Assay reader

Abstract

Various embodiments described herein allow for standardization of test reports, which in turn improves the confidence of lateral flow device testing, reduces user errors, and improves the overall accuracy of POCT result reading in any resource limited environment for medical diagnostic use. Generally, the computer-readable code includes a QR code. Furthermore, the QR code is typically associated with a device-specific key such that output data can be securely associated with a particular device and can be read only by a reference key.

Description

[0001] Related Applications

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 405,748, filed on September 12, 2022, and U.S. Provisional Patent Application No. 63 / 489,998, filed on March 13, 2023, the entire contents of both applications being incorporated herein by reference.

[0003] Statement Regarding Federally Sponsored Research or Development

[0004] This application was supported in part by the National Institutes of Health under grant number 1R44DE030842-01. Background of the Invention

[0005] Lateral flow assay test devices primarily rely on human evaluation and comparison of a colorimetric control strip with an indicator strip or indicator line. Other versions of lateral flow tests can include a color change or color appearance of a portion or all of a test strip when the fluid being tested includes a minimum concentration of the substance being tested, such as a virus, bacterium, enzyme, or chemical or biological compound.

[0006] Traditional test devices are subject to human error in use due to inappropriate sample application and also when test indicators are weak or rare. The presently described devices, systems, and methods address these and other needs in the art. Summary of the Invention

[0007] Various embodiments of the present disclosure relate to systems and methods for recording and evaluating lateral flow assay results from test strips and for digitally reporting such results in a compliant manner while using a dedicated reader device to authenticate the manner and the subject being tested.

[0008] According to presently described embodiments, there is provided a diagnostic assay reading device including: a housing configured to receive a point-of-care testing (POCT) device for testing a sample from a subject and sized for hand-held use; a receiving chamber configured to position the POCT within the housing; optionally, a sample introduction port, a light source, a detector, a processor, and a data interface / functional interface, wherein the POCT is positioned within the receiving chamber within the housing, wherein the light source and the detector are positioned in optical communication with the receiving chamber and with the test area and, if present, the control area of the POCT, wherein the processor is configured to receive and process an image acquired by the detector, wherein processing is provided to reduce noise and interference and to interpret the received captured signal against set standards to produce output data, and wherein the data interface is configured to transmit or allow transmission of the output data from the diagnostic assay reading device in the form of a graphical user interface and / or a data link.

[0009] According to embodiments that are often included, the device further includes a sample introduction port that defines a fluid path extending from an external opening to the sample application area of the POCT.

[0010] Also according to embodiments that are often included, the device further includes a sensor that is adapted to identify or authenticate that the subject using the device is the same subject as the subject providing the sample. According to related embodiments that are often included, the processor is adapted to incorporate the identification or authentication of the subject into the output data. Typically, in such embodiments, the sensor is adapted to face the exterior of the device, where the sensor includes a CMOS device and is adapted to capture or record the process of obtaining a sample from the subject and applying the sample to the POCT.

[0011] Also according to embodiments that are often included, the output data is contained in computer-readable code. Typically, the computer-readable code includes a QR code. Additionally, the QR code is typically associated with a device-specific key such that the output data can be securely associated with a specific device and can only be read by reference to the key.

[0012] Also according to embodiments that are often included, the POCT is a lateral flow test strip or a vertical flow test device. Typically, the lateral flow test strip is a nitrocellulose-based lateral flow test strip.

[0013] Also according to embodiments that are often included, a method of performing a diagnostic assay is provided, which includes: introducing the POCT into the device described herein; introducing a sample containing or suspected of containing an analyte into the sample application area of the POCT; irradiating the test area and / or control area of the POCT using an illumination source; detecting, using a detector, an image signal provided by a label that binds to or is associated with the analyte in the test area and / or control area; receiving and processing the image signal to reduce noise and background and determining a signal attribute related to the signal intensity or power; determining whether a positive signal or a negative signal associated with the analyte is present on the POCT based on the attribute; and generating output data that embodies the determination of the positive signal or negative signal.

[0014] Also according to embodiments that are often included, the device further includes a sample introduction port, and after introducing the POCT into the device, the sample is introduced into the device.

[0015] Also according to embodiments that are often included, the method further includes using the sensor of the device to automatically confirm that the subject providing the sample is the subject using the device. Typically, the sensor is adapted to face the exterior of the device, where the sensor includes a CMOS device and is adapted to capture or record the process of obtaining a sample from the subject and applying the sample to the POCT.

[0016] Also according to often-included embodiments, the method further includes providing output data included in computer-readable code. Typically, the computer-readable code includes a QR code. Additionally, the QR code is typically associated with a device-specific key such that the output data can be securely associated with a specific device and can only be read by reference to the key.

[0017] Also according to often-included embodiments, the method further includes recording one or more of the following: the time of obtaining a sample from a subject; the time of introducing the sample into the POCT; and / or the time the sample has been in contact with the POCT before illumination by a light source.

[0018] In an exemplary embodiment of the present disclosure, a diagnostic assay reader device includes: a housing configured to receive a point-of-care testing device (POCT); a receiving chamber configured to position the POCT within the housing; optionally, a sample introduction port, a light source, a detector, a processor, and a data interface / functional interface, wherein the POCT is positioned within the receiving chamber and within the housing. The light source and the detector are positioned in optical communication with the receiving chamber and with the test area of the POCT and, if present, the control area. The processor is configured to receive and process an image acquired by the detector, wherein the processing is provided to reduce noise and interference (e.g., via image stacking and signal processing using Gaussian smoothing and least squares method), and to interpret the received captured signal against set criteria related to signal position, signal intensity, relative background intensity, and background intensity artifacts to generate output data. A data interface is provided to transmit or allow transmission of the output data from the automated assay reader to, for example, a subject, a medical practitioner, an insurance company, or other person. The data interface can be in the form of a graphical user interface and / or can be a data link.

[0019] In some embodiments, the detector includes a CMOS sensor, which includes a broadband CMOS sensor and / or a wavelength-filtering CMOS sensor. In some other embodiments, the detector includes a photodiode. In some embodiments, the detector is a reflection signal capture device.

[0020] In some embodiments, a machine learning algorithm and a signal interpretation algorithm are provided and used in combination with the received image in the processor to determine whether the image data meets one or more predetermined thresholds, the one or more predetermined thresholds being used to determine whether an analyte is present or absent in the POCT or whether the test is invalid based on the nature of the POCT, the type of target analyte, and / or the imaging conditions. The determination is then recorded in the output data set; and the data interface is utilized to transmit or allow transmission of the output data from the device.

[0021] In often-included embodiments, the devices described herein are handheld devices. For example, in some embodiments, the handheld device fits within a volume of 3” high × 5” long × 2” wide. In some embodiments, the handheld device fits within a volume of 5” high × 5” long × 5” wide. In some embodiments, the handheld device fits within a volume of 2” high × 5” long × 4” wide. In some embodiments, the handheld device fits within a volume of 4” high × 4” long × 1” wide. In some embodiments, the handheld device fits within a volume of 3” high × 5” long × 1” wide. In some embodiments, the handheld device fits within a volume of 3” high × 6” long × 2” wide.

[0022] The POCT can be any of a variety of known POCT devices. The most common POCT is the commercially available type of lateral flow test strip. Exemplary POCTs contemplated herein also include lateral flow tests that use non-nitrocellulose matrix materials such as cellulose of other natural polymers or other synthetic polymer matrices, provided that they provide channels for the wicking and non-wicking flow of the analyte to the test area and / or control area and are capable of producing results that can be visually observed and detected by the detectors described herein. Exemplary labels that can be detected using the devices and systems of the present disclosure in combination with the POCTs contemplated herein generally include latex microbeads, colloidal gold particles, fluorescent labels including quantum dots and other fluorescent moieties, luminescents such as chemiluminescent labels, and other such label substances. The present devices, systems, and methods are for detecting signals generated from an analyte bound to any one or more of these latex microbeads, colloidal gold particles, fluorescent labels including quantum dots and other fluorescent moieties, and / or luminescents such as chemiluminescent labels.

[0023] In some further embodiments of the present disclosure, multiple reflected images are acquired and stacked. The images are stacked and processed to reduce noise and interference and to identify any apparitions.

[0024] In certain embodiments of the present disclosure, methods are provided for verifying and reporting lateral flow assay tests (e.g., to healthcare providers, insurance companies, etc.), which include: introducing a point-of-care testing (POCT) device having a test area and optionally a control area into an automated assay reader defined by a housing, and the automated assay reader having a receiving chamber, optionally a sample introduction port, a light source, a detector, a processor, and a data interface / functional interface, wherein the POCT is positioned in the receiving chamber within the housing. The light source and the detector are positioned in optical communication with the receiving chamber and with the test area and, if present, the control area of the POCT. Before introducing the automated lateral flow assay testing device, a sample obtained from a subject and having or suspected of containing an analyte is introduced into the POCT. When the sample is introduced into the POCT after being positioned in the automated assay reader, the sample is introduced via the sample introduction port, which defines a fluid path extending from an external opening to the sample application area of the POCT. The processor is configured to receive and process an image acquired by the detector, wherein the processing is provided to reduce noise and interference and to interpret the received captured signal against set criteria related to signal position, signal intensity, relative background intensity, and background intensity artifacts to produce output data. In the operation of an exemplary embodiment of the method, after a predetermined period of time following sample introduction, the light source illuminates the test area and the control area of the POCT, the detector captures an image of the illuminated area, and the processor processes the image to provide a determination as to whether the analyte is present in the subject, absent in the subject, or the test has failed. In practice, two or more images are typically acquired by the detector and processed by the processor. These images are typically direct images. The images are also typically fluorescence images or luminescence images. Based on the type of image to be acquired and processed (e.g., direct imaging, fluorescence imaging, or luminescence imaging), the type of light source and the wavelength of the light source as well as the detection wavelength are adjusted. A data interface is provided to transmit or permit transmission of the output data from the automated assay reader to, for example, the subject, a healthcare practitioner, an insurance company, or others. The data interface can be in the form of a graphical user interface and / or can be a data link. According to other aspects of the method, the test results are provided via an encrypted file, wherein the encrypted file is a QR code unique to the individual test performed and the QR code encodes the test results.

[0025] In certain embodiments of the present disclosure, the device may include one or more of the following features, from a single feature to a combination of two or more features to any combination including all of the following features: the illumination source irradiates a portion of the POCT within a broadband visible spectrum; the illumination source irradiates a portion of the POCT within a narrowband wavelength for fluorescence excitation; the illumination source irradiates a portion of the POCT within a broadband visible spectrum and within a narrowband wavelength for fluorescence excitation; the detector includes a broadband CMOS sensor; the detector includes a wavelength-filtered CMOS sensor; the detector includes at least one of a broadband CMOS sensor and a wavelength-filtered CMOS sensor; the processor is configured to capture at least one reflected image within the broadband visible spectrum and one image within a narrowband wavelength for fluorescence excitation; the processor is configured to receive at least two or more images within the broadband visible spectrum and at least two or more images within a narrowband wavelength for fluorescence excitation; the processor is configured to receive and combine multiple detected image signals and stack the captured image signals to facilitate noise reduction; the processor is configured to normalize the captured reflected signals; wherein the processor is configured to normalize the captured reflected signals and further process the signals using at least one of a machine learning signal processing algorithm and a signal interpretation algorithm to determine whether the captured signals meet a predetermined threshold and record the determination as output data; wherein the output data is configured to be transmitted from the device via at least one of a graphical user interface; a QR code generated for each set of output data; a WiFi, Bluetooth, or cellular connection; or a direct network connection; and the output data is locally stored at the processor.

[0026] These and other embodiments, features, and advantages will become apparent to those skilled in the art when reference is made to the following more detailed description of various exemplary embodiments of the present disclosure taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Various embodiments are disclosed in the following detailed description and the accompanying drawings. Those skilled in the art will understand that the drawings described below are for illustrative purposes only.

[0028] Figure 1 A schematic diagram of a computing device on which embodiments of the present disclosure may be implemented is illustrated.

[0029] Figure 2A An exploded view of an exemplary assay reader according to an embodiment herein is illustrated.

[0030] Figure 2B Illustrated Figure 2A a top transparent view of the assay reader in

[0031] Figure 2CIllustrates a perspective transparent view of the assay reader with its components fully assembled.

[0032] Figure 2D Illustrates Figure 2B a top transparent view of the assay reader in

[0033] Figure 3 Illustrates a schematic diagram of a networked computer environment and system 900 on which embodiments of the present disclosure may be implemented.

[0034] Figure 4 Illustrates a flowchart depicting an exemplary embodiment of the method of the present disclosure.

[0035] Figure 5 Illustrates a graphical comparison of test results including those obtained using exemplary embodiments of the present disclosure.

[0036] Figure 6 Illustrates a comparison of test results including those obtained using exemplary embodiments of the present disclosure.

[0037] Figure 7A Illustrates a comparison of test results including those obtained using exemplary embodiments of the present disclosure.

[0038] Figure 7B Illustrates another comparison of test results including those obtained using exemplary embodiments of the present disclosure.

[0039] Figure 8A Illustrates test result indications on a common POCT.

[0040] Figure 8B Illustrates test result indications on other common POCTs.

[0041] Figure 8C Illustrates test result indications on other common POCTs. Detailed Description

[0042] For clarity of disclosure, and not by way of limitation, the detailed description of the disclosure is divided into the following subsections.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. All patents, applications, published applications, and other publications referenced herein are incorporated by reference in their entirety. If the definitions set forth in this section are contrary to or inconsistent with the definitions set forth in the patents, applications, published applications, and other publications incorporated by reference herein, the definitions set forth in this section shall control.

[0044] As used herein, "a / an" means "at least one" or "one or more".

[0045] As used herein, the term "and / or" can mean "and", it can mean "or", it can mean "exclusive or", it can mean "one", it can mean "some but not all", it can mean "none", and / or it can mean "both".

[0046] As used herein, "weak positive" refers to a test result related to a POCT, where the result is only faintly visible or even possibly indistinguishable to the naked eye. In this regard, the sensitivity of the analyte concentration levels that the present device and system can detect is provided at a level lower than that detectable by the naked eye. Exemplary analyte concentrations included in the meaning of "weak positive" are described herein and are merely based on examples of the type of label and the type of POCT used in specific instances. It is contemplated herein that the analyte concentration at or below the level identified by "weak positive" in the specific instances herein can be detected by the presently described device and system.

[0047] As used herein, "lateral flow test strip" refers to an exemplary form of a point-of-care testing (POCT) device. According to the disclosed method, it is contemplated that other POCTs can be used by the devices and systems of the present disclosure. The most common POCTs are lateral flow test strips of commercially available types. Exemplary POCTs contemplated herein also include lateral flow tests using non-nitrocellulose matrix materials (such as cellulose of other natural polymers or other synthetic polymer matrices), provided that they provide channels for the absorbent and non-absorbent flow of the analyte to the test area and / or the control area and are capable of generating results that can be visually observed and detected by the detector described herein. Exemplary labels that can be detected using the devices and systems of the present disclosure in combination with the POCTs contemplated herein generally include latex microbeads, colloidal gold particles, fluorescent labels including quantum dots and other fluorescent moieties, luminophores such as chemiluminescent labels, and other such labels. The present device, system, and method are used to detect signals generated from analytes bound to any one or more of these latex microbeads, colloidal gold particles, fluorescent labels including quantum dots and other fluorescent moieties, and / or luminophores such as chemiluminescent labels.

[0048] As used herein, "broadband visible spectrum" is not intended to be limiting and generally refers to illumination that provides a signal reflected from the target label that can be primarily detected in the non-fluorescent visible spectrum and the non-luminescent visible spectrum (even if accompanied by fluorescent and / or non-luminescent visible signals).

[0049] As used herein, "narrowband wavelength" is not intended to be limiting and generally refers to illumination that provides excitation and provides a fluorescent or luminescent signal from a target label that is primarily capable of being detected in the fluorescent visible spectrum and the luminescent visible spectrum, even if accompanied by non-fluorescent and / or non-luminescent visible signals. For example, for europium dyes and quantum dots, excitation is provided in the sub-400 nm range, and the peak excitation for europium is 365 nm, both of which are below the visible spectrum in the UV spectrum. Other narrowband wavelength excitations by the illumination source are envisioned herein that correspond to all commercially known fluorescent labels used or that can be used in POCT.

[0050] As used herein, "reducing noise and interference" refers to a way of obtaining a more accurate indication of the image of the target label on a POCT. This process is typically performed using image stacking and signal processing using Gaussian smoothing and least squares, but other methods can also be considered. According to an aspect often included in currently envisioned embodiments, processing of the image is provided in a way that erases background noise and any irrelevant streaking and other artifacts to reduce noise and interference such that the true signal from the target label is provided as a distinct and distinguishable peak. Currently envisioned algorithms provide such operations that are performed in an automated manner in the device based on the type and nature of the POCT, the target analyte, and the target label type.

[0051] As used herein, "set criteria" primarily relate to signal position, signal intensity, relative background intensity, and background intensity artifacts. Based on the type of POCT, the base material of the underlying matrix material, the analyte to be detected, and the type of label used in the POCT, the set criteria are adjusted according to the positions of the test area and the control area and according to identifying and generating an ideal signal intensity, relative background intensity, and reducing background intensity artifacts, thereby generating output data.

[0052] As used herein, the term "sample" refers to anything that may contain an analyte for which an analyte determination is required. A sample can be a biological sample such as a biological fluid or a biological tissue. Examples of biological fluids include urine, blood, plasma, serum, saliva, semen, feces, sputum, cerebrospinal fluid, tears, mucus, amniotic fluid, etc. Biological tissue includes aggregates of cells, typically a particular kind of cell together with their intercellular material, which aggregates of cells form one of the structural materials in the structural materials of a human, animal, plant, bacterial, fungal, or viral structure, including connective tissue, epithelial tissue, muscle tissue, and nerve tissue. Examples of biological tissue also include organs, tumors, lymph nodes, arteries, and individual cells.

[0053] "Fluid sample" refers to a material suspected of containing an analyte of interest, which has sufficient fluidity to flow through an immunoassay device accordingly. The fluid sample can be obtained directly from a source or used after pretreatment to alter its properties. Such samples can include human samples, animal samples, or artificial samples. The sample can be prepared in any convenient medium without disturbing the assay. Typically, the sample is an aqueous solution or a biological fluid, as described in more detail below.

[0054] Fluid samples can be from any source, such as physiological fluids, including blood, serum, plasma, saliva, sputum, aqueous humor, sweat, urine, milk, ascitic fluid, mucus, synovial fluid, peritoneal fluid, percutaneous exudate, pharyngeal exudate, bronchoalveolar lavage fluid, tracheal aspirate, cerebrospinal fluid, semen, cervical mucus, vaginal or urethral secretions, amniotic fluid, etc. Here, fluid homogenates of cellular tissues such as hair, skin, and nail clippings, meat extracts, and the skins of fruits and nuts are also considered biological fluids. Pretreatment can include preparing plasma from blood, diluting viscous fluids, etc. Treatment methods can include filtration, distillation, separation, concentration, inactivation of interfering components, and addition of reagents. In addition to physiological fluids, other samples such as water, food, soil extracts, etc. can be used for performing industrial, environmental, or food production assays as well as diagnostic assays. Additionally, solid materials suspected of containing an analyte can be used as test samples once they are modified to form a liquid medium or release the analyte. The selection and pretreatment of biological samples, industrial samples, and environmental samples prior to testing are well known in the art and do not require further description.

[0055] "Analyte" refers to a compound or composition to be detected or measured, and which has at least one epitope or binding site. The analyte can be an analyte-specific binding member that occurs naturally for its presence or any substance for which an analyte-specific binding member can be prepared, such as carbohydrates and lectins, hormones and receptors, complementary nucleic acids, etc. In addition, possible analytes actually include any compound, composition, aggregate, or other substance that can be immunologically detected. That is, the analyte or a part thereof will be an antigenic or haptenic substance having at least one determinant site, or will be a member of a naturally occurring binding pair.

[0056] Analytes include, but are not limited to, toxins, organic compounds, proteins, peptides, microorganisms, bacteria, viruses, amino acids, nucleic acids, carbohydrates, hormones, steroids, vitamins, drugs (including drugs administered for therapeutic purposes and drugs administered for illegal purposes), pollutants, pesticides, and metabolites or antibodies of any of the foregoing substances. The term analyte also includes any antigenic substance, hapten, antibody, macromolecule, and combinations thereof. A non-exhaustive list of exemplary analytes is set forth in U.S. Patent No. 4,366,241, columns 19, line 7 to column 26, line 42, the disclosure of which is incorporated herein by reference. Further descriptions and lists of representative analytes are found in U.S. Patent Nos. 4,299,916; 4,275,149, and 4,806,311, all of which are incorporated herein by reference.

[0057] Embodiments of the present disclosure relate to systems and methods for reading POCT using a networked dedicated reading device or reader configured to apply clinical AI and deep learning by leveraging TinyML to drive the intelligence behind clinically relevant image analysis in medical applications. Exemplary embodiments of the present disclosure are applicable to the needs of manufacturers and healthcare providers for accurate test strip results, as recently highlighted by the COVID-19 pandemic for medical applications, including but not limited to accurate and standardized reading of lateral flow tests.

[0058] The various embodiments described herein allow for the standardization of test reports, which in turn increases the confidence in lateral flow device testing, reduces user error, and improves the overall accuracy of AI-driven lateral flow device testing procedures that utilize TinyML (or TensorFlow Lite for microcontrollers) in any resource-limited environment for medical diagnostic use. Rapid antigen lateral flow devices allow for the testing of large numbers of asymptomatic or symptomatic individuals for SARS-COV-2, as well as large-scale testing programs for various other medical indications. When compared to real-time quantitative PCR testing, lateral flow devices have different sensitivity ranges for viral loads and can be used for self-testing. When used correctly, these tests have the potential to reduce disease transmission, but self-testing poses challenges for non-expert users to interpret, especially in cases of low viral loads and significant variability observed in device interpretation.

[0059] In addition to SARS-COV-2, the presently envisioned device can be used in combination with POCT for a variety of analytes. For example, analytes including but not limited to the following can be target analytes that can be evaluated in combination with the POCT of the present disclosure: FluA, FluB, drugs of abuse, women's health, fertility, cardiovascular health, target analytes in cancer screening, etc. The present device and system are provided in an analyte-agnostic form, with the limitations and aspects of the fact that the POCT as described herein must produce a detectable result.

[0060] In various exemplary embodiments of the present disclosure, the reader system includes software applications available as a smartphone application and a web application, which use cloud-based algorithms of end-to-end deep learning to automatically read and analyze different diagnostic lateral flow tests in less than one second. The reader instructs the end user to perform the lateral flow test and interpret the test results, while also being able to quickly detect the presence of otherwise undetected low viral loads of various target viruses such as SARS-COV-2. The rapid retraining of the system allows for endless future indications, including multiplex lateral flow devices, and applications in infectious diseases, cancer, and broader medical and surgical specialties. The system then provides a digital certificate embodying the test results and the associated health status, while providing immediate government advice on instructions such as, for example, the device can provide meaningful population-level trends to allow for the formulation of health policies. The system is platform-agnostic with respect to the type of test device utilized (e.g., lateral flow devices and other test devices), as long as the device provides a visually detectable signal or a fluorescent signal, and provides fast, accurate, and secure test interpretation, thereby ensuring that the results are confidential and cannot be tampered with.

[0061] In certain embodiments, the exemplary device of the present disclosure can include a reader configured to provide a cloud-based API of end-to-end deep learning capable of reading POCT results, which reduces the risk of human error by enabling visual interpretation beyond the human visual range. The reader described herein is adapted to provide results to the user in a much faster time than prior art test strip readers, such as returning results within 1 minute, 45 seconds, 30 seconds, 20 seconds, 10 seconds, 5 seconds, 2 seconds, and / or 1 second. In addition, the reader of the present disclosure can be used globally, either alone or in combination with the use of a smartphone or other networked device, in any environment, and can be trained to read any quantitative and multiplexed assay POCT.

[0062] As contemplated herein, the present devices and systems can be used for POCT adapted to detect two or more analytes in a multiplexed assay. For example, in such embodiments, each of the two or more different analytes can be bound or associated with a label having different and / or distinguishable detection characteristics, and the device is adapted to detect the two or more analytes simultaneously (in instances where different excitation wavelengths / illumination wavelengths are required to cause the generation of a detectable signal, typically in different images). In certain related embodiments, the POCT includes two or more different fluorescent labels and / or chemiluminescent labels, and the device utilizes illumination in narrow bands necessary to generate different signals from each of the two or more different fluorescent labels and / or chemiluminescent labels, and the detector is configured to receive and process an image including the two or more different fluorescent labels and / or chemiluminescent labels.

[0063] According to the embodiments described herein, the presently described devices and systems are capable of detecting positive results of a POCT that would otherwise typically be mis-identified as negative test results when viewed with the naked eye. Thus, the present devices and systems provide sensitivity far exceeding that of the naked eye, which in some cases generally improves the utility and sensitivity of POCT testing to a level comparable to that of molecular testing. In this sense, the presently described devices can detect weak positives.

[0064] Hardware

[0065] Figure 1 A diagram of a computer system 900 is shown on which embodiments of the present disclosure can be further implemented. The computer system 900 can be a remote device, appliance, server, or other computing device described in the computing environment of FIG. 7. The computer system 900 can be in the form of a mobile device, a tablet computing device, a laptop device, a workstation, or a specialized device configured to implement the steps and functions described in the present disclosure. The computer system 900 generally includes a processor 905, a main memory 910, a non-volatile memory 915, and a network interface device 920. For simplicity of illustration, various common components (e.g., cache memory) are omitted, but these components are known to those of ordinary skill in the art. The computer system 900 is intended to illustrate a hardware device on which any of the above components and methods can be implemented. The computer system 900 can be of any suitable known or convenient type. The components of the computer system 900 can be coupled together via a bus 925 or by some other known or convenient means.

[0066] The processor 905 can be, for example, a conventional microprocessor such as an Intel Pentium microprocessor or a Motorola PowerPC microprocessor, or other commercially available microprocessors. Those skilled in the relevant art will recognize that the term "computer system readable (storage) medium" or "computer readable (storage) medium" includes any type of device accessible by the processor.

[0067] The main memory 910 is coupled to the processor 905 via a bus 925 such as a PCI bus, SCSI bus, etc. By way of example and not limitation, the main memory 910 can include random access memory (RAM), such as dynamic RAM (DRAM) and static RAM (SRAM). The main memory 910 can be local, remote, or distributed.

[0068] The bus 925 also couples the processor 905 to the non-volatile memory 915 and the drive unit 945. The non-volatile memory 915 is typically a magnetic floppy disk or hard disk, magneto-optical disk, optical disk, read-only memory (ROM) such as a CD-ROM, EPROM, or EEPROM, magnetic card or optical card, SD card, or another form of storage for large amounts of data. During the execution of software in the computer system 900, some of this data is typically written to the memory via a direct memory access process. The non-volatile memory 915 can be local, remote, or distributed. The non-volatile memory can be optional since a system can be created with all applicable data available in the memory. A typical computer system generally includes at least a processor, a memory, and a means (e.g., a bus) for coupling the memory to the processor.

[0069] Software is typically stored in the non-volatile memory 915 and / or the drive unit 945. In fact, for large programs, it may not even be possible to store the entire program in the memory. However, it should be understood that for software to run, if necessary, it is moved to a computer-readable location suitable for processing, and for illustrative purposes, this location is referred to in this disclosure as the main memory 910. Even when the software is moved to the memory for execution, the processor typically uses hardware registers to store values associated with the software and local caches. Ideally, this usage helps to accelerate execution. As used herein, when a software program is said to be "implemented in a computer-readable medium", the software program is assumed to be stored in any known or convenient location (from non-volatile storage devices to hardware registers). When at least one value associated with the program is stored in a register that can be read by the processor, the processor is considered to be "configured to execute the program".

[0070] The bus 925 also couples the processor to the network interface device 920. The interface can include one or more of a modem or a network interface. It should be understood that the modem or the network interface can be considered part of the computer system 900. The interface can include an analog modem, an ISDN modem, a cable modem, a token ring interface, a satellite transmission interface (e.g., "DirectPC"), or other interfaces for coupling the computer system to other computer systems. The interface can include one or more input and / or output devices 935. By way of example and not limitation, the I / O devices can include a keyboard, a mouse or other pointing device, a disk drive, a printer, a scanner, a speaker, a DVD / CD-ROM drive, a disk drive, and other input and / or output devices, including a display device. By way of example and not limitation, the display device 930 can include a cathode ray tube (CRT), a liquid crystal display (LCD), an LED display, a projection display (such as a head-up display), a touch screen, or some other suitable known or convenient display device. The display device 930 can be used to display text and graphics. For simplicity, it is assumed that the controllers for any components not depicted in the Figures 2A to 2C instance reside in the interface.

[0071] In operation, the computer system 900 can be controlled by an operating system software including a file management system such as a disk operating system. An example of an operating system software with an associated file management system software is the series of operating systems of Microsoft Corporation and its associated file management system. Another example of an operating system software and its associated file management system software is the Linux operating system and its associated file management system. The file management system is typically stored in the non-volatile memory 915 and / or the drive unit 945 and causes the processor to perform various actions required for operating system input and output data and storing data in the memory, including storing files on the non-volatile memory 915 and / or the drive unit 945.

[0072] In another embodiment of the present disclosure, the reader can be configured to utilize the intelligence of the TinyML model to keep the hardware requirements simple and low-cost, including low-cost microcontrollers, particularly those using the Arm Cortex-M Series architecture and microcontrollers for detecting hardware, such as low-resolution CMOS camera modules and other optical detection systems. Various embodiments of the present disclosure can use off-the-shelf hardware systems that serve as examples of microcontrollers that the reader system will utilize to deploy its TinyML model, including:

[0073] ·Arduino Nano 33BLE Sense

[0074] ·SparkFun Edge

[0075] ·STM32F746 Discovery kit

[0076] ·Adafruit EdgeBadge

[0077] ·Adafruit TensorFlow Lite for Microcontrollers Kit

[0078] ·Arducam Pico4ML

[0079] ·Adafruit Circuit Playground Bluefruit

[0080] ·Espressif ESP32-DevKitC

[0081] ·Espressif ESP-EYE

[0082] ·Wio Terminal: ATSAMD51

[0083] ·Himax WE-IPlus EVB Endpoint AI Development Board

[0084] ·Synopsys DesignWare ARC EM Software Development Platform

[0085] ·Sony Spresense

[0086] In an exemplary embodiment, the reader includes various low-cost, mass-producible hardware that is encapsulated in a custom housing (e.g., produced by injection molding), which is designed to standardize the position and illumination of the LFAs being analyzed. In some often-included embodiments, the housing that incorporates all aspects of the device and system is handheld or has a size that can be held in the hand. The ability to have TinyML-based model-driven intelligence running on low-cost, mass-producible hardware provides scalability, making hundreds of millions of reader units commercially viable and thus enabling the practical accessibility and utility of low-cost LFA diagnostics anywhere in the world, regardless of infrastructure.

[0087] Reference Figures 2A to 2C, exemplary embodiments of the present disclosure are provided, which include: a diagnostic assay reading device or reader 200; a body 210 configured to receive a POCT 215 and an additional housing; a receiving chamber 220 configured to position the POCT 215 within the housing; a light source 225 positioned adjacent to the receiving chamber 220; a detector 230; a processor 250 configured to: capture an image acquired at the detector 230; process the acquired image to reduce noise and interference; interpret the captured signal against a set standard to generate output data; and a data interface 260 for allowing transmission or transmitting the output data from the diagnostic assay reading device or reader 200.

[0088] In yet another exemplary embodiment of the diagnostic assay reading device 200 of the present disclosure, the device may include: a body 210 configured to receive a POCT 215 and an additional housing; a receiving chamber 220 configured to position the POCT 215 within the body 210; a light source 225 positioned adjacent to the receiving chamber 220, wherein the light source is configured to illuminate a portion of the POCT 215 within at least one of a broadband visible spectrum and a narrowband wavelength for fluorescence excitation; the detector 230 includes at least one of a broadband CMOS sensor 231 and a wavelength filtering CMOS sensor 232; a processor 250 configured to: capture an image acquired at the detector 230, wherein the image includes at least two or more images within a broadband visible spectrum, at least two or more images within a narrowband wavelength for fluorescence excitation, or at least one image within a broadband visible spectrum and at least one image within a narrowband wavelength for fluorescence excitation; the processor 250 further processes the acquired image to reduce noise and interference; use at least one of a machine learning algorithm and a signal interpretation algorithm to interpret the captured signal against a set standard to determine whether the captured image data meets a predetermined threshold, and record the determination into an output data set; and a data interface 260 for transmitting or allowing transmission of the output data from the diagnostic assay reading device 200, wherein the interface includes at least one of a graphical user interface, a QR code, WiFi, Bluetooth, or a cellular connection or a direct network connection.

[0089] In yet another exemplary embodiment, a method of using various embodiments of the diagnostic assay reader device 200 of the present disclosure may include the steps of: (410) inserting a POCT into the body of the diagnostic assay reader (420), such as into a receiving chamber of the device body, where the receiving chamber may be incorporated into a slot receiver, an alligator or clam shell type receiver, or a tray that is at least partially removable from the body and then insertable into the device body; (430) positioning the POCT within the receiving chamber in optical communication with an illumination source such that at least a test area and a control area of the POCT are irradiated using at least one of a visible spectrum illumination source and a fluorescent dye illumination source / excitation source; (440) activating the device after placing the test strip; (450) irradiating the test strip with one or more of a light source / illumination source including at least one of a broadband visible spectrum and a narrowband wavelength for fluorescence excitation; (460) capturing an image from the irradiated POCT using a CMOS sensor in the visible spectrum or using a wavelength-filtered CMOS sensor in at least one of narrowband fluorescence wavelengths; (470) acquiring the captured images in a data stack such that at least one image from the visible spectrum and one image from within the fluorescence band are acquired. In some embodiments, multiple reflectance images are acquired and stacked. The images are stacked and processed to reduce noise and interference and to identify any anomalies. In certain embodiments, the device includes a sample application port such that after the POCT is positioned in the chamber, a sample containing or suspected of containing an analyte can be introduced into the POCT. In other embodiments, the sample containing or suspected of containing an analyte is introduced into the POCT before the POCT is placed in the receiving chamber.

[0090] The processor then acquires the stacked images and normalizes the images using any normalization function for further processing. For example, normalization of the illumination intensity and the overall signal reflected into the sensor such that the readings can be normalized from reader to reader and from strip to strip. In some embodiments, the normalization is done via the squared power of the CMOS signal.

[0091] The normalized stacked images are then further processed to determine whether the reflected signal meets a pre-determined criterion to indicate a positive or negative LFA exposure. In one embodiment, the further processing is done by a machine learning algorithm. In yet another embodiment, the further processing is done using a signal processing algorithm. In a further embodiment, multiple algorithms are used and compared to achieve a higher confidence in the test result determination.

[0092] Whether positive or negative, the determination is saved to an output data file. The output data file may contain only the final determination of the test result or may contain one or more of the stacked images in the data stack that were processed to make the test determination.

[0093] Finally, the output data is configured to be output via a graphical user interface, a QR code, or a network connection (such as WiFi, NFC, Bluetooth, cellular, or direct network).

[0094] Figure 4 An example method of an embodiment using the reader disclosed herein is illustrated.

[0095] Software

[0096] In an example embodiment of the present disclosure, the reader 200 is driven by a TensorFlow Lite model that is designed / minimized to fit on a simple low-power and low-cost microcontroller with imaging driven by low-cost, low-resolution optics. The advantages of such example embodiments provide a model that is robust enough to provide >99.9% accuracy while facilitating the constraints of operating low-cost hardware. The enabling software of the present disclosure may include:

[0097] The platform architecture includes an administrative panel (front-end and back-end) and user applications.

[0098] · Three roles - super administrator, administrator who can access statistics, and user.

[0099] · Super administrator - user list, management, and statistics

[0100] · Authentication architecture

[0101] · Terms of use and privacy policy documents <9000230>· GDPR and HIPAA compliance

[0103] · User data, including name / surname / location

[0104] · Record database, search, and filtering

[0105] ]>· Test progress chart

[0106] · UI / UX design with healthcare focus

[0107] · Cloud-based application server

[0108] · Web application deployment

[0109] · iOS mobile application deployment (app store)

[0110] · Android mobile application deployment (play market)

[0111] In an example implementation of the present disclosure, a reader model is developed in TensorFlow / Keras and trained using images collected from a reader hardware kit. The process is iterative and based on an acquisition closed-loop pipeline where images are fed back to continuously improve the model over time on a growing user-generated dataset.

[0112] The benefits of the reader's implementation are outlined under the simple, accessible, and intelligent "SAS" pillars. Under the "SAS" pillars, the key unique advantages include: simple - accurate, automated, and flexible testing; accessible - fast, easy-to-use, and realistic testing; and intelligent - proven, secure testing with AI-based population-level insights. These are to help: test, provide digital connectivity; read, streamline lateral flow interpretation; and verify, integrate the final key step of digital personal identification.

[0113] The present disclosure is further described by the following examples. These examples are provided solely to illustrate the invention by reference to specific implementations. While these examples illustrate certain specific aspects of the present disclosure, they do not depict limitations or define the scope of the disclosed innovation.

[0114] Example 1:

[0115] The preliminary data provided herein is to demonstrate the improvement of various implementations of the present disclosure for POCT interpretation. For example, for an over-the-counter (OTC) lateral flow COVID-19 antigen test reader platform, it is superior to human visual interpretation (HVI). Since HVI is the basis for the clinical performance and FDA authorization of lateral fluid devices, this study quantified the benefits of implementing a reader to interpret test results to improve test accuracy, sensitivity, and precision, and provided a method to digitally report test results on a population scale.

[0116] As Figure 5 shown, when using an example implementation of the reader platform of the present disclosure, QuickVue TM At-Home OTC COVID-19 test strip interpretation is superior to visual human interpretation at all levels of test strip intensity (SP, MP, FP, and Neg), with the greatest improvement (+71.2%) in the weak positive (FP) category.

[0117] Overall, when compared to visual human interpretation, relative to n = 7000 DxTrack readings and n = 3580 human visual interpretations, the example reader increased the accuracy of positive test strips by +29.9% and the accuracy of negative test strips by 4.6%. <{

[0118] The reader disclosed herein improves the sensitivity of the QuickVue At-Home OTC COVID-19 test kit.

[0119] Quidel TM The current FDA EUA document of [Quidel] estimates the limit of detection, which is almost equal to the medium positive [MP] test line intensity conducted in this study. In this medium positive category of test line intensity, an example implementation of the reader provides an improvement (+5.8%) - which translates to a reduction in the false negative results that currently exist only due to misinterpretation by end-users in the population.

[0120] With the support of BARDA EZ-BAA, the reader can improve the limit of detection of the QuickVue At-Home OTC COVID-19 test kit from (1.9E4 TCID50 / ml down to 1.1E4 TCID50 / ml) to 2-fold without any changes to the design or manufacture of the test kit itself.

[0121] Modular interpretation for streamlined reporting of COVID-19 test results in a home environment

[0122] Example implementations of the reader disclosed herein demonstrate how the analog (visual interpretation) results from the LFA strip can be reliably digitized and timestamped, thus significantly improving the utility of any POC or OTC LFA test.

[0123] In addition to reducing the number of false negative results at Quidel's current limit of detection and improving the overall clinical performance of the assay, the reader also provides an objective and standardized interpretation to build confidence in the current LFA detection platform.

[0124] Experimental protocol

[0125] The Quidel QuickVue At-Home OTC COVID-19 test kit was purchased at a local pharmacy and prepared according to the provided IFU and modified so that the NR-52287 Isolate USA-WA1 / 2020, gamma-irradiated (GIV) SARS-CoV-2 sample bank was spiked at the following concentrations:

[0126]

[0127] *Using the publicly released document from the FDA, medium positive [MP] meets Quidel's current estimated LoD

[0128] A total of twenty (20) strips were prepared: 6 strongly positive, 3 medium positive, 6 weakly positive, and 5 negative. These were used to compare human visual interpretation against the reader platform.

[0129] Visual human interpretation

[0130] At the 10-minute mark, each strip run was photographed. These strips were then uploaded to a Google form and randomized. Each study participant was given 5 minutes to complete a positive or negative interpretation of all 20 strips, with the mindset that "the test result will determine whether it is safe to visit a loved one." 179 individuals participated in this study, generating 179 × 20 = 3580 different data points for analysis.

[0131] Reader interpretation

[0132] The same 20 strips used for human visual interpretation were then used by the reader for interpretation. Between 10 and 15 minutes after the start of the test, reader-based images were taken of each test strip. To increase the diversity and authenticity of the data collected, specially constructed hardware was used to randomly vary: 1) the horizontal position; 2) the vertical position; and 3) the light intensity, to represent the various reading scenarios that might be encountered in the field. Each strip was interrogated 350 times, resulting in 7000 different data points. These images were interpreted as positive or negative in real time by the reader platform. In this study, each strip was read a total of 350 different times, generating 350 × 20 = 7000 different data points for analysis. As Figure 6 A and Figure 6 B illustrate, the reader of the present disclosure shows an improvement over the visual human reading of test strips in all categories, particularly a 71.2% improvement for weakly positive indications.

[0133] Step

[0134] The reader is easy to scale and can interface with any visual reading LFA and OTC tests available on the market. The commercial goal of the reader is to achieve an overall accuracy of >99% when interpreting LFA test strips.

[0135] Protocol

[0136]

[0137] According to FDA documents, Quidel uses 50ul of "nasal matrix" in the analytical test - this is the expected volume carrying 1.9 × 10E4 TCID50 / ml.

[0138] When a swab used to collect 50 μl of “nasal matrix” with 1.9×10E4 TCID50 / ml is introduced into the provided 333 μl of Quidel Kit Buffer, the viral protein concentration dilutes the virus content to 2.8×10E3 TCID50 / ml. It is expected that 50% of the viral protein in the swab is released when introduced into Quidel Kit Buffer, and we are left with an equivalent of 1426 TCID50 / ml of GIV in the 333 μl of Quidel Kit Buffer. This will be used as the baseline viral protein load when analyzing strips prepared with different viral protein loads.

[0139] In this study, 10 μl of a dilution of the NR-52287 Isolate USA-WA1 / 2020, gamma-irradiated (GIV) sample bank was pipetted into Quidel Kit Buffer instead of loading “nasal matrix” from a swab to ensure a reproducible and controlled viral protein load was introduced into Quidel Kit Buffer each time.

[0140] Table 1

[0141]

[0142] · Prepare a 1×PBS solution of GIV at the above dilution.

[0143] · Add 10 μl to 333 μl of buffer reaction solution and vortex the tube before centrifugation. Incubate for 1 minute.

[0144] · Insert the strip for 10 minutes

[0145] · Start collecting data / validating reader performance

[0146] · Do not read for more than 15 minutes.

[0147] The reader disclosed herein utilizes TFLM and low-cost hardware, enabling accurate, rapid, and objective interpretation of currently available lateral flow assays (LFAs) in less than 10 seconds. LFAs are used as diagnostic tools because they are low-cost and simple to use, requiring no specialized skills or equipment. LFAs, recently popularized by COVID-19 rapid antigen tests, are also widely used to test for pregnancy, fertility, and women's health issues, disease tracking, STDs, food intolerances, alcohol, drugs, and a wide range of biomarkers, with billions of tests sold annually. The reader is applicable to any type of visually read lateral flow assay, demonstrating a healthcare use case for TFLM that can directly impact our daily lives.

[0148] The LFA starts with a sample (nasal swab, saliva, urine, blood, etc.) loaded at (1) a sample application area such as a sample application port. Once the sample flows to the binding zone (2), any analyte present binds to the labeled moiety. Through wicking and non-wicking flow, the labeled analyte flows across the test strip substrate to the capture line, where it is immobilized at (3). For most LFA tests, two lines indicate a positive result and one line indicates a negative result. Embodied in these two lines are the control region and the test region. The control region captures the labeled moiety, usually regardless of whether the labeled moiety is bound to the target analyte, and the test region captures the labeled moiety bound to the target analyte. This explanation is merely exemplary as one of ordinary skill in the art will readily understand the nature of a particular LFA and the specific chemical composition.

[0149] As Figure 8A shown in the side view (A) and top view (B) of a lateral flow assay (LFA) sample, where the sample (nasal swab, saliva, urine, blood, etc.) is loaded at (1) and then flows to the green zone (2), where the target is labeled with a signaling moiety. By capillary action, the sample will continue to flow until it is immobilized at (3) to form a test line. Excess material is absorbed at (4). Figure 8B and Figure 8C discloses the possible results when using such test strips, as well as the typical control and test lines on a common test strip.

[0150] When used correctly, these tests are very effective; however, self-testing poses challenges for interpretation by non-professional users. There is significant variability between devices, making it difficult to distinguish whether the test line you see is negative or weakly positive.

[0151] To address this challenge, the present disclosure presents an over-the-counter (OTC) LFA reader that improves the utility of lateral flow assays by enabling fast and objective reading using a simple, low-cost, handheld, and globally deployable device. The reader disclosed herein uses TinyML to read lateral flow assay tests, for example, to achieve two goals: 1) the ability to quickly and objectively read LFAs; and 2) streamline digital reporting.

[0152] TinyML allows software on the reader to be deployed on low-cost hardware that can be widely distributed, which is difficult for existing LFA readers that rely on high-cost / high-complexity hardware that costs hundreds to thousands of dollars per unit.

[0153] Finally, TinyML enables the reader to capture missed positive test results by eliminating human bias, increasing confidence in lateral flow device testing, reducing user error, and improving the accuracy of overall results.

[0154] Example 2:

[0155] In an example implementation of the present disclosure, the systems and methods disclosed herein maintain consistent high result accuracy in interpreting LFA strips operating in real time, including an overall accuracy of up to 99% for model performance (99% sensitivity, 99% specificity).

[0156] The ability to read and compare test data to ensure accuracy is limited by two pieces of hardware: flash memory and SRAM.

[0157] In one example implementation, a Pico4ML DevKit with 2MB of flash memory is used in the reader 200 to host the.uf2 file, and 264kb of SRAM accommodates the intermediate arrays of the model (and other items). This, together with the process and workflow, allows the arena size of the model to be quantified by first using the interpreter function. See below, where this function is called during setup:

[0158]

[0159] In this example implementation, the values from the interpreter function during the startup of the Pico4ML Dev Kit are:

[0160] DEV_Module_Init OK Arena_Size Used:93500

[0161] sd_spi_go_low_frequency:Actual frequency:122070V2-Version Card

[0162] R3 / R7:0x1aa R3 / R7:0xff8000

[0163] R3 / R7:0xc0ff8000

[0164] Card Initialized:High Capacity CardSD card initialized

[0165] SDHC / SDXC Card:hc_c_size:15237Sectors:15603712

[0166] Capacity: 7619MB

[0167] sd_spi_go_high_frequency: Actual frequency:12500000

[0168] Using this value, an appropriate TensorArenaSize can be set. The model uses 93500 bytes of SRAM. By setting the TensorArenaSize to just above this amount, 99×1024 = 101376 bytes, we are able to allocate enough memory to host the model without exceeding the hardware limits (which would also cause the Pico4ML Dev Kit to freeze).

[0169] Converting from non - quantized mode to quantized mode

[0170] In an example implementation, the reader platform interprets 96×96 images. In the original model design, some of the implementations described herein achieved >99.999% accuracy, but the intermediate layer was 96×96×32 in fp32, which requires more than 1MB of memory and is not suitable for the 264KB SRAM of the Pico4ML Dev Kit. To meet the model size requirements, the model needs to be quantized from non - quantized to quantized; using full int8 quantization. Essentially, the tensor values are associated with integers (int8) rather than treating these values as floating - point (float32).

[0171] To optimize the accuracy of the quantized data, post - training quantization (PTQ) and quantization - aware training (QAT) are used to examine the effects of two different quantization strategies.

[0172] As described below and shown in Figure 9, we compare 3 different models to see which quantization strategy is the best. For reference:

[0173] ● Model 1: 2 - layer convolutional network

[0174] ● Model 2: 3 - layer convolutional network

[0175] ● Model 3: 4 - layer convolutional network

[0176] It is found that quantization - aware training (QAT) consistently outperforms post - training quantization (PTQ) and is integrated into the workflows, processors, and related algorithms of this disclosure.

[0177] Results of optimizing the workflow

[0178] Tested on over 800 real - world test runs, the reader initially achieved an overall accuracy of 98.7%.

[0179] According to Embodiment 1, there is provided a diagnostic assay reading device comprising: a housing configured to receive a point-of-care testing (POCT) device for testing a sample from a subject and sized for hand-held use; a receiving chamber configured to position the POCT within the housing; optionally, a sample introduction port, a light source, a detector, a processor, and a data interface / functional interface, wherein the POCT is positioned within the receiving chamber and within the housing, wherein the light source and the detector are positioned in optical communication with the receiving chamber and with the test area of the POCT and, if present, a control area, wherein the processor is configured to receive and process an image acquired by the detector, wherein processing is provided to reduce noise and interference and to interpret the received captured signal against a set standard to generate output data, and wherein the data interface is configured to transmit or permit transmission of the output data from the diagnostic assay reading device in the form of a graphical user interface and / or a data link.

[0180] According to Embodiment 2, there is provided the device as described in Embodiment 1, wherein the light source irradiates a portion of the POCT within a broadband visible spectrum.

[0181] According to Embodiment 3, there is provided the device as described in Embodiment 1 or 2, wherein the light source irradiates a portion of the POCT within a narrowband wavelength for fluorescence excitation.

[0182] According to Embodiment 4, there is provided the device as described in Embodiments 1 to 3, wherein the light source irradiates a portion of the POCT within the broadband visible spectrum and within a narrowband wavelength for fluorescence excitation.

[0183] According to Embodiment 5, there is provided the device as described in Embodiments 1 to 4, wherein the detector comprises a broadband CMOS sensor.

[0184] According to Embodiment 6, there is provided the device as described in Embodiments 1 to 5, wherein the detector comprises a wavelength-filtered CMOS sensor.

[0185] According to Embodiment 7, there is provided the device as described in Embodiments 1 to 6, wherein the detector comprises at least one of a broadband CMOS sensor and a wavelength-filtered CMOS sensor.

[0186] According to Embodiment 8, there is provided the device as described in Embodiments 1 to 7, wherein the processor is configured to capture at least one image within a broadband visible spectrum and one image within a narrowband wavelength for fluorescence excitation.

[0187] According to embodiment 9, there is provided a device as described in embodiments 1 to 8, wherein the processor is configured to capture at least two or more images within a broadband visible spectrum and at least two or more images within a narrowband wavelength for fluorescence excitation.

[0188] According to embodiment 10, there is provided a device as described in embodiments 1 to 9, wherein the processor is configured to capture and combine a plurality of reflection signals and stack the captured signals to facilitate noise reduction.

[0189] According to embodiment 11, there is provided a device as described in embodiments 1 to 10, wherein the processor is configured to normalize the captured reflection signals.

[0190] According to embodiment 12, there is provided a device as described in embodiments 1 to 11, wherein the processor is configured to normalize the captured reflection signals and further process the signals using at least one of a machine learning signal processing algorithm and a signal interpretation algorithm to determine whether the captured signals meet a predetermined threshold and record the determination as output data.

[0191] According to embodiment 13, there is provided a device as described in embodiments 1 to 12, wherein the output data is transmitted or capable of being transmitted from the device via at least one of a graphical user interface; a QR code generated for each set of output data; a WiFi, Bluetooth, or cellular connection; or a direct network connection.

[0192] According to embodiment 14, there is provided a device as described in embodiments 1 to 13, wherein the output data is locally stored at the processor.

[0193] According to embodiment ********, there is provided a device as described in embodiments 1 to 14, further comprising a sample introduction port that defines a fluid path extending from an external opening to a sample application area of the POCT.

[0194] According to embodiment 16, there is provided a device as described in embodiments 1 to 15, further comprising a sensor adapted to identify or authenticate that the subject using the device is the same subject as the subject providing the sample.

[0195] According to embodiment 17, there is provided a device as described in embodiments 1 to 16, wherein the processor is adapted to incorporate the identification or authentication of the subject into the output data.

[0196] According to embodiment 18, there is provided a device as described in embodiments 1 to 17, wherein the sensor is adapted to face the exterior of the device, wherein the sensor includes a CMOS device, and is adapted to capture or record the process of obtaining the sample from the subject and applying the sample to the POCT.

[0197] According to embodiment 19, there is provided a device as described in embodiments 1 to 18, wherein the output data is contained in computer-readable code.

[0198] According to embodiment 20, there is provided a device as described in embodiments 1 to 19, wherein the computer-readable code includes a QR code.

[0199] According to embodiment 21, there is provided a device as described in embodiments 1 to 20, wherein the QR code is associated with a key specific to the device, such that the output data can be securely associated with a specific device and can only be read by referring to the key.

[0200] According to embodiment 22, there is provided a device as described in embodiments 1 to 21, wherein the POCT is a lateral flow test strip or a vertical flow test device.

[0201] According to embodiment 23, there is provided a device as described in embodiments 1 to 22, wherein the lateral flow test strip is a nitrocellulose-based lateral flow test strip.

[0202] According to embodiment 24, there is provided a method for performing a diagnostic assay, comprising: introducing a POCT into a device as described in any one of embodiments 1 to 23; introducing a sample containing or suspected of containing an analyte into the sample application area of the POCT; irradiating the test area and / or the control area of the POCT using the light source; detecting, using the detector, an image signal provided by a label that binds to or associates with the analyte in the test area and / or the control area; receiving and processing the image signal to reduce noise and background, and determining a signal attribute related to signal intensity or power; determining, based on the attribute, whether a positive signal or a negative signal associated with the analyte is present on the POCT; and generating output data embodying the determination of the positive signal or the negative signal.

[0203] According to embodiment 25, there is provided a method as described in embodiment 24, further comprising a sample introduction port, and after introducing the POCT into the device, introducing the sample into the device.

[0204] According to embodiment 26, there is provided a method as described in embodiment 24 or 25, which further comprises using a sensor of the device to automatically confirm that the subject providing the sample is the subject using the device.

[0205] According to embodiment 27, there is provided a method as described in embodiments 24 to 26, wherein the sensor is adapted to face the exterior of the device, wherein the sensor comprises a CMOS device, and is adapted to capture or record the process of obtaining the sample from the subject and applying the sample to the POCT.

[0206] According to embodiment 28, there is provided a method as described in embodiments 24 to 27, wherein the output data is contained in a computer-readable code.

[0207] According to embodiment 29, there is provided a method as described in embodiments 24 to 28, wherein the computer-readable code comprises a QR code.

[0208] According to embodiment 30, there is provided a method as described in embodiments 24 to 29, wherein the QR code is associated with a key specific to the device, such that the output data can be securely associated with a specific device and can only be read by referring to the key.

[0209] According to embodiment 31, there is provided a method as described in embodiments 24 to 30, which further comprises recording one or more of the following: the time of obtaining the sample from the subject, the time of introducing the sample into the POCT; and / or the time the sample has been in contact with the POCT before being irradiated by the illumination source.

[0210] Some portions of the detailed description may be presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, considered to be a self-consistent sequence of operations leading to a desired result. These operations are those requiring physical manipulation of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc.

[0211] However, it should be borne in mind that all these and similar terms are intended to be associated with appropriate physical quantities and are merely convenient labels applied to these quantities. Unless otherwise stated, it will be apparent from the following discussion that, throughout the specification, discussions using terms such as "processing", "computing", "calculating", "determining", "displaying", etc. refer to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (electronic) quantities within the registers and memories of the computer system into other data similarly represented as physical quantities within the memories or registers of the computer system or other such information storage, transmission, or display devices.

[0212] The algorithms and displays presented herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized devices to perform the methods of some embodiments. The structure required for various such systems will appear in the following description. Additionally, these techniques are described without reference to any particular programming language, and thus various programming languages can be used to implement the various embodiments.

[0213] In an alternative embodiment, the computer system operates as a stand-alone device or may be connected (e.g., networked) to other computer systems. In a networked deployment, the computer system can operate in a client-server network environment as either a server or a client computer system, or as a peer computer system in a peer-to-peer (or distributed) network environment.

[0214] The computer system can be a server computer (e.g., a database server); a client computer; a personal computer (PC); a tablet, phablet; a wearable device; a laptop; a set-top box (STB); a personal digital assistant (PDA); a cellular phone; an iPhone; a BlackBerry; a processor; a telephone; a web appliance; a network router, switch, or bridge; or any computer system capable of executing a set of instructions (sequential or otherwise) that specify the actions to be taken by that computer system.

[0215] Although a computer system readable medium or a computer system readable storage medium is shown as a single medium in the exemplary embodiments, the terms "computer system readable medium" and "computer system readable storage medium" should be understood to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store a set of one or more instructions. The terms "computer system readable medium" and "computer system readable storage medium" should also be understood to include any medium that is capable of storing, encoding, or carrying a set of instructions for execution by a computer system and that causes the computer system to perform any one or more of the methods of the presently disclosed technologies and innovations.

[0216] Generally speaking, the routines executed to implement the embodiments of the present disclosure can be implemented as part of an operating system or as a specific application, component, program, object, module, or sequence of instructions referred to as a "computer program". A computer program typically includes one or more instructions that are set at various memories and storage devices in a computer at different times and that, when read and executed by one or more processing units or processors in the computer, cause the computer to perform operations to execute elements including aspects of the present disclosure.

[0217] Furthermore, although the embodiments have been described in the context of fully functional computers and computer systems, those skilled in the art will understand that the various embodiments can be distributed in various forms as a program product, and the present disclosure applies equally regardless of the specific type of computer system or computer readable medium used for the actual implementation of the distribution.

[0218] Other examples of computer system readable storage media, computer system readable media, or computer readable (storage) media include, but are not limited to, recordable type media such as volatile and non-volatile storage devices, floppy disks and other removable disks, hard disk drives, optical disks (e.g., compact disc read-only memories (CD ROMS), digital versatile discs (DVDs), etc.), and SD cards, etc.

[0219] Unless the context clearly requires otherwise, throughout the specification and claims, the words "comprising," "including," and the like shall be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, in the sense of "including but not limited to." As used herein, the term "connected," "coupled," or any variation thereof means any direct or indirect connection or coupling between two or more elements; the connection or coupling between elements may be physical, logical, or a combination thereof. Additionally, when used in this application, the words "herein," "above," "below," and words of similar import shall refer to the entire application and not to any particular part of the application. Where context permits, words in the above detailed description using the singular or plural number may also include the plural or singular number, respectively.

[0220] The teachings of the disclosure provided herein can be applied to other systems and not just the systems described above. The elements and acts of the various embodiments described above can be combined to provide further embodiments.

[0221] It will be understood from the foregoing that, for purposes of illustration, specific embodiments have been described herein, but various modifications may be made without departing from the spirit and scope of the embodiments. Accordingly, the embodiments are not limited except as by the appended claims.

Claims

1. A diagnostic assay reading device, comprising: a housing configured to receive a point-of-care testing (POCT) device for testing a sample from a subject and sized for hand-held use; a receiving chamber configured to position the POCT within the housing; optionally, a sample introduction port, a light source, a detector, a processor, and a data interface / functional interface, wherein the POCT is positioned within the receiving chamber and within the housing, wherein the light source and the detector are positioned in optical communication with the receiving chamber and with the test area and, if present, the control area of the POCT, wherein the processor is configured to receive and process an image acquired by the detector, wherein the processing is provided to reduce noise and interference and to interpret the received captured signal against a set standard to generate output data, and wherein the data interface is configured to transmit or allow transmission of the output data from the diagnostic assay reading device in the form of a graphical user interface and / or a data link.

2. The device according to claim 1, wherein the light source irradiates a portion of the POCT within a broadband visible spectrum.

3. The device according to claim 1, wherein the light source irradiates a portion of the POCT within a narrowband wavelength for fluorescence excitation.

4. The device according to claim 1, wherein the light source irradiates a portion of the POCT within the broadband visible spectrum and within a narrowband wavelength for fluorescence excitation.

5. The device according to claim 1, wherein the detector comprises a broadband CMOS sensor.

6. The device according to claim 1, wherein the detector comprises a wavelength-filtered CMOS sensor.

7. The device according to claim 1, wherein the detector comprises at least one of a broadband CMOS sensor and a wavelength-filtered CMOS sensor.

8. The device according to claim 1, wherein the processor is configured to capture at least one image within a broadband visible spectrum and one image within a narrowband wavelength for fluorescence excitation.

9. The device according to claim 1, wherein the processor is configured to capture at least two or more images within a broadband visible spectrum and at least two or more images within a narrowband wavelength for fluorescence excitation.

10. The device according to claim 1, wherein the processor is configured to capture and combine multiple reflection signals and stack the captured signals to facilitate noise reduction.

11. The device according to claim 10, wherein the processor is configured to normalize the captured reflection signals.

12. The device according to claim 10, wherein the processor is configured to normalize the captured reflection signals and further process the signals using at least one of a machine learning signal processing algorithm and a signal interpretation algorithm to determine whether the captured signals meet a predetermined threshold and record the determination as output data.

13. The device according to claim 1, wherein the output data is transmitted or capable of being transmitted from the device via a graphical user interface; a QR code generated for each set of output data; a WiFi, Bluetooth, or cellular connection; or via at least one of direct network connections.

14. The device according to claim 1, wherein the output data is locally stored at the processor.

15. The device according to claim 1, further comprising a sample introduction port that defines a fluid path extending from an external opening to the sample application area of the POCT.

16. The device according to claim 1, further comprising a sensor adapted to identify or authenticate that the subject using the device is the same subject who provided the sample.

17. The device according to claim 16, wherein the processor is adapted to incorporate the identification or authentication of the subject into the output data.

18. The device according to claim 16, wherein the sensor is adapted to face the exterior of the device, wherein the sensor comprises a CMOS device and is adapted to capture or record the process of obtaining the sample from the subject and applying the sample to the POCT.

19. The device according to claim 1, wherein the output data is contained in computer-readable code.

20. The device according to claim 19, wherein the computer-readable code comprises a QR code.

21. The device according to claim 20, wherein the QR code is associated with a key specific to the device such that the output data can be securely associated with a specific device and can only be read by referring to the key.

22. The device according to claim 1, wherein the POCT is a lateral flow test strip or a vertical flow test device.

23. The device according to claim 22, wherein the lateral flow test strip is a nitrocellulose-based lateral flow test strip.

24. A method of performing a diagnostic assay, comprising: introducing a POCT into the device according to any one of claims 1 to 23; introducing a sample containing or suspected of containing an analyte into the sample application area of the POCT; irradiating a test area and / or a control area of the POCT using the illumination source; detecting, using the detector, an image signal provided by a label bound or associated with the analyte in the test area and / or the control area; receiving and processing the image signal to reduce noise and background and determining signal attributes related to signal strength or power; determining, based on the attributes, whether a positive signal or a negative signal associated with the analyte is present on the POCT; and generating output data embodying the determination of the positive signal or the negative signal.

25. The method according to claim 24, further comprising a sample introduction port, and after introducing the POCT into the device, introducing the sample into the device.

26. The method according to claim 24, further comprising using a sensor of the device to automatically confirm that the subject providing the sample is the subject using the device.

27. The method according to claim 26, wherein the sensor is adapted to face the exterior of the device, wherein the sensor comprises a CMOS device, and is adapted to capture or record the process of obtaining the sample from the subject and applying the sample to the POCT.

28. The method according to claim 24, wherein the output data is contained in computer-readable code.

29. The method according to claim 28, wherein the computer-readable code comprises a QR code.

30. The method according to claim 29, wherein the QR code is associated with a key specific to the device, such that the output data can be securely associated with a specific device and can only be read by reference to the key.

31. The method according to claim 24, further comprising recording one or more of the following: the time of obtaining the sample from the subject, the time of introducing the sample into the POCT; and / or the time the sample has been in contact with the POCT before being irradiated by the light source.

Images