Method and system for predicting postoperative complications of patient with incisional hernia through medical big data

Abstract

The invention provides a method and system for predicting postoperative complications of an incisional hernia patient through medical big data, and relates to the technical field of data analysis and processing. The method comprises the following steps: selecting at least one contact person in an information release area of an information interaction interface of a doctor client to release a medical information acquisition request according to a preset postoperative complication prediction task of an incisional hernia patient; an information receiving area and an information prediction area corresponding to the information issuing area are arranged in the information interaction interface; acquiring medical information of the patient through the information receiving area; and aiming at medical information variables in the medical information of the patient, displaying a risk assessment index value obtained by predicting postoperative complications of the patient with the incisional hernia after single-factor analysis and / or multi-factor analysis operation through the information prediction region. According to the method, information interaction between a doctor user and a contact person can be facilitated, and the medical information of the patient is obtained so as to realize risk prediction of postoperative complications of the incisional hernia patient.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis and processing, and in particular to a method for predicting postoperative complications of incisional hernia patients using medical big data. Background Art

[0002] Incisional hernia is a common complication after abdominal surgery with a high incidence rate. According to current reports on incisional hernia, its overall incidence ranges from 2% to 20%.

[0003] With the widespread popularity of surgical procedures and the aging of the population, the incidence of incisional hernias has been gradually increasing worldwide. This is mainly due to the failure of the fascia and / or muscle layer of the abdominal wall incision from the original surgery to heal completely, resulting in the inability of the abdominal wall tissue to maintain sufficient strength, which in turn causes the hernia to form under the action of intra-abdominal pressure. If treatment is not timely, pain and discomfort may occur, affecting the quality of life, and intestinal contents may become entrapped or strangulated, leading to intestinal obstruction, and in severe cases, even threatening the patient's life. With the rapid development of current minimally invasive surgical techniques and rapid recovery surgery, open or laparoscopic repair relying on hernia mesh has become the preferred treatment for abdominal wall incisional hernias.

[0004] Despite continuous improvements in incisional hernia repair techniques, surveys show that the complication rate of laparoscopic incisional hernia repair remains as high as 5% to 30%. These complications primarily include intestinal injury and fistula, bleeding, intra-abdominal hypertension, intestinal obstruction, incision-related complications (including incisional fat liquefaction, hematoma, seroma, surgical site infection, and dehiscence), recurrence, chronic pain, gastrointestinal dysfunction, patch infection, and patch rejection. The occurrence of surgical complications after abdominal wall incisional hernia surgery and the resulting decline in postoperative quality of life place a heavy emotional and financial burden on patients' families and the healthcare system.

[0005] Therefore, early prediction and detection, allowing for early intervention, can effectively improve patients' clinical prognosis and reduce unnecessary medical disputes and conflicts. However, in the process of early prediction, how to facilitate physicians to assess perioperative risk factors for complications after abdominal wall incisional hernia surgery (such as high subcutaneous fat, visceral obesity, high BMI, use of immunosuppressants, and a history of postoperative wound infection or incisional dehiscence) has become a technical challenge that needs to be addressed.

[0006] Based on this, the present invention provides a method and system for predicting postoperative complications of incisional hernia patients using medical big data, so that doctor users can evaluate the perioperative risk factors that cause postoperative complications of abdominal wall incisional hernia, and then provide an analytical basis for providing prevention plans, which has become a technical problem that needs to be solved urgently. Summary of the Invention

[0007] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a method and system for predicting postoperative complications of incisional hernia patients using medical big data. The present invention can facilitate information exchange between doctor users and contacts, and obtain patient medical information to achieve risk prediction of postoperative complications of incisional hernia patients.

[0008] In order to solve the existing technical problems, the present invention provides the following technical solutions: A method for predicting postoperative complications of incisional hernia patients using medical big data, comprising: According to a preset task of predicting postoperative complications of incisional hernia patients, at least one contact is selected in the information release area of the doctor client information interaction interface to issue a medical information acquisition request; the information interaction interface is provided with an information receiving area and an information prediction area corresponding to the aforementioned information release area; wherein the identities of the contacts include the patient himself, the patient's emergency contact, and the medical data administrator; The information receiving area is capable of collecting patient medical information sent by at least one contact; The information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model; Obtain patient medical information through the information receiving area; For the medical information variables in the patient's medical information, the risk assessment index values of postoperative complications of incisional hernia patients obtained after univariate analysis and / or multivariate analysis are displayed through the aforementioned information prediction area.

[0009] Furthermore, the patient medical information can exist in at least one form of text, voice, picture, video and link; The medical information variable is at least one of demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information.

[0010] Furthermore, in the doctor client, the information release area is provided with a plurality of information acquisition request items; the information acquisition request items are provided with information acquisition request templates corresponding to the acquisition requirements of demographic information, past medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information; the information acquisition request templates can be displayed in at least one form of text, table, document, picture, video, audio, and link; When the doctor user inputs information in the aforementioned information release area, he can fill in the medical information acquisition request to be sent to the aforementioned contact according to the selected information acquisition request item, and send it to the designated contact.

[0011] Furthermore, the contact person can use the contact client and fill in the patient's medical information in the information release area of the contact client information interaction interface according to the received medical information acquisition request; Among them, when filling in the patient's medical information, you can select the preset information provision items in the corresponding information release area to fill in the patient's medical information; the information provision items correspond to demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information and incisional hernia postoperative record information.

[0012] Furthermore, after obtaining the patient's medical information through the information receiving area, determining whether the patient's medical information is correct includes: Count the number of contacts, contact identities, and patient medical information published by contacts; When the number of contacts is at least one, identifying the patient medical information provided by each contact; judging the correctness of the patient medical information provided by the contact based on the context information of the patient medical information; When the number of contacts is at least 2, the same patient medical information provided by different contacts is compared; when the same patient medical information provided by each contact is consistent, it is determined that the patient medical information provided by each contact is correct; when the same patient medical information provided by each contact is inconsistent, it is determined that there is an error in the patient medical information provided by at least one contact.

[0013] Furthermore, when it is determined that the patient medical information provided by the aforementioned contact person is incorrect, the erroneous patient medical information will be fed back to the corresponding contact person, and then the correct patient medical information will be summarized and output based on the new patient medical information provided by the corresponding contact person or the confirmed correct patient medical information provided by other contacts.

[0014] Furthermore, an information verification area is also provided in the information interaction interface of the doctor client; the information verification area can display feedback information after verification of the acquired patient medical information based on the medical information acquisition request sent by the doctor user; the feedback information can reflect the patient medical information not provided by the aforementioned contact person, and / or the patient medical information that needs to be confirmed by the aforementioned contact person.

[0015] Furthermore, in the aforementioned information prediction area, a single factor analysis option is configured for the single factor analysis operation; the single factor analysis option is independently set corresponding to each medical information variable in the patient's medical information; A multi-factor analysis option is configured for the multi-factor analysis operation; the multi-factor analysis option is set in combination with the medical information variables in the patient's medical information.

[0016] Furthermore, the risk assessment indicators obtained after the aforementioned univariate analysis operation are set corresponding to continuous variables and categorical variables; the continuous variables include at least one of mean, standard deviation, t value and p value, and the categorical variables include at least one of frequency, chi-square value and p value; The risk assessment indicators obtained after the aforementioned multivariate analysis operation include at least one of the following: regression coefficient, standard error, odds ratio, hazard ratio, confidence interval, and p-value; Wherein, after the aforementioned single factor analysis operation and / or multi-factor analysis operation, the obtained risk assessment index values are normalized.

[0017] A system for predicting postoperative complications of incisional hernia patients using medical big data, including: A doctor client is used to display information sent and received by doctor users in the doctor client information interaction interface, wherein the information interaction interface is provided with at least an information publishing area, an information receiving area, and an information prediction area; the information publishing area is used to select at least one contact to issue a medical information acquisition request; the information receiving area can collect patient medical information sent by at least one contact from the contact client; the information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model; Corresponding to the aforementioned doctor client, a contact client for obtaining patient medical information is provided. The contact client corresponds to the information acquisition needs of the doctor user, and at least an information receiving area and an information publishing area are provided in the information interaction interface of the contact client; the information receiving area in the information interaction interface of the contact client is provided correspondingly to the information publishing area in the information interaction interface of the doctor client; and the information publishing area in the information interaction interface of the contact client is provided correspondingly to the information receiving area in the information interaction interface of the doctor client; The system server is used to select at least one contact in the information release area of the doctor client information interaction interface to issue a medical information acquisition request based on a preset postoperative complication prediction task for incisional hernia patients; the identities of the contacts include the patient himself, the patient's emergency contact, and the medical data manager; for the medical information variables in the patient's medical information, the risk assessment index value obtained after univariate analysis and / or multivariate analysis of postoperative complications of incisional hernia patients is displayed in the aforementioned information prediction area.

[0018] Based on the above advantages and positive effects, the advantages of the present invention are: facilitating information interaction between doctor users and contacts, and providing information release areas and information receiving areas on the information interaction interfaces of the doctor client and the contact client to ensure information interaction between doctor users and specific contacts, and provide data support for obtaining patient medical information to achieve risk prediction of postoperative complications in patients with incisional hernia.

[0019] Furthermore, an information prediction area is set on the doctor client information interaction interface to display the risk assessment index values of postoperative complications of incisional hernia patients obtained after univariate analysis and / or multivariate analysis operations. This operation is suitable for guiding clinical work so that doctor users can realize the risk prediction assessment of postoperative complications of incisional hernia patients based on the patient's physical condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a method provided in an embodiment of the present invention.

[0021] Figure 2 A schematic diagram of the functional modules of the doctor client provided in an embodiment of the present invention.

[0022] Figure 3 Another functional module diagram of the doctor client provided in an embodiment of the present invention.

[0023] Figure 4 A schematic diagram of the structure of a system provided in an embodiment of the present invention.

[0024] Description of reference numerals: System 200 , doctor client 201 , contact client 202 , system server 203 . DETAILED DESCRIPTION

[0025] The following is a further detailed description of a method and system for predicting postoperative complications of incisional hernia patients using medical big data disclosed in the present invention in conjunction with the accompanying drawings and specific embodiments. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated, and they can be combined with each other to achieve better technical effects. In the drawings of the following embodiments, the same reference numerals appearing in each drawing represent the same features or components, which can be applied in different embodiments. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0026] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not intended to limit the conditions under which the invention can be implemented. Any structural modification, change in proportional relationship, or adjustment of size should fall within the scope of the technical content disclosed in the invention without affecting the efficacy and purpose of the invention. The scope of the preferred embodiments of the present invention includes alternative implementations, in which the functions can be performed in a non-described or discussed order, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by those skilled in the art of the art to which the embodiments of the present invention belong.

[0027] Technologies, methods, and apparatus known to persons of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the specification. In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values. Example

[0028] See also Figure 1 FIG. 1 is a flow chart of the present invention. The implementation step S100 of the method is as follows: S101, according to a preset task of predicting postoperative complications of incisional hernia patients, select at least one contact in the information release area of the doctor client information interaction interface to publish a medical information acquisition request.

[0029] In this embodiment, the postoperative complication prediction task for incisional hernia patients refers to predicting possible complications that may occur to patients after surgery by analyzing patient medical information (e.g., demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgical plan information, and incisional hernia postoperative record information). The postoperative complication prediction task for incisional hernia patients can help doctors take preventive measures in advance, improve the quality of postoperative recovery of patients, and reduce risks. The postoperative complication prediction task for incisional hernia is preferably set to at least one of: prediction of incisional hernia recurrence, prediction of postoperative incisional infection, prediction of poor postoperative wound healing, prediction of ascites after incisional hernia repair, prediction of postoperative intestinal obstruction, prediction of long-term postoperative pain, and prediction of postoperative thrombosis.

[0030] The above prediction tasks are preferably based on logistic regression models, random forest models, support vector machines (SVMs), neural network models, deep learning models, Bayesian networks, or gradient boosted decision trees (GBDTs). After training using multi-dimensional patient medical information, they are used to provide patients with personalized postoperative complication risk assessment results for incisional hernia patients. This helps doctors develop personalized postoperative management plans for patients, thereby reducing the occurrence of postoperative complications of incisional hernias and improving patients' postoperative recovery outcomes through timely intervention. The logistic regression model, random forest model, support vector machine (SVM), neural network model, deep learning model, Bayesian network, and gradient boosted decision tree (GBDT) involved are all existing technologies in this field and will not be elaborated on here.

[0031] The doctor client is a terminal for doctor users, which is connected to the cloud server via the Internet. The cloud server can also connect to the terminal for contact users, namely the contact client. The cloud server and multiple terminals together form a medical service system.

[0032] The identities of the contacts include the patient himself, the patient's emergency contacts (such as the patient's family members, friends of the patient, contacts of the social organization to which the patient belongs), and medical data administrators (such as administrators of the HIS hospital management information system).

[0033] Preferably, an information receiving area is provided in the information interaction interface corresponding to the aforementioned information release area, and the information receiving area can collect patient medical information sent by at least one contact.

[0034] It is worth noting that the information receiving area in the information interaction interface of the doctor client is set corresponding to the information publishing area in the information interaction interface of the contact client; the information publishing area in the information interaction interface of the doctor client is set corresponding to the information receiving area in the information interaction interface of the contact client.

[0035] Combine Figure 2 As shown, in the doctor client, the doctor user can select a contact in the information publishing area of the information interaction interface to publish a medical information acquisition request, and the corresponding contact can receive the aforementioned medical information acquisition request in the information receiving area of the contact client information interaction interface; and in the contact client, the contact can send the provided patient medical information through the information publishing area in the information interaction interface of the contact client based on the received medical information acquisition request, and enable the aforementioned doctor user to receive the aforementioned patient medical information in the information receiving area of the doctor client information interaction interface.

[0036] The medical information variables in the patient medical information are at least one of demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information.

[0037] Specifically, the medical information variables in the demographic information include but are not limited to at least one of age, gender, height, weight, BMI, recent weight gain or loss, recent changes in food intake, nutritional risk screening (such as NRS2002), ASA grade, and Charlson Comorbidity Index information.

[0038] The medical information variables in the past medical history information include at least one of the following information: smoking history, drinking history, long-term medication history, daily activity level, abdominal surgery history, original tumor site, tumor tissue pathological type, tumor staging (TNM), tumor size, surgical method, anesthesia method, anesthetic drug usage, operation time, specimen retrieval location, gastrointestinal anastomosis method, intraoperative bleeding volume, history of postoperative intestinal obstruction, history of postoperative wound infection or incision dehiscence, history of radiotherapy and chemotherapy, history of immunosuppressant use, etc.

[0039] The medical information variables in the laboratory test results include at least one of perioperative albumin, hemoglobin, white blood cells, lymphocytes, CRP and other indicator information.

[0040] The medical information variables in the imaging examination results include but are not limited to the examination type (for example, X-ray, CT scan, MRI, ultrasound, nuclear medicine scan, etc.), examination site (for example, abdomen), imaging description (for example, mass, nodule, bleeding, fracture, lesion area, pathological change, etc.), image quality (for example, resolution, contrast, artifacts, etc.), nature of the lesion (for example, benign, malignant, whether there is invasion, size, shape, boundary clarity, density of the lesion, etc.), location of the lesion, stage of the disease (for example, TNM stage of cancer), use of contrast agent (for example, CT enhancement or MRI enhancement), examination time, diagnostic conclusion (such as whether abnormality is found, whether further diagnosis or treatment is needed), image sequence, slice thickness, at least one of preoperative images and postoperative images.

[0041] The medical information variables in the incisional hernia surgical plan information include at least one of the surgical method, tissue structure separation (CST) / abdominal wall reconstruction (AWR) / transverse abdominal muscle release (TAR), abdominal wall defect size and classification, hernia sac size, operation time, patch type, patch placement level, intraoperative blood loss and anesthetic drug usage information.

[0042] The medical information variables in the postoperative record information of the incisional hernia include at least one of the following information: postoperative flatulence and defecation time, postoperative meal time, time to get out of bed, time to remove subcutaneous / preperitoneal / peritoneal drainage tubes, postoperative abdominal belt pressure, postoperative analgesia methods and drugs, pain assessment (such as visual analog scale (VAS)) and quality of life assessment (such as QLQ C30 scale).

[0043] As one of the preferred implementations of this embodiment, in order to facilitate doctor users and contacts to fill in information in the information release area. Preferably, in the doctor client, the information release area is provided with several information acquisition request items. The information acquisition request items correspond to the acquisition requirements of demographic information, past medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information and incisional hernia postoperative record information, and are provided with information acquisition request templates; the information acquisition request templates can be displayed in at least one form of text, table, document, picture, video, audio, and link.

[0044] When the doctor user inputs information in the aforementioned information release area, he can fill in the medical information acquisition request to be sent to the aforementioned contact according to the selected information acquisition request item, and send it to the designated contact.

[0045] By way of example and not limitation, Figure 2 As shown, in the information release area of the information interaction interface of the doctor client, information acquisition request items 1, 2, 3, and 4 are preferably provided corresponding to the requested demographic information, medical history information, incisional hernia surgery plan information, and incisional hernia postoperative record information. The doctor user can use this information release area to issue medical information acquisition requests to specific contacts.

[0046] exist Figure 2 In the doctor client, doctor user Zhang San can search for the selected contact Chen through the contact list in the information release area of the corresponding information interaction interface, and issue a medical information acquisition request to Chen.

[0047] In actual operation, in order to facilitate the doctor user to fill in the operation while accurately describing the medical information acquisition request to the contact person, it is preferred to configure an information acquisition request template for the above-mentioned information acquisition request item.

[0048] After the doctor user selects the aforementioned information acquisition request item, the information acquisition request template for the aforementioned information acquisition request item is preferably displayed in the information release area. Doctor user Zhang San can then send the information content corresponding to the aforementioned information acquisition request template to contact Chen. Alternatively, doctor user Zhang San can adjust the information content in the information acquisition request template based on the aforementioned information acquisition request template and then click the "Send" button to send the aforementioned information content to contact Chen.

[0049] After being sent, the medical information acquisition request sent by the doctor user is treated as published information and can be displayed in the aforementioned information release area along with the sending time (eg, 12:05).

[0050] Correspondingly, the contact can use the contact client and fill in the patient's medical information in the information release area of the contact client information interaction interface according to the received medical information acquisition request.

[0051] Among them, when the contact person fills in the patient's medical information, he or she can select the preset information provision items in the corresponding information release area to fill in the patient's medical information; the information provision items correspond to demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information and incisional hernia postoperative record information.

[0052] Combine Figure 2 As shown, the contact Chen can fill in the patient's medical information in the information release area of the contact client information interaction interface. He can select preset information provision items (such as information provision items corresponding to demographic information, past medical history information, incisional hernia surgery plan information and incisional hernia postoperative record information settings) in the information release area of the contact client information interaction interface in response to the received medical information acquisition request to fill in the patient's medical information.

[0053] It's worth noting that, corresponding to the doctor client used by the doctor user, the contact user can use the contact client to send and receive information. The contact client's information interaction interface includes at least an information publishing area and an information receiving area. The information receiving area can receive medical information acquisition requests sent by the doctor user via the information publishing area on the doctor client's information interaction interface. The contact user can then select pre-set information provision items in the information publishing area on the contact client's information interaction interface to enter the patient's medical information.

[0054] In actual operation, the contact person can select preset information provision items to fill in the patient's medical information, wherein the information provision items preferably provide corresponding selection controls based on the aforementioned information acquisition request items. For example, the information acquisition request items are set corresponding to demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information, that is, six information acquisition request item selection controls are set, and the corresponding information provision items correspond to demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information, and six information provision item selection controls are also set.

[0055] Preferably, the patient medical information provided by the contact can be filled in according to the information provided in the information release area. After filling in, the contact Chen can send the patient medical information he filled in to the doctor user Zhang San through the "Send" button.

[0056] S102, obtaining patient medical information through the information receiving area.

[0057] Combine Figure 2 As shown, doctor user Zhang San can receive patient medical information provided by contact Chen through the doctor client he holds. Taking the information receiving area of Zhang San's doctor client information interaction interface as an example, the patient medical information he receives can be listed in the aforementioned information receiving area in the order in which contact Chen selects the information provision items to fill in the patient medical information.

[0058] It is worth noting that when the patient medical information provided by the contact Chen is file data provided in text format, picture format, video format, PDF document format, word document format or Excel spreadsheet format, it can also display the storage path of the aforementioned patient medical information when it is uploaded, and the storage path includes a local storage path and a cloud storage path.

[0059] Since the contact can provide the patient's medical information in at least one of the following forms: text, table, document, picture, video, audio, and link; therefore, when the aforementioned patient's medical information is provided in at least one of the following forms: text, table, document, picture, video, audio, and link, that is, when the contact uploads the patient's medical information in the information publishing area of the contact client information interaction interface, the information receiving area of the doctor user's information interaction interface can respectively display the original patient's medical information uploaded by the contact, and the patient's medical information after data processing (for example, according to the doctor user's viewing habits of information, the text information is processed into a chart, the text in the picture is subjected to OCR recognition, etc.), so that the doctor user can compare and view the original patient's medical information with the data-processed patient's medical information. When viewing, the information receiving area can be enlarged or reduced according to the user's needs.

[0060] As another preferred implementation of this embodiment, after obtaining the patient medical information through the information receiving area, the correctness of the aforementioned patient medical information is judged, including: counting the number of contacts, contact identities and patient medical information released by the contacts.

[0061] When the number of contacts is at least one, the patient medical information provided by each contact is identified; and the correctness of the patient medical information provided by the contact is determined based on contextual information of the patient medical information.

[0062] By way of example and not limitation, a patient's family member, acting as a contact, reports that "the patient recovered quickly after surgery without any complications, his wound healed well, his temperature remained normal, and his appetite was good." While this information may appear positive on the surface, physicians need to verify its accuracy by verifying the details in the context.

[0063] First, the doctor user will check the patient's basic information and postoperative course of disease. Suppose the patient is a 65-year-old male with a high BMI and hypertension before surgery, and a long history of anesthesia and surgical trauma during the operation. The recovery of such a patient may be more complicated than that of a young, healthy patient, so the description of "recovering quickly" requires more verification. Furthermore, the doctor user can check the patient's medical history information to see if there are records showing the healing of the wound, or whether there are relevant monitoring data, such as body temperature, white blood cell count and other indicators. If the patient's body temperature record is slightly elevated, or the white blood cell count is slightly elevated, it is not completely consistent with the patient's family's description of "normal body temperature", which may indicate that the family does not fully understand the patient's true condition or that their description is exaggerated.

[0064] Furthermore, the patient's family member, acting as a contact, mentioned that "the wound is healing well," which requires further physical examination and medical imaging support. The doctor user may compare photos of the patient's wound area taken at different times to see if there are any potential signs of infection, such as local redness, swelling, exudate, or pain. If there are no obvious abnormalities in the patient's wound, it may mean that the patient's family member's description is relatively accurate; but if there is mild redness, swelling, or exudate around the wound, the doctor user needs to further inquire with the patient's family member through the information interaction interface to understand whether the patient has other symptoms such as discomfort, fatigue, etc., which may indicate relevant information about early complications. Through the above analysis, the accuracy of the provided patient medical information can be judged.

[0065] When the number of contacts is at least 2, the same patient medical information provided by different contacts is compared; when the same patient medical information provided by each contact is consistent, it is determined that the patient medical information provided by each contact is correct; when the same patient medical information provided by each contact is inconsistent, it is determined that there is an error in the patient medical information provided by at least one contact.

[0066] Taking into account the subjective cognition of each contact, for non-objective descriptions, such as patient complaints, certain errors are allowed in the information provided by multiple contacts. When the error is greater than the preset error tolerance value, it is determined that the patient medical information provided by the contact is erroneous.

[0067] As another preferred implementation of this embodiment, when it is determined that the patient medical information provided by the aforementioned contact person is erroneous, the erroneous patient medical information is marked (for example, an error display label is set to mark the erroneous patient medical information). The mark can preferably be displayed in the information receiving area, and the erroneous patient medical information is fed back to the corresponding contact person. Thereafter, the correct patient medical information is summarized and output based on the new patient medical information provided by the corresponding contact person or the confirmed correct patient medical information provided by other contacts.

[0068] Preferably, combined Figure 3 As shown, an information verification area is also provided in the information interaction interface of the doctor client; the information verification area can display feedback information after verification of the acquired patient medical information based on the medical information acquisition request sent by the doctor user.

[0069] Combine Figure 3 The display of the information verification area, the feedback information can reflect the patient medical information not provided by the aforementioned contact person, and / or the patient medical information that needs to be confirmed by the aforementioned contact person.

[0070] Taking into account that the purpose of this embodiment is to solve the problem that doctor users obtain patient medical information through the doctor client and to apply it to predict postoperative complications of incisional hernia patients, for this purpose, in the doctor client, an information prediction area is also provided in the information interaction interface corresponding to the aforementioned information release area; the information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model.

[0071] S103, for the medical information variables in the patient's medical information, display the risk assessment index values of postoperative complications of the incisional hernia patient obtained through univariate analysis and / or multivariate analysis operations through the aforementioned information prediction area.

[0072] Specific combination Figure 2 As shown, in the aforementioned information prediction area, a univariate analysis option is configured for the univariate analysis operation; the univariate analysis option is independently set corresponding to each medical information variable in the patient's medical information.

[0073] As an example and not a limitation, take Chen, a patient with incisional hernia, as an example. After undergoing surgery, the doctor user needs to predict the possible postoperative complications of Chen and provide corresponding analysis and treatment plans.

[0074] First, the doctor user obtained Chen's patient medical information, including: Among them, demographic information includes: age: 55 years old, sex: male, weight 95 kg, height 170 cm, body mass index (BMI): 32.8 (overweight); past medical history information includes: smoking history: 20 years, 15 cigarettes per day, chronic disease history: hypertension, diabetes (type 1, controlled); incisional hernia surgical plan information includes: surgical type: open incisional hernia repair (using mesh), preoperative medication: prophylactic antibiotics (starting 24 hours before surgery), postoperative medication: analgesics (NSAIDs), antibiotics (used 48 hours after surgery), postoperative observation: 3 days after surgery; incisional hernia postoperative record information includes: patient-provided symptom information: "On the third day after surgery, the patient felt obvious pain in the wound site, local redness and swelling, slight exudation, and body temperature of 38.2°C. Accompanying symptoms: mild abdominal distension and occasional nausea." The patient's postoperative data include: postoperative blood routine examination: white blood cells: 12.5 x10^9 / L (slightly increased), hemoglobin: 13.2 g / dL (normal), platelets: 250 x 10^9 / L (normal). Postoperative imaging findings were: Wound area: localized edema, mild hematoma, no obvious signs of leakage or infection. - Abdominal ultrasound: no signs of intestinal obstruction, no obvious fluid accumulation.

[0075] Based on this information, a pre-defined medical big data prediction model (such as a logistic regression model, random forest model, support vector machine (SVM), neural network model, deep learning model, Bayesian network, or gradient boosted decision tree (GBDT)) is used to obtain a risk assessment for postoperative complications in patients with incisional hernias and display it in the information prediction area. In a univariate analysis, the risk assessment results include the risk assessment index values and model analysis conclusions obtained from the univariate analysis.

[0076] In the aforementioned information prediction area, a single-factor analysis option is configured for single-factor analysis operations; the single-factor analysis option is independently set for each medical information variable in the patient's medical information; a multi-factor analysis option is configured for multi-factor analysis operations; the multi-factor analysis option is combined and set corresponding to the medical information variables in the patient's medical information.

[0077] Among them, the risk assessment indicators obtained after the aforementioned univariate analysis operation are set corresponding to continuous variables and categorical variables; the continuous variables include at least one of mean, standard deviation, t value and p value, and the categorical variables include at least one of frequency, chi-square value and p value.

[0078] The risk assessment indicators obtained after the aforementioned multivariate analysis operation include at least one of the regression coefficient, standard error, odds ratio, hazard ratio, confidence interval and p value.

[0079] Among them, it is worth mentioning that after the aforementioned univariate analysis operation and / or multivariate analysis operation, before displaying in the information prediction area, it is preferred to normalize the obtained risk assessment index value, and then evaluate the patient's risk level in a certain disease or complication based on the contribution of each risk factor. This helps to quantify these risk factors, so that doctor users can provide patients with personalized treatment plans or management recommendations based on the normalized risk assessment index value.

[0080] In the multi-factor analysis, the risk assessment results include the risk assessment index values and model analysis conclusions obtained after the multi-factor analysis.

[0081] By way of example and not limitation, Figure 2 As shown, using multivariate analysis as an example, a statistical model (such as multiple regression analysis) is preferably used to assess the risk of postoperative complications in patients with incisional hernias. After analyzing the patient's medical information, the regression analysis results for postoperative complications (such as wound infection, incisional hernia recurrence, and thrombosis) are displayed in the information prediction area to help physicians more accurately predict the patient's complication risk. After multiple regression analysis, the following regression analysis results were obtained.

[0082] Among them, the regression analysis results of wound infection are shown in Table 1.

[0083]

[0084] The results of regression analysis on the recurrence of incisional hernia are shown in Table 2.

[0085]

[0086] The results of regression analysis of thrombosis are shown in Table 3.

[0087]

[0088] Based on this, physician users can intuitively see from the aforementioned regression analysis results that multiple factors have a significant impact on the occurrence of postoperative complications. Specifically, age, BMI, smoking, diabetes, postoperative fever, and leukocytosis are important predictors of wound infection; BMI, smoking, postoperative activity restrictions, and mesh use have a significant impact on incisional hernia recurrence; and BMI, smoking, and postoperative activity restrictions are major risk factors for thrombosis.

[0089] Through the above multi-factor analysis, doctor users can more accurately assess patients' postoperative risks and take effective preventive and intervention measures to ensure patients' postoperative recovery.

[0090] For other technical features, please refer to the previous embodiments and will not be repeated here.

[0091] In addition, see Figure 4 As shown, the present invention also provides an embodiment, providing a system 200 for predicting postoperative complications of incisional hernia patients using medical big data, comprising: The doctor client 201 is used to display the information sent and received by the doctor user in the doctor client information interaction interface, and the information interaction interface is provided with at least an information release area, an information receiving area and an information prediction area; the information release area is used to select at least one contact to issue a medical information acquisition request; the information receiving area can collect patient medical information sent by at least one contact from the contact client; the information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model.

[0092] Corresponding to the aforementioned doctor client 201, a contact client 202 for obtaining patient medical information is provided. The contact client 202 corresponds to the information acquisition needs of the doctor user, and at least an information receiving area and an information publishing area are provided in the information interaction interface of the contact client 202; the information receiving area in the information interaction interface of the contact client 202 is provided correspondingly to the information publishing area in the information interaction interface of the doctor client 201; the information publishing area in the information interaction interface of the contact client 202 is provided correspondingly to the information receiving area in the information interaction interface of the doctor client 201.

[0093] The system server 203 is used to select at least one contact person in the information release area of the doctor client information interaction interface to issue a medical information acquisition request based on a preset postoperative complication prediction task for incisional hernia patients; the identities of the contacts include the patient himself, the patient's emergency contact, and the medical data manager; for the medical information variables in the patient's medical information, the risk assessment index value obtained after univariate analysis and / or multivariate analysis of postoperative complications of incisional hernia patients is displayed in the aforementioned information prediction area.

[0094] For other technical features, please refer to the previous embodiments and will not be repeated here.

[0095] It should be noted that those skilled in the art will understand that the "terminal" referred to in the present invention may include: cellular or other communication devices with or without a multi-line display; a personal communication system (PCS) that can combine voice and data processing, fax and / or data communication capabilities; a personal digital assistant (PDA) that may include a radio frequency receiver and a pager, Internet / intranet access, a web browser, a notepad, a calendar and / or a global positioning system (GPS) receiver; and / or a conventional laptop and / or palmtop computer or other device that includes a radio frequency receiver.

[0096] In the above description, although all components of various aspects of the present disclosure can be interpreted as being assembled or being operatively connected as a module, the present disclosure is not intended to limit itself to these aspects. Rather, within the scope of the target protection of the present disclosure, each component can be selectively and operatively merged with any number. Each component in these components itself can also be implemented as hardware, and each component can be partially merged or selectively overall merged and implemented as a computer program with a program module for executing the function of a hardware equivalent. The code or code segment in order to construct such a program can be easily derived by those skilled in the art. Such a computer program can be stored in a computer-readable medium, which can be run to realize various aspects of the present disclosure. The computer-readable medium can include a magnetic recording medium, an optical recording medium, and a carrier medium.

[0097] In addition, terms such as "include," "comprising," and "having" should be interpreted as inclusive or open-ended rather than exclusive or closed-ended by default, unless expressly defined to the contrary. All technical, scientific, or other terms have the meanings understood by those skilled in the art unless expressly defined to the contrary. Common terms found in dictionaries should not be interpreted in an overly idealistic or unrealistic manner in the context of the relevant technical documents, unless expressly defined to that effect by this disclosure.

[0098] Although example aspects of the present disclosure have been described for illustrative purposes, those skilled in the art will appreciate that the foregoing description is merely a description of preferred embodiments of the present invention and does not limit the scope of the present invention in any way. The scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order in which they appear or are discussed. Any changes or modifications made by those skilled in the art based on the foregoing disclosure are intended to fall within the scope of the claims.

Claims

1. A method for predicting postoperative complications of incisional hernia patients using medical big data, characterized in that: include: According to a preset task of predicting postoperative complications of incisional hernia patients, at least one contact is selected in the information release area of the doctor client information interaction interface to issue a medical information acquisition request; the information interaction interface is provided with an information receiving area and an information prediction area corresponding to the aforementioned information release area; wherein the identities of the contacts include the patient himself, the patient's emergency contact, and the medical data administrator; The information receiving area is capable of collecting patient medical information sent by at least one contact; The information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model; Obtain patient medical information through the information receiving area; For the medical information variables in the patient's medical information, the risk assessment index values of postoperative complications of incisional hernia patients predicted after univariate analysis and / or multivariate analysis are displayed through the aforementioned information prediction area.

2. The method according to claim 1, characterized in that The patient medical information can exist in at least one form of text, voice, picture, video and link; The medical information variable is at least one of demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information, and incisional hernia postoperative record information.

3. The method according to claim 2, characterized in that In the doctor client, the information release area is provided with several information acquisition request items; the information acquisition request items correspond to the acquisition requirements of demographic information, past medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information and incisional hernia postoperative record information, and are provided with information acquisition request templates; the information acquisition request templates can be displayed in at least one of the following forms: text, table, document, picture, video, audio, and link; When the doctor user inputs information in the aforementioned information release area, he can fill in the medical information acquisition request to be sent to the aforementioned contact according to the selected information acquisition request item, and send it to the designated contact.

4. The method according to claim 2, characterized in that The contact person can use the contact client and fill in the patient's medical information in the information release area of the contact client information interaction interface according to the received medical information acquisition request; Among them, when filling in the patient's medical information, you can select the preset information provision items in the corresponding information release area to fill in the patient's medical information; the information provision items correspond to demographic information, medical history information, laboratory test results, imaging test results, incisional hernia surgery plan information and incisional hernia postoperative record information.

5. The method according to claim 1, wherein After obtaining the patient's medical information through the information receiving area, determine whether the patient's medical information is correct, including: Count the number of contacts, contact identities, and patient medical information published by contacts; When the number of contacts is at least one, identifying the patient medical information provided by each contact; judging the correctness of the patient medical information provided by the contact based on the contextual information of the patient medical information; When the number of contacts is at least 2, the same patient medical information provided by different contacts is compared; when the same patient medical information provided by each contact is consistent, it is determined that the patient medical information provided by each contact is correct; when the same patient medical information provided by each contact is inconsistent, it is determined that there is an error in the patient medical information provided by at least one contact.

6. The method according to claim 5, characterized in that When it is determined that the patient medical information provided by the aforementioned contact person is incorrect, the erroneous patient medical information will be fed back to the corresponding contact person, and then the correct patient medical information will be summarized and output based on the new patient medical information provided by the corresponding contact person or the confirmed correct patient medical information provided by other contacts.

7. The method according to claim 1, characterized in that An information verification area is also provided in the information interaction interface of the doctor client; the information verification area can display feedback information after verification of the acquired patient medical information based on the medical information acquisition request sent by the doctor user; the feedback information can reflect the patient medical information not provided by the aforementioned contact person, and / or the patient medical information that needs to be confirmed by the aforementioned contact person.

8. The method according to claim 1, characterized in that In the aforementioned information prediction area, a single factor analysis option is configured for single factor analysis operation; the single factor analysis option is independently set corresponding to each medical information variable in the patient's medical information; A multi-factor analysis option is configured for the multi-factor analysis operation; the multi-factor analysis option is set in combination with the medical information variables in the patient's medical information.

9. The method according to claim 1 or 8, characterized in that The risk assessment indicators obtained after the aforementioned univariate analysis operation are set corresponding to continuous variables and categorical variables; the continuous variables include at least one of mean, standard deviation, t value and p value, and the categorical variables include at least one of frequency, chi-square value and p value; The risk assessment indicators obtained after the aforementioned multivariate analysis operation include at least one of the following: regression coefficient, standard error, odds ratio, hazard ratio, confidence interval, and p-value; Wherein, after the aforementioned single factor analysis operation and / or multi-factor analysis operation, the obtained risk assessment index values are normalized.

10. A system for predicting postoperative complications of incisional hernia patients using medical big data according to the method according to any one of claims 1 to 9, characterized in that include: A doctor client is used to display information sent and received by doctor users in the doctor client information interaction interface, wherein the information interaction interface is provided with at least an information publishing area, an information receiving area, and an information prediction area; the information publishing area is used to select at least one contact to issue a medical information acquisition request; the information receiving area can collect patient medical information sent by at least one contact from the contact client; the information prediction area can display the risk assessment results of postoperative complications of incisional hernia patients based on a preset medical big data prediction model; Corresponding to the aforementioned doctor client, a contact client for obtaining patient medical information is provided. The contact client corresponds to the information acquisition needs of the doctor user, and at least an information receiving area and an information publishing area are provided in the information interaction interface of the contact client; the information receiving area in the information interaction interface of the contact client is provided correspondingly to the information publishing area in the information interaction interface of the doctor client; and the information publishing area in the information interaction interface of the contact client is provided correspondingly to the information receiving area in the information interaction interface of the doctor client; The system server is used to select at least one contact in the information release area of the doctor client information interaction interface to issue a medical information acquisition request based on a preset postoperative complication prediction task for incisional hernia patients; the identities of the contacts include the patient himself, the patient's emergency contact, and the medical data manager; for the medical information variables in the patient's medical information, the risk assessment index value obtained after univariate analysis and / or multivariate analysis of postoperative complications of incisional hernia patients is displayed in the aforementioned information prediction area.

Images