CN116168804B - Patient diet recommendation system and method based on HIS system - Google Patents

Patient diet recommendation system and method based on HIS system Download PDF

Info

Publication number
CN116168804B
CN116168804B CN202310430854.2A CN202310430854A CN116168804B CN 116168804 B CN116168804 B CN 116168804B CN 202310430854 A CN202310430854 A CN 202310430854A CN 116168804 B CN116168804 B CN 116168804B
Authority
CN
China
Prior art keywords
patient
result
disease
meal
diet
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
Application number
CN202310430854.2A
Other languages
Chinese (zh)
Other versions
CN116168804A (en
Inventor
杨浩
何升韩
彭立香
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Green Olives Network Technology Co ltd
Original Assignee
Hangzhou Green Olives Network Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Green Olives Network Technology Co ltd filed Critical Hangzhou Green Olives Network Technology Co ltd
Priority to CN202310430854.2A priority Critical patent/CN116168804B/en
Publication of CN116168804A publication Critical patent/CN116168804A/en
Application granted granted Critical
Publication of CN116168804B publication Critical patent/CN116168804B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Nutrition Science (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention provides a patient diet recommendation system and method based on an HIS system, which belongs to the technical field of nutrition management and specifically comprises the following steps: the data reading module is responsible for acquiring disease diagnosis results, basic diseases and examination results of a patient based on the HIS system; the attention examination result determination module is responsible for judging whether the patient has attention examination results or not based on the examination results; the potential abnormal disease determination module is responsible for acquiring the potential abnormal disease of the patient based on the attention examination result; the recommended meal recommendation result output module is responsible for generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet tabu of the disease diagnosis result of the patient and the diet tabu of the basic disease; the meal recommendation result output module is responsible for determining matching degree scores of each meal to recommend the meal based on raw material proportion of the recommended meal recommendation result, disease diagnosis results of patients, basic diseases and potential abnormal diseases, so that accuracy of meal recommendation and comprehensiveness of consideration are further improved.

Description

Patient diet recommendation system and method based on HIS system
Technical Field
The invention belongs to the technical field of nutrition management, and particularly relates to a patient meal recommendation system and method based on an HIS system.
Background
In order to realize personalized recommendation of diet of patients, in the patent grant bulletin No. CN112102922B, an information recommendation method and device, basic body consumption data, aerobic exercise consumption data and anaerobic exercise consumption data of the current day of a target user and basic disease information of the current target user are obtained to determine dish collocation information, so that not only can consumption supplement after exercise be taken care of, but also negative influence on the body of the target user can be avoided, but the following technical problems exist:
1. the disease information of the patient obtained based on the HIS system is ignored, compared with consumption data, the disease diagnosis information and detection information of the hospitalized patient are more important, meanwhile, the doctor only depends on doctor orders, and as the doctor only knows diet taboo of the existing disease, the basic disease of the patient cannot be considered, and the recommended result is single and cannot meet various catering and nutrition requirements of the patient.
2. The analysis according to the inspection result of the HIS system is ignored and the diet recommendation is performed according to the analysis result, and in the conventional disease diagnosis process, when the diseased part or suspected diseased part of the patient does not reach a certain threshold, the patient is generally recommended to strengthen the observation, and once the diseased part or suspected diseased part which does not reach the threshold is ignored in the diet recommendation process, the part may further develop, further cause a more serious disease, and further cause damage to the body of the patient.
3. The matching degree scoring of the diet is not performed according to the disease diagnosis result, the basic disease, the suspected disease condition and the raw material proportion of the diet of the patient, for example, for the patient suffering from basic iron deficiency anemia, excessive blood loss or nerve deafness, the matching degree of the raw materials with higher heme such as animal livers, lean meat, eggs and the like in the diet is obviously higher than that of the general diet without the raw materials, so that the recommendation result cannot be accurate if the matching degree scoring of the diet is performed without combining various factors.
Aiming at the technical problems, the invention provides a patient meal recommendation system and a patient meal recommendation method based on an HIS system.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
in accordance with one aspect of the present invention, a patient meal recommendation system and method based on the HIS system is provided.
The patient diet recommending method based on the HIS system is characterized by comprising the following steps of:
s11, acquiring a disease diagnosis result, a basic disease and an inspection result of a patient based on an HIS system;
judging whether the patient has an attention examination result or not based on the examination result, if not, generating an alternative meal recommendation result based on a hospital menu and the age of the patient, and entering a step S13, if yes, entering a step S12;
s12, converting the attention checking result into word vectors, adopting a word segmentation model of a BIGRU-IDF-CRF algorithm to obtain word vectors, wherein the BIGRU algorithm carries out serialization learning on the word vectors to obtain processed word vectors, generates fusion vectors by combining IDF values of the processed word vectors, sends the fusion vectors into a DRF model to obtain word vectors, determines potential abnormal diseases based on the word vectors, and generates alternative meal recommendation results based on diet contraindications of the potential abnormal diseases, hospital menus and ages of patients;
s13, generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet tabu of the disease diagnosis result of the patient and the diet tabu of the basic disease;
s14, determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, the basic disease and the potential abnormal disease, and recommending the meal.
By firstly generating alternative meal recommended results by combining the examination result with the age of the patient, the technical problem that the recommended results are inaccurate due to the fact that only a single disease diagnosis result is adopted in the prior art is avoided, the possibility of further development of potential abnormal diseases is prevented, and the physical health of the patient is guaranteed.
The word segmentation vector is obtained by adopting a word segmentation model of the BIGRU-IDF-CRF algorithm, so that the advantages of retaining bidirectional historical effective information of the BIGRU algorithm are combined, meanwhile, the relevance of front and rear words is considered by further adopting the IDF algorithm and the CRF algorithm, and a keyword database matching result is further adopted, so that the weight of the fusion vector not only considers the influence of inverse word frequency, but also is combined with the actual condition of medicine, and the accuracy and reliability of the final word segmentation vector are further ensured.
The matching degree score of each meal in the recommended meal recommendation result is determined based on the raw material proportion of the recommended meal recommendation result, the disease diagnosis result, the basic disease and the potential abnormal disease of the patient, and the meal is recommended, so that the evaluation of each meal from various angles is realized, the objectivity and the accuracy of the recommendation are further improved, and the actual diet requirement of the patient can be better met.
On the other hand, the invention provides a patient meal recommending system based on an HIS system, and the patient meal recommending method based on the HIS system comprises the following steps of
The data reading module is used for paying attention to the checking result determining module, the potential abnormal disease determining module, the recommended meal recommending result outputting module and the meal recommending result outputting module;
the data reading module is responsible for acquiring disease diagnosis results, basic diseases and examination results of a patient based on the HIS system;
the attention test result determination module is responsible for determining whether the patient has an attention test result based on the test result;
the potentially abnormal disease determination module is responsible for acquiring potentially abnormal disease of the patient based on the attention test result;
the recommended meal recommendation result output module is responsible for generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet taboo of the disease diagnosis result of the patient and the diet taboo of the underlying disease;
the meal recommendation result output module is responsible for determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, basic diseases and potential abnormal diseases, and recommending the meal.
Additional features and advantages will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings;
FIG. 1 is a flow chart of a patient meal recommendation method based on the HIS system;
FIG. 2 is a flowchart showing specific steps of word segmentation vector determination;
FIG. 3 is a flowchart of specific steps for acquiring a potentially abnormal disease of the patient;
FIG. 4 is a flowchart of specific steps for generating alternative meal recommendations;
FIG. 5 is a flowchart of specific steps in the construction of a fitness score for each meal;
fig. 6 is a frame diagram of a patient meal recommendation system based on HIS system.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus detailed descriptions thereof will be omitted.
The terms "a," "an," "the," and "said" are used to indicate the presence of one or more elements/components/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. in addition to the listed elements/components/etc.
To solve the above problems, according to one aspect of the present invention, as shown in fig. 1, there is provided a patient meal recommendation method based on HIS system, which is characterized by comprising:
s11, acquiring a disease diagnosis result, a basic disease and an inspection result of a patient based on an HIS system;
specifically, the HIS system refers to a hospital information system, which utilizes modern means such as computer software and hardware technology and network communication technology to comprehensively manage the personnel flow, logistics and financial flow of the hospital and departments to which the hospital belongs, collect, store, process, extract, transmit and summarize the data generated in each stage of medical activity, and process and form various information, so as to provide comprehensive automatic management and various service information systems for the overall operation of the hospital.
Judging whether the patient has an attention examination result or not based on the examination result, if not, generating an alternative meal recommendation result based on a hospital menu and the age of the patient, and entering a step S13, if yes, entering a step S12;
specifically, the attention examination result is determined according to doctor diagnosis comments in the examination result and abnormal items in the examination result, and specifically, when coarse, echoed, lump, calcification lesion and other keywords appear in the doctor diagnosis comments, the attention examination result is judged to exist.
Specifically, when the patient is less than three years old or more than 60 years old, the spicy and pungent foods, foods containing allergens, and the like in the hospital menu are excluded at this time, and an alternative meal recommendation result is generated.
By firstly generating alternative meal recommended results by combining the examination result with the age of the patient, the technical problem that the recommended results are inaccurate due to the fact that only a single disease diagnosis result is adopted in the prior art is avoided, the possibility of further development of potential abnormal diseases is prevented, and the physical health of the patient is guaranteed.
S12, converting the attention checking result into word vectors, adopting a word segmentation model of a BIGRU-IDF-CRF algorithm to obtain word vectors, wherein the BIGRU algorithm carries out serialization learning on the word vectors to obtain processed word vectors, generates fusion vectors by combining IDF values of the processed word vectors, sends the fusion vectors into a DRF model to obtain word vectors, determines potential abnormal diseases based on the word vectors, and generates alternative meal recommendation results based on diet contraindications of the potential abnormal diseases, hospital menus and ages of patients;
specifically, the specific steps of word segmentation vector determination are as follows:
vectorizing the original text sequence, and representing each word by a vector with a fixed length; text vectorization is to convert the Chinese text expressed by natural language into numbers which can be read and understood by a machine; text vectorization adopts a distributed representation method to obtain vectors corresponding to each word
Processing the input text vector through a forward and a backward GRU model, and reserving and removing context information so as to accurately predict the current output word;
obtaining a mapping weight of the processed word vector based on a matching result of the processed word vector and a keyword database; acquiring an IDF value of the processed word vector by adopting a TF-IDF algorithm, determining a weight of the processed word vector based on the IDF value and the mapping weight, constructing and generating a fusion vector based on the weight of the processed word vector and the processed word vector, taking the fusion vector as an input of CRF, and predicting to obtain a word segmentation vector;
the specific steps for determining the word segmentation vector by adopting the word segmentation model based on the BIGRU-IDF-CRF algorithm are specifically illustrated as follows:
for example, for a blood drawing test chart, first, word2vec is used to convert the attention test result into a word vector, for example, if the attention test result is "the number of red blood cells, hematocrit, hemoglobin concentration, hemoglobin amount of the patient is smaller than the normal value", it may be converted into "the patient", "the number of red blood cells", "the hematocrit", "the hemoglobin concentration", "the hemoglobin amount", "smaller than the normal value".
Processing the input word vector through a forward GRU model and a backward GRU model to obtain a processed word vector, thereby forming semantic codes of context related features;
obtaining a mapping weight of the processed word vector based on a matching result of the processed word vector and a keyword database; acquiring an IDF value of the processing word vector by adopting a TF-IDF algorithm, determining a weight of the processing word vector based on the IDF value and the mapping weight, and constructing and generating a fusion vector based on the weight of the processing word vector and the processing word vector;
specifically, according to the matching result of the keyword database, determining the mapping weight of semantic codes of ' red blood cell number ', ' red blood cell pressure product ', ' hemoglobin concentration ', ' hemoglobin amount ', ' less than ' normal value ';
obtaining an IDF value of the processed word vector by adopting a TF-IDF algorithm, wherein the IDF value reflects inverse word frequencies in different inspection results, and the inverse word frequencies are commonly used as recognition of stop words in the prior art and are used as a formation mode for weighting in the application;
in the actual operation process, determining the weight of the processing word vector based on the IDF value and the mapping weight, for example, if the mapping weight of "hemoglobin amount" is 0.6 and the IDF value is 0.7, the weight is 0.65;
and outputting the feature extracted by the Bi GRU model through the CRF layer to obtain a label sequence with the maximum probability, so as to obtain global optimal labels, and extracting named entities of the word segmentation vectors, thereby obtaining the final marked word segmentation vectors.
After the word segmentation vector is obtained, inputting the word segmentation vector into a classification model of an algorithm of the GA-IPSO-SVM of the application to obtain the final determination of the potential abnormal disease, and obtaining the final potential abnormal disease as mild anemia;
other diagnostic results may also be combined during actual operation.
The word segmentation vector is obtained by adopting a word segmentation model of the BIGRU-IDF-CRF algorithm, so that the advantages of retaining bidirectional historical effective information of the BIGRU algorithm are combined, meanwhile, the relevance of front and rear words is considered by further adopting the IDF algorithm and the CRF algorithm, and a keyword database matching result is further adopted, so that the weight of the fusion vector not only considers the influence of inverse word frequency, but also is combined with the actual condition of medicine, and the accuracy and reliability of the final word segmentation vector are further ensured.
S13, generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet tabu of the disease diagnosis result of the patient and the diet tabu of the basic disease;
for example, when the diet contraindication of the disease diagnosis result of the patient is a diet which cannot be eaten by the patients and the diet contraindication of the basic disease is an allergic food such as beef/mutton, the raw materials in the alternative diet recommendation result and dishes of the raw materials are required to be removed, so that the recommended diet recommendation result is obtained.
S14, determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, the basic disease and the potential abnormal disease, and recommending the meal.
Specifically, the content contained in the raw material proportion of the recommended diet result is matched with the requirements of the disease diagnosis result, basic disease and potential abnormal disease of the patient, so that a matching degree score can be obtained, and the value range is 0 to 1.
The matching degree score of each meal in the recommended meal recommendation result is determined based on the raw material proportion of the recommended meal recommendation result, the disease diagnosis result, the basic disease and the potential abnormal disease of the patient, and the meal is recommended, so that the evaluation of each meal from various angles is realized, the objectivity and the accuracy of the recommendation are further improved, and the actual diet requirement of the patient can be better met.
In another possible embodiment, the attention test result is determined according to doctor's diagnosis opinion in the test result, abnormal item in the test result.
In another possible embodiment, when the age of the patient is not within the set age range, the spicy and pungent dishes containing peppers, caffeine and alcohol in the raw materials are removed according to the raw materials of the hospital menu, so that the alternative meal recommendation result is obtained.
In another possible embodiment, as shown in fig. 2, the specific steps of word segmentation vector determination are:
s21, converting the attention checking result into a word vector by word2vec, and sending the word vector into a word vector processing model of a BIGRU algorithm, and processing the input word vector through a forward GRU model and a backward GRU model to obtain a processed word vector;
s22, obtaining a mapping weight of the processed word vector based on a matching result of the processed word vector and a keyword database; acquiring an IDF value of the processing word vector by adopting a TF-IDF algorithm, determining a weight of the processing word vector based on the IDF value and the mapping weight, and constructing and generating a fusion vector based on the weight of the processing word vector and the processing word vector;
s23, the fusion vector is sent into a DRF model to obtain a word segmentation vector.
The generation of the fusion vector is realized by comprehensively combining the IDF value and the mapping weight, so that the importance of word frequency and data in the medical field is comprehensively combined, and the reliability of the generation of the fusion vector is further improved.
In another possible embodiment, the calculation formula of the weight is:
wherein t is 1 To map the weight, t 2 To process the IDF value, K, of the word vector 1 Is constant and has a value ranging from 0 to 1.
In another possible embodiment, as shown in fig. 3, the specific steps for obtaining the potentially abnormal disease of the patient are:
s31, initializing a kernel function g and a penalty factor c of an SVM algorithm, and randomly generating initial particles based on the kernel function g and the penalty factor c;
s32, carrying out GA algorithm evolution on the particle population, respectively recording the fitness of different positions of different particles under different iteration times in the evolution process, and sequencing the fitness; the batch of particles with the lowest adaptability are defined as inert particles according to the elimination proportion set by a particle elimination mechanism;
specifically, the maximum iteration number D of the GA algorithm has the following value:
wherein T is max For the upper limit of the iteration times of the particles, n is the number of the particle dimensions, t 1 Is constant and has a value ranging from 0 to 0.1.
S33, carrying out iteration of an IPSO algorithm based on the active particle population until the algorithm converges or the maximum iteration times are reached, so as to obtain a kernel function optimal solution g1 and a penalty factor optimal solution c1;
s34, transmitting the word segmentation vector to a classification model of the optimized SVM algorithm to obtain the potential abnormal disease of the patient, wherein a kernel function and a penalty factor of the classification model of the optimized SVM algorithm adopt a kernel function optimal solution g1 and a penalty factor optimal solution c1.
Specifically, the IPSO optimization parameters are set to 100 of initial population number of particles, 1000 of maximum iteration times, 0.8 of inertia factor w, 0.5 of learning factors c1 and 0.7 of GA optimization parameters and 0.9 of crossover probability.
It should be noted that, the IPSO algorithm is an improved PSO algorithm.
Specifically, the classification accuracy of the algorithm of GA-IPSO-SVM was 92.15%.
In another possible embodiment, based on the diet taboo of the potential abnormal disease, the hospital menu, the age of the patient, as shown in fig. 4, the specific steps of generating the alternative diet recommendation result are:
s41, when the age of the patient is not within the set age range, removing pungent and pungent dishes containing peppers, caffeine and alcohol from the raw materials according to the raw materials of a hospital menu to obtain a basic diet recommendation result, and if not, taking the hospital menu as the basic diet recommendation result;
the set age range is between 12 and 50 years.
S42, judging whether the diet taboo of the potential abnormal disease exists in the raw material ratio of the basic diet recommended result based on the raw material ratio of the basic diet recommended result, if so, removing dishes of the diet taboo of the potential abnormal disease in the raw material ratio of the basic diet recommended result to obtain an alternative diet recommended result, and if not, taking the basic diet recommended result as the alternative diet recommended result.
In another possible embodiment, as shown in fig. 5, the specific steps of the matching score construction for each meal are:
s51, determining the nutrient substances required by the patient based on the disease diagnosis result of the patient, determining the content and the type of 100g in each meal of the nutrient substances required by the patient based on the raw material proportion of each meal, and obtaining a matching degree score of the disease diagnosis result based on the content and the type of each 100 g;
specifically, for iron deficiency anemia, for dish couple lung tablets, the beef heart is 100g, the iron content in the beef heart is 5.9 mg and is greater than the set threshold value of 4 mg, and the matching degree score is 1; for dishes smaller than the set threshold, the matching degree score is determined according to the ratio of the dishes to the threshold.
Specifically, in the method, for example, for a couple lung tablet, the method firstly gives different original contents of a recommended menu, and when purchasing, the contents are recommended to be determined according to the contents, and in the actual operation process, after the meal is finally manufactured, the actual proportion of the raw materials is determined according to the difference between the use amount and the purchasing amount of different raw materials in the meal.
S52, determining the nutrition matters required by the basic diseases of the patients based on the basic diseases of the patients, determining the content and the type of 100g in each meal of the nutrition matters required by the basic diseases of the patients based on the raw material proportion of each meal, and obtaining the matching degree score of the basic diseases based on the content and the type of each 100 g;
s53, determining the nutrition matters required by the potential abnormal diseases of the patient based on the potential abnormal diseases of the patient, determining the content and the type of 100g in each meal of the nutrition matters required by the potential abnormal diseases of the patient based on the raw material proportion of each meal, and obtaining the matching degree score of the potential abnormal diseases based on the content and the type of each 100 g;
s54 obtains a matching score for each meal based on the matching score for the disease diagnosis, the matching score for the underlying disease, and the matching score for the potentially abnormal disease.
The matching degree score of each meal is obtained by respectively based on the matching degree score of the disease diagnosis result, the matching degree score of the basic disease and the matching degree score of the potential abnormal disease, so that the matching degree score of each meal can accurately reflect the matching conditions in multiple aspects, and the difference of the influence degrees of different diseases is fully considered, so that the accuracy and the comprehensiveness of the matching degree score are further improved.
In another possible embodiment, the matching degree score is calculated according to the following formula:
wherein P is 1 、P 2 、P 3 K is the matching degree score of the disease diagnosis result, the matching degree score of the basic disease and the matching degree score of the potential abnormal disease respectively 3 、K 4 K5 is the disease weight.
In the actual course of the operation, it is specifically illustrated that if the disease diagnosis results in fracture, kidney stones as the underlying disease, and anemia as the underlying abnormal disease, the severity of the fracture is significantly greater than that of kidney stones, thus K 3 、K 4 、K 5 Respectively 0.6/0.3/0.1, in the actual operation process, the system can also adopt fixed weight to make sureAnd (5) setting.
In another possible embodiment, the disease weight is determined by expert scoring based on the disease diagnosis, the underlying disease, and the severity of the underlying abnormal disease.
Specifically, generally, the weight of the disease diagnosis result is greater than that of the underlying disease and greater than that of the potentially abnormal disease.
As shown in FIG. 6, the present invention provides a patient meal recommendation system based on HIS system, which comprises
The data reading module is used for paying attention to the checking result determining module, the potential abnormal disease determining module, the recommended meal recommending result outputting module and the meal recommending result outputting module;
the data reading module is responsible for acquiring disease diagnosis results, basic diseases and examination results of a patient based on the HIS system;
the attention test result determination module is responsible for determining whether the patient has an attention test result based on the test result;
the potentially abnormal disease determination module is responsible for acquiring potentially abnormal disease of the patient based on the attention test result;
it should be noted that the specific steps of generating the alternative meal recommendation result are:
when the age of the patient is not within the range of 12 to 50 years, removing pungent and pungent dishes containing peppers, caffeine and alcohol from the raw materials according to the raw materials of a hospital menu to obtain a basic diet recommended result;
and based on the raw material ratio of the basic diet recommended result, when the raw material ratio of the basic diet recommended result is judged to determine that the diet taboo of the potential abnormal disease exists, removing dishes of the diet taboo of the potential abnormal disease in the raw material ratio of the basic diet recommended result to obtain an alternative diet recommended result.
The recommended meal recommendation result output module is responsible for generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet taboo of the disease diagnosis result of the patient and the diet taboo of the underlying disease;
the meal recommendation result output module is responsible for determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, basic diseases and potential abnormal diseases, and recommending the meal.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.

Claims (6)

1. The patient diet recommending method based on the HIS system is characterized by comprising the following steps of:
s11, acquiring a disease diagnosis result, a basic disease and an inspection result of a patient based on an HIS system, judging whether the patient has an attention inspection result based on the inspection result, if not, generating an alternative meal recommendation result based on a hospital menu and the age of the patient, and entering a step S13, if so, entering a step S12;
s12, converting the attention checking result into word vectors, adopting a word segmentation model of a BIGRU-IDF-CRF algorithm to obtain word vectors, wherein the BIGRU algorithm carries out serialization learning on the word vectors to obtain processed word vectors, generates fusion vectors by combining IDF values of the processed word vectors, sends the fusion vectors into a DRF model to obtain word vectors, determines potential abnormal diseases based on the word vectors, and generates alternative meal recommendation results based on diet contraindications of the potential abnormal diseases, hospital menus and ages of patients;
the specific steps of word segmentation vector determination are as follows:
converting the attention checking result into a word vector by word2vec, sending the word vector into a word vector processing model of a BIGRU algorithm, and processing the input word vector through a forward GRU model and a backward GRU model to obtain a processed word vector;
obtaining a mapping weight of the processed word vector based on a matching result of the processed word vector and a keyword database; acquiring an IDF value of the processing word vector by adopting a TF-IDF algorithm, determining a weight of the processing word vector based on the IDF value and the mapping weight, and constructing and generating a fusion vector based on the weight of the processing word vector and the processing word vector;
sending the fusion vector into a DRF model to obtain a word segmentation vector;
the calculation formula of the weight is as follows:wherein t is 1 To map the weight, t 2 To process the IDF value, K, of the word vector 1 Is constant and has a value range of 0 to 1;
the specific steps for obtaining the potential abnormal diseases of the patient are as follows:
initializing a kernel function g and a penalty factor c of an SVM algorithm, and randomly generating initial particles based on the kernel function g and the penalty factor c;
carrying out GA algorithm evolution on the particle population, respectively recording the fitness of different positions of different particles under different iteration times in the evolution process, and sequencing the fitness; the batch of particles with the lowest adaptability are defined as inert particles according to the elimination proportion set by a particle elimination mechanism;
performing iteration of the IPSO algorithm based on the active particle population until the algorithm converges or the maximum iteration times are reached, so as to obtain a kernel function optimal solution g1 and a penalty factor optimal solution c1;
transmitting the word segmentation vector to a classification model of an SVM algorithm with optimized completion to obtain potential abnormal diseases of the patient, wherein a kernel function and a penalty factor of the classification model of the SVM algorithm with optimized completion adopt a kernel function optimal solution g1 and a penalty factor optimal solution c1;
s13, generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet tabu of the disease diagnosis result of the patient and the diet tabu of the basic disease;
s14, determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, the basic disease and the potential abnormal disease, and recommending the meal;
the specific steps of matching degree scoring construction of each meal are as follows:
determining the required nutrient substances of the patient based on the disease diagnosis result of the patient, determining the content and the type of 100g in each meal of the required nutrient substances of the patient based on the raw material proportion of each meal, and obtaining a matching degree score of the disease diagnosis result based on the content and the type of each 100 g;
determining the nutrients required by the basic disease of the patient based on the basic disease of the patient, determining the content and the type of 100g in each meal of the nutrients required by the basic disease of the patient based on the raw material proportion of each meal, and obtaining a matching degree score of the basic disease based on the content and the type of each 100 g;
determining the nutrients required by the potential abnormal diseases of the patient based on the potential abnormal diseases of the patient, determining the content and the type of 100g in each meal of the nutrients required by the potential abnormal diseases of the patient based on the raw material proportion of each meal, and obtaining a matching degree score of the potential abnormal diseases based on the content and the type of each 100 g;
obtaining a matching degree score of each meal based on the matching degree score of the disease diagnosis result, the matching degree score of the basic disease and the matching degree score of the potential abnormal disease;
the calculation formula of the matching degree score is as follows:wherein P is 1 、P 2 、P 3 K is the matching degree score of the disease diagnosis result, the matching degree score of the basic disease and the matching degree score of the potential abnormal disease respectively 3 、K 4 、K 5 Is the disease weight.
2. The patient meal recommendation method of claim 1, wherein the attention test result is determined based on doctor's diagnostic comments in the test result, abnormal items in the test result.
3. The patient meal recommendation method according to claim 1, wherein when the age of the patient is not within the set age range, pungent and pungent dishes containing peppers, caffeine and alcohol in the raw materials are removed according to the raw materials of the hospital menu, and an alternative meal recommendation result is obtained.
4. The patient meal recommendation method of claim 1, wherein the specific step of generating alternative meal recommendation results based on the diet taboo of the potential abnormal disease, a hospital menu, the age of the patient is:
when the age of the patient is not within the set age range, removing pungent and pungent dishes containing peppers, caffeine and alcohol from the raw materials according to the raw materials of the hospital menu to obtain a basic diet recommendation result, and if not, taking the hospital menu as the basic diet recommendation result;
judging whether the diet taboo of the potential abnormal disease exists in the raw material ratio of the basic diet recommended result or not based on the raw material ratio of the basic diet recommended result, if so, removing dishes of the diet taboo of the potential abnormal disease in the raw material ratio of the basic diet recommended result to obtain an alternative diet recommended result, and if not, taking the basic diet recommended result as the alternative diet recommended result.
5. The patient meal recommendation method of claim 1, wherein the disease weight is determined by expert scoring based on the disease diagnosis, the underlying disease, and the severity of the underlying abnormal disease.
6. A patient meal recommendation system based on HIS system, which adopts the patient meal recommendation method based on HIS system as claimed in any one of claims 1-5, and is characterized by comprising the following steps
The data reading module is used for paying attention to the checking result determining module, the potential abnormal disease determining module, the recommended meal recommending result outputting module and the meal recommending result outputting module;
the data reading module is responsible for acquiring disease diagnosis results, basic diseases and examination results of a patient based on the HIS system;
the attention test result determination module is responsible for determining whether the patient has an attention test result based on the test result;
the potentially abnormal disease determination module is responsible for acquiring potentially abnormal disease of the patient based on the attention test result;
the recommended meal recommendation result output module is responsible for generating a recommended meal recommendation result based on the alternative meal recommendation result, the diet taboo of the disease diagnosis result of the patient and the diet taboo of the underlying disease;
the meal recommendation result output module is responsible for determining matching degree scores of each meal in the recommended meal recommendation result based on the raw material proportion, the disease diagnosis result of the patient, basic diseases and potential abnormal diseases, and recommending the meal.
CN202310430854.2A 2023-04-21 2023-04-21 Patient diet recommendation system and method based on HIS system Active CN116168804B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310430854.2A CN116168804B (en) 2023-04-21 2023-04-21 Patient diet recommendation system and method based on HIS system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310430854.2A CN116168804B (en) 2023-04-21 2023-04-21 Patient diet recommendation system and method based on HIS system

Publications (2)

Publication Number Publication Date
CN116168804A CN116168804A (en) 2023-05-26
CN116168804B true CN116168804B (en) 2023-08-01

Family

ID=86418517

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310430854.2A Active CN116168804B (en) 2023-04-21 2023-04-21 Patient diet recommendation system and method based on HIS system

Country Status (1)

Country Link
CN (1) CN116168804B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116434916B (en) * 2023-06-15 2023-08-22 北京四海汇智科技有限公司 Digital nutrition management method for tumor rehabilitation
CN117558410B (en) * 2024-01-12 2024-03-22 吉林大学 Artificial intelligence-based diet management system and method for diabetic nephropathy patients

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111599439A (en) * 2020-05-14 2020-08-28 陕西师范大学 Family diet recommendation method and equipment based on multi-target demand similarity

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109003674A (en) * 2017-06-06 2018-12-14 深圳大森智能科技有限公司 A kind of health control method and system
WO2018234083A1 (en) * 2017-06-23 2018-12-27 Nestec S.A. System and methods for calculating, displaying, modifying, and using single dietary intake score reflective of optimal quantity and quality of consumables
CN108198603A (en) * 2017-12-12 2018-06-22 昆明亿尚科技有限公司 A kind of nutrition dietary based on personal physical examination information recommends method
CN109190113B (en) * 2018-08-10 2021-08-31 北京科技大学 Knowledge graph construction method of traditional Chinese medicine theory book
CN110491526A (en) * 2019-07-30 2019-11-22 美睿健康产业(重庆)有限公司 A kind of slow sick life style medical supervision system of various dimensions intervention
CN111223552A (en) * 2019-12-31 2020-06-02 苏州健玺信息科技有限公司 Disease nutrition diet taboo recommendation system and use method thereof
CN112102922B (en) * 2020-11-18 2021-02-12 北京妙医佳健康科技集团有限公司 Information recommendation method and device
CN113051391A (en) * 2021-03-29 2021-06-29 深圳软通动力信息技术有限公司 Personalized diet recommendation method based on food nutrition and health knowledge base
CN113380427A (en) * 2021-06-28 2021-09-10 联硕智能(深圳)有限公司 Health management platform and management method based on wearable intelligent terminal
CN113823412B (en) * 2021-09-29 2024-04-12 康键信息技术（深圳）有限公司 Health management plan generation method and device, electronic equipment and storage medium
CN114496165A (en) * 2022-01-27 2022-05-13 国家食品安全风险评估中心 Food diet recommendation method based on heteromorphic graph
CN115762711A (en) * 2022-10-21 2023-03-07 东华医为科技有限公司 Inpatient auxiliary nutrition intervention system, method and device

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111599439A (en) * 2020-05-14 2020-08-28 陕西师范大学 Family diet recommendation method and equipment based on multi-target demand similarity

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Decoding Plant-Based and Other Popular Diets: Ensuring Patients Are Meeting Their Nutrient Needs;Christine Werner等;Physician Assistant Clinics;第7卷(第4期);615-628 *
基于电子病历利用矩阵乘法构建医生推荐模型;杨晓夫;秦函书;;计算机与现代化(第06期);全文 *

Also Published As

Publication number Publication date
CN116168804A (en) 2023-05-26

Similar Documents

Publication Publication Date Title
US11928570B2 (en) Artificial intelligence methods and systems for generation and implementation of alimentary instruction sets
US20230245776A1 (en) Methods and systems for using artificial intelligence to select a compatible element
CN116168804B (en) Patient diet recommendation system and method based on HIS system
US11289198B2 (en) Systems and methods for generating alimentary instruction sets based on vibrant constitutional guidance
US20220261693A1 (en) Methods and systems for classification to prognostic labels using expert inputs
US11568351B2 (en) Systems and methods for arranging transport of alimentary components
US12014252B2 (en) Systems and methods for implementing generated alimentary instruction sets based on vibrant constitutional guidance
US20210005317A1 (en) Methods and systems for achieving vibrant constitution based on user inputs
US11114193B2 (en) Methods and systems for optimizing dietary levels utilizing artificial intelligence
US12014834B2 (en) Methods and systems for generating a vibrant compatbility plan using artificial intelligence
US11915827B2 (en) Methods and systems for classification to prognostic labels
US11581094B2 (en) Methods and systems for generating a descriptor trail using artificial intelligence
US11205140B2 (en) Methods and systems for self-fulfillment of an alimentary instruction set based on vibrant constitutional guidance
US11315684B2 (en) Systems and methods for generating alimentary instruction sets based on vibrant constitutional guidance
US20210397996A1 (en) Methods and systems for classification using expert data
US20200321115A1 (en) Systems and methods for generating alimentary instruction sets based on vibrant constitutional guidance
CN112528009A (en) Method, device and computer readable medium for generating user chronic disease conditioning scheme
US20210004713A1 (en) Methods and systems for generating a supplement instruction set using artificial intelligence
US20220054091A1 (en) Methods and systems for self-fulfillment of an alimentary instruction set based on vibrant constitutional guidance
US20200321112A1 (en) Systems and methods for generating alimentary instruction sets based on vibrant constitutional guidance
US11211158B1 (en) System and method for representing an arranged list of provider aliment possibilities
US20230284931A1 (en) Systems and methods for generating a metabolic dysfunction nourishment program
US20230187072A1 (en) Methods and systems for generating a descriptor trail using artificial intelligence
Rahman et al. Predicting obesity: a comparative analysis of machine learning models incorporating different features
Herron Mulet Towards fair machine learning in healthcare: ensuring non-discrimination for disease prediction

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
GR01 Patent grant
GR01 Patent grant