Artificial intelligence-based prediction system for postoperative rehabilitation effect of thoracic surgery

Abstract

The present invention discloses a postoperative rehabilitation effect prediction system for thoracic surgery based on artificial intelligence, including a thoracic surgery data acquisition module, an intraoperative data transmission module, an operation result pre-classification module, a postoperative complication pre-module, a postoperative rehabilitation effect prediction module for thoracic surgery, and a rehabilitation report generation module. The present invention belongs to the field of rehabilitation prediction technology, and specifically is a postoperative rehabilitation effect prediction system for thoracic surgery based on artificial intelligence. This scheme establishes an intraoperative data transmission connection, calculates the energy consumption during the intraoperative data transmission process using distance energy consumption and cluster operation energy consumption, and realizes comprehensive grasp and management of the intraoperative data transmission energy consumption; uses calculation support, combined with confidence and lift value screening to find out the correlation between surgical operation details and postoperative complications; uses calculation of overall measurement scores, collects thoracic surgery rehabilitation feature data, identifies feature importance, and makes a trend chart predicting model performance by changing the rehabilitation effect over time.

Description

Technical Field

[0001] The present invention belongs to the technical field of rehabilitation prediction, and in particular is a system for predicting the postoperative rehabilitation effect of thoracic surgery based on artificial intelligence. Background Art

[0002] The postoperative rehabilitation effect prediction system for thoracic surgery is a system that uses advanced data analysis technology and machine learning technology to accurately predict the patient's postoperative rehabilitation status by integrating the patient's preoperative physiological indicators, medical history and surgery-related information. It aims to better guide the patient's postoperative care and rehabilitation process, improve the rehabilitation effect and the patient's quality of life, and promptly discover possible risks and problems so as to take effective intervention measures. However, the existing postoperative rehabilitation effect prediction system for thoracic surgery has a large amount of surgical data that needs to be smoothly transmitted to the hospital data center for remote consultation, resulting in excessive data transmission energy consumption and difficulty in accurately managing data transmission energy consumption; there are technical problems that a variety of complications may occur after thoracic surgery, and inadequate prediction will delay the timing of complication treatment, causing patients to experience secondary pain and increase the difficulty of subsequent treatment; there are technical problems that the thoracic rehabilitation effect is complex, and it is difficult for medical staff to obtain the patient's postoperative rehabilitation effect in time, resulting in the patient's postoperative care plan not being able to follow up in time, affecting the patient's rehabilitation process. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system. In view of the technical problem that a large amount of surgical data needs to be smoothly transmitted to the hospital data center for remote consultation, resulting in excessive data transmission energy consumption and difficulty in accurately managing data transmission energy consumption, an intraoperative data transmission connection is established, and the energy consumption during the intraoperative data transmission process is calculated using distance energy consumption and cluster operation energy consumption, so as to achieve comprehensive grasp and management of the intraoperative data transmission energy consumption; in view of the technical problem that various complications may occur after thoracic surgery, and inadequate prediction will delay the timing of complication treatment, causing patients to experience secondary pain and increase the difficulty of subsequent treatment, the support of surgical operation details and the support of postoperative complications caused by surgical operation details are calculated, and the confidence and lift value are combined to find out the correlation between surgical operation details and postoperative complications; in view of the technical problem that the thoracic rehabilitation effect is complicated, it is difficult for medical staff to obtain the patient's postoperative rehabilitation effect in time, resulting in the patient's postoperative nursing plan cannot be followed up in time, affecting the patient's rehabilitation process, the overall measurement score is calculated, the thoracic surgery rehabilitation feature data is collected, the feature importance is identified, and the rehabilitation effect is changed over time into a trend chart to predict the model performance.

[0004] The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system provided by the present invention comprises a thoracic surgery data acquisition module, an intraoperative data transmission module, an operation result pre-classification module, a postoperative complication pre-classification module, a thoracic surgery postoperative rehabilitation effect prediction module and a rehabilitation report generation module;

[0005] The thoracic surgery data collection module is specifically used to collect various information and data related to thoracic surgery;

[0006] The intraoperative data transmission module is specifically used to establish an intraoperative data transmission connection, calculate the energy consumption during the intraoperative data transmission process using the distance energy consumption and the cluster operation energy consumption, and realize the comprehensive grasp and management of the intraoperative data transmission energy consumption;

[0007] The surgical result pre-classification module is specifically used to pre-classify the thoracic surgery results;

[0008] The postoperative complication prediction module specifically calculates the support of the surgical operation details and the support of the surgical operation details leading to postoperative complications, and combines the screening of confidence and lift value to find the correlation between the surgical operation details and postoperative complications;

[0009] The postoperative rehabilitation effect prediction module of thoracic surgery specifically calculates the overall measurement score, collects thoracic surgery rehabilitation feature data, identifies feature importance, and makes a trend chart of the rehabilitation effect over time to predict model performance;

[0010] The rehabilitation report generation module is specifically used to record the patient's rehabilitation progress.

[0011] Further, in the thoracic surgery data collection module, the thoracic surgery data collection module is specifically used to collect various information and data related to thoracic surgery, and the thoracic surgery data includes the patient's basic information, preoperative examination results, surgery details and postoperative recovery status;

[0012] The basic information of the patient includes the patient's age, gender and medical history;

[0013] The preoperative examination results include imaging examinations and blood tests;

[0014] The surgical details include the surgical method, operation time and blood loss;

[0015] The postoperative recovery status includes the occurrence of complications and rehabilitation progress.

[0016] Furthermore, in the intraoperative data transmission module, there are provided a transmission connection establishment unit, a distance energy consumption calculation unit, a total energy consumption unit generated by cluster operation calculation unit and an intraoperative data transmission energy consumption calculation unit, and the intraoperative data transmission module includes the following contents:

[0017] Establish a transmission connection unit to transmit the data generated during the operation to the hospital data center for remote consultation, and establish a reliable communication connection between nodes to ensure smooth data transmission;

[0018] To calculate the distance energy consumption unit, the formula used is as follows:

[0019] ;

[0020] In the formula, represents the distance energy consumption part, d represents the distance between a node and the next hop node, Represents the distance energy consumption coefficient;

[0021] The total energy consumption units generated by cluster operations are calculated using the following formula:

[0022] ;

[0023] In the formula, represents the total energy consumption generated by cluster operations, represents the threshold of data processing capability, represents the energy consumption coefficient of cluster formation;

[0024] The energy consumption unit of data transmission during operation is calculated using the following formula:

[0025] ;

[0026] In the formula, represents the energy consumption of data transmission during thoracic surgery, Indicates the energy consumption of data transmission in the core control part during operation.

[0027] Furthermore, in the surgical outcome pre-classification module, specifically in thoracic surgery, the patients are classified according to the resection of the lesion, the postoperative recovery and the presence or absence of complications;

[0028] The lesion resection includes complete resection, partial resection and no resection;

[0029] The postoperative recovery conditions include good recovery of respiratory function, improvement of respiratory function and deterioration of respiratory function.

[0030] Furthermore, in the postoperative complication prediction module, a support calculation unit, a confidence calculation unit, an improvement value calculation unit and a screening unit are provided. The postoperative complication prediction module includes the following contents:

[0031] The support unit was calculated to predict postoperative complications based on the surgical operation details. The formula used is as follows:

[0032] ;

[0033] ;

[0034] In the formula, X represents the details of the surgical operation, represents the frequency of occurrence of surgical operation details X, N represents the total number of surgical cases, represents the support of surgical operation details in all surgical cases, reflecting the prevalence of surgical operation details. Y represents postoperative complications. represents the frequency of simultaneous occurrence of surgical operation details X and postoperative complication Y, Indicates the support for surgical procedure details leading to postoperative complications;

[0035] The confidence unit is calculated using the following formula:

[0036] ;

[0037] In the formula, It represents the confidence level of postoperative complication Y when surgical operation details X and postoperative complication Y occur at the same time, that is, the ratio of the confidence level of postoperative complication Y caused by the surgical operation details combination to the frequency of occurrence of the surgical operation details combination itself. It indicates the support degree that the simultaneous occurrence of surgical operation details X and postoperative complication Y leads to the occurrence of postoperative complication Y;

[0038] To calculate the promotion value unit, the formula used is as follows:

[0039] ;

[0040] In the formula, The combination of surgical details X and postoperative complication Y leads to the increase in the occurrence of postoperative complication Y, which reflects the strength and importance of the association between this surgical detail and postoperative complication.

[0041] The screening unit checks the confidence and lift value of each surgical operation detail one by one, screens out the associations that meet the threshold requirements, eliminates accidental factors, confirms the reliability of the screening results based on the clinical experience of experts, and formulates preventive measures for the identified associations, including improving surgical operation methods, strengthening preoperative evaluation and preparation, and optimizing postoperative care.

[0042] Furthermore, in the postoperative rehabilitation effect prediction module for thoracic surgery, there are provided an overall measurement score calculation unit, a rehabilitation feature collection unit, a feature importance identification unit and a visualization display unit. The postoperative rehabilitation effect prediction module for thoracic surgery includes the following contents:

[0043] To calculate the overall measurement score unit, the formula used is as follows:

[0044] ;

[0045] In the formula, represents the overall measurement score, N represents the number of surgical samples, Indicates the expected risk of massive intraoperative blood loss. represents the actual probability of massive intraoperative blood loss, i is the index of the surgical sample;

[0046] The rehabilitation feature collection unit collects features such as lung function indicators, body inflammation indicators, and physical recovery progress, and organizes and stores the feature data;

[0047] Identify the feature importance unit and input the collected specific feature value SHAP value to identify the feature importance. The formula used is as follows:

[0048] ;

[0049] In the formula, represents the explanation model, M represents the number of input feature parameters, Represents a constant used for model offset. Represents the SHAP value of each model feature, which is used to quantify the contribution of each input feature to the model prediction result. Represents the value of a specific input feature;

[0050] The visualization unit plots the changes in rehabilitation effects over time as trend graphs, objectively measuring the performance of the prediction model so that decision makers and medical staff can clearly understand and interpret it.

[0051] Furthermore, in the rehabilitation report generation module, the patient's rehabilitation progress is specifically recorded, the patient's recovery process and change trend from postoperative to the current stage are described, the rehabilitation plan is adjusted according to the change trend, and a rehabilitation report is generated.

[0052] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0053] (1) In order to solve the technical problem that a large amount of surgical data needs to be smoothly transmitted to the hospital data center for remote consultation, which results in excessive data transmission energy consumption and makes it difficult to accurately manage data transmission energy consumption, an intraoperative data transmission connection is established, and the energy consumption during intraoperative data transmission is calculated using distance energy consumption and cluster operation energy consumption, so as to achieve comprehensive understanding and management of intraoperative data transmission energy consumption;

[0054] (2) In view of the technical problem that multiple complications may occur after thoracic surgery, and inadequate prediction will delay the treatment of complications, causing patients to experience secondary pain and increasing the difficulty of subsequent treatment, we calculated the support for surgical operation details and the support for surgical operation details leading to postoperative complications, combined with confidence and lift value screening, to find the correlation between surgical operation details and postoperative complications;

[0055] (3) In view of the complex situation of thoracic rehabilitation, it is difficult for medical staff to obtain the postoperative rehabilitation effect of patients in a timely manner, resulting in the failure to follow up the postoperative care plan of patients in a timely manner, which affects the technical problem of patients' rehabilitation process. We calculated the overall measurement score, collected the characteristic data of thoracic surgery rehabilitation, identified the importance of the characteristics, and made a trend chart of the rehabilitation effect over time to predict the performance of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of a system for predicting the postoperative rehabilitation effect of thoracic surgery based on artificial intelligence provided by the present invention;

[0057] Figure 2 It is a schematic diagram of the intraoperative data transmission module;

[0058] Figure 3 Schematic diagram of the postoperative complication prediction module;

[0059] Figure 4 This is a schematic diagram of the module for predicting the postoperative rehabilitation effect of thoracic surgery.

[0060] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0062] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0063] Example 1, see Figure 1 The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system provided by the present invention includes a thoracic surgery data acquisition module, an intraoperative data transmission module, a surgery result pre-classification module, a postoperative complication pre-module, a thoracic surgery postoperative rehabilitation effect prediction module and a rehabilitation report generation module;

[0064] The thoracic surgery data collection module is specifically used to collect various information and data related to thoracic surgery;

[0065] The intraoperative data transmission module is specifically used to establish an intraoperative data transmission connection, calculate the energy consumption during the intraoperative data transmission process using the distance energy consumption and the cluster operation energy consumption, and realize the comprehensive control and management of the intraoperative data transmission energy consumption;

[0066] The surgical result pre-classification module is specifically used to pre-classify the thoracic surgery results;

[0067] The postoperative complication prediction module specifically calculates the support of the surgical operation details and the support of the surgical operation details leading to postoperative complications, and combines the screening of confidence and lift value to find the correlation between the surgical operation details and postoperative complications;

[0068] The postoperative rehabilitation effect prediction module of thoracic surgery specifically calculates the overall measurement score, collects thoracic surgery rehabilitation feature data, identifies feature importance, and makes a trend chart of the rehabilitation effect over time to predict model performance;

[0069] The rehabilitation report generation module is specifically used to record the patient's rehabilitation progress.

[0070] Example 2, see Figure 1 , this embodiment is based on the above embodiment, in the thoracic surgery data acquisition module, the thoracic surgery data acquisition module specifically collects various information and data related to thoracic surgery, and the thoracic surgery data includes the patient's basic information, preoperative examination results, surgery details and postoperative recovery status;

[0071] The basic information of the patient includes the patient's age, gender and medical history;

[0072] The preoperative examination results include imaging examinations and blood tests;

[0073] The surgical details include the surgical method, operation time and blood loss;

[0074] The postoperative recovery status includes the occurrence of complications and rehabilitation progress.

[0075] Example 3, see Figure 1 and Figure 2This embodiment is based on the above embodiment. In the intraoperative data transmission module, there are provided a transmission connection establishment unit, a distance energy consumption calculation unit, a total energy consumption unit generated by cluster operation calculation unit and an intraoperative data transmission energy consumption calculation unit. The intraoperative data transmission module includes the following contents:

[0076] Establish a transmission connection unit to transmit the data generated during the operation to the hospital data center for remote consultation, and establish a reliable communication connection between nodes to ensure smooth data transmission;

[0077] To calculate the distance energy consumption unit, the formula used is as follows:

[0078] ;

[0079] In the formula, represents the distance energy consumption part, d represents the distance between a node and the next hop node, Represents the distance energy consumption coefficient;

[0080] The total energy consumption units generated by cluster operations are calculated using the following formula:

[0081] ;

[0082] In the formula, represents the total energy consumption generated by cluster operations, represents the threshold of data processing capability, represents the energy consumption coefficient of cluster formation;

[0083] The energy consumption unit of data transmission during operation is calculated using the following formula:

[0084] ;

[0085] In the formula, represents the energy consumption of data transmission during thoracic surgery, Indicates the energy consumption of data transmission in the core control part during operation.

[0086] By performing the above operations, an intraoperative data transmission connection is established, and the energy consumption during the intraoperative data transmission process is calculated using the distance energy consumption and cluster operation energy consumption, thereby achieving comprehensive grasp and management of the intraoperative data transmission energy consumption, and solving the technical problem that a large amount of surgical data needs to be smoothly transmitted to the hospital data center for remote consultation, resulting in excessive data transmission energy consumption and difficulty in accurately managing data transmission energy consumption.

[0087] Example 4, see Figure 1 , This embodiment is based on the above embodiment. In the surgical result pre-classification module, specifically in thoracic surgery, the lesion is classified according to the resection condition, postoperative recovery condition and the presence or absence of complications;

[0088] The lesion resection includes complete resection, partial resection and no resection;

[0089] The postoperative recovery conditions include good recovery of respiratory function, improvement of respiratory function and deterioration of respiratory function.

[0090] Example 5, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In the postoperative complication prediction module, a support calculation unit, a confidence calculation unit, an improvement value calculation unit and a screening unit are provided. The postoperative complication prediction module includes the following contents:

[0091] The support unit was calculated to predict postoperative complications based on the surgical operation details. The formula used is as follows:

[0092] ;

[0093] ;

[0094] In the formula, X represents the details of the surgical operation, represents the frequency of occurrence of surgical operation details X, N represents the total number of surgical cases, represents the support of surgical operation details in all surgical cases, reflecting the prevalence of surgical operation details. Y represents postoperative complications. represents the frequency of simultaneous occurrence of surgical operation details X and postoperative complication Y, Indicates the support for surgical procedure details leading to postoperative complications;

[0095] The confidence unit is calculated using the following formula:

[0096] ;

[0097] In the formula, It represents the confidence level of postoperative complication Y when surgical operation details X and postoperative complication Y occur at the same time, that is, the ratio of the confidence level of postoperative complication Y caused by the surgical operation details combination to the frequency of occurrence of the surgical operation details combination itself. It indicates the support degree that the simultaneous occurrence of surgical operation details X and postoperative complication Y leads to the occurrence of postoperative complication Y;

[0098] To calculate the promotion value unit, the formula used is as follows:

[0099] ;

[0100] In the formula, The combination of surgical details X and postoperative complication Y leads to the increase in the occurrence of postoperative complication Y, which reflects the strength and importance of the association between this surgical detail and postoperative complication.

[0101] The screening unit checks the confidence and lift value of each surgical operation detail one by one, screens out the associations that meet the threshold requirements, eliminates accidental factors, confirms the reliability of the screening results based on the clinical experience of experts, and formulates preventive measures for the identified associations, including improving surgical operation methods, strengthening preoperative evaluation and preparation, and optimizing postoperative care.

[0102] By performing the above operations, the support degree of surgical operation details and the support degree of postoperative complications caused by surgical operation details are calculated, and the confidence and lift value are combined to find out the correlation between surgical operation details and postoperative complications. This solves the technical problem that multiple complications may occur after thoracic surgery, and inadequate prediction will delay the treatment of complications, causing patients to experience secondary pain and increasing the difficulty of subsequent treatment.

[0103] Example 6, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In the postoperative rehabilitation effect prediction module for thoracic surgery, there are provided an overall measurement score calculation unit, a rehabilitation feature collection unit, a feature importance identification unit and a visualization display unit. The postoperative rehabilitation effect prediction module for thoracic surgery includes the following contents:

[0104] To calculate the overall measurement score unit, the formula used is as follows:

[0105] ;

[0106] In the formula, represents the overall measurement score, N represents the number of surgical samples, Indicates the expected risk of massive intraoperative blood loss. represents the actual probability of massive intraoperative blood loss, i is the index of the surgical sample;

[0107] The rehabilitation feature collection unit collects features such as lung function indicators, body inflammation indicators, and physical recovery progress, and organizes and stores the feature data;

[0108] Identify the feature importance unit and input the collected specific feature value SHAP value to identify the feature importance. The formula used is as follows:

[0109] ;

[0110] In the formula, represents the explanation model, M represents the number of input feature parameters, Represents a constant used for model offset. Represents the SHAP value of each model feature, which is used to quantify the contribution of each input feature to the model prediction result. Represents the value of a specific input feature;

[0111] The visualization unit plots the changes in rehabilitation effects over time as trend graphs, objectively measuring the performance of the prediction model so that decision makers and medical staff can clearly understand and interpret it.

[0112] By performing the above operations, the overall measurement score is calculated, the characteristic data of thoracic surgery rehabilitation is collected, the importance of the characteristics is identified, and the changes in rehabilitation effect over time are made into a trend chart to predict the performance of the model. This solves the technical problem that the situation of thoracic rehabilitation effect is complicated, and it is difficult for medical staff to obtain the patient's postoperative rehabilitation effect in time, resulting in the patient's postoperative care plan cannot be followed up in time, affecting the patient's rehabilitation process.

[0113] Embodiment 7, see Figure 1 This embodiment is based on the above embodiment. In the rehabilitation report generation module, it specifically records the patient's rehabilitation progress, describes the patient's recovery process and change trend from postoperative to the current stage, adjusts the rehabilitation plan according to the change trend, and generates a rehabilitation report.

[0114] 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 any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0115] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0116] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system, characterized by: The system includes a thoracic surgery data collection module, an intraoperative data transmission module, a surgical result pre-classification module, a postoperative complication pre-classification module, a thoracic surgery postoperative rehabilitation effect prediction module, and a rehabilitation report generation module; The thoracic surgery data collection module is specifically used to collect various information and data related to thoracic surgery; The intraoperative data transmission module is specifically used to establish an intraoperative data transmission connection, calculate the energy consumption during the intraoperative data transmission process using the distance energy consumption and the cluster operation energy consumption, and realize the comprehensive grasp and management of the intraoperative data transmission energy consumption; The surgical result pre-classification module is specifically used to pre-classify the thoracic surgery results; The postoperative complication prediction module specifically calculates the support of the surgical operation details and the support of the surgical operation details leading to postoperative complications, and combines the screening of confidence and lift value to find the correlation between the surgical operation details and postoperative complications; The postoperative rehabilitation effect prediction module of thoracic surgery specifically calculates the overall measurement score, collects thoracic surgery rehabilitation feature data, identifies feature importance, and makes a trend chart of the rehabilitation effect over time to predict model performance; The rehabilitation report generation module is specifically used to record the patient's rehabilitation progress; In the postoperative complication prediction module, there are provided a support calculation unit, a confidence calculation unit, an improvement value calculation unit and a screening unit. The postoperative complication prediction module includes the following contents: The support unit was calculated to predict postoperative complications based on the surgical operation details. The formula used is as follows: ； ； In the formula, X represents the details of the surgical operation, represents the frequency of occurrence of surgical operation details X, N represents the total number of surgical cases, represents the support of surgical operation details in all surgical cases, reflecting the prevalence of surgical operation details. Y represents postoperative complications. represents the frequency of simultaneous occurrence of surgical operation details X and postoperative complication Y, Indicates the support for surgical procedure details leading to postoperative complications; The confidence unit is calculated using the following formula: ； In the formula, It represents the confidence level of postoperative complication Y when surgical operation details X and postoperative complication Y occur at the same time, that is, the ratio of the confidence level of postoperative complication Y caused by the surgical operation details combination to the frequency of occurrence of the surgical operation details combination itself. It indicates the support degree that the simultaneous occurrence of surgical operation details X and postoperative complication Y leads to the occurrence of postoperative complication Y; To calculate the promotion value unit, the formula used is as follows: ； In the formula, It indicates the increase in the occurrence of postoperative complication Y caused by the combination of surgical operation details X and postoperative complication Y, which is used to reflect the strength and importance of the association between surgical operation details and postoperative complications; The screening unit combines the confidence and lift value screening to find out the correlation between surgical operation details and postoperative complications, and prepare countermeasures in advance; In the postoperative rehabilitation effect prediction module for thoracic surgery, there are provided an overall measurement score calculation unit, a rehabilitation feature collection unit, a feature importance identification unit and a visualization display unit. The postoperative rehabilitation effect prediction module for thoracic surgery includes the following contents: To calculate the overall measurement score unit, the formula used is as follows: ； In the formula, represents the overall measurement score, N represents the number of surgical samples, Indicates the expected risk of massive intraoperative blood loss, represents the actual probability of massive intraoperative blood loss, i is the index of the surgical sample; A rehabilitation feature collection unit collects rehabilitation features and organizes and stores feature data; Identify the feature importance unit and input the SHAP value of the specific feature value collected to identify the feature importance. The formula used is as follows: ； In the formula, represents the explanation model, M represents the number of input feature parameters, Represents a constant used for model offset. Represents the SHAP value of each model feature, which is used to quantify the contribution of each input feature to the model prediction result. Represents the value of a specific input feature; The visualization unit creates a trend chart of the rehabilitation effect over time and objectively measures the performance of the prediction model.

2. The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system according to claim 1 is characterized by: In the intraoperative data transmission module, there are provided a transmission connection establishment unit, a distance energy consumption calculation unit, a total energy consumption unit generated by cluster operation calculation unit and an intraoperative data transmission energy consumption calculation unit. The intraoperative data transmission module includes the following contents: Establish a transmission connection unit to transmit the data generated during the operation to the hospital data center for remote consultation, and establish a reliable communication connection between nodes to ensure smooth data transmission; To calculate the distance energy consumption unit, the formula used is as follows: ； In the formula, represents the distance energy consumption part, d represents the distance between a node and the next hop node, represents the distance energy consumption coefficient; The total energy consumption units generated by cluster operations are calculated using the following formula: ； In the formula, represents the total energy consumption generated by cluster operations, Indicates the threshold of data processing capability, represents the energy consumption coefficient of cluster formation; The energy consumption unit of data transmission during operation is calculated using the following formula: ； In the formula, represents the energy consumption of data transmission during thoracic surgery, Indicates the energy consumption of data transmission in the core control part during operation.

3. The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system according to claim 1 is characterized by: In the thoracic surgery data collection module, the thoracic surgery data collection module specifically collects various information and data related to thoracic surgery. The thoracic surgery data includes the patient's basic information, preoperative examination results, surgery details and postoperative recovery status.

4. The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system according to claim 1 is characterized by: In the surgical outcome pre-classification module, specifically in thoracic surgery, classification is performed according to the lesion resection, postoperative recovery, and the presence or absence of complications.

5. The artificial intelligence-based thoracic surgery postoperative rehabilitation effect prediction system according to claim 1 is characterized by: In the rehabilitation report generation module, the patient's rehabilitation progress is recorded, the patient's recovery process and change trends from postoperatively to the current stage are described, the rehabilitation plan is adjusted according to the change trends, and a rehabilitation report is generated.

Images