CN117316458A - Disease risk assessment method, device, storage medium and electronic equipment - Google Patents
Disease risk assessment method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117316458A CN117316458A CN202311588798.1A CN202311588798A CN117316458A CN 117316458 A CN117316458 A CN 117316458A CN 202311588798 A CN202311588798 A CN 202311588798A CN 117316458 A CN117316458 A CN 117316458A
- Authority
- CN
- China
- Prior art keywords
- disease
- disease risk
- factors
- risk
- cognitive model
- 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
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 259
- 201000010099 disease Diseases 0.000 title claims abstract description 257
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012502 risk assessment Methods 0.000 title claims abstract description 39
- 230000001149 cognitive effect Effects 0.000 claims abstract description 52
- 238000013186 photoplethysmography Methods 0.000 claims abstract description 22
- 238000010219 correlation analysis Methods 0.000 claims description 14
- 238000007477 logistic regression Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 14
- 238000009412 basement excavation Methods 0.000 abstract description 8
- 206010020772 Hypertension Diseases 0.000 description 14
- 230000000694 effects Effects 0.000 description 7
- 239000008280 blood Substances 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000000391 smoking effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 208000008589 Obesity Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000036772 blood pressure Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000012880 independent component analysis Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 235000020824 obesity Nutrition 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 4
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 239000008103 glucose Substances 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- -1 respiration rate Substances 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 208000031226 Hyperlipidaemia Diseases 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010036067 polydipsia Diseases 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 235000015598 salt intake Nutrition 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000013517 stratification Methods 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012544 monitoring process 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
-
- 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
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Veterinary Medicine (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Epidemiology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Cardiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a disease risk assessment method, a disease risk assessment device, a storage medium and electronic equipment. The disease risk assessment method comprises the following steps: acquiring disease-associated factors affecting the occurrence of a disease; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; and inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model. The technical problem that the autonomous diagnosis and treatment of the patient cannot be assisted due to the fact that deeper excavation is not carried out on the physiological data of the human body is solved.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a disease risk assessment method, a disease risk assessment device, a storage medium, and an electronic device.
Background
Human vital signs, i.e., human physiological data, including pulse, heart rate variability, blood pressure, blood oxygen, respiration rate, blood glucose, etc.; estimation and monitoring of physiological data of a human body are important for determining the physical state of a person, and conventional methods for measuring vital signs such as heart rate are all contact-type. Such as an electrode electrocardiogram, heart rate is measured by sensing a cardiac current of a human body through an electrode pad; on wearable devices such as smartwatches, it is most common to make measurements with photoplethysmography (PPG), but also in close contact with the skin. Although the contact measurement mode is accurate, the contact measurement mode inevitably causes a lot of discomfort and inconvenience, and particularly in some special scenes, the contact measurement mode cannot be used.
At present, non-contact acquisition of human body temperature is already appeared under the influence of epidemic situation, and remote photoelectric volume pulse wave tracing is also adopted in some measurement methods or systems to acquire human body physiological data such as pulse, heart rate, blood pressure and the like, but no deeper excavation is carried out on the human body physiological data so as to assist patients to realize autonomous diagnosis and treatment.
Aiming at the problem that the autonomous diagnosis and treatment of a patient cannot be assisted due to the fact that deeper mining is not carried out on human physiological data in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The main objective of the present application is to provide a disease risk assessment method, a device, a storage medium and an electronic apparatus, so as to solve the problem that the autonomous diagnosis and treatment of a patient cannot be assisted due to the fact that deeper mining is not performed on physiological data of a human body.
To achieve the above object, according to one aspect of the present application, there is provided a disease risk assessment method.
The disease risk assessment method according to the present application comprises: acquiring disease-associated factors affecting the occurrence of a disease; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; and inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
Further, the method further comprises the steps of: carrying out correlation analysis on the disease association factors by adopting a Logistic regression method, and screening out strong association factors of disease occurrence risks; and inputting the strong correlation factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
Further, performing correlation analysis on the disease association factors by using a Logistic regression method, and screening out strong association factors of disease occurrence risk includes: and carrying out correlation analysis on the disease correlation factors by a binary Logistic regression method to obtain hidden state P values of the disease correlation factors, and selecting variables with the P values smaller than a set threshold as strong correlation factors of disease occurrence.
Further, acquiring vital sign data of the user using remote photoplethysmography blank comprises: firstly, detecting a region of interest (ROI) of each frame of face of a video; calculating the average value of pixels for the ROI region, calculating the three channels of the rgb image by the ROI region of each channel to obtain the average value of the pixels of the three channels of each frame of image, and having three signals with the length of T for the video segment of one T frame; filtering or transforming the acquired signal with the length of T; and estimating vital signs of the user by using the extracted signals.
Further, inputting the disease-related factor into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model further comprises: determining a disease risk level from the disease risk score; and determining disease risk prompts and suggestions in a preset level-suggestion relationship table according to the disease risk level.
Further, inputting the disease-related factor into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model further comprises: determining an area under the ROC curve based on the disease risk score; and determining whether the clinical risk judgment value exists or not according to whether the area under the ROC curve meets a preset limit threshold.
Further, the evaluation of the disease risk score by the disease risk cognitive model includes: preprocessing based on regression coefficient values of the disease-associated factors; calculating a risk score for each disease-associated factor with reference to the pre-processing results; a disease risk score is determined based on the risk score for each disease-associated factor.
In order to achieve the above object, according to another aspect of the present application, there is provided a disease risk assessment apparatus.
The disease risk assessment device according to the present application includes: the acquisition module is used for acquiring disease-related factors affecting occurrence of diseases; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; and the evaluation module is used for inputting the disease association factors into a preset disease risk cognitive model and evaluating and obtaining a disease risk score through the disease risk cognitive model.
To achieve the above object, according to another aspect of the present application, there is provided a computer-readable storage medium.
A computer readable storage medium according to the present application, having stored therein a computer program, wherein the computer program is arranged to execute the disease risk assessment method at run-time.
To achieve the above object, according to another aspect of the present application, there is provided an electronic apparatus.
An electronic device according to the present application, comprising: a memory and a processor, the memory having stored therein a computer program, wherein the processor is arranged to run the computer program to perform the disease risk assessment method.
In the embodiment of the application, a disease risk assessment mode is adopted, and disease association factors influencing the occurrence of diseases are obtained; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk cognitive model to obtain a disease risk score; the purpose of performing deeper excavation on the physiological data of the human body is achieved, so that the technical effect of assisting the autonomous diagnosis and treatment of the patient is achieved, and the technical problem that the autonomous diagnosis and treatment of the patient cannot be assisted due to the fact that the deeper excavation is not performed on the physiological data of the human body is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, are included to provide a further understanding of the application and to provide a further understanding of the application with regard to the other features, objects and advantages of the application. The drawings of the illustrative embodiments of the present application and their descriptions are for the purpose of illustrating the present application and are not to be construed as unduly limiting the present application. In the drawings:
FIG. 1 is a flow chart of a disease risk assessment method according to an embodiment of the present application;
fig. 2 is a schematic structural view of a disease risk assessment device according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present invention and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present invention will be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, the terms "mounted," "configured," "provided," "connected," "coupled," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
According to an embodiment of the present invention, there is provided a disease risk assessment method, as shown in fig. 1, including the following steps S101 to S102:
step S101, obtaining disease-related factors affecting occurrence of diseases; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography;
disease-associated factors refer to data that has an impact on disease occurrence; in this embodiment, the disease-related factor includes a user's personal index and a user's vital sign, wherein the user's personal index includes information such as age, gender, smoking, exercise, family history of hypertension, obesity, etc., and the user's vital sign includes pulse, heart rate variability, blood pressure, blood oxygen, respiration rate, blood glucose, etc.
It should be understood that the user personal index can be filled in and uploaded by the user through application processing software, or can be automatically extracted from medical record information of a hospital, preferably, the user personal index is automatically extracted from the medical record information of the hospital, so that the degree of intelligence can be improved.
It should be further appreciated that the vital signs of the user are acquired by remote photoplethysmography, and may be a method for analyzing based on a region of interest of a human face, or may be a method for analyzing based on deep learning.
Specifically, the method for analyzing based on the region of interest of the face comprises the following steps: firstly, detecting a region of interest (ROI) of each frame of face of a video, wherein the cheek and forehead regions are generally considered to be more excellent, and the reason is that the motion noise of the mouth of the glasses is avoided, but a box is generally selected directly to cover the face region for convenience; next, calculating an average value of pixels for the ROI area, and calculating the rgb image three channels by using the ROI area of each channel, thereby obtaining an average value of pixels of three channels of each frame of image, so that three signals with the length of T are provided for a video segment of one T frame; thirdly, filtering or converting the acquired signal with the length of T, namely, using a signal processing method; the purpose is to remove noise, separate out useless signals, extract periodic signals similar to PPG signals; and finally, estimating vital signs such as heart rate by using the extracted signals.
For example, the periodic peaks are found in the processed signal, and the peak interval, i.e. the heartbeat interval, can be simply considered, so that the number of peaks in a period of time can be calculated as the number of beats per minute. Here, the signal, when obtained, typically contains noise, and thus requires signal processing to obtain a clean, enhanced signal. The more common methods are Independent Component Analysis (ICA) and Blind Source Separation (BSS) methods to process a desired signal for a set of signal components. There are also many model-based methods such as PBV, etc.
Specifically, the flow of the method for analysis based on deep learning is similar to the method for analysis based on the region of interest of the face; the difference is that the ROI area detection is submitted to the existing algorithm, and the extracted ROI is sent to the network to regress the PPG signal or directly return vital sign data such as heart rate value.
It should be appreciated that the deep learning-based approach is divided into two types, one is end-to-end heart rate detection and the other is non-end-to-end. The two methods are distinguished by looking at whether the features fed into the network are the extracted ROI area original images or the manually processed features, spatial Temporal map (spatiotemporal map). The ROI area is divided into n blocks, and the n blocks can be more refined than the n blocks, so that the generated map is more similar to a picture, and the map can be conveniently sent into a network, such as CNN, wherein C is the channel number, and the frame numbers T and n form the length and the width. Methods for heart rate detection using STmap input to CNN are more common, such as inputting STmap to Resnet18 and outputting as heart rate values. The pretraining mode is to reversely generate an STmap according to the PPG signal by using prior knowledge except pretraining of Resnet18 on an Imagenet for training a model. Then the last access to the GRU module at the Resnet18 improves the model performance. The module incorporating rnn can handle timing characteristics more efficiently, considering the timing of the video.
Step S102, inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
And inputting the obtained disease-related factors into a disease risk cognition model, and performing risk assessment through the model. Specifically, the evaluation of the disease risk score by the disease risk cognitive model includes:
preprocessing based on regression coefficient values of the disease-associated factors; dividing each regression coefficient beta value by the minimum regression coefficient：
；
Calculating a risk score for each disease-associated factor with reference to the pre-processing results; the new coefficients are rounded into integer parts according to rounding method, and the danger scores Si corresponding to the respective variables are as follows:
；
determining a disease risk score based on the risk score for each disease-associated factor; the total score Sc is the sum of the risk scores added together:
sc is the sum of all the danger scores in the danger scoring system; si represents the risk score corresponding to the respective variable in the risk scoring system, i=1, 2, … …, n; si and Sc are rounded integers.
Therefore, disease risk scoring is realized by deeper mining of human physiological data, and the user can assist himself in autonomous diagnosis and treatment by referring to the score.
From the above description, it can be seen that the following technical effects are achieved:
in the embodiment of the application, a disease risk assessment mode is adopted, and disease association factors influencing the occurrence of diseases are obtained; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk cognitive model to obtain a disease risk score; the purpose of performing deeper excavation on the physiological data of the human body is achieved, so that the technical effect of assisting the autonomous diagnosis and treatment of the patient is achieved, and the technical problem that the autonomous diagnosis and treatment of the patient cannot be assisted due to the fact that the deeper excavation is not performed on the physiological data of the human body is solved.
According to an embodiment of the present invention, it is preferable that the acquiring of disease-related data affecting occurrence of a disease further includes:
carrying out correlation analysis on the disease association factors by adopting a Logistic regression method, and screening out strong association factors of disease occurrence risks;
and inputting the strong correlation factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
Specifically, the correlation analysis is carried out on the disease association factors by adopting a Logistic regression method, and the screening of the strong association factors of the occurrence risk of the disease comprises the following steps: carrying out correlation analysis on the disease association factors by a binary Logistic regression method to obtain hidden state P values of the disease association factors, and selecting variables with the P values smaller than a set threshold as strong association factors of disease occurrence; and then inputting the strong correlation factors into the disease risk cognitive model to perform disease risk assessment, wherein the specific disease risk assessment refers to the process of inputting the disease correlation factors into the disease risk cognitive model to perform disease risk assessment, and the description is omitted herein. On the premise of ensuring the evaluation accuracy, the calculation load can be reduced, and the processing efficiency is improved.
For example, according to the Chinese hypertension health management Specification (2019) and the recent hypertension crowd statistics table, a plurality of factors possibly affecting hypertension, namely disease association factors, can be determined first. Comprising 15: age, gender, smoking, exercise, family history of hypertension, obesity, diabetes, long-term stress, smoking, hyperlipidemia, high salt intake, systolic blood pressure, diastolic blood pressure, excessive drinking and air pollution.
The screening purpose is to exclude the variable with poor prediction efficiency from 15 variables, and screen out the strong related variable as the basis for the establishment of the subsequent prediction model. Taking out hypertension disease factor data according to health information data provided by a CDC BRFSS database, screening variables by adopting a statistical method, and carrying out correlation analysis according to a binary Logistic regression method to obtain P values of single variables; the P value less than 0.05 is statistically significant, so that factors with smaller influence on hypertension are eliminated.
According to an embodiment of the present invention, preferably, the inputting the disease-related factor into a preset disease risk cognitive model, and the evaluating the disease risk score through the disease risk cognitive model further includes:
determining a disease risk level from the disease risk score;
and determining disease risk prompts and suggestions in a preset level-suggestion relationship table according to the disease risk level.
The risk stratification can be carried out on the results according to the disease risk scores, and then the disease risk prompts and suggestions are determined through table lookup, for example, the results are classified into three levels of low risk, medium risk and high risk, the scores are higher than A and are medium risk, the scores are between A and B, and the scores are lower than B; after the disease risk grade is determined, corresponding disease risk prompts and suggestions can be associated according to the low-risk, medium-risk and high-risk grades, so that basis is provided for subsequent recuperation of the patient, and the auxiliary diagnosis and treatment effect is further improved.
According to an embodiment of the present invention, preferably, the inputting the disease-related factor into a preset disease risk cognitive model, and the evaluating the disease risk score through the disease risk cognitive model further includes:
determining an area under the ROC curve based on the disease risk score; namely, simplifying a Logistics regression model into a new prediction model, wherein the formula is as follows:
；
wherein S is c Representing the sum of all the risk scores in the risk scoring system;representing a minimum regression coefficient; p is the area under the ROC curve.
And determining whether the clinical risk judgment value exists or not according to whether the area under the ROC curve meets a preset limit threshold.
The area under the ROC curve is used for judging the size of the model risk judging value, 0.5 is used as a limit, the area under the ROC curve is more than 0.5, the clinical risk judging value is considered to exist, and the clinical risk judging value is considered to be absent when the area under the ROC curve is less than or equal to 0.5.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the disease risk assessment method, as shown in fig. 2, the apparatus includes:
an acquisition module 10 for acquiring disease-related factors affecting occurrence of a disease; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography;
disease-associated factors refer to data that has an impact on disease occurrence; in this embodiment, the disease-related factor includes a user's personal index and a user's vital sign, wherein the user's personal index includes information such as age, gender, smoking, exercise, family history of hypertension, obesity, etc., and the user's vital sign includes pulse, heart rate variability, blood pressure, blood oxygen, respiration rate, blood glucose, etc.
It should be understood that the user personal index can be filled in and uploaded by the user through application processing software, or can be automatically extracted from medical record information of a hospital, preferably, the user personal index is automatically extracted from the medical record information of the hospital, so that the degree of intelligence can be improved.
It should be further appreciated that the vital signs of the user are acquired by remote photoplethysmography, and may be a method for analyzing based on a region of interest of a human face, or may be a method for analyzing based on deep learning.
Specifically, the method for analyzing based on the region of interest of the face comprises the following steps: firstly, detecting a region of interest (ROI) of each frame of face of a video, wherein the cheek and forehead regions are generally considered to be more excellent, and the reason is that the motion noise of the mouth of the glasses is avoided, but a box is generally selected directly to cover the face region for convenience; next, calculating an average value of pixels for the ROI area, and calculating the rgb image three channels by using the ROI area of each channel, thereby obtaining an average value of pixels of three channels of each frame of image, so that three signals with the length of T are provided for a video segment of one T frame; thirdly, filtering or converting the acquired signal with the length of T, namely, using a signal processing method; the purpose is to remove noise, separate out useless signals, extract periodic signals similar to PPG signals; and finally, estimating vital signs such as heart rate by using the extracted signals.
For example, the periodic peaks are found in the processed signal, and the peak interval, i.e. the heartbeat interval, can be simply considered, so that the number of peaks in a period of time can be calculated as the number of beats per minute. Here, the signal, when obtained, typically contains noise, and thus requires signal processing to obtain a clean, enhanced signal. The more common methods are Independent Component Analysis (ICA) and Blind Source Separation (BSS) methods to process a desired signal for a set of signal components. There are also many model-based methods such as PBV, etc.
Specifically, the flow of the method for analysis based on deep learning is similar to the method for analysis based on the region of interest of the face; the difference is that the ROI area detection is submitted to the existing algorithm, and the extracted ROI is sent to the network to regress the PPG signal or directly return vital sign data such as heart rate value.
It should be appreciated that the deep learning-based approach is divided into two types, one is end-to-end heart rate detection and the other is non-end-to-end. The two methods are distinguished by looking at whether the features fed into the network are the extracted ROI area original images or the manually processed features, spatial Temporal map (spatiotemporal map). The ROI area is divided into n blocks, and the n blocks can be more refined than the n blocks, so that the generated map is more similar to a picture, and the map can be conveniently sent into a network, such as CNN, wherein C is the channel number, and the frame numbers T and n form the length and the width. Methods for heart rate detection using STmap input to CNN are more common, such as inputting STmap to Resnet18 and outputting as heart rate values. The pretraining mode is to reversely generate an STmap according to the PPG signal by using prior knowledge except pretraining of Resnet18 on an Imagenet for training a model. Then the last access to the GRU module at the Resnet18 improves the model performance. The module incorporating rnn can handle timing characteristics more efficiently, considering the timing of the video.
The evaluation module 20 is configured to input the disease-related factor into a preset disease risk cognitive model, and evaluate the disease risk score through the disease risk cognitive model.
And inputting the obtained disease-related factors into a disease risk cognition model, and performing risk assessment through the model. Specifically, the evaluation of the disease risk score by the disease risk cognitive model includes:
preprocessing based on regression coefficient values of the disease-associated factors; dividing each regression coefficient beta value by the minimum regression coefficient：
；
Calculating a risk score for each disease-associated factor with reference to the pre-processing results; the new coefficients are rounded into integer parts according to rounding method, and the danger scores Si corresponding to the respective variables are as follows:
；
determining a disease risk score based on the risk score for each disease-associated factor; the total score Sc is the sum of the risk scores added together:
sc is the sum of all the danger scores in the danger scoring system; si represents the risk score corresponding to the respective variable in the risk scoring system, i=1, 2, … …, n; si and Sc are rounded integers.
Therefore, disease risk scoring is realized by deeper mining of human physiological data, and the user can assist himself in autonomous diagnosis and treatment by referring to the score.
From the above description, it can be seen that the following technical effects are achieved:
in the embodiment of the application, a disease risk assessment mode is adopted, and disease association factors influencing the occurrence of diseases are obtained; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography; inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk cognitive model to obtain a disease risk score; the purpose of performing deeper excavation on the physiological data of the human body is achieved, so that the technical effect of assisting the autonomous diagnosis and treatment of the patient is achieved, and the technical problem that the autonomous diagnosis and treatment of the patient cannot be assisted due to the fact that the deeper excavation is not performed on the physiological data of the human body is solved.
According to an embodiment of the present invention, it is preferable that the acquiring of disease-related data affecting occurrence of a disease further includes:
carrying out correlation analysis on the disease association factors by adopting a Logistic regression method, and screening out strong association factors of disease occurrence risks;
and inputting the strong correlation factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
Specifically, the correlation analysis is carried out on the disease association factors by adopting a Logistic regression method, and the screening of the strong association factors of the occurrence risk of the disease comprises the following steps: carrying out correlation analysis on the disease association factors by a binary Logistic regression method to obtain hidden state P values of the disease association factors, and selecting variables with the P values smaller than a set threshold as strong association factors of disease occurrence; and then inputting the strong correlation factors into the disease risk cognitive model to perform disease risk assessment, wherein the specific disease risk assessment refers to the process of inputting the disease correlation factors into the disease risk cognitive model to perform disease risk assessment, and the description is omitted herein. On the premise of ensuring the evaluation accuracy, the calculation load can be reduced, and the processing efficiency is improved.
For example, according to the Chinese hypertension health management Specification (2019) and the recent hypertension crowd statistics table, a plurality of factors possibly affecting hypertension, namely disease association factors, can be determined first. Comprising 15: age, gender, smoking, exercise, family history of hypertension, obesity, diabetes, long-term stress, smoking, hyperlipidemia, high salt intake, systolic blood pressure, diastolic blood pressure, excessive drinking and air pollution.
The screening purpose is to exclude the variable with poor prediction efficiency from 15 variables, and screen out the strong related variable as the basis for the establishment of the subsequent prediction model. Taking out hypertension disease factor data according to health information data provided by a CDC BRFSS database, screening variables by adopting a statistical method, and carrying out correlation analysis according to a binary Logistic regression method to obtain P values of single variables; the P value less than 0.05 is statistically significant, so that factors with smaller influence on hypertension are eliminated.
According to an embodiment of the present invention, preferably, the inputting the disease-related factor into a preset disease risk cognitive model, and the evaluating the disease risk score through the disease risk cognitive model further includes:
determining a disease risk level from the disease risk score;
and determining disease risk prompts and suggestions in a preset level-suggestion relationship table according to the disease risk level.
The risk stratification can be carried out on the results according to the disease risk scores, and then the disease risk prompts and suggestions are determined through table lookup, for example, the results are classified into three levels of low risk, medium risk and high risk, the scores are higher than A and are medium risk, the scores are between A and B, and the scores are lower than B; after the disease risk grade is determined, corresponding disease risk prompts and suggestions can be associated according to the low-risk, medium-risk and high-risk grades, so that basis is provided for subsequent recuperation of the patient, and the auxiliary diagnosis and treatment effect is further improved.
According to an embodiment of the present invention, preferably, the inputting the disease-related factor into a preset disease risk cognitive model, and the evaluating the disease risk score through the disease risk cognitive model further includes:
determining an area under the ROC curve based on the disease risk score; namely, simplifying a Logistics regression model into a new prediction model, wherein the formula is as follows:
；
wherein S is c Representing the sum of all the risk scores in the risk scoring system;representing a minimum regression coefficient; p is the area under the ROC curve.
And determining whether the clinical risk judgment value exists or not according to whether the area under the ROC curve meets a preset limit threshold.
The area under the ROC curve is used for judging the size of the model risk judging value, 0.5 is used as a limit, the area under the ROC curve is more than 0.5, the clinical risk judging value is considered to exist, and the clinical risk judging value is considered to be absent when the area under the ROC curve is less than or equal to 0.5.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored in a memory device for execution by the computing devices, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the same, but rather, various modifications and variations may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method of disease risk assessment comprising:
acquiring disease-associated factors affecting the occurrence of a disease; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography;
and inputting the disease-related factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
2. The disease risk assessment method of claim 1, further comprising, after obtaining disease-related data affecting disease occurrence:
carrying out correlation analysis on the disease association factors by adopting a Logistic regression method, and screening out strong association factors of disease occurrence risks;
and inputting the strong correlation factors into a preset disease risk cognitive model, and evaluating the disease risk score through the disease risk cognitive model.
3. The disease risk assessment method according to claim 2, wherein the correlation analysis of the disease-associated factors using a Logistic regression method, and the screening of the strong-associated factors for disease occurrence risk comprises:
and carrying out correlation analysis on the disease correlation factors by a binary Logistic regression method to obtain hidden state P values of the disease correlation factors, and selecting variables with the P values smaller than a set threshold as strong correlation factors of disease occurrence.
4. The disease risk assessment method of claim 1, wherein acquiring the user vital sign data using remote photoplethysmography blank comprises:
firstly, detecting a region of interest (ROI) of each frame of face of a video;
calculating the average value of pixels for the ROI region, calculating the three channels of the rgb image by the ROI region of each channel to obtain the average value of the pixels of the three channels of each frame of image, and having three signals with the length of T for the video segment of one T frame;
filtering or transforming the acquired signal with the length of T;
and estimating vital signs of the user by using the extracted signals.
5. The disease risk assessment method according to claim 1, wherein inputting the disease-related factor into a preset disease risk cognitive model, and after obtaining a disease risk score through the disease risk cognitive model assessment, further comprises:
determining a disease risk level from the disease risk score;
and determining disease risk prompts and suggestions in a preset level-suggestion relationship table according to the disease risk level.
6. The disease risk assessment method according to claim 1, wherein inputting the disease-related factor into a preset disease risk cognitive model, and after obtaining a disease risk score through the disease risk cognitive model assessment, further comprises:
determining an area under the ROC curve based on the disease risk score;
and determining whether the clinical risk judgment value exists or not according to whether the area under the ROC curve meets a preset limit threshold.
7. The disease risk assessment method of claim 1, wherein evaluating the disease risk score by the disease risk cognitive model comprises:
preprocessing based on regression coefficient values of the disease-associated factors;
calculating a risk score for each disease-associated factor with reference to the pre-processing results;
a disease risk score is determined based on the risk score for each disease-associated factor.
8. A disease risk assessment apparatus, comprising:
the acquisition module is used for acquiring disease-related factors affecting occurrence of diseases; wherein the disease-related factors comprise at least a user's personal index and a user's vital sign acquired at intervals using remote photoplethysmography;
and the evaluation module is used for inputting the disease association factors into a preset disease risk cognitive model and evaluating and obtaining a disease risk score through the disease risk cognitive model.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program, wherein the computer program is arranged to execute the disease risk assessment method of any of claims 1 to 7 at run-time.
10. An electronic device, comprising: a memory and a processor, characterized in that the memory has stored therein a computer program, wherein the processor is arranged to run the computer program to perform the disease risk assessment method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311588798.1A CN117316458A (en) | 2023-11-27 | 2023-11-27 | Disease risk assessment method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311588798.1A CN117316458A (en) | 2023-11-27 | 2023-11-27 | Disease risk assessment method, device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117316458A true CN117316458A (en) | 2023-12-29 |
Family
ID=89286785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311588798.1A Pending CN117316458A (en) | 2023-11-27 | 2023-11-27 | Disease risk assessment method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117316458A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113903450A (en) * | 2021-09-13 | 2022-01-07 | 吾征智能技术(北京)有限公司 | Construction system of type 2 diabetes risk prediction model |
| CN114360728A (en) * | 2021-12-28 | 2022-04-15 | 南京鼓楼医院 | Prediction model for mild cognitive dysfunction of diabetes and construction method of nomogram |
| CN114694211A (en) * | 2022-02-24 | 2022-07-01 | 合肥工业大学 | Non-contact synchronous detection method and system for multiple physiological parameters |
| CN115517681A (en) * | 2022-10-24 | 2022-12-27 | 无锡市精神卫生中心 | Method and system for monitoring mood fluctuation and evaluating emotional disorder state of MD (MD) patient |
| CN117017297A (en) * | 2023-08-03 | 2023-11-10 | 吾征智能技术(北京)有限公司 | Method for establishing prediction and identification model of driver fatigue and application thereof |
-
2023
- 2023-11-27 CN CN202311588798.1A patent/CN117316458A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113903450A (en) * | 2021-09-13 | 2022-01-07 | 吾征智能技术(北京)有限公司 | Construction system of type 2 diabetes risk prediction model |
| CN114360728A (en) * | 2021-12-28 | 2022-04-15 | 南京鼓楼医院 | Prediction model for mild cognitive dysfunction of diabetes and construction method of nomogram |
| CN114694211A (en) * | 2022-02-24 | 2022-07-01 | 合肥工业大学 | Non-contact synchronous detection method and system for multiple physiological parameters |
| CN115517681A (en) * | 2022-10-24 | 2022-12-27 | 无锡市精神卫生中心 | Method and system for monitoring mood fluctuation and evaluating emotional disorder state of MD (MD) patient |
| CN117017297A (en) * | 2023-08-03 | 2023-11-10 | 吾征智能技术(北京)有限公司 | Method for establishing prediction and identification model of driver fatigue and application thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7261811B2 (en) | Systems and methods for non-invasive determination of blood pressure lowering based on trained predictive models | |
| US20200214575A1 (en) | Pulse Detection From Head Motions In Video | |
| Lahdenoja et al. | Atrial fibrillation detection via accelerometer and gyroscope of a smartphone | |
| KR102200526B1 (en) | Method and system for providing medical information based on the open APIs | |
| US20200196961A1 (en) | Non-Invasive Determination of Disease States | |
| Zhang et al. | Webcam-based, non-contact, real-time measurement for the physiological parameters of drivers | |
| EP3453321B1 (en) | Non-invasive method and system for estimating blood pressure from photoplethysmogram using statistical post-processing | |
| KR101738278B1 (en) | Emotion recognition method based on image | |
| US20150099987A1 (en) | Heart rate variability evaluation for mental state analysis | |
| US20210386343A1 (en) | Remote prediction of human neuropsychological state | |
| CN115024725A (en) | Tumor treatment aid decision-making system integrating psychological state multi-parameter detection | |
| Karthick et al. | Analysis of vital signs using remote photoplethysmography (RPPG) | |
| Gupta et al. | Availability and performance of face based non-contact methods for heart rate and oxygen saturation estimations: A systematic review | |
| CN115337018A (en) | Electrocardiosignal classification method and system based on overall dynamic characteristics | |
| Gupta et al. | Remote photoplethysmography‐based human vital sign prediction using cyclical algorithm | |
| Hsieh et al. | The emotion recognition system with Heart Rate Variability and facial image features | |
| CN117316458A (en) | Disease risk assessment method, device, storage medium and electronic equipment | |
| Paliwal et al. | Real time heart rate detection and heart rate variability calculation | |
| Vasavi et al. | Regression modelling for stress detection in humans by assessing most prominent thermal signature | |
| Cho et al. | Instant automated inference of perceived mental stress through smartphone ppg and thermal imaging | |
| Tarmizi et al. | A review of facial thermography assessment for vital signs estimation | |
| CN114271800B (en) | Non-invasive continuous blood pressure monitoring method and application in office environment | |
| Tan et al. | Camera-based Cardiovascular Screening based on Heart Rate and Its Variability In Pre-and Post-Exercise Conditions | |
| Balaraman et al. | Recent Innovations and Improvements in Remote Heart Rate and Heart Disease Measuring Methods Using RGB Camera | |
| Ma | Towards a Contactless Vital Sign System |
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 |