A method, device, equipment and product for predicting the prognosis of cerebral hemorrhage in patients

Abstract

The present invention provides a method, device, equipment and product for predicting the prognosis of cerebral hemorrhage in patients, and relates to the medical field. The method comprises: obtaining the corresponding single test results of the patient to be predicted on each independent risk prediction factor; obtaining a comprehensive prediction value based on the determined single impact value of each independent risk prediction factor and the single test result, and generating a prediction result of the patient to be predicted based on the comprehensive prediction value; wherein the prediction result characterizes the risk of hematoma expansion of the patient. The present invention improves the accuracy of the prediction of the prognosis of cerebral hemorrhage, can assist medical staff in formulating treatment plans, and increases the feasibility of clinical implementation.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a method, device, equipment and product for predicting the prognosis of cerebral hemorrhage in patients. Background Art

[0002] Spontaneous cerebral hemorrhage is a cerebrovascular disease with a high morbidity and mortality rate in clinical practice. Many patients with cerebral hemorrhage will experience hematoma expansion in the early stage. Once hematoma expansion occurs, it often indicates a poor prognosis in clinical practice. Therefore, hematoma expansion is one of the risk factors for poor prognosis. If the possibility of rebleeding can be predicted in the early stage of cerebral hemorrhage in patients and timely intervention can be carried out, it will be of great significance to reduce mortality and improve prognosis. It is a technical problem that needs to be solved urgently in the field of cerebral hemorrhage. Summary of the invention

[0003] In view of the problems mentioned in the background technology, the purpose of the present invention is to provide a method, device, equipment and product for predicting the prognosis of cerebral hemorrhage in patients, so as to solve the problems mentioned in the background technology.

[0004] The above technical objectives of the present invention are achieved through the following technical solutions:

[0005] A method for predicting the prognosis of cerebral hemorrhage in a patient comprises the following steps:

[0006] Obtain the corresponding single test results of each independent risk prediction factor for the patient to be predicted;

[0007] Based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value; wherein the prediction result characterizes the risk of hematoma expansion in the patient.

[0008] Preferably, the independent risk prediction factors include diabetes, coagulation function, systolic blood pressure at admission, GCS score and specific signs in CT imaging; wherein, the specific signs include one sign of irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign, and mixed sign, or a combination of multiple signs.

[0009] Preferably, the independent risk prediction factor is determined by the following steps:

[0010] The risk predictors of each sample from the patient where the sample was collected;

[0011] Inputting the sample risk prediction factors into a Logistic regression analysis model to obtain the correlations corresponding to the sample risk prediction factors;

[0012] Determine that the correlation corresponding to the sample risk prediction factor is greater than a preset correlation, and use the sample risk prediction factor as the independent risk prediction factor.

[0013] Preferably, obtaining a comprehensive prediction value based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, and generating a prediction result for the patient based on the comprehensive prediction value specifically comprises the following steps:

[0014] determining the independent risk predictors and the baseline factors among the independent risk predictors;

[0015] Obtaining the influence relationship between each of the independent risk prediction factors and the baseline factors;

[0016] Determine the single impact value corresponding to the baseline factor, and based on the impact relationship, determine the single impact value corresponding to each of the independent risk prediction factors;

[0017] Based on the single impact value and the single test result of each of the independent risk prediction factors, the single prediction value corresponding to each of the independent risk prediction factors is obtained, and all the single prediction values ​​are accumulated to obtain the comprehensive prediction value;

[0018] The prediction result is generated based on the comprehensive prediction value.

[0019] Preferably, generating the prediction result based on the comprehensive prediction value specifically includes:

[0020] Determine the score interval to which the comprehensive prediction value belongs, and generate the prediction result based on the determined score interval; wherein each score interval corresponds to one prediction result, and different score intervals correspond to different prediction results.

[0021] Preferably, the benchmark factor is obtained by odds ratio analysis.

[0022] The present invention also provides a device for predicting the prognosis of cerebral hemorrhage in a patient, comprising:

[0023] An acquisition module is used to obtain the corresponding single test results of each independent risk prediction factor of the patient to be predicted;

[0024] A prediction module is used to obtain a comprehensive prediction value based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, and to generate a prediction result for the patient to be predicted based on the comprehensive prediction value; wherein the prediction result represents the risk of hematoma expansion in the patient.

[0025] The present invention also provides an electronic device, comprising 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 steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as described in any one of the above items are implemented.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as described in any one of the above items are implemented.

[0027] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as described in any one of the above items.

[0028] In summary, the present invention mainly has the following beneficial effects:

[0029] By obtaining the corresponding single test results of each independent risk prediction factor of the patient to be predicted, and then obtaining the comprehensive prediction value of the patient based on the determined single influence values ​​and single test results of each independent risk prediction factor, and generating the prediction result of the patient to be predicted based on the comprehensive prediction value, the prediction result is used to indicate the risk of hematoma expansion of the patient. Therefore, medical staff can formulate corresponding treatment plans according to the prediction results of the patient to be predicted, and intervene in the hematoma expansion of the patient in time. The present invention improves the accuracy of cerebral hemorrhage prognosis prediction, can assist medical staff in formulating treatment plans, and increases the feasibility of clinical implementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a process for predicting the prognosis of cerebral hemorrhage in a patient according to the present invention;

[0031] Figure 2 A schematic diagram of a process for obtaining independent risk prediction factors in the method for predicting the prognosis of cerebral hemorrhage in patients of the present invention;

[0032] Figure 3 The specific flow chart of step S200 in the method for predicting the prognosis of cerebral hemorrhage in patients of the present invention;

[0033] Figure 4 It is a schematic diagram of the structure of the device for predicting the prognosis of cerebral hemorrhage in patients according to the present invention;

[0034] Figure 5 It is a schematic diagram of the specific structure of the prediction module in the device for predicting the prognosis of cerebral hemorrhage in patients of the present invention;

[0035] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 The present invention provides a method for predicting the prognosis of cerebral hemorrhage in a patient, the method comprising the following steps:

[0038] S100, obtaining the corresponding single test results of each independent risk prediction factor for the patient to be predicted.

[0039] S200, based on the determined single impact values ​​and single test results of each independent risk prediction factor, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value. In this method, the prediction result of the patient represents the risk of hematoma expansion of the patient. It is understandable that the higher the risk of hematoma expansion, the greater the probability of postoperative rebleeding of the patient, and the lower the risk of hematoma expansion, the lower the probability of postoperative rebleeding of the patient.

[0040] Disease prognosis refers to the prediction of the future course and outcome of a disease (including recovery, recurrence, deterioration, disability, complications and death, etc.) after the disease occurs. In this method, medical staff can obtain the risk or probability of hematoma expansion of the patient to be predicted based on the prediction results. Based on the probability of hematoma expansion, medical staff can formulate corresponding treatment plans and intervene in the patient's hematoma expansion in a timely manner.

[0041] In this embodiment, the single test result corresponding to each independent risk prediction factor includes a specific value or whether a certain independent risk prediction factor exists.

[0042] In the method for predicting the prognosis of cerebral hemorrhage of a patient provided by the present invention, the single test results corresponding to each independent risk prediction factor of the patient to be predicted are obtained, and then the comprehensive prediction value of the patient is obtained based on the determined single influence values ​​and single test results of each independent risk prediction factor, and the prediction result of the patient to be predicted is generated based on the comprehensive prediction value. The prediction result is used to indicate the risk of hematoma expansion of the patient. Therefore, medical staff can formulate corresponding treatment plans according to the prediction results of the patient to be predicted, and intervene in the hematoma expansion of the patient in time. The present invention improves the accuracy of the prediction of the prognosis of cerebral hemorrhage, can assist medical staff in formulating treatment plans, and increases the feasibility of clinical implementation.

[0043] In this embodiment, the independent risk prediction factors include (whether or not suffering from) diabetes, blood coagulation function, systolic blood pressure at admission, GCS score and specific signs in CT imaging, and the specific signs include irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign, mixed sign, one sign or multiple combined signs. CT imaging examination is one of the most clinically significant examinations for diagnosing cerebral hemorrhage, which can most intuitively reflect the location of cerebral hemorrhage in patients, the morphological characteristics of hematoma, and one sign or multiple combined signs of irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign, mixed sign can be used as an independent risk prediction factor for hematoma expansion.

[0044] For more details, see Figure 2 , independent risk predictors were determined by the following steps:

[0045] A100. Various sample risk prediction factors for patients from whom samples were collected.

[0046] Please refer to Table 1. In this method, the predictive risk factors such as age, initial blood pressure, gender, diabetes, GCS score, initial hematoma volume, specific signs in CT imaging, and blood coagulation function (thromboelastography results) of the sample patients were collected as independent variables.

[0047] coding variable Assignment X1 age 1=(30-45) years old, 2=(46-60) years old, 3=(61-75) years old, 4=(76-90) years old X2 gender 0=female, 1=male X3 Systolic blood pressure on admission 1=[140-180]mmhg, 2=(180-220]mmhg X4 Initial hematoma volume 1 = hematoma volume <10 ml, 2 = 10 ≤ hematoma volume ≤ 20 ml, 3 = hematoma volume > 20 ml X5 GCS score 1=(3-8) points, 2=(9-15) points X6 Blood coagulation function 0=5min≤R≤10min and 54mm≤MA≤72mm, 1=R>10min or MA<54mm X7 Irregular hematoma margin sign 0=no, 1=yes X8 Whirlpool sign 0=no, 1=yes X9 Lobular sign 0=no, 1=yes X10 Black hole sign 0=no, 1=yes X11 Mixed signs 0=no, 1=yes X12 diabetes 0=no, 1=yes Y Hematoma expansion 0=no, 1=yes

[0048] In Table 1, R is the reaction time in the thromboelastogram, and MA is the maximum amplitude value in the thromboelastogram.

[0049] A200. Input the sample risk prediction factors into the Logistic regression analysis model to obtain the corresponding correlation of the sample risk prediction factors.

[0050] A300. Determine that the correlation corresponding to the sample risk prediction factor is greater than the preset correlation, and take the sample risk prediction factor as an independent risk prediction factor.

[0051] Please refer to Table 2. After obtaining the independent variables of the Logistic regression analysis model, the Logistic regression analysis model assigns the presence or absence of hematoma expansion as the dependent variable, and uses the assignment method to perform binary univariate non-conditional Logistic regression analysis on these sample risk prediction factors to obtain the output structure corresponding to each input parameter, i.e., the sample risk prediction factor, i.e., the P value.

[0052] Table 2 Results of univariate analysis of factors affecting the expansion of intracranial hematoma

[0053]

[0054] Afterwards, the relationship between the P value corresponding to each sample risk prediction factor and the preset P value is determined. Preferably, in this method, the preset P value is 0.05. If the P value corresponding to a certain sample risk prediction factor is less than the preset P value, it is considered that the sample risk prediction factor has no obvious statistical significance for the prediction method of the prognosis of cerebral hemorrhage of the present invention. In this method, the sample risk prediction factors with no obvious statistical significance in the numerical difference value will be removed, and then the sample risk prediction factors with significant statistical significance will be screened out, so as to perform multifactor non-conditional Logistic regression analysis later, so as to analyze the most relevant factors that may lead to hematoma expansion.

[0055] According to the data results in Table 2, there were no statistically significant differences in age, gender, and initial hematoma volume between the hematoma non-expansion group and the hematoma expansion group. However, there were statistically significant differences in the presence or absence of diabetes, blood coagulation function, systolic blood pressure at admission, GCS score, irregular density sign of hematoma edge, black hole sign, vortex sign, lobulation sign, mixed sign, and combined signs in CT imaging between the two groups. After univariate Logistic regression analysis, please refer to Table 3, which can screen out significant variables for multivariate non-conditional Logistic regression analysis. The results showed that the GCS score was negatively correlated with the expansion of intracranial hematoma; having diabetes and abnormal coagulation function would increase the possibility of hematoma expansion; the presence of each sign in CT imaging and the combination of two or more combined signs would increase the possibility of intracranial hematoma expansion in patients.

[0056] variable β SE WaldX2 P OR OR95%Cl GCS score -1.394 0.465 8.981 0.003 0.248 0.100-0.617 Blood coagulation function 2.380 0.558 18.212 0.000 10.809 3.622-32.253 Systolic blood pressure on admission 1.424 0.515 7.654 0.006 4.154 1.515-11.392 Whirlpool sign 1.227 0.509 5.810 0.016 3.410 1.258-9.245 Lobular sign 1.098 0.474 5.357 0.021 2.998 1.183-7.597 Black hole sign 1.597 0.512 9.750 0.002 4.939 1.812-13.462 Mixed signs 1.197 0.481 6.198 0.013 3.311 1.290-8.495 Irregular density sign at the edge of hematoma 1.391 0.499 7.752 0.005 4.017 1.509-10.692 diabetes 2.174 0.532 16.718 0.000 8.797 3.102-24.946

[0057] The analysis of Tables 2 and 3 showed that the initial hematoma volume value was not an independent risk predictor for hematoma expansion after cerebral hemorrhage.

[0058] See also Figure 3 , step S200 in the method specifically includes the following steps:

[0059] S210. Determine independent risk prediction factors and benchmark factors among independent risk prediction factors.

[0060] S220. Obtain the influence relationship between each independent risk prediction factor and the baseline factor.

[0061] S230. Determine the single impact value corresponding to the baseline factor, and based on the impact relationship, determine the single impact value corresponding to each independent risk prediction factor.

[0062] S240. Based on the single impact value and single test result of each independent risk prediction factor, obtain the single prediction value corresponding to each independent risk prediction factor, accumulate all the single prediction values, and obtain the comprehensive prediction value.

[0063] S250: Generate a prediction result based on the comprehensive prediction value.

[0064] After analyzing the results of the above-mentioned univariate and multivariate unconditional Logistic regression, in this method, the patient's (whether or not) diabetes, systolic blood pressure at admission, abnormal coagulation function, GCS score, irregular density sign of hematoma edge in CT imaging, black hole sign, vortex sign, lobulation sign, mixed sign and one or more combined signs are identified as independent risk prediction factors. Although these independent risk prediction factors have high specificity, they have the problem of low sensitivity. In addition, in clinical practice, sometimes patients have not only one independent risk factor, but a complex of multiple risk factors. Therefore, the possibility of evaluating the expansion of hematoma in patients by a single independent risk factor is limited. Therefore, in this method, each independent related risk factor is assigned a value, and the single impact value of each independent risk prediction factor is determined, and then the single prediction value obtained based on the single impact value of each independent risk prediction factor and the single prediction result can be accumulated to calculate the comprehensive prediction value of the patient to be predicted, which is used as the basis for predicting the expansion of hematoma.

[0065] Preferably, the odds ratio (OR) analysis method is used to find the influence relationship between each independent risk prediction factor, and the individual influence value is assigned by rounding. For example, the lobulation sign is first determined as the baseline factor, and its individual influence value is assigned to 1 point, so that the individual influence value of the black hole sign is calculated to be 2 points, the individual influence value of the vortex sign is 1 point, the individual influence value of the mixed sign is 1 point, the individual influence value of the irregular density sign at the edge of the hematoma is 1 point, the individual influence value of abnormal coagulation function is 4 points, the individual influence value of the GCS score (4-8) is 1 point, the individual influence value of the systolic blood pressure at admission is 1 point, and the individual influence value of diabetes is 3 points.

[0066] The prediction results generated based on the comprehensive prediction value specifically include:

[0067] The score interval to which the comprehensive prediction value belongs is determined, and a prediction result is generated based on the determined score interval. In this method, each score interval corresponds to a prediction result, and different score intervals correspond to different prediction results.

[0068] In this embodiment, the interval value of each score interval is also determined based on Logistic regression analysis.

[0069] Please refer to Table 4. The results of multivariate logistic regression analysis showed that the differences in the comprehensive prediction values ​​between the groups of 1-3 points, 4-8 points, 9-11 points, and 12-15 points were statistically significant (P<0.05), and the OR value was >1. It can be seen that the risk of hematoma expansion increases with the increase of the scale score.

[0070] Independent risk predictors Sensitivity Specificity Negative predictive value Positive predictive value Irregular hematoma margin sign 54.3% 78.6% 79.1% 53.5% Black hole sign 44.3% 83.8% 76.8% 55.4% Whirlpool sign 41.4% 85.7% 76.3% 56.9% Lobular sign 35.7% 81.8% 73.7% 47.1% Mixed signs 40.0% 80.5% 74.7% 48.3% Abnormal blood coagulation 52.9% 91.6% 81.0% 74% GCS: (3-8) points 47.1% 90.9% 79.1% 70.2% diabetes 45.2% 72.3% 75.6% 69.4% Systolic blood pressure on admission 58.1% 83.2% 71.6% 62.9%

[0071] See also Figure 4 The present invention also provides a device for predicting the prognosis of cerebral hemorrhage in a patient, the device comprising:

[0072] The acquisition module 100 is used to obtain the corresponding single test results of the patient to be predicted on each independent risk prediction factor.

[0073] The prediction module 200 is used to obtain a comprehensive prediction value based on the determined single impact value and single test result of each independent risk prediction factor, and generate a prediction result of the patient to be predicted based on the comprehensive prediction value. In the device, the prediction result of the patient represents the risk of hematoma expansion of the patient. It can be understood that the higher the risk of hematoma expansion, the greater the probability of postoperative rebleeding of the patient, and the lower the risk of hematoma expansion, the lower the probability of postoperative rebleeding of the patient.

[0074] Disease prognosis refers to the prediction of the future course and outcome of a disease (including recovery, recurrence, deterioration, disability, complications and death, etc.) after the disease occurs. In this device, medical staff can obtain the risk or probability of hematoma expansion of the patient to be predicted based on the prediction results. Based on the probability of hematoma expansion, medical staff can formulate corresponding treatment plans and intervene in the patient's hematoma expansion in a timely manner.

[0075] In this embodiment, the single test result corresponding to each independent risk prediction factor includes a specific value or whether a certain independent risk prediction factor exists.

[0076] In the prediction device for the prognosis of cerebral hemorrhage of patients provided by the present invention, by obtaining the corresponding single test results of the patient to be predicted on each independent risk prediction factor, then, based on the determined single influence values ​​and single test results of each independent risk prediction factor, the comprehensive prediction value of the patient is obtained, and the prediction result of the patient to be predicted is generated based on the comprehensive prediction value. The prediction result is used to indicate the risk of hematoma expansion of the patient. Therefore, medical staff can formulate corresponding treatment plans according to the prediction results of the patient to be predicted, and intervene in the hematoma expansion of the patient in time. The present invention improves the accuracy of the prediction of the prognosis of cerebral hemorrhage, can assist medical staff in formulating treatment plans, and increases the feasibility of clinical implementation.

[0077] In this embodiment, the independent risk prediction factors include (whether or not suffering from) diabetes, blood coagulation function, systolic blood pressure at admission, GCS score and specific signs in CT imaging, and the specific signs include irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign, mixed sign, one sign or multiple combined signs. CT imaging examination is one of the most clinically significant examinations for diagnosing cerebral hemorrhage, which can most intuitively reflect the location of cerebral hemorrhage in patients, the morphological characteristics of hematoma, and one sign or multiple combined signs of irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign, mixed sign can be used as an independent risk prediction factor for hematoma expansion.

[0078] See also Figure 5 , the prediction module 200 in the device specifically includes:

[0079] The first prediction unit 210 is used to determine independent risk prediction factors and benchmark factors among the independent risk prediction factors.

[0080] The second prediction unit 220 is used to obtain the influence relationship between each independent risk prediction factor and the benchmark factor.

[0081] The third prediction unit 230 is used to determine the single impact value corresponding to the benchmark factor, and based on the impact relationship, determine the single impact value corresponding to each independent risk prediction factor.

[0082] The fourth prediction unit 240 is used to obtain the single prediction value corresponding to each independent risk prediction factor based on the single impact value and the single test result of each independent risk prediction factor, and accumulate all the single prediction values ​​to obtain the comprehensive prediction value.

[0083] The fifth prediction unit 250 is used to generate a prediction result based on the comprehensive prediction value.

[0084] After analyzing the results of the above-mentioned univariate and multivariate unconditional Logistic regression, the device identified the patient's (whether or not) diabetes, systolic blood pressure at admission, abnormal coagulation function, GCS score, irregular density sign of hematoma edge in CT imaging, black hole sign, vortex sign, lobulation sign, mixed sign and one or more combined signs as independent risk prediction factors. Although these independent risk prediction factors have high specificity, they have the problem of low sensitivity. In addition, in clinical practice, sometimes patients have not only one independent risk factor, but a complex of multiple risk factors. Therefore, the possibility of evaluating the expansion of hematoma in patients by a single independent risk factor is limited. Therefore, the device assigns values ​​to each independent related risk factor, determines the single impact value of each independent risk prediction factor, and then can accumulate the single impact value of each independent risk prediction factor and the single prediction result to obtain the single prediction value, and calculate the comprehensive prediction value of the patient to be predicted, which is used as the basis for predicting the expansion of hematoma.

[0085] Preferably, the odds ratio (OR) analysis method is used to find the influence relationship between each independent risk prediction factor, and the individual influence value is assigned by rounding. For example, the lobulation sign is first determined as the baseline factor, and its individual influence value is assigned to 1 point, so that the individual influence value of the black hole sign is calculated to be 2 points, the individual influence value of the vortex sign is 1 point, the individual influence value of the mixed sign is 1 point, the individual influence value of the irregular density sign at the edge of the hematoma is 1 point, the individual influence value of abnormal coagulation function is 4 points, the individual influence value of the GCS score (4-8) is 1 point, the individual influence value of the systolic blood pressure at admission is 1 point, and the individual influence value of diabetes is 3 points.

[0086] The fifth prediction unit 250 specifically includes: determining the score interval to which the comprehensive prediction value belongs, and generating a prediction result based on the determined score interval. In the device, each score interval corresponds to a prediction result, and different score intervals correspond to different prediction results.

[0087] In this embodiment, the interval value of each score interval is also determined based on Logistic regression analysis.

[0088] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the method for predicting the prognosis of cerebral hemorrhage of the patient, and the method includes the following steps:

[0089] S100, obtaining the corresponding single test results of each independent risk prediction factor of the patient to be predicted;

[0090] S200. Based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value; wherein the prediction result characterizes the risk of hematoma expansion of the patient.

[0091] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0092] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for predicting the prognosis of cerebral hemorrhage of a patient provided by the above methods, the method comprising the following steps:

[0093] S100, obtaining the corresponding single test results of each independent risk prediction factor of the patient to be predicted;

[0094] S200. Based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value; wherein the prediction result characterizes the risk of hematoma expansion of the patient.

[0095] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the method for predicting the prognosis of cerebral hemorrhage in a patient provided by the above methods, the method comprising the following steps:

[0096] S100, obtaining the corresponding single test results of each independent risk prediction factor of the patient to be predicted;

[0097] S200. Based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value; wherein the prediction result characterizes the risk of hematoma expansion of the patient.

[0098] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0099] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting the prognosis of cerebral hemorrhage in a patient, characterized in that: The following steps are involved: Obtain the corresponding single test results of each independent risk prediction factor for the patient to be predicted; Based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, a comprehensive prediction value is obtained, and a prediction result of the patient to be predicted is generated based on the comprehensive prediction value; wherein the prediction result represents the risk of hematoma expansion of the patient; The independent risk predictive factors include diabetes, blood coagulation function, systolic blood pressure at admission, GCS score and specific signs in CT imaging; wherein the specific signs include one of the irregular density sign at the edge of hematoma, black hole sign, vortex sign, lobulation sign and mixed sign, or a combination of multiple signs; The independent risk predictors were determined by the following steps: The risk predictors of each sample from the patient where the sample was collected; Inputting the sample risk prediction factors into a Logistic regression analysis model to obtain the correlations corresponding to the sample risk prediction factors; Determining that the correlation corresponding to the sample risk prediction factor is greater than a preset correlation, and using the sample risk prediction factor as the independent risk prediction factor; The step of obtaining a comprehensive prediction value based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, and generating a prediction result for the patient based on the comprehensive prediction value specifically includes the following steps: determining the independent risk predictors and the baseline factors among the independent risk predictors; Obtaining the influence relationship between each of the independent risk prediction factors and the baseline factors; Determine the single impact value corresponding to the baseline factor, and based on the impact relationship, determine the single impact value corresponding to each of the independent risk prediction factors; Based on the single impact value and the single test result of each of the independent risk prediction factors, the single prediction value corresponding to each of the independent risk prediction factors is obtained, and all the single prediction values ​​are accumulated to obtain the comprehensive prediction value; Generate the prediction result based on the comprehensive prediction value; Generating the prediction result based on the comprehensive prediction value specifically includes: Determine the score interval to which the comprehensive prediction value belongs, and generate the prediction result based on the determined score interval; wherein each score interval corresponds to one prediction result, and different score intervals correspond to different prediction results; The benchmark factors were obtained by odds ratio analysis.

2. A prediction device for the method for predicting the prognosis of cerebral hemorrhage in a patient as claimed in claim 1, characterized in that: include: An acquisition module is used to obtain the corresponding single test results of each independent risk prediction factor of the patient to be predicted; A prediction module is used to obtain a comprehensive prediction value based on the determined single impact values ​​of each of the independent risk prediction factors and the single test results, and to generate a prediction result for the patient to be predicted based on the comprehensive prediction value; wherein the prediction result represents the risk of hematoma expansion in the patient.

3. 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 steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as claimed in claim 1 are implemented.

4. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as claimed in claim 1 are implemented.

5. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for predicting the prognosis of cerebral hemorrhage in a patient as claimed in claim 1 are implemented.

Images