CN113488168A - Personalized physical examination item recommendation method based on user health information characteristic set - Google Patents
Personalized physical examination item recommendation method based on user health information characteristic set Download PDFInfo
- Publication number
- CN113488168A CN113488168A CN202110731371.7A CN202110731371A CN113488168A CN 113488168 A CN113488168 A CN 113488168A CN 202110731371 A CN202110731371 A CN 202110731371A CN 113488168 A CN113488168 A CN 113488168A
- Authority
- CN
- China
- Prior art keywords
- physical examination
- feature
- user
- data
- health
- 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.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000013507 mapping Methods 0.000 claims abstract description 12
- 238000011160 research Methods 0.000 claims abstract description 5
- 238000011835 investigation Methods 0.000 claims description 18
- 208000024891 symptom Diseases 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 230000005183 environmental health Effects 0.000 claims description 10
- 230000004630 mental health Effects 0.000 claims description 10
- 206010020751 Hypersensitivity Diseases 0.000 claims description 2
- 208000026935 allergic disease Diseases 0.000 claims description 2
- 230000007815 allergy Effects 0.000 claims description 2
- 235000005911 diet Nutrition 0.000 claims description 2
- 230000037213 diet Effects 0.000 claims description 2
- 230000035622 drinking Effects 0.000 claims description 2
- 229940079593 drug Drugs 0.000 claims description 2
- 239000003814 drug Substances 0.000 claims description 2
- 230000035558 fertility Effects 0.000 claims description 2
- 230000005906 menstruation Effects 0.000 claims description 2
- 230000000391 smoking effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 17
- 238000004891 communication Methods 0.000 description 14
- 201000010099 disease Diseases 0.000 description 11
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 11
- 230000003993 interaction Effects 0.000 description 5
- 206010012601 diabetes mellitus Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 108091005995 glycated hemoglobin Proteins 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010006187 Breast cancer Diseases 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010009944 Colon cancer Diseases 0.000 description 1
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 1
- 201000005569 Gout Diseases 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 208000037490 Medically Unexplained Symptoms Diseases 0.000 description 1
- 208000005718 Stomach Neoplasms Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 208000002495 Uterine Neoplasms Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004159 blood analysis Methods 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 206010017758 gastric cancer Diseases 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 201000011549 stomach cancer Diseases 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 206010046766 uterine cancer Diseases 0.000 description 1
Images
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
- 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
Landscapes
- Medical Informatics (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a personalized physical examination project recommendation method based on a user health information characteristic set, which comprises the steps of segmenting acquired user health research data and user historical physical examination data to obtain a plurality of text data, and constructing a user characteristic set by key characteristic information corresponding to the maximum characteristic similarity meeting a similarity threshold; mapping the user feature set by using a key value pair of the HashMap to obtain a plurality of physical examination items, and constructing a recommended physical examination item set by the plurality of physical examination items; sending the recommended physical examination item set to a user terminal, receiving a user-selected physical examination item set input by the user terminal, sending the user characteristic set and the selectable physical examination item set to a doctor terminal, and receiving a modulated selectable physical examination item set input by the doctor terminal; and sending the modulated optional physical examination item set to a user terminal, and receiving the modulated optional physical examination item set by the user terminal to obtain a final physical examination item set so as to finish the selection of the physical examination items. The method can accurately provide physical examination items reflecting physical conditions.
Description
Technical Field
The invention belongs to the field of medical treatment, and particularly relates to a personalized physical examination item recommendation method based on a user health information characteristic set.
Background
The physical examination is to carry out physical examination on the examinee by a medical means and method, and to know the health condition of the examinee, and to find disease clues and diagnosis and treatment behaviors of health hidden dangers at an early stage; the physical examination can be used for early detection and treatment of diseases which have no subjective symptoms but are serious, such as gastric cancer, colorectal cancer, lung cancer, breast cancer, uterine cancer and the like, and can completely cure the diseases if the diseases are detected early.
The physical examination can reduce the probability of future diseases, such as people with high blood pressure, high cholesterol value and high blood sugar value, which have no subjective symptoms at ordinary times, but the probability of the people suffering from cerebral apoplexy, myocardial infarction and diabetes is very high, even though no subjective symptoms exist at present, once the disease is serious, so the abnormality of the factors is discovered early to restore the normal state, and the disease is prevented to the utmost extent.
With the rapid development of society, people pay more and more attention to health threats caused by various diseases. Through investigation, the diseases affecting the health of the masses of China at present mainly comprise hypertension, diabetes, heart disease, cardiovascular and cerebrovascular diseases, respiratory diseases, gout and the like, and the diseases also have the characteristics of enlarged area and low age. Physical examination is an important means for early prevention of the above diseases, people often cannot obtain physical examination item suggestions based on past physical state analysis in terms of selection of physical examination items, and the evaluation of personal health conditions is incomplete and unspecific. Thus, the physical examination can be carried out selectively and individually.
When people want physical examination, physical examination items suitable for the physical examination people need to be selected by the physical examination people who go to a hospital or a physical examination institution in advance because physical conditions, living habits and past medical histories of the physical examination people are different. Some examination items have special requirements on physical examiners, for example, some blood examinations need to take blood in a fasting and non-eating state, and some ultrasound examinations need to examine in a urine-holding and bladder-filling state. The physical examination person still needs to go to the hospital or physical examination mechanism again after preparing the special requirement of the examination project and carry out the physical examination, and when the physical examination number is more, need to wait outside the department queue, expend a large amount of time energy, user experience is not good.
At present, related business processes and technologies are adopted, particularly when children health physical examination is carried out, parents basically hold paper physical examination forms, departments run, and mobile terminals only stop on registration and report lookup functions; doctors still need to manually fill data in the form, and then manually upload the physical examination results to a computer PC end one by one; medical equipment and a doctor PC (personal computer) related to the health care center cannot be in complete information butt joint with the health examination service; the analysis of the physical examination results only stays at a data statistics level, and other information contained in the data cannot be deeply mined; in a word, the processing method has low efficiency and information exchange is not timely.
Therefore, an intelligent health examination recommendation system capable of providing professional and personalized physical examination items based on intelligent analysis of personal health conditions becomes a demand of health care centers and residents.
Disclosure of Invention
The invention provides a personalized physical examination item recommendation method based on a user health information characteristic set, which can provide personalized physical examination items based on the personal health condition of a user, and the user can select the physical examination items in a personalized manner.
A personalized physical examination item recommendation method based on a user health information characteristic set comprises the following steps:
s1: receiving user health research data input by a user terminal and user historical physical examination data input by a physical examination system;
s2: based on the existing feature knowledge base, segmenting the acquired user health investigation data and user historical physical examination data to obtain a plurality of text data, extracting first key feature information in each text data, forming a first key feature information set, calculating feature similarity between each first key feature information and the feature knowledge base by traversing the first key feature information set to obtain maximum feature similarity, judging whether the maximum feature similarity meets a similarity threshold, taking the first key feature information corresponding to the maximum feature similarity meeting the similarity threshold as second key feature information, and constructing a user feature set by a plurality of second key feature information;
s3: mapping the user feature set by using a key value pair of the HashMap to obtain a plurality of physical examination items, constructing a recommended physical examination item set by the plurality of physical examination items, and selecting the physical examination items by the user terminal based on the recommended physical examination item set.
According to the method, the health investigation data of the user and the historical physical examination data of the user are combined and compared with the existing characteristic knowledge base, the key characteristic information of the user is accurately obtained, and the key value pair of a HashMap is key-value, and the key-value pair is mapped to obtain the recommended physical examination item.
Second key feature information in the user feature set is described through a constructed feature dictionary, wherein the feature dictionary comprises:
feature similarity CaComprises the following steps: ca＝Max(Ca,i)；
Characteristic weight WFaComprises the following steps: characteristic weight WFaComprises the following steps: WFa(ii) (demographic characteristics, health history characteristics, physical symptom characteristics, lifestyle characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics, health literacy characteristics };
type of characteristic TypeaComprises the following steps: non-type 1, frequency type 2, class type I, class II, class III, … …, class N3;
eigenvalue ValueaComprises the following steps: is invariable ═ 0,1]Frequency variable is [1,2,3 ]]Grade variable ═ 1,2, …, n]。
The physical examination items in the recommended physical examination item set are described through a constructed physical examination item dictionary, wherein the physical examination item dictionary comprises:
item weight WIaComprises the following steps: item weight WIaComprises the following steps: WI (Wireless electric appliance)aRank 1 item, rank 2 item, rank 3 item };
physical examination frequency FIaComprises the following steps: FIa1: 1-2 years type 2:1 years type 3: 3-6 months };
recommended level LaComprises the following steps: l isa＝Ca×WFa×Fa×WIa；
Wherein, FaFrequency of physical examination items, Fa＝na/N，naThe frequency of the physical examination items a in the recommended physical examination item set, N is the sum of all the physical examination items in the recommended physical examination item set, and the recommendation level LaBy feature similarity CaCharacteristic weight WFaFrequency of physical examination items FaAnd item weight WIaAnd (4) obtaining.
And constructing a physical examination item recommendation level through the feature dictionary, the item weight and the physical examination item frequency in the second key feature information, and using the physical examination item recommendation level as a label of a recommended physical examination item to provide intelligent guidance for the user to select the physical examination item.
The physical examination frequency is the attribute of the physical examination items, and the examination frequency of different physical examination items is determined by the characteristics of the items or physical examination objects, (for example, CT has radiation, two physical examinations need to have a half-year interval, and glycated hemoglobin is an index that a diabetic needs to monitor regularly, and the diabetic needs to measure glycated hemoglobin every half year or one year).
The specific steps of mapping the user feature set to obtain a plurality of physical examination items according to the user feature set are as follows:
based on a feature knowledge base, a physical examination item base and a decision support base in a decision support module, features in the feature knowledge base and physical examination items in the physical examination item base are respectively used as keys and values, the decision support base provides a mapping relation between the keys and the values, the keys and the values are stored in a key-value key value pair form of a HashMap, whether second key feature information exists in the HashMap as the keys or not is judged, if not, a null value is returned, and if yes, the value corresponding to the key is returned.
The calculation of the similarity between each piece of first key feature information and the features in the feature knowledge base is as follows:
wherein,
is the feature vector of the first set of key feature information,
the feature vectors in the feature knowledge base;
the maximum feature similarity is as follows:
Max(Ca,i)＝Max{Ca,1,...,Ca,i,...,Ca,n}(i＝1...n)
where i is an index of the feature vector in the feature knowledge base.
The user health investigation data comprises demographic data, health history data, somatic symptom data, lifestyle data, environmental health data, mental health data, sleep health data and health literacy data;
the health history data comprises family history data, current medical history data, allergy history data, medication history data, surgical history data and menstruation fertility history data;
the lifestyle data includes diet data, smoking data, drinking data, and exercise data.
The characteristic knowledge base comprises demographic characteristics, health history characteristics, physical symptom characteristics, life style characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics and health literacy characteristics.
The invention provides more comprehensive user health investigation data and a more comprehensive characteristic knowledge base, and provides a data basis for accurately obtaining the key characteristic information of the user.
And if the maximum feature similarity meets the similarity threshold, adding second key feature information corresponding to the maximum feature similarity into the user feature set, and if the maximum feature similarity does not meet the similarity threshold, taking the key feature information corresponding to the maximum feature similarity as third key feature information and deleting the third key feature information.
The specific steps of selecting the physical examination items based on the recommended physical examination item set by the user are as follows:
s31: the remote server sends the recommended physical examination item set to a user terminal, receives a user-selected physical examination item set input by the user terminal, reserves a necessary physical examination item set, sends a second key feature information set and a selectable physical examination item set to a doctor terminal, and receives a modulated selectable physical examination item set input by the doctor terminal;
s32: and the remote server sends the modulated optional physical examination item set to the user terminal, if the user terminal does not accept the modulated optional physical examination item set, the step S31 is iterated until the user terminal accepts the modulated optional physical examination item set to obtain a final physical examination item set, the final physical examination item set input by the user terminal is received, and meanwhile, the final physical examination item set is sent to the doctor terminal to complete the selection of the physical examination items.
Compared with the prior art, the invention has the beneficial effects that:
the physical examination items are intelligently recommended for the user through correlation matching of the user health research data and the user historical physical examination data with the feature knowledge base and by utilizing the HashMap, meanwhile, more professional guidance is provided for the user to select the physical examination items in combination with the physical examination item recommendation of offline doctors, and the user can personally select the physical examination items according to personal requirements.
Drawings
Fig. 1 is a flowchart of a personalized physical examination item recommendation method based on a user health information feature set according to an embodiment of the present invention;
FIG. 2 is a flow chart of a recommended physical examination item provided in accordance with an embodiment of the present invention;
fig. 3 is a general architecture diagram of a personalized physical examination item recommendation device based on a user health information feature set according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
A personalized physical examination item recommendation method based on a user health information feature set is shown in figure 1 and comprises the following specific steps:
s1: the user terminal acquires user health investigation data, performs primary processing on the user health investigation data, sends the processed user health investigation data to the remote server, and the physical examination system inquires user historical physical examination data and sends the inquired user historical physical examination data to the remote server;
s2: the remote server divides the acquired user health investigation data and the user historical physical examination data to obtain a plurality of text data based on the existing characteristic knowledge base which comprises demographic characteristics, health history characteristics, body symptom characteristics, life style characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics and health literacy characteristics, extracts first key characteristic information in each text data, forms a first key characteristic information set by the plurality of first key characteristic information, calculates the characteristic similarity between each first key characteristic information and the characteristic knowledge base to obtain the maximum characteristic similarity by traversing the first key characteristic information set, judges whether the maximum characteristic similarity meets a similarity threshold value or not, and takes the first key characteristic information corresponding to the maximum characteristic similarity meeting the similarity threshold value as second key characteristic information, constructing a user feature set by a plurality of second key feature information, wherein the second key feature information in the user feature set is described by the constructed feature dictionary;
s3: the remote server maps the user feature set by using a key value pair of the HashMap to obtain a plurality of physical examination items, the physical examination items construct a recommended physical examination item set, and the physical examination items in the recommended physical examination item set are described through the constructed physical examination item dictionary;
s4: the remote server stores a recommended physical examination item set and simultaneously sends the recommended physical examination item set to a user terminal, the user terminal autonomously selects physical examination items to obtain a user selected physical examination item set based on the recommended physical examination item set and sends the user selected physical examination item set to the remote server, the remote server divides the input user selected physical examination item set into a required item set and a selectable item set, the required item set is reserved, a second key characteristic information set and the selectable item set are sent to a doctor terminal, the doctor terminal adjusts the input selectable item set to obtain a modulated selectable physical examination item set and sends the modulated selectable physical examination item set to the remote server, and the remote server sends the modulated selectable physical examination item set to the user terminal;
s5: the user terminal receives the modulated optional physical examination item set and confirms whether the modulated optional physical examination item set is received or not, if the modulated optional physical examination item set is received, the modulated optional physical examination item set and the optional item set are used as a final physical examination item set, the final physical examination item set is sent to the remote server, the remote server stores the final physical examination item set, and meanwhile, the final physical examination item set is sent to the doctor terminal to complete the selection of the physical examination items; if not, the step of S4 is iterated until the user terminal receives and modulates the selectable physical examination item sets to obtain a final physical examination item set, the final physical examination item set input by the user terminal is received, and meanwhile, the final physical examination item set is sent to the doctor terminal to complete the selection of the physical examination items.
In step S2, the user feature set is constructed by the multiple pieces of second key feature information, and the specific steps are as follows:
the calculation of the similarity between each piece of first key feature information and the features in the feature knowledge base is as follows:
wherein,
is the feature vector of the first set of key feature information,
the feature vectors in the feature knowledge base;
the maximum feature similarity is as follows:
Max(Ca,i)＝Max{Ca,1,...,Ca,i,...,Ca,n}(i＝1...n)
where i is an index of the feature vector in the feature knowledge base.
And if the maximum feature similarity meets the similarity threshold, adding second key feature information corresponding to the maximum feature similarity into the user feature set, and if the maximum feature similarity does not meet the similarity threshold, taking the key feature information corresponding to the maximum feature similarity as third key feature information and deleting the third key feature information.
In step S3, the mapping of the user feature set to obtain a plurality of recommended physical examination items includes, as shown in fig. 2, the following steps:
the feature dictionary includes:
feature similarity CaComprises the following steps: ca＝Max(Ca,i)；
Characteristic weight WFa(ii) (demographic characteristics, health history characteristics, physical symptom characteristics, lifestyle characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics, health literacy characteristics };
type of characteristic TypeaComprises the following steps: non-type 1, frequency type 2, class type I, class II, class III, … …, class N3;
eigenvalue ValueaComprises the following steps: is invariable ═ 0,1]Frequency variable is [1,2,3 ]]Grade variable ═ 1,2, …, n]。
The specific steps of mapping the user feature set to obtain a plurality of physical examination items according to the user feature set are as follows:
based on a feature knowledge base, a physical examination item base and a decision support base in a decision support module, features in the feature knowledge base and physical examination items in the physical examination item base are respectively used as keys and values, the decision support base provides a mapping relation between the keys and the values, the keys and the values are stored in a key-value key value pair form of a HashMap, whether second key feature information exists in the HashMap as the keys or not is judged, if not, a null value is returned, and if yes, the value corresponding to the key is returned.
The physical examination item dictionary comprises:
item weight WIaComprises the following steps: WI (Wireless electric appliance)aRank 1 item, rank 2 item, rank 3 item };
physical examination frequency FIaComprises the following steps: FIa1: 1-2 years type 2:1 years type 3: 3-6 months };
recommended level LaComprises the following steps: l isa＝Ca×WFa×Fa×WIa；
Wherein, Fa＝na/N，naThe frequency of the physical examination items alpha in the recommended physical examination item set, N is the sum of all the physical examination items in the recommended physical examination item set, and the recommendation level LaBy feature similarity CaCharacteristic weight WFaFrequency of physical examination items FaAnd item weight WIaAnd (4) obtaining.
A personalized physical examination item recommendation apparatus based on a user health information feature set, as shown in fig. 3, comprising:
the user terminal is used for acquiring the user health investigation data, carrying out primary processing on the user health investigation data and sending the processed user health investigation data to the remote server, and comprises a human-computer interaction unit used for acquiring the user health investigation data and sending the user health investigation data to the data processing unit; the data processing unit is used for carrying out primary processing on the input user health investigation data and sending a processing result to the inter-terminal communication unit, and the inter-terminal communication unit sends the received processing result to the remote server through the communication network;
the user terminal is also used for receiving the recommended physical examination item set sent by the remote server, autonomously selecting the physical examination items to obtain a user selected physical examination item set, and sending the user selected physical examination item set to the remote server, wherein the human-computer interaction unit receives the recommended physical examination item set sent by the remote server and sends the user selected physical examination item set selected by the user to the data processing unit, the data processing unit confirms submission and sends the user selected physical examination item set to the inter-terminal communication unit, and the inter-terminal communication unit is used for sending the received user selected physical examination item set to the remote server through a communication network;
the user terminal is also used for receiving the modulated optional physical examination item set sent by the remote server and confirming whether the modulated optional physical examination item set is accepted or not, if so, the modulated optional physical examination item set and the optional item set are used as a final physical examination item set, the final physical examination item set is sent to the remote server, if not, a submission item is reselected until the user terminal receives the modulated optional physical examination item set to obtain the final physical examination item set, the final physical examination item set input by the user terminal is received, meanwhile, the final physical examination item set is sent to the remote server to complete the physical examination item selection, wherein, the human-computer interaction unit is used for receiving the modulated optional physical examination item set sent by the remote server and sending the result whether the user accepts to the data processing unit, if so, the final physical examination item set is generated and the final physical examination item set is sent to the inter-terminal communication unit, if the final physical examination item set is not accepted, the recommended physical examination item set is reselected, and the inter-terminal communication unit is used for accepting the final physical examination item set and sending the final physical examination item set to the remote server through the communication network;
the clinical terminal comprises a physical examination system and a doctor terminal, the physical examination system is used for sending stored user historical physical examination data to a remote server, the doctor terminal is used for adjusting a second information characteristic set and a selectable item set sent by the remote server to obtain a modulated selectable physical examination item set, sending the modulated selectable physical examination item set to the remote server and receiving a final physical examination item set, the doctor terminal comprises a human-computer interaction unit, a data processing unit and an inter-terminal communication unit, the human-computer interaction unit is used for receiving the second information characteristic set and the selectable item set, sending the modulated selectable physical examination item set adjusted by a doctor to the data processing unit, receiving the final physical examination item set and sending the modulated physical examination item set to the data processing unit, and the data processing unit is used for receiving the modulated physical examination item set, sending an instruction to an inter-terminal communication unit, wherein the inter-terminal communication unit is used for sending the modulated physical examination item set to a remote server;
the remote server comprises a data communication unit, a data processing unit and a data storage unit, wherein the data communication unit comprises an input checker, a resolver and an output generator, the input checker is used for receiving the user health investigation data, the user historical physical examination data, the user selected physical examination item set, the modulated optional physical examination item set, the final physical examination item set, and the output generator is used for outputting a recommended physical examination item set, a second key characteristic information set, the user selected physical examination item set, the modulated optional physical examination item set and the final physical examination item set;
a data processing unit comprising: the characteristic calculation module is used for calculating the similarity between each piece of first key characteristic information and the characteristics in the characteristic knowledge base as follows:
wherein,
is the feature vector of the first set of key feature information,
the feature vectors in the feature knowledge base;
the maximum feature similarity is as follows:
Max(Ca,i)＝Max{Ca,1,…,Ca,i,...,Ca,n}(i＝1…n)
where i is an index of the feature vector in the feature knowledge base.
And if the maximum feature similarity meets the similarity threshold, adding second key feature information corresponding to the maximum feature similarity into the user feature set, and if the maximum feature similarity does not meet the similarity threshold, taking the key feature information corresponding to the maximum feature similarity as third key feature information and deleting the third key feature information.
The feature dictionary includes:
feature similarity CaComprises the following steps: ca＝Max(Ca,i)；
Characteristic weight WFa(ii) (demographic characteristics, health history characteristics, physical symptom characteristics, lifestyle characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics, health literacy characteristics };
type of characteristic TypeaComprises the following steps: non-type 1, frequency type 2, class type I, class II, class III, … …, class N3;
eigenvalue ValueaComprises the following steps: is invariable ═ 0,1]Frequency variable is [1,2,3 ]]Grade variable ═ 1,2, …, n]；
And the recommendation rule module is based on the feature knowledge base, the physical examination item base and the decision support base in the decision support module, the features in the feature knowledge base and the physical examination items in the physical examination item base are respectively used as keys and values, the decision support base provides a mapping relation between the keys and the values, the keys and the values are stored in a key-value key value pair form of the HashMap, whether the second key feature information exists in the HashMap as the keys or not is judged, if not, a null value is returned, and if yes, the value corresponding to the keys is returned.
The physical examination item dictionary comprises:
item weight WIaComprises the following steps: WI (Wireless electric appliance)aRank 1 item, rank 2 item, rank 3 item };
physical examination frequency FIaComprises the following steps: FIa1: 1-2 years type 2:1 years type 3: 3-6 months };
recommended level LaComprises the following steps: l isa＝Ca×WFa×Fa×WIa；
Wherein, Fa＝na/N，naThe frequency of the physical examination items alpha in the recommended physical examination item set is N, and the sum of all the physical examination items in the recommended physical examination item set is N.
A decision support module comprising: the system comprises a characteristic knowledge base, a physical examination item base and a decision support base, wherein the characteristic knowledge base is used for a remote server and is based on the existing characteristic knowledge base, the characteristic knowledge base comprises demographic characteristics, health history characteristics, body symptom characteristics, life style characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics and health literacy characteristics, the obtained user health investigation data and the user historical physical examination data are segmented to obtain a plurality of text data, first key characteristic information in each text data is extracted, and a first key characteristic information set is formed; the system is used for providing a mapping relation between a user characteristic set and physical examination items by a remote server based on the existing decision support library; the remote server is used for providing necessary physical examination items and optional physical examination items based on the existing physical examination item library;
and the data storage equipment is used for storing the recommended physical examination item set, the final physical examination item set and the original data in the data processing process, preparing for calling the data at any time, and storing an original database, a characteristic knowledge base, a physical examination item base and a decision support base.
Claims (9)
1. A personalized physical examination item recommendation method based on a user health information characteristic set comprises the following steps:
s1: receiving user health research data input by a user terminal and user historical physical examination data input by a physical examination system;
s2: based on the existing feature knowledge base, segmenting the acquired user health investigation data and user historical physical examination data to obtain a plurality of text data, extracting first key feature information in each text data, forming a first key feature information set, calculating feature similarity between each first key feature information and the feature knowledge base by traversing the first key feature information set to obtain maximum feature similarity, judging whether the maximum feature similarity meets a similarity threshold, taking the first key feature information corresponding to the maximum feature similarity meeting the similarity threshold as second key feature information, and constructing a user feature set by a plurality of second key feature information;
s3: mapping the user feature set by using a key value pair of the HashMap to obtain a plurality of physical examination items, constructing a recommended physical examination item set by the plurality of physical examination items, and selecting the physical examination items by the user terminal based on the recommended physical examination item set.
2. The personalized physical examination item recommendation method based on the user health information feature set is characterized in that second key feature information in the user feature set is described through a constructed feature dictionary, wherein the feature dictionary comprises:
feature similarity CaComprises the following steps: ca＝Max(Ca,i)；
Characteristic weight WFaComprises the following steps: WFa(ii) (demographic characteristics, health history characteristics, physical symptom characteristics, lifestyle characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics, health literacy characteristics };
type of characteristic TypeaComprises the following steps: non-type 1, frequency type 2, class type I, class II, class III, … …, class N3;
eigenvalue ValueaComprises the following steps: is invariable ═ 0,1]Frequency variable is [1,2,3 ]]Grade variable ═ 1,2, …, n]。
3. The personalized physical examination item recommendation method based on the user health information feature set as claimed in claim 2, wherein the physical examination items in the recommended physical examination item set are described by a constructed physical examination item dictionary, wherein the physical examination item dictionary comprises:
item weight WIaComprises the following steps: WI (Wireless electric appliance)aRank 1 item, rank 2 item, rank 3 item };
physical examination frequency FIaComprises the following steps: FIa1: 1-2 years type 2:1 years type 3: 3-6 months };
recommended level LaComprises the following steps: l isa＝Ca×WFa×Fa×WIa；
Wherein, FaFrequency of physical examination items, Fa＝na/N，naThe frequency of the physical examination items a in the recommended physical examination item set, N is the sum of all the physical examination items in the recommended physical examination item set, and the recommendation level LaFeatures of passingSign degree of similarity CaCharacteristic weight WFaFrequency of physical examination items FaAnd item weight WIaAnd (4) obtaining.
4. The method for recommending personalized physical examination items based on the user health information feature set according to claim 1, wherein the step of mapping the user feature set to obtain a plurality of physical examination items comprises:
based on a feature knowledge base, a physical examination item base and a decision support base in a decision support module, features in the feature knowledge base and physical examination items in the physical examination item base are respectively used as keys and values, the decision support base provides a mapping relation between the keys and the values, the keys and the values are stored in a key-value key value pair form of a HashMap, whether second key feature information exists in the HashMap as the keys or not is judged, if not, a null value is returned, and if yes, the value corresponding to the key is returned.
5. The method for recommending personalized physical examination items based on the user health information feature set of claim 1, wherein the calculating the feature similarity between each first key feature information and the feature knowledge base comprises:
wherein,
is the feature vector of the first set of key feature information,
the feature vectors in the feature knowledge base;
the maximum feature similarity is as follows:
Max(Ca,i)＝Max{Ca,1,...,Ca,i,...,Ca,n}(i＝1...n)
where i is an index of the feature vector in the feature knowledge base.
6. The method for recommending personalized physical examination items based on a user health information feature set of claim 1, wherein the user health research data comprises demographic data, health history data, physical symptom data, lifestyle data, environmental health data, mental health data, sleep health data, and health literacy data;
the health history data comprises family history data, current medical history data, allergy history data, medication history data, surgical history data and menstruation fertility history data;
the lifestyle data includes diet data, smoking data, drinking data, and exercise data.
7. The method as claimed in claim 1, wherein the characteristic knowledge base comprises demographic characteristics, health history characteristics, physical symptom characteristics, lifestyle characteristics, environmental health characteristics, mental health characteristics, sleep health characteristics, and health literacy characteristics.
8. The method for recommending personalized physical examination items based on the user health information feature set of claim 1, wherein if the maximum feature similarity is greater than or equal to a similarity threshold, the second key feature information corresponding to the maximum feature similarity is added to the user feature set, and if the maximum feature similarity is less than the similarity threshold, the key feature information corresponding to the maximum feature similarity is used as the third key feature information and the third key feature information is deleted.
9. The method for recommending personalized physical examination items based on the user health information feature set according to claim 1, wherein the specific steps of selecting the physical examination items based on the recommended physical examination item set by the user terminal are as follows:
s31: the remote server sends the recommended physical examination item set to a user terminal, receives a user-selected physical examination item set input by the user terminal, reserves a necessary physical examination item set, sends a second key characteristic information set and a selectable physical examination item set to a doctor terminal, and receives a modulated selectable physical examination item set input by the doctor terminal;
s32: and the remote server sends the modulated optional physical examination item set to the user terminal, if the user terminal does not accept the modulated optional physical examination item set, the step S31 is iterated until the user terminal accepts the modulated optional physical examination item set to obtain a final physical examination item set, the final physical examination item set input by the user terminal is received, and meanwhile, the final physical examination item set is sent to the doctor terminal to complete the selection of the physical examination items.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110731371.7A CN113488168A (en) | 2021-06-30 | 2021-06-30 | Personalized physical examination item recommendation method based on user health information characteristic set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110731371.7A CN113488168A (en) | 2021-06-30 | 2021-06-30 | Personalized physical examination item recommendation method based on user health information characteristic set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113488168A true CN113488168A (en) | 2021-10-08 |
Family
ID=77936934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110731371.7A Pending CN113488168A (en) | 2021-06-30 | 2021-06-30 | Personalized physical examination item recommendation method based on user health information characteristic set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113488168A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114329198A (en) * | 2021-12-27 | 2022-04-12 | 海信集团控股股份有限公司 | Method and device for recommending health information based on user sleep |
| CN116030984A (en) * | 2023-03-31 | 2023-04-28 | 武汉携康智能健康设备有限公司 | User physical examination system and physical examination method based on intelligent health station |
| CN116864062A (en) * | 2023-09-04 | 2023-10-10 | 山东普瑞森医疗设备股份有限公司 | Health physical examination report data analysis management system based on Internet |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025368A (en) * | 2016-01-29 | 2017-08-08 | 北京弘达君康健康科技有限公司 | The self-service method for customizing and system of physical examination project alternative are obtained for physical examination of healthy population |
| CN110097199A (en) * | 2018-01-31 | 2019-08-06 | 深圳市前海安测信息技术有限公司 | Physical examination self-service reservation system and method based on medical history |
| CN110797115A (en) * | 2019-10-26 | 2020-02-14 | 曹庆恒 | Intelligent recommended medical examination and inspection method, system and equipment |
| CN112071385A (en) * | 2020-09-23 | 2020-12-11 | 广州瀚信通信科技股份有限公司 | Rare disease auxiliary analysis method and device based on artificial intelligence and storage medium |
| CN112232556A (en) * | 2020-09-29 | 2021-01-15 | 江苏苏宁物流有限公司 | Product recommendation method and device, computer equipment and storage medium |
-
2021
- 2021-06-30 CN CN202110731371.7A patent/CN113488168A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025368A (en) * | 2016-01-29 | 2017-08-08 | 北京弘达君康健康科技有限公司 | The self-service method for customizing and system of physical examination project alternative are obtained for physical examination of healthy population |
| CN110097199A (en) * | 2018-01-31 | 2019-08-06 | 深圳市前海安测信息技术有限公司 | Physical examination self-service reservation system and method based on medical history |
| CN110797115A (en) * | 2019-10-26 | 2020-02-14 | 曹庆恒 | Intelligent recommended medical examination and inspection method, system and equipment |
| CN112071385A (en) * | 2020-09-23 | 2020-12-11 | 广州瀚信通信科技股份有限公司 | Rare disease auxiliary analysis method and device based on artificial intelligence and storage medium |
| CN112232556A (en) * | 2020-09-29 | 2021-01-15 | 江苏苏宁物流有限公司 | Product recommendation method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 贾珺: "Java程序设计教程（第2版）》", 航空工业出版社, pages: 157 - 161 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114329198A (en) * | 2021-12-27 | 2022-04-12 | 海信集团控股股份有限公司 | Method and device for recommending health information based on user sleep |
| CN116030984A (en) * | 2023-03-31 | 2023-04-28 | 武汉携康智能健康设备有限公司 | User physical examination system and physical examination method based on intelligent health station |
| CN116864062A (en) * | 2023-09-04 | 2023-10-10 | 山东普瑞森医疗设备股份有限公司 | Health physical examination report data analysis management system based on Internet |
| CN116864062B (en) * | 2023-09-04 | 2023-11-21 | 山东普瑞森医疗设备股份有限公司 | Health physical examination report data analysis management system based on Internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696675B (en) | User data classification method and device based on Internet of things data and computer equipment | |
| Amal et al. | Use of multi-modal data and machine learning to improve cardiovascular disease care | |
| CN113488168A (en) | Personalized physical examination item recommendation method based on user health information characteristic set | |
| CN103690240B (en) | A kind of medical system | |
| US7617078B2 (en) | Patient data mining | |
| KR101497690B1 (en) | Method and system providing healthcare program service based on bio-signals and symptoms information | |
| US20080033894A1 (en) | Prognosis Modeling From One or More Sources of Information | |
| CN111475713A (en) | Doctor information recommendation method and device, electronic equipment, system and storage medium | |
| US20170147753A1 (en) | Method for searching for similar case of multi-dimensional health data and apparatus for the same | |
| US11581094B2 (en) | Methods and systems for generating a descriptor trail using artificial intelligence | |
| CN114067940A (en) | Health management method and storage medium | |
| CN110491475A (en) | A kind of menu recommendation process method and device | |
| CN115579104A (en) | Artificial intelligence-based liver cancer full-course digital management method and system | |
| Li et al. | Association rule-based breast cancer prevention and control system | |
| CN114783580B (en) | Medical data quality evaluation method and system | |
| CN110299207A (en) | For chronic disease detection in based on computer prognosis model data processing method | |
| Inbar et al. | A machine learning approach to the interpretation of cardiopulmonary exercise tests: Development and validation | |
| CN117271804A (en) | Method, device, equipment and medium for generating common disease feature knowledge base | |
| CN115798662A (en) | Case transport analysis system for hospital case management based on artificial intelligence algorithm | |
| Fu et al. | Data-driven preference learning in multiple criteria decision making in the evidential reasoning context | |
| WO2022141925A1 (en) | Intelligent medical service system and method, and storage medium | |
| Diamantoulaki et al. | Health risk assessment with federated learning | |
| CN113220895A (en) | Information processing method and device based on reinforcement learning and terminal equipment | |
| JP6152678B2 (en) | Information processing method, apparatus and program | |
| Fuhrman et al. | Cascaded deep transfer learning on thoracic CT in COVID-19 patients treated with steroids |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |