Patent Application
20230074922
Millions of people are being tested for SARS-CoV-2 (COVID-19) around the world and the tests themselves, though a crucial starting point in efforts to flatten the spread of the virus have become an impediment. There exist an urgent need to identify bacteria and viruses in near real-time for the purpose of clinical treatment as well as infection tracking within the world's population. Currently, FDA approved pathogen test require hours to days to process with varying reliability and are not readily useable for large populations.
The Center for Disease Control and Prevention (CDC) current approved testing methods are listed in Table 1.0. Each of these methods requires swabs of nasal, sputum or endotracheal aspirate and is primarily used for influenza testing. Other conventional methods for virus characterization include virus isolation, immunostaining, and PCR sequencing.
Many tests are being investigated and a few have been issued emergency utilization authorization (EUA) due to the urgent need for rapid testing. These tests require some type of chemical process and each test kit is disposable. This invention is reusable and do not require a chemical process.
This invention is based on the use of optical spectroscopy to identify the presence of bacteria or viruses in the respiratory airway. Optical diagnostic apparatus are very effective as compared to conventional disease detection methods. Optical techniques are noninvasive, direct, cost-effective, and easy to use with high specificity, sensitivity, and small size. Optical diseases diagnostic research and development has been useful to healthcare, environmental applications, biotechnology industry, and medical sciences.
This invention uses Raman Spectroscopy which occurs when monochromatic radiation is incident upon a sample and this light interacts with the sample in some fashion. It may be reflected, absorbed or scattered in some manner. It is the scattering of the radiation that is referred to as Raman Spectroscopy which identifies the sample's molecular structure. If the frequency (wavelength) of the scattered radiation is analyzed, not only is the incident radiation wavelength seen (Rayleigh scattering) but also, a small amount of that radiation is scattered at some different wavelength (Stokes and Anti-Stokes Raman scattering). Only 1×10−7 of the scattered light is Raman. It is the change in wavelength of the scattered photon which provides the chemical and structural information.
Each bacteria and virus has a unique Fluoresced Spectra Analysis (FSA) pattern.
Current patents that address detection and identification of bacteria, viruses, fungal, and microorganism using Raman Spectroscopy techniques include:
U.S. Pat. No. 10,746,600 This disclosure for a Raman probe has a scanning optical bench that enables a 1-cm linear traverse across a target rock or soil, both on target materials as encountered and on fresh surfaces of rocks exposed by abrasion or coring. From these spectra, it is possible to identify major, minor, and trace minerals, obtain their approximate relative proportions, and determine chemical features (e.g., Mg/Fe ratio) and rock textural features (e.g., mineral clusters, amygdular fill, and veins). It is also possible to detect and identify organic species, graphitic carbon, and water-bearing phases. Extensive performance tests have been done on a brassboard model of the MMRS using a variety of geological materials (minerals, rocks, Martian meteorites, etc.). This device does not provide an instrument for identifying microorganisms.
U.S. Pat. No. 10,714,209 This disclosure characterizes proteins, peptides, and/or peptoids via two-dimensional correlation spectroscopy and/or two-dimensional co-distribution spectroscopies. This technique does not provide an instrument for identifying microorganisms.
U.S. Pat. No. 10,712,259 This invention relates to a photoacoustic sensor system for detecting target molecules in air samples or compressed air samples. This technique does not provide an instrument for identifying microorganisms.
U.S. Pat. No. 10,716,499 This invention is for optical spectroscopic devices, apparatus, systems and methods useable for physiological monitoring from intraosseous, subosseous, epidural, subdural, intraventricular, intramuscular, sub-adipose and other subcutaneous locations. This technique does not provide an instrument for identifying microorganisms.
U.S. Pat. No. 10,718,668 This invention is for an advanced miniature optical spectrometer that is resistant to mechanical vibration. This technique does not provide an instrument for identifying microorganisms.
This invention provides a reusable mobile point-of-care testing for bacterial and viral infections present in the respiratory airways. The point-of-care testing unit identifies the presence of MRSA, H1-N1, MERS, SARS, and COVID-19 type infections present at ACE-2 receptor sites in the oral airway. The identification process is based on the unique fluoresced spectra pattern of a particular microorganism. Deep Learning Neural Networks are used to automatically identify their unique spectral patterns. The execution of the neural networks is performed at a remote site connected to the mobile point-of-care testing unit by SmartPhone or PC. The test response time is a function of the SmartPhone or PC computation time and the remote site AI processing. Typical delays are less than 30 seconds. The remote site provides massive data base storage, super computers, and information processing required for individual tracking. The point-of-care test unit is completely reusable for thousands of test without the need for maintenance or repair.
The invention is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings in which like references indicate similar elements. It should be noted that references to “an” or “one” embodiment in this disclosure are not necessarily to the same embodiment and such references mean at least one.
The following detailed description and the accompanying drawings to which it refers are intended to describe some, but not necessarily all, examples or embodiments of the invention. The described embodiments are to be considered in all respects as illustrative and not restrictive. The contents of this detailed description and the accompanying drawings do not limit the scope of the invention in any way.
One embodiment of the POCT invention is illustrated in
A second embodiment of the POCT invention is illustrated in
A third embodiment of the POCT invention is illustrated in
The basic neural network architecture used in this invention is illustrated in
The architecture of the neural network consist of hidden layers with multiple nodes 902, 903, 904 that are used to learn the weights and their associated biases 906, 907, 908. The hidden layers use a ReLu Activation Function and the output level uses a Sign Activation Function. The loss function is least squares regression whose results are used for the backpropagation process. The input level uses an Identity Activation Function.
This invention's Neural Network training data is derived from the spectral patterns of specific microorganisms in a laboratory environment. The Neural Network can be retrained for any microorganism spectral pattern of interest and therefore allows the creation of weighting and biases for multiple types of microorganisms. The particular target bacteria or virus is selectable by the clinician.
The training data set is created by collecting at least fifty samples of the subject pathogen at colony concentrations ranging from very low to very high. A spectral pattern measurement is done for each sample using the POCT UV Spectrometer. The spectral pattern data is used to train the DLNN using a backpropagation process to determine the weights and biases that best identify the subject pathogen. When using the POCT in the testing mode, the neural network output node indicates whether the subject pathogen is detected (i.e. positive or negative results). If the results is positive, an associated neural network the density level of the detected pathogen. The AI neural network process is equivalent to observing the microorganism microscopically and making a cognitive decision on the type and infection level of the microorganism. A detail description of this process is provided by A. Pandya and R. Macy[41].
The remote AI processing site block diagram is shown in
