A method and system for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage

Abstract

The present invention discloses a method and system for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage, the method comprising: obtaining the current patient's condition information, and determining the key condition characteristics required for the surgery based on the current patient's condition information; based on the key condition characteristics, searching for historical cases of successful surgery that are consistent with the key condition characteristics in the knowledge graph search engine data layer; calculating the similarity between the patient's condition information in the historical cases of successful surgery and the current patient's condition information, and screening out historical cases of successful surgery with a similarity greater than a similarity threshold as reference cases; analyzing the reference cases, determining the key surgical treatment parameters contained in the reference cases, and generating a recommended plan for minimally invasive puncture surgery for cerebral hemorrhage based on simulation of the key surgical treatment parameters. The present invention can generate a recommended surgical plan suitable for the current patient based on the historical cases of successful surgery in the knowledge graph search engine data layer, and assist doctors in making surgical decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of medical intelligent decision-making assistance, and in particular to a method and system for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage. Background Art

[0002] Stroke has become an important cause of death among Chinese residents. Cerebral hemorrhage is the subtype of stroke with the highest mortality and disability rate, which greatly threatens the life and health of the Chinese people. Minimally invasive puncture surgery has the advantages of less trauma, easy operation, and simple equipment. It has become a widely used procedure in the clinical treatment of cerebral hemorrhage. In recent years, neurosurgical robots have begun to enter the clinical minimally invasive puncture surgery of cerebral hemorrhage. They have the advantages of high precision, high reliability, accurate positioning, and fast surgery. They have achieved significant treatment effects and have become an important development direction for minimally invasive surgery of cerebral hemorrhage in the future.

[0003] However, the existing neurosurgery robots have relatively simple functions and are mainly used for intraoperative registration and assisted navigation. Intraoperative hematoma aspiration is still performed manually by doctors, but due to the lack of online sensing and monitoring means for the intracranial environment, hematoma drainage and aspiration are mostly blind. In recent years, some medical device companies have begun to develop cerebral hemorrhage hematoma aspiration equipment that can monitor the intracranial environment during the liquefaction and aspiration process online, improving the doctor's intraoperative perception ability. However, specific surgical decisions rely entirely on the doctor's experience, and hematoma drainage plans are difficult to be precise, individualized, and standardized.

[0004] Knowledge graphs have powerful knowledge representation and storage capabilities. Knowledge graphs based on semantic information have achieved remarkable application results in the field of medical diagnosis and treatment. Therefore, applying knowledge graphs to minimally invasive surgery for cerebral hemorrhage, assisting doctors in making surgical decisions, and achieving precise and individualized aspiration surgery will be an important development direction for improving the technical level of minimally invasive surgery for cerebral hemorrhage in the future. However, the medical data and related surgical knowledge in the knowledge graph system cannot directly guide surgical decisions. How to use the data and knowledge in the knowledge graph system and apply it to decision-making assistance in clinical surgery is still a key technical problem that technicians in this field urgently need to solve. Summary of the invention

[0005] The embodiment of the present invention provides a method and system for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage to solve the above-mentioned technical problems existing in the prior art.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a method for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage is provided.

[0008] In one embodiment, the method for assisting decision making in minimally invasive puncture surgery for cerebral hemorrhage comprises:

[0009] Obtaining current patient condition information, and determining key condition characteristics required for surgery based on the current patient condition information;

[0010] Based on the key disease characteristics, searching for historical successful surgical cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer;

[0011] Calculating the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, selecting the successful surgery history case with a similarity greater than the similarity threshold as a reference case;

[0012] The reference case is analyzed to determine the key surgical treatment parameters contained in the reference case, and a recommended plan for minimally invasive puncture surgery for cerebral hemorrhage is generated based on the simulation of the key surgical treatment parameters.

[0013] In one embodiment, obtaining the current patient's condition information includes: obtaining multimodal condition information data of the current patient, and preprocessing the multimodal condition information data to obtain structured condition information.

[0014] In one embodiment, the multimodal medical information data includes: patient electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, physiological time series data collected by medical monitoring equipment, specific operation process of surgical equipment, time series data of corresponding intracranial environment changes, and video data collected in real time by endoscope.

[0015] In one embodiment, the multimodal medical condition information data is preprocessed to obtain structured medical condition information, including: performing image recognition processing, natural language processing and / or three-dimensional reconstruction processing on the medical condition information data of each modality to extract medical condition characteristic information; performing logical reasoning processing on the medical condition characteristic information according to the logical judgment items of the knowledge graph search engine rule layer to obtain structured medical condition information.

[0016] In one embodiment, the condition characteristic information includes: key condition characteristics required for surgery, discrete quantities of patient status assessment grades, and continuous quantities of various data of the patient's treatment process.

[0017] In one embodiment, the key disease characteristics include lesion location, past medical history, and history of trauma; the discrete quantities include intellectual disability level, smoking level, drinking level, and mental state level before bleeding; the continuous quantities include the time from bleeding to medical treatment, hematoma volume, edema volume, blood pressure data, and intracranial pressure data.

[0018] In one embodiment, the similarity calculation formula includes:

[0019] ;

[0020] in, S is the similarity, C is a constant coefficient, is the number of continuous variables, is the number of discrete variables, and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization.

[0021] In one embodiment, the key surgical treatment parameters include: physiological state condition parameters of the surgical process and surgical operation execution parameters.

[0022] According to a second aspect of an embodiment of the present invention, a decision-making support system for minimally invasive puncture surgery for cerebral hemorrhage is provided.

[0023] In one embodiment, the cerebral hemorrhage minimally invasive puncture surgery decision-making support system includes:

[0024] The condition acquisition and analysis module is used to obtain the current patient condition information and determine the key condition characteristics required for surgery based on the current patient condition information;

[0025] A knowledge graph processing module, used for searching, based on the key disease characteristics, historical successful surgical cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer;

[0026] A similarity processing module is used to calculate the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, screen out successful surgery history cases with a similarity greater than the similarity threshold as reference cases;

[0027] The scheme simulation module is used to analyze the reference case, determine the key surgical treatment parameters contained in the reference case, and generate a recommended scheme for minimally invasive puncture surgery for cerebral hemorrhage based on the simulation of the key surgical treatment parameters.

[0028] In one embodiment, when acquiring the current patient's condition information, the condition acquisition and analysis module acquires multimodal condition information data of the current patient, and preprocesses the multimodal condition information data to obtain structured condition information.

[0029] In one embodiment, the multimodal medical information data includes: patient electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, physiological time series data collected by medical monitoring equipment, specific operation process of surgical equipment, time series data of corresponding intracranial environment changes, and video data collected in real time by endoscope.

[0030] In one embodiment, when the condition acquisition and analysis module pre-processes the multimodal condition information data to obtain structured condition information, it performs image recognition processing, natural language processing and / or three-dimensional reconstruction processing on the condition information data of each modality to extract condition characteristic information; according to the logical judgment items of the knowledge graph search engine rule layer, it performs logical reasoning processing on the condition characteristic information to obtain structured condition information.

[0031] In one embodiment, the condition characteristic information includes: key condition characteristics required for surgery, discrete quantities of patient status assessment grades, and continuous quantities of various data of the patient's treatment process.

[0032] In one embodiment, the key disease characteristics include lesion location, past medical history, and history of trauma; the discrete quantities include intellectual disability level, smoking level, drinking level, and mental state level before bleeding; the continuous quantities include the time from bleeding to medical treatment, hematoma volume, edema volume, blood pressure data, and intracranial pressure data.

[0033] In one embodiment, the similarity calculation formula includes:

[0034] ;

[0035] in, S is the similarity, C is a constant coefficient, is the number of continuous variables, is the number of discrete variables, and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization.

[0036] The standardization process includes: using the historical case database to extract quantitative The corresponding variables in the samples The mean and standard deviation of , the formula is as follows:

[0037] ;

[0038] In the formula, is the variable after standardization. For the variables that need to be processed, is the number of samples, and Respectively Samples and The value of the corresponding variable in each sample.

[0039] In one embodiment, the key surgical treatment parameters include: physiological state condition parameters of the surgical process and surgical operation execution parameters.

[0040] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0041] The present invention can generate surgical recommendation plans suitable for current patients based on historical successful surgical cases in the knowledge graph search engine data layer, assist doctors in making surgical decisions, achieve precise and individualized surgical treatment, and improve the safety and effectiveness of minimally invasive surgery for cerebral hemorrhage.

[0042] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0044] Figure 1 It is a flowchart of a method for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage according to an exemplary embodiment;

[0045] Figure 2 It is a structural block diagram of a decision-making auxiliary system for minimally invasive puncture surgery for cerebral hemorrhage according to an exemplary embodiment;

[0046] Figure 3is a flowchart of assisting decision-making for minimally invasive puncture surgery for perioperative cerebral hemorrhage in actual application according to an exemplary embodiment;

[0047] Figure 4 is a patient analysis flow chart for actual application according to an exemplary embodiment;

[0048] Figure 5 is a surgical decision flow chart for actual application according to an exemplary embodiment;

[0049] Figure 6 It is a knowledge graph ontology knowledge framework data layer in actual application according to an exemplary embodiment;

[0050] Figure 7 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0052] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0053] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0054] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0055] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0056] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0057] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0058] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0059] Figure 1An embodiment of a method for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage according to the present invention is shown.

[0060] In this optional embodiment, the method for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage includes:

[0061] Step S101, obtaining the current patient's condition information, and determining the key condition characteristics required for surgery based on the current patient's condition information;

[0062] Step S103, based on the key disease characteristics, searching for historical successful surgery cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer;

[0063] Step S105, calculating the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, selecting the successful surgery history case with a similarity greater than the similarity threshold as a reference case;

[0064] Step S107, analyzing the reference case, determining the key surgical treatment parameters contained in the reference case, and generating a recommended minimally invasive puncture surgery for cerebral hemorrhage based on the simulation of the key surgical treatment parameters.

[0065] Figure 2 An embodiment of a decision-making auxiliary system for minimally invasive puncture surgery for cerebral hemorrhage of the present invention is shown.

[0066] In this optional embodiment, the cerebral hemorrhage minimally invasive puncture surgery decision-making auxiliary system includes:

[0067] The condition acquisition and analysis module 201 is used to acquire the current patient's condition information and determine the key condition characteristics required for surgery based on the current patient's condition information;

[0068] The knowledge graph processing module 203 is used to search for historical successful surgical cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer based on the key disease characteristics;

[0069] The similarity processing module 205 is used to calculate the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, screen out the successful surgery history cases with a similarity greater than the similarity threshold as reference cases;

[0070] The scheme simulation module 207 is used to analyze the reference case, determine the key surgical treatment parameters contained in the reference case, and generate a recommended minimally invasive puncture surgery scheme for cerebral hemorrhage based on the simulation of the key surgical treatment parameters.

[0071] In the above embodiment, when obtaining the current patient's condition information, multimodal condition information data of the current patient may be obtained, and the multimodal condition information data may be preprocessed to obtain structured condition information.

[0072] The multimodal disease information data includes: patient electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, physiological time series data collected by medical monitoring equipment, specific operation process of surgical equipment, time series data of corresponding intracranial environment changes, and video data collected in real time by endoscopes. When preprocessing the multimodal disease information data to obtain structured disease information, image recognition processing, natural language processing and / or three-dimensional reconstruction processing are performed on the disease information data of each modality to extract disease characteristic information; logical reasoning processing is performed on the disease characteristic information according to the logical judgment items of the knowledge graph search engine rule layer to obtain structured disease information.

[0073] In the above embodiment, the condition characteristic information includes: key condition characteristics required for surgery, discrete quantities of patient status assessment and grading, and continuous quantities of various data of the patient's treatment process. The key condition characteristics include lesion location, past medical history, and history of trauma; the discrete quantities include intellectual disability level, smoking level, drinking level, and mental state level before bleeding; the continuous quantities include the time from bleeding to medical treatment, hematoma volume, edema volume, blood pressure data, and intracranial pressure data.

[0074] In the above embodiment, the calculation formula of similarity includes:

[0075] ;

[0076] in, S is the similarity, C is a constant coefficient, is the number of continuous variables, is the number of discrete variables, and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization.

[0077] In the above embodiment, the key surgical treatment parameters include: physiological state condition parameters of the surgical process and surgical operation execution parameters.

[0078] In order to facilitate understanding of the above technical solutions of the present invention, the above technical solutions of the present invention are described in detail below based on the practical application of minimally invasive puncture surgery for perioperative cerebral hemorrhage.

[0079] Figure 3 The following figure shows the decision-making process of minimally invasive puncture surgery for perioperative cerebral hemorrhage. Figure 3 As shown, surgical decision-making includes patient analysis, similar patient matching, plan recommendation and case storage.

[0080] S1: Patient analysis, receiving multimodal patient information input and forming an accurate and structured description of the condition, mainly including the patient information collection module and the data processing module.

[0081] Specifically, see Figure 4 As shown, the multimodal data may include the patient's electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, as well as physiological time series data collected by medical monitoring equipment during the operation, the specific operation process of the surgical equipment, the time series data of the corresponding intracranial environment changes, and video data collected in real time by the endoscope.

[0082] The information acquisition module structures and pre-processes the data of various modalities and stores them in the file system or object storage service. The data processing module extracts features after performing image recognition, natural language processing, three-dimensional reconstruction and other processing on the data of each modality, and performs logical reasoning on the feature values ​​according to the logical judgment items stored in the knowledge graph rule layer to obtain a concise description of the patient's condition. The description of the patient's condition includes the key disease characteristics needed to determine the surgical plan, the discrete quantities obtained by grading the patient's condition through various practical assessment criteria, and the continuous quantities that record various data information of the patient from the onset of the disease to the end of treatment.

[0083] S2: Similar patient matching: This is to filter out historical cases whose key features are consistent with the current patient from the knowledge graph data layer, and further match historical cases similar to the current patient through similarity calculation. It mainly includes classification screening module and similarity matching module.

[0084] Specifically, see Figure 5 , randomly extract a part of historical cases from the knowledge graph database, estimate the mean and standard deviation of each variable, and then compare the key disease characteristics of each historical case to see if they are consistent with the current patient. If not, stop recommending surgical plans based on similar patients, and recommend surgical plans based on the practical minimally invasive puncture surgery standards for cerebral hemorrhage stored in the knowledge graph rule layer. If they are consistent, calculate the patient similarity.

[0085] If the similarity is higher than the screening threshold, the historical case is added to the candidate surgical plan reference. The candidate surgical plan references are sorted and the various evaluations of the historical case surgery are displayed. The screening threshold can be adjusted by the doctor to screen out an appropriate number of similar historical cases, and the doctor can comprehensively consider the similarity between the historical case and the current patient and the surgical effect of the historical case to select the historical case for reference of the surgical plan recommendation procedure. The evaluation of the surgical effect of the historical case includes the doctor's score of the degree of consistency between the surgical process and the surgical plan, the score of the patient's postoperative recovery, and a text summary of the surgery.

[0086] S3: Scheme recommendation, extracting key parameters from the surgical process of historical cases and generating intraoperative hematoma drainage plans, mainly including parameter extraction module and scheme generation module.

[0087] Specifically, see Figure 5 The surgical process data of historical cases include the patient's physiological state data and the doctor's operation labels at each moment. The parameter extraction module automatically identifies different stages of treatment such as rapid suction and blood pressure reduction, replacement and suction of liquid semi-solid hematoma, shock and crushing of solid hematoma, hemostasis, and re-bleeding treatment from the surgical process data, determines the physiological state condition parameters such as intracranial pressure, body temperature, liquid hematoma volume distribution, solid hematoma volume distribution, etc. of the applicable patients for various surgical operations such as suction, replacement, and injection of liquefied agents, as well as key parameters such as surgical operation execution parameters under different conditions, and integrates them into parameter group P. The scheme generation module, based on the surgical operation judgment method summarized by the hematoma drainage method of minimally invasive puncture surgery for cerebral hemorrhage, uses the key treatment parameter group P of similar cases extracted by the parameter extraction module as the recommended treatment parameter group for this operation, and uses the simulation program of the intracranial hematoma suction environment of minimally invasive surgery for cerebral hemorrhage to simulate the surgical process to generate a set of surgical recommendation schemes suitable for the current patient, describing the recommended operations and the methods and parameters for performing the operations in different stages or under different circumstances of the operation.

[0088] S4: Case storage. After the operation, the case information of the current patient, the operations taken by the doctor during the operation, the patient's physiological condition, and the doctor's score of the operation effect and other multimodal data information are structured and stored in the knowledge graph. This will expand the data layer of the knowledge graph of minimally invasive puncture surgery for perioperative cerebral hemorrhage with more case data, help improve the accuracy and effectiveness of surgical plan recommendations, and have important socioeconomic value. It mainly includes a case annotation module and a knowledge graph construction module.

[0089] Specifically, the case annotation module completes the annotation work of differentiating the intervals of each stage of the surgical process, annotating the doctor's surgical operations and operation parameters at each moment, and annotating the doctor's evaluation of the postoperative surgical effect, so as to improve the accuracy and readability of the surgical data of the case in the knowledge graph data layer. The knowledge graph construction module adds the patient's preoperative and intraoperative information data to the data layer of the knowledge graph. Figure 6 As shown, it specifically includes patient information, personal symptoms, lifestyle habits, past medical history, medical examinations, diagnosed diseases, drug treatment, preoperative planning, intraoperative aspiration, etc.

[0090] After structured preprocessing, multimodal data is stored in the file system or object storage service. Key information such as file name, format, link, creation time, etc. is stored in the node attributes of Neo4j, thereby achieving rapid retrieval of multimodal data.

[0091] Figure 7 An embodiment of a computer device of the present invention is shown. The computer device may be a server, and the computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0092] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0093] In addition, the computer device provided by the present invention includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0094] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0096] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for assisting decision making in minimally invasive puncture surgery for cerebral hemorrhage, characterized in that: include: Obtaining current patient condition information, and determining key condition characteristics required for surgery based on the current patient condition information; Based on the key disease characteristics, searching for historical successful surgical cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer; Calculating the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, selecting the successful surgery history case with a similarity greater than the similarity threshold as a reference case; Analyze the reference case, determine the key surgical treatment parameters contained in the reference case, and generate a recommended minimally invasive puncture surgery for cerebral hemorrhage based on the simulation of the key surgical treatment parameters; The similarity calculation formula includes: ； In the formula, S is the similarity, C is a constant coefficient, is the number of continuous variables, is the number of discrete variables, and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; The standardization process includes: using the historical case database to extract quantitative The corresponding variables in the samples The mean and standard deviation of , the formula is as follows: ； In the formula, is the variable after standardization. For the variables that need to be processed, is the number of samples, and Respectively Samples and The value of the corresponding variable in the samples; Wherein, obtaining the current patient's condition information includes: obtaining the current patient's multimodal condition information data, and preprocessing the multimodal condition information data to obtain structured condition information; the multimodal condition information data includes: patient electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, physiological time series data collected by medical monitoring equipment, specific operation process of surgical equipment, time series data of corresponding intracranial environment changes, and video data collected in real time by endoscope; Among them, preprocessing the multimodal disease information data to obtain structured disease information includes: performing image recognition processing, natural language processing and / or three-dimensional reconstruction processing on the disease information data of each modality to extract disease characteristic information; performing logical reasoning processing on the disease characteristic information according to the logical judgment items of the rule layer of the knowledge graph search engine to obtain structured disease information; The condition characteristic information includes: key condition characteristics required for surgery, discrete quantities of patient condition assessment grades, and continuous quantities of various data during the patient's treatment process; the key condition characteristics include lesion location, past medical history, and history of trauma; the discrete quantities include intellectual disability level, smoking level, drinking level, and mental state level before bleeding; the continuous quantities include the length of time from bleeding to medical treatment, hematoma volume, edema volume, blood pressure data, and intracranial pressure data.

2. The method for assisting decision-making in minimally invasive puncture surgery for cerebral hemorrhage according to claim 1, characterized in that: The key surgical treatment parameters include: physiological state condition parameters of the surgical process and surgical operation execution parameters.

3. A decision-making support system for minimally invasive puncture surgery for cerebral hemorrhage, characterized in that: include: The condition acquisition and analysis module is used to obtain the current patient condition information and determine the key condition characteristics required for surgery based on the current patient condition information; A knowledge graph processing module, used for searching, based on the key disease characteristics, historical successful surgical cases consistent with the key disease characteristics in a pre-configured knowledge graph search engine data layer; A similarity processing module is used to calculate the similarity between the patient condition information in the successful surgery history case and the current patient condition information, and based on a predetermined similarity threshold, screen out successful surgery history cases with a similarity greater than the similarity threshold as reference cases; A scheme simulation module is used to analyze the reference case, determine the key surgical treatment parameters contained in the reference case, and generate a recommended minimally invasive puncture surgery scheme for cerebral hemorrhage based on the simulation of the key surgical treatment parameters; The similarity calculation formula includes: ； In the formula, S is the similarity, C is a constant coefficient, is the number of continuous variables, is the number of discrete variables, and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; and They are the current patient and the successful surgery history case data. The values ​​of the variables after standardization; The standardization process includes: using the historical case database to extract quantitative The corresponding variables in the samples The mean and standard deviation of , the formula is as follows: ； In the formula, is the variable after standardization. For the variables that need to be processed, is the number of samples, and Respectively Samples and The value of the corresponding variable in the samples; Wherein, when acquiring the current patient's condition information, the condition acquisition and analysis module acquires the current patient's multimodal condition information data, and pre-processes the multimodal condition information data to obtain structured condition information; the multimodal condition information data includes: patient electronic medical record text data, imaging examination image data, doctor-patient consultation audio data, physiological time series data collected by medical monitoring equipment, specific operation process of surgical equipment, time series data of corresponding intracranial environment changes, and video data collected in real time by endoscope; Among them, when the condition acquisition and analysis module pre-processes the multimodal condition information data to obtain structured condition information, it performs image recognition processing, natural language processing and / or three-dimensional reconstruction processing on the condition information data of each modality to extract condition characteristic information; according to the logical judgment items of the knowledge graph search engine rule layer, it performs logical reasoning processing on the condition characteristic information to obtain structured condition information; The condition characteristic information includes: key condition characteristics required for surgery, discrete quantities of patient condition assessment grades, and continuous quantities of various data during the patient's treatment process; the key condition characteristics include lesion location, past medical history, and history of trauma; the discrete quantities include intellectual disability level, smoking level, drinking level, and mental state level before bleeding; the continuous quantities include the length of time from bleeding to medical treatment, hematoma volume, edema volume, blood pressure data, and intracranial pressure data.

4. The cerebral hemorrhage minimally invasive puncture surgery decision-making support system according to claim 3 is characterized in that: The key surgical treatment parameters include: physiological state condition parameters of the surgical process and surgical operation execution parameters.

Images