CN111341452B - Multisystem atrophy disability prediction method, model building method, device and equipment - Google Patents

Abstract

The invention relates to a multi-system atrophy disability prediction method, a model building method, a device and equipment, and belongs to the technical field of disease prediction.

Description

Multiple system atrophy disability prediction method, model building method, device and equipment

technical field

The invention belongs to the technical field of disease prediction, and in particular relates to a multiple system atrophy disability prediction method, model building method, device and equipment.

Background technique

Multiple system atrophy (MSA) is a rare, progressive neurodegenerative disorder characterized by varying combinations of parkinsonism, cerebellar ataxia, and autonomic dysfunction. The mean median times from the onset of illness to needing assistance in walking, wheelchair use, bedridden, and death were 3, 5, 8, and 9 years, respectively. Due to its low incidence, the disease has been included in the national list of rare diseases. The disease has an insidious onset, rapid progression, and short survival period, which brings a great burden to patients, their families and the whole society.

Previous studies on the prognosis of patients with multiple system atrophy mainly used death as the clinical outcome indicator to construct a death prediction model. Studies have found that the onset of autonomic symptoms, late onset age, frequent falls and other factors are closely related to the prognosis.

However, in the prior art, there is no prediction of disability in patients with multiple system atrophy. Due to the rapid disease progression of patients with multiple system atrophy, they gradually lose their mobility within 4-5 years of the course of the disease and are confined to wheelchairs. They lose their ability to take care of themselves and seriously affect their quality of life. Therefore, it is particularly important to establish a multiple system atrophy disability prediction model, which can guide clinicians to carry out individualized and precise treatment for patients, improve their quality of life, and improve the prognosis of patients.

Contents of the invention

In order to at least solve the above-mentioned problems in the prior art, the present invention provides a multi-system atrophy disability prediction method, a model building method, a device and equipment.

The technical scheme provided by the invention is as follows:

On the one hand, a method for constructing a multiple system atrophy disability prediction model, comprising:

Obtain the basic data of patients with multiple system atrophy whose disease course is within a preset time period, the basic data includes: clinical index data and hematological index data;

Processing the clinical index data and the hematology index data based on preset processing rules to obtain a target data set;

According to the target data set, the support vector machine algorithm and the preset linear kernel function, the prediction model of multiple system atrophy and disability is constructed by using the kernlab package in the R program.

Optionally, the processing of the clinical index data and the hematology index data based on preset processing rules to obtain a target data set includes:

Use the rapid eye movement sleep behavior disorder assessment scale to score the patients in the patient group;

The unified multiple system atrophy assessment scale was used to evaluate the motor symptoms of the patients;

Based on the preset orthostatic hypotension evaluation rules, the patients were evaluated for orthostatic hypotension.

Optionally, the clinical indicators include: age, gender, age of onset, delay in diagnosis, course of disease, body mass index, type of diagnosis, form of first symptoms, whether there are repeated falls within a preset time period, whether there are pyramidal tract signs, whether there is wheezing Snoring, severe snoring, rapid eye movement sleep behavior disorder, unified multisystem atrophy assessment scale first part score, unified multiple system atrophy assessment scale second part score, unified multiple system atrophy assessment scale The score in the fourth part of the table, the total score of the Unified Multiple System Atrophy Assessment Scale, and whether there is orthostatic hypotension;

Hematological indicators include: red blood cell count, hemoglobin, hematocrit, mean corpuscular volume, mean corpuscular hemoglobin content, mean corpuscular hemoglobin concentration, red blood cell distribution width CV, red blood cell distribution width SD, platelet count, white blood cell count, neutrophils Percentage of cells, percentage of lymphocytes, percentage of monocytes, percentage of eosinophils, percentage of basophils, absolute value of neutrophils, absolute value of lymphocytes, absolute value of monocytes, absolute value of eosinophils value, absolute value of basophils, total bilirubin, direct bilirubin, indirect bilirubin, alanine aminotransferase, aspartate aminotransferase, alanine aminotransferase/aspartate amino Transferase ratio, total protein, albumin, globulin, white globule ratio, glucose, urea, creatinine, serum cystatin C, uric acid, triglyceride, cholesterol, high-density lipoprotein, low-density lipoprotein, alkaline phosphate enzymes, glutamyl transpeptidase, creatine kinase, lactate dehydrogenase, hydroxybutyrate dehydrogenase.

Optionally, the processing of the clinical index data and the hematology index data based on preset processing rules to obtain a target data set includes:

According to gender, the gender of the patient is assigned, male = 1, female = 0;

Obtain the patient's body mass index, body mass index = weight/height squared;

According to the diagnosis type, the diagnosis type of the patient is assigned, Parkinson's disease-dominant type = 1, cerebellar ataxia-dominant type = 0; the form of the first symptom is divided into the onset of autonomic dysfunction = 0; the onset of motor symptoms = 1; recurrent falls within 3 years = 1, no = 0; pyramidal tract sign = 1, no = 0; wheezing = 1, no = 0; severe snoring = 1, no = 0 ; REM sleep behavior disorder = 1, no = 0; orthostatic hypotension = 1, no = 0.

Optionally, the method for constructing the preset linear kernel function includes:

Construct kernel function: k(xi,xj)=φ(xi)·φ(xj);

Based on the slack variable, create a soft interval, and obtain the classification plane constraints: y _i (wx _i + b)≥1, i=1,2,...,N;

ξ_i≥0，i＝1,2,…,N；Obtain the soft-boundary objective function:

ξ _i ≥ 0, i=1,2,...,N;

y _i (wx _i +b)≥1-ξ _i , ξ _i ≥0;

Among them, C is the error penalty factor; ξ is the slack variable.

Optionally, the selection range of the error penalty factor C of the support vector machine is 5-8.

Optionally, it also includes: evaluating the accuracy of the prediction model based on Kappa statistics.

In yet another aspect, a multiple system atrophy disability prediction method, comprising:

Obtain the basic data of the target multiple system atrophy patient, the basic data including: clinical index data and hematological index data;

Processing the target data based on preset processing rules to obtain the target data;

Predict the disability of the target multiple system atrophy patient according to the target data and the model established by any of the methods for constructing the multiple system atrophy disability prediction model described above.

In yet another aspect, a device for constructing a multi-system atrophy disability prediction model includes: an acquisition module, a processing module, and a construction module;

The obtaining module is used to obtain basic data of patients with multiple system atrophy whose course of disease is within a preset time period, the basic data includes: clinical index data and hematological index data;

The processing module is configured to process the clinical index data and the hematology index data based on preset processing rules to obtain a target data set;

The construction module is used to construct a prediction model of multiple system atrophy and disability by using the kernlab program package in the R program according to the target data set, the support vector machine algorithm and the preset linear kernel function.

In yet another aspect, a multiple system atrophy disability prediction device includes: a processor, and a memory connected to the processor;

The memory is used to store a computer program, and the computer program is at least used to execute the above-mentioned multiple system atrophy disability prediction method;

The processor is used to call and execute the computer program in the memory.

The beneficial effects of the present invention are:

The multiple system atrophy disability prediction method, model building method, device and equipment provided by the present invention use the clinical indicators of patients with multiple system atrophy combined with hematological indicators as the prediction data for the first time, perform feature screening on the prediction data, and filter out multiple The features are modeled by support vector machines, so as to realize the accurate prediction of the disability of patients with multiple system atrophy, so as to guide clinicians to carry out individualized and precise treatment for patients, improve their quality of life, and improve the prognosis of patients.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a schematic flowchart of a method for constructing a multiple system atrophy disability prediction model provided by an embodiment of the present invention;

Fig. 2 is a schematic flowchart of a method for predicting multiple system atrophy disability provided by an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of a device for constructing a multi-system atrophy disability prediction model provided by an embodiment of the present invention;

Fig. 4 is a schematic structural diagram of a multi-system atrophy disability prediction device provided by an embodiment of the present invention.

Reference numerals: 31 - acquisition module; 32 - processing module; 33 - building module; 41 - processor; 42 - memory.

Detailed ways

In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other implementations obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

The disease progression of multiple system atrophy is very complex, usually the result of multiple factors acting together. Traditional regression analysis statistical methods do not perform well when dealing with complex multiple factors, and there is currently no prediction model for multiple system atrophy disability.

Based on this, the present invention establishes a disability prediction model of multiple system atrophy based on support vector machine technology, thereby guiding individualized treatment, delaying disease progression, and improving quality of life.

An embodiment of the present invention provides a method for constructing a multiple system atrophy disability prediction model.

Figure 1 is a schematic flowchart of a method for constructing a multiple system atrophy disability prediction model provided by an embodiment of the present invention, please refer to Figure 1, the method provided by an embodiment of the present invention may include the following steps:

S11. Obtain basic data of patients with multiple system atrophy in a preset time period, the basic data including: clinical index data and hematological index data.

S12. Based on preset processing rules, the clinical index data and the hematological index data are processed to obtain a target data set.

When constructing the multiple system atrophy disability prediction model, the basic data of multiple system atrophy patients whose disease course is within a preset time period can be collected first, and the basic data can include: clinical index data and hematological index data.

For example, the preset time period may be 3 years, and the basic data (baseline clinical data) of multiple system atrophy patients whose disease course is within 3 years at the time of treatment in a certain hospital or a certain area are collected. Clinical index data, which can include: age, gender, date of onset, date of first diagnosis, delay in diagnosis, course of disease, body mass index, type of diagnosis, form of first symptoms, whether there are repeated falls within 3 years, whether there are pyramidal tract signs, whether there is asthma Snoring, severe snoring, rapid eye movement sleep behavior disorder, Unified Multiple System Atrophy Assessment Scale Part I score, Unified Multiple System Atrophy Assessment Scale Part II score, Unified Multiple System Atrophy Assessment Scale The score in the fourth part of the table, the total score of the Unified Multiple System Atrophy Assessment Scale, and whether there is orthostatic hypotension

Among them, when judging whether there is rapid eye movement sleep behavior disorder (Rapid eye movement sleep behavior disorder, RBD), the rapid eye movement sleep behavior disorder assessment scale is used for evaluation, and a score greater than or equal to 5 means RBD. The motor symptoms of patients were assessed by Unified Rating MSA Scale (UMSARS). When evaluating whether a patient has orthostatic hypotension, the patient can lie flat on the examination bed and rest quietly for 10 minutes, then measure and record the supine blood pressure, and then ask the patient to stand up from the examination bed and measure 1, 3, 5, Orthostatic hypotension (OH) was defined as orthostatic hypotension (OH) if the systolic blood pressure in the upright position decreased by more than 30 mmHg compared with the supine position, or the diastolic blood pressure decreased by more than 15 mmHg compared with the supine position. .

When obtaining hematological index data, fasting hematological samples of patients during the treatment period can be collected for testing: the testing indicators are blood routine, liver and kidney function.

A total of 167 patients with multiple system atrophy with a disease course of less than 3 years were included after excluding patients who were incapacitated in a wheelchair at the baseline assessment.

A follow-up evaluation was performed on 167 patients with multiple system atrophy. The follow-up evaluation was an annual face-to-face evaluation or telephone evaluation to observe whether they were incapacitated and confined to a wheelchair, and recorded the time when they started using the wheelchair. Patient incapacity confined to a wheelchair was defined as disability. We used disability as the outcome measure. According to the follow-up results, we took the 4-year duration of the disease as the limit, marking 0 for disability within 4 years, and marking 1 for no disability within 4 years. At the same time, we excluded data with no disability within 4 years of disease course. Finally, the data of 137 patients with multiple system atrophy were obtained, and all patients met the probable multiple system atrophy according to the second edition of diagnostic criteria in 2008.

The data of 137 patients with multiple system atrophy were preprocessed and format transformed: gender (male=1, female=0); body mass index (BMI) = weight/height squared (international unit kg/m2); diagnosis types were divided into MSA with predominantly parkinsonian features (MSA-P) = 1 and MSA with predominantly cerebellar ataxia (MSA-C) = 0; Onset of disturbance = 0 (including urinary disturbance and orthostatic hypotension) and onset of motor symptoms = 1 (including symptoms of cerebellar ataxia and parkinsonism); recurrent falls within 3 years = 1, absence = 0 ;with pyramidal tract sign=1, without=0;with stridor=1,without=0;with severe snoring=1,without=0;with RBD=1,without=0;with orthostatic hypotension=1 , none = 0; the rest of the indicators are numerical data.

The target data set finally obtained includes: clinical indicators include: age, gender, age of onset, delay in diagnosis, course of disease, body mass index (BMI), type of diagnosis, form of first symptoms, whether repeated falls within 3 years, whether there is Pyramidal tract signs, wheezing, severe snoring, rapid eye movement sleep behavior disorder (RBD), Unified Multiple System Atrophy Assessment Scale (Unified Rating MSA Scale, UMSARS) first part score, UMSARS Second part score, UMSARS fourth part score, UMSARS total score, whether there is orthostatic hypotension; hematological indicators include: red blood cell count, hemoglobin, hematocrit, mean corpuscular volume, mean corpuscular hemoglobin content, mean corpuscular hemoglobin concentration, Red blood cell distribution width CV, red blood cell distribution width SD, platelet count, white blood cell count, percentage of neutrophils, percentage of lymphocytes, percentage of monocytes, percentage of eosinophils, percentage of basophils, neutrophils Absolute granulocytes, absolute lymphocytes, absolute monocytes, absolute eosinophils, absolute basophils, total bilirubin, direct bilirubin, indirect bilirubin, alanine transamination Enzyme (ALT), aspartate aminotransferase (AST), AST/ALT ratio, total protein, albumin, globulin, white globule ratio, glucose, urea, creatinine, serum cystatin C, uric acid, triglycerides Ester, cholesterol, high-density lipoprotein, low-density lipoprotein, alkaline phosphatase, glutamyl transpeptidase, creatine kinase, lactate dehydrogenase, hydroxybutyrate dehydrogenase.

For example, take patient 1 as an example, gender male=1, age 49 years old, age of onset 47 years old, diagnosis delayed by 1.5 years, course of disease 2 years, body mass index 23.6, diagnosis type MSA-P=1, first symptom was motor symptoms = 1, repeated falls within 3 years = 1, pyramidal tract sign = 1, no wheeze = 0, no severe snoring = 0, rapid eye movement sleep behavior disorder = 1, UMSARS first part score is 10 points, UMSARS Score of 12 on the second part, 2 on the fourth part of UMSARS, 24 on the total UMSARS score, with orthostatic hypotension = 1, red blood cell count = 4.76, hemoglobin = 138, hematocrit = 0.41, mean corpuscular volume = 86.3, mean corpuscular hemoglobin content = 29, mean corpuscular hemoglobin concentration = 336, red blood cell distribution width CV = 12.7, red blood cell distribution width SD = 40.5, platelet count = 199, white blood cell count = 6.1, percentage of neutrophils = 56.6, percentage of lymphocytes=36.9, percentage of monocytes=4.4, percentage of eosinophils=1.8, percentage of basophils=0.3, absolute value of neutrophils=3.45, absolute value of lymphocytes=2.25 , Absolute value of monocytes=0.27, absolute value of eosinophils=0.11, absolute value of basophils=0.02, total bilirubin=14.2, direct bilirubin=3.2, indirect bilirubin=11, alanine amino Transferase (ALT) = 11, aspartate aminotransferase (AST) = 15, AST/ALT ratio = 1.36, total protein = 69.2, albumin = 40.8, globulin = 28.4, white globule ratio = 1.44, glucose =5.38, urea=4.88, creatinine=67.1, serum cystatin C=0.94, uric acid=424, triglyceride=2.1, cholesterol=4.81, high-density lipoprotein=1, low-density lipoprotein=2.89, alkaline phosphate Enzyme = 82, glutamyl transpeptidase = 16, creatine kinase = 82, lactate dehydrogenase = 173, hydroxybutyrate dehydrogenase = 125. Disability at the 3rd year of follow-up = 0.

S13. According to the target data set, the preset linear kernel function and the support vector machine algorithm and the support vector machine algorithm and the preset linear kernel function, use the kernlab package in the R program to construct a prediction model of multiple system atrophy and disability.

After obtaining the target data set, use the linear inseparable support vector machine algorithm first, use the kernel function: k( _xi , x _j )=φ( _xi )·φ(x _j ), use the kernlab program in the R program Package to build predictive models of multiple system atrophy disability.

In this application, the classification plane constraints can be:

y _i (wx _i +b)≥1, i=1,2,...,N.

In order to balance generalization ability and misclassification, a penalty term is introduced in min1/ ^2‖w‖2 :

Transform the objective function into:

ξ_i≥0，i＝1,2,…,N。

ξ _i ≥0, i=1,2,...,N.

Among them, C is the error penalty factor, also known as the cost value, which represents the degree of punishment for misclassified sample points. So the algorithm tries to minimize the total cost instead of finding the maximum interval. Right now

y _i (wx _i +b)≥1-ξ _i , ξi≥0.

The target data set is input into the support vector machine model, and all valid samples are randomly divided into training set and test set through the system. For example, 137 samples are randomly divided into training set and test set through systematic sampling; 80% (109 cases) of them are training set, and 20% (28 cases) are test set. It is worth noting that the data here are just enumerations, not limitations.

According to the support vector machine algorithm and the above-mentioned linear kernel function and the target data set, a multiple system atrophy disability prediction model was constructed.

The selection range of the error penalty factor C of the support vector machine is 5-20, for example, it can be considered to select specific point values between 5, 6, 7, 8, ..., 17, 18, 19, 20 and the above values, here Without going into details, the preferred penalty factor is 5-8.

In order to verify the accuracy of the assessment of the disability prediction model, Kappa statistics can be used to measure. The value range of Kappa is [0,1]. The higher the value of this coefficient, the higher the classification accuracy of the model. Generally, when the value of Kappa is 0.6 or above, it represents the predicted value and the real value of the model. have a good consistency.

Use Cohen's kappa statistical calculation method among the present invention, its expression can be:

Pr(a) represents the real consistency between the model predicted value and the real value, and Pr(e) represents the consistency between the model predicted value and the expected value.

After obtaining the results of the prediction model, use the test set for verification, compare the prediction results with the actual situation, and obtain the confusion matrix between the two. The confusion matrix is shown in Table 1 below, where 8 means that the actual disability within 4 years is predicted to be a disability. 2 is the number of samples that were actually disabled within 4 years and were predicted to be non-disabled; 4 is the number of samples that were predicted to be disabled without actually occurring within 4 years; 14 is the actual The number of sample cases in which disability-free within 4 years is predicted to be non-disabled.

Table 1

In Table 1, 0 means disability occurred within 4 years, and 1 means no disability occurred within 4 years.

Therefore, the sensitivity of the disability prediction model constructed in this example is 87.5%, the specificity is 66.7%, the Kappa coefficient is 0.6, and the value range of 0.6 belongs to [0.6,1]. Therefore, the accuracy of the model is good.

The method for constructing a multi-system atrophy disability prediction model based on a support vector machine in the present invention performs feature screening according to the clinical characteristics of patients with multiple system atrophy combined with hematological indicators, and adopts support vector machine modeling for multiple features screened out to realize Accurate prediction of disability in patients with multiple system atrophy, so as to guide clinicians to carry out individualized precise treatment for patients, in order to improve the prognosis of patients and improve their quality of life.

The multiple system atrophy disability prediction model construction method provided by the embodiment of the present invention uses the clinical characteristics of patients with multiple system atrophy combined with hematological indicators as the prediction data for the first time, performs feature screening on the prediction data, and uses support vectors for the screened out multiple features Machine modeling, so as to achieve accurate prediction of disability in patients with multiple system atrophy, so as to guide clinicians to carry out individualized and precise treatment for patients, so as to improve the prognosis of patients and improve their quality of life.

Based on a general inventive concept, an embodiment of the present invention also provides a multiple system atrophy disability prediction method.

Fig. 2 is a schematic flowchart of a method for predicting multiple system atrophy disability provided by an embodiment of the present invention, please refer to Fig. 2, the prediction method provided by an embodiment of the present invention may include the following steps:

S21. Obtain basic data of the target multiple system atrophy patient, the basic data including: clinical index data and hematological index data.

S22. Based on a preset processing rule, process the target data to obtain the target data.

S23. Predict the disability of the target multiple system atrophy patient according to the target data and the model established by any one of the methods for constructing the multiple system atrophy disability prediction model mentioned above.

In a specific prediction process, the basic data of the target patient can be acquired. The specific acquisition process and processing process have been described in the above-mentioned embodiments, and will not be repeated here. The obtained target data is input into the constructed prediction model, so as to obtain the disability prediction of the target patient.

Based on a general inventive concept, an embodiment of the present invention also provides a device for constructing a multi-system atrophy and disability prediction model.

FIG. 3 is a schematic structural diagram of a device for constructing a multi-system atrophy disability prediction model provided by an embodiment of the present invention. Please refer to FIG. processing module 32 and building module 33 .

An acquisition module 31, configured to acquire basic data of patients with multiple system atrophy whose course of disease is within a preset time period, the basic data includes: clinical index data and hematological index data;

A processing module 32, configured to process the clinical index data and the hematological index data based on preset processing rules to obtain a target data set;

The construction module 33 is used for constructing a prediction model of multiple system atrophy and disability according to the target data set, the support vector machine algorithm and the preset linear kernel function, using the kernlab program package in the R program.

Regarding the apparatus in the foregoing embodiments, the specific manner in which each module executes operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

The multiple system atrophy disability prediction model construction device provided by the embodiment of the present invention uses the clinical indicators of multiple system atrophy patients combined with hematological indicators as the prediction data for the first time, performs feature screening on the prediction data, and uses support vectors for the screened out multiple features Machine modeling, so as to achieve accurate prediction of disability in patients with multiple system atrophy, so as to guide clinicians to carry out individualized and precise treatment for patients, so as to improve the prognosis of patients and improve their quality of life.

Based on a general inventive concept, an embodiment of the present invention also provides a multi-system atrophy disability prediction device.

Figure 4 is a schematic structural diagram of a multi-system atrophy disability prediction device provided by an embodiment of the present invention, please refer to Figure 4, a multi-system atrophy disability prediction device provided by an embodiment of the present invention includes: a processor 41, and The memory 42 to which the processor is connected.

The memory 42 is used to store computer programs, and the computer programs are at least used in the multiple system atrophy disability prediction method described in any of the above-mentioned embodiments;

The processor 41 is used to call and execute computer programs in the memory.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

It can be understood that, the same or similar parts in the above embodiments can be referred to each other, and the content that is not described in detail in some embodiments can be referred to the same or similar content in other embodiments.

It should be noted that, in the description of the present invention, terms such as "first" and "second" are only used for description purposes, and should not be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" means at least two.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent modules, segments or portions of code comprising one or more executable instructions for implementing specific logical functions or steps of the process , and the scope of preferred embodiments of the invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order depending on the functions involved, which shall It is understood by those skilled in the art to which the embodiments of the present invention pertain.

It should be understood that various parts of the present invention can be realized by hardware, software, firmware or their combination. In the embodiments described above, various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques known in the art: Discrete logic circuits, ASICs with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. During execution, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention, those skilled in the art can make the above-mentioned The embodiments are subject to changes, modifications, substitutions and variations.

Claims (6)

1. A method for building a multiple system atrophy disability prediction model, comprising: Obtain the basic data of patients with multiple system atrophy whose course of disease is within a preset time period, the basic data includes: clinical index data and hematological index data; wherein, the clinical index includes: age, gender, age of onset, diagnosis delay, course of disease, Body mass index, type of diagnosis, pattern of first symptoms, presence of repeated falls within a predetermined period of time, presence of pyramidal tract signs, presence of stridor, presence of severe snoring, presence of rapid eye movement sleep behavior disorder, unified Multiple System Atrophy Assessment Scale Part 1 Score, Unified Multiple System Atrophy Assessment Scale Part 2 Score, Unified Multiple System Atrophy Assessment Scale Part 4 Score, Unified Multiple System Atrophy Assessment Scale Total Score, Whether There Is Upright Hematological indicators include: red blood cell count, hemoglobin, hematocrit, mean corpuscular volume, mean corpuscular hemoglobin content, mean corpuscular hemoglobin concentration, red blood cell distribution width CV, red blood cell distribution width SD, platelet count, white blood cell count, neutral Percentage of segmented granulocytes, percentage of lymphocytes, percentage of monocytes, percentage of eosinophils, percentage of basophils, absolute value of neutrophils, absolute value of lymphocytes, absolute value of monocytes, Absolute eosinophils, absolute basophils, total bilirubin, direct bilirubin, indirect bilirubin, alanine aminotransferase, aspartate aminotransferase, alanine aminotransferase/gate Ratio of partate aminotransferase, total protein, albumin, globulin, white globule ratio, glucose, urea, creatinine, serum cystatin C, uric acid, triglyceride, cholesterol, high-density lipoprotein, low-density lipoprotein , alkaline phosphatase, glutamyl transpeptidase, creatine kinase, lactate dehydrogenase, hydroxybutyrate dehydrogenase; Based on preset processing rules, the clinical index data and the hematological index data are processed to obtain the target data set, including: using the Rapid Eye Movement Sleep Behavior Disorder Assessment Scale to score the patient; using a unified multiple Systemic atrophy assessment scale, to assess the patient's motor symptoms; based on the preset orthostatic hypotension assessment rules, to assess whether the patient has orthostatic hypotension; specifically include: assign the patient's gender according to gender, male = 1 , female = 0; obtain the patient's body mass index, body mass index = weight/height square; according to the diagnosis type, assign a value to the patient's diagnosis type, Parkinson's disease-dominant type = 1, cerebellar ataxia-dominant type = 0 ; The form of the first symptom is divided into autonomic dysfunction onset = 0; motor symptom onset = 1; repeated falls within 3 years = 1, no occurrence = 0; pyramidal tract sign = 1, no = 0; With wheezing = 1, without = 0; with severe snoring = 1, without = 0; with rapid eye movement sleep behavior disorder = 1, without = 0; with orthostatic hypotension = 1, without = 0; According to the target data set, the support vector machine algorithm and the preset linear kernel function, use the kernlab program package in the R program to construct the prediction model of multiple system atrophy and disability; wherein, the construction method of the preset linear kernel function includes : Construct kernel function: k(xi,xj)=φ(xi)·φ(xj); Based on the slack variable, create a soft interval, and obtain the classification plane constraints: y _i (wx _i + b)≥1, i=1,2,...,N; Obtain the soft-boundary objective function:

y _i (wx _i +b)≥1-ξ _i , ξ _i ≥0; Among them, C is the error penalty factor; ξ is the slack variable. 2. The method according to claim 1, characterized in that: The selection range of the error penalty factor C of the support vector machine is 5-8. 3. The method according to claim 1, further comprising: evaluating the accuracy of the prediction model based on Kappa statistics. 4. A multiple system atrophy disability prediction method, characterized in that it comprises: Obtain the basic data of the target multiple system atrophy patient, the basic data including: clinical index data and hematological index data; Processing the target data based on preset processing rules to obtain the target data; According to the target data and the model established by the method for constructing the multiple system atrophy disability prediction model described in any one of claims 1-3, the disability of the target multiple system atrophy patient is predicted. 5. A device for constructing a multi-system atrophy disability prediction model, comprising: an acquisition module, a processing module and a construction module; The acquiring module is used to acquire the basic data of patients with multiple system atrophy whose course of disease is within a preset time period, the basic data includes: clinical index data and hematological index data; wherein, the clinical index includes: age, gender, onset Age, delay in diagnosis, duration, body mass index, type of diagnosis, pattern of first symptoms, presence of repeated falls within a predetermined time period, presence of pyramidal signs, presence of stridor, severe snoring, rapid eye movement sleep behavior disorder, unified multiple system atrophy assessment scale part 1 score, unified multiple system atrophy assessment scale part 2 score, unified multiple system atrophy assessment scale part 4 score, unified multiple system atrophy assessment scale Table total score, whether there is orthostatic hypotension; hematological indicators include: red blood cell count, hemoglobin, hematocrit, mean corpuscular volume, mean corpuscular hemoglobin content, mean corpuscular hemoglobin concentration, red blood cell distribution width CV, red blood cell distribution width SD, platelets Count, white blood cell count, percentage of neutrophils, percentage of lymphocytes, percentage of monocytes, percentage of eosinophils, percentage of basophils, absolute value of neutrophils, absolute value of lymphocytes , monocyte absolute value, eosinophil absolute value, basophil absolute value, total bilirubin, direct bilirubin, indirect bilirubin, alanine aminotransferase, aspartate aminotransferase, alanine Amino acid aminotransferase/aspartate aminotransferase ratio, total protein, albumin, globulin, white globule ratio, glucose, urea, creatinine, serum cystatin C, uric acid, triglycerides, cholesterol, high density Lipoprotein, low-density lipoprotein, alkaline phosphatase, glutamyl transpeptidase, creatine kinase, lactate dehydrogenase, hydroxybutyrate dehydrogenase; The processing module is configured to process the clinical index data and the hematological index data based on preset processing rules to obtain a target data set; specifically, it is used to adopt the rapid eye movement sleep behavior disorder assessment scale to Score the patient; use the unified multiple system atrophy assessment scale to assess the patient's motor symptoms; based on the preset orthostatic hypotension assessment rules, assess whether the patient has orthostatic hypotension; specifically used for: according to gender, Assign the gender of the patient, male=1, female=0; obtain the patient’s body mass index, body mass index=weight/height square; Predominant cerebellar ataxia = 0; form of first symptom divided into autonomic dysfunction onset = 0; motor symptom onset = 1; recurrent falls within 3 years = 1, absence = 0; cones present Fascic signs = 1, no = 0; wheezing = 1, no = 0; severe snoring = 1, no = 0; rapid eye movement sleep behavior disorder = 1, no = 0; orthostatic hypotension = 1, none = 0; The construction module is used to construct a prediction model of multiple system atrophy disability using the kernlab program package in the R program according to the target data set, the support vector machine algorithm and the preset linear kernel function; wherein, the preset linear The construction method of the kernel function, including: Construct kernel function: k(xi,xj)=φ(xi)·φ(xj); Based on the slack variable, create a soft interval, and obtain the classification plane constraints: y _i (wx _i + b)≥1, i=1,2,...,N; Obtain the soft-boundary objective function:

y _i (wx _i +b)≥1-ξ _i , ξ _i ≥0; Among them, C is the error penalty factor; ξ is the slack variable. 6. A multi-system atrophy disability prediction device, comprising: a processor, and a memory connected to the processor; The memory is used to store a computer program, and the computer program is at least used to execute the multiple system atrophy disability prediction method described in claim 4; The processor is used to call and execute the computer program in the memory.

Images