Laboratory Information Management System Based on Digitalization

Abstract

The present invention discloses a laboratory information management system based on digitization. The present invention receives a patient's test data packet and determines whether the patient is a follow-up patient or a newly added patient. When the patient is determined to be a follow-up patient, the present invention extracts the patient's relevant historical test data and the test data packet from a database for comprehensive analysis. By constructing a change trend graph and calculating a slope, an evaluation of the change trend of abnormal indicators is provided. At the same time, the concepts of hidden danger points and hidden danger levels are introduced to make the hidden danger evaluation clearer and more specific, thereby generating a follow-up report for the follow-up patient and a new diagnosis report for the newly added patient, thereby solving the problem in the prior art of failing to effectively distinguish and adopt different treatment strategies when dealing with follow-up patients and newly added patients.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information management, and in particular to a laboratory information management system based on digitization. Background Art

[0002] With the rapid development of medical informatization, laboratory medical information management system has become an important part of hospital management.

[0003] However, the laboratory information management system in the prior art still has the following deficiencies:

[0004] Although existing information management systems are capable of processing patients' test data, they usually lack efficient and in-depth analysis capabilities, resulting in failure to effectively distinguish and adopt different treatment strategies when dealing with returning patients and new patients. The intelligence and pertinence of information management need to be improved;

[0005] At the same time, when patients receive reports generated by laboratory test data and need expert evaluation, it is impossible to effectively screen suitable experts who meet the requirements at the current time point and evaluate the patient's report, and there are limitations in the use of the system.

[0006] To this end, a digital laboratory information management system was launched. Summary of the invention

[0007] In view of this, the present invention provides a digital laboratory information management system to solve the problems raised by the above background technology.

[0008] The purpose of the present invention can be achieved through the following technical solutions: A digital laboratory information management system comprising:

[0009] Data collection module: collects the patient's test data, analyzes the collected test data through the medical equipment connected to the laboratory, summarizes the analyzed test data index results into the patient's test data package and sends it to the data tracing module;

[0010] Data tracing module: Receive the patient's test data packet, extract the patient's personal information from the test data packet as a matching basis; match the extracted patient personal information with the personal information set stored in the pre-built database; if the match is successful, the patient is regarded as a follow-up patient and a follow-up signal is sent to the report generation module; if the match fails, the patient is regarded as a new patient and a new signal is sent to the report generation module;

[0011] Report generation module: receives the follow-up signal generated by the patient, extracts the patient's relevant historical test data and test data package from the database for comprehensive analysis, and generates the patient's follow-up report;

[0012] It is also used to receive new signaling generated by the patient, extract the patient's test data packet for analysis, and generate the patient's diagnosis report;

[0013] Expert evaluation module: When a patient receives a follow-up report or a diagnosis report, the expert evaluation signal is selectively triggered, and when the expert evaluation signal is triggered, the patient sends his or her own follow-up report or diagnosis report to the candidate expert with the largest superior diagnosis value Yz at the current time point. After the candidate expert evaluates the patient's follow-up report or diagnosis report, the evaluation content is added to the patient's follow-up report or diagnosis report, and the supplemented follow-up report or diagnosis report is sent to the patient;

[0014] Data encryption module: Encrypt the patient's follow-up report or diagnosis report and store it in the constructed database.

[0015] In some embodiments, relevant historical test data and test data packets of the patient are extracted from the database for comprehensive analysis, specifically:

[0016] Parse the patient's test data package, extract the results of the various data indicators of the patient's corresponding tests, and extract the normal reference range of the various test data indicators corresponding to the current patient from the pre-built database;

[0017] Compare the results of each data indicator of the patient's corresponding test with the corresponding normal reference range. If the comparison shows that a data indicator result is outside the corresponding normal reference range, mark the indicator as an abnormal indicator;

[0018] At the same time, historical indicator results matching the abnormal indicators are extracted from the patient's relevant historical test data. If the historical indicator results corresponding to the patient's abnormal indicators are all within the normal reference range, the patient's abnormal indicators are judged as suddenly added abnormalities; if one or more groups of historical indicator results corresponding to the patient's abnormal indicators are outside the normal reference range, the patient's abnormal indicators are judged as long-term abnormalities.

[0019] In some embodiments, extracting relevant historical test data and test data packets of the patient from the database for comprehensive analysis also includes:

[0020] If the abnormal index is determined to be a long-term abnormality, the patient's abnormal index is first converted into a hidden danger score, and then a change trend chart of the patient's corresponding abnormal index is constructed;

[0021] Preset the value ranges of each group of indicator results corresponding to the abnormal indicators, and set each group of indicator result value ranges to correspond to a hidden danger score; match the patient's abnormal indicators with the preset value ranges of each group of indicator results, so as to obtain the hidden danger score corresponding to the abnormal indicator of the patient;

[0022] Draw the patient's current hidden danger score and the corresponding historical hidden danger scores in the change trend diagram; connect adjacent numerical points to obtain the hidden danger line of the abnormal indicator; at the same time, preset the highest threshold of the hidden danger score corresponding to the abnormal indicator, and draw the threshold line corresponding to the highest threshold in the change trend diagram;

[0023] Calculate the slope of each hidden danger line and the angle between it and the horizontal line. If the angle between a hidden danger line and the horizontal line is an acute angle, mark the slope of the hidden danger line as a descending slope. If the angle between a hidden danger line and the horizontal line is an obtuse angle, mark the slope of the hidden danger line as an ascending slope.

[0024] Sum all the rising slopes and falling slopes respectively to get the rising estimate and the falling estimate, and calculate the ratio of the rising estimate to the falling estimate, that is, through , obtain the change trend value of the patient's corresponding abnormal indicator;

[0025] Three groups of trend value ranges are preset for the change trend values, and the three groups of trend value ranges are set to correspond to three groups of evaluation results, respectively, and the three groups of evaluation results are a gradually decreasing trend, a gradually increasing trend, and an ups and downs fluctuation trend; the change trend value of the patient's corresponding abnormal indicator is matched with the preset three groups of trend value ranges, so as to obtain the evaluation result of the patient's corresponding abnormal indicator.

[0026] In some embodiments, a follow-up report for a patient is generated, specifically:

[0027] Construct vertical lines between the patient's current hidden danger score and the corresponding numerical points drawn for each historical hidden danger score and the threshold line, calculate the length of each constructed vertical line, calculate the average of the vertical line lengths corresponding to each historical hidden danger score, and use the calculated result as the average length of the historical indicator corresponding to the abnormal indicator of the patient;

[0028] Extract the length of the vertical line corresponding to the patient's hidden danger score as the average length of the detection index of the patient corresponding to the abnormal index; set the weight coefficient corresponding to the average length of the historical index and the average length of the detection index, multiply the average length of the historical index and the average length of the detection index corresponding to the abnormal index of the patient by the set weight coefficient respectively, and then sum them, divide the preset correction value by the summed result, and obtain the hidden danger assessment value of the patient corresponding to the abnormal index;

[0029] Three groups of assessment value ranges corresponding to the preset hidden danger assessment values ​​are set, and the three groups of assessment value ranges are respectively corresponding to a hidden danger level, and the hidden danger levels are respectively a lower hidden danger level, a general hidden danger level and a higher hidden danger level;

[0030] Matching the hidden danger assessment value of the patient corresponding to the abnormal indicator with the three preset assessment value ranges, thereby obtaining the hidden danger level of the patient corresponding to the abnormal indicator;

[0031] The above analysis results are integrated and filled into the preset report template to generate the patient's follow-up report.

[0032] In some embodiments, a diagnostic report for a patient is generated, specifically:

[0033] Parse the patient's test data packets, extract the data indicator results of the patient's corresponding tests, fill the patient's personal information and various data indicator results into the preset report template, and based on the comparison of the various data indicator results with the corresponding normal reference range, mark the abnormal indicators in the filled report template, and generate the patient's diagnosis report after marking.

[0034] In some embodiments, when the expert evaluation signaling is triggered, the follow-up report or diagnosis report is sent to the candidate expert with the largest excellent diagnosis value Yz at the current time point, specifically:

[0035] When receiving the follow-up report or diagnosis report of the patient, screen the range of experts based on the types of abnormal indicators appearing in the follow-up report or diagnosis report, select the experts who meet the requirements and mark them as candidate experts;

[0036] The number of reports to be processed by each candidate expert at the current time point is counted and marked as h1; at the same time, the number of historical reports processed by each candidate expert is obtained and marked as h2, and the patient's satisfaction score for the expert is extracted from each historical report processing of each candidate expert; the average of the satisfaction scores of each group is taken as the professional valuation h3 of each candidate expert;

[0037] According to the formula , weighted calculation is performed on the number of pending reports h1, the number of historical report processing h2, and the professional valuation h3 of each candidate expert, so as to obtain the excellent diagnosis value Yz of each candidate expert; where a1, a2, and a3 are the influencing weight factors of the number of pending reports h1, the number of historical report processing h2, and the professional valuation h3 respectively; the candidate expert with the largest excellent diagnosis value Yz is selected, and the number of pending reports of this expert is increased by one.

[0038] In some embodiments, the patient's follow-up report or diagnosis report is encrypted, specifically:

[0039] First, the patient's name spelling letters and the report generation date are extracted from the patient's personal information, and the patient's name spelling letters are converted into numbers based on the preset conversion rules, and each group of letters is set to correspond to a number;

[0040] After converting the spelling letters of the patient's name into numbers, a string of numbers is obtained, and the constituent numbers of the patient report generation date are further extracted and added to the number set to obtain a new string of numbers;

[0041] Preset an encryption conversion formula; substitute each group of numbers in the new string of numbers into the preset encryption conversion formula for calculation, and after the calculation is completed, obtain the final encrypted number set;

[0042] Based on each group of numbers in the encrypted digital set, an encrypted graphic of the patient's follow-up report or diagnosis report is drawn, the number of numbers in the encrypted digital set is counted, and a bar frame equal to the number of numbers is drawn. The groups of bar frames are sorted in sequence, and the blank areas of the bar frames are filled with each group of numbers in the encrypted digital set as the filling area. After the filling is completed, the remaining blank areas of each bar frame after filling are intercepted. After the interception is completed, the encrypted graphic of the patient's follow-up report or diagnosis report is obtained.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention receives the patient's test data packet and determines whether the patient is a returning patient or a newly added patient. When the patient is determined to be a returning patient, the relevant historical test data of the patient and the test data packet are extracted from the database for comprehensive analysis. By constructing a change trend graph and calculating the slope, an evaluation of the change trend of abnormal indicators is provided. At the same time, the concepts of hidden danger points and hidden danger levels are introduced to make the hidden danger evaluation clearer and more specific, thereby generating a return visit report for the returning patient and a new diagnosis report for the newly added patient, thereby solving the problem in the prior art of failing to effectively distinguish and adopt different treatment strategies when dealing with returning patients and newly added patients.

[0045] The present invention selectively triggers an expert evaluation signal when the patient receives a follow-up report or a diagnosis report, and when the expert evaluation signal is triggered, sends the patient's follow-up report or diagnosis report to the candidate expert with the largest optimal diagnosis value at the current time point. By calculating the optimal diagnosis value, the most suitable expert is selected for report evaluation, thereby improving processing efficiency and ensuring patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0047] Figure 1 It is a principle block diagram of the present invention;

[0048] Figure 2 It is a schematic diagram of a change trend diagram in the present invention;

[0049] Figure 3 It is a schematic diagram of the encrypted graph in the present invention. DETAILED DESCRIPTION

[0050] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete, and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0051] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined as such herein.

[0052] See also Figure 1-Figure 2 As shown, the digital laboratory information management system includes a data acquisition module, a data tracing module, a report generation module, an expert evaluation module and a data encryption module;

[0053] The data collection module is used to collect the patient's test data, analyze the collected test data through the medical equipment connected in the laboratory, summarize the analyzed test data index results into the patient's test data package and send it to the data tracing module;

[0054] Test data such as blood, biochemistry, and immunity are collected and analyzed according to patient needs;

[0055] The data acquisition module is integrated with various medical testing equipment in the laboratory (such as blood analyzers, biochemical analyzers, immunoassay analyzers, etc.) at the hardware or software level to ensure that data from these devices can be received;

[0056] The data tracing module is used to receive the patient's test data packet, extract the patient's personal information from the test data packet as a matching basis; the personal information is the patient's ID or identity card number; match the extracted patient's personal information with the personal information set stored in the pre-built database; the personal information set includes all historical patient information; if the match is successful, the patient is regarded as a follow-up patient and a follow-up signal is sent to the report generation module; if the match fails, the patient is regarded as a new patient and a new signal is sent to the report generation module;

[0057] The report generation module is used to receive the follow-up signal generated by the patient, and extract the patient's relevant historical test data and test data package from the database for comprehensive analysis to generate the patient's follow-up report; the patient's relevant historical test data is the patient's historical test data packages stored in the database;

[0058] Specifically:

[0059] Parse the patient's test data package, extract the results of various data indicators of the patient's corresponding tests, and extract the normal reference range of various test data indicators corresponding to the current patient from the pre-built database; the normal reference range of the test data indicators is set based on multiple factors such as age, gender, weight, etc. in the patient's personal information;

[0060] Compare the results of each data indicator of the patient's corresponding test with the corresponding normal reference range. If the comparison shows that a data indicator result is outside the corresponding normal reference range, mark the indicator as an abnormal indicator;

[0061] At the same time, historical indicator results matching the abnormal indicators are extracted from the patient's relevant historical test data. If the historical indicator results corresponding to the abnormal indicators of the patient are all within the normal reference range, the abnormal indicators of the patient are determined to be suddenly newly abnormal; if one or more groups of historical indicator results corresponding to the abnormal indicators of the patient are outside the normal reference range, the abnormal indicators of the patient are determined to be long-term abnormal;

[0062] If the abnormal index is determined to be a long-term abnormality, the patient's abnormal index is first converted into a hidden danger score, and then a change trend chart of the patient's corresponding abnormal index is constructed;

[0063] Preset the value ranges of each group of indicator results corresponding to the abnormal indicators, and set each group of indicator result value ranges to correspond to a hidden danger score; match the patient's abnormal indicators with the preset value ranges of each group of indicator results, so as to obtain the hidden danger score corresponding to the abnormal indicator of the patient;

[0064] The hidden danger score range is set at 5-15, and the more the abnormal index result deviates from the corresponding normal reference range, the higher the hidden danger score obtained by matching. The higher the hidden danger score, the greater the hidden danger of the abnormal index of the patient;

[0065] Draw the patient's current hidden danger score and the corresponding historical hidden danger scores in the change trend chart. The numerical points are drawn in order based on time, and the historical hidden danger scores are similar to the above conversion rules to match the indicator results and then converted;

[0066] Connect adjacent numerical points to obtain the hidden danger line of the abnormal indicator; at the same time, preset the highest threshold of the hidden danger score corresponding to the abnormal indicator, and draw the threshold line corresponding to the highest threshold in the change trend diagram;

[0067] Calculate the slope of each hidden danger line and the angle between it and the horizontal line. If the angle between a hidden danger line and the horizontal line is an acute angle, mark the slope of the hidden danger line as a descending slope. If the angle between a hidden danger line and the horizontal line is an obtuse angle, mark the slope of the hidden danger line as an ascending slope.

[0068] Sum all the rising slopes and falling slopes respectively to get the rising estimate and the falling estimate, and calculate the ratio of the rising estimate to the falling estimate, that is, through , obtain the change trend value of the patient's corresponding abnormal indicator;

[0069] Three groups of trend value ranges are preset for the change trend values, and the three groups of trend value ranges are set to correspond to three groups of evaluation results, respectively, and the three groups of evaluation results are a gradually decreasing trend, a gradually increasing trend, and an up and down fluctuation trend; the change trend value of the patient corresponding to the abnormal indicator is matched with the preset three groups of trend value ranges, so as to obtain the evaluation result of the patient corresponding to the abnormal indicator;

[0070] Construct vertical lines between the patient's current hidden danger score and the corresponding numerical points drawn for each historical hidden danger score and the threshold line, calculate the length of each constructed vertical line, calculate the average of the vertical line lengths corresponding to each historical hidden danger score, and use the calculated result as the average length of the historical indicator corresponding to the abnormal indicator of the patient;

[0071] Extract the vertical line length corresponding to the patient's hidden danger score as the average length of the patient's detection index corresponding to the abnormal index;

[0072] The smaller the average length of historical indicators and the average length of detection indicators, the closer the corresponding value point is to the threshold line, and the indicator result has a higher risk;

[0073] Set the weight coefficient corresponding to the average length of historical indicators and the average length of detection indicators, multiply the average length of historical indicators and the average length of detection indicators corresponding to the abnormal indicator of the patient by the set weight coefficient respectively, then sum them up, divide the preset correction value by the summed result, and obtain the hidden danger assessment value of the patient corresponding to the abnormal indicator; the preset correction value is set to 1.593, which can be dynamically adjusted by the technical staff later;

[0074] The larger the hidden danger assessment value is, the higher the hidden danger of the patient corresponding to the abnormal indicator is;

[0075] Three groups of assessment value ranges corresponding to the preset hidden danger assessment values ​​are set, and the three groups of assessment value ranges are respectively corresponding to a hidden danger level, and the hidden danger levels are respectively a lower hidden danger level, a general hidden danger level and a higher hidden danger level;

[0076] Matching the hidden danger assessment value of the patient corresponding to the abnormal indicator with the three preset assessment value ranges, thereby obtaining the hidden danger level of the patient corresponding to the abnormal indicator;

[0077] Integrate the above analysis results and fill them into the preset report template; including user personal information, various data indicator results, abnormal indicators, abnormal indicator determination results, abnormal indicator evaluation results and hidden danger level; thereby generating a follow-up report for the patient;

[0078] It should be noted that, in summary, it is possible to integrate patients' real-time test data and historical test data to provide a more comprehensive analysis perspective.

[0079] It is also used to receive new signaling generated by the patient, extract the patient's test data packet for analysis, and generate the patient's diagnosis report;

[0080] Specifically:

[0081] Parse the patient's test data packet, extract the data indicator results of the patient's corresponding test, fill the patient's personal information and the data indicator results into the preset report template, and mark the abnormal indicators in the filled report template based on the comparison of the data indicator results with the corresponding normal reference range; the mark can be filled with color; after marking, generate the patient's diagnosis report;

[0082] The expert evaluation module is used to selectively trigger the expert evaluation signaling when the patient receives the follow-up report or diagnosis report, and when the expert evaluation signaling is triggered, send the follow-up report or diagnosis report to the candidate expert with the largest superior diagnosis value Yz at the current time point. After the candidate expert evaluates the follow-up report or diagnosis report of the patient, the evaluation content is supplemented to the follow-up report or diagnosis report of the patient, and the supplemented follow-up report or diagnosis report is sent to the patient;

[0083] Specifically:

[0084] When receiving the follow-up report or diagnosis report of the patient, screen the range of experts based on the types of abnormal indicators appearing in the follow-up report or diagnosis report, select the experts who meet the requirements and mark them as candidate experts;

[0085] The screening process is:

[0086] Report reception: The system receives the patient's follow-up report or diagnosis report, which contains the patient's test data and abnormal indicators;

[0087] Abnormal indicator identification: The system automatically parses the report content, identifies and extracts all abnormal indicators pointed out in the report;

[0088] Database query: The system accesses a database that contains information on the expertise of medical experts in various fields;

[0089] Expertise matching: Matching abnormal indicators with experts’ areas of expertise to find experts who can handle these abnormal indicators;

[0090] The number of reports to be processed by each candidate expert at the current time point is counted and marked as h1; at the same time, the number of historical report processing of each candidate expert is obtained and marked as h2, and the patient's satisfaction score of the expert is extracted from each historical report processing of each candidate expert; the satisfaction score is used for the patient to rate the expert after receiving the expert's evaluation content, and the score range is set to 1-5, and the higher the score, the higher the patient's satisfaction;

[0091] Take the average of the satisfaction scores of each group as the professional valuation h3 of each candidate expert;

[0092] According to the formula , weighted calculation is performed on the number of pending reports h1, the number of historical reports processed h2, and the professional valuation h3 of each candidate expert, so as to obtain the excellent diagnosis value Yz of each candidate expert; where a1, a2, and a3 are the influence weight factors of the number of pending reports h1, the number of historical reports processed h2, and the professional valuation h3 respectively;

[0093] The candidate expert with the largest superior diagnosis value Yz is selected, and the number of reports to be processed by this expert is increased by one;

[0094] The data encryption module is used to encrypt the patient's follow-up report or diagnosis report and store it in the constructed database;

[0095] The specific process of encryption is as follows:

[0096] First, extract the patient's name spelling letters and report generation date from the patient's personal information, convert the patient's name spelling letters into numbers, and convert them based on the preset conversion rules, setting each group of letters to correspond to a number; for example, z=5, m=12;

[0097] After converting the patient's name into numbers, a string of numbers is obtained, and the constituent numbers of the patient report generation date are further extracted and added to the number set to obtain a new string of numbers; for example, if the report generation date is 2023-09-08, the extracted constituent numbers are 20230908;

[0098] Preset an encryption conversion formula; an addition, subtraction, multiplication and division formula based on the encryption conversion formula, such as {(x+3)×4-5} / 2; substitute each group of numbers in the new string of numbers into the preset encryption conversion formula for calculation, and after the calculation is completed, the final encrypted number set is obtained;

[0099] Based on each group of numbers in the encrypted digital set, an encrypted graphic of a patient's follow-up report or diagnosis report is drawn, the number of numbers in the encrypted digital set is counted, a bar frame equal to the number of numbers is drawn, each group of bar frames is sorted in sequence, and each group of numbers in the encrypted digital set is used as the filling area to fill the blank area of ​​the bar frame; different patterns are used for filling, the bar frames are of the same size, and the blank area is large enough; after the filling is completed, the remaining blank area of ​​each bar frame after filling is intercepted, and after the interception is completed, the encrypted graphic of the patient's follow-up report or diagnosis report is obtained;

[0100] It should be noted that, as Figure 3 As shown, a plane rectangular coordinate system is constructed, and after counting the number of numbers in the encrypted digital set, blank bar frames equal to the number of numbers are drawn in the constructed plane rectangular coordinate system, and each group of blank bar frames are connected and have the same size, and then the area of ​​each group of bar frames is filled in turn according to the sorting order of the numbers. For example, if the first group of numbers is 5, the number 5 is used as the filling area to fill the area of ​​the bar frame. Different filling patterns are used. The filling patterns are pre-set by the technicians, and the order of the filling patterns is shuffled according to the preset time period. For example, the order of the filling patterns of the previous week is randomly shuffled every week to generate a new order of filling patterns;

[0101] According to the sorting order of each group of numbers in the encrypted digital set, after matching with the corresponding filling pattern, the bar frame is filled, and after the filling is completed, the remaining blank area in each group of bar frames is intercepted to obtain the encrypted graphic of the patient's follow-up report or diagnosis report.

[0102] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factor and specific coefficient value in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0103] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A digital laboratory information management system, characterized by: include: Data collection module: collects the patient's test data, analyzes the collected test data through the medical equipment connected to the laboratory, summarizes the analyzed test data index results into the patient's test data package and sends it to the data tracing module; Data tracing module: receives the patient's test data packet, extracts the patient's personal information from the test data packet as a matching basis; matches the extracted patient's personal information with the personal information set stored in the pre-built database; if the match is successful, the patient is regarded as a follow-up patient and a follow-up signal is sent to the report generation module; If the match fails, the patient is considered as a new patient and the new signaling is sent to the report generation module; Report generation module: receives the follow-up signal generated by the patient, extracts the patient's relevant historical test data and test data package from the database for comprehensive analysis, and generates the patient's follow-up report; Extract the patient's relevant historical test data and test data package from the database for comprehensive analysis, specifically: Parse the patient's test data package, extract the results of the various data indicators of the patient's corresponding tests, and extract the normal reference range of the various test data indicators corresponding to the current patient from the pre-built database; Compare the results of each data indicator of the patient's corresponding test with the corresponding normal reference range. If the comparison shows that a data indicator result is outside the corresponding normal reference range, mark the indicator as an abnormal indicator; At the same time, historical indicator results matching the abnormal indicators are extracted from the patient's relevant historical test data. If the historical indicator results corresponding to the abnormal indicators of the patient are all within the normal reference range, the abnormal indicators of the patient are determined to be sudden new abnormalities; If one or more sets of historical indicator results corresponding to abnormal indicators of the patient are outside the normal reference range, the abnormal indicators of the patient are judged to be long-term abnormal; If the abnormal index is determined to be a long-term abnormality, the patient's abnormal index is first converted into a hidden danger score, and then a change trend chart of the patient's corresponding abnormal index is constructed; Preset the value range of each group of indicator results corresponding to the abnormal indicators, and set each group of indicator result value range to correspond to a hidden danger score; Match the patient's abnormal index with the preset value range of each group of index results, so as to obtain the hidden danger score corresponding to the abnormal index of the patient; Draw the numerical points of the patient's current hidden danger score and the corresponding historical hidden danger scores in the change trend graph; connect adjacent numerical points to obtain the hidden danger line of the abnormal indicator; at the same time, preset the highest threshold of the hidden danger score corresponding to the abnormal indicator, and draw the threshold line corresponding to the highest threshold in the change trend graph; Calculate the slope of each hidden danger line and the angle between it and the horizontal line. If the angle between a hidden danger line and the horizontal line is an acute angle, mark the slope of the hidden danger line as a descending slope. If the angle between a hidden danger line and the horizontal line is an obtuse angle, mark the slope of the hidden danger line as an ascending slope. Sum all the rising slopes and falling slopes respectively to get the rising estimate and the falling estimate, and calculate the ratio of the rising estimate to the falling estimate, that is, through , obtain the change trend value of the patient's corresponding abnormal indicator; Three groups of trend value ranges are preset for the change trend value, and the three groups of trend value ranges are set to correspond to three groups of evaluation results respectively, and the three groups of evaluation results are a gradually decreasing trend, a gradually increasing trend, and an up and down fluctuation trend; Matching the change trend value of the patient's corresponding abnormal indicator with the three preset trend value ranges, thereby obtaining the evaluation result of the patient's corresponding abnormal indicator; Generate a follow-up report for the patient, specifically: Construct vertical lines between the patient's current hidden danger score and the corresponding numerical points drawn for each historical hidden danger score and the threshold line, calculate the length of each constructed vertical line, calculate the average of the vertical line lengths corresponding to each historical hidden danger score, and use the calculated result as the average length of the historical indicator corresponding to the abnormal indicator of the patient; Extract the length of the vertical line corresponding to the patient's hidden danger score this time as the average length of the detection index of the patient corresponding to the abnormal index; set the weight coefficient corresponding to the average length of the historical index and the average length of the detection index, multiply the average length of the historical index and the average length of the detection index corresponding to the abnormal index of the patient by the set weight coefficient respectively, and then sum them, divide the preset correction value by the summed result, and obtain the hidden danger assessment value of the patient corresponding to the abnormal index; Three groups of assessment value ranges corresponding to the preset hidden danger assessment values ​​are set, and the three groups of assessment value ranges are respectively corresponding to a hidden danger level, and the hidden danger levels are respectively a lower hidden danger level, a general hidden danger level and a higher hidden danger level; Matching the hidden danger assessment value of the patient corresponding to the abnormal indicator with the three preset assessment value ranges, thereby obtaining the hidden danger level of the patient corresponding to the abnormal indicator; Integrate the above analysis results and fill them into the preset report template to generate the patient's follow-up report; It is also used to receive new signaling generated by the patient, extract the patient's test data packet for analysis, and generate the patient's diagnosis report; Expert evaluation module: When a patient receives a follow-up report or a diagnosis report, the expert evaluation signal is selectively triggered, and when the expert evaluation signal is triggered, the patient sends his or her own follow-up report or diagnosis report to the candidate expert with the largest superior diagnosis value Yz at the current time point. After the candidate expert evaluates the patient's follow-up report or diagnosis report, the evaluation content is added to the patient's follow-up report or diagnosis report, and the supplemented follow-up report or diagnosis report is sent to the patient; Specifically: When receiving the follow-up report or diagnosis report of the patient, screen the range of experts based on the types of abnormal indicators appearing in the follow-up report or diagnosis report, select the experts who meet the requirements and mark them as candidate experts; The number of reports to be processed by each candidate expert at the current time point is counted and marked as h1; at the same time, the number of historical reports processed by each candidate expert is obtained and marked as h2, and the patient's satisfaction score for the expert is extracted from each historical report processing of each candidate expert; the average of the satisfaction scores of each group is taken as the professional valuation h3 of each candidate expert; According to the formula , weighted calculation is performed on the number of pending reports h1, the number of historical reports processed h2, and the professional valuation h3 of each candidate expert, so as to obtain the excellent diagnosis value Yz of each candidate expert; where a1, a2, and a3 are the influence weight factors of the number of pending reports h1, the number of historical reports processed h2, and the professional valuation h3 respectively; The candidate expert with the largest superior diagnosis value Yz is selected, and the number of reports to be processed by this expert is increased by one; Data encryption module: Encrypt the patient's follow-up report or diagnosis report and store it in the constructed database.

2. The digital laboratory information management system according to claim 1, characterized in that: Generate a diagnostic report for the patient, specifically: Parse the patient's test data packets, extract the data indicator results of the patient's corresponding tests, fill the patient's personal information and various data indicator results into the preset report template, and based on the comparison of the various data indicator results with the corresponding normal reference range, mark the abnormal indicators in the filled report template, and generate the patient's diagnosis report after marking.

3. The digital laboratory information management system according to claim 1, characterized in that: The patient's follow-up report or diagnosis report is encrypted, specifically: First, the patient's name spelling letters and the report generation date are extracted from the patient's personal information, and the patient's name spelling letters are converted into numbers based on the preset conversion rules, and each group of letters is set to correspond to a number; After converting the spelling letters of the patient's name into numbers, a string of numbers is obtained, and the constituent numbers of the patient report generation date are further extracted and added to the number set to obtain a new string of numbers; Preset an encryption conversion formula; substitute each group of numbers in the new string of numbers into the preset encryption conversion formula for calculation, and after the calculation is completed, obtain the final encrypted number set; Based on each group of numbers in the encrypted digital set, an encrypted graphic of the patient's follow-up report or diagnosis report is drawn, the number of numbers in the encrypted digital set is counted, and a bar frame equal to the number of numbers is drawn. The groups of bar frames are sorted in sequence, and the blank areas of the bar frames are filled with each group of numbers in the encrypted digital set as the filling area. After the filling is completed, the remaining blank areas of each bar frame after filling are intercepted. After the interception is completed, the encrypted graphic of the patient's follow-up report or diagnosis report is obtained.

Images