A method for analyzing the efficacy of shunt surgery in patients with hydrocephalus

Abstract

The present invention belongs to the field of medical technology and relates to a method for analyzing the efficacy of shunt surgery on hydrocephalus patients. The method retrieves historical hydrocephalus patient subgroups that are highly similar to the target patient's basic information level, diagnostic information level and surgical information level, marks them in sequence into historical patient subgroups at each level, organizes the follow-up record information of each historical hydrocephalus patient included in each historical patient subgroup, constructs a reference curve for predicting the postoperative efficacy of the target patient's shunt surgery, and corrects the reference curve for predicting the postoperative efficacy of the target patient's shunt surgery based on the postoperative efficacy score of the target patient under the current follow-up status. In this way, the expected efficacy trend of the shunt surgery on the target patient under the current follow-up status is fed back, and long-term postoperative efficacy evaluation of the shunt surgery on the hydrocephalus patient is achieved, providing a more scientific and reliable basis for clinical treatment decision-making, and greatly improving the treatment effect and prognosis quality of hydrocephalus patients.

Description

Technical Field

[0001] The invention belongs to the field of medical technology and relates to a method for analyzing the efficacy of shunt surgery for patients with hydrocephalus. Background Art

[0002] Hydrocephalus is a condition caused by an excess accumulation of cerebrospinal fluid within the brain's ventricular system. A common treatment is shunt surgery, which directs excess cerebrospinal fluid away from the ventricles and into other parts of the body for absorption. However, the effectiveness of shunt surgery varies from patient to patient, influenced by numerous factors such as patient age, severity of the condition, surgical technique, and postoperative care. Therefore, accurately predicting the therapeutic effect of shunt surgery in patients with hydrocephalus is crucial.

[0003] Several existing solutions exist for predicting the efficacy of hydrocephalus shunt surgery. For example, Chinese Patent Publication No. CN113284126A describes a method for predicting the efficacy of hydrocephalus shunt surgery using artificial neural network image analysis. This method involves three steps: collecting and preprocessing imaging specimens before and after hydrocephalus shunt surgery; using artificial neural networks to analyze the probability of ventricular volume change in a single plane to predict postoperative ventricular morphology; and evaluating the relationship between ventricular volume change and patient prognosis. This method shifts surgical treatment from empiricism to personalized assessment based on big data imaging and artificial neural networks, providing new insights for hydrocephalus research and treatment.

[0004] Another Chinese patent, with publication number CN118800450A, is a method for constructing and applying a shunt surgery efficacy prediction model for idiopathic normal-pressure hydrocephalus. The method includes the following steps: extracting multivariate morphological features such as cortical thickness, surface area, volume, sulcus depth and curvature from structural magnetic resonance images, calculating the morphological inverse divergence to construct a morphological similarity network and determine its strength, then using correlation filtering and the Lasso method to screen the optimal feature subset, and combining the support vector regression model to construct a shunt surgery efficacy prediction model to achieve non-invasive and accurate evaluation of the efficacy and prognosis of patients with idiopathic normal-pressure hydrocephalus.

[0005] Although the above scheme proposes some solutions related to the prediction of the efficacy of hydrocephalus shunt surgery, it still has limitations. Specifically, the existing technology mainly relies on relevant follow-up data such as imaging monitoring. For example, the above-mentioned data on ventricular volume changes and brain region morphology are used to predict the immediate or short-term efficacy of shunt surgery in patients with hydrocephalus.

[0006] On the one hand, the dimensions of follow-up data are relatively single and cannot fully reflect the patient's condition changes, treatment response and recovery, resulting in inaccurate prediction results of the postoperative efficacy of shunt surgery in patients with hydrocephalus.

[0007] On the other hand, existing evaluation systems mostly focus on short-term efficacy, but lack a systematic tracking and evaluation mechanism for the long-term effects after shunt surgery, which is not conducive to understanding the durability of treatment and its impact on patients' quality of life. Summary of the Invention

[0008] In view of this, in order to solve the problems raised in the above background technology, a method for analyzing the efficacy of shunt surgery in patients with hydrocephalus is proposed.

[0009] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a method for analyzing the efficacy of shunt surgery for hydrocephalus patients, including: S1. Importing a collection of medical information of a target patient, respectively retrieving historical hydrocephalus patient subgroups that are highly similar to the target patient's basic information level, diagnostic information level, and surgical information level, and marking them in sequence as historical patient subgroups at each level.

[0010] S2. Organize the follow-up records of each historical hydrocephalus patient in each stratum of historical patient subgroups, including the postoperative interval days and postoperative efficacy scores of each follow-up, and construct a reference curve for predicting the postoperative efficacy of shunt surgery for the target patients.

[0011] S3. Import the current follow-up feedback information of the target patient and analyze the postoperative efficacy score of the target patient under the current follow-up status.

[0012] S4. Modify the reference curve for predicting the postoperative efficacy of the target patient's shunt surgery based on the target patient's current postoperative efficacy score under follow-up status.

[0013] S5. Provide feedback on the expected efficacy trend of shunt surgery for target patients under current follow-up status.

[0014] Compared with the existing technology, the present invention has the following beneficial effects: (1) Based on the similarity quantification model of multimodal data fusion, the present invention realizes accurate retrieval of historical patient subgroups from the basic, diagnostic and surgical information levels. In the quantification of similarity, the adaptive weighted integration of similarity coefficients between various information parameters is adopted to ensure that all factors affecting postoperative efficacy are fully covered, so that the historical patient subgroups at each level and the target patients achieve a high degree of consistency in the corresponding key features, thereby improving the accuracy of subsequent analysis.

[0015] (2) The present invention uses data fitting methods to fully capture the trends and patterns of postoperative efficacy changes over time in patients in different subgroups, so as to obtain representative curves of postoperative efficacy in each layer of historical patient subgroups, and map the efficacy change trends of hydrocephalus patients at different follow-up time points, thereby providing real-time, dynamic and long-term decision support for postoperative management.

[0016] (3) Based on the common characteristics of historical patient subgroups, the present invention selects the patient group with the most reference value for predicting the target patient, and conducts in-depth analysis of the follow-up record information of the group to obtain the control benchmark of each planned follow-up time of the target patient. On this basis, a comprehensive and highly accurate postoperative efficacy prediction reference curve is constructed through the multivariate regression fusion method to provide higher quality postoperative follow-up support for the target patient.

[0017] (4) The present invention comprehensively analyzes the postoperative efficacy score of the target patient under the current follow-up status by combining multiple indicators, and uses a local weighted smoothing correction method to correct the prediction curve, accurately reflecting the individualized recovery trend and providing targeted guidance for subsequent treatment.

[0018] (5) Based on the modified prediction curve, the present invention introduces standardized indicators such as slope value, curvature value, upper and lower tertiles to quantify the expected therapeutic effect trend, and uses data-driven feedback on trend types to achieve long-term postoperative efficacy evaluation and provide a scientific basis for clinical decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a flow chart of a method for analyzing the efficacy of shunt surgery for hydrocephalus patients provided by the first embodiment of the present invention.

[0021] Figure 2 This is a structural block diagram of a device for analyzing the efficacy of shunt surgery for hydrocephalus patients provided by the second embodiment of the present invention.

[0022] Figure 3 A schematic diagram of the hardware structure of a computer provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0024] Example 1

[0025] See also Figure 1As shown, the first embodiment of the present invention provides a method for analyzing the efficacy of shunt surgery on hydrocephalus patients, including: S1. importing a collection of target patient medical information, retrieving historical hydrocephalus patient subgroups that are highly similar to the target patient's basic information level, diagnostic information level, and surgical information level, and marking them in sequence as historical patient subgroups at each level.

[0026] In a preferred embodiment of the present invention, the medical information collection includes basic information, diagnostic information, surgical information and a planned follow-up schedule, wherein the basic information includes age, gender, allergy history, past medical history and family medical history; the diagnostic information includes the hydrocephalus diagnosis type, course of disease, severity of disease diagnosis and a set of symptom description keywords; the surgical information includes the type of surgery, surgical difficulty level and postoperative complications; the planned follow-up schedule includes each planned follow-up time and its corresponding number of days after surgery.

[0027] In a preferred embodiment of the present invention, the specific retrieval process of each layer of historical patient subgroups includes: extracting basic information, diagnosis information and surgical information of each historical hydrocephalus patient stored in the WEB cloud.

[0028] The basic information of each historical hydrocephalus patient was compared with the basic information of the target patient, and the similarity between the target patient and each historical hydrocephalus patient at the basic information level was quantified. The historical hydrocephalus patients whose similarity level was greater than the preset similarity threshold were screened and incorporated into the subgroup of historical hydrocephalus patients with high similarity to the target patient at the basic information level.

[0029] It should be noted that the specific quantitative process for the degree of similarity between the above-mentioned target patient and each historical hydrocephalus patient at the basic information level is as follows: calculate the age difference between the target patient and each historical hydrocephalus patient, take the ratio analysis result of the age difference with the preset benchmark age difference as the age span, take the negative value of the age span and import it into the natural exponential function to obtain the age similarity coefficient between the target patient and each historical hydrocephalus patient.

[0030] Based on the comparison rule of setting the gender similarity coefficient to 1 for the same gender and 0 for the opposite gender, the gender similarity coefficient between the target patient and each historical hydrocephalus patient was obtained.

[0031] According to the content of allergy history, past medical history and family medical history, the allergy history set, past medical history set and family medical history set of the target patient and each historical hydrocephalus patient were created respectively, and substituted into the Jaccard similarity coefficient calculation formula (that is, the number of intersection elements divided by the number of union elements) to obtain the allergy history similarity coefficient, past medical history similarity coefficient and family medical history similarity coefficient between the target patient and each historical hydrocephalus patient.

[0032] The cumulative value of the age similarity coefficient, gender similarity coefficient, allergy history similarity coefficient, past medical history similarity coefficient and family medical history similarity coefficient multiplied by their corresponding preset weights is used as the similarity degree at the relative basic information level, thereby obtaining the similarity degree at the relative basic information level between the target patient and each historical hydrocephalus patient.

[0033] It should be noted that the above-mentioned preset weight distribution mainly depends on the degree of influence of age, gender, allergy history, past medical history and family medical history on the efficacy of shunt surgery in patients with hydrocephalus. Based on expert experience and clinical research statistics, the order of preset weights is: age = past medical history > allergy history = family medical history > gender. The corresponding preset weights of age similarity coefficient, gender similarity coefficient, allergy history similarity coefficient, past medical history similarity coefficient and family medical history similarity coefficient are 0.3, 0.1, 0.15, 0.3 and 0.15.

[0034] Similarly, the similarity between the target patient and each historical hydrocephalus patient at the diagnostic information level and the surgical information level is quantified respectively, and the subgroup of historical hydrocephalus patients with high similarity to the target patient at the diagnostic information level and the surgical information level is retrieved.

[0035] It should be noted that the specific quantification process of the degree of similarity between the above-mentioned target patients and each historical hydrocephalus patient at the relative diagnostic information level and surgical information level is as follows: referring to professional hydrocephalus research guidelines, such as "Progress in the Classification, Diagnosis and Treatment of Hydrocephalus" or "Expert Consensus on Standardized Treatment of Hydrocephalus in China", obtain the correlation between the target patient and the hydrocephalus diagnosis type of each historical hydrocephalus patient, and quantify the similarity coefficient of the hydrocephalus diagnosis type between the target patient and each historical hydrocephalus patient. For example, if the hydrocephalus diagnosis type is the same, the similarity coefficient is set to 1; if the hydrocephalus diagnosis type is different but originates from a disease subtype with a certain pathological basis, the similarity coefficient is set to 0.5; if the hydrocephalus diagnosis type is different and is not a homologous disease subtype, the similarity coefficient is set to 0.

[0036] The analysis method of the disease course similarity coefficient between the target patient and each historical hydrocephalus patient is consistent with the above-mentioned age similarity coefficient, which will not be elaborated here.

[0037] Based on the comparison rule that the similarity coefficient of the severity level of the disease diagnosis is set to 1 if the disease diagnosis severity level is the same and set to 0 otherwise, the similarity coefficient of the disease diagnosis severity level of the target patient and each historical hydrocephalus patient is obtained.

[0038] The bag-of-words model was used to count the number of identical or similar keywords in the symptom description keyword sets of the target patients and historical patients, and a ratio analysis was performed on the total number of keywords after the symptom description keywords of the target patients and historical patients were combined to obtain the similarity coefficient of the symptom description keyword set between the target patients and each historical hydrocephalus patient.

[0039] The cumulative value of the product of the hydrocephalus diagnosis type similarity coefficient, disease course similarity coefficient, disease diagnosis severity similarity coefficient and disease description keyword set similarity coefficient and their corresponding preset weights is used as the similarity level at the relative diagnostic information level, thereby obtaining the similarity level at the relative diagnostic information level between the target patient and each historical hydrocephalus patient.

[0040] It should be noted that the above-mentioned preset weight distribution mainly depends on the degree of influence of the hydrocephalus diagnosis type, course of disease, severity of disease diagnosis and symptom description content on the efficacy of shunt surgery for hydrocephalus patients. It can also be based on expert experience and clinical research statistics. The preset weight size arrangement order is set in the content of the present invention as follows: hydrocephalus diagnosis type = severity of disease diagnosis > course of disease > symptom description content. The preset weights corresponding to the hydrocephalus diagnosis type similarity coefficient, course of disease similarity coefficient, severity of disease diagnosis similarity coefficient and symptom description keyword set similarity coefficient are 0.35, 0.2, 0.35 and 0.1.

[0041] The similarity coefficients of surgical type and surgical difficulty level between the target patient and the patients with historical hydrocephalus are analyzed in the same way as the similarity coefficients of the severity level of the disease diagnosis mentioned above, and will not be elaborated here.

[0042] A binary variable method was used. If the target patient and the historical hydrocephalus patients had a certain complication or neither, it was recorded as 1. If one had the complication and the other did not, it was recorded as 0. The sum of the similarities of all recorded complications after hydrocephalus shunt surgery stored in the WEB cloud for the target patient and the historical hydrocephalus patients was calculated. The sum of the similarities was compared with the total number of complication types to obtain the similarity coefficient of postoperative complications between the target patient and each historical hydrocephalus patient.

[0043] The cumulative value of the similarity coefficient of surgical type, similarity coefficient of surgical difficulty level and similarity coefficient of postoperative complications is used as the similarity degree at the relative surgical information level, thereby obtaining the similarity degree at the relative surgical information level between the target patient and each historical hydrocephalus patient.

[0044] This embodiment of the present invention utilizes a similarity quantification model based on multimodal data fusion to accurately retrieve historical patient subgroups from the perspectives of baseline, diagnostic, and surgical information. To quantify similarity, an adaptive weighted integration approach is employed to integrate similarity coefficients between various information parameters. This ensures comprehensive coverage of all factors influencing postoperative efficacy, ensuring high consistency between each historical patient subgroup and the target patient in corresponding key features, thereby improving the accuracy of subsequent analysis.

[0045] S2. Organize the follow-up records of each historical hydrocephalus patient in each stratum of historical patient subgroups, including the postoperative interval days and postoperative efficacy scores of each follow-up, and construct a reference curve for predicting the postoperative efficacy of shunt surgery for the target patients.

[0046] In a preferred embodiment of the present invention, the construction of a reference curve for predicting the postoperative efficacy of shunt surgery for target patients includes: taking the number of days after surgery as the horizontal axis and the postoperative efficacy score as the vertical axis, obtaining the coordinate sequence of each historical hydrocephalus patient included in each historical patient subgroup based on the follow-up record information of each historical hydrocephalus patient included in each historical patient subgroup, and further obtaining the representative curve of the postoperative efficacy of each historical patient subgroup through data fitting.

[0047] It should be noted that the specific process of obtaining the representative curves of postoperative efficacy of the above-mentioned historical patient subgroups is: summarizing the coordinate sequences of each historical hydrocephalus patient belonging to the same historical patient subgroup, calculating the mean of the vertical coordinate values ​​of each coordinate data under the same horizontal coordinate value, sorting out and obtaining a series of coordinate data with different horizontal coordinate values ​​belonging to the same historical patient subgroup, importing them into Matlab software and using the best fitting tool to obtain the best fitting function corresponding to the series of coordinate data with different horizontal coordinate values ​​belonging to the same historical patient subgroup, and using the fitting curve corresponding to the best fitting function as the representative curve of postoperative efficacy, thereby obtaining the representative curve of postoperative follow-up efficacy of each historical patient subgroup.

[0048] The embodiment of the present invention uses a data fitting method to fully capture the trends and patterns of postoperative efficacy changes over time in patients in different subgroups, so as to obtain representative curves of postoperative efficacy of each historical patient subgroup, map the efficacy change trends of hydrocephalus patients at different follow-up time points, and thus provide real-time, dynamic and long-term decision support for postoperative management.

[0049] Patients with a history of hydrocephalus who were present in the historical patient subgroups of each layer were regarded as high-reference-value patients. The high-reference-value patients were screened and the postoperative efficacy prediction scores of the target patients at each planned follow-up time were obtained based on their follow-up record information. The postoperative efficacy reference scores of the target patients at each planned follow-up time were analyzed.

[0050] It should be noted that the specific process of obtaining the postoperative efficacy prediction score of each planned follow-up time of the target patient based on the follow-up record information of each high-value patient is as follows: the postoperative interval days and postoperative efficacy score of each follow-up of each high-value patient are obtained through the follow-up record information, a rectangular coordinate system is established with time as the horizontal axis and the postoperative efficacy score as the vertical axis, discrete data points corresponding to each follow-up of each high-value patient are marked in the rectangular coordinate system, and the postoperative efficacy fitting curve of each high-value patient is drawn by the best fitting tool in the Matlab software. The postoperative interval days corresponding to each planned follow-up time of the target patient is obtained through the planned follow-up schedule of the target patient, and the corresponding ordinate value of each planned follow-up time is found in the postoperative efficacy fitting curve of each high-value patient. The ordinate value is used as the postoperative efficacy prediction score, thereby realizing the process of obtaining the postoperative efficacy prediction score of each planned follow-up time of the target patient based on the follow-up record information of each high-value patient.

[0051] The postoperative efficacy reference scores of the target patients at each planned follow-up time were used as the test set. The representative curves of the postoperative efficacy of each historical patient subgroup were fused to construct the reference curves for predicting the postoperative efficacy of the target patient's shunt surgery.

[0052] It should be noted that the above-mentioned fusion of the representative curves of postoperative efficacy of each historical patient subgroup is mainly carried out through the multivariate regression fusion method. The specific process is: each historical patient subgroup represents the basic physical factors, diagnostic disease factors and surgical factors that affect the efficacy of shunt surgery for hydrocephalus patients in sequence. Therefore, the representative curves of postoperative efficacy of each historical patient subgroup are respectively expressed as schematic curves of the changes in the postoperative efficacy scores of shunt surgery for hydrocephalus patients with reference significance relative to the target patients under the influence of basic physical factors, diagnostic disease factors and surgical factors over time.

[0053] The postoperative efficacy score of shunt surgery for hydrocephalus patients with reference significance relative to the target patients under the influence of basic physical factors, diagnostic disease factors and surgical factors is taken as the independent variable, denoted as , the postoperative efficacy prediction score corresponding to the target patient's shunt surgery is used as the dependent variable, recorded as , combined with the time variable, i.e., the number of days after surgery , construct a linear multiple regression model equation, which can be exemplified as: ,in is the intercept, is the regression coefficient, is the error term, then All are unknown parameters.

[0054] Create a series of linear multiple regression model equation simulation parameter sets, the simulation parameter sets specifically refer to The actual simulation value of is used to obtain the postoperative efficacy prediction score output by the linear multiple regression model equation at each planned follow-up time of the target patients corresponding to each simulation parameter set. The postoperative efficacy reference score of the target patients at each planned follow-up time in the test set is compared. The mean square error of the linear multiple regression model equation in predicting the postoperative efficacy score of the target patients under each simulation parameter set is calculated. The simulation parameter set corresponding to the minimum mean square error is selected as the adaptive simulation parameter set and substituted into the linear multiple regression model equation.

[0055] The representative curves of the postoperative efficacy of each historical patient subgroup were converted into postoperative efficacy scores of hydrocephalus patients undergoing shunt surgery at each postoperative interval day, which were affected by basic physical factors, diagnostic disease factors, and surgical factors and had reference significance for the target patients. The scores were substituted into the linear multiple regression model equation to output the predicted postoperative efficacy scores corresponding to each postoperative interval day for the target patients. The corresponding curves were drawn in a rectangular coordinate system with time as the horizontal axis and the postoperative efficacy score as the vertical axis, thereby constructing a reference curve for the prediction of the postoperative efficacy of shunt surgery for the target patients.

[0056] The embodiment of the present invention screens out the patient group with the most reference value for predicting the target patient based on the common characteristics of historical patient subgroups, and conducts in-depth analysis of the follow-up record information of the group to obtain the control benchmark of each planned follow-up time of the target patient. On this basis, a comprehensive and highly accurate postoperative efficacy prediction reference curve is constructed through the multivariate regression fusion method to provide higher quality postoperative follow-up support for the target patient.

[0057] S3. Import the current follow-up feedback information of the target patient and analyze the postoperative efficacy score of the target patient under the current follow-up status.

[0058] In a preferred embodiment of the present invention, the current follow-up feedback information of the target patient includes the relative improvement degree of the triad, the degree of stabilization of intracranial pressure, the rationality of imaging monitoring and the degree of improvement of postoperative complications.

[0059] It should be noted that the data source of the target patient's current follow-up feedback information mainly relies on the target patient's subjective feedback and actual monitoring during the follow-up process, and is finally evaluated by the attending physician.

[0060] The relative improvement degree of the triad syndrome involves the dimensions of cognitive improvement, urination improvement, and gait disorder improvement. Specifically, the Mini-Mental State Examination score and its growth score relative to the previous follow-up, the urination symptom examination baseline score and its decreased incidence of abnormal urination symptoms relative to the previous follow-up, and the walking test baseline score and its improvement rate of walking test indicators relative to the previous follow-up are monitored.

[0061] The degree of intracranial pressure stabilization specifically monitors the intracranial pressure value of the target patient within a preset time period.

[0062] The rationality of imaging monitoring specifically monitors the size of the ventricles and cerebrospinal fluid flow indicators.

[0063] The degree of improvement of postoperative complications is comprehensively judged by the patient's self-reported complication-related symptoms combined with relevant examination reports.

[0064] In a preferred embodiment of the present invention, the analysis of the postoperative efficacy score of the target patient in the current follow-up status includes: assessing the postoperative efficacy score values ​​for the triple indications, physiological indications, imaging indications and concurrent indications in the target patient's current follow-up status based on the relative improvement degree of the triad, the degree of intracranial pressure stabilization, the rationality of imaging monitoring and the degree of improvement of postoperative complications in the target patient's current follow-up feedback information, and accumulating the values ​​to obtain the postoperative efficacy score of the target patient in the current follow-up status.

[0065] It should be noted that the assessment of the postoperative efficacy scoring values ​​for the triple indications, physiological indications, imaging indications and concurrent indications of the above-mentioned target patients in the current follow-up status mainly refers to the postoperative efficacy scoring standards stored in the WEB cloud, which include the preset basic scoring values ​​corresponding to the relative improvement degree of the unit triad, the unit intracranial pressure stabilization degree, the unit imaging monitoring rationality and the unit postoperative complication improvement degree, which are obtained by multiplying the relative improvement degree of the triple, the intracranial pressure stabilization degree, the imaging monitoring rationality and the postoperative complication improvement degree in the current follow-up feedback information of the target patients with the preset basic scoring values ​​corresponding to their corresponding unit indicators.

[0066] S4. Modify the reference curve for predicting the postoperative efficacy of the target patient's shunt surgery based on the target patient's current postoperative efficacy score under follow-up status.

[0067] In a preferred embodiment of the present invention, the modified reference curve for predicting the postoperative efficacy of the target patient's shunt surgery includes: based on the number of postoperative interval days corresponding to the current follow-up time of the target patient, obtaining the corresponding postoperative efficacy prediction score from the reference curve for predicting the postoperative efficacy of the target patient's shunt surgery, performing a difference calculation between the score and the postoperative efficacy score under the current follow-up status of the target patient, and obtaining the prediction score error of the postoperative efficacy prediction reference curve for the current follow-up status of the target patient.

[0068] It should be noted that the prediction score error of the above-mentioned postoperative efficacy prediction reference curve for the current follow-up status of the target patient is in the form of a negative number calculated by the difference.

[0069] The subsequent curve segment whose starting horizontal coordinate node in the reference curve for the postoperative efficacy prediction of the target patient's shunt surgery is the postoperative interval days corresponding to the current follow-up time is determined as the correction curve segment, and the postoperative efficacy prediction score corresponding to each postoperative interval day contained in the correction curve segment is extracted in sequence.

[0070] Based on the prediction score error of the postoperative efficacy prediction reference curve for the current follow-up status of the target patient, the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment is adjusted to achieve the correction processing of the postoperative efficacy prediction reference curve of the target patient's shunt surgery.

[0071] In a preferred embodiment of the present invention, adjusting the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment includes: taking the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment as a basic item.

[0072] In view of the prediction score error of the postoperative efficacy prediction reference curve for the current follow-up status of the target patient, a control smoothing factor and a time attenuation factor are introduced to generate dynamic adjustment items. The dynamic adjustment items are superimposed on the basic items to obtain the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment after adjustment.

[0073] It should be noted that the adjustment process of the postoperative efficacy prediction score corresponding to each postoperative interval day included in the above calibration curve segment can be exemplified by referring to the following formula: ,in is the basic item, specifically indicating the first The postoperative efficacy prediction score corresponding to the number of days after surgery, is the number of each postoperative interval day included in the calibration curve segment, , For dynamic adjustment items, is the number of postoperative interval days included in the calibration curve segment, is the prediction score error of the reference curve for the postoperative efficacy prediction for the current follow-up status of the target patient, are preset control smoothing factor, preset time attenuation factor, is a natural constant, is the number of days after surgery corresponding to the current follow-up time of the target patient.

[0074] This exemplary formula specifically draws on the decay exponential function. Its core idea is the analytical calculation of the dynamic adjustment term, which is expressed as ,here , , The constant term helps to control the overall adjustment range and avoid drastic fluctuations in the prediction curve due to a single error. The exponential term ensures that the adjustment amount gradually decreases over time, maintains the smoothness of the curve, and can more reasonably reflect the changing trend of the postoperative efficacy, so as to enhance the rationality and scientificity of the prediction of the postoperative efficacy of the correction curve segment.

[0075] Combined with this exemplary formula, assuming that the target patient's current follow-up time corresponds to a postoperative interval of 60 days, , , , when the future postoperative interval is 90 days, the initial postoperative efficacy prediction score is 100. The adjusted postoperative efficacy prediction score calculated by the above adjustment formula is 101.85.

[0076] The embodiment of the present invention comprehensively analyzes the postoperative efficacy score of the target patient under the current follow-up status by combining multiple indicators, and uses a local weighted smoothing correction method to correct the prediction curve, accurately reflecting the individualized recovery trend and providing targeted guidance for subsequent treatment.

[0077] S5. Provide feedback on the expected efficacy trend of shunt surgery for target patients under current follow-up status.

[0078] In a preferred embodiment of the present invention, the feedback of the expected efficacy trend of the shunt surgery under the current follow-up status of the target patient includes: based on the modified reference curve of the postoperative efficacy prediction of the shunt surgery of the target patient, collecting the slope value, curvature value and postoperative efficacy prediction score corresponding to the upper and lower tertiles of the curve segment after the postoperative interval corresponding to the current follow-up time, and analyzing the expected efficacy trend index of the shunt surgery under the current follow-up status of the target patient .

[0079] It should be noted that the specific analysis process of the expected efficacy trend indicators of shunt surgery for the above-mentioned target patients under the current follow-up status is: respectively obtain the calculated difference between the postoperative efficacy prediction scores corresponding to the upper and lower tertiles presented by the curve segment after the postoperative interval days corresponding to the current follow-up time and the postoperative efficacy score threshold value of the hydrocephalus patient's postoperative efficacy reaching the cure indication state stored in the WEB cloud, and then further perform a ratio analysis on the calculated difference with the postoperative efficacy score threshold value of the hydrocephalus patient's postoperative efficacy reaching the cure indication state stored in the WEB cloud, so as to obtain the postoperative efficacy cure index corresponding to the upper and lower tertiles.

[0080] The calculated difference between the postoperative efficacy prediction scores of the upper and lower tertiles presented by the curve segment after the postoperative interval corresponding to the current follow-up time was analyzed with the postoperative efficacy score threshold value of the hydrocephalus patients stored in the WEB cloud when the postoperative efficacy reached the state of cure indication to obtain the postoperative efficacy span index corresponding to the upper and lower tertiles.

[0081] The cumulative value of the postoperative efficacy recovery index corresponding to the upper and lower tertiles is used as the numerator, and the postoperative efficacy span index corresponding to the upper and lower tertiles is used as the denominator. A ratio analysis is performed to obtain the postoperative efficacy baseline level assessment index presented by the curve segment after the postoperative interval days corresponding to the current follow-up time. If the denominator is 0 in the ratio analysis process, a preset constant needs to be added to the denominator.

[0082] The slope value and curvature value of the curve segment after the postoperative interval corresponding to the current follow-up time respectively indicate the rate of change and degree of fluctuation of the postoperative efficacy score change trend, and can be directly used as the postoperative efficacy dynamic evaluation index and postoperative efficacy stability evaluation index presented by the curve segment after the postoperative interval corresponding to the current follow-up time.

[0083] The postoperative efficacy baseline level evaluation index, postoperative efficacy dynamic evaluation index, and postoperative efficacy stability evaluation index are accumulated to obtain the expected efficacy trend evaluation index of shunt surgery in the target patient's current follow-up status.

[0084] Extract the upper limit value of the preset indicator value range corresponding to the expected fluctuation trend after shunt surgery for hydrocephalus patients stored in the WEB cloud and lower limit ,like , then the expected efficacy trend of shunt surgery in the current follow-up status of the target patient is the expected deviation trend. If , then the expected efficacy trend of shunt surgery in the current follow-up state of the target patient is the expected matching trend. , then the expected efficacy trend of shunt surgery under the current follow-up status of the target patient is fed back as the expected fluctuation trend.

[0085] It should be noted that the above-mentioned expected consistent trend indicates that the postoperative recovery of hydrocephalus patients is consistent with expectations and meets expectations. The expected fluctuating trend indicates that the patient's postoperative recovery is partially in line with expectations, but further observation is required. The expected deviation trend indicates that the patient's postoperative recovery is not meeting expectations, symptoms have not been alleviated, or have worsened, and the doctor should be informed of the risk.

[0086] Based on the corrected prediction curve, the embodiment of the present invention introduces standardized indicators such as slope value, curvature value, upper and lower tertiles to quantify the expected therapeutic effect trend, and feedbacks the trend type in a data-driven manner to achieve long-term postoperative efficacy evaluation, providing a scientific basis for clinical decision-making.

[0087] It should also be noted that in the method for analyzing the efficacy of shunt surgery for hydrocephalus patients involved in the present invention, the expected efficacy trend of shunt surgery for the target patient under the current follow-up status is fed back as an auxiliary predictive opinion for the doctor's clinical diagnosis, and ultimately the doctor still needs to conduct a comprehensive evaluation to give a predicted result of the efficacy of shunt surgery for the target patient.

[0088] Example 2

[0089] like Figure 2 As shown, in the second embodiment of the present invention, a device for analyzing the efficacy of shunt surgery for patients with hydrocephalus is provided, including: a similar patient subgroup retrieval module, an efficacy prediction curve construction module, a postoperative efficacy score analysis module, an efficacy prediction curve correction module and an expected efficacy trend feedback module.

[0090] The similar patient subgroup retrieval module is connected to the efficacy prediction curve construction module, the efficacy prediction curve construction module is connected to the postoperative efficacy score analysis module, the postoperative efficacy score analysis module is connected to the efficacy prediction curve correction module, and the efficacy prediction curve correction module is connected to the expected efficacy trend feedback module.

[0091] The similar patient subgroup retrieval module is used to import the target patient's medical information collection, and retrieve historical hydrocephalus patient subgroups that are highly similar to the target patient's basic information level, diagnostic information level, and surgical information level, and mark them in sequence as historical patient subgroups at each level.

[0092] The efficacy prediction curve construction module is used to organize the follow-up record information of each historical hydrocephalus patient in each historical patient subgroup. The follow-up record information includes the postoperative interval days and postoperative efficacy score of each follow-up, and construct a reference curve for postoperative efficacy prediction of shunt surgery for target patients.

[0093] The postoperative efficacy score analysis module is used to import the current follow-up feedback information of the target patient and analyze the postoperative efficacy score of the target patient under the current follow-up status.

[0094] The efficacy prediction curve correction module is used to correct the postoperative efficacy prediction reference curve of the target patient's shunt surgery based on the postoperative efficacy score of the target patient in the current follow-up status.

[0095] The expected efficacy trend feedback module is used to feedback the expected efficacy trend of shunt surgery under the current follow-up status of the target patient.

[0096] An embodiment of the present invention provides a device for analyzing the efficacy of shunt surgery for patients with hydrocephalus. Its implementation principle and technical effects are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0097] Example 3

[0098] In a third embodiment of the present invention, the embodiment of the present invention provides the following technical solution: a computer, comprising a memory 202, a processor 201, and a computer program stored in the memory 202 and executable on the processor 201; the processor 201, when executing the computer program, implements the above-mentioned method for analyzing the efficacy of shunt surgery for patients with hydrocephalus.

[0099] Specifically, the processor 201 may include a central processing unit, or a specific integrated circuit, or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0100] Memory 202 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 202 may include a hard disk drive, a floppy disk drive, a solid-state drive, flash memory, an optical disk, a magneto-optical disk, magnetic tape, or a universal serial bus drive, or a combination of two or more of these. Where appropriate, memory 202 may include removable or non-removable (or fixed) media. Where appropriate, memory 202 may be internal or external to the data processing device. In certain embodiments, memory 202 is non-volatile memory. In certain embodiments, memory 202 includes read-only memory and random access memory. Where appropriate, the ROM may be mask-programmed ROM, programmable ROM, erasable PROM, electrically erasable PROM, electrically rewritable ROM, or flash memory, or a combination of two or more of these.

[0101] The memory 202 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 201 .

[0102] The processor 201 reads and executes computer program instructions stored in the memory 202 to implement the above-mentioned method for analyzing the efficacy of shunt surgery for patients with hydrocephalus.

[0103] In some embodiments, the computer may further include a communication interface 203 and a bus 200. Figure 3 As shown, the processor 201 , the memory 202 , and the communication interface 203 are connected via a bus 200 and communicate with each other.

[0104] The communication interface 203 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application. The communication interface 203 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0105] Bus 200 includes hardware, software or both, and couples the components of the computer to each other. Bus 200 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 200 may include an accelerated graphics interface or other graphics bus, an enhanced industrial standard architecture bus, a front-side bus, a hypertransport interconnect, an industrial standard architecture bus, a wireless bandwidth interconnect, a low pin count bus, a memory bus, a microchannel architecture bus, a peripheral component interconnect bus, a PCI-Express bus, a serial advanced technology attachment bus, a video electronics standard association local bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 200 may include one or more buses. Although the present application describes and illustrates a specific bus, the present application contemplates any suitable bus or interconnect.

[0106] Example 4

[0107] In a fourth embodiment of the present invention, in combination with the above-mentioned method for analyzing the efficacy of shunt surgery for patients with hydrocephalus, the embodiment of the present invention provides the following technical solution: a storage medium having a computer program stored thereon, which implements the above-mentioned method for analyzing the efficacy of shunt surgery for patients with hydrocephalus when executed by a processor.

[0108] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A method for analyzing the efficacy of shunt surgery in patients with hydrocephalus, characterized in that: The method includes: S1. Import the target patient's medical information collection and search for historical hydrocephalus patient subgroups that are highly similar to the target patient's basic information, diagnostic information, and surgical information, and mark them sequentially into historical patient subgroups at each level; S2. Organize the follow-up records of each patient with hydrocephalus within each stratum of historical patient subgroups, including the number of days between each follow-up visit and the postoperative efficacy score, to construct a reference curve for predicting the postoperative efficacy of shunt surgery for the target patient; The method of constructing a reference curve for predicting the postoperative efficacy of shunt surgery for a target patient includes: using the number of days after surgery as the horizontal axis and the postoperative efficacy score as the vertical axis, obtaining a coordinate sequence of each patient with historical hydrocephalus in each historical patient subgroup based on follow-up records of each patient with historical hydrocephalus in each historical patient subgroup, and further obtaining a representative curve for the postoperative efficacy of each historical patient subgroup by data fitting. Patients with a history of hydrocephalus who were present in the historical patient subgroups of each stratum were considered as high-reference-value patients. The high-reference-value patients were screened and their follow-up records were used to obtain the postoperative efficacy prediction scores of the target patients at each planned follow-up time. The postoperative efficacy reference scores of the target patients at each planned follow-up time were then analyzed. The postoperative efficacy reference scores of the target patients at each planned follow-up time were used as the test set. The representative postoperative efficacy curves of each historical patient subgroup were fused to construct a reference curve for predicting the postoperative efficacy of the target patient's shunt surgery. S3. Import the current follow-up feedback information of the target patient and analyze the postoperative efficacy score of the target patient under the current follow-up status; S4. Modify the reference curve for predicting the postoperative efficacy of the target patient's shunt surgery based on the target patient's current postoperative efficacy score at follow-up; The method comprises: obtaining a corresponding postoperative efficacy prediction score from the target patient's shunt surgery postoperative efficacy prediction curve based on the number of postoperative days corresponding to the target patient's current follow-up time, performing a difference calculation between the corresponding postoperative efficacy prediction score and the target patient's current follow-up postoperative efficacy score, and obtaining a prediction score error of the postoperative efficacy prediction curve for the target patient's current follow-up status; The subsequent curve segment of the target patient's shunt surgery postoperative efficacy prediction reference curve, whose starting abscissa node is the postoperative interval days corresponding to the current follow-up time, is determined as a correction curve segment, and the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment is sequentially extracted; Based on the prediction score error of the postoperative efficacy prediction reference curve for the current follow-up status of the target patient, the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment is adjusted, thereby achieving the correction processing of the postoperative efficacy prediction reference curve of the target patient's shunt surgery; The adjusting the postoperative efficacy prediction score corresponding to each postoperative interval day included in the calibration curve segment includes: taking the postoperative efficacy prediction score corresponding to each postoperative interval day included in the calibration curve segment as a basic item; In view of the prediction score error of the reference curve for the postoperative efficacy prediction for the current follow-up status of the target patient, a control smoothing factor and a time decay factor are introduced to generate dynamic adjustment items. The dynamic adjustment items are superimposed on the basic items to obtain the postoperative efficacy prediction score corresponding to each postoperative interval day included in the correction curve segment after adjustment. ; The adjustment process of the postoperative efficacy prediction score corresponding to each postoperative interval day included in the above calibration curve segment is based on the following formula: ,in is the basic item, specifically indicating the first The postoperative efficacy prediction score corresponding to the number of days after surgery, is the number of each postoperative interval day included in the calibration curve segment, , For dynamic adjustment items, is the number of postoperative interval days included in the calibration curve segment, is the prediction score error of the reference curve for the postoperative efficacy prediction for the current follow-up status of the target patient, are preset control smoothing factor, preset time attenuation factor, is a natural constant, The number of days after surgery corresponding to the current follow-up time of the target patient; S5. Provide feedback on the expected efficacy trend of shunt surgery for target patients during their current follow-up period; The feedback on the expected efficacy trend of the shunt surgery of the target patient in the current follow-up state includes: based on the revised reference curve for the postoperative efficacy prediction of the shunt surgery of the target patient, collecting the slope value, curvature value and postoperative efficacy prediction scores corresponding to the upper and lower tertiles of the curve segment after the postoperative interval corresponding to the current follow-up time, and analyzing the expected efficacy trend index of the shunt surgery of the target patient in the current follow-up state. ; Extract the upper limit value of the preset indicator value range corresponding to the expected fluctuation trend after shunt surgery for hydrocephalus patients stored in the WEB cloud and lower limit ,like , then the expected efficacy trend of shunt surgery in the current follow-up status of the target patient is the expected deviation trend. If , then the expected efficacy trend of shunt surgery in the current follow-up state of the target patient is the expected matching trend. , then the expected efficacy trend of shunt surgery in the current follow-up status of the target patient is fed back as the expected fluctuation trend; The specific analysis process of the trend indicators of the expected efficacy of shunt surgery for the above-mentioned target patients in the current follow-up status is as follows: The postoperative efficacy baseline level evaluation index, postoperative efficacy dynamic evaluation index, and postoperative efficacy stability evaluation index presented by the curve segment after the postoperative interval days corresponding to the current follow-up time were obtained based on the collected slope value, curvature value, and postoperative efficacy prediction score corresponding to the upper and lower tertiles; The postoperative efficacy benchmark level evaluation index, postoperative efficacy dynamic evaluation index, and postoperative efficacy stability evaluation index are accumulated to obtain the expected efficacy trend index of shunt surgery in the current follow-up status of the target patient; The cumulative value of the postoperative efficacy recovery index corresponding to the upper and lower tertiles was used as the numerator, and the postoperative efficacy span index corresponding to the upper and lower tertiles was used as the denominator. Ratio analysis was performed to obtain the postoperative efficacy benchmark level assessment index presented by the curve segment after the postoperative interval corresponding to the current follow-up time; The slope value and curvature value of the curve segment after the postoperative interval corresponding to the current follow-up time respectively indicate the rate of change and degree of fluctuation of the postoperative efficacy score change trend, and can be directly used as the postoperative efficacy dynamic evaluation index and postoperative efficacy stability evaluation index presented by the curve segment after the postoperative interval corresponding to the current follow-up time.

2. The method for analyzing the efficacy of shunt surgery for hydrocephalus patients according to claim 1, characterized in that: The medical information collection includes basic information, diagnostic information, surgical information and planned follow-up schedule, wherein the basic information includes age, gender, allergy history, past medical history and family medical history; the diagnostic information includes the hydrocephalus diagnosis type, course of disease, severity of disease diagnosis and a set of symptom description keywords; the surgical information includes the type of surgery, surgical difficulty level and postoperative complications; the planned follow-up schedule includes each planned follow-up time and its corresponding number of days after surgery.

3. The method for analyzing the efficacy of shunt surgery for hydrocephalus patients according to claim 2, characterized in that: The specific retrieval process of each layer of historical patient subgroups includes: extracting the basic information, diagnosis information and surgery information of each historical hydrocephalus patient stored in the WEB cloud; Compare the basic information of each historical hydrocephalus patient with that of the target patient, quantify the similarity between the target patient and each historical hydrocephalus patient at the basic information level, screen the historical hydrocephalus patients whose similarity level is greater than a preset similarity threshold, and incorporate them into a subgroup of historical hydrocephalus patients with a high degree of similarity to the target patient at the basic information level; Similarly, the similarity between the target patient and each historical hydrocephalus patient at the diagnostic information level and the surgical information level is quantified respectively, and the subgroup of historical hydrocephalus patients with high similarity to the target patient at the diagnostic information level and the surgical information level is retrieved.

4. The method for analyzing the efficacy of shunt surgery for hydrocephalus patients according to claim 1, characterized in that: The specific analysis method of the postoperative efficacy reference score of the target patients at each planned follow-up time is: the postoperative efficacy prediction score of the target patients at the same planned follow-up time is obtained by comparing the follow-up record information of each high-reference value patient and performing truncated mean calculation.

5. The method for analyzing the efficacy of shunt surgery for hydrocephalus patients according to claim 1, characterized in that: The current follow-up feedback information of the target patients includes the relative improvement of the triad, the degree of stabilization of intracranial pressure, the rationality of imaging monitoring and the degree of improvement of postoperative complications.

6. The method for analyzing the efficacy of shunt surgery for hydrocephalus patients according to claim 5, characterized in that: The analysis of the postoperative efficacy score of the target patient in the current follow-up status includes: assessing the postoperative efficacy score values ​​for the triple indications, physiological indications, imaging indications and concurrent indications in the target patient's current follow-up status based on the relative improvement degree of the triad, the degree of intracranial pressure stabilization, the rationality of imaging monitoring and the degree of improvement of postoperative complications in the target patient's current follow-up feedback information, and accumulating the values ​​to obtain the postoperative efficacy score of the target patient in the current follow-up status.

Images