CN112890816A - Health index scoring method and device for individual user - Google Patents
Health index scoring method and device for individual user Download PDFInfo
- Publication number
- CN112890816A CN112890816A CN202011448477.8A CN202011448477A CN112890816A CN 112890816 A CN112890816 A CN 112890816A CN 202011448477 A CN202011448477 A CN 202011448477A CN 112890816 A CN112890816 A CN 112890816A
- Authority
- CN
- China
- Prior art keywords
- data
- health
- dimension
- index
- score
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4815—Sleep quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- 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
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- 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
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Evolutionary Computation (AREA)
- Educational Technology (AREA)
- Anesthesiology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本发明的一个技术方案是提供了一种个人用户的健康指数评分方法。本发明的另一个技术方案是提供了一种个人用户的健康指数评分装置。本发明通过采集与目标用户的健康指数相关联的多个维度数据，采用统计方法得到多个维度中各个维度的特征变量，分别输入各个维度对应的维度评分模型，得到维度分值，最后，基于健康指数分评分模型得到目标用户的健康指数分值，形成一个“1+N”的综合性健康水平评价体系，为健康管理新模式、个性化健康险定价以及自我驱动的健康管理提供量化指标，也为主动健康管理规范的制定、分析、评估和优化提供量化支持。
A technical solution of the present invention is to provide a health index scoring method for individual users. Another technical solution of the present invention is to provide a personal user health index scoring device. The present invention collects multiple dimensional data associated with the target user's health index, adopts a statistical method to obtain the characteristic variables of each dimension in the multiple dimensions, respectively inputs the dimension scoring model corresponding to each dimension, and obtains the dimension score, and finally, based on The health index scoring model obtains the target user's health index score, forming a "1+N" comprehensive health level evaluation system, providing quantitative indicators for new health management models, personalized health insurance pricing and self-driven health management. It also provides quantitative support for the formulation, analysis, evaluation and optimization of active health management practices.
Description
Technical Field
The invention relates to a health index scoring method and a health index scoring device for an individual user, and belongs to the technical field of data processing and health management.
Background
In traditional cognition, health is often limited to a narrow range-the body is not sick. With the improvement of living standard and the transformation of thinking mode, the scope of health administration is getting larger and larger. On the one hand, the concept of health has been extended from organic diseases to the physical and mental aspects of people and their lives. On the other hand, health breaks through a single hospital medical scene and extends to daily life scenes such as clothes and eating houses. In recent years, with the sufficient development of mobile interconnection, IOT, big data and artificial intelligence, health management is met with a new opportunity, and the traditional extensive and single health management mode is gradually changed into personalization, accessibility, precision, intelligence and digitization. The third aspect, the introduction of a risk management model such as "KYN (Know Your numbers)", further facilitates the exploration of a new model of health management. Fourth, Ulrik, a world-leading sports medical scientist
The personal motor function index PAI developed by the professor can be used as an easily understood activity tracking index to better help the user to manage self health without paying attention to a complicated physical data index item and only paying attention to the PAI data to help the user to keep the optimal health state. The research shows that PAI helpsThe improvement of the heart and lung function (such as heart health condition) has a great effect, 100PAI can greatly reduce the risk of cardiovascular diseases of users, and can bring about 60% of health benefits to the users if only 50PAI is achieved, and the users quantify the self exercise condition through PAI and put into practice to carry out self health management, which is a powerful attempt of quantifying indexes in personal health management.
Therefore, under a new opportunity, a health management mode based on data driving and an active health management mode come, and the core of the health management mode different from the traditional health management mode is that the health management mode has an index for comprehensively quantifying the personal health level and a whole set of personalized promotion scheme, can be applied to personalized health management and self-driven health management, and also provides quantitative support for the formulation, analysis, evaluation and optimization of active health management and digital health management specifications.
Chinese patent CN104850758A discloses a health index scoring method, but the focused evaluation index focuses only on physiological indexes. The world health organization states in the declaration "health not only as no disease or debilitation, but rather as a state of perfect health of physiological, psychological and social functions" and thus affecting the level of health is the result of a comprehensive evaluation of multiple dimensions. In 2009, 18 th 9 th, the Chongqing city publishes the first national index system for citizen health self-assessment, which is divided into six system indexes of physique dimension, physiological dimension, psychological dimension, birth dimension, diet dimension and behavior dimension. According to the evaluation system, citizens can intuitively understand their own health conditions so as to perform health intervention or self health promotion. Therefore, exploring a way to evaluate the health level of an individual by using data is significant for a new health management mode facing the future.
Disclosure of Invention
The purpose of the invention is: a health index score based on the personal health related data is achieved.
In order to achieve the above object, one aspect of the present invention provides a method for scoring a health index of an individual user, including the steps of:
collecting health data relating to a target user health index score, the health data comprising: data of multiple dimensions related to the health index score of the target user and personal basic information data; the plurality of dimensions includes:
a physiological health dimension reflecting data related to the physiological health of the target user to be scored;
a mental health dimension reflecting data related to the mental health of the target user to be scored;
the health behavior dimension reflects data related to the health behaviors of the target user to be scored;
a disease status dimension reflecting data related to the target user's disease status to be scored;
a health environment dimension reflecting data related to the health environment of the target user to be scored;
a health care dimension reflecting data related to the health care of the target user to be scored;
obtaining the characteristic variable of each dimension in the multiple dimensions from the data of the multiple dimensions according to a statistical method;
inputting the feature variable of each dimension in the multiple dimensions into a corresponding dimension scoring model of each dimension to obtain a score of each dimension in the multiple dimensions; the dimension scoring model of each dimension is obtained by pre-training according to the sample data of the dimension;
inputting the score of each dimension and the characteristic variable of each dimension into a health index scoring model to obtain the health index score of a target user; the health index scoring model is obtained by pre-training according to sample data.
Preferably, the data reflecting the physiological health of the target user to be scored comprises sign data, body circumference data, body composition data and model data;
the data reflecting the psychological health of the target user to be scored comprises environmental adaptation data, emotion control data, self-consciousness data, contusion response data, self-potential data and emotional data; the environment adaptation data comprises data for describing the state of the individual and the external relationship, social blending feeling rating data for measuring the adaptability of a person to the real environment, and solitary feeling rating data for measuring a closed psychology of the person; the emotional control data reflects the individual's ability to control emotions, mental activities, and word behavior; the self-awareness data reflects an internal mental state; the frustration response data reflects whether an individual can control and adjust own behaviors to achieve the purpose of overcoming various difficulties; the self-potential data reflects whether the individual can actively mine self potential or not, and the personal value can be creatively realized;
the data reflecting the health behavior of the target user to be scored comprises life habit data, exercise habit data, diet preference data, sleep condition data and model data; the living habit data is used for describing daily living habits of the user; the exercise habit data is used for describing exercise habits of the user; the dietary preference data is used to describe a user's dietary preference; the sleep condition data is used for describing the sleep condition of the user;
the data related to reflecting the disease state of the target user to be scored comprises past history data, operation history data, family history data, medication history data, allergy history data and risk assessment model data; the past history data is used for describing the past medical history of the user, and more data can be formed according to disease system typing and finer granularity segmentation of disease typing; the surgical history data is used to describe a surgical history of the user; the family history data is used for describing family history of the user; the medication history data is used for describing the medication history of the user and can be segmented according to disease classification and fine granularity; the allergy history data is used for describing the allergy history of the user; the risk assessment model data are obtained by mining a user disease risk or comprehensive risk model;
the data reflecting the correlation with the health environment of the target user to be evaluated comprises natural environment data and life and working environment data;
the data reflecting the health guarantee correlation of the target user to be scored comprises personal and family guarantee data and social guarantee data.
Preferably, the obtaining the feature variable of each of the dimensions from the data of the dimensions according to a statistical method includes the following steps:
preprocessing data;
selecting an index set, and selecting the index set on which the score of each dimension depends in a plurality of dimensions by adopting a statistical method, wherein the index set consists of an atomic index and a derivative index;
and characterizing data, each index item of the index set is characterized.
Preferably, when each index item is characterized, the index features are ordered according to the principle that the larger the score of the health index score and the score of the dimension score is, the better health promotion level is in a comparable population, and when the index features are ordered, negative indexes, intermediate indexes and interval indexes are uniformly converted according to positive indexes.
Preferably, the dimension scoring model comprises a supervised model and an expert model, wherein:
the expert model is characterized in that a health management expert determines the weight of each index by adopting a weight calculation algorithm according to an initial reliable index set formed in the step, and then obtains the dimension grading model by adopting a weighting algorithm;
and the supervised model divides the characteristic data into a positive sample and a negative sample based on the characteristic data, the historical health level of the population of the positive sample is superior to the historical health level of the population of the negative sample, and the dimension scoring model of each dimension is trained according to the data of each dimension.
Preferably, the scoring indexes of the dimension scoring models of the dimensions are different, emphasis is placed on the scoring indexes according to different preconditions, combinations of preconditions are superimposed on the formed feature variables of the dimensions, the feature variables are reselected, and corresponding dimension scoring models are trained on the selected feature variable sets.
Preferably, the health index score model is composed of a basic health score and a health promotion score, the basic health score is calculated from the non-intervention index, and the health promotion score is calculated from the intervention index.
Preferably, the health index score and the score of each dimension may be standardized, and the score standardization standardizes the score of the health index score and the score of the dimension of the target user to corresponding business partitions according to the business partition dividing standard of the business system scored by the health index of the target user.
Another aspect of the present invention provides a health index scoring apparatus for an individual user, including:
a data collection module for collecting health data related to a target user health index score, the health data comprising: a dataset personal base information data of a plurality of dimensions relating to the health index score of the target user;
the plurality of dimensions includes: a physiological health dimension reflecting data related to the physiological health of the target user to be scored;
a mental health dimension reflecting data related to the mental health of the target user to be scored;
the health behavior dimension reflects data related to the health behaviors of the target user to be scored;
a disease status dimension reflecting data related to the target user's disease status to be scored;
a health environment dimension reflecting data related to the health environment of the target user to be scored;
a health care dimension reflecting data related to the health care of the target user to be scored;
the characteristic data module is used for obtaining the characteristic variable of each dimension in the dimensions by utilizing a statistical method according to the data of the dimensions;
the dimension score calculation module is used for respectively inputting the characteristic variables of each dimension in the dimensions into a dimension scoring model corresponding to the dimension and calculating the dimension score corresponding to the dimension, wherein the scoring model of each dimension in the dimensions is obtained by pre-training according to sample data of the dimension;
and the health index score calculation module is used for inputting the scores of all the dimensions and the characteristic variables of all the dimensions into a pre-trained health index score model to obtain the health index score of the target user, wherein the health index score model is obtained by pre-training according to sample health data.
Preferably, the health index scoring means further comprises:
the preposed rule module is used for calling a corresponding statistical method according to the rules to obtain characteristic variables, calculate dimensionality values and health index values according to different preposed conditions, provide the preset preposed conditions of age and gender and support updating of the preposed conditions;
the standardization module is used for standardizing the health index score obtained by the health index scoring model and the dimension score obtained by each dimension scoring model into a service partition and providing interpretable service partition labels;
the index reading module is used for feeding back health reading to a target user from the point of view of the score and the index according to a preset rule, helping the user to know self health influence factors, providing an auxiliary health management guidance scheme and providing an incentive scheme for promoting health;
the knowledge base module is used for managing a constituent index set of the health index score and the dimension score and whether the function of interventionality is provided;
and the model management module is used for managing the training of the health index scoring model and the dimension scoring model.
The invention provides a method and a device for scoring health indexes of individual users, which are characterized in that a plurality of dimensional data associated with the health indexes of target users are collected, characteristic variables of each dimension in the plurality of dimensions are obtained by adopting a statistical method, dimension scoring models corresponding to the dimensions are respectively input to obtain dimension scores, finally, the health index scores of the target users are obtained based on the health index scoring models, a 1+ N comprehensive health level evaluation system is formed, quantitative indexes are provided for a new health management mode, personalized health risk pricing and self-driven health management, and quantitative support is provided for formulation, analysis, evaluation and optimization of active health management specifications.
Drawings
FIG. 1 illustrates a method for scoring a health index of an individual user in accordance with at least one embodiment of the present disclosure;
FIG. 2 illustrates various dimensions of a health index score for an individual user and data categories associated with the dimensions, as provided in at least one embodiment of the present description;
FIG. 3 is a health index scoring apparatus for an individual user provided in at least one embodiment of the present description;
FIG. 4 is a health index scoring apparatus for an individual user provided in at least one embodiment of the present description;
fig. 5 is a schematic structural diagram of a health index "1 + N" score result of an individual user provided in at least one embodiment of the present specification.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
On the other hand, with the great development of mobile internet and IOT, the collection of personal health information is easier than before, people begin to rely on these data for daily health management, and changes in health data such as blood pressure, blood sugar, heart rate, weight, and exercise condition gradually affect the personal health level. On the other hand, the factors affecting health can be classified into interventable factors and non-interventable factors, and health management needs to be started from multiple dimensions, so that a new personalized, accessible, precise, intelligent and digital mode is formed. Based on the above, exploring a way of evaluating the personal health level by using data is significant for a new health management mode facing the future, and provides quantitative tongs for personalized health management and self-driven health management.
To this end, the present invention provides an implementation of a health level quantitative index, namely an implementation of a health index, which describes that there is not a real health risk from the perspective of medical diagnosis, but rather a multi-dimensional comprehensive score based on health data of an individual user, and is a quantitative index that is comparable to a population, comprehensive, time-varying, and individual difference, and can improve or avoid certain factors by influencing indexes included in multiple dimensions associated with the health index, so as to achieve the effect of promoting health, and play a role in comprehensive perception, self-motivation, and decision assistance.
Referring to fig. 1, a method for scoring a health index of an individual user according to at least one embodiment of the present invention includes the following steps:
step 101: collecting health data relating to a target user health index score, the health data comprising: data of multiple dimensions related to the health index score of the target user and personal basic information data;
step 102: obtaining the characteristic variable of each dimension in the multiple dimensions from the data of the multiple dimensions according to a statistical method;
step 103: inputting the feature variable of each dimension in the multiple dimensions into the corresponding scoring model of each dimension to obtain the score of each dimension in the multiple dimensions; the scoring model of each dimension in the multiple dimensions is obtained by pre-training according to the sample data of the dimension;
step 104: inputting the score of each dimension and the characteristic variable of each dimension into a health index scoring model to obtain the health index score of a target user; the health index scoring model is obtained by pre-training according to sample data.
In step 101, the collected data of multiple dimensions related to the health index score of the target user includes at least one of the following items:
data related to the physiological health of the target user to be scored is reflected;
reflecting the target user mental health related data to be scored;
data related to the target user health behaviors to be scored is reflected;
data related to reflect the target user disease state to be scored;
data related to the target user health environment to be scored is reflected;
reflecting data related to the target user health care to be scored.
Referring to fig. 2, each dimension of the personal user health index score and the associated data category in an embodiment are illustrated, and the data category of each dimension is described in the following with reference to fig. 2 by way of example, it should be noted that the data category of each dimension described below is also exemplary, and the actual implementation is not limited to the following data, and there are differences according to some pre-condition settings described above, specifically:
a physiological health dimension reflecting data related to the physiological health of the target user to be scored, such as:
1) sign data: data related to physical signs of an individual user, obtained or calculated through channels such as an IOT device or a health profile, for example: electrocardio, blood oxygen saturation, blood sugar, blood pressure, heart rate, body temperature and other data;
2) body circumference data: data related to the body circumference of an individual user, which is acquired or calculated through channels such as an IOT device or a health record, for example: height, weight, chest circumference, waist circumference, hip circumference, arm circumference, thigh circumference, shank circumference, BMI;
3) body composition data: data related to body components of an individual user, which are acquired or calculated through channels such as an IOT device or a health profile, for example: body fat, muscle mass, water, basal metabolism, subcutaneous fat rate, bone mass, bone density, etc.;
4) model data: data obtained by a specific evaluation model, such as fatigue degree obtained by a fatigue scale-14, constitution score obtained by a traditional Chinese medicine constitution identification scale, whether pregnant women exist, and the like.
A mental health dimension reflecting data related to the mental health of the target user to be scored, for example:
1) environmental adaptation data: data obtained by a particular evaluation model, pertaining to the state description of the individual's relationship to the outside, such as: the social integration rating data for measuring the adaptability of a person to the real environment can be obtained through a social support rating scale; data for rating autism to measure a closed psychology of a person, wherein, in general, transient or accidental autism does not cause mental behavior disorder, but long-term or severe autism can cause certain emotional disorders and reduce the mental health level of the person, such as data obtained from UCLA autism volume table;
2) mood control data: data obtained through a specific evaluation model reflects the self-control ability of an individual on emotion, thinking activity and speech behavior, such as the sentiment rating data obtained by an international standard sentiment rating scale or a baron sentiment rating scale;
3) self-awareness data: the data obtained by a particular assessment model is an important aspect of the internal mental state, which is expressed as whether or not self-satisfaction, self-awareness is clear, such as the level of confidence obtained by the Rosenberg confidence Scale;
4) frustration deals with data: the data obtained by a specific evaluation model reflects whether an individual can govern and regulate own behaviors so as to achieve the purpose of overcoming various difficulties, such as the willingness rating data obtained by a willingness scale;
5) self potential data: data obtained through a specific evaluation model reflects whether an individual can actively mine the potential of the individual, and the value of the individual can be creatively realized, for example, creativity rating data obtained through a Williams creativity tendency test table;
6) emotional feeling: data obtained by a particular assessment model is an important assessment component of mental health, including but not limited to, psychological stress index, depression level, anxiety level, and often such data can lead to a number of negative emotional experiences, which in turn lead to mental health problems. The specific assessment model includes but is not limited to a psychological stress index rating scale, a PHQ-9 depression screening scale, a Becker depression self-rating scale, a Hamilton depression scale-HAMD, a GAD-7 anxiety self-rating scale, a mood self-rating scale, a depression-anxiety-stress scale (DASS-21) and the like, an Edinburgh Postpartum Depression Scale (EPDS) can be included for postpartum people, and a children social interaction anxiety rating scale (SASC) and the like can be included for children.
A health behavior dimension reflecting data related to the health behavior of the target user to be scored, such as:
1) lifestyle data: data describing the daily habits of a user, such as: smoking frequency, single smoking amount, drinking frequency, single drinking amount, defecation condition, defecation duration and urination condition;
2) exercise habit data: data describing the exercise habits of a user, such as: exercise frequency, exercise mode, exercise heart rate maintenance level, calorie consumption, step number, exercise load EPOC and other data;
3) dietary preference data: data describing dietary preferences of a user, such as: dietary taste, spicy taste preference, vegetable preference, fruit preference, drinking preference, and the like;
4) sleep condition data: data describing the sleep condition of the user, for example: the sleep quality can be obtained by evaluating the sleep condition self-evaluation table, the Pittsburgh sleep quality index and other evaluation tables;
5) model data: for example: health knowledge watching or reading times, personal motor function index PAI and the like.
A disease status dimension reflecting data related to the disease status of the target user to be scored, such as:
1) past history data: data describing the user's past medical history, such as: whether the patient suffers from malignant tumor, whether the patient suffers from respiratory system diseases, whether the patient suffers from hypertension, whether the patient suffers from rare diseases, whether the patient suffers from type 2 diabetes, the number of times of treatment, the interval of treatment, the number of serious diseases and the like, and more data can be formed according to the disease systematic typing and the finer-grained segmentation of the disease typing;
2) surgical history data: data describing the user's surgical history, such as: data such as the number of operations and whether operation infection occurs;
3) family history data: data describing the family history of the user, such as: data such as family history of lung cancer, family history of hypertension, family history of gout and the like;
4) medication history data: data describing the user's medication history, such as: the data such as the drug frequency, the drug compliance and the like can also be segmented according to disease classification and fine granularity;
5) allergy history data: data describing the user's allergy history, such as: data on rhinitis condition, whether allergic condition exists, etc.;
6) risk assessment model data: and (3) mining the obtained data through a user disease risk or comprehensive risk model, such as a Charlson syndrome index, an Elixhauser syndrome index, an improved Framingham stroke risk model, a type 2 diabetes risk assessment Findrisc model, a breast cancer risk prediction Gail model and the like.
A health environment dimension reflecting data related to the health environment of the target user to be scored, such as:
1) natural environment data: for example: air Quality Index (AQI), PM2.5 concentration, PM10 concentration, air humidity, etc.;
2) life and work environment data: for example: occupational exposure, residence conditions, duration of operation, etc.
A health care dimension reflecting data related to the health care of the target user to be scored, such as:
1) personal and family security data: whether to purchase data such as business health insurance, business health insurance premium rating, personal income/expense ratio, etc.;
2) social security data: whether to participate in social medical insurance, whether to participate in new agriculture and society, and the like.
Each dimension data of the above embodiment may be an internal factor affecting the health of the target user, or an external factor affecting the health of the target user; may be factors that already affect health and are not interventable, or may be factors that affect health and are interventable; differences may also exist due to authorized data acquisition channels, data sources owned by business parties, and groups to be evaluated.
In step 102, obtaining the feature variable of each of the multiple dimensions by using a statistical method generally includes the following steps:
data preprocessing, comprising: methods such as missing data processing and abnormal value processing belong to common data preprocessing means, and details are not repeated;
selecting an index set, selecting the index set on which each dimension in a plurality of dimensions depends by adopting a statistical method, wherein the index set consists of an atom index and a derivative index, the derivative method comprises common means such as a superposition time period and/or modifiers, a calculation difference, a calculation ratio and the like, and details are not repeated;
the characterizing data, which characterizes each index item of the index set, includes: the operations of feature coding, data discretization, data flattening, decimal scaling, standardization, principal component extraction and the like belong to common data characterization means, and details are not repeated;
in at least one embodiment, the index features are all ordered according to the principle that a greater health index score and a greater dimension score indicate a better level of health promotion in a comparable population. Specifically, when each index item is characterized, a negative index, a middle index and an interval index are converted according to the consistency of a positive index. The conversion method belongs to a common index consistency means, and details are not repeated.
Table 1 illustrates a portion of the index items of each dimension in at least one embodiment, and table 2 illustrates a process for characterizing an index in at least one embodiment, specifically:
the index of the most recent psychological stress assessment grade is divided into [0,31], discretization is firstly carried out and divided into 4 intervals, the 4 intervals respectively represent no stress, light stress, moderate stress and severe stress, and the 4 intervals belong to negative indexes relative to psychological health, so that positive processing is carried out during characterization, and positive operation is completed in a reverse order mode.
TABLE 1 index entries for multiple dimensions in one embodiment
TABLE 2 last mental stress assessment rating characterization procedure
| Discrete interval of psychological stress assessment result | Segmented meaning | Characterizing results |
| [0,5] | Without pressure | 4 |
| [6,10] | Mild stress | 3 |
| [11,20] | Moderate pressure | 2 |
| [20,31] | |
1 |
In step 103, inputting the feature variable of each of the multiple dimensions into the corresponding scoring model of each of the multiple dimensions to obtain a score of each of the multiple dimensions, where the scoring model of each of the multiple dimensions relied on in the process is obtained by pre-training sample data of the dimension, and generally includes a supervised model and an expert model, and is specifically implemented as follows:
and the expert model is characterized in that the health management expert determines the weight of each index by adopting a weight calculation algorithm according to an initial reliable index set formed in the step, and then obtains each dimension scoring model by adopting a weighting algorithm. In this embodiment, a Delphi method is used to determine a reliable index set, and an analytic hierarchy process is used to determine the weight of each index.
And (3) a supervised model, namely dividing the characteristic data into a positive sample and a negative sample based on the characteristic data obtained in the step (102), wherein the historical health level of the population of the positive sample is superior to the historical health level of the population of the negative sample, and further training the scoring model of each dimension according to the data of each dimension. The model used may be various, such as a random forest, a deep-learning sequence model, a support vector machine, an ensemble tree algorithm, a scorecard model, an Adaboost model, and the like. In addition, the positive and negative sample partitioning methods described herein, in at least one embodiment, partition into 2 classes in the form of clusters.
In at least one embodiment, in step 104, the dimension scores of the dimensions and the feature variables of the dimensions are input into a health index scoring model obtained through pre-training to obtain the health index scores of the users to be scored, and a training process of the pre-trained health index scoring model is similar to that of the dimension scoring model and is not repeated.
Referring to table 3, a part of the scoring index set and the weights trained by using the expert model in one embodiment are given, and the dimension score of the target user to be scored can be obtained by combining the feature data of each dimension input by the weights. The health index score is obtained by multiplying the index weight of each dimension by the characteristic variable of the target user to be evaluated, and the health index score is obtained by multiplying the combined weight by the characteristic variable of the target user to be evaluated.
TABLE 3 partial Scoring index set and weights for training with expert model in one embodiment
It is worth mentioning that after the scoring models of all dimensions and the health index scoring models start to be commercialized, user behaviors can be collected, users who promote health management by themselves and keep high health indexes for a long time are brought into a positive sample, and the dimension scoring models and the health index scoring models are continuously optimized.
The scoring indexes of the scoring models of all dimensions are different, and the emphasis is placed on the scoring indexes according to different preconditions. The precondition at least comprises age and gender, and can be added according to different countries, regions and ethnicities of the collected data. In one or more real-time examples, age and gender were selected as preconditions, with ages being divided between 0-18, 18-40, 41-65 and greater than 65, and gender being divided between male and female. And on the basis of the characteristic variables formed by each dimension of the multiple dimensions, superposing the combination of preconditions, reselecting the characteristic variables, and training a corresponding scoring model on the selected characteristic variable set. The training process is similar to the above-described scoring model for each dimension, and is not repeated. The feature variable selection can be formed by determining or selecting some features which have important influence on the dimensionality score by an expert model, and the importance of the feature variable on the score influence degree can be realized by adopting various methods such as information entropy, mutual information and the like.
The health index score model consists of a basic health score and a health promotion score, wherein the basic health score is obtained by calculating an irreplaceable index, and the health promotion score is obtained by calculating an interplaceable index. In at least one embodiment, the indicators are pre-classified into two categories, and then the base health score and the promoted health score are weighted from the corresponding set of indicators, the sum of which equals the health index score.
The health index score and the score for each dimension may be normalized. The score standardization can standardize the score of the health index score and the score of the dimensionality of the target user to the corresponding business partition according to the business partition dividing standard of the business system of the health index score of the target user.
In at least one embodiment, table 4 gives the maximum value of the health index score and the scores of the various dimensions taken as 100 points and normalized to 5 intervals.
TABLE 4 health index score and various dimension score normalization examples
| Model result partitioning | Normalized value | Normalized Interval interpretation |
| [0.85,1] | [85,100] | Is excellent in |
| [0.75,0.85) | [75,84] | Good effect |
| [0.6,0.75) | [60,74] | Medium and high grade |
| [0,0.6) | [0,59] | Is poor |
Table 5 shows a normalization scheme when the health index score and the maximum value of each dimension score are different, and an expansion coefficient is introduced to convert 5 intervals of 100 into new intervals, so that the user can understand conveniently and perform data flattening.
TABLE 5 psychological stress assessment data and characterization procedure
In order to implement the above-mentioned method for scoring the health index of the individual user, in at least one embodiment of the present specification, a device for scoring the health index of the individual user is further provided, which is shown in fig. 3, and the device includes a data acquisition module 301, a data processing module 302, a dimension score calculation module 303, and a health index score calculation module 304, and specifically includes:
a data collection module 301, configured to collect health data related to a target user health index score, where the health data includes: a dataset personal base information data of a plurality of dimensions relating to the health index score of the target user;
a characterization data module 302, configured to obtain a feature variable of each of the multiple dimensions by using a statistical method for the data of the multiple dimensions;
a dimension score calculation module 303, configured to input the feature variable of each of the multiple dimensions into a dimension score model corresponding to the dimension, and calculate a dimension score corresponding to the dimension, where the dimension score model of each of the multiple dimensions is obtained by pre-training according to sample data of the dimension;
and the health index score calculation module 304 is used for inputting the scores of the dimensions and the characteristic variables of the dimensions into a pre-trained health index score model to obtain the health of the target user.
In at least one embodiment, in conjunction with FIG. 4, the apparatus further includes a pre-rule module 300 that employs different scoring models based on pre-conditioning rules.
In at least one embodiment, in conjunction with fig. 4, the apparatus further includes a normalization module 305, which normalizes the score and the dimension score of the user health index into corresponding business intervals according to a business interval division standard of a business system.
In at least one embodiment, in conjunction with fig. 4, the apparatus further includes an index interpretation module 306.
In at least one embodiment, in conjunction with FIG. 4, the apparatus also includes a knowledge base model 307 and a model management module 308.
As shown in fig. 5, according to the health index scoring method and apparatus, for any user, a comprehensive health level evaluation system of "1 + N" is formed, and the user can evaluate the aspect affecting the health problem according to the scoring result and can help the business side to form a label describing the health level of the user.
Under the standardized policy of 100 points, if the physiological health dimension of a user is 80, the user is labeled with "good" physiological health, and the health index is 80, the user is labeled with "excellent" health level, and the business party can perform subsequent management measures by using the labels. Meanwhile, the change of the health index and the change of the score of each dimension are caused by the index change of each dimension, so that the change reason of the user score is fed back according to the influence degree under the recent change condition, the user is assisted to perceive the self health problem, and corresponding incentive support is provided. For example: the increase of BMI leads to the reduction of physiological health, and some exercise plans, diet plans and health instructions for keeping the physique of the user are fed back; the health behavior score is reduced due to long-term sleep disorder, and some health guidance such as sleep aiding and pressure reduction can be fed back to the user. Furthermore, the health index of the individual user can be integrated with other business systems to form more generalized applications, for example, if the health index is classified as "excellent" and the health behavior is classified as "better" and above, the premium of the health risk can be reduced.
For the above-described method and apparatus, in at least one embodiment, a plurality of modules are implemented in one or more of software and/or hardware by a computer program, and an implementation device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the scoring method as described above is implemented.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011448477.8A CN112890816A (en) | 2020-12-11 | 2020-12-11 | Health index scoring method and device for individual user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011448477.8A CN112890816A (en) | 2020-12-11 | 2020-12-11 | Health index scoring method and device for individual user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112890816A true CN112890816A (en) | 2021-06-04 |
Family
ID=76111676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011448477.8A Pending CN112890816A (en) | 2020-12-11 | 2020-12-11 | Health index scoring method and device for individual user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112890816A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113703923A (en) * | 2021-08-31 | 2021-11-26 | 深信服科技股份有限公司 | Method, device, equipment and medium for identifying service problems |
| CN113707270A (en) * | 2021-10-19 | 2021-11-26 | 潘道延 | Novel diabetes exercise rehabilitation guidance system |
| CN113851222A (en) * | 2021-12-01 | 2021-12-28 | 北京妙医佳健康科技集团有限公司 | Autonomous health management assisting method and device |
| CN113871014A (en) * | 2021-12-01 | 2021-12-31 | 北京妙医佳健康科技集团有限公司 | Autonomous health assisting method and device |
| CN114005546A (en) * | 2021-12-31 | 2022-02-01 | 四川大学华西医院 | A disease prediction algorithm based on feature space fitting of random forest model |
| CN114052670A (en) * | 2021-11-17 | 2022-02-18 | 深圳市盛景基因生物科技有限公司 | Health risk assessment method and disease early warning system |
| CN114343585A (en) * | 2022-01-13 | 2022-04-15 | 平安科技（深圳）有限公司 | Early warning method, device, equipment and storage medium for cognitive and behavioral disorders |
| CN114496264A (en) * | 2022-04-14 | 2022-05-13 | 深圳市瑞安医疗服务有限公司 | Health index analysis method, device, equipment and medium based on multi-dimensional data |
| CN115295123A (en) * | 2022-08-17 | 2022-11-04 | 慕思健康睡眠股份有限公司 | Diet recommendation method, device, equipment and medium based on sleep big data |
| CN115919286A (en) * | 2022-11-12 | 2023-04-07 | 湖北明络医疗科技有限公司 | A disease data acquisition and analysis method and acquisition and analysis system |
| CN116543910A (en) * | 2023-07-05 | 2023-08-04 | 山东大学 | Antibiotic auxiliary decision-making system for reducing clinical uncertainty of upper respiratory tract infection |
| CN116631630A (en) * | 2023-07-21 | 2023-08-22 | 北京中科心研科技有限公司 | Method and device for identifying anxiety disorder and wearable device |
| CN117038073A (en) * | 2023-07-18 | 2023-11-10 | 西南石油大学 | Construction method of pregnancy physical exercise behavior assessment index system |
| CN117408823A (en) * | 2023-10-24 | 2024-01-16 | 北京明熹五品人工智能科技有限公司 | Health data design life insurance scheme system for real-time human body monitoring |
| CN117592877A (en) * | 2023-11-30 | 2024-02-23 | 航天信息股份有限公司 | A security personnel performance supervision method, device and related equipment |
| CN117690582A (en) * | 2024-01-31 | 2024-03-12 | 吉林大学 | Information management system and method for nursing workstation |
| CN119157505A (en) * | 2024-08-30 | 2024-12-20 | 福州飞蟹网络科技有限公司 | A health data tracking method and system |
| CN119523484A (en) * | 2025-01-20 | 2025-02-28 | 北京市中医药研究所 | An auxiliary assessment system for anhedonia in patients with depression using multimodal physiological parameters |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012090226A2 (en) * | 2010-12-31 | 2012-07-05 | Tata Consultancy Services Limited | Computer implemented system and method for measuring individual wellness index |
| CN104850758A (en) * | 2015-06-10 | 2015-08-19 | 史方 | Health index scoring method |
| CN105678100A (en) * | 2016-03-01 | 2016-06-15 | 万达信息股份有限公司 | Health record browsing system |
| CN106096274A (en) * | 2016-06-08 | 2016-11-09 | 江苏华康信息技术有限公司 | A kind of sectional linear fitting health evaluating method based on normal distribution |
| CN107103177A (en) * | 2017-03-09 | 2017-08-29 | 徐小健 | A kind of personal health theory of index number points-scoring system and its methods of marking |
| US20170300655A1 (en) * | 2016-04-19 | 2017-10-19 | Vivametrica Ltd. | Apparatus and methodologies for personal health analysis |
| CN107798390A (en) * | 2017-11-22 | 2018-03-13 | 阿里巴巴集团控股有限公司 | A kind of training method of machine learning model, device and electronic equipment |
| CN107863153A (en) * | 2017-11-24 | 2018-03-30 | 中南大学 | A kind of human health characteristic modeling measuring method and platform based on intelligent big data |
| CN108108887A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of Internet of Things based on multidimensional data is traveled out the intelligent evaluation model of row index |
| CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
| CN109542742A (en) * | 2018-11-14 | 2019-03-29 | 国网江苏省电力有限公司信息通信分公司 | Database server hardware health evaluating method based on expert model |
| CN110838367A (en) * | 2019-11-18 | 2020-02-25 | 北京妙医佳健康科技集团有限公司 | Comprehensive health risk assessment method |
| CN111079941A (en) * | 2019-12-03 | 2020-04-28 | 武汉纺织大学 | Credit information system combining expert experience model and supervised machine learning algorithm |
| CN111815487A (en) * | 2020-06-28 | 2020-10-23 | 珠海中科先进技术研究院有限公司 | Health education assessment method, device and medium based on deep learning |
-
2020
- 2020-12-11 CN CN202011448477.8A patent/CN112890816A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012090226A2 (en) * | 2010-12-31 | 2012-07-05 | Tata Consultancy Services Limited | Computer implemented system and method for measuring individual wellness index |
| CN104850758A (en) * | 2015-06-10 | 2015-08-19 | 史方 | Health index scoring method |
| CN105678100A (en) * | 2016-03-01 | 2016-06-15 | 万达信息股份有限公司 | Health record browsing system |
| US20170300655A1 (en) * | 2016-04-19 | 2017-10-19 | Vivametrica Ltd. | Apparatus and methodologies for personal health analysis |
| CN106096274A (en) * | 2016-06-08 | 2016-11-09 | 江苏华康信息技术有限公司 | A kind of sectional linear fitting health evaluating method based on normal distribution |
| CN107103177A (en) * | 2017-03-09 | 2017-08-29 | 徐小健 | A kind of personal health theory of index number points-scoring system and its methods of marking |
| CN107798390A (en) * | 2017-11-22 | 2018-03-13 | 阿里巴巴集团控股有限公司 | A kind of training method of machine learning model, device and electronic equipment |
| CN107863153A (en) * | 2017-11-24 | 2018-03-30 | 中南大学 | A kind of human health characteristic modeling measuring method and platform based on intelligent big data |
| CN108108887A (en) * | 2017-12-18 | 2018-06-01 | 广东广业开元科技有限公司 | A kind of Internet of Things based on multidimensional data is traveled out the intelligent evaluation model of row index |
| CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
| CN109542742A (en) * | 2018-11-14 | 2019-03-29 | 国网江苏省电力有限公司信息通信分公司 | Database server hardware health evaluating method based on expert model |
| CN110838367A (en) * | 2019-11-18 | 2020-02-25 | 北京妙医佳健康科技集团有限公司 | Comprehensive health risk assessment method |
| CN111079941A (en) * | 2019-12-03 | 2020-04-28 | 武汉纺织大学 | Credit information system combining expert experience model and supervised machine learning algorithm |
| CN111815487A (en) * | 2020-06-28 | 2020-10-23 | 珠海中科先进技术研究院有限公司 | Health education assessment method, device and medium based on deep learning |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113703923B (en) * | 2021-08-31 | 2024-05-28 | 深信服科技股份有限公司 | Service problem identification method, device, equipment and medium |
| CN113703923A (en) * | 2021-08-31 | 2021-11-26 | 深信服科技股份有限公司 | Method, device, equipment and medium for identifying service problems |
| CN113707270A (en) * | 2021-10-19 | 2021-11-26 | 潘道延 | Novel diabetes exercise rehabilitation guidance system |
| CN114052670A (en) * | 2021-11-17 | 2022-02-18 | 深圳市盛景基因生物科技有限公司 | Health risk assessment method and disease early warning system |
| CN113851222A (en) * | 2021-12-01 | 2021-12-28 | 北京妙医佳健康科技集团有限公司 | Autonomous health management assisting method and device |
| CN113871014A (en) * | 2021-12-01 | 2021-12-31 | 北京妙医佳健康科技集团有限公司 | Autonomous health assisting method and device |
| CN114005546A (en) * | 2021-12-31 | 2022-02-01 | 四川大学华西医院 | A disease prediction algorithm based on feature space fitting of random forest model |
| CN114005546B (en) * | 2021-12-31 | 2022-05-03 | 四川大学华西医院 | A disease prediction method based on feature space fitting of random forest model |
| CN114343585A (en) * | 2022-01-13 | 2022-04-15 | 平安科技（深圳）有限公司 | Early warning method, device, equipment and storage medium for cognitive and behavioral disorders |
| CN114343585B (en) * | 2022-01-13 | 2023-09-29 | 平安科技（深圳）有限公司 | Cognitive and behavioral disorder early warning method, device, equipment and storage medium |
| CN114496264A (en) * | 2022-04-14 | 2022-05-13 | 深圳市瑞安医疗服务有限公司 | Health index analysis method, device, equipment and medium based on multi-dimensional data |
| CN115295123A (en) * | 2022-08-17 | 2022-11-04 | 慕思健康睡眠股份有限公司 | Diet recommendation method, device, equipment and medium based on sleep big data |
| CN115295123B (en) * | 2022-08-17 | 2023-12-01 | 慕思健康睡眠股份有限公司 | Diet recommendation method, device, equipment and medium based on sleep big data |
| CN115919286B (en) * | 2022-11-12 | 2024-02-02 | 上海爱渡医疗科技有限公司 | Disease data acquisition and analysis method and system |
| CN115919286A (en) * | 2022-11-12 | 2023-04-07 | 湖北明络医疗科技有限公司 | A disease data acquisition and analysis method and acquisition and analysis system |
| CN116543910B (en) * | 2023-07-05 | 2023-11-03 | 山东大学 | Antibiotic auxiliary decision-making system for reducing clinical uncertainty of upper respiratory tract infection |
| CN116543910A (en) * | 2023-07-05 | 2023-08-04 | 山东大学 | Antibiotic auxiliary decision-making system for reducing clinical uncertainty of upper respiratory tract infection |
| CN117038073A (en) * | 2023-07-18 | 2023-11-10 | 西南石油大学 | Construction method of pregnancy physical exercise behavior assessment index system |
| CN116631630A (en) * | 2023-07-21 | 2023-08-22 | 北京中科心研科技有限公司 | Method and device for identifying anxiety disorder and wearable device |
| CN117408823A (en) * | 2023-10-24 | 2024-01-16 | 北京明熹五品人工智能科技有限公司 | Health data design life insurance scheme system for real-time human body monitoring |
| CN117592877A (en) * | 2023-11-30 | 2024-02-23 | 航天信息股份有限公司 | A security personnel performance supervision method, device and related equipment |
| CN117690582A (en) * | 2024-01-31 | 2024-03-12 | 吉林大学 | Information management system and method for nursing workstation |
| CN117690582B (en) * | 2024-01-31 | 2024-04-26 | 吉林大学 | Information management system and method for nursing workstation |
| CN119157505A (en) * | 2024-08-30 | 2024-12-20 | 福州飞蟹网络科技有限公司 | A health data tracking method and system |
| CN119523484A (en) * | 2025-01-20 | 2025-02-28 | 北京市中医药研究所 | An auxiliary assessment system for anhedonia in patients with depression using multimodal physiological parameters |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112890816A (en) | Health index scoring method and device for individual user | |
| Kumar et al. | Hierarchical deep neural network for mental stress state detection using IoT based biomarkers | |
| JP7625301B2 (en) | SYSTEM AND METHOD FOR PERSONALIZED COGNITIVE INTERVENTION - Patent application | |
| US12073296B2 (en) | Methods and systems for generating physical activity sets for a human subject | |
| Nath et al. | Machine learning based stress monitoring in older adults using wearable sensors and cortisol as stress biomarker | |
| US11393589B2 (en) | Methods and systems for an artificial intelligence support network for vibrant constitutional guidance | |
| CN113168919A (en) | System for performing health analysis by using personalized indexes and using method thereof | |
| CN110838367A (en) | Comprehensive health risk assessment method | |
| CN109065162A (en) | A kind of comprehensive intelligent diagnostic system | |
| US20240008813A1 (en) | Smart wearable device and method for estimating traditional medicine system parameters | |
| CN108738299A (en) | System and method for determining the hemodynamic instability risk score for pediatric subject | |
| CN119049718A (en) | Patient risk assessment method and system for multi-index comprehensive scoring | |
| CN113795835A (en) | A method, system and computer storage medium for intelligent recommendation of cosmetics | |
| Thandi et al. | Mapping frailty concepts to SNOMED CT | |
| Paula et al. | Analysing iot data for anxiety and stress monitoring: A systematic mapping study and taxonomy | |
| Maguluri et al. | Unravelling the gait and balance: A novel approach for detecting depression in young healthy individuals | |
| CN120473078A (en) | Home intelligent health management system and method thereof | |
| CN113707329A (en) | Method, system and computer storage medium for intelligent analysis of cosmetic use | |
| CN113876302A (en) | Traditional Chinese medicine regulation and treatment system based on intelligent robot | |
| Amira et al. | Stress level classification using heart rate variability | |
| Norweg et al. | A multidimensional computer adaptive test approach to dyspnea assessment | |
| Sun et al. | The capacity of skin potential in generalized anxiety disorder discrimination using weighted feature fusion | |
| Alhejaili | Wearable technology for mental wellness monitoring and feedback | |
| CN118647960B (en) | Brain-computer signal safety system and application method thereof | |
| JP7774359B1 (en) | Treatment effect evaluation system, treatment effect evaluation method, and program |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210604 |