CN108269607B - Tumor patient nutrition screening method and system - Google Patents
Tumor patient nutrition screening method and system Download PDFInfo
- Publication number
- CN108269607B CN108269607B CN201611248920.0A CN201611248920A CN108269607B CN 108269607 B CN108269607 B CN 108269607B CN 201611248920 A CN201611248920 A CN 201611248920A CN 108269607 B CN108269607 B CN 108269607B
- Authority
- CN
- China
- Prior art keywords
- medical record
- electronic medical
- key
- record data
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
Abstract
The application provides a method and a system for screening nutrition of a tumor patient, wherein the method comprises the following steps: acquiring electronic medical record data to be screened, wherein the electronic medical record data comprises an identifier of a user; extracting a key field set from the electronic medical record data according to a preset extraction rule; and determining the nutritional state to which the user belongs according to the number and/or type of the key fields included in the key field set. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
Description
Technical Field
The application relates to the field of medical diagnosis, in particular to a method and a system for screening nutrition of tumor patients.
Background
Researches show that most of tumor patients have nutrition problems, and the nutrition problems can aggravate the disease conditions of the tumor patients and influence the treatment effect of the patients. In recent years, with the increase of tumor patients, how to diagnose the nutritional problem of the tumor patients becomes a problem which people are increasingly concerned about and need to solve urgently.
At present, nutritional problems of tumor patients are usually diagnosed by a clinical dietician with professional skills. However, since the number of clinical dieticians is seriously insufficient and it takes much time to diagnose each patient, the nutritional problems of the tumor patients cannot be diagnosed in time.
The diagnosis method for the nutrition problems of the tumor patients wastes a large amount of cost and time, has low working efficiency and influences the rehabilitation of the tumor patients.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present application is to provide a method for screening nutrition of a tumor patient, which is to quickly determine a nutrition state of a user by screening key fields in electronic case data of the user, thereby saving costs for diagnosing nutrition problems of the tumor patient, saving time, and improving accuracy and efficiency of diagnosis.
A second object of the present application is to propose a tumor patient nutrition screening system.
In order to achieve the above object, a first aspect of the embodiments of the present application provides a method for screening tumor patients for nutrition, comprising: acquiring electronic medical record data to be screened, wherein the electronic medical record data comprises an identifier of a user; extracting a key field set from the electronic medical record data according to a preset extraction rule; and determining the nutritional state to which the user belongs according to the number and/or type of the key fields included in the key field set.
In a possible implementation form of the first aspect, the extracting, according to a preset extraction rule, a set of key fields from the electronic medical record data includes:
extracting a field set comprising the key information from the electronic medical record data of the user according to preset key information, wherein the key information is related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators.
In another possible implementation form of the first aspect, the nutritional status comprises: risk and malnutrition exists;
the determining the nutritional status to which the user belongs according to the number and/or type of the key fields included in the set of key fields comprises:
judging whether at least one key field in the key field set is matched with a field in a first field set;
if so, determining that the nutritional state of the user is malnutrition;
otherwise, judging whether at least one key field in the key field set is matched with a field in a second field set;
if so, determining that the nutritional state of the user is a risk;
the first field set is a feature set corresponding to the malnutrition state, and the second field set is a feature set corresponding to the risk state.
In another possible implementation form of the first aspect, after determining whether at least one key field in the set of key fields matches a field in the first set of fields, the method further includes:
if not, determining the score and the weight value corresponding to each key field in the key field set respectively;
determining whether the score of the key field set is greater than a preset value or not according to the score and the weight value corresponding to each key field;
and if so, determining that the nutritional state of the user is malnutrition.
In another possible implementation form of the first aspect, before determining the score and the weight value respectively corresponding to each key field in the set of key fields, the method further includes:
acquiring electronic medical record data of a historical tumor patient, wherein the electronic medical record data comprises the nutritional state and corresponding characteristic state information of the tumor patient;
training the electronic medical record data, and determining scores and weight values respectively corresponding to the characteristic state information;
the determining the score and the weight value respectively corresponding to each key field in the key field set includes:
respectively determining characteristic state information matched with each key field;
and determining the score and the weight value respectively corresponding to each key field according to the determined matching characteristic state information.
In another possible implementation form of the first aspect, the electronic medical record of the historical oncology patient further includes attribute information of the oncology patient, and the electronic medical record data to be screened further includes attribute information of the user;
the determining the scores and the weighted values respectively corresponding to the characteristic state information includes:
determining corresponding scores and weight values of the characteristic state information under different attribute information respectively;
the determining the feature state information matched with the key fields respectively includes:
and respectively determining the characteristic state information matched with each key field according to the attribute information of the user.
In another possible implementation form of the first aspect, after the acquiring the electronic medical record data of the historic tumor patient, the method further includes:
and carrying out language analysis on the electronic medical record data, and determining the nutritional state and the corresponding characteristic state information of the tumor patient included in the electronic medical record data.
In another possible implementation form of the first aspect, after determining the nutritional status to which the user belongs, the method further includes:
and determining and outputting improvement suggestions corresponding to the nutritional state to which the user belongs by inquiring the nutritional state and improvement suggestion database.
According to the nutrition screening method for the tumor patient, electronic case data to be screened are firstly acquired, then the key field set is extracted from the electronic case data according to the preset extraction rule, and finally the nutrition state of the user is determined according to the number and/or the type of the key fields included in the key field set. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
To achieve the above object, a second aspect of the embodiments of the present application provides a tumor patient nutrition screening system, including: a communication interface, a processor, and a memory; the communication interface is used for acquiring electronic medical record data to be screened, and the electronic medical record data comprises an identifier of a user; the processor is used for extracting a key field set from the electronic medical record data according to a preset extraction rule; determining the nutritional state of the user according to the number and/or type of the key fields in the key field set; the memory is used for storing the execution program of the processor.
In a possible implementation form of the second aspect, the processor is specifically configured to:
extracting a field set comprising the key information from the electronic medical record data of the user according to preset key information, wherein the key information is related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators.
In another possible implementation form of the second aspect, the nutritional status comprises: risk and malnutrition exists;
the processor is further configured to:
judging whether at least one key field in the key field set is matched with a field in a first field set;
if so, determining that the nutritional state of the user is malnutrition;
otherwise, judging whether at least one key field in the key field set is matched with a field in a second field set;
if so, determining that the nutritional state of the user is a risk;
the first field set is a feature set corresponding to the malnutrition state, and the second field set is a feature set corresponding to the risk state.
In another possible implementation form of the second aspect, the processor is further configured to:
when any key field in the key field set is not matched with a field in the first field set, determining a score and a weight value respectively corresponding to each key field in the key field set;
determining whether the score of the key field set is greater than a preset value or not according to the score and the weight value corresponding to each key field;
and if so, determining that the nutritional state of the user is malnutrition.
In another possible implementation form of the second aspect, the communication interface is further configured to:
acquiring electronic medical record data of a historical tumor patient, wherein the electronic medical record data comprises the nutritional state and corresponding characteristic state information of the tumor patient;
the processor is further configured to train the electronic medical record data, and determine scores and weight values corresponding to the characteristic state information respectively;
respectively determining characteristic state information matched with each key field;
and determining the score and the weight value respectively corresponding to each key field according to the determined matching characteristic state information.
In another possible implementation form of the second aspect, the electronic medical record of the historical oncology patient further includes attribute information of the oncology patient, and the electronic medical record data to be screened further includes attribute information of the user;
the processor is further configured to:
determining corresponding scores and weight values of the characteristic state information under different attribute information respectively;
and respectively determining the characteristic state information matched with each key field according to the attribute information of the user.
In another possible implementation form of the second aspect, the processor is further configured to:
and carrying out language analysis on the electronic medical record data, and determining the nutritional state and the corresponding characteristic state information of the tumor patient included in the electronic medical record data.
In another possible implementation form of the second aspect, the tumor patient nutrition screening system further includes: a display component;
the processor is further configured to determine an improvement suggestion corresponding to the nutritional state to which the user belongs after querying the nutritional state and improvement suggestion database through the communication interface, and output the improvement suggestion corresponding to the nutritional state to which the user belongs through the display component.
The tumor patient nutrition screening system provided by this embodiment first acquires electronic case data to be screened, then extracts a key field set from the electronic case data according to a preset extraction rule, and finally determines a nutrition state to which a user belongs according to the number and/or type of key fields included in the key field set. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method of tumor patient nutrition screening according to one embodiment of the present application;
FIG. 2 is a flow chart of a method of tumor patient nutritional screening according to another embodiment of the present application;
FIG. 3 is a schematic diagram of a tumor patient nutrition screening system according to one embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The embodiment of the application mainly aims at the diagnosis of the nutrition problems of the existing tumor patients, and generally depends on a clinical dietician with professional skills, so that a large amount of cost and time are wasted, the working efficiency is low, and the rehabilitation of the tumor patients is influenced.
Specifically, the method for screening the nutrition of the tumor patient can acquire the characteristics corresponding to the risk state or the malnutrition state by using the electronic medical record data of the historical tumor patient, and then compare the characteristics acquired from the electronic medical record data of the tumor patient to be screened with the characteristics to determine the nutrition state of the tumor patient.
The tumor patient nutrition screening method and system according to the embodiments of the present application will be described with reference to the drawings.
FIG. 1 is a flow chart of a method for nutritional screening of a tumor patient according to one embodiment of the present application.
As shown in fig. 1, the method for screening tumor patients for nutrition comprises the following steps:
In the nutrition screening method for tumor patients provided by this embodiment, the main implementation body is the nutrition screening system for tumor patients provided by this embodiment, and the system can be configured in a central data management center of a hospital or a central data management center of a oncology department of a hospital, etc., and the central data management center manages the electronic medical record data of each user in a unified manner, so that medical staff can call up related data to assist diagnosis and treatment in a diagnosis process as needed.
The user identifier may be any identifier which can uniquely identify the user from other users, such as the name, the identification number, the medical insurance card number, the patient number and the like of the tumor patient.
And 102, extracting a key field set from the electronic medical record data according to a preset extraction rule.
The preset extraction rule is a method for extracting a key field set from an electronic medical record database, and specifically may include the type, number, and the like of extracted key fields.
It can be understood that, during the treatment of the user, the medical staff can record various symptoms or feelings of the user into the electronic medical record of the central data management center, so that when diagnosing the nutritional problem of the tumor patient, the electronic medical record data of the user can be called through the identification of the user, and key fields are extracted from the electronic medical record data to determine the nutritional state of the user.
For example, when a tumor patient has nutritional problems, the patients usually have problems such as nausea, dizziness, inappetence, defecation and exhaustion stopping, progressive dysphagia, physical condition ECOG score of more than or equal to 3 points, emaciation, yellow stain (yellow skin mucous membrane), pale complexion, edema of both lower limbs, and body mass index BMI of less than or equal to 18.5kg/m2(kilogram/square meter), weight loss of more than or equal to 5kg (kilogram), albumin of less than or equal to 35g/L (gram/liter), weight loss of 2kg, dyscrasia, and the like. When the nutritional status of the tumor patient is diagnosed, the fields related to the symptoms can be extracted from the electronic medical record of the patient by means of field matching.
In specific implementation, the key information to be screened can be preset according to symptoms, signs, hematological variables, biochemical indexes and the like corresponding to each nutritional state, and after the electronic medical record data to be screened is acquired, a field set comprising the key information can be extracted from a medical record database of a user.
Wherein the key information may be related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators. In particular, the symptoms are the self experience and feeling of the physiological dysfunction of the organism after the patient suffers from the disease, such as nausea, dizziness, progressive dysphagia and the like; signs are abnormal changes found by a physician while examining a patient, e.g., body temperature, pulse, weight, blood pressure, etc.; hematological variables are variables associated with blood and hematopoietic tissues, e.g., total white blood cells, total platelets, etc.; the biochemical index is an index of liver function, kidney function, inflammation, etc., for example, a creatine index, uric acid index, albumin index, prealbumin index, C-reactive protein index, etc.
For example, if the key information related to physical signs and biochemical indicators is preset and extracted, the acquired electronic medical record data of the user to be screened includes weight loss and body mass index BMI less than or equal to 18.5kg/m2Meanwhile, the weight is reduced by more than or equal to 5kg, and information such as nausea, dizziness and the like can be extracted from the electronic medical record data of the user, wherein the information comprises the following information: weight loss and body mass index BMI less than or equal to 18.5kg/m2And meanwhile, the weight is reduced by more than or equal to 5kg and other fields are used as a key field set corresponding to the current nutritional state of the patient.
And 103, determining the nutritional state of the user according to the number and/or the type of the key fields included in the key field set.
The nutritional status to which the user belongs may include an existing risk status and a malnutrition status.
In specific implementation, the feature set corresponding to the malnutrition state and the feature set corresponding to the risk state can be preset, after a key field set is extracted from electronic medical record data of a user, the key fields in the key field set can be matched with the feature set corresponding to the malnutrition state and the fields in the feature set corresponding to the risk state, and the nutrition state to which the user belongs is determined according to the number and/or the type of the matched key fields.
The specific process can comprise the following steps:
step 103a, determining whether at least one key field in the key field set matches with a field in the first field set.
Wherein the first field set is a set of characteristics corresponding to malnutrition state, such as BMI ≦ 18.5kg/m2And the weight is reduced at the same time, the weight is reduced by more than or equal to 5kg, the albumin is less than or equal to 35g/L, the weight is reduced at the same time, and the like.
And step 103b, if so, determining that the nutritional state of the user is malnutrition.
Step 103c, otherwise, judging whether at least one key field in the key field set is matched with the field in the second field set.
The second field set is a feature set corresponding to the risk existence state, and may include fields such as yellow stain, pale skin color, navicular abdomen, and the like.
And step 103d, if so, determining that the nutritional state to which the user belongs is risk.
For example, assume that a malnourished state corresponds to a feature set of: BMI is less than or equal to 18.5kg/m2Simultaneously, the weight is reduced by more than or equal to 5kg, the albumin is reduced by less than or equal to 35g/L, the weight is reduced, the muscle mass is lower than the normal value range, the weight is reduced by 2kg, and the dyscrasia is poor; the set of features corresponding to the presence of risk states is: stopping defecation and exhausting, performing deglutition difficulty, grading the physical condition ECOG to be more than or equal to 3 points, emaciation, yellow dyeing, pale skin color, scaphoid abdomen and edema of both lower limbs.
Then, in the diagnosis process, if the key field set extracted from the electronic medical record data of the user is that the weight is reduced by 7kg, and the BMI is 19kg/m2", it may be determined that" weight loss 7kg "in the set of key fields matches" weight loss ≧ 5kg "in the feature set corresponding to the malnutrition status, it may be determined that the user belongs to the malnutrition status. If the key field set extracted from the electronic medical record data of the user is 'pale skin color, edema of both lower limbs and physical condition ECOG score of 2', any key field in the key field set can be determined to be in the feature set corresponding to the malnutrition stateAny field is not matched, the key field in the key field set can be compared with the field in the feature set corresponding to the risk state, and the user can be determined to belong to the risk state due to the fact that the 'skin color is pale and edema of two lower limbs' is matched with the field in the feature set corresponding to the risk state.
In addition, it is understood that, after determining the nutritional status to which the user belongs, the tumor patient nutrition screening system may further provide the user with an improvement suggestion corresponding to the nutritional status, that is, in this embodiment, after determining the nutritional status to which the user belongs, the method may further include:
and determining and outputting improvement suggestions corresponding to the nutritional state to which the user belongs by inquiring the nutritional state and improvement suggestion database.
In specific implementation, a mapping relation between the nutrition state and the improvement suggestion can be preset, various nutrition states of a user and corresponding improvement suggestions, corresponding feature sets in each nutrition state and the improvement suggestions corresponding to different fields are stored in an improvement suggestion database, and after the nutrition state of the user is determined, the improvement suggestion database can be inquired to determine and output the improvement suggestions corresponding to the nutrition state, so that medical staff can improve the nutrition problem of a tumor patient according to the improvement suggestions.
After the improvement suggestion corresponding to the nutrition state to which the user belongs is determined, the improvement suggestion can be displayed through a display screen, or the improvement suggestion can be printed in a standard report form through an associated printer, which is not limited herein.
According to the nutrition screening method for the tumor patient, electronic case data to be screened are firstly acquired, then the key field set is extracted from the electronic case data according to the preset extraction rule, and finally the nutrition state of the user is determined according to the number and/or the type of the key fields included in the key field set. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
Through the analysis, the key fields in the key field set extracted from the electronic case data of the user can be compared with the fields in the feature set corresponding to each nutrition state one by one to determine the nutrition state of the user. In a possible implementation form of the present application, if it cannot be accurately determined whether a patient has malnutrition according to any single symptom appearing in a tumor patient, then comprehensive evaluation can be performed according to various symptoms appearing in the patient to determine whether the patient has malnutrition problem, so as to accurately determine the nutrition status of the user, which is specifically described below with reference to fig. 2.
FIG. 2 is a flow chart of a method of tumor patient nutrition screening according to another embodiment of the present application.
As shown in fig. 2, the method for screening tumor patients for nutrition provided in this embodiment includes the following steps:
Wherein the first field set is a set of characteristics corresponding to the malnutrition status.
It can be understood that, in a central data management center of a hospital or a oncology department, electronic medical record data of each user may be stored, where the electronic medical record data includes a determined nutritional state of a tumor patient and a corresponding feature set. That is, before step 205, it may further include:
acquiring electronic medical record data of a historical tumor patient, wherein the electronic medical record data comprises the nutritional state and corresponding characteristic state information of the tumor patient;
and training the electronic medical record data, and determining scores and weighted values respectively corresponding to the characteristic state information.
The characteristic state information may be characteristic state information in a characteristic set corresponding to the malnutrition state, and may include, for example, information on weight change, appetite, diet, eating, ECOG score, disease diagnosis, edema, and the like.
Specifically, because different medical personnel's parlance is different, therefore, when different medical personnel diagnose the same patient, the language in the electronic medical record data of record probably is not completely unanimous, in order to improve the accuracy of the analysis of the electronic medical record data, can carry out language analysis to the electronic medical record data earlier to the natural language in the accurate discernment electronic medical record, then through characteristic extraction, extract tumour patient's nutrition state and the characteristic state information that corresponds from the electronic medical record data.
For example, after the electronic case data of the tumor patient is read, the functions of the composition components of each sentence in the electronic case data are determined by applying the syntax and other knowledge of the natural language to establish a data structure and obtain the meaning of each sentence, so that the nutritional state and the corresponding characteristic state information of the tumor patient in the electronic case are accurately identified, and the tumor nutrition problem database is gradually established and perfected by effectively learning and memorizing.
After the nutritional states and the corresponding characteristic state information of the tumor patients in the historical electronic medical record data are obtained, the electronic medical record data can be trained through machine learning, boosting algorithm and the like based on an artificial intelligence technology, a weight relation model of the characteristic state information corresponding to each nutritional state is constructed, a complex classifier is formed, and the weight relation model is continuously optimized, so that the corresponding model of each nutritional state and the characteristic state information, and the value and the weight value of each characteristic state information in each nutritional state are determined. And then after the electronic medical record to be screened is obtained, the nutritional state to which the user belongs can be determined according to the key field set in the electronic medical record data by combining the determined corresponding models of the nutritional state and the characteristic state information and the scores and the weighted values of the characteristic state information in different nutritional states.
Correspondingly, step 205 may specifically include:
respectively determining characteristic state information matched with each key field;
and determining the score and the weight value corresponding to each key field according to the determined matching characteristic state information.
In specific implementation, after the scores and the weight values corresponding to the characteristic state information corresponding to the malnutrition state are determined, if a key field extracted from the electronic medical record data to be screened is matched with certain characteristic state information, the scores and the weight values corresponding to the matched key field can be determined according to the scores and the weight values corresponding to the characteristic state information, so as to determine the score of a key field set, and if the score is greater than a preset value, it can be determined that a user corresponding to the electronic medical record data belongs to the malnutrition state.
When the preset value is that the user belongs to a malnutrition state, the score of the key field set can be specifically set according to the score and the weighted value of each characteristic state information obtained by training the electronic medical record data of the historical tumor patient.
For example, it is assumed that the scores and the weight values corresponding to the characteristic status information included in the malnutrition status are obtained through training of the electronic medical record data of the historical oncology patients. Specifically, the weight value corresponding to the "weight change condition" is 0.5, wherein the score corresponding to the "weight reduction of 5 kg" is 10.0 points, and the score corresponding to the "weight reduction of 4 kg" is 9.0 points; the weight value corresponding to the 'appetite situation' is 0.2, wherein the score corresponding to the 'no appetite' is 10.0 points, and the score corresponding to the 'appetite reduction' is 9.0 points; the "ECOG score" corresponds to a weight value of 0.3, wherein the "ECOG score of 3" corresponds to a score of 10.0, and the "ECOG score of 2" corresponds to a score of 9.0. If the key fields extracted from the electronic medical record data to be screened of a certain patient are 'weight loss 4 kg' and 'inappetence', the key fields are not matched with the fields in the first field set, and various symptoms of the patient can be comprehensively evaluated to determine whether the patient has malnutrition problems. Since "weight loss 4 kg" is related to the characteristic state information "weight change condition," anorexia "is related to the characteristic state information" appetite condition, "and according to the scores and weights respectively corresponding to the characteristic state information" weight change condition "and" appetite condition, "it can be determined that the weight corresponding to the" weight change condition "is 0.5, the score corresponding to the" weight loss 4kg "is 9.0, the weight corresponding to the" appetite condition "is 0.2, the score corresponding to the" anorexia "is 10.0, and further it is determined that the score of the key field set is 6.5, and if the preset value is 6.0, the score is greater than the preset value, and it can be determined that the user corresponding to the electronic medical record data belongs to the malnutrition state.
It should be noted that the same feature status information may correspond to different scores and weight values for different users. For example, if the weight of the user is reduced by 5kg, the influence on the elderly and adults is different, and the biochemical index health reference values of the males and females are also different, in the embodiment of the present application, the nutritional status of the user may be determined according to the information of the age, sex, and the like of the user.
That is, before step 205, when the electronic medical record data of the historical oncology patient is trained to determine the score and the weight value corresponding to the characteristic state information, it may also be determined that the characteristic state information corresponds to the score and the weight value under different attribute information. Correspondingly, when determining the score and the weight value respectively corresponding to each key field in the key field set extracted from the electronic medical record data to be screened, the feature state information matched with each key field can be determined according to the attribute information of the user, the score and the weight value respectively corresponding to each key field can be determined according to the determined matched feature state information, and then the score of the key field set is determined, so that whether the nutritional state of the user belongs to malnutrition or not is determined.
The electronic medical record data of the historical tumor patients and the electronic medical record data to be screened both include attribute information of the tumor patients, such as sex, age, height, weight, and the like.
For example, if the user is an adult male, the weight value corresponding to the "weight change condition" is 0.5, wherein the score corresponding to the "weight reduction of 5 kg" is 10.0 points, and the score corresponding to the "weight reduction of 4 kg" is 9.0 points; the weight value corresponding to the 'appetite situation' is 0.2, wherein the score corresponding to the 'no appetite' is 10.0 points, and the score corresponding to the 'appetite reduction' is 9.0 points; the 'ECOG score' corresponds to a weight value of 0.3, wherein the 'ECOG score equal to 3 points' corresponds to a score of 10.0, and the 'ECOG score equal to 2 points' corresponds to a score of 9.0; when the user is an adult female, the weight value corresponding to the weight change condition is 0.5, wherein the score corresponding to the weight reduction of 5kg is 8.0, and the score corresponding to the weight reduction of 4kg is 7.0; the weight value corresponding to the 'appetite situation' is 0.2, wherein the score corresponding to the 'no appetite' is 8.0 points, and the score corresponding to the 'appetite reduction' is 7.0 points; the "ECOG score" corresponds to a weight value of 0.3, wherein the "ECOG score of 3" corresponds to a score of 8.0, and the "ECOG score of 2" corresponds to a score of 7.0. If the key fields extracted from the electronic medical record data of a certain adult female to be screened are 'weight loss 4 kg' and 'inappetence', the key fields do not match with the fields in the first field set, and various symptoms of the patient can be comprehensively evaluated to determine whether the patient has malnutrition problems. Because "weight loss 4 kg" is related to the characteristic state information "weight change condition", and "anorexia" is related to the characteristic state information "appetite condition", and according to the scores and weights respectively corresponding to the characteristic state information "weight change condition" and "appetite condition" when the user is an adult female, the weight corresponding to the "weight change condition" can be determined to be 0.5, the score corresponding to the "weight loss 4 kg" is 7.0, the weight corresponding to the "appetite condition" is 0.2, and the score corresponding to the "anorexia" is 8.0, and further the score of the key field set is determined to be 5.1, and if the preset value is 5.5, the score is smaller than the preset value, and the user corresponding to the electronic medical record data can be determined not to belong to a malnutrition state, so that whether the nutrition state to which the user belongs to is in another state can be continuously determined.
And the second field set is a feature set corresponding to the risk state.
And 208, if so, determining that the nutritional state of the user is a risk.
Specifically, if the score of the key field set is less than or equal to a preset value, it may be determined whether the nutritional status of the user is a risk status.
It can be understood that, when it is determined whether the nutritional state to which the user belongs is a risk state, the scores of the key fields may be determined according to the scores and the weight values respectively corresponding to the feature state information corresponding to the risk state by matching the key fields with the feature state information corresponding to the risk state, so as to determine whether the user belongs to the risk state.
In the method for screening tumor patients, after electronic medical record data to be screened is acquired, a key field set is extracted from the electronic medical record data, whether the key field set is matched with fields in a first field set is judged, if not, scores and weight values corresponding to key fields in the key field set are determined to determine scores of the key field set, whether the nutritional state to which the user belongs is a malnutrition state is determined according to the scores, and if not, whether the key field set is matched with fields in a second field set is judged, so that whether the nutritional state to which the user belongs is a risk state is determined. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user and scoring the key field set extracted from the electronic case data of the user according to the feature set corresponding to each nutritional state, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
In order to realize the embodiment, the application also provides a nutrition screening system for the tumor patients. FIG. 3 is a schematic diagram of a tumor patient nutrition screening system according to one embodiment of the present application.
As shown in fig. 3, the tumor patient nutrition screening system 30 includes: a communication interface 31, a processor 32, and a memory 33;
the communication interface 31 is configured to acquire electronic medical record data to be screened, where the electronic medical record data includes an identifier of a user;
the processor 32 is configured to extract a key field set from the electronic medical record data according to a preset extraction rule; determining the nutritional state of the user according to the number and/or type of the key fields in the key field set;
the memory 33 is used for storing the execution program of the processor.
Further, in a possible implementation form of the embodiment of the present application, the processor 32 is specifically configured to:
extracting a field set comprising the key information from the electronic medical record data of the user according to preset key information, wherein the key information is related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators.
In another possible implementation form of the embodiment of the present application, the nutritional status includes: risk and malnutrition exists;
accordingly, the processor 32 is further configured to:
judging whether at least one key field in the key field set is matched with a field in a first field set;
if so, determining that the nutritional state of the user is malnutrition;
otherwise, judging whether at least one key field in the key field set is matched with a field in a second field set;
if so, determining that the nutritional state of the user is a risk;
the first field set is a feature set corresponding to the malnutrition state, and the second field set is a feature set corresponding to the risk state.
In another possible implementation form of the embodiment of the present application, the processor 32 is further configured to:
when any key field in the key field set is not matched with a field in the first field set, determining a score and a weight value respectively corresponding to each key field in the key field set;
determining whether the score of the key field set is greater than a preset value or not according to the score and the weight value corresponding to each key field;
and if so, determining that the nutritional state of the user is malnutrition.
Further, the communication interface 31 is further configured to:
acquiring electronic medical record data of a historical tumor patient, wherein the electronic medical record data comprises the nutritional state and corresponding characteristic state information of the tumor patient;
correspondingly, the processor 32 is further configured to train the electronic medical record data, and determine scores and weight values corresponding to the characteristic state information respectively;
respectively determining characteristic state information matched with each key field;
and determining the score and the weight value respectively corresponding to each key field according to the determined matching characteristic state information.
In another possible implementation form of the embodiment of the present application, the electronic medical record of the historical oncology patient further includes attribute information of the oncology patient, and the electronic medical record data to be screened further includes attribute information of the user;
accordingly, the processor 32 is further configured to:
determining corresponding scores and weight values of the characteristic state information under different attribute information respectively;
and respectively determining the characteristic state information matched with each key field according to the attribute information of the user.
In another possible implementation form of the embodiment of the present application, the processor 32 is further configured to:
and carrying out language analysis on the electronic medical record data, and determining the nutritional state and the corresponding characteristic state information of the tumor patient included in the electronic medical record data.
In another possible implementation form of the embodiment of the present application, the tumor patient nutrition screening system 30 further includes: a display assembly 34;
the processor 32 is further configured to determine an improvement suggestion corresponding to the nutritional status of the user after querying the nutritional status and improvement suggestion database through the communication interface 31, and output the improvement suggestion corresponding to the nutritional status of the user through the display component 34.
It should be noted that the foregoing explanation of the embodiment of the tumor patient nutrition screening method is also applicable to the tumor patient nutrition screening system of this embodiment, and is not repeated herein.
The tumor patient nutrition screening system provided by this embodiment first acquires electronic case data to be screened, then extracts a key field set from the electronic case data according to a preset extraction rule, and finally determines a nutrition state to which a user belongs according to the number and/or type of key fields included in the key field set. Therefore, the method and the device realize that the nutritional state of the user is quickly determined by screening the key fields in the electronic case data of the user, save the cost for diagnosing the nutritional problems of the tumor patients, save the time and improve the accuracy and efficiency of diagnosis.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (14)
1. A method for screening for nutrition in a patient with a tumor, comprising the steps of:
acquiring electronic medical record data to be screened, wherein the electronic medical record data to be screened comprises an identifier of a user;
extracting a key field set from the electronic medical record data to be screened according to a preset extraction rule;
judging whether a key field set is matched with fields in a first field set or not, if not, determining scores and weight values corresponding to all key fields in the key field set respectively to determine scores of the key field set, wherein electronic medical record data of historical oncology patients are obtained, the electronic medical record data of the historical oncology patients comprise nutrition states and corresponding characteristic state information of the oncology patients, the electronic medical record data of the historical oncology patients are trained, the scores and the weight values corresponding to the characteristic state information respectively are determined, the characteristic state information matched with all the key fields is determined respectively, and the scores and the weight values corresponding to all the key fields are determined according to the determined matched characteristic state information;
and determining whether the nutritional state to which the user belongs is a malnutrition state according to the scores of the key field set.
2. The method as claimed in claim 1, wherein the extracting a set of key fields from the electronic medical record data to be screened according to a preset extraction rule comprises:
extracting a field set including the key information from the electronic medical record data to be screened of the user according to preset key information, wherein the key information is related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators.
3. The method of claim 1, after determining whether the nutritional status to which the user belongs is a non-nutritional status, further comprising:
judging whether at least one key field in the key field set is matched with a field in a second field set;
if so, determining that the nutritional state of the user is a risk;
the first field set is a feature set corresponding to the malnutrition state, and the second field set is a feature set corresponding to the risk state.
4. The method of claim 3, further comprising:
determining whether the score of the key field set is greater than a preset value or not according to the score and the weight value corresponding to each key field;
and if so, determining that the nutritional state of the user is malnutrition.
5. The method of claim 1, wherein the historical electronic medical record of the oncology patient further includes attribute information of the oncology patient, and the electronic medical record data to be screened further includes attribute information of the user;
the determining the scores and the weighted values respectively corresponding to the characteristic state information includes:
determining corresponding scores and weight values of the characteristic state information under different attribute information respectively;
the determining the feature state information matched with the key fields respectively includes:
and respectively determining the characteristic state information matched with each key field according to the attribute information of the user.
6. The method of claim 1, wherein after acquiring the electronic medical record data of the historic tumor patient, further comprising:
and performing language analysis on the electronic medical record data of the historical tumor patients, and determining the nutritional state and the corresponding characteristic state information of the tumor patients, which are included in the electronic medical record data of the historical tumor patients.
7. The method of any one of claims 1-6, wherein the determining the nutritional status to which the user belongs further comprises:
and determining and outputting improvement suggestions corresponding to the nutritional state to which the user belongs by inquiring the nutritional state and improvement suggestion database.
8. A tumor patient nutrition screening system, comprising: a communication interface, a processor, and a memory;
the communication interface is used for acquiring electronic medical record data to be screened, wherein the electronic medical record data to be screened comprises a user identifier and electronic medical record data of a historical tumor patient, and the electronic medical record data of the historical tumor patient comprises a nutrition state and corresponding characteristic state information of the tumor patient;
the processor is used for extracting a key field set from the electronic medical record data to be screened according to a preset extraction rule; judging whether a key field set is matched with fields in a first field set or not, if not, determining scores and weight values corresponding to all key fields in the key field set respectively to determine scores of the key field set, wherein electronic medical record data of historical tumor patients are trained, the scores and the weight values corresponding to the characteristic state information are determined respectively, the characteristic state information matched with all the key fields is determined respectively, and the scores and the weight values corresponding to all the key fields are determined according to the determined matched characteristic state information; determining whether the nutritional state of the user is a malnutrition state or not according to the scores of the key field set;
the memory is used for storing the execution program of the processor.
9. The system of claim 8, wherein the processor is specifically configured to:
extracting a field set including the key information from the electronic medical record data to be screened of the user according to preset key information, wherein the key information is related to at least one of the following information: symptoms, signs, hematological variables, and biochemical indicators.
10. The system of claim 8, wherein the processor is further configured to:
judging whether at least one key field in the key field set is matched with a field in a second field set;
if so, determining that the nutritional state of the user is a risk;
the first field set is a feature set corresponding to the malnutrition state, and the second field set is a feature set corresponding to the risk state.
11. The system of claim 10, wherein the processor is further configured to:
determining whether the score of the key field set is greater than a preset value or not according to the score and the weight value corresponding to each key field;
and if so, determining that the nutritional state of the user is malnutrition.
12. The system of claim 8, wherein the historical electronic medical record of the oncology patient further includes attribute information of the oncology patient, the electronic medical record data to be screened further includes attribute information of the user;
the processor is further configured to:
determining corresponding scores and weight values of the characteristic state information under different attribute information respectively;
and respectively determining the characteristic state information matched with each key field according to the attribute information of the user.
13. The system of claim 8, wherein the processor is further configured to:
and performing language analysis on the electronic medical record data of the historical tumor patients, and determining the nutritional state and the corresponding characteristic state information of the tumor patients, which are included in the electronic medical record data of the historical tumor patients.
14. The system of any of claims 8-13, further comprising: a display component;
the processor is further configured to determine an improvement suggestion corresponding to the nutritional state to which the user belongs after querying the nutritional state and improvement suggestion database through the communication interface, and output the improvement suggestion corresponding to the nutritional state to which the user belongs through the display component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248920.0A CN108269607B (en) | 2016-12-29 | 2016-12-29 | Tumor patient nutrition screening method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248920.0A CN108269607B (en) | 2016-12-29 | 2016-12-29 | Tumor patient nutrition screening method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108269607A CN108269607A (en) | 2018-07-10 |
| CN108269607B true CN108269607B (en) | 2020-11-24 |
Family
ID=62753959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611248920.0A Active CN108269607B (en) | 2016-12-29 | 2016-12-29 | Tumor patient nutrition screening method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108269607B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109597847B (en) * | 2018-11-09 | 2021-03-09 | 金色熊猫有限公司 | Medical data retrogradation method and device, storage medium and electronic terminal |
| CN110111872A (en) * | 2019-03-28 | 2019-08-09 | 北京康爱营养科技股份有限公司 | A kind of tumors of nutrients recommender system |
| CN112541064A (en) * | 2020-12-09 | 2021-03-23 | 联仁健康医疗大数据科技股份有限公司 | Health evaluation method and device, computer equipment and storage medium |
| CN112786130B (en) * | 2020-12-31 | 2022-12-09 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for acquiring main medical record diagnosis information |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201114139Y (en) * | 2007-08-31 | 2008-09-10 | 张春雨 | Medical terminal equipment and intelligent hospitalizing system for providing network hospitalizing service |
| CN102902881A (en) * | 2012-09-03 | 2013-01-30 | 广州百特侨光医疗用品有限公司 | Screening and computing system for parenteral nutrition |
| CN104361252A (en) * | 2014-11-27 | 2015-02-18 | 广州迈康智源医疗管理技术有限公司 | Clinical nutrition diagnosis and treatment simulation system |
| WO2014179594A3 (en) * | 2013-05-01 | 2015-10-29 | Francis Nathania Alexandra | System and method for monitoring administration of nutrition |
| CN105528529A (en) * | 2016-02-20 | 2016-04-27 | 成都中医药大学 | Data processing method of traditional Chinese medicine clinical skill evaluation system based on big data analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002019245A2 (en) * | 2000-08-30 | 2002-03-07 | Healtheheart, Inc. | Patient analysis and risk reduction system and associated methods |
-
2016
- 2016-12-29 CN CN201611248920.0A patent/CN108269607B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201114139Y (en) * | 2007-08-31 | 2008-09-10 | 张春雨 | Medical terminal equipment and intelligent hospitalizing system for providing network hospitalizing service |
| CN102902881A (en) * | 2012-09-03 | 2013-01-30 | 广州百特侨光医疗用品有限公司 | Screening and computing system for parenteral nutrition |
| WO2014179594A3 (en) * | 2013-05-01 | 2015-10-29 | Francis Nathania Alexandra | System and method for monitoring administration of nutrition |
| CN104361252A (en) * | 2014-11-27 | 2015-02-18 | 广州迈康智源医疗管理技术有限公司 | Clinical nutrition diagnosis and treatment simulation system |
| CN105528529A (en) * | 2016-02-20 | 2016-04-27 | 成都中医药大学 | Data processing method of traditional Chinese medicine clinical skill evaluation system based on big data analysis |
Non-Patent Citations (1)
| Title |
|---|
| 运用PG-SGA对常见恶性肿瘤患者营养状态的调查与分析;石华伟;《中国优秀硕士学位论文全文数据库》;20150315(第3期);第7-17页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108269607A (en) | 2018-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108269607B (en) | Tumor patient nutrition screening method and system | |
| Lekadir et al. | A convolutional neural network for automatic characterization of plaque composition in carotid ultrasound | |
| CN109741806B (en) | Auxiliary generation method and device for medical image diagnosis report | |
| CN109036502B (en) | Physical examination report health management method and system | |
| CN111563891B (en) | Disease prediction system based on color cognition | |
| CN111192682A (en) | Image exercise data processing method, system and storage medium | |
| CN106485085A (en) | A kind of intellect service robot health identification system and method | |
| CN108091391A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
| CN107705853A (en) | Clinical nutrition risk screening method and system | |
| Takeuchi et al. | Impact of reading habit on white matter structure: Cross-sectional and longitudinal analyses | |
| CN104462765A (en) | Three-dimensional visualization doctor-patient communication platform construction method and system | |
| Gharehbaghi et al. | An intelligent method for discrimination between aortic and pulmonary stenosis using phonocardiogram | |
| CN115024725A (en) | Tumor treatment aid decision-making system integrating psychological state multi-parameter detection | |
| US20140170741A1 (en) | Hepatic fibrosis detection apparatus and system | |
| CN202776267U (en) | Health maintaining and recuperating system in constitution theory of traditional Chinese medicine | |
| CN112002419B (en) | Disease auxiliary diagnosis system, equipment and storage medium based on clustering | |
| CN111582366B (en) | Image processing method, device and equipment | |
| TWI711050B (en) | Medical image recognizition device and medical image recognizition method | |
| Stolte et al. | DOMINO: Domain-aware model calibration in medical image segmentation | |
| CN110200599A (en) | A kind of pulse wave detecting method, terminal device and system | |
| Yang et al. | Functional Connectivity Based Classification for Autism Spectrum Disorder Using Spearman’s Rank Correlation | |
| CN112820370A (en) | Health management system based on tongue picture information | |
| Clark et al. | Detecting cardiac abnormalities with multi-lead ECG signals: A modular network approach | |
| Wong et al. | Identifying vital sign abnormality in acutely-ill patients | |
| Zhao et al. | Key symptoms selection for two major syndromes diagnosis of Chinese medicine in chronic hepatitis B |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 102200 1805, 18th floor, building 1, yard 8, Longyu North Street, Changping District, Beijing Applicant after: BEIJING KANCARE NUTRITION TECHNOLOGY Co.,Ltd. Address before: 102206 Building No. 29, life Garden Road, Changping District, Beijing, A101 Applicant before: BEIJING KANCARE NUTRITION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201029 Address after: 225300 B (South), 3 / F, building 16, standard plant, phase II, medical equipment zone, 900 Yaocheng Avenue, Taizhou City, Jiangsu Province Applicant after: Jiangsu Kangai Nutrition Technology Co.,Ltd. Address before: 102200 1805, 18th floor, building 1, yard 8, Longyu North Street, Changping District, Beijing Applicant before: BEIJING KANCARE NUTRITION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |