Perioperative period operation time prediction method, perioperative period operation time prediction model and perioperative period management system

Abstract

The invention provides a perioperative period operation time prediction method, a perioperative period operation time prediction model and a perioperative period management system, and the perioperative period operation time prediction method comprises the following steps: obtaining patient information collected and checked by a nurse, and determining operation starting time; dividing the operation process into a plurality of stages according to the flow; operation names, levels and surgeon information are obtained, and the duration of each stage of the operation is evaluated; the operation time prediction model predicts the duration required by the whole operation process according to the duration of each stage, and pushes the estimated duration or the estimated end time of the operation to the display terminal to realize dynamic information sharing of the operation patient; in the operation process, the operation time prediction model collects information uploaded in each stage in real time, processes the uploaded information and dynamically corrects the operation estimated duration or the operation estimated end time. According to the invention, the accuracy of the operation prediction duration is improved. The invention also provides a model for realizing the prediction method and a perioperative period management system.

Description

Technical Field

[0001] The present invention relates to the technical field of surgery management, and in particular to a perioperative surgery time prediction method, model and perioperative management system. Background Art

[0002] Since 2001, day surgery (DS; ambulatory surgery, AS) has emerged and developed in major hospitals in my country. At present, there are three main management models in my country: centralized, decentralized, and centralized and decentralized. In addition, each hospital has established a corresponding information system for the convenience of management. However, these information systems are independent of each other, and are only for the sake of informatization. There is no connection and integration, and there is no comprehensive management of patient and doctor information, effective estimation of surgery duration and reminder of relevant plans.

[0003] In particular, for perioperative management, after the patient is pushed into the operating room, the internal operations are like a black box, and the patient's family members have no way of knowing what is going on inside. They just wait at the door of the operating room and dare not leave. However, the operation generally takes more than half an hour, or even longer. Therefore, if the duration of the operation can be predicted and the remaining duration of the operation can be obtained in real time through the terminal, it will greatly facilitate the patient's family members and give them more time to arrange related matters.

[0004] In addition, since the duration of an operation cannot be determined, a fixed time is usually estimated. When arranging the operating room, the operating room will be vacant for a certain period of time and cannot be effectively used, resulting in a huge waste of resources. This situation is urgently needed to be improved, especially for hospitals with a large number of operations and a shortage of operating rooms. In recent years, with the development of big data technology and artificial intelligence, especially breakthroughs in the field of machine learning, a new solution has been provided for achieving more accurate prediction of the duration of surgery. Summary of the invention

[0005] In order to solve the problems in the prior art, the present invention provides a perioperative surgery time prediction method, and also provides a perioperative surgery time prediction model and a perioperative management system including the perioperative surgery time prediction model.

[0006] The perioperative surgery time prediction method of the present invention comprises the following steps:

[0007] S1: The nurse collects and verifies the patient information and determines the start time of the operation based on the upload time of the collected patient information;

[0008] S2: The surgical process is divided into several stages according to the process flow, and the time periods include the information verification stage, the surgical preparation stage, the anesthesia stage, the surgical stage and the postoperative stage. The information verification stage is mainly the verification time before entering the operating room, the anesthesia stage is the time period between the anesthesia start verification time and the anesthesia end evaluation time, the surgical stage is the time period between the surgical start verification time and the surgical end evaluation time, and the postoperative stage is the time period between the time after the surgery and the time of leaving the operating room;

[0009] S3: Obtain the name, level and surgeon information of the surgery, and estimate the duration of the surgery according to the name, level and surgeon information;

[0010] S4: The surgery time prediction model predicts the duration of the entire surgery according to the duration of each stage, and pushes the estimated surgery duration or expected end time to the display terminal to achieve dynamic information sharing of surgical patients;

[0011] S5: During the operation, the operation time prediction model collects information uploaded at each stage in real time, processes the uploaded information, and dynamically corrects the estimated operation duration or the estimated end time of the operation.

[0012] Furthermore, before the operation time prediction model predicts the time, a model training step is also included:

[0013] Standardize the processes at each stage of the operation. Medical staff will perform the corresponding processes according to the instruction standards. Then upload the start time of each standardized process to the model. The model will calculate the required duration based on the start time.

[0014] Determine the impact factor of each stage, and determine the weighted value of each impact factor based on the impact factor and the duration of the stage;

[0015] Based on the duration of each training sample in the training set, the weighted values ​​of the influencing factors are continuously modified to obtain the optimal weighted value data set;

[0016] The final prediction model is determined based on the optimal weighted value data set to predict the duration of the next sample.

[0017] Furthermore, after determining the duration of each stage, the transfer time between each stage is evaluated, and then the estimated end time of the operation is predicted based on the duration of each stage and the transfer time.

[0018] Furthermore, in the information verification stage, the influencing factors include: medical staff, patient information, whether the patient's family members are involved, and whether the safety verification is passed. Through the influencing factors, medical staff and patients are profiled and the weighted values ​​of the influencing factors are comprehensively determined.

[0019] Furthermore, the influencing factors of the surgical stage include: surgery name, surgical site, surgeon, patient critical value, and emergency type. The prediction results of the model are dynamically adjusted based on the changes in patient critical values ​​and emergency types uploaded during the surgery.

[0020] The present invention also provides a perioperative surgery time prediction model for realizing the perioperative surgery time prediction method, comprising:

[0021] Surgery start time acquisition unit: used to obtain the patient information collected and checked by the nurse, and determine the surgery start time based on the upload time of the collected patient information;

[0022] Information verification phase duration prediction sub-model, surgery preparation phase duration prediction sub-model, anesthesia phase duration prediction sub-model, surgery phase duration prediction sub-model, postoperative phase prediction sub-model: used to predict the duration of each phase based on the acquired information;

[0023] Surgery duration prediction unit: used to predict the duration of the entire surgery based on the time predicted by each sub-model;

[0024] Dynamic adjustment unit: used to collect information uploaded at each stage in real time, process the uploaded information, and dynamically correct the estimated duration of the surgery or the estimated end time of the surgery;

[0025] Information push unit: used to push the predicted estimated duration of surgery or estimated end time of surgery to the display terminal.

[0026] The present invention also provides a perioperative management system, including a preoperative management module, an intraoperative management module, an operation time prediction model, and a display module, wherein:

[0027] The preoperative management module receives patient information, performs preoperative management on the patient, obtains preoperative parameters, and transmits the patient information to the intraoperative management module when the surgical conditions are met;

[0028] The intraoperative management module is used to obtain various intraoperative parameters, surgical videos and intraoperative emergencies during surgery;

[0029] The operation time prediction model is used to obtain relevant parameters of the preoperative management module and the intraoperative management module, and to predict the duration of each stage of the patient who needs surgery, the estimated duration of the surgery or the expected end time based on the perioperative operation time prediction method;

[0030] The display module is used to display the predicted estimated duration of the operation or the estimated end time of the operation to the patient or the sharing platform.

[0031] Furthermore, the perioperative management system also includes a scheduling module: used to automatically schedule according to the working hours of doctors and nurses to obtain the scheduling information of medical staff;

[0032] Operating room scheduling module: used to determine the availability of the operating room based on the surgery duration predicted by the perioperative surgery time prediction method, and then schedule the operating room based on the surgery time of the operating room.

[0033] Furthermore, it also includes a surgery reservation module: after passing the first-level verification, it receives patient information that meets the surgery conditions, and then automatically matches medical staff and operating rooms based on patient information, surgery name, surgery level, medical staff scheduling information, and operating room availability. The patient information, medical staff, operating room and surgery time are then transmitted to the preoperative management module.

[0034] Furthermore, the surgery reservation module further includes a hierarchical management unit for hierarchical management of surgeries according to the name of the surgery and the difficulty of the surgery. The processing method of the hierarchical management unit is:

[0035] Step 1: Obtain the surgical classification authorizations of doctors at all levels;

[0036] Step 2: During the medical staff matching process, the surgeon’s surgical authority and the grade of the surgery to be performed are matched;

[0037] Step 3: Determine whether the surgical authority is less than the surgical grade. If not, match normally. If so, the current doctor's level is not enough and the doctor needs to be rearranged. The surgical participants, operating room and surgical time are re-determined according to the new surgeon's time.

[0038] Compared with the prior art, the beneficial effects of the present invention are: the present invention relies on the perioperative information management system, can collect information uploaded at various stages, can realize pre-operative safety checks, time control during surgery, etc. The present invention processes the uploaded information, and then trains the model based on massive data, and predicts the perioperative surgical time based on the model. Since the data are based on real perioperative data, the prediction accuracy is greatly improved, and the error of the prediction time can be controlled within 30 minutes, which is conducive to improving the utilization rate of the operating room.

[0039] By analyzing the duration and process of each doctor's surgery, we can quantitatively evaluate the surgical level of each doctor, which is conducive to strengthening communication between doctors and promoting the improvement of doctors' surgical quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the present invention or the solutions in the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is a flow chart of the perioperative surgery time prediction method of the present invention;

[0042] Figure 2 This is a structural diagram of the perioperative surgery time prediction model of the present invention;

[0043] Figure 3 The present invention is a flowchart of a processing method for a hierarchical management unit. DETAILED DESCRIPTION

[0044] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present invention or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0045] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it mutually exclusive, independent, or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present invention may be combined with other embodiments.

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0047] like Figure 1 As shown, the perioperative surgery time prediction method of the present invention comprises the following steps:

[0048] S1: The nurse collects and verifies the patient information and determines the start time of the operation based on the upload time of the collected patient information;

[0049] S2: The surgical process is divided into several stages according to the process flow, and the time periods include the information verification stage, the surgical preparation stage, the anesthesia stage, the surgical stage and the postoperative stage. The information verification stage is mainly the verification time before entering the operating room, the anesthesia stage is the time period between the anesthesia start verification time and the anesthesia end evaluation time, the surgical stage is the time period between the surgical start verification time and the surgical end evaluation time, and the postoperative stage is the time period between the time after the surgery and the time of leaving the operating room;

[0050] S3: Obtain the name, level and surgeon information of the surgery, and estimate the duration of the surgery according to the name, level and surgeon information;

[0051] S4: The surgery time prediction model predicts the duration of the entire surgery according to the duration of each stage, and pushes the estimated surgery duration or expected end time to the display terminal to achieve dynamic information sharing of surgical patients;

[0052] S5: During the operation, the operation time prediction model collects information uploaded at each stage in real time, processes the uploaded information, and dynamically corrects the estimated operation duration or the estimated end time of the operation.

[0053] Before predicting the operation time by the operation time prediction model, the present invention further includes a model training step:

[0054] Standardize the processes at each stage of the operation. Medical staff will perform the corresponding processes according to the instruction standards. Then upload the start time of each standardized process to the model. The model will calculate the required duration based on the start time.

[0055] Determine the impact factor of each stage, and determine the weighted value of each impact factor based on the impact factor and the duration of the stage;

[0056] Based on the duration of each training sample in the training set, the weighted values ​​of the influencing factors are continuously modified to obtain the optimal weighted value data set;

[0057] The final prediction model is determined based on the optimal weighted value data set to predict the duration of the next sample.

[0058] Since the applicant performs tens of thousands of surgeries every month, the patient information, surgery name and level have been determined during the outpatient diagnosis and treatment process. Therefore, this information can be used in subsequent laboratory appointments and surgical experiments to standardize each stage and process, so that the time of each stage can be controlled. The present invention relies on the perioperative information management system, which can collect information uploaded at each stage and realize the sharing and circulation of various information. Therefore, the present invention can effectively connect and integrate various information to realize safety verification before surgery, time control during surgery, etc.

[0059] During the model training process, the number and quality of samples determine the accuracy of the prediction, which is also the difficulty in realizing prediction in hospitals. The system of the present invention is based on real perioperative data and can truly reflect the actual working and surgical conditions of doctors and nurses. Therefore, the present invention processes the uploaded information, trains the model based on real and massive data, and predicts the perioperative surgical time based on the model, which greatly improves the prediction accuracy and can accurately control the prediction time within 20 minutes or even 10 minutes, which is conducive to improving the utilization rate of the operating room and improving the satisfaction of patients' families.

[0060] The medical staff in the surgical stage of the present invention include the surgeon, anesthesiologist, operating room nurse, etc. The present invention can achieve standardization of each stage, thereby achieving controllability of each time node. In the information verification stage, since the nurse in the operating room will conduct an assessment of the patient's body, the patient information can be retrieved in real time by scanning the QR code on the patient's wristband. When the model receives the scanned patient information, it takes it as the start time of the operation and starts to predict the duration of the operation.

[0061] When verifying the information, the nurse will check the safety items on the screen one by one. The content of the verification includes the patient's basic information and surgical items. In the information verification stage, the influencing factors include: medical staff, patient information, whether the patient's family members are involved, and whether the safety check is passed. Through the influencing factors, the medical staff and patients are profiled, and the weighted values ​​of the influencing factors are comprehensively determined. Before the operation, the patient's name, surgical level, patient age, and nurse's name have all been determined. According to the machine learning algorithm, a duration that matches the patient and medical staff portrait will be evaluated. During the prediction process, the model retrieves the information uploaded at each stage, and no additional settings are required, so that it can be achieved without increasing the workload of medical staff, which greatly facilitates patients.

[0062] Preferably, in this example, when the nurse checks and ticks the item, the information will be uploaded to the model, and the model will dynamically update the duration based on each node and operation efficiency.

[0063] Before anesthesia, it is necessary to prepare the consumables and anesthetic drugs required for the operation. When the current level information is verified, the system will automatically remind the surgical nurse and anesthesiologist to enter the surgical preparation stage. Only when the previous level verification is passed will the processing of this stage be started. Therefore, after the verification is passed, the model will obtain the pass notification. The remaining time is the overall estimated time for each stage of the surgical preparation stage, anesthesia stage, surgical stage and postoperative stage. This time can be calculated from the nurse swiping the card to enter the operating room. When the consumables are collected, the consumable barcode information will be scanned and associated with the patient. The influencing factors of this stage are: the type and quantity of consumables. The time for this part is relatively controllable, and a relatively standard time can be predicted through machine learning.

[0064] At this stage, the second processing submodule of the system is used to construct and display the surgery information list, wherein the surgery information list includes information such as the surgeon, surgery time, the patient's ward, the patient's bed number, the patient's hospitalization number, the surgery name + level, the patient's preoperative diagnosis, anesthesia method, notes, isolation status, etc.

[0065] After the operation is ready, the system enters the preoperative anesthesia stage. Based on the anesthesia method, the system determines the start time of the operation. The influencing factors of this part are the name, level and anesthesia method of the operation.

[0066] Preferably, thanks to the development of AI large models and full video coverage of operating rooms, this example can also use AI image recognition. In the early stage, by dividing this stage into multiple nodes, and then using training samples for training, the training samples include anesthesia pictures, anesthesia matters verification pictures, and each sub-model of the training model. When the corresponding sub-model receives relevant picture information, it can determine which node to enter in this stage, and then evaluate the remaining time. In this example, CNN recognition network, Google's NasNet, YOLOv7 and other models can be used for model training and recognition.

[0067] Similarly, the surgical stage in this case is also predicted using machine learning + image recognition correction. The influencing factors of the surgical stage include: surgery name, surgical site, surgeon, patient critical value, and emergency type. The prediction results of the model are dynamically adjusted based on the changes in patient critical values ​​and emergency types uploaded during the surgery. The machine model continuously learns and collects the time doctors spend on this type of surgery to determine the weighted values ​​of each influencing factor, and predicts the duration of the surgical stage at the beginning of the surgery.

[0068] During the operation, the model collects images uploaded by the camera, identifies the stage, and dynamically corrects the predicted time.

[0069] The invention can accurately predict the duration of the entire operation within 10-20 minutes through machine learning. By automatically recognizing images during the operation, the time can be continuously corrected, further improving the accuracy of the predicted time, so that it can be within 10 minutes, thereby gaining more time to arrange the next operation. This greatly improves the utilization efficiency of the operating room and helps solve the problem of tight daytime operating rooms.

[0070] In addition, by pushing the predicted time to the patient's family through WeChat, platforms, various terminals, etc., the patient's family can understand the progress of the operation in a timely manner and can arrange their time more calmly without having to wait at the door of the operating room, thereby improving patient satisfaction.

[0071] like Figure 2As shown, the present invention also provides a perioperative surgery time prediction model for implementing the perioperative surgery time prediction method, comprising:

[0072] Surgery start time acquisition unit: used to obtain the patient information collected and checked by the nurse, and determine the surgery start time based on the upload time of the collected patient information;

[0073] Information verification phase duration prediction sub-model, surgery preparation phase duration prediction sub-model, anesthesia phase duration prediction sub-model, surgery phase duration prediction sub-model, postoperative phase prediction sub-model: used to predict the duration of each phase based on the acquired information;

[0074] Surgery duration prediction unit: used to predict the duration of the entire surgery based on the time predicted by each sub-model;

[0075] Dynamic adjustment unit: used to collect information uploaded at each stage in real time, process the uploaded information, and dynamically correct the estimated duration of the surgery or the estimated end time of the surgery;

[0076] Information push unit: used to push the predicted estimated duration of surgery or estimated end time of surgery to the display terminal.

[0077] On the basis of the above prediction methods and models, the present invention explores a relatively scientific and reasonable operating room daytime perioperative management system to adapt to the large-scale development of daytime surgery in ophthalmic specialty hospitals and realize medical quality and safety management.

[0078] The perioperative management system of the present invention includes a preoperative management module, an intraoperative management module, an operation time prediction model, and a display module, wherein:

[0079] The preoperative management module receives patient information, performs preoperative management on the patient, obtains preoperative parameters, and transmits the patient information to the intraoperative management module when the surgical conditions are met;

[0080] The intraoperative management module is used to obtain various intraoperative parameters, surgical videos and intraoperative emergencies during surgery;

[0081] The operation time prediction model is used to obtain relevant parameters of the preoperative management module and the intraoperative management module, and to predict the duration of each stage of the patient who needs surgery, the estimated duration of the surgery or the expected end time based on the perioperative operation time prediction method;

[0082] The display module is used to display the predicted estimated duration of the operation or the estimated end time of the operation to the patient or the sharing platform.

[0083] The perioperative management system also includes a scheduling module: used to automatically schedule shifts according to the working hours of doctors and nurses and obtain scheduling information for medical staff;

[0084] Operating room scheduling module: used to determine the availability of the operating room based on the surgery duration predicted by the perioperative surgery time prediction method, and then schedule the operating room based on the surgery time of the operating room.

[0085] Furthermore, it also includes a surgery reservation module: after passing the first-level verification, it receives patient information that meets the surgery conditions, and then automatically matches medical staff and operating rooms based on patient information, surgery name, surgery level, medical staff scheduling information, and operating room availability. The patient information, medical staff, operating room and surgery time are then transmitted to the preoperative management module.

[0086] The present invention integrates the hospital's information resources and can meet the surgical application needs of ophthalmic surgery to the greatest extent. After completing various preoperative examinations and evaluations, the surgery must implement a 24-hour open application model; through the management platform of the perioperative management system (PIMS) of the present invention, the hierarchical management of the entire perioperative process is realized; a surgery reservation system is established to achieve unified coordination and overall planning of day surgeries throughout the hospital; a correspondence between surgical applications and surgical patient wristbands is established to ensure full coverage of surgical applications for surgical patients. The closed-loop process management model of the present invention records and supervises the people, places, times and events related to the quality control of each link in the surgical process, which can not only improve the efficiency and accuracy of verification and surgery, but also trace the problems that arise in the process, find the root causes of the problems in a timely manner, and implement responsibilities to people, which is conducive to adapting well to the management pressure brought to the operating room by day surgery due to the short operation time and large number of operations in a relatively short period of time.

[0087] Preferably, the surgery reservation module in this example also includes a classification management unit, which is used to classify and manage surgeries according to the name of the surgery and the difficulty of the surgery, so that the surgery reservation process can be more reasonable.

[0088] like Figure 3 As shown, the processing method of the hierarchical management unit is:

[0089] Step 1: Obtain the surgical classification authorizations of doctors at all levels;

[0090] Step 2: During the medical staff matching process, the surgeon’s surgical authority and the grade of the surgery to be performed are matched;

[0091] Step 3: Determine whether the surgical authority is less than the surgical grade. If not, match normally. If so, the current doctor's level is not enough and the doctor needs to be rearranged. The surgical participants, operating room and surgical time are re-determined according to the new surgeon's time.

[0092] By grading the names of surgeries in the front-end clinic, it is possible to better arrange for appropriate doctors to perform surgeries and avoid medical accidents caused by insufficient doctor capabilities. In addition, by analyzing the duration and process of each doctor's surgery, it is possible to quantitatively evaluate the surgical level of each doctor, which is conducive to strengthening communication between doctors and promoting the improvement of doctors' surgical quality.

[0093] The specific implementation modes described above are preferred implementation modes of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the specific implementation modes, and all equivalent changes made according to the present invention are within the protection scope of the present invention.

Claims

1. A perioperative surgery time prediction method, characterized in that: The steps include: S1: The nurse collects and verifies the patient information and determines the start time of the operation based on the upload time of the collected patient information; S2: The surgical process is divided into several stages according to the process, and the time periods include information verification stage, surgical preparation stage, anesthesia stage, surgical stage and postoperative stage; S3: Obtain the name, level and surgeon information of the surgery, and estimate the duration of the surgery according to the name, level and surgeon information; S4: The surgery time prediction model predicts the duration of the entire surgery according to the duration of each stage, and pushes the estimated surgery duration or expected end time to the display terminal to achieve dynamic information sharing of surgical patients; S5: During the operation, the operation time prediction model collects information uploaded at each stage in real time, processes the uploaded information, and dynamically corrects the estimated operation duration or the estimated end time of the operation.

2. The perioperative surgery time prediction method according to claim 1, characterized in that: Before the operation time prediction model predicts the time, it also includes a model training step: Standardize the processes at each stage of the operation. Medical staff will perform the corresponding processes according to the instruction standards. Then upload the start time of each standardized process to the model. The model will calculate the required duration based on the start time. Determine the impact factor of each stage, and determine the weighted value of each impact factor based on the impact factor and the duration of the stage; Based on the duration of each training sample in the training set, the weighted values ​​of the influencing factors are continuously modified to obtain the optimal weighted value data set; The final prediction model is determined based on the optimal weighted value data set to predict the duration of the next sample.

3. The perioperative surgery time prediction method according to claim 2, characterized in that: After determining the duration of each stage, the transfer time between each stage was evaluated, and then the estimated end time of the operation was predicted based on the duration of each stage and the transfer time.

4. The perioperative surgery time prediction method according to claim 2, characterized in that: During the information verification stage, the influencing factors include: medical staff, patient information, whether the patient's family members are involved, and whether the safety verification is passed. Through the influencing factors, medical staff and patients are profiled and the weighted values ​​of the influencing factors are comprehensively determined.

5. The perioperative surgery time prediction method according to claim 2, characterized in that: The influencing factors of the surgical stage include: surgery name, surgical site, surgeon, anesthesia process, patient critical value, and emergency type. The prediction results of the model are dynamically adjusted based on the changes in patient critical values ​​and emergency types uploaded during the surgery.

6. A perioperative surgery time prediction model, characterized by: Used to execute the perioperative surgery time prediction method according to any one of claims 1 to 5, the perioperative surgery time prediction model comprises: Surgery start time acquisition unit: used to obtain the patient information collected and checked by the nurse, and determine the surgery start time based on the upload time of the collected patient information; Information verification phase duration prediction sub-model, surgery preparation phase duration prediction sub-model, anesthesia phase duration prediction sub-model, surgery phase duration prediction sub-model, postoperative phase prediction sub-model: used to predict the duration of each phase based on the acquired information; Surgery duration prediction unit: used to predict the duration of the entire surgery process based on the time predicted by each sub-model; Dynamic adjustment unit: used to collect information uploaded at each stage in real time, process the uploaded information, and dynamically correct the estimated duration of the surgery or the estimated end time of the surgery; Information push unit: used to push the predicted estimated duration of surgery or estimated end time of surgery to the display terminal.

7. A perioperative management system, characterized in that: It includes preoperative management module, intraoperative management module, operation time prediction model and display module, among which: The preoperative management module receives patient information, performs preoperative management on the patient, obtains preoperative parameters, and transmits the patient information to the intraoperative management module when the surgical conditions are met; The intraoperative management module is used to obtain various intraoperative parameters, surgical videos and intraoperative emergencies during surgery; The operation time prediction model is used to obtain relevant parameters of the preoperative management module and the intraoperative management module, and to predict the duration of each stage of the patient who needs surgery, the estimated duration of the surgery or the expected end time based on the perioperative operation time prediction method; The display module is used to display the predicted estimated duration of the operation or the estimated end time of the operation to the patient or the sharing platform.

8. The perioperative management system according to claim 7, characterized in that: The perioperative management system also includes a scheduling module: used to automatically schedule shifts according to the working hours of doctors and nurses and obtain scheduling information for medical staff; Operating room scheduling module: used to determine the availability of the operating room based on the surgery duration predicted by the perioperative surgery time prediction method, and then schedule the operating room based on the surgery time of the operating room.

9. The perioperative management system according to claim 8, characterized in that: It also includes a surgery reservation module: after passing the first-level verification, it receives patient information that meets the surgery conditions, and then automatically matches medical staff and operating rooms based on the patient information, surgery name, surgery level, medical staff scheduling information, and operating room availability. The patient information, medical staff, operating room and surgery time are then transmitted to the preoperative management module.

10. The perioperative management system according to claim 9, characterized in that: The surgery reservation module further includes a hierarchical management unit for hierarchical management of surgeries according to the name of the surgery and the difficulty of the surgery. The processing method of the hierarchical management unit is as follows: Step 1: Obtain the surgical classification authorizations of doctors at all levels; Step 2: During the medical staff matching process, the surgeon’s surgical authority and the grade of the surgery to be performed are matched; Step 3: Determine whether the surgical authority is less than the surgical grade. If not, match normally. If so, the current doctor's level is not enough and the doctor needs to be rearranged. The surgical participants, operating room and surgical time are re-determined according to the new surgeon's time.

Images