WO2022045872A1 - A system for calibrating medical devices and its method - Google Patents

A system for calibrating medical devices and its method Download PDF

Info

Publication number
WO2022045872A1
WO2022045872A1 PCT/MY2020/050152 MY2020050152W WO2022045872A1 WO 2022045872 A1 WO2022045872 A1 WO 2022045872A1 MY 2020050152 W MY2020050152 W MY 2020050152W WO 2022045872 A1 WO2022045872 A1 WO 2022045872A1
Authority
WO
WIPO (PCT)
Prior art keywords
variation
medical devices
module
master device
devices
Prior art date
Application number
PCT/MY2020/050152
Other languages
French (fr)
Inventor
Katrul Nadia BINTI BASRI
Mohd Hafizulfika BIN HISHAM
Nur Azera BINTI TUHAIME
Zalhan BINTI MD YUSOF
Amal Asyikin BINTI ABDUL HALIM
Muhammad Hafiz BIN LAILI
Hyzan BIN MOHD YUSOF
Original Assignee
OSA Technology Sdn Bhd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by OSA Technology Sdn Bhd filed Critical OSA Technology Sdn Bhd
Priority to AU2020465148A priority Critical patent/AU2020465148A1/en
Publication of WO2022045872A1 publication Critical patent/WO2022045872A1/en

Links

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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
    • 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
    • A61B5/1495—Calibrating or testing of in-vivo probes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
    • A61B2560/02—Operational features
    • A61B2560/0223—Operational features of calibration, e.g. protocols for calibrating sensors
    • A61B2560/0228—Operational features of calibration, e.g. protocols for calibrating sensors using calibration standards
    • A61B2560/0233—Optical standards
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
    • 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
    • A61B5/14532—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 glucose, e.g. by tissue impedance measurement
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/60—Software deployment
    • G06F8/65—Updates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/70—Software maintenance or management

Definitions

  • the invention relates to a system for calibrating medical devices. More particularly, the invention relates to a system for calibrating medical devices from a remote server and method thereof.
  • diabetic patients may need to prick their fingers and test their blood glucose levels several times a day.
  • Such a method is not beneficial to these patients as their blood circulation is slower than a healthy person and this affects the process to deliver nutrients to wounds.
  • the injuries caused by pricking heal slowly, or may not heal at all.
  • the slow recovering injuries can also increase the risk of infections and other complications to these patients. Therefore, a new technique called non-invasive glucose monitoring is introduced to measure of blood glucose levels for diabetic patients without drawing blood, puncturing the skin, or causing pain or trauma.
  • One of the issues is variation across multiple optical spectroscopy instruments during measurement of a sample.
  • the variation may be caused by various factors such as interference of external light source or defected components of the optical spectroscopy instrument.
  • the existing monitoring system has a low signal-to-noise ratio that causes variation in a prediction algorithm for determining the blood glucose level.
  • US6517482B1 discloses a method and apparatus for non- invasively determining glucose levels in a fluid of a subject, typically the blood glucose level.
  • the impedance of skin tissue is measured and the measurement is used with impedance measurements previously correlated with directly determined glucose levels to determine the glucose level from the newly measured impedance. It is thus possible, to routinely non-invasively determine fluid glucose levels.
  • US9336353B2 discloses a system and method for communicating glucose concentration information between devices of a continuous glucose monitoring system.
  • the continuous glucose monitoring system can include a sensor module generates a glucose concentration measurement data and transmits the data to one or more further devices of the continuous glucose monitoring system.
  • the further devices can include a receiver unit and one or more secondary display devices.
  • the receiver unit can be configured to be a stand-alone device of or physically connect to a secondary display device.
  • a user interface can also be provided that provides enhanced functionality for using the continuous glucose monitoring system.
  • One object of the invention is to enable calibration of faulty medical devices from a remote server with a master-slave configuration.
  • Another object of the invention is to ensure measurement consistency of the medical devices by standardizing a measurement of slave devices with reference to a master device.
  • the invention provides a system for calibrating medical devices comprising a server in communication with a plurality of medical devices, in which the server having a central processing module for facilitating data communication among a plurality of modules connected thereto, the modules comprising a multiple management calibration module for differentiating between non-faulty medical devices and faulty medical devices from the plurality of medical devices based on one predetermined threshold; a variation standardization module for assigning one non-faulty medical device as a master device and other medical devices as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; and an optimization module for optimizing a learning model based on the computed variation; wherein the variation standardization module updates the master device based on the optimized learning model such that the slave devices are standardized according to the master device and thereby ensuring measurement consistency among the medical devices.
  • the multiple management calibration module compares a measurable quantity of a sample retrieved from the medical devices to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
  • the multiple management calibration module further computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module.
  • the variation standardization module computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
  • the optimization module carries out spectral pretreatment to remove noise from the computed variation.
  • the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
  • the optimization module classifies the variation based on one hot encoding into its respective class indicative of a range of the variation.
  • the optimization module optimizes the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
  • the medical devices is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
  • a method for calibrating medical device comprising the steps of differentiating, by a multiple management calibration module, between non-faulty medical devices and faulty medical devices from a plurality of medical devices based on one predetermined threshold; assigning, by a variation standardization module one non-faulty medical device as a master device and other medical devices as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; optimizing, by an optimization module, a learning model based on the computed variation; updating, by the variation standardization module, the master device based on the optimized learning model; and standardizing the slave devices according to the master device and thereby ensuring measurement consistency among the medical devices.
  • the method further comprises the step of comparing, by the multiple management calibration module, a measurable quantity of a sample retrieved from the medical devices to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
  • the method further comprises the step of computing, by the multiple management calibration module, the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module.
  • the method further comprises the step of computing, by the variation standardization module, the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
  • the method further comprises the step of carrying out, by the optimization module, spectral pretreatment to remove noise from the computed variation.
  • the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
  • the method further comprises the step of classifying, by the optimization module, the variation based on one hot encoding into its respective class indicative of a range of the variation.
  • the method further comprises the step of optimizing, by the optimization module, the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
  • the medical devices is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
  • Fig. 1 is a diagram illustrating a system for calibrating medical devices.
  • Fig. 2 is a table illustrating a computation process for binary data.
  • Fig. 3 is a table illustrating a classification process for the variation based on one hot encoding.
  • Fig. 4 is a flow chart to illustrating a method for calibrating medical devices. DETAILED DESCRIPTION OF THE INVENTION
  • These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer- readable memory produce an article of manufacture including instruction means that implement the fimction/act specified in the flowchart and/or block diagram block or blocks.
  • the computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the fimctions/acts specified in the flowchart and/or block diagram block or blocks.
  • the term “medical devices” refers to an optical spectroscopy instrument for measuring a sample of a subject, such as glucose.
  • the medical devices may employ the technology of bioimpedance spectroscopy, microwave/RF sensing, fluorescence technology, mid-infrared spectroscopy, near infrared spectroscopy, optical coherence tomography, optical polarimetry, Raman spectroscopy, reverse iontophoresis or ultrasound technology.
  • master device and “slave device” are used to indicate a master-slave configuration of the medical devices 6, which is a model of communication for medical devices 6 where one device has a unidirectional control over one or more devices. This is often used in the electronic hardware space where one device acts as the controller, whereas the other devices are the ones being controlled.
  • the system comprises a server 1 in communication with a plurality of medical devices 6, in which the server 1 having a central processing module 2 for facilitating data communication among a plurality of modules connected thereto.
  • the system is suitable for calibrating the medical devices 6 from the server 1 that is placed in a remote area.
  • a supplier may install the medical devices 6 in a hospital while the supplier may then calibrate the medical devices 6 through the server 1 from their office located away from the hospital.
  • the calibration of the medical devices 6 from the server 1 can be done wirelessly or with wired communication.
  • the medical devices 6 is a form of non-invasive medical device 6 such as an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
  • the modules comprises a multiple management calibration module 3, a variation standardization module 4 and an optimization module 5, in which the data communication of these modules are controlled by the central processing module 2.
  • the multiple management calibration module 3 is configured to differentiate between non-faulty medical devices 6 and faulty medical devices 6 from the plurality of medical devices 6 through calibration of the medical devices 6.
  • the medical devices 6 are provided with a same sample so that the medical devices 6 obtains a measurable quantity pertaining to the sample.
  • the measureable quantity and the sample refer to glucose level and blood sample of a subject respectively.
  • the medical devices 6 detects the measureable quantity through near spectroscopic field infrared technique so that the subject does not have to receive injection to draw the blood sample.
  • the multiple management calibration module 3 may also be inputted with multiple predetermined thresholds, where a suitable predetermined threshold is selected pertaining to the measurable quantity of the sample.
  • the multiple management calibration module 3 selects the predetermined threshold which is indicative of an actual reading of the subject’s glucose level.
  • the multiple management calibration module 3 compares the measurable quantity of the sample retrieved from the medical devices 6 to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
  • the comparison is conducted through identifying a peak-to-peak ratio of the measurable quantity with its predetermined threshold and the tolerance is used to determine if the peak-to-peak ratio has exceeded an allowable deviation. If the peak-to-peak ratio has exceeded the tolerance, this implies that the medical devices 6 are faulty and unable to obtain an accurate reading of the measurable quantity. If the peak-to-peak ratio is within the tolerance, this implies that the medical devices 6 are not faulty and able to obtain an accurate reading of the measurable quantity.
  • the tolerance is set at a conservative value of 0.95 of the predetermine threshold.
  • the multiple management calibration module 3 conducts calibration with poly-spectrum-analysis that uses white tiles as the predetermined threshold.
  • the comparison is conducted through comparing the measurable quantity with the white tiles and a tolerance is used to determine if the differences between the measurable quantity and the white tiles have exceeded an allowable deviation. If the differences have exceeded the tolerance, this implies that the medical devices 6 are faulty and unable to obtain an accurate reading of the measurable quantity. If the differences are within the tolerance, this implies that the medical devices 6 are not faulty and able to obtain an accurate reading of the measurable quantity.
  • the tolerance is set at a conservative value of 0.98 of the white tiles.
  • the multiple management calibration module 3 further computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module 4. If the medical devices 6 are determined as faulty medical devices 6, a binary data of 0 is to be returned to the central processing module 2, which is also deemed as fail. If the medical devices 6 are determined as non-faulty devices, a binary data of 1 is to be returned to the central processing module 2, which is also deemed as pass. In a more preferred embodiment, a combination of binary data of the two comparison method is transferred as an output to the central processing module 2 so that noisy data is excluded from the calibration process and a more informative data can be obtained.
  • the central processing module 2 if all the binary data received by the central processing module 2 is 1, the central processing module 2 then initiates the optimization module 5 as none of the medical devices 6 is faulty. However, if the a binary data of 0 is received by the central processing module 2, the central processing module 2 then initiates the variation standardization module 4 to process the binary data for identification of variation.
  • the variation standardization module 4 is configured to establish a masterslave configuration for the medical devices 6 based on the binary data.
  • the variation standardization module 4 assigns one non-faulty medical device 6 as a master device and other medical devices 6 as slave devices that are configured to receive updates from the master device. This is to enable the master device as a reference for computing variation between the master device and the slave devices.
  • the slave devices may be faulty medical devices 6 or a combination of faulty medical devices 6 and non-faulty medical devices 6.
  • the variation standardization module 4 computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices such that the variation standardization module 4 identifies the difference in measurement of the slave devices from the master device. The variation is then transferred to the optimization module 5 for further processing.
  • the optimization module 5 is configured to optimize a learning model based on the computed variation.
  • the optimization module 5 is preferred to carry out spectral pretreatment to remove noise from the computed variation.
  • the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
  • the optimization module 5 classifies the variation based on one hot encoding into its respective class indicative of a range of the variation as depicted in Fig. 3.
  • the range of the variation is high glucose level, middle glucose level and low glucose level.
  • the one hot encoding converts the classified variations into a form that could be provided to the learning model to enhance the model’s predictive ability.
  • the optimization module 5 may generate a learning model for each class and optimizes the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
  • the learning model is optimized until a best model with high correlation coefficient and lowest value of error is acquired.
  • the learning model is a specific regression model.
  • the optimization module 5 transfers the optimized learning model to the central processing module 2.
  • the variation standardization module 4 updates the master device based on the optimized learning model from the central processing module 2 such that the slave devices are standardized according to the master device and thereby ensuring measurement consistency among the medical devices 6. This eliminates the need to update each medical device 6 with a different learning model as the slave devices only have to calibrate themselves according to the updates received by the master device.
  • the variation standardization module 4 may transfer the optimized learning model to the master device such that the optimized learning model updates a measurement algorithm within the master device and the slave device then fine-tunes its respective measurement algorithm accordingly. This ensures the slave devices have a same measurement accuracy with the master device, therefore ensuring measurement consistency for all the medical devices 6.
  • the central processing module 2 may also transmit the data pertaining to the medical devices 6 to an electronic device.
  • the data may also include temperature of the subject and environmental data.
  • the electronic devices may be a personal digital assistant (PDA), a smart phone, a tablet, a laptop, a netbook, a phablet, a computer or any suitable means which is capable of receiving inputs from the server 1.
  • PDA personal digital assistant
  • a smart phone a tablet, a laptop, a netbook, a phablet, a computer or any suitable means which is capable of receiving inputs from the server 1.
  • the multiple management calibration module 3 differentiates between non-faulty medical devices 6 and faulty medical devices 6 from a plurality of medical devices 6 based on one predetermined threshold.
  • the multiple management calibration module 3 compares a measurable quantity of a sample retrieved from the medical devices 6 to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
  • the multiple management calibration module 3 computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module 4.
  • the variation standardization module 4 assigns one non-faulty medical device 6 as a master device and other medical devices 6 as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices.
  • the variation standardization module 4 computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
  • the variation standardization module 4 transfers the computed variation to the optimization module 5.
  • the optimization module 5 carries out spectral pretreatment to remove noise from the computed variation.
  • the optimization module 5 classifies the variation based on one hot encoding into its respective class indicative of a range of the variation.
  • the optimization module 5 optimizes a learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
  • the master device is updated based on the optimized learning model for standardizing the slave devices accordingly and thereby ensuring measurement consistency among the medical devices 6.

Abstract

System/method for calibrating medical devices (6), comprising server (1) communication with medical devices (6), in which the server (1) having a central processing module (2) for facilitating data communication among a connected modules comprising: a multiple management calibration module (3) for differentiating between non-faulty and faulty medical devices (6) using a predetermined threshold; a variation standardization module (4) for assigning one non-faulty medical device as a master device and other medical devices as slave devices configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master and slave devices; an optimization module (5) for optimizing a learning model based on the computed variation; wherein the variation standardization module (4) updates the master device based on the optimized learning model so the slave devices are standardized according to the master device thereby ensuring measurement consistency among medical devices (6).

Description

A SYSTEM FOR CALIBRATING MEDICAL DEVICES AND ITS METHOD
FIELD OF INVENTION
The invention relates to a system for calibrating medical devices. More particularly, the invention relates to a system for calibrating medical devices from a remote server and method thereof.
BACKGROUND OF THE INVENTION
Conventionally, diabetic patients may need to prick their fingers and test their blood glucose levels several times a day. Such a method is not beneficial to these patients as their blood circulation is slower than a healthy person and this affects the process to deliver nutrients to wounds. As a result, the injuries caused by pricking heal slowly, or may not heal at all. The slow recovering injuries can also increase the risk of infections and other complications to these patients. Therefore, a new technique called non-invasive glucose monitoring is introduced to measure of blood glucose levels for diabetic patients without drawing blood, puncturing the skin, or causing pain or trauma.
However, such a technique still faces some technical issues. One of the issues is variation across multiple optical spectroscopy instruments during measurement of a sample. The variation may be caused by various factors such as interference of external light source or defected components of the optical spectroscopy instrument. Furthermore, the existing monitoring system has a low signal-to-noise ratio that causes variation in a prediction algorithm for determining the blood glucose level.
There are a few patented technologies over the prior art relating to the system for calibrating medical devices. US6517482B1 discloses a method and apparatus for non- invasively determining glucose levels in a fluid of a subject, typically the blood glucose level. The impedance of skin tissue is measured and the measurement is used with impedance measurements previously correlated with directly determined glucose levels to determine the glucose level from the newly measured impedance. It is thus possible, to routinely non-invasively determine fluid glucose levels.
Another method and apparatus is disclosed in US9336353B2. This patent discloses a system and method for communicating glucose concentration information between devices of a continuous glucose monitoring system. The continuous glucose monitoring system can include a sensor module generates a glucose concentration measurement data and transmits the data to one or more further devices of the continuous glucose monitoring system. The further devices can include a receiver unit and one or more secondary display devices. The receiver unit can be configured to be a stand-alone device of or physically connect to a secondary display device. A user interface can also be provided that provides enhanced functionality for using the continuous glucose monitoring system.
Accordingly, it would be desirable to provide a system that ensures measurement consistency among medical devices through a master-slave configuration, in which a remote server updates a master device based on an optimized learning model such that other medical devices are standardized according to the master device. This invention provides such a system and method thereof.
SUMMARY OF INVENTION
One object of the invention is to enable calibration of faulty medical devices from a remote server with a master-slave configuration.
Another object of the invention is to ensure measurement consistency of the medical devices by standardizing a measurement of slave devices with reference to a master device.
The invention provides a system for calibrating medical devices comprising a server in communication with a plurality of medical devices, in which the server having a central processing module for facilitating data communication among a plurality of modules connected thereto, the modules comprising a multiple management calibration module for differentiating between non-faulty medical devices and faulty medical devices from the plurality of medical devices based on one predetermined threshold; a variation standardization module for assigning one non-faulty medical device as a master device and other medical devices as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; and an optimization module for optimizing a learning model based on the computed variation; wherein the variation standardization module updates the master device based on the optimized learning model such that the slave devices are standardized according to the master device and thereby ensuring measurement consistency among the medical devices.
Preferably, the multiple management calibration module compares a measurable quantity of a sample retrieved from the medical devices to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
Preferably, the multiple management calibration module further computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module.
Preferably, the variation standardization module computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
Preferably, the optimization module carries out spectral pretreatment to remove noise from the computed variation.
Preferably, the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
Preferably, the optimization module classifies the variation based on one hot encoding into its respective class indicative of a range of the variation.
Preferably, the optimization module optimizes the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
Preferably, the medical devices is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
In a further aspect of the present invention, there is provided a method for calibrating medical device, the method comprising the steps of differentiating, by a multiple management calibration module, between non-faulty medical devices and faulty medical devices from a plurality of medical devices based on one predetermined threshold; assigning, by a variation standardization module one non-faulty medical device as a master device and other medical devices as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; optimizing, by an optimization module, a learning model based on the computed variation; updating, by the variation standardization module, the master device based on the optimized learning model; and standardizing the slave devices according to the master device and thereby ensuring measurement consistency among the medical devices.
Preferably, the method further comprises the step of comparing, by the multiple management calibration module, a measurable quantity of a sample retrieved from the medical devices to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
Preferably, the method further comprises the step of computing, by the multiple management calibration module, the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module.
Preferably, the method further comprises the step of computing, by the variation standardization module, the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
Preferably, the method further comprises the step of carrying out, by the optimization module, spectral pretreatment to remove noise from the computed variation.
Preferably, the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
Preferably, the method further comprises the step of classifying, by the optimization module, the variation based on one hot encoding into its respective class indicative of a range of the variation. Preferably, the method further comprises the step of optimizing, by the optimization module, the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
Preferably, the medical devices is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
One skilled in the art will readily appreciate that the invention is well adapted to carry out the objects and obtain the ends and advantages mentioned, as well as those inherent therein. The embodiments described herein are not intended as limitations on the scope of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
For the purpose of facilitating an understanding of the invention, there is illustrated in the accompanying drawing the preferred embodiments from an inspection of which when considered in connection with the following description, the invention, its construction and operation and many of its advantages would be readily understood and appreciated.
Fig. 1 is a diagram illustrating a system for calibrating medical devices.
Fig. 2 is a table illustrating a computation process for binary data.
Fig. 3 is a table illustrating a classification process for the variation based on one hot encoding.
Fig. 4 is a flow chart to illustrating a method for calibrating medical devices. DETAILED DESCRIPTION OF THE INVENTION
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, that execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the fimctions/acts specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer- readable memory produce an article of manufacture including instruction means that implement the fimction/act specified in the flowchart and/or block diagram block or blocks.
The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the fimctions/acts specified in the flowchart and/or block diagram block or blocks.
For the purpose of description, the term “medical devices” refers to an optical spectroscopy instrument for measuring a sample of a subject, such as glucose. The medical devices may employ the technology of bioimpedance spectroscopy, microwave/RF sensing, fluorescence technology, mid-infrared spectroscopy, near infrared spectroscopy, optical coherence tomography, optical polarimetry, Raman spectroscopy, reverse iontophoresis or ultrasound technology.
The terms “master device” and “slave device” are used to indicate a master-slave configuration of the medical devices 6, which is a model of communication for medical devices 6 where one device has a unidirectional control over one or more devices. This is often used in the electronic hardware space where one device acts as the controller, whereas the other devices are the ones being controlled.
The invention will now be described in greater detail, by way of example, with reference to the drawings.
Referring to Fig. 1, there is provided a system for calibrating medical devices 6 from a remote area. In one exemplary embodiment, the system comprises a server 1 in communication with a plurality of medical devices 6, in which the server 1 having a central processing module 2 for facilitating data communication among a plurality of modules connected thereto. In one particular embodiment, the system is suitable for calibrating the medical devices 6 from the server 1 that is placed in a remote area. According to the illustrated embodiment, a supplier may install the medical devices 6 in a hospital while the supplier may then calibrate the medical devices 6 through the server 1 from their office located away from the hospital. The calibration of the medical devices 6 from the server 1 can be done wirelessly or with wired communication. By way of example, the medical devices 6 is a form of non-invasive medical device 6 such as an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
In one preferred embodiment, the modules comprises a multiple management calibration module 3, a variation standardization module 4 and an optimization module 5, in which the data communication of these modules are controlled by the central processing module 2.
Preferably, the multiple management calibration module 3 is configured to differentiate between non-faulty medical devices 6 and faulty medical devices 6 from the plurality of medical devices 6 through calibration of the medical devices 6. To carry out the calibration test, the medical devices 6 are provided with a same sample so that the medical devices 6 obtains a measurable quantity pertaining to the sample. For the purpose of description, the measureable quantity and the sample refer to glucose level and blood sample of a subject respectively. Preferably, the medical devices 6 detects the measureable quantity through near spectroscopic field infrared technique so that the subject does not have to receive injection to draw the blood sample. The multiple management calibration module 3 may also be inputted with multiple predetermined thresholds, where a suitable predetermined threshold is selected pertaining to the measurable quantity of the sample. For example, prior to the calibration test, if the measurable quantity is the glucose level of the subject, the multiple management calibration module 3 selects the predetermined threshold which is indicative of an actual reading of the subject’s glucose level. Preferably, the multiple management calibration module 3 compares the measurable quantity of the sample retrieved from the medical devices 6 to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
In one preferred embodiment, the comparison is conducted through identifying a peak-to-peak ratio of the measurable quantity with its predetermined threshold and the tolerance is used to determine if the peak-to-peak ratio has exceeded an allowable deviation. If the peak-to-peak ratio has exceeded the tolerance, this implies that the medical devices 6 are faulty and unable to obtain an accurate reading of the measurable quantity. If the peak-to-peak ratio is within the tolerance, this implies that the medical devices 6 are not faulty and able to obtain an accurate reading of the measurable quantity. Preferably, the tolerance is set at a conservative value of 0.95 of the predetermine threshold.
In another preferred embodiment, the multiple management calibration module 3 conducts calibration with poly-spectrum-analysis that uses white tiles as the predetermined threshold. In one preferred embodiment, the comparison is conducted through comparing the measurable quantity with the white tiles and a tolerance is used to determine if the differences between the measurable quantity and the white tiles have exceeded an allowable deviation. If the differences have exceeded the tolerance, this implies that the medical devices 6 are faulty and unable to obtain an accurate reading of the measurable quantity. If the differences are within the tolerance, this implies that the medical devices 6 are not faulty and able to obtain an accurate reading of the measurable quantity. Preferably, the tolerance is set at a conservative value of 0.98 of the white tiles.
Referring to Fig. 2, the multiple management calibration module 3 further computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module 4. If the medical devices 6 are determined as faulty medical devices 6, a binary data of 0 is to be returned to the central processing module 2, which is also deemed as fail. If the medical devices 6 are determined as non-faulty devices, a binary data of 1 is to be returned to the central processing module 2, which is also deemed as pass. In a more preferred embodiment, a combination of binary data of the two comparison method is transferred as an output to the central processing module 2 so that noisy data is excluded from the calibration process and a more informative data can be obtained. In one particular embodiment, if all the binary data received by the central processing module 2 is 1, the central processing module 2 then initiates the optimization module 5 as none of the medical devices 6 is faulty. However, if the a binary data of 0 is received by the central processing module 2, the central processing module 2 then initiates the variation standardization module 4 to process the binary data for identification of variation.
Preferably, the variation standardization module 4 is configured to establish a masterslave configuration for the medical devices 6 based on the binary data. In one particular embodiment, the variation standardization module 4 assigns one non-faulty medical device 6 as a master device and other medical devices 6 as slave devices that are configured to receive updates from the master device. This is to enable the master device as a reference for computing variation between the master device and the slave devices. In this particular embodiment, the slave devices may be faulty medical devices 6 or a combination of faulty medical devices 6 and non-faulty medical devices 6. Preferably, the variation standardization module 4 computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices such that the variation standardization module 4 identifies the difference in measurement of the slave devices from the master device. The variation is then transferred to the optimization module 5 for further processing.
Preferably, the optimization module 5 is configured to optimize a learning model based on the computed variation. The optimization module 5 is preferred to carry out spectral pretreatment to remove noise from the computed variation. By way of example, the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling. Upon noise removal, the optimization module 5 classifies the variation based on one hot encoding into its respective class indicative of a range of the variation as depicted in Fig. 3. For example, the range of the variation is high glucose level, middle glucose level and low glucose level. In one advantageous embodiment, the one hot encoding converts the classified variations into a form that could be provided to the learning model to enhance the model’s predictive ability. The optimization module 5 may generate a learning model for each class and optimizes the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class. The learning model is optimized until a best model with high correlation coefficient and lowest value of error is acquired. In one particular embodiment, the learning model is a specific regression model. Upon completion of the optimization process, the optimization module 5 transfers the optimized learning model to the central processing module 2.
In one advantageous embodiment, the variation standardization module 4 updates the master device based on the optimized learning model from the central processing module 2 such that the slave devices are standardized according to the master device and thereby ensuring measurement consistency among the medical devices 6. This eliminates the need to update each medical device 6 with a different learning model as the slave devices only have to calibrate themselves according to the updates received by the master device. By way of example, the variation standardization module 4 may transfer the optimized learning model to the master device such that the optimized learning model updates a measurement algorithm within the master device and the slave device then fine-tunes its respective measurement algorithm accordingly. This ensures the slave devices have a same measurement accuracy with the master device, therefore ensuring measurement consistency for all the medical devices 6.
In one preferred embodiment, the central processing module 2 may also transmit the data pertaining to the medical devices 6 to an electronic device. Advantageously, this allows doctors and caregivers to easily monitor their patient anytime and be updated if the medical device 6 is faulty or has already received updates. By way of example, the data may also include temperature of the subject and environmental data. For example, the electronic devices may be a personal digital assistant (PDA), a smart phone, a tablet, a laptop, a netbook, a phablet, a computer or any suitable means which is capable of receiving inputs from the server 1. Referring to Fig. 4, a flow chart is provided to illustrate a method for calibrating medical devices 6 by utilizing the system as described above.
At step 101, the multiple management calibration module 3 differentiates between non-faulty medical devices 6 and faulty medical devices 6 from a plurality of medical devices 6 based on one predetermined threshold. At step 102, the multiple management calibration module 3 compares a measurable quantity of a sample retrieved from the medical devices 6 to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance. At step 103, the multiple management calibration module 3 computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module 4. At step 104, the variation standardization module 4 assigns one non-faulty medical device 6 as a master device and other medical devices 6 as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices. At step 105, the variation standardization module 4 computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices. At step 106, the variation standardization module 4 transfers the computed variation to the optimization module 5. At step 107, the optimization module 5 carries out spectral pretreatment to remove noise from the computed variation. At step 108, the optimization module 5 classifies the variation based on one hot encoding into its respective class indicative of a range of the variation. At step 109, the optimization module 5 optimizes a learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class. At step 110, the master device is updated based on the optimized learning model for standardizing the slave devices accordingly and thereby ensuring measurement consistency among the medical devices 6. The present disclosure includes as contained in the appended claims, as well as that of the foregoing description. Although this invention has been described in its preferred form with a degree of particularity, it is understood that the present disclosure of the preferred form has been made only by way of example and that numerous changes in the details of construction and the combination and arrangements of parts may be resorted to without departing from the scope of the invention.

Claims

1. A system for calibrating medical devices (6) comprising: a server (1) in communication with a plurality of medical devices (6) , in which the server (1) having a central processing module (2) for facilitating data communication among a plurality of modules connected thereto, the modules comprising: a multiple management calibration module (3) for differentiating between non-faulty medical devices and faulty medical devices from the plurality of medical devices (6) based on one predetermined threshold; a variation standardization module (4) for assigning one non-faulty medical device as a master device and other medical devices as slave devices that are configured to receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; and an optimization module (5) for optimizing a learning model based on the computed variation; wherein the variation standardization module (4) updates the master device based on the optimized learning model such that the slave devices are standardized according to the master device and thereby ensuring measurement consistency among the medical devices (6).
2. The system according to claim 1, wherein the multiple management calibration module (3) compares a measurable quantity of a sample retrieved from the medical devices (6) to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
3. The system according to claim 2, wherein the multiple management calibration module (3) further computes the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module (4).
4. The system according to claim 3, wherein the variation standardization module (4) computes the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
5. The system according to claim 1, wherein the optimization module (5) carries out spectral pretreatment to remove noise from the computed variation.
6. The system according to claim 5, wherein the spectral pretreatment includes a generalized least-square regression, multiplicative scatter correction or scaling.
7. The system according to claim 6, wherein the optimization module (5) classifies the variation based on one hot encoding into its respective class indicative of a range of the variation.
8. The system according to claim 7, wherein the optimization module (5) optimizes the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
9. The system according to claim 1, wherein the medical devices (6) is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
10. A method for calibrating medical devices (6), the method comprising the steps of differentiating, by a multiple management calibration module (3), between non- faulty medical devices and faulty medical devices from a plurality of medical devices (6) based on one predetermined threshold; assigning, by a variation standardization module (4) one non-faulty medical device as a master device and other medical devices as slave devices that are configured to 17 receive updates from the master device, where the master device is used as a reference to compute variation between the master device and the slave devices; optimizing, by an optimization module (5), a learning model based on the computed variation; updating, by the variation standardization module (4), the master device based on the optimized learning model; and standardizing the slave devices according to the master device and thereby ensuring measurement consistency among the medical devices (6).
11. The method according to claim 10 further comprising the step of comparing, by the multiple management calibration module (3), a measurable quantity of a sample retrieved from the medical devices (6) to the predetermined threshold to determine if the measureable quantity has deviated away from the predetermined threshold beyond a tolerance.
12. The method according to claim 11 further comprising the step of computing, by the multiple management calibration module (3), the tolerance between the predetermined threshold with the measurable quantity into a binary data for processing by the variation standardization module (4).
13. The method according to claim 12 further comprising the step of computing, by the variation standardization module (4), the variation by comparing the measurable quantity of the master device to the measurable quantity of slave devices.
14. The method according to claim 10 further comprising the step of carrying out, by the optimization module (5), spectral pretreatment to remove noise from the computed variation.
15. The method according to claim 14, wherein the spectral pretreatment includes a 18 generalized least-square regression, multiplicative scatter correction or scaling.
16. The method according to claim 15 further comprising the step of classifying, by the optimization module (5), the variation based on one hot encoding into its respective class indicative of a range of the variation.
17. The method according to claim 16 further comprising the step of optimizing, by the optimization module (5), the learning model iteratively for each class for validation of the learning model based on a set of validation data associated to that class.
18. The method according to claim 10, wherein the medical devices (6) is in the form of an optical spectroscopy instrument for measuring a glucose level of a subject via near spectroscopic field infrared technique.
PCT/MY2020/050152 2020-08-25 2020-11-16 A system for calibrating medical devices and its method WO2022045872A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2020465148A AU2020465148A1 (en) 2020-08-25 2020-11-16 A system for calibrating medical devices and its method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MYPI2020004360 2020-08-25
MYPI2020004360 2020-08-25

Publications (1)

Publication Number Publication Date
WO2022045872A1 true WO2022045872A1 (en) 2022-03-03

Family

ID=80355450

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MY2020/050152 WO2022045872A1 (en) 2020-08-25 2020-11-16 A system for calibrating medical devices and its method

Country Status (2)

Country Link
AU (1) AU2020465148A1 (en)
WO (1) WO2022045872A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040033618A1 (en) * 1998-10-13 2004-02-19 Haass Michael J. Accommodating subject and instrument variations in spectroscopic determinations
US20050119541A1 (en) * 1999-10-08 2005-06-02 Lorenz Alexander D. Method of adapting in-vitro models to aid in noninvasive glucose determination
US20130059536A1 (en) * 2010-04-23 2013-03-07 Roche Diagnostics Operations, Inc. Method for generating a medical network
US20170150911A1 (en) * 2013-12-16 2017-06-01 Medtronic Minimed, Inc. Methods and Systems for Improving the Reliability of Orthogonally Redundant Sensors
US20200245910A1 (en) * 2019-02-01 2020-08-06 Medtronic Minimed, Inc Methods, systems, and devices for continuous glucose monitoring

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040033618A1 (en) * 1998-10-13 2004-02-19 Haass Michael J. Accommodating subject and instrument variations in spectroscopic determinations
US20050119541A1 (en) * 1999-10-08 2005-06-02 Lorenz Alexander D. Method of adapting in-vitro models to aid in noninvasive glucose determination
US20130059536A1 (en) * 2010-04-23 2013-03-07 Roche Diagnostics Operations, Inc. Method for generating a medical network
US20170150911A1 (en) * 2013-12-16 2017-06-01 Medtronic Minimed, Inc. Methods and Systems for Improving the Reliability of Orthogonally Redundant Sensors
US20200245910A1 (en) * 2019-02-01 2020-08-06 Medtronic Minimed, Inc Methods, systems, and devices for continuous glucose monitoring

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
AKMANDOR, A. O.: "Accurate, Energy-efficient, and Secure Machine Learning Models: Applications to Smart Healthcare", DISSERTATION, PRINCETON UNIVERSITY, 1 January 2020 (2020-01-01), XP055912414, Retrieved from the Internet <URL:https://dataspace.princeton.edu/bitstream/88435/dsp01v405sd30n/1/AKMANDOR_princeton_0181D_13335.pdf> *
DOGAN ÜRÜN, DESHMUKH ANIKET ANAND, MACHURA MARCIN BRONISLAW, IGEL CHRISTIAN: "Label-similarity curriculum learning", COMPUTER VISION – ECCV 2020 : 16TH EUROPEAN CONFERENCE, GLASGOW, UK, AUGUST 23–28, 2020, PROCEEDINGS, PART XXIX, vol. 11, no. 504495, July 2020 (2020-07-01), pages 174 - 190, XP047591552, Retrieved from the Internet <URL:https://arxiv.org/pdf/1911.06902.pdf> *
JING LIU ET AL.: "Accountability in smart grid and medical sensor network", DISSERTATION, UNIVERSITY OF ALABAMA, 2013, pages 1 - 171, XP055912434, Retrieved from the Internet <URL:https://ir.ua.edu/bitstream/handle/123456789/1653/file_1.pdf?sequence=1&isAllowed=y> *
SOLÓRZANO ANA, RODRÍGUEZ-PÉREZ RAQUEL, PADILLA MARTA, GRAUNKE THORSTEN, FERNANDEZ LUIS, MARCO SANTIAGO, FONOLLOSA JORDI: "Multi-unit calibration rejects inherent device variability of chemical sensor arrays", SENSORS AND ACTUATORS B: CHEMICAL, July 2018 (2018-07-01), pages 142 - 154, XP055912456, Retrieved from the Internet <URL:https://upcommons.upc.edu/bitstream/handle/2117/115415/general_calibration_rev3_f.pdf> *
YAN, K. ET AL.: "Improving the transfer ability of prediction models for electronic noses", SENSORS AND ACTUATORS B: CHEMICAL, vol. 220, pages 115 - 124, XP029263582, DOI: 10.1016/j.snb.2015.05.060 *

Also Published As

Publication number Publication date
AU2020465148A1 (en) 2023-03-23

Similar Documents

Publication Publication Date Title
US10289652B2 (en) Calibration method for the prospective calibration of measuring equipment
US11617523B2 (en) Apparatus and method for estimating biological component
US20210076995A1 (en) Method and apparatus for predicting analyte concentration
WO2017196576A4 (en) System and method for disease risk assessment and treatment
JP2008546117A (en) System and method for dynamic quantification of disease prognosis
US20200383645A1 (en) Method and device for analyzing continuously monitored physiological measurement values of a user
US20110246234A1 (en) Patient matching
EP4098194A1 (en) Method for calculating calibration sensitivity of sensor for insertion into body
Hakimi et al. Development of real-time patient health (jaundice) monitoring using wireless sensor network
CN106096231A (en) A kind of diagnostics classes medical apparatus and instruments automatic checkout system and method
AU2020465148A1 (en) A system for calibrating medical devices and its method
Albright et al. Interpreting the Knee Osteoarthritis Outcome Score Joint Replacement: minimum clinically important difference values vary over time within the same patient population
US20240016385A1 (en) Noninvasive measurement of biomarker concentration
WO2019035133A1 (en) Device, system and method for non-invasive monitoring of physiological measurements
TW201834614A (en) Non-invasive blood glucose measuring device, method, and system with identification function
US20120029942A1 (en) User-Specific Data Provision System, User-Specific Data Provision Method, Server Device, and Handheld Device
WO2020115635A1 (en) Systems, methods and computer program product for monitoring vascular perfusion in replanted tissue flaps
US20110224502A1 (en) Method and apparatus for diagnosis and treatment
Ismail Internet of medical things (IoMT) for patient healthcare monitoring system
Nurcahyana et al. Comparison of Air Pressure Control Between Discrete and PID Control Applied in the Calibration Process in Blood Pressure Meter
CN117168623B (en) Medical multi-point fusion temperature measurement system and method
Childs et al. Multi-parameter brain tissue microsensor and interface systems: calibration, reliability and user experiences of pressure and temperature sensors in the setting of neurointensive care
US20220087543A1 (en) Medical device for evaluating a pulsatile signal
Jain et al. iGLU 4.0: Intelligent Non-invasive Glucose Measurement and Its Control with Physiological Parameters
Firdaus et al. Design a Vital Sign Monitor for Body Temperature (Axilla) and Oxymetry Parameters

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20951720

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
ENP Entry into the national phase

Ref document number: 2020465148

Country of ref document: AU

Date of ref document: 20201116

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20951720

Country of ref document: EP

Kind code of ref document: A1