WO2023067611A1

WO2023067611A1 - An apparatus and a method for determining characteristics of a fluid

Info

Publication number: WO2023067611A1
Application number: PCT/IN2021/051134
Authority: WO
Inventors: Partha Pratim Das MAHAPATRA; Chaitali ROY
Original assignee: Ezerx Health Tech Pvt. Ltd.
Priority date: 2021-10-19
Filing date: 2021-12-03
Publication date: 2023-04-27

Abstract

In an embodiment, the present invention discloses an apparatus for determining characteristics of a fluid. The apparatus (100) includes a heel bed (102) at one end for resting heel of a foot. It also includes a light source (104) covering the heel bed including an LED array placed at a predefined inclination to produce a concentrated light beam. It includes an optical sensor to detect light scattered and convert into electronic signal. It includes a switch (106) to activate or deactivate the light source (104). Further, in the apparatus (100), the LED array produces the concentrated light beam to irradiate peripheral venous blood, wherein a passage of the concentrated light beam is defined through the heel bed (102), anterior side of the resting heel of the foot and then heel epidermis Lastly, in the apparatus (100), the optical sensor converts the light scattered from the irradiated venous blood into electrical signals.

Description

An apparatus and a method for determining characteristics of a fluid.

Field of invention

The present invention relates to a non-invasive portable device, more specifically, a non- invasive portable apparatus and method for measuring characteristics of a fluid in neonates, such as haemoglobin, bilirubin, lactate, sodium, potassium, calcium, vitamin D, blood glucose, cholesterol, thyroxin, and oxygen saturation from the neonatal’ s body.

Background of the invention

Generally, to obtain blood samples for measuring the blood characteristics involves piercing the skin, typically the finger to draw a drop of blood and then manually transfer it onto a disposable chemical strip for testing. This is an invasive process which is painful and inconvenient especially for neonates.

Existing solutions such as Masimo’s Pronto 7, Orsense’s NBM 200, GlucoTrack etc. are available in the market for haemoglobin, oxygen saturation, pulse rate and blood glucose measurements, however, they are for individuals above 4-5 years of age. Philip’s Bilicheck and Drager Jaundice Meter JM-105 are two such non-invasive devices for neonatal screening of bilirubin. However, for various other parameters such as haemoglobin, oxygen saturation, creatinine, bilirubin, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin and blood sugar, no solution is available.

Therefore, to overcome the aforesaid problems, the present invention provides a non- invasive portable apparatus and method for determining characteristics of a fluid.

Summary of the invention

This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.

In an embodiment, the present invention discloses an apparatus for determining characteristics of a fluid. The apparatus includes a heel bed at one end for resting heel of a foot. It also includes a light source covering the heel bed including an LED array placed at a predefined inclination to produce a concentrated light beam. It includes an optical sensor to detect light scattered and convert into electronic signal. It includes a switch on the apparatus to activate or deactivate the light source. Further, in the apparatus, the LED array produces the concentrated light beam to irradiate peripheral venous blood, wherein a passage of the concentrated light beam is defined through the heel bed, anterior side of the resting heel of the foot and then heel epidermis Lastly, in the apparatus, the optical sensor converts the light scattered from the irradiated venous blood into electrical signals.

In an embodiment, the present disclosure discloses a method of determining characteristics of a fluid. The method includes emitting light by a light source, covering a heel bed for resting heel of a foot, including an LED array placed at a predefined inclination to produce a concentrated light beam. The method includes irradiating peripheral venous blood by the concentrated light beam, wherein a passage of the concentrated light beam is defined through the heel bed, anterior side of the resting heel of the foot and then heel epidermis. The method detecting and converting by an optical sensor, light scattered from the irradiated venous blood into electrical signals.

The advantages of the present invention are:

1. Non-invasive and non-contact for painless and infection free process.

2. Affordable and accessible.

3. loT enabled system.

4. Portable and battery operated.

5. Easy to operate and telemedicine compatible.

6. Compared to traditional methods, no environmental contamination is caused as there is no biomedical waste generation.

7. Report generation is instant (within 60 seconds) thus saves time.

To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

Figure 1 illustrates an apparatus for determining characteristics of a fluid, in accordance with the present disclosure;

Figures 2 and 3 illustrate working of an optical system in the apparatus, in accordance with the present disclosure; Figure 4 illustrates a digital diagram of the electrical signals obtained as an output of the apparatus, in accordance with the present disclosure;

Figure 5 illustrates a method of determining characteristics of a fluid, in accordance with the present disclosure;

Figure 6 illustrates the data processing steps for generation to output, in accordance with the present disclosure; and

Figure 7 illustrates a sample architecture of the data model, in accordance with the present disclosure.

Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have been necessarily drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having benefit of the description herein.

DETAILED DESCRIPTION OF FIGURES

For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the present disclosure and are not intended to be restrictive thereof.

Reference throughout this specification to “an aspect”, “another aspect” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

Embodiments of the present invention will be described below in detail with reference to the accompanying drawing.

Figure 1 illustrates an apparatus (100) is shown in the form of a device for determining characteristics of a fluid, in accordance with the present disclosure. In an embodiment, the apparatus (100) is in communication with an application on a mobile device. The apparatus (100) includes a heel bed (102) at one end for resting heel of a foot. It also includes a light source (104) covering the heel bed including an LED array placed at a predefined inclination to produce a concentrated light beam. It includes an optical sensor to detect light scattered and convert into electronic signal. It includes a switch (106) to activate or deactivate the light source (104). Further, in the apparatus (100), the LED array produces the concentrated light beam to irradiate peripheral venous blood, wherein a passage of the concentrated light beam is defined through the heel bed (102), anterior side of the resting heel of the foot and then heel epidermis Lastly, in the apparatus (100), the optical sensor converts the light scattered from the irradiated venous blood into electrical signals.

In an embodiment, the LED array corresponds to a white LED ring and a combination of 6 LEDs of luminous intensity of 18 med. The combination of LEDs is of different wavelengths viz. two visible white LED (440-660 nm, typical color temperature 7000 K), two Infrared (IR) LED (940 nm) and two Ultraviolet (UV) LED (390 nm). Figures 2 and 3 illustrate working of an optical sensor (200) in the apparatus, in accordance with the present disclosure. The optical sensor (200) includes a linear image sensor (202), a focusing lens (204), a grating (206) and a collimator (208) to convert the scattered light into electrical signals. The grating (206) to receive the scattered light through the collimator (208) and disperse the light into wavelengths. The focusing lens (204) having the linear image sensor (202) arranged at a focal plane to convert the light by the grating (206) and focusing into electrical signals. Further, the grating is defined by a spectral analyzer of 310 to 980 nm, 288 pixels based with 15 nm resolution and configured to distribute the reflected light from the object to whole spectra from 310 to 980 nm.

In an embodiment, the apparatus also includes a microcontroller connected to the optical sensor (200) to process the electrical signals and communicate the electrical signals digitally on the application on the mobile device.

In an embodiment, the apparatus includes a remote server which collects the digital signals from microcontroller and processes the signals through digital signal processing (DSP) technique. Further, the remote server is trained on datasets to collect the processed signal and predict a value for the fluid defined by one or more of hemoglobin, bilirubin, creatinine, blood glucose, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin and oxygen saturation.

Figure 4 illustrates a digital diagram of the electrical signals obtained as an output of the apparatus, in accordance with the present disclosure. In an embodiment, the image sensor (202) converts the light which were dispersed into wavelengths by the grating (206) and focused by the focusing lens, into electrical signals. The electrical signals are then converted in digital form in a distributed spectrum as shown in Figure 4.

Figure 5 illustrates a method (500) of determining characteristics of a fluid, in accordance with the present disclosure. At step (502), the method (500) includes emitting light by a light source, covering a heel bed for resting heel of a foot, including an LED array placed at a predefined inclination to produce a concentrated light beam. At step (504), the method (500) includes irradiating peripheral venous blood by the concentrated light beam, wherein a passage of the concentrated light beam is defined through the heel bed, anterior side of the resting heel of the foot and then heel epidermis. At step (506), the method (500) includes detecting and converting by an optical sensor, light scattered from the irradiated venous blood into electrical signals.

In an embodiment, the method of converting the scattered light into electrical signals includes receiving, by a grating, the scattered light through a collimator and dispersing the light into wavelengths. The method includes converting, by a focusing lens having a linear image sensor arranged at a focal plane, the light by the grating and focusing into electrical signals. Further, the grating is defined by a spectral analyzer of 310 to 980 nm, 288 pixels based with 15 nm resolution and configured to distribute the reflected light from the object to whole spectra from 310 to 980 nm.

In an embodiment, the method further includes connecting, by a microcontroller to the optical sensor to process the electrical signals and communicate the electrical signals digitally on the application on the mobile device.

In an embodiment, the LED array corresponds to a white LED ring and a combination of 6 LEDs of luminous intensity of 18 med. The combination of LEDs is of different wavelengths viz. two visible white LED (440-660 nm, typical color temperature 7000 K), two Infrared (IR) LED (940 nm) and two Ultraviolet (UV) LED (390 nm).

In an embodiment, the method includes collecting, by a remote server, the digital signals from microcontroller and processing the signals through digital signal processing (DSP) technique. The method further includes training the remote server on datasets to collect the processed signal and predict a value for the fluid defined by one or more of hemoglobin, bilirubin, creatinine, blood glucose, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin and oxygen saturation.

In the clinical trials of around 2,000 subjects prove that based on the concentration of various biomarkers, the pattern of output signal of the image sensors is varied according to their vitals. After completing the training of data model using output signals of 2,000 subjects versus actual blood parameter values (i.e., haemoglobin, bilirubin, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin, oxygen saturation, creatinine and random blood glucose) the biomarker changes were observed, and it was concluded with the help of evaluation algorithm to classify a signal and calculated the actual values of the blood parameters based on the historic training data sets.

Figure 6 illustrates the data processing steps for generation to output, in accordance with the present disclosure. All data was firstly validated, by checking for a few conditions. The training data was pre-processed by removing all the erroneous values, normalized between the maxima and the minima, and noise was removed by using rolling averages. The testing data was also pre-processed in a similar way. All of this was done to prevent erroneous values in data model output of the various parameters and to make sure that the outputs of the parameters fell within a valid range. This data model was then deployed in the mobile application and a cloud server for working with real-time data. The real-time data also went through the same validation and pre-processing steps just like the training and testing data to minimize errors. Only additional step in the real time data pre-processing, was the averaging of multiple data sets, which cleans the data further. This data is then processed by the cloud data model if internet connectivity is there in the smart phone otherwise the data is processed in the android application.

In addition, the data model for this device is based on a neural network architecture. The neural network is created by defining an architecture of number of layers and the number of “neurons” in each layer. A sample architecture has been shown in Figure 7, where N represents the neurons and L represents the layers. Each neuron focusses on different portions of the data or all data at once, based on its position in the network and its connectivity. A neuron is a matrix of number, and each neuron can have its own pre-processor/post-processor. The matrices in these neurons are altered based on the input and output, such that the output of the data model has high accuracy, minimal bias, minimal variance and has a high tolerance to noisy input. The process of altering the neurons, is called “Learning”. There are many learning techniques based on which a neural network can be trained. A neural network can have N-number of layers (the depth) and each layer can have N-number of neurons (the width). But a large neural network can be slower (depending upon the computational capability of the server running the neural network), so based on the server configuration, a neural network must be optimized and trained to generate accurate results in minimum time frame. A neural network can also be customized to focus more on critical data, to have high sensitivity and specificity, which is especially important in case of neonates. In this case, the data model is tuned to focus more on the critical neonates and is highly optimized to generate results within 2 seconds on a nominal configuration server. The output of the neural network are the various device parameters, such as haemoglobin, bilirubin etc.

In an embodiment, to summarize, a method of working of device of present invention includes, passing a light through the heel of the neonate and reflecting the light at 90 degrees back from the heel to the photo diode of the device. Thereafter, a spectrum reflected light is produced by the photo diode, for example, the photo diode captures more than hundreds of signals continuously with a minimum delay of 500 milliseconds. Then an average of the signals is determined by the microcontroller of the device and the signals are amplified through the ADC to obtain a spectrum of signal. Thereafter, a signal is sent to the platform by the device on the mobile device for further processing, say via Bluetooth.

The signal is compared with the reference spectrum of the database in the platform and then the compared result is fed into the data model. Accordingly, the value of the haemoglobin, bilirubin, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin, oxygen saturation, creatinine and random blood glucose of the user’s blood (especially neonates) is determined from the signal using the data model having probability factors using existing calibrated data. Lastly, these values of user’s health parameters are stored in the cloud for future references.

While specific language has been used to describe the present disclosure, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein. The drawings and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.

Claims

CLAIMS:

1. An apparatus for determining characteristics of a fluid, the apparatus comprising: a heel bed at one end of the apparatus for resting heel of a foot; a light source covering the heel bed including an LED array placed at a predefined inclination to produce a concentrated light beam and an optical sensor to detect light scattered and convert into electronic signal; and a switch on the apparatus to activate or deactivate the light source, wherein, the LED array produces the concentrated light beam to irradiate peripheral venous blood, wherein a passage of the concentrated light beam is defined through the heel bed, anterior side of the resting heel of the foot and then heel epidermis and; and the optical sensor converts the light scattered from the irradiated venous blood into electrical signals.

2. The device as claimed in claim 1, further comprising a microcontroller connected to the optical sensor to process the electrical signals and communicate the electrical signals digitally.

3. The device as claimed in claim 1, wherein the optical sensor to convert the scattered light into electrical signals, comprises: a grating to receive the scattered light through a collimator and disperse the light into wavelengths; and a focusing lens having a linear image sensor arranged at a focal plane to convert the light by the grating and focusing into electrical signals.

4. The apparatus as claimed in claim 1, wherein the LED array is a white LED ring and a combination of 6 LEDs (viz. two white LEDs, two IR LEDs and two UV LEDs) of luminous intensity of 18 med.

5. The apparatus as claimed in claim 1, wherein the grating is defined by a spectral analyzer of 310 to 980 nm, 288 pixels based with 15 nm resolution and configured to distribute the reflected light from the object to whole spectra from 310 to 980 nm.

6. The apparatus as claimed in claim 1, further comprising a remote server which collects the digital signals from microcontroller and processes the signals through digital signal processing (DSP) technique.

7. The apparatus as claimed in claim 6, wherein the remote server is trained on datasets to collect the processed signal and predict a value for the fluid defined by one

9 or more of hemoglobin, bilirubin, creatinine, blood glucose, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin and oxygen saturation.

8. A method for determining characteristics of a fluid, the method comprising: emitting light by a light source, covering a heel bed for resting heel of a foot, including an LED array placed at a predefined inclination to produce a concentrated light beam; irradiating peripheral venous blood by the concentrated light beam, wherein a passage of the concentrated light beam is defined through the heel bed, anterior side of the resting heel of the foot and then heel epidermis; and detecting and converting by an optical sensor, light scattered from the irradiated venous blood into electrical signals.

9. The method as claimed in claim 8, further comprising connecting, by a microcontroller to the optical sensor to process the electrical signals and communicate the electrical signals digitally.

10. The method as claimed in claim 8, wherein converting the scattered light into electrical signals, comprises: receiving, by a grating, the scattered light through a collimator and dispersing the light into wavelengths; and converting, by a focusing lens having a linear image sensor arranged at a focal plane, the light by the grating and focusing into electrical signals.

11. The method as claimed in claim 8, wherein the LED array is a white LED ring and a combination of 6 LEDs (viz. two white LEDs, two IR LEDs and two UV LEDs) of luminous intensity of 18 med.

12. The method as claimed in claim 8, wherein the grating is defined by a spectral analyzer of 310 to 980 nm, 288 pixels based with 15 nm resolution and configured to distribute the reflected light from the object to whole spectra from 310 to 980 nm.

13. The method as claimed in claim 8, further comprising collecting, by a remote server, the digital signals from microcontroller and processing the signals through digital signal processing (DSP) technique.

14. The method as claimed in claim 13, further comprising training the remote server on datasets to collect the processed signal and predict a value for the fluid defined by one or more of hemoglobin, bilirubin, creatinine, blood glucose, sodium, potassium, calcium, vitamin D, lactate, cholesterol, thyroxin and oxygen saturation.