An automatic acquisition and analysis method and system for medical quality control indexes of critical care departments

Abstract

This invention discloses an automatic collection and analysis method for medical quality control indicators in critical care departments. The method includes: establishing a case feature database based on historical monitoring data; constructing and training a quality control indicator model based on the case feature database; establishing a model update database to store newly input cases; periodically inputting data from the model update database into the quality control indicator model; and determining whether the medical quality control indicators in critical care departments are within the acceptable range based on the output of the quality control indicator model display module and providing feedback to relevant personnel.

Description

Technical Field

[0001] This invention belongs to the field of medical quality control data collection and analysis, specifically relating to an automatic collection and analysis method and system for medical quality control indicators in critical care departments. Background Technology

[0002] The Department of Critical Care Medicine is an independent medical unit, a concentrated reflection of the medical level of a modern hospital, and currently one of the important hallmarks of a modern hospital. Its main medical responsibilities include: providing medical support for the rescue and life-sustaining of critically ill patients; providing medical support for the treatment and organ function restoration of patients with multiple organ dysfunction syndrome; and preventing and treating multiple organ dysfunction syndrome. This includes various critical, acute, and reversible diseases; patients requiring emergency life support, such as shock from various causes, circulatory failure and cardiac and respiratory arrest, acute respiratory failure and acute exacerbations of respiratory failure from various causes; patients requiring brain resuscitation after cardiopulmonary resuscitation; patients resuscitated from drowning or electric shock; severe trauma; multiple organ failure; coma and various metabolic crises; severe acid-base and electrolyte imbalances; patients requiring close monitoring and resuscitation after major surgery; patients requiring respiratory assistance; and postoperative monitoring of elderly patients with complications.

[0003] Critical care departments have corresponding medical quality control indicators, including: patient admission rate, patient bed-day rate, patient admission rate with an Acute Physiology and Chronic Health Evaluation (APACHE2) score of 15 or higher, completion rate of 3-hour and 6-hour bundled treatment for septic shock, pathogen testing rate before antibiotic treatment in critical care departments, deep vein thrombosis prevention rate in critical care departments, expected mortality rate of patients in critical care departments, standardized mortality index of patients in critical care departments, unplanned extubation rate in critical care departments, reintubation rate within 48 hours after extubation in critical care departments, rate of unplanned transfer to critical care departments, return rate within 48 hours after transfer out of critical care departments, incidence of ventilator-associated pneumonia in critical care departments, incidence of catheter-related bloodstream infections in critical care departments, and incidence of catheter-related urinary tract infections in critical care departments.

[0004] The vital signs of critically ill patients require long-term, real-time monitoring, collection, and analysis. Existing medical information collection and analysis equipment and systems primarily rely on setting fixed indicator alerts to monitor and provide notifications about patient vital signs. These systems suffer from poor real-time performance and only issue alarms when patient indicators exceed critical condition thresholds, posing a significant risk to timely patient care. Furthermore, the security management of medical information must be considered within the system to ensure secure and accurate data transmission and protect patient privacy. Summary of the Invention

[0005] One of the objectives of this invention is to propose an automatic collection and analysis method for medical quality control indicators in critical care departments, which overcomes the shortcomings of existing methods, such as poor real-time performance and alarms only being triggered when patients exceed the critical illness indicators, thus posing significant hidden dangers.

[0006] One of the objectives of this invention is achieved through the following technical solution:

[0007] An automatic collection and analysis method for medical quality control indicators in critical care departments includes the following steps:

[0008] S1: Establish a case characteristic database based on historical surveillance data;

[0009] S2: Construct and train a quality control index model based on the case characteristic database;

[0010] S3: Establish a model update database to store newly input cases;

[0011] S4: Periodically input the data from the model update database into the quality control index model;

[0012] S5: Based on the output of the quality control indicator model display module, determine whether the medical quality control indicators of the critical care department are within the qualified range and provide feedback to relevant personnel.

[0013] Furthermore, in step S1, establishing a case characteristic database based on historical monitoring data specifically includes:

[0014] Step S101: Preprocess the historical monitoring data and extract the status related to medical quality control indicators for each case;

[0015] Step S102: Represent the status of the medical quality control indicators for each case using 0 and 1, where 0 is unqualified and 1 is qualified.

[0016] Step S103: Store the above status of a single case into the same set of data, and store all cases into the case feature database in the same way.

[0017] Furthermore, in step S2, constructing and training the quality control index model based on the case characteristic database specifically includes:

[0018] Step S201: Construct a medical quality assessment unit, adding modules such as image acquisition, medical quality evaluation, and user evaluation acquisition;

[0019] Step S202: Construct a central cluster computing module to receive the data input from the medical quality assessment unit;

[0020] Step S203: Embed a specific pass rate algorithm in the central cluster computing module to process the various output data of the medical quality assessment unit;

[0021] Step S204: Construct a medical indicator collection module to store the medical quality control indicator ratio (MQA);

[0022] Step S205: Construct a judgment module and design a feature qualification value algorithm to judge whether the medical quality control indicators of the current department are qualified;

[0023] Step S206: Construct a medical quality level assessment algorithm in the judgment module to determine the level of medical quality in the intensive care unit;

[0024] Step S207: Train the model using the data input from the case feature database and calculate the dynamic equilibrium scenario parameter K in the feature qualification value algorithm that conforms to the current situation of the department;

[0025] Step S208: Construct an early warning module to issue early warnings to departments that fail to meet the requirements output by the judgment module;

[0026] Step S209: Construct a display module to display the qualification level of each department and early warning notices.

[0027] Furthermore, in step S203, the expression for the special item pass rate algorithm is:

[0028]

[0029] Where n represents the total number of critically ill patients, m represents the category of medical quality control scoring items that need to be referenced for medical quality control indicators, i represents the patient sequence number in the case feature database, j represents a certain medical quality control sequence number, STAT represents the value of the relevant status of the medical quality control indicator, sum(i) is the total number of times the i-th critically ill patient sought medical treatment on this medical item, max(STAT) is the maximum value of the relevant status value of this medical quality control indicator, and PCT is the final result of the fractional calculation, which is the quality control percentage data.

[0030] Furthermore, the expression for the feature qualification value algorithm in step S205 is as follows:

[0031]

[0032] Among them, PCT is the quality control percentage data output by the special pass rate algorithm, MQA is the ratio of medical quality control indicators recently published by authoritative health institutions, K is a dynamic equilibrium scenario parameter less than 1, K changes with factors such as medical admission and management. If strict management or fewer admissions lead to lower medical quality, K will be reduced, and vice versa. QC is the degree of medical quality control compliance. If QC<0, it means that the medical quality of the intensive care unit is not up to standard. The smaller the QC, the worse the medical quality. If QC>0, it means that the medical quality of the intensive care unit meets the standard. The larger the QC, the better the medical quality.

[0033] Furthermore, the expression for the medical quality level assessment algorithm in step S206 is as follows:

[0034]

[0035] Where n represents the total number of critically ill patients, m represents the category of medical quality control scoring items that need to be referenced for medical quality control indicators, i represents the patient sequence number in the case feature database, j represents a certain medical quality control sequence number, STAT represents the value of the relevant status of the medical quality control indicator, sum(i) is the total number of times the i-th critically ill patient received medical treatment for this medical item, max(STAT) is the maximum value of the relevant status value of this medical quality control indicator, MQA is the ratio of the medical quality control indicator recently published by an authoritative health institution, and RANK is the level of medical quality in this intensive care unit. This indicates that the medical quality of the intensive care unit is excellent; if RANK>0 and This indicates that the medical quality of the intensive care unit is good; if If RANK≤0, it indicates that the medical quality of the intensive care unit is poor; if This indicates that the medical quality of the intensive care unit is extremely poor, and the warning module should be used to send a message to the regulatory authorities that the medical quality of the intensive care unit is substandard.

[0036] Furthermore, in step S3, a model update database is established to store newly input cases, which specifically includes the following sub-steps:

[0037] Step S301: Construct a model with the same storage format as the pathological feature database and update the database;

[0038] Step S302: Preprocess the newly entered case data and extract relevant statuses such as medical quality control indicators from each case;

[0039] Step S303: Input the newly entered case information and relevant data of quality control indicators into the model to update the database.

[0040] Furthermore, in step S4, periodically inputting the data from the database into the model specifically includes the following sub-steps:

[0041] Step S401: Set a fixed-length period to perform data detection on the model update database;

[0042] Step S402: Add the complete case data from the model update database as sample data to the model training set;

[0043] Step S403: Input the training set into the quality control index model;

[0044] Step S404: Repeat the above steps until all sample data has been used.

[0045] Step S405: Obtain the updated quality control index model after training.

[0046] Furthermore, step S5 specifically includes the following sub-steps:

[0047] Step S501: Input the various data from the model update database into the modules of the medical quality assessment unit in the quality control index model;

[0048] Step S502: The central cluster computing module obtains the output of each module of the medical quality assessment unit and performs percentage processing on each feature vector data of each output of the medical quality assessment unit through a special pass rate algorithm to generate quality control percentage data PCT.

[0049] Step S503: The judgment module receives the quality control percentage data PCT output by the central cluster computing module and the ratio of medical quality control indicators MQA output by the medical indicator acquisition module;

[0050] Step S504: Construct a medical quality level assessment algorithm to determine the level of medical quality in the intensive care unit;

[0051] Step S505: Calculate the medical quality control qualification level (QC) of the department using the feature qualification value algorithm. If QC > 0, proceed to step S507; otherwise, proceed to step S506.

[0052] Step S506: Input the result into the early warning module, which will then provide feedback to the processing personnel, who will then take relevant actions.

[0053] Step S507: The final result is displayed by the display module.

[0054] The second objective of this invention is achieved through the following technical solution: an automatic collection and analysis system for medical quality control indicators in critical care departments, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the method described above.

[0055] The beneficial effects of this invention include:

[0056] (1) The present invention can accurately predict the quality of medical care by completing the training of the control index model. The data of the model update database is input into the quality control index model at regular intervals, which has the function of iterative update to a certain extent, eliminating the error caused by manual input, reducing labor costs, and increasing the profits of enterprises.

[0057] (2) This invention establishes a quality control indicator model by analyzing the characteristics of critically ill patients' cases. This model can comprehensively evaluate the quality of medical care by collecting all available medical information of critically ill patients, greatly improving the accuracy of medical quality control indicator judgment, and providing medical regulatory departments with detailed medical quality control data on the critical care department, which facilitates timely detection and early warning of potential medical risks;

[0058] (3) The present invention designs a feature qualified value algorithm to evaluate medical quality. Since the medical conditions and number of patients in different regions are different, the same medical control indicators cannot be used to measure the medical conditions in all regions. Therefore, the present invention adds a dynamic balance scenario parameter K, which can dynamically adjust the K value according to the current real-time situation to balance the calculation error of the control indicators under different medical scenarios. By sacrificing a small part of the numerical accuracy, the fault tolerance of the system is greatly improved.

[0059] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained from the following description and the foregoing claims. Attached Figure Description

[0060] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will now be described in further detail with reference to the accompanying drawings, wherein:

[0061] Figure 1 This is a flowchart of a method for automatically collecting and analyzing medical quality control indicators in critical care departments according to the present invention.

[0062] Figure 2 This is a schematic diagram illustrating the working principle of an automatic collection and analysis method for medical quality control indicators in critical care departments according to the present invention.

[0063] Figure 3 This is a schematic diagram illustrating the storage format of historical monitoring data stored in the case feature database in an embodiment of the present invention;

[0064] Figure 4 This is a diagram of the internal modules of the quality control index model of the present invention;

[0065] Figure 5 This is a table for inputting quality control index models in this embodiment of the invention. Detailed Implementation

[0066] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0067] like Figure 1 As shown, this invention provides an automatic collection and analysis method for medical quality control indicators in critical care departments, comprising the following steps:

[0068] S1: Establish a case characteristic database based on historical surveillance data;

[0069] In this embodiment, step S1 specifically includes the following steps:

[0070] S101: Preprocess historical monitoring data and extract the status related to medical quality control indicators in each case;

[0071] S102: The status of the medical quality control indicators for each case is represented by 0 and 1, where 0 is unqualified and 1 is qualified;

[0072] S103: Store the above status of a single case in the same set of data, and store all cases in the case feature database in the same way;

[0073] A schematic diagram of an automatic collection and analysis method for medical quality control indicators in critical care departments according to the present invention is shown below. Figure 2 As shown;

[0074] In this embodiment, the historical monitoring data stored in the case characteristic database is stored in table form. Taking four patients as an example, the storage format is as follows: Figure 3 As shown;

[0075] In this table, the horizontal axis represents the patient's serial number, the vertical axis represents the categories of medical quality control scoring items that the medical quality control indicators need to refer to, and the intersection represents the patient's medical condition as qualified in that item, with 0 indicating unqualified and 1 indicating qualified.

[0076] S2: Construct and train a quality control index model based on the case characteristic database;

[0077] The internal module diagram of the quality control index model of the present invention is as follows: Figure 4 As shown;

[0078] In this embodiment, step S2 specifically includes the following steps:

[0079] S201: Construct a medical quality assessment unit, adding modules such as image acquisition, medical quality evaluation, and user evaluation acquisition;

[0080] S202: Construct a central cluster computing module to receive various data input from the medical quality assessment unit;

[0081] S203: Embed a specialized pass rate algorithm in the central cluster computing module to process the various output data of the medical quality assessment unit;

[0082] S204: Construct a medical indicator collection module to store the ratio of medical quality control indicators (MQA);

[0083] S205: Construct a judgment module and design a feature qualification value algorithm to judge whether the medical quality control indicators of the current department are qualified;

[0084] S206: Construct a medical quality level assessment algorithm in the judgment module to determine the level of medical quality in the intensive care unit;

[0085] S207: Use the data input from the case feature database to train the model and calculate the size of the dynamic equilibrium scenario parameter K in the feature qualification value algorithm that conforms to the current situation of the department;

[0086] S208: Construct an early warning module to issue early warnings to departments that fail to meet the standards output by the judgment module;

[0087] S209: Construct a display module to show the pass / fail status of each department and early warning notices.

[0088] In step S201, the medical quality assessment unit includes, but is not limited to, a medical environment image acquisition module, a medical level evaluation module, and a user evaluation acquisition module. Each hospital may add or remove some modules in the medical quality assessment unit according to its current situation.

[0089] In this embodiment, the medical environment image acquisition module will connect to the image acquisition devices in various areas of the hospital, identify and count, but not limited to, the number of medical devices in each area, the cleanliness of the environment, and the closed status of windows to ensure that the indoor environment is dry and ventilated, and output the medical environment feature vector.

[0090] In this embodiment, the medical condition assessment module will connect to the pathology database of each patient, collect the medical information of each patient, including but not limited to the disease name, total number of days of treatment, number of days of treatment, dosage of medication, and whether the condition has improved, and output the medical condition feature vector.

[0091] In this embodiment, the user evaluation collection module will collect patient evaluation data on medical services and output user evaluation feature vectors.

[0092] In step S203, the expression for the special item pass rate algorithm is:

[0093]

[0094] Where n represents the total number of critically ill patients, m represents the category of medical quality control scoring items that need to be referenced for medical quality control indicators, i represents the patient sequence number in the case feature database, j represents a certain medical quality control sequence number, STAT represents the value of the relevant status of the medical quality control indicator, sum(i) is the total number of times the i-th critically ill patient sought medical treatment on this medical item, max(STAT) is the maximum value of the relevant status value of this medical quality control indicator, and PCT is the final result of the fractional calculation, which is the quality control percentage data.

[0095] The expression for the feature qualification value algorithm in step S205 is:

[0096]

[0097] Among them, PCT is the quality control percentage data output by the special pass rate algorithm, MQA is the ratio of medical quality control indicators recently published by authoritative health institutions, K is a dynamic equilibrium scenario parameter less than 1, K changes with factors such as medical admission and management. If strict management or fewer admissions lead to lower medical quality, K will be reduced, and vice versa. QC is the degree of medical quality control compliance. If QC<0, it means that the medical quality of the intensive care unit is not up to standard. The smaller the QC, the worse the medical quality. If QC>0, it means that the medical quality of the intensive care unit meets the standard. The larger the QC, the better the medical quality.

[0098] In this embodiment, the total number of patients n is 4, the medical quality control scoring item category m that the medical quality control indicators need to refer to is 3, the patient sequence number i in the case feature database is 1 to 4, the medical quality control sequence number j is 1 to 3, the special pass rate algorithm calculates that its denominator is 12 and the numerator is 9, and the quality control percentage data PCT is calculated to be 75%.

[0099] In this embodiment, taking ICU critically ill patient data as an example, the latest medical quality control index ratio (MQA) published by authoritative health institutions is 60%. Substituting the medical quality pass threshold (i.e., QC is 0) into the feature pass value algorithm, the dynamic equilibrium scenario parameter K, which conforms to the current situation of the ICU department, is 0.15. The formula of the feature pass value algorithm in the model is updated as follows:

[0100]

[0101] S3: Establish a model update database to store newly input cases;

[0102] In this embodiment, step S3 specifically includes the following steps:

[0103] S301: Update the database by constructing a model with the same storage format based on the pathological feature database;

[0104] S302: Preprocess newly imported case data and extract relevant statuses such as medical quality control indicators from each case;

[0105] S303: Input newly entered case information and quality control indicator data into the model to update the database.

[0106] S4: Periodically input the data from the database that updates the model into the model;

[0107] Step S4 specifically includes the following steps:

[0108] S401: Set a fixed-length period to perform data detection on the model update database;

[0109] S402: Add complete case data from the model update database as sample data to the model training set;

[0110] S403: Input the training set into the quality control index model;

[0111] S404: Repeat the above steps until all sample data has been used.

[0112] S405: Obtain the updated quality control index model after training.

[0113] In this embodiment, the "fixed-length period" in step S401 can be a week as a period, which is conducive to updating model parameters in real time in a short period of time, improving the accuracy of model output results, reflecting the current medical quality status in a timely and dynamic manner, and reducing model judgment error.

[0114] S5: Determine whether the medical quality control indicators of the emergency and critical care department are within the acceptable range based on the model output and provide feedback to relevant personnel.

[0115] Step S5 specifically includes the following steps:

[0116] S501: Input the various data from the model update database into the modules of the medical quality assessment unit in the quality control index model;

[0117] S502: The central cluster computing module acquires the outputs of each module of the medical quality assessment unit and performs percentage processing on each feature vector data of each output of the medical quality assessment unit through a special pass rate algorithm to generate quality control percentage data PCT.

[0118] S503: The judgment module receives the quality control percentage data PCT output by the central cluster computing module and the ratio of the medical quality control index MQA output by the medical index acquisition module;

[0119] S504: Construct a medical quality level assessment algorithm to determine the level of medical quality in this intensive care unit;

[0120] S505: Calculate the medical quality control qualification level (QC) of the department using the feature qualification value algorithm. If QC>0, proceed to step S507; otherwise, proceed to step S506.

[0121] S506: Input the results into the early warning module, which then feeds back the results to the processing personnel, who then take relevant actions.

[0122] S507: The final result is displayed by the display module.

[0123] In this embodiment, the table for inputting the quality control index model is as follows: Figure 5 As shown in the table. The horizontal rows represent patient serial numbers, the vertical rows represent the categories of medical quality control scoring items that need to be referenced for medical quality control indicators, and the intersection represents the patient's medical condition as qualified in that item, with 0 indicating unqualified and 1 indicating qualified.

[0124] In this embodiment, the total number of patients n is 5, the medical quality control scoring item category m that the medical quality control indicators need to refer to is 3, the patient sequence number i in the case feature database is 1 to 5, the medical quality control sequence number j is 1 to 3, the special pass rate algorithm calculates that its denominator is 15 and the numerator is 6, and the quality control percentage data PCT is calculated to be 40%.

[0125] The expression for the medical quality level assessment algorithm in step S504 is as follows:

[0126]

[0127] Among them, n represents the total number of critically ill patients, m represents the categories of medical quality control score items required for medical quality control indicators, i represents the patient serial number in the case feature database, j represents a certain medical quality control serial number, STAT represents the value of the status related to the medical quality control indicator, sum(i) is the total number of medical visits of the i-th critically ill patient in this medical item, max(STAT) is the maximum value of the status value related to this medical quality control indicator, MQA is the medical quality control indicator ratio newly announced by the authoritative health agency (in this embodiment, the medical quality control indicator ratio newly announced by the National Health Commission is adopted), RANK is the level of the medical quality of this intensive care unit. If it indicates that the medical quality of this intensive care unit is excellent; if RANK > 0 and it indicates that the medical quality of this intensive care unit is good; if and RANK ≤ 0, it indicates that the medical quality of this intensive care unit is poor; if it indicates that the medical quality of this intensive care unit is extremely poor.

[0128] In this embodiment, the quality control percentage data PCT and the medical quality control indicator ratio MQA output by the medical indicator acquisition module are simultaneously input into the medical quality level judgment algorithm, and RANK = -0.2 can be obtained, that is it indicates that the medical quality of this intensive care unit is extremely poor, and it can be selected to push the message that the medical quality of this intensive care unit is unqualified to the supervision department through the warning module.

[0129] In this embodiment, the quality control percentage data PCT and the medical quality control indicator ratio MQA output by the medical indicator acquisition module are input into the judgment module, and that is, -0.35 < QC < -0.05, and QC is always less than 0, indicating that the medical quality control of this ICU department is unqualified. Then this result is input into the warning module, and the warning module feeds it back to the processing personnel and the processing personnel take relevant operations, and finally the final result is displayed by the display module.

[0130] Those of ordinary skill in the art will realize that the embodiments described herein are for helping the reader understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations without departing from the essence of the present invention according to these technical revelations disclosed by the present invention, and these deformations and combinations are still within the protection scope of the present invention.

[0131] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0132] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0133] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0134] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for automatically collecting and analyzing medical quality control indicators in critical care departments, characterized in that: Includes the following steps: S1: Establish a case characteristic database based on historical surveillance data; In step S1, establishing a case characteristic database based on historical monitoring data specifically includes: Step S101: Preprocess the historical monitoring data and extract the status related to medical quality control indicators for each case; Step S102: Represent the status of the medical quality control indicators for each case using 0 and 1, where 0 indicates unqualified and 1 indicates qualified; Step S103: Store the above status of a single case into the same set of data, and store all cases into the case feature database in the same way; S2: Construct and train a quality control index model based on the case feature database; step S2 specifically includes: Step S201: Construct a medical quality assessment unit, adding an image acquisition module, a medical quality evaluation module, and a user evaluation acquisition module; Step S202: Construct a central cluster computing module to receive the data input from the medical quality assessment unit; Step S203: Embed a specific pass rate algorithm in the central cluster computing module to process the various output data of the medical quality assessment unit; the expression of the specific pass rate algorithm is: PCT= Where n represents the total number of critically ill patients, m represents the category of medical quality control scoring items that need to be referenced for medical quality control indicators, i represents the patient sequence number in the case feature database, j represents a certain medical quality control sequence number, STAT represents the value of the relevant status of the medical quality control indicator, sum(i) is the total number of times the i-th critically ill patient seeks medical treatment on this medical item, max(STAT) is the maximum value of the relevant status value of this medical quality control indicator, and PCT is the final result of the fractional calculation, which is the quality control percentage data. Step S204: Construct a medical indicator collection module to store the medical quality control indicator ratio (MQA); Step S205: Construct a judgment module and design a feature pass value algorithm to judge whether the medical quality control indicators of the current department are qualified; the expression of the feature pass value algorithm is: Among them, PCT is the quality control percentage data output by the special pass rate algorithm, MQA is the ratio of medical quality control indicators recently published by authoritative health institutions, K is a dynamic equilibrium scenario parameter less than 1, K changes with medical admission and management factors. If strict management or fewer admissions lead to lower medical quality, K will be reduced, and vice versa. QC is the degree of medical quality control compliance. If QC<0, it means that the medical quality of the intensive care unit is not up to standard. The smaller the QC, the worse the medical quality. If QC>0, it means that the medical quality of the intensive care unit meets the standard. The larger the QC, the better the medical quality. Step S206: Construct a medical quality level assessment algorithm in the judgment module to determine the level of medical quality in the intensive care unit; the expression of the medical quality level assessment algorithm is: RANK= -MQA Where n represents the total number of critically ill patients, m represents the category of medical quality control scoring items that need to be referenced for medical quality control indicators, i represents the patient sequence number in the case feature database, j represents a certain medical quality control sequence number, STAT represents the value of the relevant status of the medical quality control indicator, sum(i) is the total number of times the i-th critically ill patient has sought medical treatment for this medical item, max(STAT) is the maximum value of the relevant status value of this medical quality control indicator, MQA is the ratio of the medical quality control indicator recently published by an authoritative health institution, RANK is the level of medical quality in this critical care department, if RANK > If MQA is high, it indicates that the medical quality of the intensive care unit is excellent; if RANK > 0 and RANK < 0, it indicates that the intensive care unit has excellent medical quality. If MQA is high, it indicates that the quality of medical care in the intensive care unit is good; if RANK > - If MQA and RANK ≤ 0, it indicates that the medical quality of the intensive care unit is poor; if RANK ≤ - MQA indicates that the quality of medical care in the intensive care unit is extremely poor; Step S207: Train the model using the data input from the case feature database and calculate the dynamic equilibrium scenario parameter K in the feature qualification value algorithm that conforms to the current situation of the department; Step S208: Construct an early warning module to issue early warnings to departments that fail to meet the requirements output by the judgment module; Step S209: Construct a display module to show the pass / fail status of each department and early warning notices; S3: Establish a model update database to store newly input cases; S4: Periodically input the data from the model update database into the quality control index model; S5: Based on the output of the quality control indicator model display module, determine whether the medical quality control indicators of the critical care department are within the qualified range and provide feedback to relevant personnel.

2. The method for automatically collecting and analyzing medical quality control indicators in critical care departments according to claim 1, characterized in that: In step S3, a model update database is established to store newly input cases, which specifically includes the following sub-steps: Step S301: Construct a model with the same storage format as the pathological feature database and update the database; Step S302: Preprocess the newly entered case data and extract relevant statuses such as medical quality control indicators from each case; Step S303: Input the newly entered case information and relevant data of quality control indicators into the model to update the database.

3. The method for automatically collecting and analyzing medical quality control indicators in critical care departments according to claim 1, characterized in that: Step S4, which involves periodically updating the model by inputting data from the database into the model, specifically includes the following sub-steps: Step S401: Set a fixed-length period to perform data detection on the model update database; Step S402: Add the complete case data from the model update database as sample data to the model training set; Step S403: Input the training set into the quality control index model; Step S404: Repeat the above steps until all sample data has been used. Step S405: Obtain the updated quality control index model after training.

4. The method for automatic collection and analysis of medical quality control indicators in critical care departments according to claim 1, characterized in that: Step S5 specifically includes the following sub-steps: Step S501: Input the various data from the model update database into the modules of the medical quality assessment unit in the quality control index model; Step S502: The central cluster computing module obtains the output of each module of the medical quality assessment unit and performs percentage processing on each feature vector data of each output of the medical quality assessment unit through a special pass rate algorithm to generate quality control percentage data PCT. Step S503: The judgment module receives the quality control percentage data PCT output by the central cluster computing module and the ratio of medical quality control indicators MQA output by the medical indicator acquisition module; Step S504: Construct a medical quality level assessment algorithm to determine the level of medical quality in the intensive care unit; Step S505: Calculate the medical quality control qualification level (QC) of the department using the feature qualification value algorithm. If QC > 0, proceed to step S507; otherwise, proceed to step S506. Step S506: Input the result into the early warning module, which will then provide feedback to the processing personnel, who will then take relevant actions. Step S507: The final result is displayed by the display module.

5. An automatic data acquisition and analysis system for medical quality control indicators in critical care departments, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, it implements the method as described in any one of claims 1-4.

Images