classification, resulting in heavy workload and high time cost, which cannot meet the needs of efficient operation of hospitals.
Adopting intelligent analysis methods, the test data is received and standardized, event labels are assigned and sorted according to priority, department processing is matched, and analysis results are integrated. Efficiency is improved by using data standardization processing modules, department matching modules and analysis data integration modules.
It achieves efficient classification and distribution of medical test data, reduces manual intervention, improves data processing efficiency, and meets the hospital's efficient operation needs.
Smart Images
Figure CN120654055A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent analysis method and system for medical test data. Background Art
[0002] With the development of information technology and the advent of the intelligent era, information technology has been widely used in the medical industry, generating a large amount of medical data. The data growth in the medical industry is particularly significant. Analyzing massive amounts of clinical medical test data can effectively promote the advancement of the medical industry.
[0003] In the daily operation of hospitals, the management and distribution of medical test data are crucial. Currently, the classification of medical test data often relies on manual classification by medical staff, and then the department that processes the test data is determined. The classification workload is large and the time cost investment is high, resulting in inefficient data distribution and unable to meet the needs of efficient hospital operations. Summary of the Invention
[0004] The purpose of the present invention is to provide an intelligent analysis method and system for medical test data, aiming to solve the technical problem in the existing technology that the classification of medical test data often requires medical staff to perform manual classification and then determine the department that processes the test data. The classification workload is large and the time cost investment is high, resulting in low data allocation efficiency and failure to meet the needs of efficient hospital operation.
[0005] To achieve the above-mentioned purpose, the present invention adopts an intelligent analysis method of medical test data, comprising the following steps:
[0006] Receive inspection data, perform standardization on the inspection data, and obtain processing event data;
[0007] Assign event labels to the processing event data, sort the processing events according to the priority of the event labels, assign department processing labels, compare the event labels with the processing labels, and match the departments for the processing events;
[0008] Obtain departmental test analysis data, integrate analysis results for the same patient, and output them.
[0009] Among them, in the step of receiving the inspection data, performing standardization processing on the inspection data, and obtaining the processing event data:
[0010] Obtain inspection data and process the data according to the inspection data type;
[0011] Process text data and character data into standardized data, obtain processed event data, and output it.
[0012] After the step of processing the text data and word data into standardized data:
[0013] Assign reception time data to the standardized data.
[0014] Among them, in the steps of assigning event labels to processing event data, sorting processing events according to the priority of the event labels, assigning department processing labels, comparing the event labels with the processing labels, and matching departments for processing events:
[0015] Preset event tags, assign identification features to each event tag, and prioritize each event tag; the priorities include first-level priority, second-level priority, and third-level priority;
[0016] Extracting the main label features and auxiliary label features from the standardized event data, and matching the main label features and the auxiliary label features with recognition features;
[0017] Based on the matched identification features, it is determined whether the main tag is affected by the auxiliary tag, and event tags are assigned to the standardized event data. The priority of processing the event is determined and the acceptance time data is assigned.
[0018] After determining whether the primary tag is affected by the auxiliary tag based on the matched identification features, assigning event tags to the standardized event data, determining the priority of the event, and assigning the acceptance time data:
[0019] Assign a service label to each department, compare the event label of the processed event with the service label, and output the judgment threshold;
[0020] Match the accepting department based on the judgment threshold.
[0021] Among them, before obtaining departmental test analysis data, integrating analysis results for the same patient, and outputting the steps:
[0022] Obtain inspection time data and predict the inspection processing time of inspection data with the same event label.
[0023] Among them, in the step of obtaining the inspection time data and predicting the inspection processing time of the inspection data of the same event label:
[0024] After the processing event is completed, the inspection completion time data of the processing event is assigned;
[0025] For the receipt time data, acceptance time data and inspection completion time data, the acceptance time period and resolution time period are calculated respectively;
[0026] Count the acceptance and resolution time periods of multiple processing events with the same event tag, and predict the total estimated completion time of the processing events.
[0027] Among them, in the steps of obtaining departmental test analysis data, integrating analysis results for the same patient, and outputting:
[0028] Obtain the test and analysis results data of the same patient from various departments, integrate the test and analysis results of the same patient from different departments, obtain the correlation between various indicators, and form a test and analysis report.
[0029] The present invention also provides an intelligent analysis system for medical test data, including a data standardization processing module, a department matching module, and an analysis data integration module; wherein:
[0030] The data standardization processing module is used to receive the inspection data, perform standardization processing on the inspection data, and obtain processing event data;
[0031] The department matching module is used to assign event tags to processing event data, sort processing events according to the priority of the event tags, assign department processing tags, compare the event tags with the processing tags, and match departments for processing events;
[0032] The analysis data integration module is used to obtain departmental test analysis data, integrate analysis results for the same patient, and output them.
[0033] An intelligent analysis method and system for medical test data of the present invention uses the data standardization processing module, the department matching module and the analysis data integration module to perform the following process: receiving test data, standardizing the test data to obtain processing event data; assigning event labels to the processing event data, sorting the processing events according to the priority of the event labels, and assigning department processing labels, comparing the event labels with the processing labels, and matching departments for the processing events; obtaining department test analysis data, integrating analysis results for the same patient, and outputting them; by assigning corresponding departments according to the test data, converting the patient's current test data into processing events, matching departments for processing events, clarifying the departments that process the test data, and improving the efficiency of test data processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0035] Figure 1 It is a flowchart of the steps of the intelligent analysis method of medical test data of the present invention.
[0036] Figure 2It is a step flow chart of S100 of the present invention.
[0037] Figure 3 It is a step flow chart of S200 of the present invention.
[0038] Figure 4 It is a step flow chart of S300 of the present invention.
[0039] Figure 5 It is a structural principle diagram of the intelligent analysis system for medical test data of the present invention.
[0040] Figure 6 It is a structural principle diagram of the electronic device of the present invention.
[0041] 501-data standardization processing module, 502-department matching module, 503-processing time prediction module, 504-analysis data integration module. DETAILED DESCRIPTION
[0042] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with this application.
[0043] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
[0044] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0045] See also Figures 1 to 4 The present invention provides an intelligent analysis method for medical test data, comprising the following steps:
[0046] S100: receiving inspection data, performing standardization processing on the inspection data, and obtaining processing event data.
[0047] In this embodiment, the test data is received and standardized to obtain the processed event data. The specific process is as follows:
[0048] S101: Acquire test data and process the data according to the test data type;
[0049] S102: Process the text data and word data into standardized data, add reception time data, obtain processing event data, and output it.
[0050] During the above process, raw test data is received from various testing equipment, external systems, or data interfaces. This data may come from different testing instruments and have different formats and units. For example, routine blood test data includes items such as white blood cell count and red blood cell count; biochemical test data includes blood sugar and liver function indicators. The received test data is standardized according to pre-set standard rules. For example, data in different units can be uniformly converted to international standard units, or test results from different instruments can be mapped to a unified reference range to facilitate subsequent data processing and analysis. After standardization, processed event data is obtained, which has a unified format and units, facilitating subsequent operations.
[0051] S200: assigning event tags to processing event data, sorting processing events according to the priority of the event tags, assigning department processing tags, comparing the event tags with the processing tags, and matching departments for processing events.
[0052] In this embodiment, event tags are assigned to the processing event data, and the processing events are sorted according to the priority of the event tags. The department processing tags are assigned, and the event tags are compared with the processing tags to match the departments for the processing events. The specific process is as follows:
[0053] S201: Preset event tags, assign identification features to each event tag, and prioritize each event tag; the priorities include first-level priority, second-level priority, and third-level priority;
[0054] S202: extracting the main label features and the auxiliary label features from the standardized event data, and matching the main label features and the auxiliary label features with recognition features;
[0055] S203: Based on the matched identification features, determine whether the primary tag is affected by the auxiliary tag, assign an event tag to the standardized event data, determine the priority of the event, and assign acceptance time data;
[0056] S204: Assign a service label to each department, compare the event label of the processed event with the service label, and output a judgment threshold;
[0057] S205: Match the accepting department according to the judgment threshold.
[0058] In the above process, each event tag is assigned a unique feature that can accurately identify and locate the event. The following are the identification features corresponding to each tag:
[0059] 1. Critical Value Reporting Events
[0060] Numerical features: Set clear critical value range thresholds, such as the specific numerical ranges of indicators such as blood potassium and blood sugar. When the test results exceed these thresholds, the event tag is triggered.
[0061] Patient information association: Record the patient's age, underlying diseases, and other information. For example, for patients with a history of heart disease, changes in certain test indicators that are not normally within the critical range may also require special attention and can be used as auxiliary identification features.
[0062] Test item identification: clarify which test items are related to critical values, such as specific indicators of common items such as blood routine, complete biochemistry set, coagulation function, etc.
[0063] 2. Abnormal Fluctuation of Test Results
[0064] Time series data: Collect the patient's test results data for multiple consecutive times and record the time point of each test.
[0065] Fluctuation Calculation: Set the calculation method for the fluctuation range, such as calculating the percentage difference between two consecutive test results, or the degree of deviation from the historical average. For example, a patient's white blood cell count fluctuates significantly for three consecutive times.
[0066] Physiological fluctuation range reference: Combined with the patient's age, gender, physiological status and other factors, refer to the normal physiological fluctuation range to determine whether the current fluctuation exceeds the normal range.
[0067] 3. Inspection sample quality issues
[0068] Sample appearance characteristics: record the appearance of the sample, such as whether it is hemolyzed (serum is red), lipemic (serum is milky white), icteric (serum is darker yellow), etc.
[0069] Sample volume information: Clarify the sample volume standards required for different test items and record the actual sample volume collected. For example, some biochemistry tests require a serum sample volume of at least 1ml. If the actual collected volume is only 0.5ml, it can be identified as insufficient sample volume.
[0070] Specimen identification information: Check whether the patient's name, gender, age, test items and other information on the specimen container are consistent with the application form, and whether there are any identification errors or omissions.
[0071] 4. Inspection equipment failure incident
[0072] Fault codes or alarm messages: Modern testing equipment often has fault diagnosis capabilities and will display corresponding fault codes or alarm messages. Recording these codes and messages is important for identifying equipment faults.
[0073] Abnormal equipment operating parameters: Monitor equipment operating parameters such as temperature, pressure, and speed. When these parameters exceed the normal range, it indicates a possible equipment failure. For example, the constant temperature bath of a biochemistry analyzer should be stable at around 37°C. If the temperature fluctuates by more than ±0.5°C, there may be a problem.
[0074] Equipment operation log: Check the equipment operation log, analyze the equipment operation records before and after the fault occurs, and determine whether the fault is caused by improper operation.
[0075] 5. Events of expired or quality problems with test reagents
[0076] Reagent validity period information: Record the production date and validity expiration date of the reagent, and check before using the reagent. If the validity period has exceeded, the reagent is considered expired.
[0077] Reagent appearance inspection: Observe the appearance of the reagents, such as whether there is precipitation, discoloration, turbidity, container damage, etc. For example, some reagents should be clear and transparent liquids. If turbidity or precipitation occurs, there may be quality problems.
[0078] Reagent batch number traceability: Record the batch number information of the reagent. When multiple abnormal test results occur for the same batch of reagents, it is possible to trace whether there are quality problems with the batch of reagents.
[0079] 6. Incidents of missed inspection items
[0080] Comparison of medical orders and test items: Obtain the patient's medical order information from the hospital information system to identify the list of tests prescribed by the doctor. Compare the actual tests performed with the medical order list to identify any that were not performed.
[0081] Inspection application form audit records: Check the inspection application form audit records to understand whether any missed inspections were found during the audit process and how the auditors handled them.
[0082] Patient feedback information: Collect patient feedback on test items. For example, if a patient indicates that they did not undergo a test item that the doctor informed them of, this can be used as an auxiliary identification feature for missed tests.
[0083] Prioritize each event tag based on factors such as the urgency of the event, its impact on medical safety, and the complexity of subsequent treatment measures:
[0084] Level 1 priority, event label: Critical value reporting event
[0085] Critical value reports are directly related to patient safety. If not promptly addressed, they could worsen the patient's condition or even endanger their life. For example, severe hyperkalemia could trigger cardiac arrest, necessitating immediate notification to clinicians and appropriate treatment. These incidents must be prioritized to ensure the fastest possible response.
[0086] Secondary priority, event labels: abnormal test result fluctuation events, test sample quality problem events
[0087] Classification Basis: Abnormal Fluctuation in Test Results: Abnormal fluctuations in a patient's test results may indicate a change in their condition or a test error. If not promptly identified and addressed, these changes may delay treatment; test errors may lead to incorrect diagnoses and treatment plans. Therefore, these events require prompt investigation and resolution to determine the cause of the fluctuation and implement appropriate measures. However, these events are considered less urgent than critical value events.
[0088] Test sample quality issues: Poor sample quality can affect the accuracy of test results, which in turn can impact doctors' diagnostic and treatment decisions. While not immediately life-threatening, it can lead to misdiagnosis or missed diagnosis, posing potential risks to patients. Therefore, re-collecting samples or implementing other remedial measures as soon as possible is necessary to ensure the reliability of test results.
[0089] Level 3 priority, event labels: test equipment failure event, test reagent expiration or quality problem event, test item missed event
[0090] Categorized by: Laboratory Equipment Failure: Equipment failures can disrupt normal laboratory work, but can usually be resolved gradually by activating backup equipment or arranging repairs. While some tests may be delayed during equipment failures, this generally does not significantly impact immediate patient care. However, prolonged or frequent equipment failures can impact laboratory efficiency and patient satisfaction, requiring prompt attention, but are considered a relatively low priority.
[0091] Expired or quality-issued test reagents: Reagent issues can affect the accuracy of test results, but they can generally be corrected by replacing the reagents or retesting. For issued error reports, tracing and correcting them can reduce the impact on patients. Compared to equipment failures and sample quality issues, handling this issue has a longer timeline.
[0092] Missed test items: Missed tests may affect the overall assessment of a patient's condition, but if discovered during subsequent examinations or treatment, additional testing may be performed. Compared to the other events listed above, these missed tests have a relatively small impact on the patient's current treatment and can be gradually improved through process refinement and enhanced auditing.
[0093] Extract primary and secondary features from standardized event data. Primary features directly reflect the core nature of the event, while secondary features supplement the primary features or aid in decision-making. For example, for a device failure event, the primary feature might be the device type, while secondary features might include the time of failure, frequency, and so on.
[0094] The extracted primary and secondary tag features are matched with the identification features of the preset event tag. Feature matching can be achieved using string matching algorithms (such as exact matching, fuzzy matching), numerical comparison algorithms, etc. For example, if the extracted device type feature matches the device type in the identification features of the "device failure" event tag, then the event is considered to be related to the "device failure" event tag.
[0095] Based on the matched identification features, analyze whether the auxiliary tag features will affect the main tag features and thus affect the event judgment. For example, if the auxiliary tag features show that the equipment failure occurred during the critical business time period, then even if the main tag features indicate that the fault type is a general fault, it may be necessary to increase the priority of the event. This judgment process can be implemented using conditional judgment statements or decision tree algorithms. Assume that the auxiliary tag feature set is F auxiliary ={f1,f2,…,f n}, the main label feature is F main , by defining a series of rules R i To determine whether the auxiliary label affects the main label, that is:
[0096] If R1(F auxiliary ,F main ), then the auxiliary tag is considered to have a positive impact on the main tag, that is, to increase its priority;
[0097] If R2(F auxiliary ,F main ), the auxiliary tag is considered to have a negative impact on the main tag, that is, the priority is reduced;
[0098] Otherwise, the auxiliary label is considered to have no effect on the primary label.
[0099] The event label for the event is determined based on the feature matching results and the impact judgment of the auxiliary labels. The final priority of the event is determined by combining the preset priority of the event label and the impact judgment of the auxiliary labels. For example, if the event label is preset as priority 2, but the auxiliary labels indicate that the event has a large impact, the priority can be raised to priority 1.
[0100] According to the priority of the event, the corresponding acceptance time data is assigned to the event.
[0101] For example, a first-level priority event needs to be handled within t1, a second-level priority event needs to be handled within t2, and a third-level priority event needs to be handled within t3, where t1 <t2<t3。
[0102] Assign a service label to each department, compare the event label of the processed event with the service label, calculate the similarity or matching degree between the two, and match the receiving department.
[0103] S300: Acquire inspection time data and predict the inspection processing time of inspection data with the same event tag.
[0104] In this embodiment, the inspection time data is obtained and the inspection processing time of the inspection data of the same event tag is predicted. The specific process is:
[0105] S301: After the processing event is completed, the inspection completion time data of the processing event is assigned;
[0106] S302: Calculate the acceptance time period and the resolution time period for the reception time data, the acceptance time data, and the inspection completion time data;
[0107] S303: Counting the acceptance time periods and resolution time periods of multiple processing events with the same event tag, and predicting the total estimated completion time of the processing events.
[0108] During the above process, test data with the same event tag is collected from historical test data, including key time node information such as test application time, sample receipt time, test start time, and test completion time. For example, for the "abnormal blood sugar" event tag, test time data for all patients with abnormal blood sugar over a period of time is collected. Data analysis models such as regression analysis and time series analysis are used to process and analyze the collected test time data, identify key factors affecting test processing time, and establish a prediction model. This model predicts the test processing time of test data with the same event tag based on the event tag and related information of the current test data to be processed, providing a reference for subsequent process arrangements and patient notification.
[0109] S400: Obtain departmental test analysis data, integrate analysis results for the same patient, and output.
[0110] In this embodiment, departmental test and analysis data is obtained, and the analysis results for the same patient are integrated and output. The specific process is: the test and analysis result data of the same patient is obtained from various departments, and the test and analysis results of the same patient from different departments are integrated to obtain the correlation between various indicators and form a test and analysis report.
[0111] During the above process, test and analysis data for the same patient is obtained from various departments. This data may include the values of various indicators in the test report, diagnostic opinions, recommended measures, and other content. For example, for a patient who undergoes both a routine blood test and a biochemical test, the routine blood test analysis results are obtained from the hematology department, and the biochemical test analysis results are obtained from the endocrinology department. The test and analysis results of the same patient from different departments are then integrated to obtain the correlation between the various indicators and form a test and analysis report. During the integration process, a comprehensive analysis of the various indicators is performed to identify the correlations between the indicators and potential health problems. For example, an abnormal white blood cell count in a routine blood test is correlated with an elevated inflammatory indicator in a biochemical test to determine whether the patient has an infection or other conditions.
[0112] The integrated test and analysis reports are output in a suitable format, such as paper reports for patients to collect, or electronic reports sent through the hospital information system to the patient's personal health record or designated mobile device for easy viewing and use by patients and doctors. The system can also generate statistical reports as needed to provide data support for hospital management and decision-making.
[0113] In the present invention, test data is received, standardized, and processed event data is obtained; event labels are assigned to the processed event data, and the processing events are sorted according to the priority of the event labels, and department processing labels are assigned. The event labels are compared with the processing labels to match the departments for the processing events; test time data is obtained to predict the test processing time of the test data with the same event label; department test analysis data is obtained, and the analysis results for the same patient are integrated and output; by assigning the corresponding department according to the test data, the patient's current test data is converted into processing events, and the departments are matched with the processing events to clarify the departments that process the test data, thereby improving the test data processing efficiency.
[0114] Corresponding to the aforementioned embodiment of the intelligent analysis method for medical test data, the present application also provides an embodiment of an intelligent analysis system for medical test data.
[0115] Figure 5 FIG1 is a block diagram of an intelligent analysis system for medical test data according to an exemplary embodiment. Figure 5The system may include: a data standardization processing module 501, a department matching module 502, a processing time prediction module 503 and an analysis data integration module 504; wherein:
[0116] The data standardization processing module 501 is used to receive test data, perform standardization processing on the test data, and obtain processing event data;
[0117] The department matching module 502 is used to assign event tags to the processing event data, sort the processing events according to the priority of the event tags, assign department processing tags, compare the event tags with the processing tags, and match the departments for the processing events;
[0118] The processing time prediction module 503 is used to obtain inspection time data and predict the inspection processing time of inspection data with the same event tag;
[0119] The analysis data integration module 504 is used to obtain departmental test analysis data, integrate analysis results for the same patient, and output them.
[0120] In this embodiment, the data standardization processing module 501 receives the test data, performs standardization processing on the test data, and obtains processing event data; the department matching module 502 assigns event labels to the processing event data, sorts the processing events according to the priority of the event labels, assigns department processing labels, compares the event labels with the processing labels, and matches the departments for the processing events; the processing time prediction module 503 obtains the test time data and predicts the test processing time of the test data with the same event label; the analysis data integration module 504 obtains the department test analysis data, integrates the analysis results for the same patient, and outputs them; by assigning the corresponding department according to the test data, the patient's current test data is converted into processing events, the department is matched with the processing events, the department that processes the test data is clarified, and the test data processing efficiency is improved.
[0121] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0122] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application. A person of ordinary skill in the art can understand and implement it without paying any creative work.
[0123] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned intelligent analysis method for medical test data. Figure 6 As shown in the figure, a hardware structure diagram of any device with data processing capability in an intelligent analysis system for medical test data provided by an embodiment of the present invention is shown. Figure 6 In addition to the processor, memory, and network interface shown, any device with data processing capabilities in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.
[0124] Accordingly, the present application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the intelligent analysis method for medical test data as described above. The computer-readable storage medium may be an internal storage unit of any device with data processing capabilities as described in any of the aforementioned embodiments, such as a hard disk or memory. The computer-readable storage medium may also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and may also be used to temporarily store data that has been output or is to be output.
[0125] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed in this application.
[0126] It will be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.
Claims
1. An intelligent analysis method for medical test data, characterized in that: The steps include: Receive inspection data, perform standardization on the inspection data, and obtain processing event data; Assign event labels to the processing event data, sort the processing events according to the priority of the event labels, assign department processing labels, compare the event labels with the processing labels, and match the departments for the processing events; Obtain departmental test analysis data, integrate analysis results for the same patient, and output them.
2. The intelligent analysis method for medical test data according to claim 1, characterized in that: In the steps of receiving inspection data, standardizing the inspection data, and obtaining processing event data: Obtain inspection data and process the data according to the inspection data type; Process text data and character data into standardized data, obtain processed event data, and output it.
3. The intelligent analysis method for medical test data according to claim 2, characterized in that: After the steps of processing text data and word data into normalized data: Assign reception time data to the standardized data.
4. The intelligent analysis method for medical test data according to claim 3, characterized in that: In the steps of assigning event labels to processing event data, sorting processing events according to the priority of the event labels, assigning department processing labels, comparing the event labels with the processing labels, and matching departments for processing events: Preset event tags, assign identification features to each event tag, and prioritize each event tag; the priorities include first-level priority, second-level priority, and third-level priority; Extracting the main label features and auxiliary label features from the standardized event data, and matching the main label features and the auxiliary label features with recognition features; Based on the matched identification features, it is determined whether the main tag is affected by the auxiliary tag, and event tags are assigned to the standardized event data. The priority of processing the event is determined and the acceptance time data is assigned.
5. The intelligent analysis method for medical test data according to claim 4, characterized in that: After determining whether the primary tag is affected by the auxiliary tag based on the matched identification features, assigning event tags to the standardized event data, determining the priority of handling the event, and assigning acceptance time data: Assign a service label to each department, compare the event label of the processed event with the service label, and output the judgment threshold; Match the accepting department based on the judgment threshold.
6. The intelligent analysis method for medical test data according to claim 5, characterized in that: Before obtaining departmental test analysis data, integrating analysis results for the same patient, and outputting the results: Obtain inspection time data and predict the inspection processing time of inspection data with the same event label.
7. The intelligent analysis method for medical test data according to claim 6, characterized in that: In the steps of obtaining inspection time data and predicting the inspection processing time of inspection data with the same event label: After the processing event is completed, the inspection completion time data of the processing event is assigned; For the receipt time data, acceptance time data and inspection completion time data, the acceptance time period and resolution time period are calculated respectively; Count the acceptance and resolution time periods of multiple processing events with the same event tag, and predict the total estimated completion time of the processing events.
8. The intelligent analysis method for medical test data according to claim 7, characterized in that: In the steps of obtaining departmental test analysis data, integrating analysis results for the same patient, and outputting: Obtain the test and analysis results data of the same patient from various departments, integrate the test and analysis results of the same patient from different departments, obtain the correlation between various indicators, and form a test and analysis report.
9. An intelligent analysis system for medical test data, applied to the intelligent analysis method for medical test data according to claim 1, characterized in that: It includes data standardization processing module, department matching module and analysis data integration module; among which: The data standardization processing module is used to receive the inspection data, perform standardization processing on the inspection data, and obtain processing event data; The department matching module is used to assign event tags to processing event data, sort processing events according to the priority of the event tags, assign department processing tags, compare the event tags with the processing tags, and match departments for processing events; The analysis data integration module is used to obtain departmental test analysis data, integrate analysis results for the same patient, and output them.