Postoperative recovery plan generation system, generation method and storage medium

Abstract

The present invention provides a postoperative recovery plan generation system, generation method, and storage medium. The system includes an interactive subsystem and an analysis subsystem that are communicatively connected. The interactive subsystem is used to obtain a patient's preoperative and intraoperative information, integrate the information to obtain the patient's original information, and send the original information to the analysis subsystem. The analysis subsystem is used to convert the received original information into structured parameters, update the structured parameters based on the patient's current status information, and analyze the updated structured parameters to generate a postoperative recovery plan and send it to the interactive subsystem. The present invention can update the patient's structured parameters in real time, thereby allowing the recovery plan to be adjusted in real time based on the patient's current status, further facilitating the patient's postoperative recovery.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a postoperative recovery plan generation system, generation method and storage medium. Background Art

[0002] In recent years, with the rapid development of big data and artificial intelligence technologies, machine learning has begun to be applied to assistive diagnosis and treatment, intelligently generating and recommending treatments for patients and helping doctors quickly develop treatment plans. However, most existing technologies rely on one-way information transmission, lacking continuous feedback on patient status and information, making it impossible to track patients' postoperative recovery and the ability to adjust recovery plans in real time.

[0003] It should be noted that the information disclosed in the background technology section of the invention is only intended to deepen the understanding of the general background technology of the invention, and should not be regarded as an admission or any form of implication that the information constitutes prior art already known to those skilled in the art. Summary of the Invention

[0004] The purpose of the present invention is to provide a postoperative recovery plan generation system, generation method and storage medium, which can continuously track and provide feedback on the patient's status, so that the recovery plan can be adjusted in real time according to the patient's status.

[0005] To achieve the above-mentioned object, the present invention provides a postoperative recovery plan generation system, comprising an interactive subsystem and an analysis subsystem connected in communication;

[0006] The interactive subsystem is used to obtain the patient's preoperative information and intraoperative information, integrate them to obtain the patient's original information, and send the original information to the analysis subsystem;

[0007] The analysis subsystem is used to convert the received original information into structured parameters, and update the structured parameters based on the current status information of the patient obtained, and analyze the updated structured parameters to generate a postoperative recovery plan and send it to the interaction subsystem.

[0008] Optionally, the interaction subsystem is configured to obtain the patient's preoperative information through the following process:

[0009] Obtaining patient identification information;

[0010] Access a medical system according to the identity information to obtain preoperative information of the patient.

[0011] Optionally, the interactive subsystem is used to obtain the patient's identity information by scanning a QR code worn by the patient; or

[0012] The patient's identity information is obtained by collecting the patient's facial information.

[0013] Optionally, the preoperative information includes discrete variable information and continuous variable information;

[0014] The discrete variable information includes the type of surgery and / or the admission diagnosis and / or the physical fitness assessment and / or whether there is a chronic disease and / or whether the surgical site is inflamed and / or whether there is a relevant surgical history;

[0015] The continuous variable information includes patient age and / or coagulation function index and / or blood routine index and / or liver and kidney function index and / or electrolyte index.

[0016] Optionally, the intraoperative information includes at least one of endoscopic image information, surgical process recording information, surgical instrument movement information and electronic spreadsheet information.

[0017] Optionally, the electronic spreadsheet information includes the amount of bleeding and / or the mass of resected tissue and / or the amount of drainage and / or the operation time and / or the difficulty of the operation and / or whether the operation was completed normally and / or the estimated risk of complications and / or the estimated recovery time.

[0018] Optionally, the analysis subsystem includes an information analysis module and a solution generation module;

[0019] The information analysis module is used to convert the received original information into structured parameters and send them to the solution generation module;

[0020] The solution generation module is used to update the structured parameters and analyze the updated structured parameters to generate a postoperative recovery solution and send it to the interactive subsystem.

[0021] Optionally, the information analysis module includes a complication analysis unit, a feature extraction unit and a parameter generation unit;

[0022] The complication analysis unit is used to obtain complication information based on the preoperative information and the electronic table information;

[0023] The feature extraction unit is configured to obtain, based on the endoscopic image information and the surgical instrument movement information, a first feature parameter for characterizing the degree of damage caused to the patient by the surgical instrument; and to obtain, based on the surgical recording information, a second feature parameter for characterizing the surgical procedure sequence;

[0024] The parameter generating unit is configured to generate structured parameters according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter.

[0025] Optionally, the complication analysis unit is configured to obtain the complication information through the following process:

[0026] Acquiring initial structured parameters of the patient based on the preoperative information and the electronic spreadsheet information;

[0027] According to the initial structural parameters of the patient, searching in a database for target initial structural parameters whose distance from the initial structural parameters of the patient is within a preset threshold range;

[0028] taking the case corresponding to the target initial structured parameter as a similar case matching the patient;

[0029] The complication information of the patient is obtained based on the complication information of the similar cases.

[0030] Optionally, obtaining the complication information of the patient based on the complication information of the similar case includes:

[0031] Count the frequency of each complication in all similar cases;

[0032] According to the frequency of each complication, complications that meet the preset conditions are selected as valid complications;

[0033] Determine whether the number of effective complications is equal to a first preset number. If not, increase the preset threshold range and continue to search the database for similar cases matching the patient until the number of effective complications is equal to the first preset number to obtain the patient's complication information.

[0034] Optionally, the feature extraction unit is used to use a pre-trained deep convolutional neural network model to identify the endoscopic image information to determine whether the surgical instrument contacts the patient's tissue. If the judgment result is yes, the cumulative path of the surgical instrument contacting the patient's tissue is calculated based on the motion information of the surgical instrument to obtain a first characteristic parameter for characterizing the degree of damage to the patient caused by the surgical instrument.

[0035] Optionally, the feature extraction unit is used to use a pre-trained Seq2Seq model to identify the surgical process recording information to obtain a second feature parameter for characterizing the surgical process sequence.

[0036] Optionally, the complication information includes complication type information and corresponding complication severity information;

[0037] The solution generation module includes a parameter updating unit, a sensitive parameter analysis unit, a complication prediction unit and a solution generation unit;

[0038] The parameter updating unit is used to update the complication information of the patient according to the current status information of the patient to obtain updated structured parameters;

[0039] The sensitive parameter analysis unit is used to analyze each complication in the updated structured parameters to obtain the sensitive parameter corresponding to each complication;

[0040] The complication prediction unit is used to obtain an augmented structured parameter based on the updated structured parameter and the sensitive parameter, and predict the occurrence probability of each complication based on the augmented structured parameter to obtain a complication prediction result;

[0041] The plan generating unit is used to generate a postoperative recovery plan based on the complication prediction result and send it to the interactive subsystem.

[0042] Optionally, the parameter updating unit updates the patient's complication information through the following process:

[0043] determining whether the patient has a new complication according to the patient's current condition information;

[0044] If yes, adding the new complication and the complication in the structured parameters before updating into the same list;

[0045] All complications in the list are sorted according to severity, complications ranked in the first preset digit range of severity are removed, and the remaining complications are used as updated complications to obtain updated complication information.

[0046] Optionally, the sensitive parameter analysis unit analyzes each type of complication in the updated structural parameters through the following process:

[0047] According to the updated structural parameters, searching for a second preset number of similar cases in the database to form a first case set;

[0048] For each complication type in the updated structured parameters:

[0049] Counting whether each similar case in the first case set has the same type of complication, so as to obtain a binary classification result of the same type of complication;

[0050] According to the binary classification results of this type of complication, significance analysis was performed to obtain the sensitive parameters of this type of complication.

[0051] Optionally, the complication prediction unit predicts the probability of occurrence of each complication through the following process:

[0052] According to the augmented structured parameters, searching a third preset number of similar cases in the database to form a second case set;

[0053] For each complication in the augmented structured parameters:

[0054] Counting whether each similar case in the second case set has the complication to obtain a binary classification result of the complication;

[0055] According to the binary classification results of the complication, the occurrence probability of the complication is calculated to obtain the prediction result of the complication.

[0056] Optionally, the plan generating unit generates the postoperative recovery plan through the following process:

[0057] Performing a confidence analysis on the complication prediction result and the complications of the patient's clinical manifestations to determine whether the complication prediction result is accurate;

[0058] If yes, the complication with the probability of occurrence ranked in the second preset range is used as the target complication; if no, the complication of the clinical manifestation in the updated structured parameters is used as the target complication;

[0059] The treatment plan for the target complication is searched in the database according to the target complication to generate a postoperative recovery plan.

[0060] Optionally, the interactive subsystem is further configured to receive a doctor's confirmation operation or modification operation on the postoperative recovery plan, and send the modified postoperative recovery plan to the analysis subsystem.

[0061] To achieve the above-mentioned object, the present invention further provides a method for generating a postoperative recovery plan, comprising:

[0062] Obtaining preoperative and intraoperative information of the patient, and integrating the information to obtain the original information of the patient;

[0063] The raw information is sent to the analysis subsystem so that the analysis subsystem can perform the following operations: converting the received raw information into structured parameters, updating the structured parameters according to the acquired current status information of the patient, and analyzing the updated structured parameters to generate a postoperative recovery plan;

[0064] Receive the postoperative recovery plan sent by the analysis subsystem.

[0065] To achieve the above-mentioned object, the present invention further provides a method for generating a postoperative recovery plan, comprising:

[0066] receiving original information of the patient sent by the interactive subsystem and converting the received original information into structured parameters, wherein the original information includes preoperative information and intraoperative information;

[0067] updating the structured parameters according to the acquired current status information of the patient;

[0068] The updated structured parameters are analyzed to generate a postoperative recovery plan and send the plan to the interactive subsystem.

[0069] To achieve the above-mentioned object, the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for generating a postoperative recovery plan is implemented.

[0070] Compared with the prior art, the postoperative recovery plan generation system, method and storage medium provided by the present invention have the following advantages: the present invention converts the patient's preoperative information and intraoperative information into structured parameters, updates the structured parameters according to the patient's current status information, and then analyzes the updated structured parameters to generate a postoperative recovery plan. It can be seen that the present invention can update the patient's structured parameters in real time, so that the recovery plan can be adjusted in real time according to the patient's current status, which is more helpful for the patient's postoperative recovery. In addition, the present invention can effectively reduce the doctor's workload by automatically generating a postoperative recovery plan. In addition, the present invention can effectively reduce the error rate of medication by generating a recovery plan based on historical cases in the database and the patient's own conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 Schematic diagram of the block structure of a postoperative recovery plan generation system in one embodiment of the present invention;

[0072] Figure 2 This is a schematic diagram illustrating the implementation principle of a postoperative recovery plan generation system in one embodiment of the present invention;

[0073] Figure 3 This is a schematic diagram of a process for obtaining preoperative information of a patient in one embodiment of the present invention;

[0074] Figure 4 is a top view of a portable terminal in one embodiment of the present invention;

[0075] Figure 5 is a rear view of a portable terminal in another embodiment of the present invention;

[0076] Figure 6 Schematic diagram of the principle of intraoperative information acquisition in one embodiment of the present invention;

[0077] Figure 7is a schematic diagram of displaying electronic table information in one embodiment of the present invention;

[0078] Figure 8 This is a schematic diagram of the overall workflow of a postoperative recovery plan generation system in one embodiment of the present invention;

[0079] Figure 9 Schematic diagram of the block structure of an information analysis module in one embodiment of the present invention;

[0080] Figure 10 Schematic diagram of the workflow of the complication analysis unit in one embodiment of the present invention;

[0081] Figure 11 This is a schematic diagram of a process for obtaining complication information based on similar cases in one embodiment of the present invention;

[0082] Figure 12 Schematic diagram of the recognition principle of endoscopic images in one embodiment of the present invention;

[0083] Figure 13 Schematic diagram of the recognition principle of surgical process recording information in one embodiment of the present invention;

[0084] Figure 14 Schematic diagram of the block structure of a solution generation module in one embodiment of the present invention;

[0085] Figure 15 FIG1 is a working principle diagram of a parameter updating unit in one embodiment of the present invention;

[0086] Figure 16 Schematic diagram of the working process of the parameter updating unit in one embodiment of the present invention;

[0087] Figure 17 Schematic diagram of the workflow of a sensitive parameter analysis unit in one embodiment of the present invention;

[0088] Figure 18 Schematic diagram of the workflow of the complication prediction unit in one embodiment of the present invention;

[0089] Figure 19 Schematic diagram of the workflow of a solution generation unit in one embodiment of the present invention;

[0090] Figure 20 A schematic diagram showing a recovery solution in one embodiment of the present invention;

[0091] Figure 21 Schematic diagram of a process for generating a postoperative recovery plan in one embodiment of the present invention;

[0092] Figure 22Schematic diagram of a process for generating a postoperative recovery plan in one embodiment of the present invention.

[0093] The accompanying drawings are numerals as follows:

[0094] Interaction subsystem-100; information interaction module-110; communication module-120;

[0095] Analysis subsystem 200; information analysis module 210; complication analysis unit 211; feature extraction unit 212; parameter generation unit 213; solution generation module 220; parameter update unit 221; sensitive parameter analysis unit 222; complication prediction unit 223; solution generation unit 224;

[0096] Portable terminal-1; code scanning device-11; image acquisition device-12;

[0097] Cloud Server-2;

[0098] Medical system-3;

[0099] Main control terminal-41; Operation terminal-42;

[0100] Feature extraction network-51; classification network-52; DETAILED DESCRIPTION

[0101] The postoperative recovery program generation system, generation method and storage medium proposed in the present invention are further described in detail below in conjunction with the accompanying drawings and specific embodiments. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the drawings. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification, so that people familiar with this technology can understand and read them, and are not used to limit the conditions for the implementation of the present invention. Any modification of the structure, change in the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed in the present invention, as long as it is the same or similar to the effect that can be produced and the purpose that can be achieved by the present invention.

[0102] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. In the description of the present invention, the meaning of "plurality" is at least two, for example two, three, etc., unless otherwise clearly and specifically defined.

[0103] The core concept of this invention is to provide a postoperative recovery plan generation system, method, and storage medium that can continuously track and provide feedback on the patient's condition, thereby enabling real-time adjustment of the recovery plan based on the patient's condition. It should be noted that the structured parameters referred to in this article refer to quantified characteristic parameters related to the formulation of the recovery plan.

[0104] To realize the above idea, the present invention provides a postoperative recovery plan generation system, please refer to Figure 1 , which schematically shows a block diagram of a postoperative recovery plan generation system provided by one embodiment of the present invention. Figure 1As shown, the postoperative recovery plan generation system includes an interactive subsystem 100 and an analysis subsystem 200 that are communicatively connected. The interactive subsystem 100 is used to obtain the patient's preoperative and intraoperative information, integrate the preoperative and intraoperative information to obtain the patient's original information, and send the original information to the analysis subsystem 200. The analysis subsystem 200 is used to convert the received original information into structured parameters, update the structured parameters based on the patient's current state information, analyze the updated structured parameters, generate a postoperative recovery plan, and send the postoperative recovery plan to the interactive subsystem 100. Thus, the postoperative recovery plan generation system provided by the present invention converts the patient's preoperative and intraoperative information into structured parameters, updates the structured parameters based on the patient's current state information, and analyzes the updated structured parameters to generate a postoperative recovery plan. It can be seen that the present invention can update the patient's structured parameters in real time, so that the recovery plan can be adjusted in real time according to the patient's current state, which is more helpful for the patient's postoperative recovery. It should be noted that, as those skilled in the art will appreciate, both the interaction subsystem 100 and the analysis subsystem 200 herein can access the internal medical system 3 of the hospital to implement related functions such as query and storage.

[0105] For further information, please refer to Figure 1 ,like Figure 1 As shown, the interactive subsystem 100 includes an information interaction module 110 and a communication module 120; wherein, the information interaction module 110 is used to obtain the patient's preoperative information and intraoperative information; the communication module 120 is used to realize data transmission between the information interaction module 110 and the analysis subsystem 200, and to integrate the preoperative information and the intraoperative information to obtain the patient's original information.

[0106] Specifically, the communication module 120 can be a wireless communication module, an active communication module, a Bluetooth communication module, etc. in the prior art, and the present invention is not limited thereto. It should be noted that, as can be understood by those skilled in the art, when the analysis subsystem 200 is provided on the cloud server 2 and the interaction subsystem 100 is provided on a portable mobile terminal, the communication module 120 is preferably a wireless communication module. Thus, by providing a wireless communication module, data transmission between the information interaction module 110 and the analysis subsystem 200 can be more easily achieved.

[0107] Furthermore, the preoperative information includes discrete variable information and continuous variable information;

[0108] The discrete variable information includes the type of surgery and / or the admission diagnosis and / or the physical fitness assessment and / or whether there is a chronic disease and / or whether the surgical site is inflamed and / or whether there is a relevant surgical history;

[0109] The continuous variable information includes patient age and / or coagulation function index and / or blood routine index and / or liver and kidney function index and / or electrolyte index.

[0110] It should be noted that, as those skilled in the art will appreciate, the preoperative information required for the present invention preferably includes all data items including the type of surgery (e.g., abdominal surgery, thoracic surgery, etc.), admission diagnosis, physical fitness assessment, presence of chronic diseases (e.g., heart disease, hypertension), inflammation at the surgical site, relevant surgical history, patient age, coagulation function indicators, blood routine indicators, liver and kidney function indicators, and electrolyte indicators. Therefore, obtaining detailed preoperative information can effectively improve the accuracy of the resulting postoperative recovery plan.

[0111] Please continue to refer to Figure 2 , which schematically shows the implementation principle diagram of the postoperative recovery plan generation system provided by one embodiment of the present invention. Figure 2 As shown, in an exemplary embodiment, the interactive subsystem 100 can be set on a portable terminal 1, such as a mobile phone, tablet computer, or other mobile terminal with various operating systems, and the analysis subsystem 200 can be set on a server, such as a cloud server 2. Thus, by adopting the specific implementation of the portable terminal 1 and the server, the interactive subsystem 100 and the analysis subsystem 200 can be separated, thereby making the doctor's operation more convenient and effectively simplifying the operation process.

[0112] Please continue to refer to Figure 3 , which schematically shows a flow chart of obtaining preoperative information of a patient provided by one embodiment of the present invention. Figure 3 As shown, the interaction subsystem 100 (the information interaction module 110) is used to obtain the patient's preoperative information through the following process:

[0113] Obtaining patient identification information;

[0114] The medical system 3 is accessed according to the identity information to obtain the preoperative information of the patient.

[0115] Specifically, when the interactive subsystem 100 is provided on the portable terminal 1, the portable terminal 1 should have the following functions:

[0116] 1. High-speed identification of patient identity information;

[0117] 2. Wireless high-speed data transmission;

[0118] 3. Log into the hospital's internal medical system 3;

[0119] 4. Portable display interactive function.

[0120] Therefore, after the interactive subsystem 100, that is, the portable terminal 1 obtains the patient's identity information, it can wirelessly log in to the medical system 3 within the hospital to query the patient's relevant data and prompt for missing data items. After the missing data items are supplemented, all the patient's preoperative information can be obtained.

[0121] Please continue to refer to Figure 4 , which schematically shows a top view of a portable terminal 1 in one embodiment of the present invention. Figure 4 As shown, the portable terminal 1 (the interactive subsystem 100) includes a code scanning device 11. Therefore, in this embodiment, the portable terminal 1 (the interactive subsystem 100) can obtain the patient's identity information by scanning the QR code worn by the patient.

[0122] Please continue to refer to Figure 5 , which schematically shows a rear view of a portable terminal 1 provided in another embodiment of the present invention. Figure 5 The portable terminal 1 (the interactive subsystem 100) includes an image acquisition device 12. Therefore, in this embodiment, the portable terminal 1 (the interactive subsystem 100) can obtain the patient's identity information by collecting the patient's facial information.

[0123] Furthermore, the intraoperative information includes at least one of endoscopic image information, surgical process recording information, surgical instrument movement information, and electronic spreadsheet information. Figure 6 , which schematically shows the principle diagram of intraoperative information acquisition provided by one embodiment of the present invention. Figure 6As shown, when a surgical robot system is used to perform surgery, the doctor can control the operating terminal 42 to perform the surgery by manipulating the main control terminal 41, wherein the end of at least one robotic arm of the operating terminal 42 is equipped with a surgical instrument for performing the surgery, and the end of at least one robotic arm of the operating terminal 42 is equipped with an endoscope for collecting endoscopic images. The operating room is also equipped with a recording device, so that the surgical process can be recorded through the recording device. After the surgery is performed, the doctor fills out an electronic spreadsheet on the computer to record the surgical situation. Therefore, by connecting the portable terminal 1 (the interactive subsystem 100) to the corresponding device for communication, endoscopic image information, surgical process recording information, surgical instrument movement information and electronic spreadsheet information can be obtained. Therefore, the present invention can provide a basis for subsequently obtaining key time nodes in the surgical process by obtaining surgical process recording information, and can provide a basis for subsequently obtaining the degree of damage caused by the instrument to the patient by obtaining endoscopic image information and surgical instrument movement information.

[0124] Furthermore, the electronic spreadsheet information includes the amount of bleeding and / or the mass of resected tissue and / or the amount of drainage and / or the operation time and / or the difficulty of the operation and / or whether the operation was completed normally and / or the estimated risk of complications and / or the estimated recovery time. Figure 7 , which schematically shows a display diagram of electronic table information provided by an embodiment of the present invention. Figure 7 As shown, in order to further improve the accuracy of the generated postoperative recovery plan, the electronic spreadsheet information includes all the data items listed above.

[0125] Please continue to refer to Figure 1 ,like Figure 1 As shown, the analysis subsystem 200 includes an information analysis module 210 and a solution generation module 220; the information analysis module 210 is used to convert the received original information into structured parameters and send them to the solution generation module 220; the solution generation module 220 is used to update the structured parameters and analyze the updated structured parameters to generate a postoperative recovery plan and send it to the interactive subsystem 100.

[0126] Please continue to refer to Figure 8 , which schematically shows the overall workflow of the postoperative recovery plan generation system provided by one embodiment of the present invention. Figure 8As shown, the postoperative recovery plan generation system provided by the present invention first obtains the patient's preoperative information and intraoperative information through the information interaction module 110; then integrates the preoperative information and the intraoperative information through the communication module 120 to obtain the original information, and transmits it to the information analysis module 210; then converts the original information into structured parameters through the information analysis module 210; then updates the structured parameters through the plan generation module 220 to generate a postoperative recovery plan; then returns the postoperative recovery plan to the information interaction module 110 through the communication module 120 for display, and the doctor can modify or confirm the displayed postoperative recovery plan.

[0127] Please continue to refer to Figure 9 , which schematically shows a block diagram of the information analysis module 210 provided by an embodiment of the present invention. Figure 9 As shown, the information analysis module 210 includes a complication analysis unit 211, a feature extraction unit 212, and a parameter generation unit 213. The complication analysis unit 211 is configured to obtain complication information based on the preoperative information and the spreadsheet information; the feature extraction unit 212 is configured to obtain a first feature parameter for characterizing the degree of damage caused to the patient by the surgical instrument based on the endoscopic image information and the surgical instrument motion information; and to obtain a second feature parameter for characterizing the surgical procedure sequence based on the surgical recording information; and the parameter generation unit 213 is configured to generate structured parameters based on the preoperative information, the spreadsheet information, the complication information, the first feature parameter, and the second feature parameter.

[0128] Specifically, if Figure 9 As shown, the complication information (i.e., complication condition parameters) can be obtained by integrating the patient's preoperative information and the intraoperative spreadsheet information and inputting them into the complication analysis unit 211 for analysis. Since the patient's preoperative information collected before the operation and the doctor's spreadsheet information filled in are themselves quantitative feature parameters, no further conversion is required. Since the intraoperative endoscopic image information, the surgical process recording information, and the surgical instrument movement information have no intuitive connection with the formulation of the patient's postoperative recovery plan, it is necessary to use the feature extraction unit 212 to convert the endoscopic image information and the surgical instrument movement information into a first feature parameter that has an intuitive connection with the formulation of the patient's postoperative recovery plan, and to convert the surgical process recording information into a second feature parameter that has an intuitive connection with the formulation of the patient's postoperative recovery plan. The parameter generation unit 213 then merges the patient's preoperative information, the intraoperative spreadsheet information, the complication information, the first feature parameter, and the second feature parameter to generate the patient's structured parameters.

[0129] Please continue to refer to Figure 10 , which schematically shows a workflow diagram of the complication analysis unit 211 provided in one embodiment of the present invention. Figure 10 As shown, the complication analysis unit 211 is specifically configured to obtain the complication information through the following process:

[0130] Acquiring initial structured parameters of the patient based on the preoperative information and the electronic spreadsheet information;

[0131] According to the initial structural parameters of the patient, searching in a database for target initial structural parameters whose distance from the initial structural parameters of the patient is within a preset threshold range;

[0132] taking the case corresponding to the target initial structured parameter as a similar case matching the patient;

[0133] The complication information of the patient is obtained based on the complication information of the similar cases.

[0134] Specifically, the database stores a large number of cases, each of which includes structured parameters of previous patients (including preoperative information, intraoperative spreadsheet information, complication information, first characteristic parameters, and second characteristic parameters) and corresponding treatment plans (postoperative recovery plans). Initial structured parameters are generated based on the patient's preoperative information and intraoperative spreadsheet information, and then the target initial structured parameters (i.e., parameters generated by the preoperative information and intraoperative spreadsheet information of previous patients) are searched in the database based on the patient's initial structured parameters. The distance between the target initial structured parameters and the patient's initial structured parameters (e.g., paradigm distance) is within a preset threshold range. Since the difference between the target initial structured parameters and the patient's initial structured parameters is small (the smaller the difference, the smaller the distance), the case corresponding to the target initial structured parameters can be used as a similar case matching the patient (the smaller the distance, the closer the situation), so that the complication information of the patient can be obtained based on the complication information of the similar case. Thus, the present invention uses a big data-based method to obtain the complication information of the patient using the data of historical patients with similar conditions to the patient, which can effectively improve the accuracy of the obtained complication information of the patient.

[0135] Please continue to refer to Figure 11 , which schematically shows a flow chart of obtaining complication information based on similar cases provided by one embodiment of the present invention. Figure 11 As shown, the step of obtaining the complication information of the patient based on the complication information of the similar cases includes:

[0136] Count the frequency of each complication in all similar cases;

[0137] According to the frequency of each complication, complications that meet the preset conditions are selected as valid complications;

[0138] Determine whether the number of effective complications is equal to a first preset number; if not, increase the preset threshold range and continue searching the database for similar cases matching the patient until the number of effective complications is equal to the first preset number.

[0139] Specifically, complications with a higher frequency of occurrence can be selected as effective complications (i.e., complications that may occur in the patient). If the number of effective complications selected based on the preset threshold range does not reach the first preset number, the threshold range is increased, and the target initial structural parameters whose distance from the initial structural parameters of the patient is within the new threshold range are searched again in the database to expand similar cases. Then, according to the same method, complications with a higher frequency of occurrence are screened as effective complications, and the number of screened effective complications is further determined to be equal to the first preset number. If so, the search is terminated, and the screened effective complications are used as complications that may occur in the patient to obtain the patient's complication information. If it has not yet been reached, the threshold range is continued to be increased, and similar cases are continued to be expanded until the number of effective complications is equal to the first preset number.

[0140] Furthermore, the complication information includes complication type information and corresponding complication severity information. Since complications of the same type may have different severities, for example, if the complications of incision redness and swelling (mild) and incision redness and swelling (severe) have different severities, their corresponding treatment plans (e.g., medication dosage, medication type) may also be different. Therefore, the complication information obtained by the present invention includes both complication type information and complication severity information, which can further improve the accuracy of the generated postoperative recovery plan.

[0141] In an exemplary embodiment, the feature extraction unit 212 is used to use a pre-trained deep convolutional neural network model to identify the endoscopic image information to determine whether the surgical instrument contacts the patient's tissue. If the judgment result is yes, the cumulative path of the surgical instrument contacting the patient's tissue is calculated based on the motion information of the surgical instrument to obtain a first feature parameter for characterizing the degree of damage caused by the surgical instrument to the patient. Since the endoscopic image information is composed of a series of endoscopic images (i.e., an endoscopic image sequence), and each endoscopic image corresponds to a surgical moment, each endoscopic image can be identified separately by the pre-trained deep convolutional neural network model to determine whether the surgical instrument contacts the patient's tissue at the corresponding moment, thereby determining at which moments the surgical instrument contacts the patient's tissue. Then, based on the motion information of the surgical instrument, the movement speed of the surgical instrument is calculated and integrated to calculate the cumulative path of the surgical instrument contacting the patient's tissue. The longer the cumulative path, the greater the degree of damage caused by the surgical instrument to the patient. Please continue to refer to Figure 12 , which schematically shows the recognition principle of endoscopic images provided by one embodiment of the present invention. Figure 12 As shown, the deep convolutional neural network model includes a feature extraction network 51 and a classification network 52. The feature extraction network 51 includes multiple convolution layers, and the classification network 52 includes multiple fully connected layers. When the endoscopic image is input into the feature extraction network 51, the convolution operation is performed through the convolution layer to extract the image features. After the extracted image features are regressed through the nonlinear mapping of the fully connected layer in the classification network 52, the classification result of the endoscopic image can be output, that is, whether the surgical instrument contacts the patient's tissue at the surgical moment corresponding to the endoscopic image.

[0142] In an exemplary embodiment, the feature extraction unit 212 is used to use a pre-trained Seq2Seq model to identify the surgical process recording information to obtain a second feature parameter for characterizing the surgical process sequence. The Seq2Seq model is simply a translation model used to translate a language sequence into another language sequence. The entire processing process is to use a deep neural network (LSTM (Long Short Term Memory Network) or RNN (Recurrent Neural Network) to map a sequence as input to another output sequence. For details, please refer to Figure 13, which schematically shows a schematic diagram of the recognition principle of the surgical process recording information provided by one embodiment of the present invention. As shown in Figure 13, the Seq2Seq model includes an encoder and a decoder, the encoder is used to encode the audio time course of the surgical process recording information, and the decoder is used to identify key time nodes (such as entering anesthesia, ending anesthesia, starting resection, ending resection, etc.) according to the encoding results of the audio time course, so as to obtain a second characteristic parameter for characterizing the surgical process sequence. As for how the encoder encodes the audio time course of the surgical process recording information and how the decoder identifies key time node information according to the encoding results of the audio time course, you can refer to the existing audio recognition technology, so we will not elaborate on this.

[0143] Please continue to refer to Figure 14 , which schematically shows a block diagram of the solution generation module 220 provided in one embodiment of the present invention. Figure 14 As shown, the solution generation module 220 includes a parameter updating unit 221, a sensitive parameter analyzing unit 222, a complication prediction unit 223 and a solution generation unit 224; wherein the parameter updating unit 221 is used to update the complication information of the patient according to the current status information of the patient to obtain updated structured parameters; the sensitive parameter analyzing unit 222 is used to analyze each complication in the updated structured parameters to obtain sensitive parameters corresponding to each complication; the complication prediction unit 223 is used to obtain augmented structured parameters according to the updated structured parameters and the sensitive parameters, and predict the occurrence probability of each complication according to the augmented structured parameters to obtain complication prediction results; the solution generation unit 224 is used to generate a postoperative recovery plan according to the complication prediction results, and send it to the interactive subsystem 100.

[0144] Specifically, the parameter updating unit 221 is connected to the medical system 3 within the hospital, so that the parameter updating unit 221 can obtain the current status information of the patient from the medical system 3 to cyclically update the patient's structured parameters. Figure 15 , which schematically shows the working principle diagram of the parameter updating unit 221 provided in one embodiment of the present invention. Figure 15 As shown, the parameter updating unit 221 only needs to update the patient's complication information, without having to update the patient's preoperative information, intraoperative electronic spreadsheet information, first characteristic parameter, second characteristic parameter and other information. Figure 16 , which schematically shows a workflow diagram of the parameter updating unit 221 provided in one embodiment of the present invention. Figure 16As shown, the parameter updating unit 221 updates the patient's complication information through the following process:

[0145] determining whether the patient has a new complication according to the patient's current condition information;

[0146] If yes, adding the new complication and the complication in the structured parameters before updating into the same list;

[0147] All complications in the list are sorted according to severity, complications ranked in the first preset digit range of severity are removed, and the remaining complications are used as updated complications to obtain updated complication information.

[0148] Specifically, if a patient develops a new complication during clinical treatment (a new type of complication appears or the original type of complication becomes more severe), that is, the new complication is not in the structured parameter before the update, then the new complication and the complication in the structured parameter before the update are first added to the same list, and then all complications in the list are sorted according to severity, and complications with low severity rankings are removed (if several new complications are added, several complications with relatively mild severity are removed), and the remaining complications are used as updated complications to obtain updated complication information. In special cases, if the severity of multiple complications is relatively mild at the same time, the complications with relatively low frequency when screening for effective complications are removed. The present invention can ensure that the number of complications in the structured parameter remains unchanged before and after the update by removing complications whose severity ranking is within the first preset digit range, thereby ensuring the uniformity of the structured parameter dimensions, which is more conducive to data analysis.

[0149] Please continue to refer to Figure 17 , which schematically shows a workflow diagram of the sensitive parameter analysis unit 222 provided in one embodiment of the present invention. Figure 17 As shown, the sensitive parameter analysis unit 222 analyzes each type of complication in the updated structural parameters through the following process:

[0150] According to the updated structural parameters, searching for a second preset number of similar cases in the database to form a first case set;

[0151] For each complication type in the updated structured parameters:

[0152] Counting whether each similar case in the first case set has the same type of complication, so as to obtain a binary classification result of the same type of complication;

[0153] According to the binary classification results of this type of complication, significance analysis was performed to obtain the sensitive parameters of this type of complication.

[0154] Specifically, the paradigm distance between the structured parameters of the patient and the structured parameters corresponding to each case in the database can be calculated based on the updated structured parameters, and a second preset number of similar cases close to the patient can be screened out to form a first case set. Then, for each type of complication in the updated structured parameters (excluding severity, such as wound redness and swelling), each similar case in the first case set is counted to see whether the complication of that type occurs. If so, the similar case is assigned to the data group with the classification label of "yes" corresponding to the complication of that type. If not, the similar case is assigned to the data group with the classification label of "no" corresponding to the complication of that type. By analogy, a binary classification result of similar cases corresponding to each type of complication can be obtained. For each type of complication, by comparing the data of similar cases of the two classifications corresponding to the complication of that type and performing a significance analysis, the sensitive parameters of the complication of that type (i.e., which parameters the complication of that type is more sensitive to) can be obtained.

[0155] Please continue to refer to Figure 18 , which schematically shows a workflow diagram of the complication prediction unit 223 provided in one embodiment of the present invention. Figure 18 As shown, the complication prediction unit 223 predicts the probability of occurrence of each complication through the following process:

[0156] According to the augmented structured parameters, searching a third preset number of similar cases in the database to form a second case set;

[0157] For each complication in the augmented structured parameters:

[0158] Counting whether each similar case in the second case set has the complication to obtain a binary classification result of the complication;

[0159] According to the binary classification results of the complication, the occurrence probability of the complication is calculated to obtain the prediction result of the complication.

[0160] Specifically, the paradigm distance between the augmented structured parameters of the patient and the structured parameters corresponding to each case in the database can be calculated based on the augmented structured parameters (a combination of the updated structured parameters and the results of the sensitive parameter analysis), and a third preset number of similar cases close to the patient can be screened out to form a second case set. Then, for each complication in the augmented structured parameters (including the type and severity of the complication, such as redness and swelling of the incision (mild)), statistics are made on whether the complication occurs in each similar case in the second case set. If it occurs, the similar case is assigned to the data group with the classification label "yes" corresponding to the complication. If it does not occur, the similar case is assigned to the data group with the classification label "no" corresponding to the complication. By analogy, the binary classification results of the similar cases corresponding to each complication can be obtained. For each complication, the number of cases in the data group with the classification label "yes" corresponding to the complication is counted, expressed as the number of cases of the complication, and the number of cases of the complication is divided by the total number of cases in the third set (i.e., the third preset number), and the probability of occurrence of the complication, i.e., the prediction result of the complication, can be obtained. Therefore, by obtaining the prediction results of various complications, the present invention can warn of complications that may occur with a high probability, which helps patients take protective measures in advance.

[0161] Please continue to refer to Figure 19 , which schematically shows a workflow diagram of the solution generation unit 224 provided in one embodiment of the present invention. Figure 19 As shown, the plan generating unit 224 generates a postoperative recovery plan through the following process:

[0162] Performing a confidence analysis on the complication prediction result and the complications of the patient's clinical manifestations to determine whether the complication prediction result is accurate;

[0163] If yes, the complication with the probability of occurrence ranked in the second preset range is used as the target complication; if no, the complication of the clinical manifestation in the updated structured parameters is used as the target complication;

[0164] The treatment plan for the target complication is searched in the database according to the target complication to generate a postoperative recovery plan.

[0165] Specifically, if the complications ranked with the highest probability of occurrence match the patient's clinical presentation, the predicted complication is accurate, and the complications ranked with the highest probability of occurrence are selected as target complications. If the complications ranked with the highest probability of occurrence do not match the patient's clinical presentation, the predicted complication is inaccurate, and the patient's clinical presentation is selected as the target complication. After the target complication is determined, the treatment plan for the target complication can be searched in the database to generate a postoperative recovery plan.

[0166] Furthermore, searching the database for a treatment plan for the target complication to generate a postoperative recovery plan includes:

[0167] According to the target complication and the updated structured parameters, searching the database for all similar cases having the target complication, and collecting statistics on similar cases in which the target complication improved after treatment;

[0168] All treatment plans for similar cases in which the target complication was improved were evaluated, and the treatment plan with the highest evaluation was used as the postoperative recovery plan.

[0169] Specifically, according to the target complication and the updated structured parameters, all similar cases with the target complication and close to the patient's condition can be found in the database, and all similar cases in which the target complication has improved can be screened out, and the treatment plans of all similar cases in which the target complication has improved can be evaluated based on multi-dimensional indicators such as comprehensive recovery status and recovery speed, so as to screen out the best treatment plan (i.e. the treatment plan with the highest evaluation) as the postoperative recovery plan. Therefore, the present invention can effectively improve the patient's recovery speed by matching the best recovery plan with historical data based on a big data analysis method. It should be noted that, as can be understood by those skilled in the art, if the patient has multiple target complications, the best treatment plan is screened out for each target complication according to the above method, and then the treatment plans for multiple target complications are merged to obtain a postoperative recovery plan.

[0170] In an exemplary embodiment, the interactive subsystem 100 (portable terminal 1) is further configured to receive the doctor's confirmation or modification of the postoperative recovery plan and send the modified postoperative recovery plan to the analysis subsystem 200 (cloud server 2). Thus, by receiving the doctor's confirmation or modification of the postoperative recovery plan, the accuracy of the final postoperative recovery plan can be further ensured; by returning the modified postoperative recovery plan to the analysis subsystem 200 (cloud server 2), the accuracy of the recovery plan stored in the database of the analysis subsystem 200 can be guaranteed. Please continue to refer to Figure 20 , which schematically shows a display diagram of a recovery solution provided by an embodiment of the present invention. Figure 20 As shown, the doctor can confirm and modify the postoperative recovery plan generated by the plan generation module 220 through the interactive subsystem 100 (portable terminal 1), thereby further ensuring the accuracy of medication and improving the patient's postoperative recovery effect. In addition, since the present invention can automatically generate a postoperative recovery plan, the doctor only needs to adjust and confirm part of the medication, which can effectively reduce the doctor's workload. In addition, as Figure 20 As shown, the analysis subsystem 200 (cloud server 2) also sends the updated structural parameters and complication prediction results to the interactive subsystem 100 (portable terminal 1) for display. Thus, the doctor can better judge whether the postoperative recovery plan pushed by the analysis subsystem 200 is correct based on the updated structural parameters and complication prediction results.

[0171] Based on the same inventive concept, the present invention also provides a method for generating a postoperative recovery plan. In this embodiment, the execution subject of the postoperative recovery plan generation method is the interactive subsystem (portable terminal 1) in the postoperative recovery plan generation system mentioned above. Figure 21 , which schematically shows a flow chart of a method for generating a postoperative recovery plan according to an embodiment of the present invention. Figure 21 As shown, the postoperative recovery plan generation method includes the following steps:

[0172] Step S110: obtaining the patient's preoperative information and intraoperative information, and integrating them to obtain the patient's original information;

[0173] Step S120: Sending the raw information to the analysis subsystem so that the analysis subsystem can perform the following operations: converting the received raw information into structured parameters, updating the structured parameters based on the acquired current status information of the patient, and analyzing the updated structured parameters to generate a postoperative recovery plan;

[0174] Step S130: Receive the postoperative recovery plan sent by the analysis subsystem.

[0175] In an exemplary embodiment, obtaining the patient's preoperative information includes:

[0176] Obtaining patient identification information;

[0177] Log into the medical system according to the identity information to obtain the patient's preoperative information.

[0178] In an exemplary embodiment, the postoperative recovery plan generation method further includes:

[0179] Receive the doctor's confirmation operation or modification operation on the postoperative recovery plan, and send the modified postoperative recovery plan to the analysis subsystem.

[0180] The postoperative recovery plan generation method provided by the present invention can thus update the patient's structured parameters in real time, allowing for real-time adjustments to the recovery plan based on the patient's current condition, further facilitating postoperative recovery. Furthermore, since doctors only need to adjust and confirm the automatically generated postoperative recovery plan, their workload can be effectively reduced.

[0181] Regarding how the analysis subsystem converts the received raw information into structured parameters, updates the structured parameters based on the current status information of the patient obtained, and analyzes the updated structured parameters to generate a postoperative recovery plan, please refer to the relevant description above and will not be repeated here.

[0182] Based on the same inventive concept, the present invention also provides a method for generating a postoperative recovery plan. In this embodiment, the execution subject of the postoperative recovery plan generation method is the analysis subsystem (cloud server 2) in the postoperative recovery plan generation system mentioned above. Figure 22 , which schematically shows a flow chart of a method for generating a postoperative recovery plan according to an embodiment of the present invention. Figure 22 As shown, the postoperative recovery plan generation method includes the following steps:

[0183] Step S210: receiving original information of the patient sent by the interactive subsystem, and converting the received original information into structured parameters, wherein the original information includes preoperative information and intraoperative information;

[0184] Step S220: updating the structured parameters according to the acquired current status information of the patient;

[0185] Step S230: Analyze the updated structured parameters to generate a postoperative recovery plan and send it to the interactive subsystem.

[0186] In an exemplary embodiment, the intraoperative information includes: endoscopic image information, surgical process recording information, surgical instrument movement information, and electronic spreadsheet information.

[0187] In an exemplary embodiment, converting the received original information into structured parameters includes:

[0188] obtaining complication information based on the preoperative information and the electronic form information;

[0189] Acquire, based on the endoscopic image information and the surgical instrument movement information, a first characteristic parameter for characterizing a degree of damage caused to the patient by the surgical instrument;

[0190] Acquiring a second characteristic parameter for characterizing a sequence of the surgical procedure according to the surgical procedure recording information;

[0191] A structured parameter is generated according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter.

[0192] In an exemplary embodiment, obtaining complication information based on the preoperative information and the electronic spreadsheet information includes:

[0193] Acquiring initial structured parameters of the patient based on the preoperative information and the electronic spreadsheet information;

[0194] According to the initial structural parameters of the patient, searching in a database for target initial structural parameters whose distance from the initial structural parameters of the patient is within a preset threshold range;

[0195] taking the case corresponding to the target initial structured parameter as a similar case matching the patient;

[0196] The complication information of the patient is obtained based on the complication information of the similar cases.

[0197] In an exemplary embodiment, obtaining the complication information of the patient based on the complication information of the similar case includes:

[0198] Count the frequency of each complication in all similar cases;

[0199] According to the frequency of each complication, complications that meet the preset conditions are selected as valid complications;

[0200] determining whether the number of the effective complications is equal to a first preset number;

[0201] If not, the preset threshold range is increased, and similar cases matching the patient are continuously searched in the database until the number of effective complications is equal to a first preset number.

[0202] In an exemplary embodiment, the acquiring, based on the endoscopic image information and the surgical instrument motion information, a first characteristic parameter for characterizing the degree of damage caused by the surgical instrument to the patient, includes:

[0203] Using a pre-trained deep convolutional neural network model to identify the endoscopic image information to determine whether the surgical instrument contacts the patient's tissue;

[0204] If the judgment result is yes, the cumulative path of the surgical instrument contacting the patient's tissue is calculated based on the movement information of the surgical instrument to obtain a first characteristic parameter for characterizing the degree of damage caused by the surgical instrument to the patient.

[0205] In an exemplary embodiment, obtaining a second characteristic parameter for characterizing a surgical procedure sequence based on the surgical procedure recording information includes:

[0206] The pre-trained Seq2Seq model is used to identify the surgical process recording information to obtain a second feature parameter for characterizing the surgical process sequence.

[0207] In an exemplary embodiment, updating the structured parameters according to the acquired current status information of the patient includes:

[0208] The complication information of the patient is updated according to the current status information of the patient to obtain updated structured parameters.

[0209] In an exemplary embodiment, updating the patient's complication information based on the patient's current status information includes:

[0210] determining whether the patient has a new complication according to the patient's current condition information;

[0211] If yes, adding the new complication and the complication in the structured parameters before updating into the same list;

[0212] All complications in the list are sorted according to severity, complications ranked in the first preset digit range of severity are removed, and the remaining complications are used as updated complications to obtain updated complication information.

[0213] In an exemplary embodiment, analyzing the updated structured parameters to generate a postoperative recovery plan includes:

[0214] Analyzing each type of complication in the updated structured parameters to obtain a sensitive parameter corresponding to each type of complication;

[0215] Acquire augmented structured parameters according to the updated structured parameters and the sensitive parameters;

[0216] Predicting the occurrence probability of each complication according to the augmented structured parameters to obtain a complication prediction result;

[0217] A postoperative recovery plan is generated based on the complication prediction results.

[0218] In an exemplary embodiment, analyzing each type of complication in the updated structured parameters to obtain a sensitive parameter corresponding to each type of complication includes:

[0219] According to the updated structural parameters, searching for a second preset number of similar cases in the database to form a first case set;

[0220] For each complication type in the updated structured parameters:

[0221] Counting whether each similar case in the first case set has the same type of complication, so as to obtain a binary classification result of the same type of complication;

[0222] According to the binary classification results of this type of complication, significance analysis was performed to obtain the sensitive parameters of this type of complication.

[0223] In an exemplary embodiment, predicting the occurrence probability of each complication based on the augmented structured parameter to obtain a complication prediction result includes:

[0224] According to the augmented structured parameters, searching a third preset number of similar cases in the database to form a second case set;

[0225] For each complication in the augmented structured parameters:

[0226] Counting whether each similar case in the second case set has the complication to obtain a binary classification result of the complication;

[0227] According to the binary classification results of the complication, the occurrence probability of the complication is calculated to obtain the prediction result of the complication.

[0228] In an exemplary embodiment, generating a postoperative recovery plan based on the complication prediction result includes:

[0229] Performing a confidence analysis on the complication prediction result and the complications of the patient's clinical manifestations to determine whether the complication prediction result is accurate;

[0230] If yes, the complication with the probability of occurrence ranked in the second preset range is used as the target complication; if no, the complication of the clinical manifestation in the updated structured parameters is used as the target complication;

[0231] The treatment plan for the target complication is searched in the database according to the target complication to generate a postoperative recovery plan.

[0232] In an exemplary embodiment, searching the database for a treatment plan for the target complication according to the target complication to generate a postoperative recovery plan includes:

[0233] According to the target complication and the updated structured parameters, searching the database for all similar cases having the target complication, and collecting statistics on similar cases in which the target complication improved after treatment;

[0234] All treatment plans for similar cases in which the target complication was improved were evaluated, and the treatment plan with the highest evaluation was used as the postoperative recovery plan.

[0235] Thus, the postoperative recovery plan generation method provided by the present invention can update the patient's structured parameters in real time, so that the recovery plan can be adjusted in real time according to the patient's current condition, which is more helpful for the patient's postoperative recovery. In addition, the postoperative recovery plan generation method provided by the present invention can effectively reduce the doctor's workload by automatically generating a postoperative recovery plan. In addition, the postoperative recovery plan generation method provided by the present invention can effectively reduce the error rate of medication by generating a recovery plan based on historical cases in the database and the patient's own condition.

[0236] The present invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the method for generating a postoperative recovery plan described above. Because the readable storage medium provided by the present invention and the method for generating a postoperative recovery plan described above are based on the same inventive concept, it possesses all the advantages of the method described above and will not be further described.

[0237] The readable storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer hard disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this article, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0238] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0239] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0240] In summary, compared with the prior art, the postoperative recovery plan generation system, method and storage medium provided by the present invention have the following advantages: the present invention converts the patient's preoperative information and intraoperative information into structured parameters, updates the structured parameters according to the patient's current status information, and then analyzes the updated structured parameters to generate a postoperative recovery plan. It can be seen that the present invention can update the patient's structured parameters in real time, so that the recovery plan can be adjusted in real time according to the patient's current status, which is more helpful for the patient's postoperative recovery. In addition, the present invention can effectively reduce the doctor's workload by automatically generating a postoperative recovery plan. In addition, the present invention can effectively reduce the error rate of medication by generating a recovery plan based on historical cases in the database and the patient's own conditions.

[0241] It should be noted that the devices and methods disclosed in the embodiments of this document may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the devices, methods, and computer program products according to the various embodiments of this document. In this regard, each box in the flowchart or block diagram may represent a module, program, or portion of code, wherein the module, program segment, or portion of code contains one or more executable instructions for implementing a specified logical function, and the module, program segment, or portion of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0242] In addition, the functional modules in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part. In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like are intended to mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0243] The above description is merely a description of preferred embodiments of the present invention and does not limit the scope of the present invention. Any changes or modifications made by persons skilled in the art based on the above disclosure are within the scope of protection of the present invention. Obviously, various modifications and variations may be made by persons skilled in the art without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the present invention and its equivalents, the present invention is intended to include such modifications and variations.

Claims

1. A postoperative recovery plan generation system, characterized in that: Including interactive subsystem and analysis subsystem with communication connection; The interactive subsystem is used to obtain the patient's preoperative information and intraoperative information, integrate them to obtain the patient's original information, and send the original information to the analysis subsystem; The analysis subsystem is used to convert the received raw information into structured parameters, update the structured parameters according to the acquired current status information of the patient, and analyze the updated structured parameters to generate a postoperative recovery plan and send it to the interaction subsystem; The intraoperative information includes endoscopic image information, surgical process recording information, surgical instrument movement information, and spreadsheet information, wherein the spreadsheet information includes bleeding volume and / or resected tissue quality and / or drainage volume and / or surgical difficulty and / or whether the surgery was completed normally and / or estimated complication risk; The analysis subsystem is used to: obtaining complication information based on the preoperative information and the electronic form information; Acquire, based on the endoscopic image information and the surgical instrument movement information, a first characteristic parameter for characterizing a degree of damage caused to the patient by the surgical instrument; Acquiring a second characteristic parameter for characterizing a sequence of the surgical procedure according to the surgical procedure recording information; as well as generating structured parameters according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter; The complication information of the patient is updated according to the current status information of the patient to obtain updated structured parameters.

2. The postoperative recovery plan generation system according to claim 1, characterized in that: The interactive subsystem is used to obtain the patient's preoperative information through the following process: Obtaining patient identification information; Access a medical system according to the identity information to obtain preoperative information of the patient.

3. The postoperative recovery plan generation system according to claim 1, characterized in that: The interactive subsystem is used to obtain the patient's identity information by scanning a QR code worn by the patient; or The patient's identity information is obtained by collecting the patient's facial information.

4. The postoperative recovery plan generation system according to claim 1, characterized in that: The preoperative information includes discrete variable information and continuous variable information; The discrete variable information includes the type of surgery and / or the admission diagnosis and / or the physical fitness assessment and / or whether there is a chronic disease and / or whether the surgical site is inflamed and / or whether there is a relevant surgical history; The continuous variable information includes patient age and / or coagulation function index and / or blood routine index and / or liver and kidney function index and / or electrolyte index.

5. The postoperative recovery plan generation system according to claim 1, characterized in that: The spreadsheet information may also include surgical time and / or estimated recovery time.

6. The postoperative recovery plan generation system according to claim 1, characterized in that: The analysis subsystem includes an information analysis module and a solution generation module; The information analysis module is used to convert the received original information into structured parameters and send them to the solution generation module; The solution generation module is used to update the structured parameters and analyze the updated structured parameters to generate a postoperative recovery solution and send it to the interactive subsystem.

7. The postoperative recovery plan generation system according to claim 6, characterized in that: The information analysis module includes a complication analysis unit, a feature extraction unit and a parameter generation unit; The complication analysis unit is used to obtain complication information based on the preoperative information and the electronic table information; The feature extraction unit is configured to obtain, based on the endoscopic image information and the surgical instrument movement information, a first feature parameter for characterizing the degree of damage caused to the patient by the surgical instrument; and to obtain, based on the surgical recording information, a second feature parameter for characterizing the surgical procedure sequence; The parameter generating unit is configured to generate structured parameters according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter.

8. The postoperative recovery plan generation system according to claim 7, characterized in that: The complication analysis unit is configured to obtain the complication information through the following process: Acquiring initial structured parameters of the patient based on the preoperative information and the electronic spreadsheet information; According to the initial structural parameters of the patient, searching in a database for target initial structural parameters whose distance from the initial structural parameters of the patient is within a preset threshold range; taking the case corresponding to the target initial structured parameter as a similar case matching the patient; The complication information of the patient is obtained based on the complication information of the similar cases.

9. The postoperative recovery plan generation system according to claim 8, characterized in that: The obtaining of complication information of the patient based on complication information of the similar case includes: Count the frequency of each complication in all similar cases; According to the frequency of each complication, complications that meet the preset conditions are selected as valid complications; Determine whether the number of effective complications is equal to a first preset number. If not, increase the preset threshold range and continue to search the database for similar cases matching the patient until the number of effective complications is equal to the first preset number to obtain the patient's complication information.

10. The postoperative recovery plan generation system according to claim 7, characterized in that: The feature extraction unit is used to use a pre-trained deep convolutional neural network model to identify the endoscopic image information to determine whether the surgical instrument contacts the patient's tissue. If the judgment result is yes, the cumulative path of the surgical instrument contacting the patient's tissue is calculated based on the surgical instrument movement information to obtain a first characteristic parameter used to characterize the degree of damage caused to the patient by the surgical instrument.

11. The postoperative recovery plan generation system according to claim 7, characterized in that: The feature extraction unit is used to use a pre-trained Seq2Seq model to identify the surgical process recording information to obtain a second feature parameter for characterizing the surgical process sequence.

12. The postoperative recovery plan generation system according to claim 6, characterized in that: The complication information includes complication type information and corresponding complication severity information; The solution generation module includes a parameter updating unit, a sensitive parameter analysis unit, a complication prediction unit and a solution generation unit; The parameter updating unit is used to update the complication information of the patient according to the current status information of the patient to obtain updated structured parameters; The sensitive parameter analysis unit is used to analyze each complication in the updated structured parameters to obtain the sensitive parameter corresponding to each complication; The complication prediction unit is used to obtain an augmented structured parameter based on the updated structured parameter and the sensitive parameter, and predict the occurrence probability of each complication based on the augmented structured parameter to obtain a complication prediction result; The plan generating unit is used to generate a postoperative recovery plan based on the complication prediction result and send it to the interactive subsystem.

13. The postoperative recovery plan generation system according to claim 12, characterized in that: The parameter updating unit updates the patient's complication information through the following process: determining whether the patient has a new complication according to the patient's current condition information; If yes, adding the new complication and the complication in the structured parameters before updating into the same list; All complications in the list are sorted according to severity, complications ranked in the first preset digit range of severity are removed, and the remaining complications are used as updated complications to obtain updated complication information.

14. The postoperative recovery plan generation system according to claim 12, characterized in that: The sensitive parameter analysis unit analyzes each type of complication in the updated structural parameters through the following process: According to the updated structural parameters, searching for a second preset number of similar cases in the database to form a first case set; For each complication type in the updated structured parameters: Counting whether each similar case in the first case set has the same type of complication, so as to obtain a binary classification result of the same type of complication; According to the binary classification results of this type of complication, significance analysis was performed to obtain the sensitive parameters of this type of complication.

15. The postoperative recovery plan generation system according to claim 12, characterized in that: The complication prediction unit predicts the probability of occurrence of each complication through the following process: According to the augmented structured parameters, searching a third preset number of similar cases in the database to form a second case set; For each complication in the augmented structured parameters: Counting whether each similar case in the second case set has the complication to obtain a binary classification result of the complication; According to the binary classification results of the complication, the occurrence probability of the complication is calculated to obtain the prediction result of the complication.

16. The postoperative recovery plan generation system according to claim 15, characterized in that: The plan generation unit generates a postoperative recovery plan through the following process: Performing a confidence analysis on the complication prediction result and the complications of the patient's clinical manifestations to determine whether the complication prediction result is accurate; If yes, the complication with the probability of occurrence ranked in the second preset range is used as the target complication; if no, the complication of the clinical manifestation in the updated structured parameters is used as the target complication; The treatment plan for the target complication is searched in the database according to the target complication to generate a postoperative recovery plan.

17. The postoperative recovery plan generation system according to claim 1, characterized in that: The interactive subsystem is further configured to receive a doctor's confirmation operation or modification operation on the postoperative recovery plan, and send the modified postoperative recovery plan to the analysis subsystem.

18. A method for generating a postoperative recovery plan, characterized in that: include: Obtaining preoperative and intraoperative information of the patient, and integrating the information to obtain the original information of the patient; The raw information is sent to the analysis subsystem so that the analysis subsystem can perform the following operations: converting the received raw information into structured parameters, updating the structured parameters according to the acquired current status information of the patient, and analyzing the updated structured parameters to generate a postoperative recovery plan; receiving a postoperative recovery plan sent by the analysis subsystem; The intraoperative information includes endoscopic image information, surgical process recording information, surgical instrument movement information, and spreadsheet information, wherein the spreadsheet information includes bleeding volume and / or resected tissue quality and / or drainage volume and / or surgical difficulty and / or whether the surgery was completed normally and / or estimated complication risk; The step of converting the received original information into structured parameters includes: obtaining complication information based on the preoperative information and the electronic form information; Acquire, based on the endoscopic image information and the surgical instrument movement information, a first characteristic parameter for characterizing a degree of damage caused to the patient by the surgical instrument; Acquiring a second characteristic parameter for characterizing a sequence of the surgical procedure according to the surgical procedure recording information; and generating structured parameters according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter; The updating of the structured parameters according to the acquired current status information of the patient includes: The complication information of the patient is updated according to the current status information of the patient to obtain updated structured parameters.

19. A method for generating a postoperative recovery plan, characterized in that: include: receiving original information of the patient sent by the interactive subsystem and converting the received original information into structured parameters, wherein the original information includes preoperative information and intraoperative information; updating the structured parameters according to the acquired current status information of the patient; Analyzing the updated structured parameters to generate a postoperative recovery plan and sending the plan to the interactive subsystem; The intraoperative information includes endoscopic image information, surgical process recording information, surgical instrument movement information, and spreadsheet information, wherein the spreadsheet information includes bleeding volume and / or resected tissue quality and / or drainage volume and / or surgical difficulty and / or whether the surgery was completed normally and / or estimated complication risk; The step of converting the received original information into structured parameters includes: obtaining complication information based on the preoperative information and the electronic form information; Acquire, based on the endoscopic image information and the surgical instrument movement information, a first characteristic parameter for characterizing a degree of damage caused to the patient by the surgical instrument; Acquiring a second characteristic parameter for characterizing a sequence of the surgical procedure based on the surgical procedure recording information; and generating structured parameters according to the preoperative information, the electronic spreadsheet information, the complication information, the first characteristic parameter, and the second characteristic parameter; The updating of the structured parameters according to the acquired current status information of the patient includes: The complication information of the patient is updated according to the current status information of the patient to obtain updated structured parameters.

20. A readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed by the processor, the postoperative recovery plan generation method according to claim 18 or 19 is implemented.

Images