CN117711626A - Depression emotion evaluating method based on multidimensional factor - Google Patents
Depression emotion evaluating method based on multidimensional factor Download PDFInfo
- Publication number
- CN117711626A CN117711626A CN202410163780.5A CN202410163780A CN117711626A CN 117711626 A CN117711626 A CN 117711626A CN 202410163780 A CN202410163780 A CN 202410163780A CN 117711626 A CN117711626 A CN 117711626A
- Authority
- CN
- China
- Prior art keywords
- depression
- year
- matrix
- cognitive
- characteristic value
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims description 58
- 239000011159 matrix material Substances 0.000 claims abstract description 79
- 230000001149 cognitive effect Effects 0.000 claims abstract description 57
- 238000011156 evaluation Methods 0.000 claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 6
- 230000000994 depressogenic effect Effects 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 25
- 230000003542 behavioural effect Effects 0.000 claims description 15
- 230000036651 mood Effects 0.000 claims description 15
- 206010012374 Depressed mood Diseases 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 10
- 230000003001 depressive effect Effects 0.000 claims description 8
- 230000000306 recurrent effect Effects 0.000 claims description 8
- 208000024714 major depressive disease Diseases 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 34
- 230000019771 cognition Effects 0.000 abstract description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000002996 emotional effect Effects 0.000 description 6
- 238000003064 k means clustering Methods 0.000 description 6
- 230000007774 longterm Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- VYFYYTLLBUKUHU-UHFFFAOYSA-N dopamine Chemical compound NCCC1=CC=C(O)C(O)=C1 VYFYYTLLBUKUHU-UHFFFAOYSA-N 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- QZAYGJVTTNCVMB-UHFFFAOYSA-N serotonin Chemical compound C1=C(O)C=C2C(CCN)=CNC2=C1 QZAYGJVTTNCVMB-UHFFFAOYSA-N 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 230000036528 appetite Effects 0.000 description 3
- 235000019789 appetite Nutrition 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 229960003638 dopamine Drugs 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 229940076279 serotonin Drugs 0.000 description 2
- 206010011971 Decreased interest Diseases 0.000 description 1
- 208000020401 Depressive disease Diseases 0.000 description 1
- 206010054089 Depressive symptom Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Cardiology (AREA)
- General Physics & Mathematics (AREA)
- Psychology (AREA)
- Physiology (AREA)
- Child & Adolescent Psychology (AREA)
- Artificial Intelligence (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Evolutionary Computation (AREA)
- Developmental Disabilities (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
Abstract
The invention relates to the technical field of depression emotion evaluation, and particularly discloses a depression emotion evaluation method based on multidimensional factors, which comprises the following steps: acquiring an evaluation sample of a user to be tested, wherein the evaluation sample comprises a self-report scale set, a behavior parameter set, a cognitive parameter set and a physiological parameter set; preprocessing an evaluation sample to obtain a sample feature matrix, wherein the sample feature matrix comprises a self-reporting matrix, a behavior matrix, a cognitive matrix and a physiological matrix; and determining the depression emotion degree of the user to be tested according to the self-reporting matrix, the behavior matrix, the cognitive matrix and the physiological matrix based on a cyclic neural network. The invention can comprehensively analyze the depression emotion grades of the users from three aspects of physiology, behavior and cognition, and improves the accuracy of depression emotion evaluation.
Description
Technical Field
The invention relates to the technical field of depression emotion evaluation, in particular to a depression emotion evaluation method based on multidimensional factors.
Background
Depression is a common psychological disorder whose symptoms include low mood, loss of interest, fatigue, sleep disorders, altered appetite, etc. Accurate assessment of depressed mood is critical for diagnosis and treatment of depression. Traditional depression assessment methods are based primarily on self-reported scales, such as the hamilton depression scale (HAMD). However, these scales can only evaluate symptoms of depression from a single dimension, and cannot fully reflect the psychological state of the patient. Therefore, developing a method for evaluating depressed emotion based on multidimensional factors to improve the accuracy and reliability of depressed emotion evaluation is a current urgent problem to be solved.
With the development of psychology and artificial intelligence technology, multi-dimensional and multi-mode data acquisition and analysis become possible, and a new idea is provided for solving the problems. For example, depressed mood can be assessed more fully by collecting physiological metrics (e.g., heart rate, blood pressure, body temperature, etc.), behavioral metrics (e.g., facial expression, body language, etc.), and cognitive metrics (e.g., attention, memory, etc.). However, how to effectively integrate these multidimensional data together to accurately evaluate depressed mood remains a technical challenge.
The invention provides a depression emotion evaluation method based on multidimensional factors, and aims to solve the problems. The method combines multidimensional data such as physiological indexes, behavioral indexes, cognitive indexes and the like, and utilizes an artificial intelligence technology to analyze and process the data so as to evaluate the depression emotion more accurately. Compared with the traditional single-dimension evaluation method, the method can reflect the psychological state of the patient more comprehensively and improve the accuracy and reliability of depression emotion evaluation.
Disclosure of Invention
The invention aims to provide a depressed emotion evaluation method based on multidimensional factors, which can comprehensively analyze the depressed emotion grades of users from three aspects of physiology, behavior and cognition, and improves the accuracy of depressed emotion evaluation.
The invention adopts the following technical scheme:
the invention provides a depression emotion evaluation method based on multidimensional factors, which comprises the following steps:
acquiring an evaluation sample of a user to be tested, wherein the evaluation sample comprises a self-report scale set, a behavior parameter set, a cognitive parameter set and a physiological parameter set;
preprocessing an evaluation sample based on a cyclic neural network to obtain a sample feature matrix, and extracting depth features of the sample feature matrix, wherein the sample feature matrix comprises a self-reporting matrix, a behavior matrix, a cognitive matrix and a physiological matrix; and determining the depression emotion degree of the user to be tested based on the circulation network and the depth features of the sample feature matrix.
Further, the self-reporting scale set includes a monthly hamilton depression scale for a continuous period of time;
the physiological parameter set includes daily physiological indicators over a continuous period of time, the physiological indicators including: heart rate, blood pressure, respiratory rate, skin site response, serotonin and/or dopamine;
the behavior parameter set comprises behavior indexes of daily for a continuous period of time, and the behavior indexes comprise: appetite, emotion, self-responsibility, sleep and/or exercise;
the cognitive parameter set includes a daily cognitive index over a continuous period of time, the cognitive index including: attention, memory, orientation and/or thinking disorders;
wherein the continuous period of time is 1 year or more.
Further, the preprocessing the evaluation sample, obtaining a sample feature matrix includes:
predicting the depression probability of each month according to the total score of each self-reporting scale, and sequentially writing the depression probability of each month into a self-reporting matrix;
further, noise reduction is carried out on the behavioral parameter set based on a K-means clustering algorithm, the behavioral characteristic value of each behavioral index in each month is determined according to the behavioral parameter set after noise reduction, and the behavioral characteristic value is correspondingly written into a behavioral matrix;
further, based on a K-means clustering algorithm, denoising the cognitive parameter set, determining the cognitive characteristic value of each cognitive index in each month according to the denoised cognitive parameter set, and correspondingly writing the cognitive characteristic value into a cognitive matrix;
further, based on a K-means clustering algorithm, the physiological parameter set is subjected to noise reduction, physiological characteristic values of each physiological index in each month are determined according to the physiological parameter set after noise reduction, and the physiological characteristic values are correspondingly written into a physiological matrix.
Further, the determining, based on the recurrent neural network, the depression emotion degree of the user to be tested according to the sample feature matrix includes:
analyzing monthly depression characteristic values of the user to be tested according to the self-reporting matrix, the behavior matrix, the cognitive matrix and the physiological matrix;
analyzing the quarter depression characteristic value of each season of the user to be tested according to the month depression characteristic value;
analyzing annual depression characteristic values of the user to be tested every year according to the quaternary depression characteristic values;
determining the depressed emotion degree according to annual depressed characteristic values of the user, and determining the depressed emotion degree of the user to be tested according to depressed emotion parameters.
Further, the monthly depression feature values include:
in the method, in the process of the invention,for the characteristic value of monthly depression, ZFor the total number of all index categories, z=m+n+i, M is the total number of physiological index categories, N is the total number of cognitive index categories, I is the total number of behavioral index categories,/is->Is->Year of lifejThe likelihood of depression for one month,jfor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer>Is the firstiPerson behavioural index->Year of lifejBehavioral characteristic value of month ∈>Is the firstnIndividual cognitive index->Year of lifejCognitive trait value for month->Is the firstmPhysiological index->Year of lifejPhysiological characteristic values of one month, E represents a mathematical expectation value, and D represents a variance.
Further, the analyzing the characteristic value of the quaternary depression of the user to be tested according to the characteristic value of the monthly depression comprises:
determining the slope of the monthly depression feature value of each quarter according to the monthly depression feature value of three months corresponding to each quarter:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining a quaternary depression characteristic value according to the following formula:
in the method, in the process of the invention,is->Year of lifeqQuarterly depression characteristic values for each quarter,qin order to make the time of day,qis 1,2, 3 or 4, < >>For the year->Is a positive integer>Is->Year of lifeqSlope of monthly depression characteristic value of individual quarters, +.>Is a characteristic value of monthly depression.
Further, the analyzing annual depression characteristic value of the user to be tested according to the annual depression characteristic value comprises:
determining the slope of the quarterly depression feature value of each year according to the four quarterly depression feature values corresponding to each year:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining an annual depression characteristic value according to the following formula:
in the method, in the process of the invention,is->Annual depression characteristic value of year, ++>Is->Slope of annual depression characteristic value of year, < ->Is->Year of lifeqQuarterly depression characteristic value of individual quarters, < ->For the year->Is a positive integer.
Further, the depressed mood parameters include:
in the method, in the process of the invention,is a depressive mood parameter, and is->For a preset change threshold value, ++>,/>Is the difference between the characteristic value of the annual depression of the last 1 year and the characteristic value of the annual depression of the 1 st year,/-degree>Is->Annual depression characteristic value of year, ++>For evaluating the total years of collection of the sample, +.>For the year->Is a positive integer>Is a non-zero positive number.
Further, the determining the degree of depressed emotion of the user to be tested according to the depressed emotion parameter includes:
comparing the absolute value of the difference between the annual depression feature value of the last 1 year and the annual depression feature value of the 1 st year with the magnitude of the threshold value:
responsive toSending out prompt warning of immediate medical treatment and exiting the process of the depression emotion evaluation method;
responsive toH is more than 0 and less than or equal to the firstDetermining the depression mood degree as major depression at a threshold;
responsive toWhen the first threshold value is more than H and less than or equal to the second threshold value, determining that the depression emotion degree is depressed;
responsive toWhen the second threshold value is more than H and less than or equal to the third threshold value, determining that the depression emotion degree is possible to be depressed;
responsive toWhen the third threshold value is more than H and less than or equal to the fourth threshold value, determining that the depression emotion degree is non-depression;
wherein,is a depressive mood parameter, and is->For a preset change threshold value, ++>The difference between the annual depression characteristic value of the last 1 year and the annual depression characteristic value of the 1 st year.
Further, the accuracy of the recurrent neural network includes the following formula:
Accuracy=(TP+TN)/(TP+FN+FP+TN),
in the formula, accuracy is the Accuracy, TP is a real example, TN is a real negative example, FP is a false positive example, and FN is a false negative example.
Compared with the prior art, the invention has the beneficial effects that at least:
the invention comprehensively considers the data of multiple dimensions such as self-report scale, behavior parameters, cognitive parameters, physiological parameters and the like, and can more comprehensively evaluate the depression emotion condition of the user. These multidimensional data sources can complement each other to provide more accurate assessment results.
The invention can effectively process multi-dimensional data with time sequence dependency and capture long-term dependency in the data by using a cyclic neural network (RNN), which is helpful for improving the prediction accuracy and reliability of depressed emotion.
Drawings
Fig. 1 is a schematic diagram of one embodiment of a multi-dimensional factor-based depression mood assessment method of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus a repetitive description thereof will be omitted.
The words expressing the positions and directions described in the present invention are described by taking the drawings as an example, but can be changed according to the needs, and all the changes are included in the protection scope of the present invention.
Example 1
The embodiment introduces a depression emotion evaluation method based on multidimensional factors.
The depression emotion estimation method of the present embodiment includes the steps of:
s1, acquiring an evaluation sample of a user to be tested, wherein the evaluation sample comprises a self-report scale set, a behavior parameter set, a cognitive parameter set and a physiological parameter set.
S2, preprocessing an evaluation sample based on a cyclic neural network to obtain a sample feature matrix, and extracting depth features of the sample feature matrix, wherein the sample feature matrix comprises a self-reporting matrix, a behavior matrix, a cognitive matrix and a physiological matrix.
And S3, determining the depression emotion degree of the user to be tested based on a circulation network and the depth features of the sample feature matrix.
In the present invention, extraction of depth features of self-reporting matrix, behavior matrix, cognitive matrix and physiological matrix is required, and a recurrent neural network model (RNN model) first calculates monthly depression feature values based on monthly input data. This may be achieved by outputting a characteristic value at each time step of the RNN model, where each time step represents a month. These monthly eigenvalues may then be further processed, such as by summing the monthly eigenvalues every three months to calculate a quarterly depression eigenvalue, and similarly summing the eigenvalues every four quarters to calculate an annual depression eigenvalue. Finally, the RNN model can determine depressive mood parameters based on the annual depressive feature values. This may involve using the output of the RNN model to estimate parameters of the level of depression, for example by connecting the output of the RNN to one or more fully connected layers that may output estimates of depression mood parameters. Then, from these parameter values, the degree of depressed emotion of the user can be judged.
The embodiment comprehensively considers the data of multiple dimensions such as self-report scales, behavior parameters, cognitive parameters, physiological parameters and the like, and can more comprehensively evaluate the depressed emotion condition of the user. These multidimensional data sources can complement each other to provide more accurate assessment results.
The present embodiment can effectively process multidimensional data having time-series dependency by using a Recurrent Neural Network (RNN), and capture long-term dependency in the data, which contributes to improvement of prediction accuracy and reliability of depressed emotion.
Example 2
On the basis of the embodiment 1, the embodiment describes a depression emotion evaluation method based on multidimensional factors in detail.
The depression emotion evaluation method of the present embodiment includes the steps of:
s1, acquiring an evaluation sample of a user to be tested, wherein the evaluation sample comprises a self-report scale set, a behavior parameter set, a cognitive parameter set and a physiological parameter set.
In use, the self-reporting scale set includes a monthly hamiltonian depression scale for a continuous period of time. Wherein the continuous period of time is 1 year or more.
When the physiological parameter set is applied, the physiological parameter set comprises physiological indexes of daily in a continuous period of time, and the physiological indexes comprise: heart rate, blood pressure, respiratory rate, skin site response, serotonin and/or dopamine. Wherein the continuous period of time is 1 year or more.
When the system is applied, the behavior parameter set comprises behavior indexes of daily for a continuous period of time, and the behavior indexes comprise: appetite, emotion, self-responsibility, sleep and/or exercise. Wherein the continuous period of time is 1 year or more.
When the method is applied, the cognitive parameter set comprises a daily cognitive index in a continuous period of time, and the cognitive index comprises: attention, memory, orientation and/or thinking disorders. Wherein the continuous period of time is 1 year or more.
The present embodiments may be used to dynamically monitor a user's depressed emotional condition. By periodically collecting and updating multidimensional data, the change of the depression emotion of the user can be timely discovered, and timely intervention and support are provided.
S2, preprocessing an evaluation sample based on a cyclic neural network to obtain a sample feature matrix, and extracting depth features of the sample feature matrix, wherein the sample feature matrix comprises a self-reporting matrix, a behavior matrix, a cognitive matrix and a physiological matrix.
When the method is applied, the depression possibility of each month is predicted according to the total score of each self-reporting scale, and the depression possibility of each month is sequentially written into the self-reporting matrix.
In practical application, the self-reporting matrix comprises a plurality of two-dimensional self-reporting sub-matrices with row number of 1 and column number of 12, wherein the elements in the self-reporting sub-matrix are the firstYear of lifejPossibility of depression for month:
in the method, in the process of the invention,for self-reporter matrix, < >>Is->Year of lifejPossibility of depression in one month, +.>The value range of (2) is [1,2 ]], jFor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer which is used for the preparation of the high-voltage power supply,
when the total score of the self-report scale is less than 7, it falls within the normal range,1.
When the total score of the self-report scale is 7 points or more and less than 17 points, there may be symptoms of depression,1.2.
When the total score of the self-report scale is 17 or more and less than 24, the symptoms of depression are confirmed,1.4.
When the total score of the self-report scale is 24 or more, the presence of major depressive symptoms is considered,1.6.
When the method is applied, noise is reduced on the behavior parameter set based on the K-means clustering algorithm, the behavior characteristic value of each behavior index in each month is determined according to the behavior parameter set after noise reduction, and the behavior characteristic value is correspondingly written into the behavior matrix.
In practical application, the behavior matrix comprises a plurality of rows representing different behavior indexes, wherein the rows represent behavior submatrices of different months, and the elements in the behavior submatrices are the firstiIndividual behavioral indicators ofYear of lifejBehavioral characteristic value of month:
in the method, in the process of the invention,for behavior submatrices, < >>Is the firstiPerson behavioural index->Year of lifejBehavioral characteristic value of month ∈>The value range of (2) is [1,2 ]],jFor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer.
When the method is applied, the cognitive parameter set is subjected to noise reduction based on a K-means clustering algorithm, the cognitive characteristic value of each cognitive index in each month is determined according to the noise-reduced cognitive parameter set, and the cognitive characteristic value is correspondingly written into the cognitive matrix.
The cognitive matrix comprises a plurality of rows representing different cognitive indexes, columns representing different months of the cognitive submatrix, and each element in the cognitive submatrix representing the first elementnIndividual cognitive index numberYear of lifejCognitive characteristic values for the month;
in the method, in the process of the invention,for cognitive submatrix, < >>Is the firstnIndividual cognitive index->Year of lifejCognitive trait value for month->The value range of (2) is [1,2 ]],jFor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer.
When the method is applied, the physiological parameter set is subjected to noise reduction based on a K-means clustering algorithm, physiological characteristic values of each physiological index in each month are determined according to the physiological parameter set subjected to noise reduction, and the physiological characteristic values are correspondingly written into a physiological matrix.
In practice, the physiological matrix comprises multiple rows representing different physiological indexes, columns representing different month physiological submatrices, and each element in the physiological submatrix representing the firstmPhysiological index number oneYear of lifejPhysiological characteristic values for the month;
in the method, in the process of the invention,physiological matrix->Is the firstmPhysiological index->Year of lifejPhysiological characteristic value of month, < >>The value range of (2) is [1,2 ]],jFor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer.
In practical application, the protection of the user privacy can be fully considered when collecting and processing the user data. In the preprocessing stage, the data can be subjected to noise reduction processing, and unnecessary sensitive information is removed so as to protect the privacy of the user.
And S3, determining the depression emotion degree of the user to be tested based on a circulation network and the depth features of the sample feature matrix.
When in use, the step S3 comprises the following steps:
s31, analyzing monthly depression characteristic values of the user to be tested according to the self-reporting matrix, the behavior matrix, the cognitive matrix and the physiological matrix.
The monthly depression feature values include:
in the method, in the process of the invention,for the characteristic value of monthly depression, Z is the total number of all index categories, z=m+n+i, M is the total number of physiological index categories, N is cognitionThe total number of index categories, I is the total number of behavior index categories, < >>Is->Year of lifejThe likelihood of depression for one month,jfor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer>Is the firstiPerson behavioural index->Year of lifejBehavioral characteristic value of month ∈>Is the firstnIndividual cognitive index->Year of lifejCognitive trait value for month->Is the firstmPhysiological index->Year of lifejPhysiological characteristic values of one month, E represents a mathematical expectation value, and D represents a variance.
S32, analyzing the quarter depression characteristic value of each season of the user to be tested according to the month depression characteristic value.
Specifically, step S32 includes:
determining the slope of the monthly depression feature value of each quarter according to the monthly depression feature value of three months corresponding to each quarter:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining a quaternary depression characteristic value according to the following formula:
in the method, in the process of the invention,is->Year of lifeqQuarterly depression characteristic values for each quarter,qin order to make the time of day,qis 1,2, 3 or 4, < >>For the year->Is a positive integer>Is->Year of lifeqSlope of monthly depression characteristic value of individual quarters, +.>Is a characteristic value of monthly depression.
The embodiment can monitor the change trend of the depression emotion of the user by calculating the characteristic value of the depression in the quarter. By analyzing the slope of the characteristic value of the quarter depression, the acceleration or deceleration change condition of the depression emotion of the user can be known, so that the emotion condition and trend of the user can be better mastered.
The present embodiment, when calculating the slope of the monthly depression feature value for each quarter, triggers an "immediate medical attention" alert signal if the user's depressed emotional condition is found to be severe or worsening.
In the embodiment, the depression characteristic value of each month is calculated to calculate the depression characteristic value of the quarter, so that continuous monitoring can be realized. Such continuous monitoring may better understand the long-term trend of depressed mood of the user.
S33, analyzing annual depression characteristic values of the user to be tested according to the quaternary depression characteristic values.
Specifically, step S33 includes:
determining the slope of the quarterly depression feature value of each year according to the four quarterly depression feature values corresponding to each year:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining an annual depression characteristic value according to the following formula:
in the method, in the process of the invention,is->Annual depression characteristic value of year, ++>First->Slope of annual depression characteristic value of year, < ->Is->Year of lifeqQuarterly depression characteristic value of individual quarters, < ->For the year->Is a positive integer.
According to the embodiment, the annual depression characteristic value is calculated, so that the depression emotional condition of the user can be comprehensively estimated, and the user can be better informed of the depression emotional condition through the comprehensive estimation.
The embodiment calculates the annual depression characteristic value by calculating the depression characteristic value of each quarter, and can realize long-term trend monitoring. The long-term trend monitoring can better know the long-term change trend of the depressed emotion of the user, and help the user to better cope with and manage own emotion problems.
The present embodiment, when calculating the slope of the quarterly depression feature value for each year, triggers an "immediate medical visit" alert signal if the user's depressed emotional condition is found to be severe or worsening.
S34, determining the depressed emotion degree according to annual depressed characteristic values of the user and determining the depressed emotion degree of the user to be tested according to depressed emotion parameters.
When in use, step S34 includes: comparing the absolute value of the difference between the annual depression feature value of the last 1 year and the annual depression feature value of the 1 st year with the magnitude of the threshold value:
responsive toSending out prompt warning of immediate medical treatment and exiting the process of the depression emotion evaluation method;
responsive toWhen H is more than 0 and less than or equal to a first threshold value, determining that the depression emotion degree is major depression;
responsive toWhen the first threshold value is more than H and less than or equal to the second threshold value, determining that the depression emotion degree is depressed;
responsive toWhen the second threshold value is more than H and less than or equal to the third threshold value, determining that the depression emotion degree is possible to be depressed;
responsive toWhen the third threshold value is more than H and less than or equal to the fourth threshold value, determining that the depression emotion degree is non-depression;
wherein,is a depressive mood parameter, and is->For a preset change threshold value, ++>The difference between the annual depression characteristic value of the last 1 year and the annual depression characteristic value of the 1 st year. In practice, the depressed mood parameters include the following formula:
in the method, in the process of the invention,is a depressive mood parameter, and is->For a preset change threshold value, ++>,/>Is the difference between the characteristic value of the annual depression of the last 1 year and the characteristic value of the annual depression of the 1 st year,/-degree>Is->Annual depression characteristic value of year, ++>For evaluating the total years of collection of the sample, +.>For the year->Is a positive integer>Is a non-zero positive number and is generally 0.01.
According to the embodiment, the annual depression characteristic value and the depression emotion parameter are used to provide an accurate assessment for the depression emotion of the user, so that the actual emotion condition of the user can be reflected.
According to different ranges of the depressed mood parameters H, the depressed mood degree of the user is divided into different categories of major depression, already depressed, possible depression, non-depression and the like.
Those skilled in the art can adjust the threshold according to actual conditions to meet the needs of different users. By adjusting the threshold, depressed emotional conditions of different users may be better accommodated and more personalized assessment and intervention provided.
According to the embodiment, the monthly depression characteristic value, the quarterly depression characteristic value and the annual depression characteristic value equivalent index are calculated, so that the depression emotion degree of the user can be estimated more objectively.
The accuracy of the recurrent neural network in this embodiment includes the following formula:
Accuracy=(TP+TN)/(TP+FN+FP+TN),
in the formula, accuracy is the Accuracy, TP is a real example, TN is a real negative example, FP is a false positive example, and FN is a false negative example.
The sensitivity of the recurrent neural network of this embodiment includes the following formula:
Sensitivity= TP /(TP+FN)
where Sensitivity is Sensitivity.
The specificity of the recurrent neural network of this embodiment includes the following formula:
Specificity = TN /(FP+TN)
in the formula, specificity is Specificity.
In the application, in the model training and prediction stage, measures such as anonymization and encryption can be adopted to protect confidentiality and integrity of user data. Thus, the security and privacy of the user data can be ensured, and the worry of the user about data leakage is reduced.
In conclusion, the depression emotion evaluation method based on the multidimensional factors has the characteristics of trend monitoring, timely intervention, continuous monitoring, accuracy improvement by integrating the multidimensional factors and the like.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.
Claims (8)
1. The depression emotion evaluation method based on the multidimensional factors is characterized by comprising the following steps of:
acquiring an evaluation sample of a user to be tested, wherein the evaluation sample comprises a self-report scale set, a behavior parameter set, a cognitive parameter set and a physiological parameter set;
preprocessing an evaluation sample based on a cyclic neural network to obtain a sample feature matrix, and extracting depth features of the sample feature matrix, wherein the sample feature matrix comprises a self-reporting matrix, a behavior matrix, a cognitive matrix and a physiological matrix; determining the depression emotion degree of the user to be tested based on a circulation network and the depth features of the sample feature matrix;
determining the depression mood level of the user to be tested comprises:
analyzing monthly depression characteristic values of the user to be tested according to the self-reporting matrix, the behavior matrix, the cognitive matrix and the physiological matrix;
analyzing the quarter depression characteristic value of each season of the user to be tested according to the month depression characteristic value;
analyzing annual depression characteristic values of the user to be tested every year according to the quaternary depression characteristic values;
determining a depressed emotion degree according to annual depressed characteristic values of the user, and determining the depressed emotion degree of the user to be tested according to depressed emotion parameters;
the monthly depression feature values include:
in (1) the->For the monthly depression feature value, Z is the total number of all index categories, z=m+n+i, M is the total number of physiological index categories, N is the total number of cognitive index categories, I is the total number of behavioral index categories,>is->Year of lifejThe likelihood of depression for one month,jfor the month of the year, the time of day,jis [1,12 ]]Integer of>For the year->Is a positive integer>Is the firstiPerson behavioural index->Year of lifejBehavioral characteristic value of month ∈>Is the firstnIndividual cognitive index->Year of lifejCognitive trait value for month->Is the firstmPhysiological index->Year of lifejPhysiological characteristic values of one month, E represents a mathematical expectation value, and D represents a variance.
2. The multi-dimensional factor based depression mood assessment method as claimed in claim 1, wherein the set of self-reporting scales comprises a monthly hamilton depression scale for a continuous period of time;
the physiological parameter set includes daily physiological indicators over a continuous period of time;
the behavior parameter set comprises daily behavior indexes in a continuous period of time;
the cognitive parameter set includes a daily cognitive index over a continuous period of time;
wherein the continuous period of time is 1 year or more.
3. The method for evaluating a depressed mood based on multi-dimensional factors as recited in claim 1, wherein said preprocessing the evaluation sample to obtain a sample feature matrix comprises:
predicting the depression probability of each month according to the total score of each self-reporting scale, and sequentially writing the depression probability of each month into a self-reporting matrix;
and/or, denoising the behavior parameter set, determining the behavior characteristic value of each behavior index in each month according to the denoised behavior parameter set, and correspondingly writing the behavior characteristic value into the behavior matrix;
and/or, denoising the cognitive parameter set, determining the cognitive characteristic value of each cognitive index in each month according to the denoised cognitive parameter set, and correspondingly writing the cognitive characteristic value into the cognitive matrix;
and/or, denoising the physiological parameter set, determining physiological characteristic values of each physiological index in each month according to the denoised physiological parameter set, and correspondingly writing the physiological characteristic values into a physiological matrix.
4. The multi-dimensional factor-based depression emotion assessment method according to claim 1, wherein the analyzing the quaternary depression characteristic value of the user to be tested per season according to the monthly depression characteristic value comprises:
determining the slope of the monthly depression feature value of each quarter according to the monthly depression feature value of three months corresponding to each quarter:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining a quaternary depression characteristic value according to the following formula:
in (1) the->Is->Year of lifeqQuarterly depression characteristic values for each quarter,qin order to make the time of day,qis 1,2, 3 or 4, < >>For the year->Is a positive integer>Is->Year of lifeqSlope of monthly depression characteristic value of individual quarters, +.>Is a characteristic value of monthly depression.
5. The multi-dimensional factor-based depression emotion assessment method of claim 4, wherein the analyzing annual depression feature values of a user to be tested according to the quaternary depression feature values comprises:
determining the slope of the quarterly depression feature value of each year according to the four quarterly depression feature values corresponding to each year:
responsive toSending out an immediate medical alarm signal and exiting the process of the depression emotion evaluation method;
responsive toDetermining an annual depression characteristic value according to the following formula:
in (1) the->Is->Annual depression characteristic value of year, ++>First->The slope of the annual depression characteristic value for the year,is->Year of lifeqQuarterly depression characteristic value of individual quarters, < ->For the year->Is a positive integer.
6. The multi-dimensional factor-based depression mood assessment method as claimed in claim 1, wherein the depression mood parameters comprise:
in (1) the->Is a depressive mood parameter, and is->For a preset change threshold value, ++>,/>Is the difference between the characteristic value of the annual depression of the last 1 year and the characteristic value of the annual depression of the 1 st year,/-degree>Is->Annual depression characteristic value of year, ++>For evaluating the total years of collection of the sample, +.>For the year->Is a positive integer>Is a non-zero positive number.
7. The method for evaluating the depressed emotion based on the multidimensional factors according to claim 1, wherein the determining the depressed emotion degree of the user to be tested according to the depressed emotion parameters comprises:
comparing the absolute value of the difference between the annual depression feature value of the last 1 year and the annual depression feature value of the 1 st year with the magnitude of the threshold value:
responsive toSending out prompt warning of immediate medical treatment and exiting the process of the depression emotion evaluation method;
responsive toWhen H is more than 0 and less than or equal to a first threshold value, determining that the depression emotion degree is major depression;
responsive toWhen the first threshold value is more than H and less than or equal to the second threshold value, determining that the depression emotion degree is depressed;
responsive toWhen the second threshold value is more than H and less than or equal to the third threshold value, determining that the depression emotion degree is possible to be depressed;
responsive toWhen the third threshold value is more than H and less than or equal to the fourth threshold value, determining that the depression emotion degree is non-depression;
wherein,is a depressive mood parameter, and is->For a preset change threshold value, ++>The difference between the annual depression characteristic value of the last 1 year and the annual depression characteristic value of the 1 st year.
8. The multi-dimensional factor-based depression mood evaluation method as recited in claim 1, wherein the accuracy of the recurrent neural network comprises the following formula:
Accuracy=(TP+TN)/(TP+FN+FP+TN),
in the formula, accuracy is the Accuracy, TP is a real example, TN is a real negative example, FP is a false positive example, and FN is a false negative example.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410163780.5A CN117711626A (en) | 2024-02-05 | 2024-02-05 | Depression emotion evaluating method based on multidimensional factor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410163780.5A CN117711626A (en) | 2024-02-05 | 2024-02-05 | Depression emotion evaluating method based on multidimensional factor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117711626A true CN117711626A (en) | 2024-03-15 |
Family
ID=90148327
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410163780.5A Pending CN117711626A (en) | 2024-02-05 | 2024-02-05 | Depression emotion evaluating method based on multidimensional factor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117711626A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118236068A (en) * | 2024-05-29 | 2024-06-25 | 江西中医药大学 | Depression emotion degree estimating method and system based on multidimensional factor |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170238858A1 (en) * | 2015-07-30 | 2017-08-24 | South China University Of Technology | Depression assessment system and depression assessment method based on physiological information |
US20190117143A1 (en) * | 2017-10-23 | 2019-04-25 | Massachusetts Institute Of Technology | Methods and Apparatus for Assessing Depression |
US20220054065A1 (en) * | 2020-08-20 | 2022-02-24 | MINDPAX s.r.o. | Method for Detection of a Relapse Into a Depression or Mania State Based on Activity Data and/or Data Obtained by Questioning the Patient |
CN114241599A (en) * | 2021-11-24 | 2022-03-25 | 人工智能与数字经济广东省实验室(广州) | Depression tendency evaluation system and method based on multi-modal characteristics |
US20230037749A1 (en) * | 2020-11-30 | 2023-02-09 | Matrixcare, Inc. | Method and system for detecting mood |
CN116631629A (en) * | 2023-07-21 | 2023-08-22 | 北京中科心研科技有限公司 | Method and device for identifying depressive disorder and wearable device |
CN116665845A (en) * | 2023-05-17 | 2023-08-29 | 北京邮电大学 | User emotion self-testing system based on multi-mode data |
CN116807476A (en) * | 2023-08-25 | 2023-09-29 | 北京智精灵科技有限公司 | Multi-mode psychological health assessment system and method based on interface type emotion interaction |
CN117454217A (en) * | 2023-10-12 | 2024-01-26 | 华中农业大学 | Deep ensemble learning-based depression emotion recognition method, device and system |
-
2024
- 2024-02-05 CN CN202410163780.5A patent/CN117711626A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170238858A1 (en) * | 2015-07-30 | 2017-08-24 | South China University Of Technology | Depression assessment system and depression assessment method based on physiological information |
US20190117143A1 (en) * | 2017-10-23 | 2019-04-25 | Massachusetts Institute Of Technology | Methods and Apparatus for Assessing Depression |
US20220054065A1 (en) * | 2020-08-20 | 2022-02-24 | MINDPAX s.r.o. | Method for Detection of a Relapse Into a Depression or Mania State Based on Activity Data and/or Data Obtained by Questioning the Patient |
US20230037749A1 (en) * | 2020-11-30 | 2023-02-09 | Matrixcare, Inc. | Method and system for detecting mood |
CN114241599A (en) * | 2021-11-24 | 2022-03-25 | 人工智能与数字经济广东省实验室(广州) | Depression tendency evaluation system and method based on multi-modal characteristics |
CN116665845A (en) * | 2023-05-17 | 2023-08-29 | 北京邮电大学 | User emotion self-testing system based on multi-mode data |
CN116631629A (en) * | 2023-07-21 | 2023-08-22 | 北京中科心研科技有限公司 | Method and device for identifying depressive disorder and wearable device |
CN116807476A (en) * | 2023-08-25 | 2023-09-29 | 北京智精灵科技有限公司 | Multi-mode psychological health assessment system and method based on interface type emotion interaction |
CN117454217A (en) * | 2023-10-12 | 2024-01-26 | 华中农业大学 | Deep ensemble learning-based depression emotion recognition method, device and system |
Non-Patent Citations (3)
Title |
---|
方振宇 等: "基于抑郁词典的社交网络心理障碍检测方法", 电脑知识与技术, vol. 13, no. 07, 5 March 2017 (2017-03-05), pages 244 - 277 * |
李钊: "基于深度神经网络的图像分类方法研究", 《中国博士学位论文全文数据库信息科技辑》, 15 November 2018 (2018-11-15), pages 54 - 55 * |
熊光明 等著: "《智能车辆理论与应用》", vol. 2, 31 December 2021, 北京理工大学出版社, pages: 124 - 125 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118236068A (en) * | 2024-05-29 | 2024-06-25 | 江西中医药大学 | Depression emotion degree estimating method and system based on multidimensional factor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102129730B1 (en) | Patient condition predicting apparatus based on artificial intelligence and predicting method using the same | |
US10332638B2 (en) | Methods and systems for pre-symptomatic detection of exposure to an agent | |
Song et al. | Development of a stress classification model using deep belief networks for stress monitoring | |
Rahman et al. | Defining and predicting pain volatility in users of the manage my pain app: analysis using data mining and machine learning methods | |
CN108135548A (en) | For monitoring the method and system of pressure state | |
US11529105B2 (en) | Digital twin updating | |
Nishadi | Predicting heart diseases in logistic regression of machine learning algorithms by Python Jupyterlab | |
Liu et al. | Noninvasive evaluation of mental stress using by a refined rough set technique based on biomedical signals | |
US20210241909A1 (en) | Method and a system for evaluating treatment strategies on a virtual model of a patient | |
JP2023519581A (en) | Systems and methods for processing retinal signal data and identifying conditions | |
Zanna et al. | Bias reducing multitask learning on mental health prediction | |
CN114343585B (en) | Cognitive and behavioral disorder early warning method, device, equipment and storage medium | |
Mouleeshuwarapprabu et al. | Nonlinear vector decomposed neural network based EEG signal feature extraction and detection of seizure | |
Molin et al. | Prediction of obstructive sleep apnea using Fast Fourier Transform of overnight breath recordings | |
Deng et al. | SparNet: a convolutional neural network for EEG space-frequency feature learning and depression discrimination | |
CN114550932A (en) | Sleep apnea risk assessment method, device, equipment and storage medium | |
JP6053166B2 (en) | Numerical data analysis apparatus and program | |
CN116453641A (en) | Data processing method and system for auxiliary analysis information of traditional Chinese medicine | |
CN117711626A (en) | Depression emotion evaluating method based on multidimensional factor | |
Fuster-Garcia et al. | Actigraphy pattern analysis for outpatient monitoring | |
CN116019429A (en) | Health monitoring method, device, equipment and storage medium based on physiological index | |
Aluru et al. | Parkinson’s Disease Detection Using Machine Learning Techniques | |
Maria et al. | Stress prediction using enhanced feature selection and knn model | |
Nguyen et al. | Digital phenotype representation by statistical, information theory, data-driven approach with digital health data | |
CN117352180B (en) | Self-abuse risk early warning method for psychiatric patient |
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 |