Risk prediction model construction method for oral mucositis nursing

Abstract

The invention relates to the technical field of data processing, in particular to a risk prediction model construction method for oral mucositis nursing, and the method comprises the steps: obtaining the data of all patients seeing a doctor; according to each risk factor of the patient under all the risk levels, obtaining an influence degree of the risk factor on the assessment risk level, and screening out a key risk factor of each risk level; according to the influence degree of each risk factor on all the assessment risk levels, the importance degree of each risk factor is obtained, and all important risk factors are screened out; and according to the key risk factors and the important risk factors of each risk level, constructing an oral mucositis risk prediction model. According to the method, the oral mucositis risk prediction model is constructed by analyzing historical patient data, so that the severity of the oral mucositis of the patient after chemotherapy is accurately predicted, and corresponding prevention and nursing are provided for the patient.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method for constructing a risk prediction model for oral mucositis care. Background Art

[0002] Oral mucositis is an ulcerative lesion that occurs in the oral mucosa and is a common oral complication related to cancer treatment. The clinical manifestations are congestion, redness, erosion, ulceration and fibrosis of the oral mucosa. Patients will show discomfort symptoms such as swallowing pain, dry mouth, and taste disorder. At the same time, due to impaired nutritional status, it will cause bacterial, viral or fungal infections. There is no accurate prediction of the development trend of the patient's condition, which will directly or indirectly lead to an increase in the patient's additional medical costs during the nursing process and reduce the patient's quality of life.

[0003] Since this year, with the rapid development of computer technology, intelligent analysis algorithms have been rapidly popularized and applied in the medical field, and artificial intelligence technology has assisted clinical nursing medical staff to make more accurate judgments and decisions. However, due to the relatively high incidence of oral mucositis, a large clinical data sample size, and complex data structures at the same time, it is difficult for existing machine learning algorithm models to make correct decisions accurately. Summary of the Invention

[0004] The present invention provides a method for constructing a risk prediction model for oral mucositis care to solve the existing problem that it is difficult to accurately predict the grade of oral mucositis after chemotherapy for patients based on various data of the visiting patients, resulting in the inability to provide effective nursing plans for patients.

[0005] The method for constructing a risk prediction model for oral mucositis care of the present invention adopts the following technical solutions: It includes the following steps: Obtain the information of all visiting patients, where the information of the patients includes the risk grades and risk factors of the patients; Mark the patients according to the presence of each risk factor in each patient under each risk grade, and obtain the patient marking sequence of each risk factor under each risk grade; obtain the correlation of the patient marking sequences between different risk factors under the same risk grade; according to the correlation, screen out the relevant risk factors of the risk factors under each risk grade; according to the correlation between different risk factors under the same risk grade, combine the differences between the risk factors and the relevant risk factors of the risk factors under the risk grade to obtain the influence degree of the risk factors on the evaluation risk grade; according to the influence degree of the risk factors on the evaluation risk grade, screen out the key risk factors of each risk grade; According to the influence degree of each risk factor on all evaluated risk levels, combined with the number of patients with corresponding risk factors in the patient data, obtain the importance degree of each risk factor; according to the importance degree of each risk factor, screen out all important risk factors; Train an oral mucositis risk prediction model according to the key risk factors and important risk factors of each risk level; according to the prediction model, predict the oral mucositis level of the visiting patients after chemotherapy, and provide care for the patients.

[0006] Preferably, the method for marking patients according to the presence of each risk factor in patients at each risk level to obtain the patient marking sequence of each risk factor at each risk level specifically includes: For any risk factor, among all the visiting patients at each risk level, mark the patients with the risk factor as and mark the patients without the risk factor as ; obtain the patient marking set of the corresponding risk factor at each risk level, sort the elements in the patient marking set of the corresponding risk factor at each risk level according to the information entry time, and obtain the patient marking sequence of the corresponding risk factor at each risk level; the and are respectively preset non - negative marking values, and is greater than .

[0007] Preferably, the marking value is 1, and the marking value is 0.

[0008] Preferably, the method for obtaining the correlation between the patient marking sequences of different risk factors at the same risk level specifically includes: Obtain the difference between the Pearson correlation coefficient between the patient marking sequences of different risk factors at the same risk level and the sum of the sequence marking values; according to the difference between the Pearson correlation coefficient between the patient marking sequences of different risk factors at the same risk level and the sum of the sequence marking values, obtain the correlation between the patient marking sequences of different risk factors at the same risk level; The absolute value of the Pearson correlation coefficient between the patient marking sequences of different risk factors at the same risk level is positively correlated with the correlation between the patient marking sequences of different risk factors at the same risk level; the difference between the sum of the sequence marking values of the patient marking sequences of different risk factors at the same risk level is negatively correlated with the correlation between the patient marking sequences of different risk factors at the same risk level.

[0009] Preferably, the method for screening out the relevant risk factors of risk factors at each risk level according to the relevance includes the following specific steps: Preset a threshold for the number of relevant risk factors , and among the correlations of the patient marker sequences between different risk factors at the same risk level, the top risk factors with the largest correlations are used as the relevant risk factors of the risk factors at this risk level.

[0010] Preferably, the method for obtaining the influence degree of risk factors on the evaluation of risk levels by combining the correlations between different risk factors at the same risk level and the differences between the risk factors and their relevant risk factors at the risk level includes the following specific steps: For the influence degree of any risk factor on the evaluation of any risk level, obtain the differences between the risk factors and their relevant risk factors at the same risk level; The correlation between different risk factors at the same risk level is positively correlated with the influence degree of risk factors on the evaluation of risk levels; the difference between the risk factors and their relevant risk factors at the same risk level is negatively correlated with the influence degree of risk factors on the evaluation of risk levels.

[0011] Preferably, the method for screening out the key risk factors of each risk level according to the influence degree of risk factors on the evaluation of risk levels includes the following specific steps: Preset a threshold for the influence degree of risk factors under a single risk , and when the influence degree of any risk factor on the evaluation of any risk level is greater than , then this risk factor is recorded as the key risk factor for evaluating this risk level.

[0012] Preferably, the method for obtaining the importance degree of each risk factor by combining the influence degree of each risk factor on all evaluated risk levels and the number of patients with the corresponding risk factor in the patient data includes the following specific steps: The influence degree of each risk factor on the evaluation of all risk levels is positively correlated with the importance degree of each risk factor; the number of patients with each risk factor is positively correlated with the importance degree of each risk factor; the difference in the influence degree of each risk factor on different risk levels is negatively correlated with the importance degree of each risk factor.

[0013] Preferably, the method for screening out all important risk factors according to the importance degree of each risk factor includes the following specific steps: Preset a threshold for the importance degree ; when the importance degree of the risk factor is greater than If so, the risk factor is recorded as an important risk factor.

[0014] Preferably, the method for training the oral mucositis risk prediction model specifically includes: Denote the set composed of the key risk factors of all risk levels as the key factor set, and denote the set composed of all important risk factors as the important factor set; denote the risk factors in the union of the key factor set and the important factor set as the target risk factors; Take the set composed of all target risk factors as the training set of the first random forest algorithm, and take the set composed of all non-target risk factors as the training set of the second random forest algorithm; preset an adjustment weight greater than 0.5 and less than 1 ; Let the random forest algorithm Select risk factors randomly from the training set of the first random forest algorithm with a probability of Select risk factors randomly from the training set of the second random forest algorithm with a probability of, and train to obtain the oral mucositis risk prediction model.

[0015] The beneficial effects of the technical solution of the present invention are: by obtaining the correlation between different risk factors at the same risk level according to each risk factor of patients at all risk levels; screening out the key risk factors of each risk level according to the correlation between different risk factors at the same risk level. Since the greater the impact of a risk factor on the evaluation of the risk level, the more similar this risk factor is to other risk factors, the degree of influence of the risk factor on the evaluation of the risk level can be obtained through the similarity between different risk factors, and then the key risk factors of each risk level can be screened out, preparing for the subsequent construction of the oral mucositis nursing knowledge base; Furthermore, all important risk factors are screened out according to the influence degree of each risk factor on all evaluated risk levels; since the key risk factors of each risk level are indicators for one risk level, all important risk factors are obtained by integrating the influence degree of all risk factors on all evaluated risk levels; further, according to the key risk factors and important risk factors of each risk level, a training set of the random forest algorithm is constructed to train the oral mucositis risk prediction model, so that the oral mucositis risk prediction model can accurately evaluate the risk level of patients, and then can provide an effective nursing plan for patients, achieving the purpose of reducing the incidence of oral mucositis complications and alleviating the pain of patients. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the steps of the method for constructing a risk prediction model for oral mucositis care according to the present invention; Figure 2 It is a flowchart for obtaining a risk prediction model for oral mucositis. Specific embodiments

[0018] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features and effects of the method for constructing a risk prediction model for oral mucositis care according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0020] The following specifically describes the specific solution of the method for constructing a risk prediction model for oral mucositis care provided by the present invention in conjunction with the accompanying drawings.

[0021] Embodiment 1: Step S1: Collect the risk information of oral mucositis of the patient.

[0022] Collect the risk factors of oral mucositis of the current patient by doctors and nurses. The risk factors are shown in the following table; at the same time, retrieve the risk factors and risk levels of oral mucositis of all historical patients in the database.

[0023] Step S2: Predict the grade of oral mucositis of the current patient after chemotherapy according to the risk information of oral mucositis of the current patient.

[0024] It should be noted that currently, before chemotherapy for patients, the severity of oral mucositis after chemotherapy is mainly predicted through scales. However, the occurrence of oral mucositis is induced and affected by various complex factors, and the accuracy and applicability of scale prediction for the severity of oral mucositis after chemotherapy for patients are limited. Therefore, in this embodiment, through the data of historical patients, an oral mucositis risk prediction model is trained to accurately predict the severity level of oral mucositis after chemotherapy for patients, so as to formulate corresponding nursing plans for patients.

[0025] Specifically, the oral mucositis risk factors of the current patient are used as the input of the oral mucositis risk prediction model to predict the level of oral mucositis after chemotherapy for the current patient.

[0026] Step S3: According to the predicted level of oral mucositis after chemotherapy for the current patient, formulate corresponding prevention strategies for the patient.

[0027] For patients with a predicted oral mucositis level of grade one, it should mainly focus on maintaining oral cleanliness, moisture, and basic care; For patients with a predicted oral mucositis level of grade two, on the basis of maintaining oral cleanliness and moisture, further reduce oral irritation, and appropriate drugs can be used for intervention; For patients with a predicted oral mucositis level of grade three, on the basis of maintaining oral cleanliness, moisture, and avoiding all irritating foods and behaviors, stronger preventive and treatment measures should be taken, and continuous monitoring by doctors and drug intervention are required.

[0028] Embodiment Two: Please refer to Figure 1 , which shows the flowchart of the steps of the risk prediction model construction method for oral mucositis care provided by an embodiment of the present invention. This method is the specific steps of step S2: Step S201: Obtain the risk factor information of the patients seeking medical treatment.

[0029] It should be noted that as a risk prediction model construction method for oral mucositis care in this embodiment, specifically, by analyzing the data of all patients seeking medical treatment in history, an oral mucositis risk prediction model is trained, and the severity of oral mucositis after chemotherapy for patients is predicted according to the oral mucositis risk prediction model. Therefore, first, the data of patients needs to be obtained.

[0030] Specifically, the data of all patients seeking medical treatment at all risk levels in the database are retrieved. The patient data includes the risk level of the patient and the risk factors. The risk levels include: mild risk, moderate risk, and severe risk. The risk factors include: whether taking opioid drugs, whether smoking, whether the oral pH value is less than 6.5, etc.

[0031] Step S202: Mark the patients according to the presence of each risk factor in patients at each risk level, and obtain the patient marking sequences of each risk factor at each risk level; obtain the correlation between the patient marking sequences of different risk factors at the same risk level; screen out the related risk factors of each risk factor at each risk level according to the correlation; according to the correlation between different risk factors at the same risk level, combine the differences between the risk factors and their related risk factors at the risk level to obtain the influence degree of the risk factor on the evaluated risk level; screen out the key risk factors of each risk level according to the influence degree of the risk factor on the evaluated risk level.

[0032] It should be noted that in this embodiment, by screening all the risk factors in the patient data, the purpose of improving the data quality of the oral mucositis nursing knowledge base is achieved. Therefore, it is first necessary to obtain the risk factors that have a great influence on the evaluation of each risk level; considering that there are some associations between different risk factors, the associations between different risk factors can be further considered. In the embodiment of the present invention, by marking the patients, the patient marking sequences of each risk factor at all risk levels are obtained, and the similarity between different risk factors is quantified by using the patient marking sequences of different risk factors at the same risk level. And when a risk factor has a greater influence on the evaluated risk level, the risk factor is more similar to other risk factors. Therefore, the influence degree of the risk factor on the evaluated risk level can be obtained through the correlation between different risk factors, and the key risk factors of each risk level can be screened out.

[0033] Specifically, for any risk factor, among all the patients visiting at each risk level, the patients with the risk factor are marked as , and the patients without the risk factor are marked as ; obtain the patient marking set corresponding to the risk factor at each risk level, sort the elements in the patient marking set corresponding to the risk factor at each risk level according to the information entry time, and obtain the patient marking sequence corresponding to the risk factor at each risk level; the and are respectively preset non - negative marking values, and is greater than , and The specific values of can be set according to the actual situation by oneself, and there is no rigid requirement in this embodiment. In this embodiment, they are described with , . Preferably, in an embodiment of the present invention, the Pearson correlation coefficient between the patient marker sequences of different risk factors under the same risk level is obtained, and the difference from the sum of the sequence marker values is calculated; based on the Pearson correlation coefficient between the patient marker sequences of different risk factors under the same risk level and the difference from the sum of the sequence marker values, the correlation between the patient marker sequences of different risk factors under the same risk level is obtained. The absolute value of the Pearson correlation coefficient between the patient marker sequences of different risk factors under the same risk level is positively correlated with the correlation between the patient marker sequences of different risk factors under the same risk level; the difference in the sum of the patient marker sequence marker values of different risk factors under the same risk level is negatively correlated with the correlation between the patient marker sequences of different risk factors under the same risk level.

[0034] In a specific embodiment of the present invention, the calculation formula is as follows: In the formula, represents the correlation between the th risk factor and the th risk factor of the patients under the th risk level; represents the Pearson correlation coefficient between the patient marker sequence of the th risk factor and the patient marker sequence of the th risk factor under the th risk level; represents the sum of the marker values within the patient marker sequence of the th risk factor under the th risk level; represents the sum of the marker values within the patient marker sequence of the th risk factor under the th risk level; represents the absolute value operation; represents the exponential function with the natural constant as the base; in this embodiment, the model is used to present the inverse proportional relationship and normalization processing,

[0035] Further, a threshold value for the number of relevant risk factors is preset. The specific value of can be set according to the actual situation, and there is no strict requirement in this embodiment. In this embodiment, Among the correlations of the patient marker sequences between different risk factors under the same risk level, the top risk factors with the largest correlations are used as the relevant risk factors of the risk factors under this risk level; For the influence degree of any risk factor on evaluating any risk level, obtain the differences between the risk factors and the relevant risk factors of the risk factors under the same risk level; The correlation between different risk factors under the same risk level is positively correlated with the influence degree of the risk factor on evaluating the risk level; the difference between the risk factor and the relevant risk factor of the risk factor under the same risk level is positively or negatively correlated with the influence degree of the risk factor on evaluating the risk level.

[0036] In a specific embodiment of the present invention, its calculation formula is: In the formula, represents the influence degree of the th risk factor on evaluating the th risk level; represents the preset threshold of the number of relevant risk factors; represents the number of risk factors; represents the th risk factor of the patients under the th risk level and the th risk factor; represents the th risk factor of the patients under the th risk level and the th relevant risk factor; represents the mean value of the correlations between the th risk factor of the patients under the th risk level and all relevant risk factors; represents the absolute value operation; represents the normalization function, and the normalization object is the key degree of each risk factor under all risk levels.

[0037] It should be noted that and The larger the value, the stronger the correlation between the th risk factor of the patients under the th risk level and all other risk factors. And when the correlation between a risk factor and other risk factors is stronger, the influence degree of this risk factor on evaluating the risk level is greater. Therefore and The larger the value, the The higher the impact degree of a risk factor on the evaluation of the th risk level; since when the impact degree of a risk factor on the evaluation of the risk level is greater, the risk factor has the characteristic of higher similarity with all relevant factors, so the smaller the value of, the greater the impact degree of the risk factor on the evaluation of the risk level.

[0038] Furthermore, a threshold value of the impact degree of a risk factor under a single risk is preset , The specific value of can be set by itself according to the actual situation, and there is no rigid requirement in this embodiment. In this embodiment, it is described with . When the impact degree of any risk factor on the evaluation of any risk level is greater than , then the risk factor is recorded as a key risk factor for evaluating the risk level.

[0039] So far, the key risk factors for evaluating each risk level are obtained.

[0040] Step S203: According to the impact degree of each risk factor on all evaluated risk levels, combined with the number of patients with the corresponding risk factor in the patient data, obtain the importance degree of each risk factor; according to the importance degree of each risk factor, screen out all important risk factors.

[0041] It should be noted that the key risk factors for evaluating each risk level obtained in step S202 are indicators for one risk level. Since there are multiple analysis levels for the evaluation results of patients, and the more the number of patients with the corresponding risk factor in the patient data, the more likely the risk factor will cause oral mucositis, that is, the more important the risk factor. Therefore, it is also necessary to obtain the importance degree of each risk factor according to the impact degree of each risk factor on all evaluated risk levels, combined with the number of patients with the corresponding risk factor in the patient data, and further screen out all important risk factors.

[0042] Specifically, according to the impact degree of each risk factor on all evaluated risk levels, combined with the number of patients with the corresponding risk factor in the patient data, obtain the importance degree of each risk factor; The impact degree of each risk factor on all evaluated risk levels is positively correlated with the importance degree of each risk factor; the number of patients with each risk factor is positively correlated with the importance degree of each risk factor; the difference in the impact degree of each risk factor on different risk levels is negatively correlated with the importance degree of each risk factor; In a specific embodiment of the present invention, its calculation formula is: In the formula, Indicates the importance level of the th risk factor; Indicates the degree of influence of the th risk factor on the evaluation of the th risk level; Indicates the number of risk levels; Indicates the mean value of the degree of influence of the th risk factor on the evaluation of all risk levels; Indicates absolute value operation; Indicates the exponential function with the natural constant as the base; in this embodiment, model is used to present the inverse proportional relationship and normalization processing, is the input of the model, and the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0043] It should be noted that, the larger the value of, the greater the degree of influence of the th risk factor on the evaluation of all risk levels; the larger the value of, it indicates that the number of patients with the th risk factor is larger. Therefore, and the larger the value of, the more important the th risk factor; the larger the value of, it indicates that the degree of influence of the th risk factor on the evaluation of each risk level is more stable, that is, the th risk factor is more important.

[0044] Furthermore, a threshold value of importance level , the specific value of can be set by itself according to the actual situation, and there is no rigid requirement in this embodiment. In this embodiment, it is described with ; when the importance level of the risk factor is greater than , the risk factor is recorded as an important risk factor.

[0045] Thus, all important risk factors are obtained.

[0046] Step S204: Train an oral mucositis risk prediction model according to the key risk factors and important risk factors of each risk level; according to the prediction model, predict the oral mucositis level of the visiting patients after chemotherapy, and provide care for the patients.

[0047] It should be noted that by obtaining the key risk factors and important risk factors of each risk level through steps S202 and S203 respectively, the target risk factors can be obtained according to the key risk factors and important risk factors of each risk level; the target risk factors are the risk factors that play a decisive role in evaluating the risk level. Therefore, the oral mucositis risk prediction model can be trained according to the target risk factors to accurately predict the oral mucositis level of patients who will undergo chemotherapy after chemotherapy. Further, corresponding care can be provided to patients before chemotherapy based on the predicted level, so as to reduce the incidence of oral mucositis complications and relieve the pain of patients.

[0048] Optionally, in a specific embodiment of the present invention, the set composed of the key risk factors of all risk levels is denoted as the key factor set, and the set composed of all important risk factors is denoted as the important factor set; the risk factors in the union of the key factor set and the important factor set are denoted as target risk factors; Further, the set composed of all target risk factors is used as the training set of the first random forest algorithm, and the set composed of all non-target risk factors is used as the training set of the second random forest algorithm; a weight greater than 0.5 and less than 1 is preset , The specific value can be set according to the actual situation and is not rigidly required in this embodiment. In this embodiment, it is described with ; Let the random forest algorithm randomly select risk factors from the training set of the first random forest algorithm with a probability of , and randomly select risk factors from the training set of the second random forest algorithm with a probability of to train the oral mucositis risk prediction model. Since the random forest algorithm is a well-known existing technology, it will not be elaborated in this embodiment.

[0049] So far, the oral mucositis risk prediction model in step S2 is obtained. Subsequently, the oral mucositis level of patients after chemotherapy can be predicted through the oral mucositis risk prediction model, and the same prevention and care can be provided for the patients based on this.

[0050] Figure 2 It is a flowchart for obtaining the oral mucositis risk prediction model.

[0051] Embodiment 3: Embodiment 3 shows the specific implementation steps of step S3: It should be noted that after obtaining the oral mucositis risk prediction model, the oral mucositis grade of patients who will undergo chemotherapy can be accurately predicted through the oral mucositis risk prediction model. Thus, according to the predicted oral mucositis grade, corresponding nursing can be provided to the patients in advance, so as to reduce the incidence of oral mucositis complications and relieve the pain of the patients.

[0052] Optionally, in an embodiment of the present invention, the risk factors of the patient are input into the oral mucositis risk prediction model to obtain the oral mucositis grade of the patient after chemotherapy.

[0053] For patients with a predicted oral mucositis grade of one, diet nursing is required for the patients; For patients with a predicted oral mucositis grade of two, diet nursing and physical nursing are required for the patients; For patients with a predicted oral mucositis grade of three, diet nursing, physical nursing and drug nursing are required for the patients; The diet nursing includes, but is not limited to: providing the patient with soft, small, and easy-to-swallow foods, while avoiding the patient from eating acidic and spicy foods, and finally providing the patient with a meal plan of eating small meals frequently; The physical nursing includes, but is not limited to: cryotherapy and low-intensity laser therapy; The drug nursing includes, but is not limited to: making the patient take non-steroidal anti-inflammatory drugs.

[0054] It should be noted that since physical nursing will produce side effects such as swelling and edema; while drug nursing has side effects on the digestive system of the patient. Therefore, in order to relieve the pain of the patient, corresponding nursing should be provided to the patient in advance according to the predicted oral mucositis grade of the patient.

[0055] So far, this embodiment is completed.

[0056] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a risk prediction model for oral mucositis care, characterized in that: The method comprises the following steps: Obtaining information about all patients who visit the hospital, including the patient's risk level and risk factors; According to the presence of each risk factor in the patient at each risk level, the patient is marked to obtain the patient marking sequence of each risk factor at each risk level; the correlation between the patient marking sequences of different risk factors at the same risk level is obtained; according to the correlation, the relevant risk factors of the risk factors at each risk level are screened out; according to the correlation between different risk factors at the same risk level, combined with the difference between the risk factors at the risk level and the relevant risk factors of the risk factors, the degree of influence of the risk factors on the assessed risk level is obtained; according to the degree of influence of the risk factors on the assessed risk level, the key risk factors of each risk level are screened out; According to the influence of each risk factor on all assessed risk levels, combined with the number of patients with corresponding risk factors in the patient data, the importance of each risk factor is obtained; according to the importance of each risk factor, all important risk factors are screened out; According to the key risk factors and important risk factors of each risk level, an oral mucositis risk prediction model is trained; according to the prediction model, the oral mucositis level of the patient after chemotherapy is predicted, and care is provided for the patient.

2. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The method of marking the patient according to the presence of each risk factor in the patient at each risk level and obtaining the patient marking sequence of each risk factor at each risk level includes: For any risk factor, among all the patients at each risk level, the patients with the risk factor are marked as , patients without the risk factors were labeled ; Obtain a patient tag set corresponding to the risk factors at each risk level, sort the elements in the patient tag set corresponding to the risk factors at each risk level according to the time of information entry, and obtain a patient tag sequence corresponding to the risk factors at each risk level; and are preset non-negative marker values, and Greater than .

3. The method for constructing a risk prediction model for oral mucositis care according to claim 2, characterized in that: Tagged Value 1, mark value is 0.

4. The method for constructing a risk prediction model for oral mucositis care according to claim 2, characterized in that: The specific method of obtaining the correlation between patient marker sequences of different risk factors at the same risk level includes: Obtaining the difference between the Pearson correlation coefficient between the patient marker sequences of different risk factors at the same risk level and the sum of the sequence marker values; obtaining the correlation between the patient marker sequences of different risk factors at the same risk level according to the difference between the Pearson correlation coefficient between the patient marker sequences of different risk factors at the same risk level and the sum of the sequence marker values; The absolute value of the Pearson correlation coefficient between patient marker sequences of different risk factors at the same risk level is positively correlated with the correlation between patient marker sequences of different risk factors at the same risk level; the difference in the sum of marker values ​​of patient marker sequences of different risk factors at the same risk level is negatively correlated with the correlation between patient marker sequences of different risk factors at the same risk level.

5. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The method of screening out the relevant risk factors of the risk factors at each risk level according to the correlation includes: Preset a threshold for the number of relevant risk factors , among the correlations between patient marker sequences of different risk factors at the same risk level, the one with the largest correlation risk factors as related risk factors of risk factors under this risk level.

6. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The method of obtaining the influence of risk factors on the risk level assessment based on the correlation between different risk factors at the same risk level and the difference between risk factors at the risk level and the risk factors related to the risk factors is as follows: For the degree of influence of any risk factor on the assessment of any risk level, obtain the difference between the risk factor and the related risk factors of the risk factor at the same risk level; The correlation between different risk factors at the same risk level is positively correlated with the degree of influence of risk factors on the assessed risk level; the difference between risk factors and the related risk factors of risk factors at the same risk level is positively correlated or negatively correlated with the degree of influence of risk factors on the assessed risk level.

7. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The key risk factors for each risk level are screened out according to the degree of influence of the risk factors on the risk level assessment, including the following specific methods: Preset a threshold for the impact of risk factors under a single risk , when the impact of any risk factor on the assessment of any risk level is greater than When the risk factor is identified, the risk factor is recorded as the key risk factor for assessing the risk level.

8. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The importance of each risk factor is obtained according to the influence of each risk factor on all assessed risk levels, combined with the number of patients with corresponding risk factors in the patient data, including the following specific methods: The degree of influence of each risk factor on the assessment of all risk levels is positively correlated with the importance of each risk factor; the number of patients with each risk factor is positively correlated with the importance of each risk factor; the difference in the degree of influence of each risk factor on the assessment of different risk levels is negatively correlated with the importance of each risk factor.

9. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The specific method of screening out all important risk factors according to the importance of each risk factor is as follows: Preset an importance threshold ; When the importance of risk factors is greater than When the risk factor is significant, it is recorded as a significant risk factor.

10. The method for constructing a risk prediction model for oral mucositis care according to claim 1, characterized in that: The specific method of training the oral mucositis risk prediction model includes: The set of key risk factors of all risk levels is recorded as the key factor set, and the set of all important risk factors is recorded as the important factor set; the risk factors in the union of the key factor set and the important factor set are recorded as the target risk factors; The set consisting of all target risk factors is used as the first random forest algorithm training set, and the set consisting of all non-target risk factors is used as the second random forest algorithm training set; preset a weight adjustment greater than 0.5 and less than 1 ; Let the random forest algorithm be The probability of randomly selecting risk factors from the No. 1 random forest algorithm training set is The probability of randomly selecting risk factors from the No. 2 random forest algorithm training set is used to train the oral mucositis risk prediction model.

Images