Method and system for early warning and evaluating bleeding risk after pancreaticoduodenectomy based on multi-factor analysis

Abstract

The invention relates to a multi-factor analysis-based postoperation bleeding risk early warning and evaluation method and system for pancreaticoduodenectomy, and belongs to the technical field of data analysis. The method comprises the steps of obtaining the age and gender of a patient, presetting an age threshold value, dividing the age according to the age threshold value to obtain age group data, obtaining physiological data, and calculating a pancreatic fistula estimated value through a pancreatic fistula prediction model according to the physiological data and the age group data; obtaining abdominal cavity physiological data, and calculating to obtain an abdominal cavity infection estimated value through the abdominal cavity infection prediction model according to the abdominal cavity physiological data; and obtaining early warning physiological data, and according to the early warning physiological data, the pancreatic fistula estimation value, the abdominal cavity infection estimation value and the gender, performing calculation through the bleeding risk early warning evaluation model to obtain bleeding estimation grade data. The hemorrhage risk early warning evaluation after the pancreaticoduodenectomy based on multi-factor analysis is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular relates to a method and system for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis. Background Art

[0002] Postoperative bleeding after pancreaticoduodenectomy is one of the most common and serious complications of this surgery. It has a high incidence, is difficult to treat, and has a high mortality rate, which seriously affects the surgical efficacy and prognosis of patients. Therefore, early identification and containment of bleeding progression is a difficult issue that pancreatic surgical medical staff are concerned about.

[0003] However, the existing early warning assessment system for post-pancreaticoduodenectomy bleeding risk based on multivariate analysis still has some shortcomings. First, the existing assessment tools often rely on empirical judgment and lack standardized and systematic operating procedures; second, the evaluation indicators for post-operative bleeding, pancreatic fistula and abdominal infection, are both based on whether they occur or not, which lacks predictability; third, all influencing factors are analyzed, the amount of calculation is too large, resulting in complexity of calculation; finally, there is a lack of a unified platform to integrate the tools. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a method and system for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] Obtaining the patient's age and gender, presetting an age threshold, dividing the age according to the age threshold to obtain age group data, obtaining physiological data, and calculating the pancreatic fistula estimation value through a pancreatic fistula prediction model according to the physiological data and the age group data;

[0007] Acquiring abdominal physiological data, and calculating an abdominal infection estimation value through an abdominal infection prediction model according to the abdominal physiological data;

[0008] Early warning physiological data is obtained, and bleeding estimation grade data is calculated through a bleeding risk early warning assessment model according to the early warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

[0009] As a preferred technical solution of the present invention, the specific training steps of the pancreatic fistula prediction model are:

[0010] S201: Obtaining a weight coefficient through multi-factor Logistic regression analysis according to the physiological data and the age group data;

[0011] S202: Integrate the physiological data and the age group data to obtain integrated data, and divide the integrated data into continuous factors and categorical factors according to characteristics of the integrated data;

[0012] S203: Grouping the continuous factors to obtain grouped data, setting the categorical factors as dummy variables, and setting the median values ​​of the grouped data and the dummy variables;

[0013] S204: Determine a basic risk reference value according to the integrated data, and calculate a distance between the basic risk reference value and the integrated data;

[0014] S205: Preset a unit distance, calculate the score of the integrated data according to the unit distance and the distance, and integrate each of the scores to obtain the pancreatic fistula estimation.

[0015] Specifically, the abdominal infection prediction model calculates the abdominal infection estimate value through a prediction calculation formula according to the abdominal physiological data and the risk factor weight value;

[0016] Acquire the infected abdominal physiological data of the patients with abdominal infection, and obtain the risk factor weight value through multivariate logistic regression analysis based on the infected abdominal physiological data.

[0017] Specifically, the blood risk warning assessment model divides the warning physiological data into continuous data and discontinuous data according to the characteristics of the warning physiological data, binarizes the discontinuous data and the gender to obtain binary data, obtains weight coefficients of the continuous data and the binarized data, calculates a bleeding estimate value according to the weight coefficient, the binarized data, and the continuous data, presets a bleeding threshold, and divides the bleeding estimate value according to the bleeding threshold to obtain the bleeding estimate level data.

[0018] Specifically, the physiological data include: platelet count, pancreatic texture score, pancreatic duct diameter, and intraoperative bleeding volume.

[0019] Specifically, the abdominal physiological data include: albumin, drainage tube placement time, and intraoperative blood loss.

[0020] Specifically, the warning physiological data include drinking history score, previous bleeding history score, blood pressure, diabetes history score, hemoglobin content, and blood sugar.

[0021] A risk early warning assessment system for post-pancreaticoduodenectomy bleeding based on multi-factor analysis, comprising: a pancreatic fistula prediction module, an abdominal infection prediction module, and an early warning module;

[0022] The pancreatic fistula prediction module is used to obtain the patient's age and gender, preset an age threshold, divide the age according to the age threshold to obtain age group data, obtain physiological data, and calculate the pancreatic fistula estimation value through the pancreatic fistula prediction model according to the physiological data and the age group data;

[0023] The abdominal infection prediction module is used to obtain abdominal physiological data, and calculate the abdominal infection estimation value through the abdominal infection prediction model according to the abdominal physiological data;

[0024] The early warning module is used to obtain early warning physiological data, and calculate the bleeding estimation level data through a bleeding risk early warning assessment model according to the early warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

[0025] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for early warning and assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis as described above is implemented.

[0026] A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis when executed by a computer processor.

[0027] The beneficial effects of the present invention are:

[0028] (1) By setting up a pancreatic fistula prediction module and an abdominal infection prediction module, relevant influencing factors are selected as the input of the pancreatic fistula prediction model and the abdominal infection prediction model to predict pancreatic fistula and abdominal infection, thereby realizing the prediction of pancreatic fistula and abdominal infection based on existing physiological indicators, avoiding the need to wait until pancreatic fistula and abdominal infection occur before making a bleeding prediction, which results in a waste of patient rescue time.

[0029] (2) Through multivariate logistic regression analysis, the factors with the greatest influence on the prediction of pancreatic fistula and abdominal infection were obtained, and the factors with the greatest influence were collected and analyzed, avoiding the waste of computing resources caused by collecting too much data for analysis and improving the computing time.

[0030] (3) The bleeding risk warning assessment system after pancreaticoduodenectomy based on multi-factor analysis is used to predict bleeding, providing important diagnostic basis for medical staff and enabling them to evaluate treatment options for patients in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0032] Figure 1The present invention is a flowchart of a method for early warning and evaluating bleeding risk after pancreaticoduodenectomy based on multi-factor analysis. DETAILED DESCRIPTION

[0033] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0034] See also Figure 1 , a method and system for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis

[0035] Obtaining the patient's age and gender, presetting an age threshold, dividing the age according to the age threshold to obtain age group data, obtaining physiological data, and calculating the pancreatic fistula estimation value through a pancreatic fistula prediction model according to the physiological data and the age group data;

[0036] Acquiring abdominal physiological data, and calculating an abdominal infection estimation value through an abdominal infection prediction model according to the abdominal physiological data;

[0037] Acquire warning physiological data, and calculate bleeding estimation grade data through a bleeding risk warning assessment model according to the warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

[0038] In this embodiment, the age threshold is 5, and the age is divided into age groups with 5 years as an age interval.

[0039] As a preferred technical solution of the present invention, the specific training steps of the pancreatic fistula prediction model are:

[0040] S201: Obtaining a weight coefficient through multi-factor Logistic regression analysis according to the physiological data and the age group data;

[0041] S202: Integrate the physiological data and the age group data to obtain integrated data, and divide the integrated data into continuous factors and categorical factors according to characteristics of the integrated data;

[0042] S203: Grouping the continuous factors to obtain grouped data, setting the categorical factors as dummy variables, and setting the median values ​​of the grouped data and the dummy variables;

[0043] S204: Determine a basic risk reference value according to the integrated data, and calculate a distance between the basic risk reference value and the integrated data;

[0044] The distance calculation formula is:

[0045] Dij =b i (W ij -W ir ),

[0046] Among them, D ij is the distance between the i-th factor and the j-th group in the integrated data, b i is the weight coefficient of the i-th factor, W ij is the median of the jth group of the ith factor, W ir is the basic risk reference value of the ith factor.

[0047] S205: Preset a unit distance, calculate the score of the integrated data according to the unit distance and the distance, and integrate each of the scores to obtain the pancreatic fistula estimation.

[0048] In this embodiment, multivariate logistic regression analysis is used to obtain the factors with greater influence on the prediction of pancreatic fistula and abdominal infection, and the factors with greater influence are collected and analyzed, thereby avoiding the waste of computing resources caused by collecting too much data for analysis and improving the computing time.

[0049] Specifically, the abdominal infection prediction model calculates the abdominal infection estimate value through a prediction calculation formula according to the abdominal physiological data and the risk factor weight value;

[0050] Acquire the infected abdominal physiological data of the patients with abdominal infection, and obtain the risk factor weight value through multivariate logistic regression analysis based on the infected abdominal physiological data.

[0051] In this embodiment, a pancreatic fistula prediction module and an abdominal infection prediction module are provided, and relevant influencing factors are selected as inputs of the pancreatic fistula prediction model and the abdominal infection prediction model to perform pancreatic fistula prediction and abdominal infection prediction. This enables the prediction of pancreatic fistula and abdominal infection based on existing physiological indicators, thereby avoiding the need to wait until pancreatic fistula and abdominal infection occur before making a bleeding prediction, which results in a waste of patient rescue time.

[0052] Specifically, the blood risk warning assessment model divides the warning physiological data into continuous data and discontinuous data according to the characteristics of the warning physiological data, binarizes the discontinuous data and the gender to obtain binary data, obtains weight coefficients of the continuous data and the binarized data, calculates a bleeding estimate value according to the weight coefficient, the binarized data, and the continuous data, presets a bleeding threshold, and divides the bleeding estimate value according to the bleeding threshold to obtain the bleeding estimate level data.

[0053] In this embodiment, the estimated bleeding level data is divided into Grade A, Grade B, and Grade C. Grade A is mild bleeding, with bleeding from any drainage tube or intra-abdominal cavity less than 500 ml, no blood transfusion or intervention is required, and the impact on the patient's postoperative recovery is small; Grade B is moderate bleeding, which may require blood transfusion or other surgical treatments, but does not require surgery or re-intervention surgery, which often changes clinical treatment decisions; Grade C is severe bleeding, with a large amount of bleeding, requiring surgery or re-intervention surgery, the situation is urgent, and seriously threatens the patient's life.

[0054] Specifically, the physiological data include: platelet count, pancreatic texture score, pancreatic duct diameter, and intraoperative bleeding volume.

[0055] In this embodiment, when scoring the pancreatic texture, the pancreatic texture is obtained by a medical detection method, and the pancreatic texture score is obtained by evaluating the pancreatic texture. If the pancreatic texture is a hard pancreas, the pancreatic texture score is 0; if the pancreatic texture is a soft pancreas, the pancreatic texture score is 2. The medical detection method includes but is not limited to ultrasound detection, CT scanning, and magnetic resonance imaging.

[0056] Specifically, the abdominal physiological data include: albumin content, drainage tube placement time, and intraoperative blood loss.

[0057] Specifically, the warning physiological data include drinking history score, previous bleeding history score, blood pressure, diabetes history score, hemoglobin content, and blood sugar.

[0058] In this embodiment, the drinking history score is obtained by judging the drinking history, if there is a drinking history, the drinking history score is 1, if there is no drinking history, the drinking history score is 0; the previous bleeding history score is obtained by judging the previous bleeding history, if there is a previous bleeding history, the previous bleeding history score is 1, if there is no previous bleeding history, the previous bleeding history score is 0; the diabetes history score is obtained by judging the diabetes history, if there is a diabetes history, the diabetes history score is 1, if there is no diabetes history, the diabetes history score is 0.

[0059] A risk early warning assessment system for post-pancreaticoduodenectomy bleeding based on multi-factor analysis, comprising: a pancreatic fistula prediction module, an abdominal infection prediction module, and an early warning module;

[0060] The pancreatic fistula prediction module is used to obtain the patient's age and gender, preset an age threshold, divide the age according to the age threshold to obtain age group data, obtain physiological data, and calculate the pancreatic fistula estimation value through the pancreatic fistula prediction model according to the physiological data and the age group data;

[0061] The abdominal infection prediction module is used to obtain abdominal physiological data, and calculate the abdominal infection estimation value through the abdominal infection prediction model according to the abdominal physiological data;

[0062] The early warning module is used to obtain early warning physiological data, and calculate the bleeding estimation level data through a bleeding risk early warning assessment model according to the early warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

[0063] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for early warning and assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis as described above is implemented.

[0064] A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis when executed by a computer processor.

[0065] In this embodiment, bleeding is estimated through a post-pancreaticoduodenectomy bleeding risk warning assessment system based on multi-factor analysis, providing important diagnostic basis for medical staff, so that medical staff can evaluate treatment methods for patients in advance.

[0066] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0067] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0068] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0069] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis, characterized in that: include: Obtaining the patient's age and gender, presetting an age threshold, dividing the age according to the age threshold to obtain age group data, obtaining physiological data, and calculating the pancreatic fistula estimation value through a pancreatic fistula prediction model according to the physiological data and the age group data; Acquiring abdominal physiological data, and calculating an abdominal infection estimation value through an abdominal infection prediction model according to the abdominal physiological data; Acquire warning physiological data, and calculate bleeding estimation grade data through a bleeding risk warning assessment model according to the warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

2. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis according to claim 1, characterized in that: The specific training steps of the pancreatic fistula prediction model are: S201: Obtaining a weight coefficient through multi-factor Logistic regression analysis according to the physiological data and the age group data; S202: Integrate the physiological data and the age group data to obtain integrated data, and divide the integrated data into continuous factors and categorical factors according to characteristics of the integrated data; S203: Grouping the continuous factors to obtain grouped data, setting the categorical factors as dummy variables, and setting the median values ​​of the grouped data and the dummy variables; S204: Determine a basic risk reference value according to the integrated data, and calculate a distance between the basic risk reference value and the integrated data; S205: Preset a unit distance, calculate the score of the integrated data according to the unit distance and the distance, and integrate each of the scores to obtain the pancreatic fistula estimation.

3. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis according to claim 1, characterized in that: The abdominal infection prediction model calculates the abdominal infection estimate value through a prediction calculation formula according to the abdominal physiological data and the risk factor weight value; Acquire the infected abdominal physiological data of the patients with abdominal infection, and obtain the risk factor weight value through multivariate logistic regression analysis based on the infected abdominal physiological data.

4. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis according to claim 1, characterized in that: The blood risk warning assessment model divides the warning physiological data into continuous data and discontinuous data according to the characteristics of the warning physiological data, binarizes the discontinuous data and the gender to obtain binary data, obtains weight coefficients of the continuous data and the binarized data, calculates a bleeding estimate value according to the weight coefficient, the binarized data, and the continuous data, presets a bleeding threshold, and divides the bleeding estimate value according to the bleeding threshold to obtain the bleeding estimate level data.

5. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis according to claim 1, characterized in that: The physiological data include: platelet count, pancreatic texture score, pancreatic duct diameter, and intraoperative blood loss.

6. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactor analysis according to claim 1, characterized in that: The abdominal physiological data include albumin, drainage tube placement time, and intraoperative blood loss.

7. The method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactorial analysis according to claim 1, characterized in that: The early warning physiological data include the drinking history score, previous bleeding history score, blood pressure, diabetes history score, hemoglobin content, and blood sugar.

8. A risk early warning assessment system for post-pancreaticoduodenectomy bleeding based on multi-factor analysis, characterized in that: include: Pancreatic fistula prediction module, abdominal infection prediction module, and early warning module; The pancreatic fistula prediction module is used to obtain the patient's age and gender, preset an age threshold, divide the age according to the age threshold to obtain age group data, obtain physiological data, and calculate the pancreatic fistula estimation value through the pancreatic fistula prediction model according to the physiological data and the age group data; The abdominal infection prediction module is used to obtain abdominal physiological data, and calculate the abdominal infection estimation value through the abdominal infection prediction model according to the abdominal physiological data; The early warning module is used to obtain early warning physiological data, and calculate the bleeding estimation level data through a bleeding risk early warning assessment model according to the early warning physiological data, the pancreatic fistula estimation, the abdominal infection estimation, and the gender.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multifactor analysis as described in any one of claims 1 to 7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the method for early warning assessment of bleeding risk after pancreaticoduodenectomy based on multi-factor analysis as described in any one of claims 1 to 7.

Images