CN117064382A - Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence - Google Patents
Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence Download PDFInfo
- Publication number
- CN117064382A CN117064382A CN202311054621.3A CN202311054621A CN117064382A CN 117064382 A CN117064382 A CN 117064382A CN 202311054621 A CN202311054621 A CN 202311054621A CN 117064382 A CN117064382 A CN 117064382A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- module
- early warning
- 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.)
- Withdrawn
Links
- 239000008280 blood Substances 0.000 title claims abstract description 74
- 210000004369 blood Anatomy 0.000 title claims abstract description 74
- 238000004458 analytical method Methods 0.000 title claims abstract description 56
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 230000005856 abnormality Effects 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 47
- 238000001228 spectrum Methods 0.000 claims abstract description 36
- 238000006243 chemical reaction Methods 0.000 claims abstract description 32
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims description 42
- 238000012544 monitoring process Methods 0.000 claims description 25
- 230000003044 adaptive effect Effects 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 16
- 201000010099 disease Diseases 0.000 claims description 15
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 10
- 238000013136 deep learning model Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000036555 skin type Effects 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000002834 transmittance Methods 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 22
- 238000005259 measurement Methods 0.000 abstract description 10
- 208000015181 infectious disease Diseases 0.000 abstract description 7
- 238000010241 blood sampling Methods 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 6
- 239000000523 sample Substances 0.000 description 5
- 210000004204 blood vessel Anatomy 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 206010033372 Pain and discomfort Diseases 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000004159 blood analysis Methods 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000012089 stop solution Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14546—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring analytes not otherwise provided for, e.g. ions, cytochromes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Optics & Photonics (AREA)
- Physiology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention belongs to the field of artificial intelligence, and discloses an intelligent analysis and abnormality early warning system for blood biochemical parameters based on artificial intelligence. The system comprises: the data acquisition module acquires a near infrared spectrum value and a temperature signal of the measured part, and then transmits the temperature signal and the spectrum value to the data conversion module for further processing; the data conversion module is used for converting the near infrared spectrum value and the temperature signal into an electric signal; the signal enhancement module is used for enhancing the signal; the signal processing module substitutes the spectrum data and the temperature data into the established correction model, and calculates the blood biochemical parameter value of the tested person; and the early warning module carries out early warning prompt according to the biochemical parameter value of the blood of the tested person. The invention can realize noninvasive, rapid and continuous measurement, avoid infection and pain during measurement and blood sampling, and can carry out intelligent analysis and early warning on detection results.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to an artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality early warning system.
Background
Blood biochemical parameters such as blood sugar, triglyceride, total cholesterol, total protein content, etc. are important indicators reflecting the health status of the human body. The existing equipment for detecting biochemical parameters of human blood generally needs to puncture a blood vessel of a person to be detected to collect a blood sample, and then the blood sample is subjected to assay analysis, so that the numerical value of a biochemical index is obtained. Since this detection method causes pain and potential risk of infection to the subject, and the detection result needs to be obtained for a certain time, the detection result cannot be obtained at that time, and thus the real-time performance is poor. Moreover, intelligent analysis and abnormal early warning cannot be carried out on the detection result, so that a detected person also needs to register and queue up to inquire a doctor, and inconvenience is caused to the detected person.
Analyzing and summarizing the defects of the existing technology for detecting the biochemical parameters of human blood and the existing technical problems to be solved urgently:
defects of the prior art:
1. invasive detection: current testing methods require puncturing a blood vessel of a subject to collect a blood sample. This approach is invasive and may cause pain and discomfort to the subject.
2. Risk of potential infection: this detection method presents a potential risk of infection due to the need to puncture the blood vessel. If the lancing tool is not sufficiently clean or is improperly operated, infection may result.
3. The detection timeliness is poor: existing detection methods do not provide immediate results. The examinee needs to wait for a period of time to obtain the value of the biochemical index, which reduces the real-time performance of the detection.
4. Lack of intelligent analysis and early warning: the current devices do not provide intelligent analysis and anomaly early warning of the detection results. This means that the subject needs to additionally seek advice and diagnosis from the doctor.
5. The user experience is poor: because the detection result cannot be obtained immediately and intelligent analysis is lacking, the examinee often needs to additionally register, queue and consult with a doctor, which increases inconvenience and time cost.
The technical problems to be solved urgently exist:
1. development of a non-invasive detection method: a method is sought and developed which can accurately measure the biochemical parameters of blood without puncturing the blood vessel of a subject.
2. The detection speed and the real-time performance are improved: and detecting equipment capable of giving results in a short time is developed, so that the real-time or near real-time detection requirement is met.
3. Integrating intelligent analysis and early warning functions: and integrating artificial intelligence and machine learning technology into the equipment, automatically analyzing the detection result and providing abnormal early warning for the user.
4. Optimizing user experience: a one-stop solution was developed so that the subject could complete the detection, analysis, and consultation process on a single device or platform, reducing unnecessary additional steps.
In general, existing blood biochemical parameter detection techniques have a number of drawbacks and technical problems that provide opportunities and challenges for research and development innovations in the relevant fields.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides an artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality early warning system.
The invention is realized in such a way that an artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality early warning system is realized by the following steps:
1) And a data acquisition module:
and monitoring and acquiring near infrared spectrum values and temperature signals of the measured part in real time.
Advanced sensor technology is adopted to ensure adaptability and data acquisition accuracy under different skin types and environmental conditions.
Noise in the data is processed and removed in real time using a deep learning algorithm.
2) And a data conversion module:
and converting the acquired spectrum value and temperature signal into an electric signal format suitable for subsequent processing.
A high speed analog to digital converter (ADC) converts the data.
An adaptive algorithm is used to identify and filter outliers or errors in the conversion process.
3) A signal enhancement module:
enhancing the incoming electrical signal from the data conversion module.
The electrical signal is enhanced by applying adaptive filtering techniques.
The filtering and enhancement parameters are automatically adjusted by AI techniques and deep learning.
4) And a signal processing module:
analyzing the enhanced electrical signals and predicting corresponding blood biochemical parameter values.
Pre-training of the model was performed using existing blood biochemical parameter datasets.
A correction model is constructed using deep learning (e.g., CNN, RNN, etc.).
Continuous learning of the system is realized, and the model is optimized and updated regularly by collecting new data.
5) And the early warning module is used for:
and comparing the predicted blood biochemical parameter value with a health standard, and providing an early warning for a user.
A health standard database containing normal ranges of various biochemical indexes is constructed based on the database technology.
And comparing the predicted value with the standard in the database in real time by using an algorithm, and judging whether the early warning needs to be triggered.
Personalized pre-warnings and advice are provided for each user, taking into account the user's historical data and other relevant health information.
Further, the system overall structure optimizing module:
and the data cloud storage and analysis sub-module: the system can upload the data to the cloud in real time, and remote storage, big data analysis and backup of the data are realized.
Medical expert system interfacing sub-module: interfacing with a medical expert system or medical facility ensures that medical advice or services are available quickly when needed by the user.
With the integration and refinement described above, this system aims to provide efficient, accurate and non-invasive blood biochemical parameter monitoring and early warning services for users while ensuring the safety and availability of data. The system comprises:
the data acquisition module is used for acquiring a near infrared spectrum value and a temperature signal of the measured part, and then transmitting the temperature signal and the spectrum value to the data conversion module for further processing;
the data conversion module is connected with the data acquisition module and used for converting the near infrared spectrum value and the temperature signal into an electric signal;
the signal enhancement module is connected with the data conversion module and used for enhancing the signal;
the signal processing module is connected with the signal enhancement module and is used for substituting the spectrum data and the temperature data into the established correction model and calculating the blood biochemical parameter value of the tested person;
the early warning module is connected with the signal processing module and used for carrying out early warning prompt according to the blood biochemical parameter value of the tested person.
Further, the data acquisition module comprises a light source for providing illumination through optical fiber conduction, a spectrometer for acquiring the spectrum value of the measured part and a temperature sensor for measuring the temperature value of the measured part.
Further, the specific method for converting the spectrum value and the temperature value into the electric signal by the data conversion module is as follows:
converting the spectrum value and temperature value signals into serial data packets to be transmitted;
performing serial/parallel conversion on the acquired serial data packet, and transmitting the serial data packet to a corresponding node;
each node performs PSK mapping and frequency hopping processing on the received related data;
and outputting the current of the related data obtained after PSK mapping and frequency hopping processing through an adaptive filter.
Further, the specific method for enhancing the signal by the signal enhancement module is as follows:
establishing an irregular index of a discrete time sequence by using a time function of the Hurst index;
and (3) carrying out iterative calculation on parameters of the adaptive filter by using a cost function, wherein the calculation formula is as follows:
jw=c+ into H
Wherein Jw is a cost function, cw is a convergence index, lambda is a Lagrangian multiplier, hw is an irregularity index, n is a time ordinal, w (n) is a parameter matrix of the adaptive filter, mu is an iteration step length, e (n) is an error signal, h (n) is an output signal matrix of the delay module, g (n) is an output signal of the adaptive filter, and i1 and i2 are interval ordinals;
the adaptive filter outputs a denoised target signal under the adjusted parameters;
and superposing callback signal data obtained after signal enhancement processing, and inputting the callback signal data to a signal processing module after coupling.
Further, the signal processing module substitutes the spectrum data and the temperature data into the established correction model, and the calculating of the blood biochemical parameter value of the tested person comprises the following steps:
the method comprises the steps of adopting an improved random inspection method to determine the number of optimal principal components in a modeling process, wherein the process of determining the number of the optimal principal components is as follows:
(1) Obtaining P main components by utilizing partial least square regression on the preprocessed spectrum data, wherein P is a preset value;
(2) Calculating the component vectors of the P principal components, and further calculating covariance of each component vector and the concentration vector;
(3) After the concentration matrix is arranged randomly, calculating the covariance of the concentration matrix and the component, and calculating the difference between the covariance and the covariance obtained in the step G2;
(4) Repeating the step G3 for K times to obtain K covariance differences, wherein K is a preset value;
(5) Counting the standard deviation of K covariance differences in the step G4 under each principal component;
(6) And calculating the difference of the contribution rates of two adjacent principal components to the model, and taking the critical value of the difference as the optimal number of the principal components when the difference is stable, wherein the principal components are used for building a PLS theorem correction model.
Further, the early warning module carries out early warning prompt according to the analysis result, and specifically comprises:
combining the basic information, disease type, disease stage and severity of the user, historical disease monitoring data and historical processing results, and presetting standard thresholds of various diagnosis indexes of the user after comprehensive analysis;
judging whether early warning is needed according to the current disease monitoring data and a standard threshold value corresponding to the user, and performing audible and visual alarm after the current disease monitoring data and the standard threshold value are exceeded.
Further, the analysis results include a safety signal and a hazard signal.
Further, the safety signal is a safety signal sent out after the monitoring data exceeds a standard threshold value; the dangerous signal is sent out after the monitoring data exceeds the standard threshold value.
The invention also aims to provide an artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning method for implementing the artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning system, which comprises the following steps:
s1: collecting a near infrared spectrum value and a temperature signal of a measured part by using a data collecting module, and then transmitting the temperature signal and the spectrum value to a data converting module for further processing;
s2: converting the near infrared spectrum value and the temperature signal into an electric signal by using a data conversion module, and enhancing the signal by using a signal enhancement module;
s3: substituting the spectrum data and the temperature data into the established correction model by using the signal processing module, and calculating the blood biochemical parameter value of the tested person;
s4: and (5) utilizing an early warning module to perform early warning prompt according to the biochemical parameter value of the blood of the tested person.
Another object of the present invention is to provide a computer device, where the computer device includes a memory and a processor, where the memory stores a computer program, and where the computer program when executed by the processor causes the processor to execute the steps of the artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality pre-warning method.
In combination with the technical scheme and the technical problems to be solved, the technical scheme to be protected has the following advantages and positive effects:
according to the artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality early warning system, a near infrared spectrum analysis technology is adopted, so that noninvasive, rapid and continuous measurement can be realized, and pain during infection, measurement and blood sampling is avoided. The temperature sensor arranged at the front end of the spectrum acquisition probe can transmit the temperature of the measured part of the human body to the microprocessor unit as one input of the correction model to participate in prediction calculation, and can eliminate errors caused by temperature change in the measurement process by the way, thereby further improving the measurement accuracy of the biochemical parameters of the blood of the human body.
In addition, by providing a method for selecting the number of main components in the correction model, the calculation complexity is reduced, the real-time and rapid measurement can be realized, and meanwhile, invalid information in a spectrum can be removed, so that the aim of improving the measurement accuracy is fulfilled.
Secondly, the invention effectively solves the problem of poor real-time performance in the prior art. Moreover, the intelligent analysis and abnormal early warning can not be carried out on the detection result, so that the detected person also needs to register and queue to inquire a doctor, the inconvenient technical problem is caused to the detected person, the noninvasive, rapid and continuous measurement can be realized, the pain during infection and measurement blood sampling is avoided, and the intelligent analysis and early warning can be carried out on the detection result.
Thirdly, based on each structural component of the blood biochemical parameter intelligent analysis and abnormality early warning system of artificial intelligence, we can further analyze the remarkable technical progress made by each component:
1. and a data acquisition module:
significant technical progress: the sensitivity and accuracy of the sensor are remarkably improved, so that the data acquisition process is more accurate and efficient. Meanwhile, the real-time deep learning algorithm greatly optimizes the data quality for removing noise.
2. And a data conversion module:
significant technical progress: the introduction of the high-speed analog-to-digital converter (ADC) greatly improves the speed and efficiency of the data conversion process, and meanwhile, the intelligent algorithm further ensures the quality of the data by automatically identifying and correcting the conversion errors.
3. A signal enhancement module:
significant technical progress: the self-adaptive filtering technology and the AI technology are combined, so that the quality of the electric signal is enhanced, the filtering and enhancing parameters are automatically adjusted, and the processing effect and accuracy are greatly improved.
4. And a signal processing module:
significant technical progress:
through deep learning technology such as CNN and RNN, the analysis capability of the spectrum data is greatly improved, so that the prediction is more accurate.
The introduction of continuous learning enables the system to adapt to new data at any time, and the timeliness and accuracy of the model are maintained.
5. And the early warning module is used for:
significant technical progress:
the combination of the construction of the health standard database and the real-time comparison algorithm ensures that the early warning is more timely and accurate.
The personalized early warning system is introduced to take the individual difference and the historical health data of each user into consideration, so that early warning and advice are more fit with the demands of the users.
In general, the system achieves significant technical improvements in each structural component, not only improves the overall efficiency and accuracy of the system, but also enhances the user experience and meets the personalized requirements. These technological advances provide a powerful technical support for real-time, noninvasive and accurate monitoring of blood biochemical parameters.
Drawings
FIG. 1 is a block diagram of an artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning system according to an embodiment of the present invention;
FIG. 2 is a flowchart of an intelligent analysis and abnormality pre-warning method for blood biochemical parameters based on artificial intelligence according to an embodiment of the present invention;
in the figure: 1. a data acquisition module; 2. a data conversion module; 3. a signal enhancement module; 4. a signal processing module; 5. and an early warning module.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, an embodiment of the present invention provides an artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning system, which includes:
the data acquisition module 1 is used for acquiring a near infrared spectrum value and a temperature signal of a measured part, and then transmitting the temperature signal and the spectrum value to the data conversion module for further processing;
for the data acquisition module in the blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence, the specific implementation can be as follows:
1. monitoring near infrared spectrum and temperature signal in real time
Spectral sensor: real-time monitoring of blood parameters is performed using a high-sensitivity near infrared spectrum sensor. These sensors are based on spectral reflectance or transmittance principles, which are able to identify different chemical components in blood.
Temperature sensor: the skin temperature is measured using a micro thermocouple or thermistor. These sensors need to be in close contact with the skin to ensure accuracy.
2. Advanced sensor technology adaptation
Multi-modal sensing techniques: multiple types of sensors are combined to accommodate different skin types and environmental conditions. For example, for dark skin, light sources of different wavelengths may be required to improve detection accuracy.
Adaptive light source adjustment: the optical intensity or wavelength of the transmitter is dynamically adjusted by monitoring the returned spectral signal intensity in real time to obtain an optimal signal.
Environmental compensation system: for changes in external environment (such as light, humidity, etc.), the system can be automatically calibrated or adjusted to ensure the accuracy of the data.
3. Noise removal using deep learning
Data preprocessing: firstly, the original data is standardized or normalized to meet the input requirement of a deep learning model.
Deep learning model: a Convolutional Neural Network (CNN) model is designed. The task of this model is to learn and extract useful features from the noisy spectral signal while removing noise.
Model training: the model is trained using a large amount of noisy and corresponding clean spectral data. This requires a lot of computational resources, but training is only done once or when an update is needed.
And (3) real-time denoising: when the system operates in real time, the model can remove noise of the spectrum signal acquired in real time through forward propagation, and output a clear spectrum signal to the next module.
In addition, in order to achieve the above functions, it is also necessary to provide a corresponding hardware platform, such as an embedded processor having a high-speed processing capability, a sufficient memory space, and an operating system suitable for real-time processing.
The data conversion module 2 is connected with the data acquisition module 1 and is used for converting the near infrared spectrum value and the temperature signal into an electric signal;
the signal enhancement module 3 is connected with the data conversion module 2 and is used for enhancing signals;
the signal processing module 4 is connected with the signal enhancement module 3 and is used for substituting the spectrum data and the temperature data into the established correction model to calculate the blood biochemical parameter value of the tested person;
and the early warning module 5 is connected with the signal processing module 4 and is used for carrying out early warning prompt according to the biochemical parameter value of the blood of the tested person.
The data acquisition module 1 comprises a light source for providing illumination through optical fiber conduction, a spectrometer for acquiring the spectrum value of the measured part and a temperature sensor for measuring the temperature value of the measured part.
The specific method for converting the spectrum value and the temperature value into the electric signal by the data conversion module 2 is as follows:
converting the spectrum value and temperature value signals into serial data packets to be transmitted;
performing serial/parallel conversion on the acquired serial data packet, and transmitting the serial data packet to a corresponding node;
each node performs PSK mapping and frequency hopping processing on the received related data;
and outputting the current of the related data obtained after PSK mapping and frequency hopping processing through an adaptive filter.
The blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence comprises the following detailed signal and data processing processes:
1. and a data acquisition module:
1) Sensor placement: the user places the device at a designated site (e.g., wrist) to be tested. At this point, the sensor begins to collect near infrared spectral values and temperature signals.
2) And (3) environmental adaptation: the sensor automatically recognizes the skin type and the environmental condition, and performs self-adaptive adjustment to ensure the accuracy of the data.
3) Data preprocessing: the raw data stream enters a deep learning model that has been pre-trained for real-time removal of noise and other interference factors from the data.
2. And a data conversion module:
1) Signal conversion: the preprocessed near infrared spectrum and temperature signals are converted into digital electrical signals by an analog-to-digital converter.
2) Abnormal value detection: the adaptive algorithm examines the converted electrical signal in real time, looking up and filtering any possible outliers or conversion errors.
3. A signal enhancement module:
1) And (3) signal input: an electrical signal is received from the data conversion module.
2) And (3) filtering enhancement: and (3) removing high-frequency noise and low-frequency interference in the signal by applying an adaptive filtering technology.
3) Parameter adjustment: the deep learning model automatically adjusts filtering and enhancing parameters according to the characteristics of the signals, and ensures the quality of the output signals.
4. And a signal processing module:
1) Model prediction: the enhanced electrical signals are input into a deep learning model that has been pre-trained using a large number of blood biochemical parameter datasets.
2) Outputting a result: the model analyzes the electrical signals and predicts corresponding blood biochemical parameter values.
3) Model optimization: the system continues to collect new data and uses this data periodically to optimize and update the model.
5. And the early warning module is used for:
1) Parameter comparison: the system compares the predicted blood biochemical parameter values to standards in a database of health standards.
2) Triggering and early warning: if the predicted value is beyond the normal range, the system triggers an early warning mechanism.
3) Personalized advice: the system generates personalized health advice or medical intervention advice, taking into account the user's historical data and other health information, and presents it to the user via a user interface or other means.
This process involves a number of advanced techniques including sensor technology, deep learning, signal processing, etc. Each stage is carefully designed, and the high efficiency and accuracy of the whole system are ensured.
The specific method for enhancing the signal by the signal enhancement module 3 is as follows:
establishing an irregular index of a discrete time sequence by using a time function of the Hurst index;
and (3) carrying out iterative calculation on parameters of the adaptive filter by using a cost function, wherein the calculation formula is as follows:
jw=c+ into Hw;
wherein Jw is a cost function, cw is a convergence index, lambda is a Lagrangian multiplier, hw is an irregularity index, n is a time ordinal, w (n) is a parameter matrix of the adaptive filter, mu is an iteration step length, e (n) is an error signal, h (n) is an output signal matrix of the delay module, g (n) is an output signal of the adaptive filter, and i1 and i2 are interval ordinals;
the adaptive filter outputs a denoised target signal under the adjusted parameters;
and superposing callback signal data obtained after signal enhancement processing, and inputting the callback signal data to a signal processing module after coupling.
The signal processing module 4 substitutes the spectrum data and the temperature data into the established correction model, and the calculating of the blood biochemical parameter value of the tested person comprises the following steps:
the method comprises the steps of adopting an improved random inspection method to determine the number of optimal principal components in a modeling process, wherein the process of determining the number of the optimal principal components is as follows:
(1) Obtaining P main components by utilizing partial least square regression on the preprocessed spectrum data, wherein P is a preset value;
(2) Calculating the component vectors of the P principal components, and further calculating covariance of each component vector and the concentration vector;
(3) After the concentration matrix is arranged randomly, calculating the covariance of the concentration matrix and the component, and calculating the difference between the covariance and the covariance obtained in the step G2;
(4) Repeating the step G3 for K times to obtain K covariance differences, wherein K is a preset value;
(5) Counting the standard deviation of K covariance differences in the step G4 under each principal component;
(6) And calculating the difference of the contribution rates of two adjacent principal components to the model, and taking the critical value of the difference as the optimal number of the principal components when the difference is stable, wherein the principal components are used for building a PLS theorem correction model.
The early warning module 5 carries out early warning prompt according to the analysis result, and specifically comprises:
combining the basic information, disease type, disease stage and severity of the user, historical disease monitoring data and historical processing results, and presetting standard thresholds of various diagnosis indexes of the user after comprehensive analysis;
judging whether early warning is needed according to the current disease monitoring data and a standard threshold value corresponding to the user, and performing audible and visual alarm after the current disease monitoring data and the standard threshold value are exceeded.
The analysis results include a safety signal and a hazard signal.
The safety signal is sent out after the monitoring data exceeds a standard threshold value; the dangerous signal is sent out after the monitoring data exceeds the standard threshold value.
The embodiment of the invention provides an artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning method for implementing the artificial intelligence based blood biochemical parameter intelligent analysis and abnormality early warning system, which comprises the following steps:
s1: collecting a near infrared spectrum value and a temperature signal of a measured part by using a data collecting module, and then transmitting the temperature signal and the spectrum value to a data converting module for further processing;
s2: converting the near infrared spectrum value and the temperature signal into an electric signal by using a data conversion module, and enhancing the signal by using a signal enhancement module;
s3: substituting the spectrum data and the temperature data into the established correction model by using the signal processing module, and calculating the blood biochemical parameter value of the tested person;
s4: and (5) utilizing an early warning module to perform early warning prompt according to the biochemical parameter value of the blood of the tested person.
The embodiment of the invention provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, enables the processor to execute the steps of the blood biochemical parameter intelligent analysis and abnormality early warning method based on artificial intelligence.
Based on the blood biochemical parameter intelligent analysis and abnormality early warning system based on the artificial intelligence, the following two specific embodiments and implementation schemes thereof are as follows:
example 1: portable intelligent blood detection equipment
#1, data acquisition module:
-implementation scheme: the miniature near infrared spectrum sensor and the temperature sensor are integrated into a small portable device. The user simply places the device on the wrist and the device begins to collect data.
#2. Data conversion module:
-implementation scheme: a miniature analog-to-digital converter (ADC) is integrated into the device to convert the analog signal read by the sensor into a digital signal.
#3. Signal enhancing Module:
-implementation scheme: and integrating an operational amplifier in an internal circuit of the equipment, carrying out preliminary amplification on signals, and carrying out digital filtering through an embedded system.
#4. Signal processing Module:
-implementation scheme: the device is internally provided with a micro processor, a trained deep learning model is preloaded, and the processor rapidly calculates the acquired data and outputs the blood biochemical parameter value.
#5. Early warning module:
-implementation scheme: when the obtained biochemical parameters exceed the normal range, the LED lamp on the equipment can flash or make a sound, and meanwhile, the equipment can be connected with the mobile phone APP through Bluetooth to send abnormal data and suggestions to the mobile phone of the user.
Example 2: comprehensive blood analysis system of family medical center
#1, data acquisition module:
-implementation scheme: using high precision near infrared spectrometers and temperature sensors, it is designed in a form that is easy for the user to handle, such as a probe held in one hand.
#2. Data conversion module:
-implementation scheme: high-speed and high-resolution analog-digital converter is utilized to ensure high quality and accuracy of data.
#3. Signal enhancing Module:
-implementation scheme: through high-performance signal processing chip and circuit design, the high-efficiency enhancement and optimization of signals are realized.
#4. Signal processing Module:
-implementation scheme: a high-performance computer is arranged in the system, and a deep learning model specially optimized for blood parameter analysis is operated. Meanwhile, the model can be updated and optimized in real time.
#5. Early warning module:
-implementation scheme: the large screen displays the analysis result, if there is an abnormality, the screen highlights the abnormal parameters and accompanies the voice prompt. The system can also send data and alerts to other devices or medical professionals over the internet or home lan.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
The two embodiments are respectively suitable for different use scenes, one is convenient to use anytime and anywhere, and the other is more suitable for occasions such as a family medical center. The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (10)
1. An artificial intelligence-based blood biochemical parameter intelligent analysis and abnormality early warning system is characterized in that the system comprises:
1) And a data acquisition module:
monitoring and acquiring near infrared spectrum values and temperature signals of a measured part in real time;
advanced sensor technology is adopted to ensure the adaptability and data acquisition accuracy under different skin types and environmental conditions;
processing and removing noise in the data in real time by using a deep learning algorithm;
2) And a data conversion module:
converting the collected spectrum value and temperature signal into an electric signal format suitable for subsequent processing;
the high-speed analog-to-digital converter converts the data;
identifying and filtering outliers or errors in the conversion process using an adaptive algorithm;
3) A signal enhancement module:
enhancing the electrical signal incoming from the data conversion module;
the adaptive filtering technology is applied to enhance the electric signal;
automatically adjusting filtering and enhancing parameters through AI technology and deep learning;
4) And a signal processing module:
analyzing the enhanced electric signals and predicting corresponding blood biochemical parameter values;
pre-training the model by using the existing blood biochemical parameter data set;
constructing a correction model by deep learning;
continuous learning of the system is realized, and the model is optimized and updated regularly by collecting new data;
5) And the early warning module is used for:
comparing the predicted blood biochemical parameter value with a health standard to provide an early warning for a user;
constructing a health standard database containing normal ranges of various biochemical indexes based on a database technology;
comparing the predicted value with the standard in the database in real time by using an algorithm, and judging whether the early warning needs to be triggered;
personalized pre-warnings and advice are provided for each user, taking into account the user's historical data and other relevant health information.
2. The intelligent analysis and anomaly early warning system for blood biochemical parameters based on artificial intelligence according to claim 1, further comprising a system overall structure optimization module, the module comprising:
and the data cloud storage and analysis sub-module: the system can upload the data to the cloud in real time, and remote storage, big data analysis and backup of the data are realized.
Medical expert system interfacing sub-module: interfacing with a medical expert system or medical facility to ensure that medical advice or services can be quickly obtained when needed by the user;
the data acquisition module comprises a light source for providing illumination through optical fiber conduction, a spectrometer for acquiring the spectrum value of the measured part and a temperature sensor for measuring the temperature value of the measured part.
3. The intelligent analysis and abnormality pre-warning system for blood biochemical parameters based on artificial intelligence according to claim 1, wherein the specific method for converting the spectrum value and the temperature value into the electric signal by the data conversion module is as follows:
1) Monitoring near infrared spectrum and temperature signal in real time
Spectral sensor: real-time monitoring of blood parameters using a high-sensitivity near infrared spectrum sensor; these sensors are based on spectral reflectance or transmittance principles, which are able to identify different chemical components in blood;
temperature sensor: measuring skin temperature with a micro thermocouple or thermistor; these sensors need to be in close contact with the skin to ensure accuracy;
2) Advanced sensor technology adaptation
Multi-modal sensing techniques: combining multiple types of sensors to accommodate different skin types and environmental conditions;
adaptive light source adjustment: dynamically adjusting the light intensity or wavelength of the transmitter by monitoring the returned spectrum signal intensity in real time to obtain an optimal signal;
environmental compensation system: for the change of external environment, the system can automatically calibrate or adjust to ensure the accuracy of data;
3) Noise removal using deep learning
Data preprocessing: firstly, carrying out standardization or normalization processing on original data to enable the original data to meet the input requirement of a deep learning model;
deep learning model: designing a convolutional neural network model; the task of the model is to learn and extract useful features from the noisy spectral signal while removing noise;
model training: training the model by using a large amount of noisy and corresponding clear spectrum data; this requires a lot of computational resources, but training is only done once or when an update is needed;
and (3) real-time denoising: when the system operates in real time, the model can remove noise of the spectrum signal acquired in real time through forward propagation, and output a clear spectrum signal to the next module.
4. The intelligent analysis and abnormality pre-warning system for blood biochemical parameters based on artificial intelligence as claimed in claim 1, wherein the specific method for enhancing the signals by the signal enhancement module is as follows:
establishing an irregular index of a discrete time sequence by using a time function of the Hurst index;
and (3) carrying out iterative calculation on parameters of the adaptive filter by using a cost function, wherein the calculation formula is as follows:
J w ＝C w +λH w ；
wherein Jw is a cost function, cw is a convergence index, lambda is a Lagrangian multiplier, hw is an irregularity index, n is a time ordinal, w (n) is a parameter matrix of the adaptive filter, mu is an iteration step length, e (n) is an error signal, h (n) is an output signal matrix of the delay module, g (n) is an output signal of the adaptive filter, and i1 and i2 are interval ordinals;
the adaptive filter outputs a denoised target signal under the adjusted parameters;
and superposing callback signal data obtained after signal enhancement processing, and inputting the callback signal data to a signal processing module after coupling.
5. The intelligent analysis and anomaly early warning system for blood biochemical parameters based on artificial intelligence according to claim 1, wherein the signal processing module substitutes the spectral data and the temperature data into the established correction model, and the calculating of the blood biochemical parameter value of the tested person comprises:
the method comprises the steps of adopting an improved random inspection method to determine the number of optimal principal components in a modeling process, wherein the process of determining the number of the optimal principal components is as follows:
(1) Obtaining P main components by utilizing partial least square regression on the preprocessed spectrum data, wherein P is a preset value;
(2) Calculating the component vectors of the P principal components, and further calculating covariance of each component vector and the concentration vector;
(3) After the concentration matrix is arranged randomly, calculating the covariance of the concentration matrix and the component, and calculating the difference between the covariance and the covariance obtained in the step G2;
(4) Repeating the step G3 for K times to obtain K covariance differences, wherein K is a preset value;
(5) Counting the standard deviation of K covariance differences in the step G4 under each principal component;
(6) And calculating the difference of the contribution rates of two adjacent principal components to the model, and taking the critical value of the difference as the optimal number of the principal components when the difference is stable, wherein the principal components are used for building a PLS theorem correction model.
6. The intelligent analysis and abnormality early warning system based on artificial intelligence for blood biochemical parameters according to claim 1, wherein the early warning module carries out early warning prompt according to the analysis result, specifically comprising:
combining the basic information, disease type, disease stage and severity of the user, historical disease monitoring data and historical processing results, and presetting standard thresholds of various diagnosis indexes of the user after comprehensive analysis;
judging whether early warning is needed according to the current disease monitoring data and a standard threshold value corresponding to the user, and performing audible and visual alarm after the current disease monitoring data and the standard threshold value are exceeded.
7. The intelligent analysis and anomaly early warning system for blood biochemical parameters based on artificial intelligence according to claim 1, wherein the analysis result comprises a safety signal and a danger signal.
8. The intelligent analysis and abnormality pre-warning system for blood biochemical parameters based on artificial intelligence according to claim 7, wherein the safety signal is a safety signal sent after the monitoring data exceeds a standard threshold; the dangerous signal is sent out after the monitoring data exceeds the standard threshold value.
9. An artificial intelligence based blood biochemical parameter intelligent analysis and abnormality pre-warning method for implementing the artificial intelligence based blood biochemical parameter intelligent analysis and abnormality pre-warning system as claimed in any one of claims 1 to 7, characterized in that the method comprises:
s1: collecting a near infrared spectrum value and a temperature signal of a measured part by using a data collecting module, and then transmitting the temperature signal and the spectrum value to a data converting module for further processing;
s2: converting the near infrared spectrum value and the temperature signal into an electric signal by using a data conversion module, and enhancing the signal by using a signal enhancement module;
s3: substituting the spectrum data and the temperature data into the established correction model by using the signal processing module, and calculating the blood biochemical parameter value of the tested person;
s4: and (5) utilizing an early warning module to perform early warning prompt according to the biochemical parameter value of the blood of the tested person.
10. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the artificial intelligence based blood biochemical parameter intelligent analysis and anomaly pre-warning method of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311054621.3A CN117064382A (en) | 2023-08-21 | 2023-08-21 | Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311054621.3A CN117064382A (en) | 2023-08-21 | 2023-08-21 | Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117064382A true CN117064382A (en) | 2023-11-17 |
Family
ID=88705643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311054621.3A Withdrawn CN117064382A (en) | 2023-08-21 | 2023-08-21 | Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117064382A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117912711A (en) * | 2024-03-19 | 2024-04-19 | 吉林大学 | Hemodialysis data acquisition and analysis system and method |
-
2023
- 2023-08-21 CN CN202311054621.3A patent/CN117064382A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117912711A (en) * | 2024-03-19 | 2024-04-19 | 吉林大学 | Hemodialysis data acquisition and analysis system and method |
| CN117912711B (en) * | 2024-03-19 | 2024-05-24 | 吉林大学 | Hemodialysis data acquisition and analysis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lekha et al. | Real-time non-invasive detection and classification of diabetes using modified convolution neural network | |
| US20170181670A1 (en) | Noninvasive method for estimating glucose blood constituents | |
| CN117064382A (en) | Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence | |
| US10405785B2 (en) | Determination of a concentration of an analyte in a subject | |
| CN112788200B (en) | Method and device for determining frequency spectrum information, storage medium and electronic device | |
| CN107803843A (en) | A kind of measuring of human health robot based on Raspberry Pi | |
| WO2023123864A1 (en) | Muscle state determining apparatus based on electromyographic signal and muscle blood oxygen saturation | |
| Li et al. | Low power optimisations for iot wearable sensors based on evaluation of nine qrs detection algorithms | |
| CN112006673A (en) | Human body heart rate detection method and system, storage medium, computer equipment and terminal | |
| Aziz et al. | Automated cardiac pulse cycle analysis from photoplethysmogram (PPG) signals generated from fingertip videos captured using a smartphone to measure blood hemoglobin levels | |
| CN204581297U (en) | A kind of insulin resistant detector based on pulse wave | |
| CN115979995B (en) | Blood lactic acid content detection model establishment method and detection method | |
| CN106805943A (en) | Blood glucose level data processing method and processing device based on Fractional Differential Equation | |
| CN105411568A (en) | Automatic medical monitoring method | |
| KR101661116B1 (en) | Programmable multi-modal bio-signal processing module and healthcare platform using the same | |
| CN114557691A (en) | Non-invasive blood lipid detection method and system based on multi-wavelength PPG (photoplethysmography) signals | |
| CN115349832A (en) | Vital sign monitoring and early warning system and method | |
| CN107928682B (en) | Information acquisition sensor and physiological parameter acquisition device | |
| Hamad et al. | Remote ECG signal monitoring and classification based on Arduino with AD8232 sensor | |
| CN107174220A (en) | Multi-mode biopotential sensor based on intelligent processor platform | |
| EP4230140A1 (en) | Muscle state determining apparatus based on electromyographic signal and muscle blood oxygen saturation | |
| CN112754479A (en) | Method and equipment for detecting blood glucose concentration | |
| EP2946722A1 (en) | Portable electronic device for breath sampling | |
| CN111751492A (en) | Exhaled breath detection method and device | |
| CN117174311A (en) | Post-traumatic sepsis course monitoring and early warning system, method and application |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231117 |
|
| WW01 | Invention patent application withdrawn after publication |