Systems and methods for assessing glycated fetal hemoglobin

Abstract

In at least one embodiment, a hemoglobin measuring device may include a plurality of sensors, a display configured to present information, and a computing device in communication with the sensors and display and having a processor and a memory storing instructions executable by the processor. The instructions may include instructions to receive, from the sensors, measurements of one or more forms of glycated hemoglobin in a blood samples, determine a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin, subtract the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value, determine a glycated fetal hemoglobin value, compare the glycated fetal hemoglobin value to a reference range to obtain a comparison, determine a baseline glucose control value based on the comparison, and output the baseline glucose control value and the comparison to a display for medical evaluation.

Description

SYSTEMS AND METHODS FOR ASSESSING GLYCATED FETAL HEMOGLOBINCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. provisional application Serial No. 63 / 686,393 filed August 23, 2024, the disclosure of which is hereby incorporated in its entirety by reference herein.TECHNICAL FIELD

[0002] Various embodiments relate to diagnostic testing systems, and, in particular, to systems and methods for assessing glycated fetal hemoglobin and diagnostic methods using the same.BACKGROUND

[0003] Glycated Hemoglobin (GlyHb) is hemoglobin chemically linked to glucose in the bloodstream. GlyHb offers a comprehensive assessment of average blood glucose levels over weeks or months. There are several forms of glycated hemoglobin, including adult and fetal forms of glycated hemoglobin, as well as total glycated hemoglobin (i.e. sum total of all glycated forms). Measuring GlyHb offers insights into long-term glycemic control, providing valuable information beyond single-point blood glucose readings, which only reflect glucose levels at a specific moment in time. Currently, there are no practical or clinically available options for measurement of Glycated Fetal Hb (Fetal GlyHb) for use as a biomarker for assessing glucose control.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] FIG. 1 is a block diagram of an example system and a network environment which may be used for one or more implementations described herein.

[0005] FIG. 2 is a flowchart of an example method of determining glycated fetal hemoglobin in accordance with some implementations.

[0006] FIG. 3 is a flowchart of an example method of determining glycated fetal hemoglobin in accordance with some implementations.

[0007] FIG. 4 is a flowchart of an example method of determining glycated fetal hemoglobin in accordance with some implementations.

[0008] FIG. 5 is a flowchart of an example method of determining glycated fetal hemoglobin in accordance with some implementations.

[0009] FIG. 6 is a flowchart of an example method of using determined glycated fetal hemoglobin for diagnosing gestational diabetes and / or monitoring maternal glucose control (during pregnancy) in accordance with some implementations.

[0010] FIG. 7 is a block diagram of an example computing device which may be used for one or more implementations described herein.SUMMARY

[0011] In a first illustrative embodiment, a method for assessing glycated fetal hemoglobin comprises measuring one or more forms of glycated hemoglobin in a blood sample; determining a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin in the blood sample; subtracting the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value; determining a glycated fetal hemoglobin value in the blood sample based at least two of: a total glycated hemoglobin measurement, a glycated adult hemoglobin measurement, a glycated fetal hemoglobin measurement, a total adult hemoglobin measurement, and a total fetal hemoglobin measurement; comparing the glycated fetal hemoglobin value to a reference range to obtain a comparison; determining a baseline glucose control value based on the comparison; and outputting the baseline glucose control value and the comparison to a display for medical evaluation.

[0012] Determining the glycated fetal hemoglobin value may include multiplying the total adult hemoglobin measurement and the glycated adult hemoglobin measurement to obtain a first result, subtracting from the total glycated hemoglobin measurement, and dividing by the total fetal hemoglobin measurement.

[0013] The glycated adult hemoglobin measurement may be determined relative to the total adult hemoglobin measurement prior to outputting the glycated fetal hemoglobin measurement relative to the total fetal hemoglobin measurement based on the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement.

[0014] Determining the glycated fetal hemoglobin measurement may include dividing the total glycated hemoglobin measurement by a multiplicative result of a known constant and the total adult hemoglobin measurement added to the total fetal hemoglobin measurement.

[0015] The known constant may correct for a difference in glycation rate between the adult hemoglobin measurement and the total fetal hemoglobin measurement.

[0016] The glycated fetal hemoglobin measurement may be divided by the total fetal hemoglobin measurement.|00l7] Gestational diabetes may be identified based on a deviation of the glycated fetal hemoglobin measurement outside of a threshold range of the reference range.10018 The blood sample may include fetal hemoglobin and adult hemoglobin.

[0019] The peak area summation may be based on non-calibrated peak areas.|0020[ A patient treatment plan may be determined based on a plurality of blood samples.|0021| In a second illustrative embodiment, a hemoglobin measuring device comprises a plurality of sensors; a display configured to present information; and a computing device in communication with the sensors and display and having a processor and a memory, the memory storing instructions executable by the processor to: receive, from the sensors, measurements of one or more forms of glycated hemoglobin in a blood sample; determine a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin in the blood sample; subtract the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value; determine a glycated fetal hemoglobin value in the blood sample based at least two of: a total glycated hemoglobin measurement, a glycated adult hemoglobin measurement, a glycated fetal hemoglobin measurement, a total adult hemoglobin measurement, and a total fetal hemoglobin measurement; compare the glycated fetal hemoglobin value to a reference range toobtain a comparison; determine a baseline glucose control value based on the comparison; and output the baseline glucose control value and the comparison to a display for medical evaluation.(0022] Determining the glycated fetal hemoglobin value may include multiplying the total adult hemoglobin measurement and the glycated adult hemoglobin measurement to obtain a first result, subtracting from the total glycated hemoglobin measurement, and dividing by the total fetal hemoglobin measurement.

[0023] The glycated adult hemoglobin measurement may be determined relative to the total adult hemoglobin measurement prior to outputting the glycated fetal hemoglobin measurement relative to the total fetal hemoglobin measurement based on the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement.

[0024] Determining the glycated fetal hemoglobin measurement may include dividing the total glycated hemoglobin measurement by a multiplicative result of a known constant and the total adult hemoglobin measurement added to the total fetal hemoglobin measurement.

[0025] The known constant may correct for a difference in glycation rate between the adult hemoglobin measurement and the total fetal hemoglobin measurement.

[0026] The glycated fetal hemoglobin measurement may be divided by the total fetal hemoglobin measurement.

[0027] Gestational diabetes may be identified based on a deviation of the glycated fetal hemoglobin measurement outside of a threshold range of the reference range.10028] The blood sample may include fetal hemoglobin and adult hemoglobin.

[0029] The peak area summation may be based on non-calibrated peak areas.|0030] A patient treatment plan may be determined based on a plurality of blood samples.DETAILED DESCRIPTION

[0031] The present application claims priority to U.S. Provisional Patent Application Ser. No. 63 / 686,393, filed Aug. 23, 2024, entitled SYSTEMS AND METHODS FOR ASSESSING GLYCATED FETAL HEMOGLOBIN AND DIAGNOSTIC METHODS USINGD THE SAME.

[0032] Various embodiments described in this disclosure are provided as illustrative examples and are not intended to be limiting. Alternative configurations and implementations are possible. The accompanying figures may not be drawn to scale. Certain components may be exaggerated or reduced in size to better illustrate particular features. The structural and functional details presented herein are intended to guide those skilled in the art in implementing the described concepts in a variety of ways.

[0033] The descriptions and examples given herein are intended merely to illustrate various embodiments and are not intended to be limiting. Each of the disclosed aspects and embodiments may be considered individually or in combination with other aspects, embodiments, and variations of the disclosure. In addition, unless otherwise specified, the steps of the methods of the disclosure are not confined to any particular order of performance. Modifications of the disclosed embodiments incorporating the spirit and substance of the disclosure may occur to persons skilled in the art, and such modifications are within the scope of the disclosure.(0034] Systems and methods are disclosed herein to determine glycated fetal hemoglobin (Fetal GlyHb) levels in blood samples. Some of the implementations do not require any direct measurement of Fetal GlyHb; instead, software is used to extract and integrate data from multiple technologies to determine Fetal GlyHb via a series of computational algorithms; the technologies from which data is extracted include boronate affinity chromatography (BAC) and high- performance liquid chromatography (HPLC).

[0035] Any use of the word “or” herein is intended to be inclusive and is equivalent to the expression “and / or,” unless the context clearly dictates otherwise. As such, for example, the expression “A or B” means A, or B, or both A and B. Similarly, for example, the expression “A, B, or C” means A, or B, or C, or any combination thereof.

[0036] The assessment of glycated hemoglobin (GlyHb) is commonly performed by measuring the predominant form found in adult blood, known as hemoglobin A1C or simply “A1C ” The A1C test reflects the ratio of A1C to total hemoglobin in the blood. For example, an A1C result of 5% indicates that 5% of the total hemoglobin has glucose attached to it. Although this percentage is typically understood, the "%" symbol is often omitted in reporting (e.g., “the patient has an A1C of 5”).

[0037] The test assumes that the blood sample consists almost entirely of adult hemoglobin — typically 80% of total hemoglobin or more. Sometimes, the test is expressed as total A1C divided by adult hemoglobin (rather than total hemoglobin), and terminology may vary (“adult hemoglobin,” “total adult hemoglobin,” or “total hemoglobin”). Regardless of phrasing, the underlying assumption remains the same: that adult hemoglobin predominates in the sample. If adult Hb levels fall significantly below this expected threshold, the A1C result may be flagged as invalid. However, current testing methods do not incorporate any specific correction to account for the actual proportion of adult hemoglobin present.|0038| This can be problematic in individuals who have elevated levels of other hemoglobin types, such as fetal hemoglobin (HbF) or hemoglobin variants like hemoglobin S (seen in sickle cell disease), both of which can interfere with the accuracy of A1C measurements. Additionally, during pregnancy, the altered stability of adult red blood cells can further compromise test reliability.|0039| In earlier patent fdings (U.S. Application No. 17 / 788,719; Canada Application No. 3163798), methodology was disclosed for determining A1C levels in preterm infants, who naturally have high levels of fetal hemoglobin. This approach substitutes total protein for total hemoglobin in the A1C ratio (i.e., AlC / total protein), using total protein as a proxy marker. While this offers an approach for neonatal A1C testing, it has limitations, as total protein does not specifically reflect the concentration of adult hemoglobin.|0040| A1C testing is internationally standardized, ensuring consistent and reliable measurements across different laboratory settings. A1C Rome Controls are globally approved quality control materials used to standardize A1C measurements. These controls are certified to contain over 99% adult hemoglobin and are free from abnormal hemoglobin variants. Varioustechnologies are approved for measuring A1C, including High-Performance Liquid Chromatography, Immunoassay, Boronate Affinity Chromatography, Capillary Electrophoresis, Antibody-based Assays, and Mass Spectrometry. For each technology, empiric formulas (developed by experts skilled in the art) are used to convert either measured A1C values or measured Total Glycated Hemoglobin values to standardized A1C values.

[0041] Total Glycated Hemoglobin (Total GlyHb) represents the percentage of all glycated hemoglobin (both adult and fetal) in a blood sample relative to the total hemoglobin in the sample. Total GlyHb is measured using Boronate Affinity Chromatography (BAC). In A1C testing with BAC, A1C is not directly measured; instead, Total GlyHb is measured and then converted to a standardized A1C value using validated empiric formulas.

[0042] When blood samples containing fetal hemoglobin (HbF) are analyzed using boronate affinity chromatography (BAC), the measurement of Total Glycated Hemoglobin (Total GlyHb) is technically accurate. However, converting this measurement to an A1C value can lead to biased results due to the presence of HbF. This bias occurs because HbF glycates at a slower rate than adult hemoglobin (HbA); thus, the A1C conversion formula is only accurate for samples with minimal HbF.

[0043] Other A1 C testing methods can also be affected by the presence of HbF. For example, some chromatography techniques may produce overlapping peaks for HbF and A1C, leading to falsely elevated A1C values. Unfortunately, this bias cannot be corrected by simply subtracting a calibrated HbF measurement from the Total Hemoglobin denominator.

[0044] Due to these limitations, standard A1C testing is generally not recommended when elevated HbF is present. In particular, A1C testing is not used clinically in neonates, as newborns have very high levels of HbF until they are 6-12 months old.[0045| High Performance Liquid Chromatography (HPLC) is a technology utilized for hemoglobin analysis. It works by separating different hemoglobin variants based on their retention times as they pass through a chromatographic column. As the separated hemoglobin variants elute from the column, they pass through a detector that measures their absorbance at a specific wavelength. The detector's signals are processed to produce a chromatogram, which displays peakscorresponding to different hemoglobin variants. Each peak appears at a specific time, known as the retention time (RT), which is characteristic of a particular hemoglobin variant. The height and area under each peak are proportional to the concentration of the corresponding hemoglobin variant in the sample. HbF appears as its own peak, as do other types of hemoglobin, including HbAO, HbA2, and abnormal hemoglobin variants such as HbC.

[0046] In its high-resolution mode, modified Hb products (such as acetylated Hb, glycated Hb, etc.) appear as separate peaks from the primary peak. For example, glycated adult hemoglobin (A1C) is a separate peak than the primary adult hemoglobin peak (AO). Notably, HPLC chromatographs are generally divided into Hb-specific regions such as F-region (HbF region), A- region (HbA region), and A2 region (Hb A2 region). There are additional regions for other hemoglobin variants.

[0047] As mentioned above, Fetal GlyHb is the percentage of glycated fetal hemoglobin relative to the total fetal hemoglobin (Total HbF) in a blood sample. For example, a Fetal GlyHb of 5% indicates that 5% of Total HbF is glycated. Throughout this document, Fetal GlyHb will be presented as a numerical value without a percentage sign (e.g., "Fetal GlyHb = 5").10048] Systems and methods have been invented to evaluate glycated fetal hemoglobin (Fetal GlyHb) levels in blood samples, enabling the assessment of glucose control in patients with fetal hemoglobin (HbF) present in their blood. All Fetal GlyHb determinations represent Fetal GlyHb in relation to Total HbF in the sample. This disclosure will aid in diagnosing chronic dysglycemia, defined here as abnormal glucose control — either hyperglycemia or hypoglycemia — persisting for a week or longer. It will help determine a patient's overall glucose status, categorizing it as normal, hyperglycemic, or hypoglycemic. When used for a fetus or newborn, the methodologies disclosed herein will reflect the glucose status occurring in utero, ex utero, or a combination of both. Additionally, it will help determine disease severity, with a threshold level for dysglycemia potentially established at a specific percentage above or below the mean.|0049| Some implementations of the disclosure involve software that integrates data from multiple technologies to determine Fetal GlyHb via a series of computational algorithms; the technologies (from which data is extracted) include boronate affinity chromatography (BAC) and high-performance liquid chromatography (HPLC). Additionally, this document describes anetwork environment designed to support a range of functionalities related to various embodiments, including the determination of Fetal GlyHb. This environment consists of server systems and client devices interconnected via a network. The server system includes a server device, a database, and specialized applications, such as the Fetal GlyHb determination application.

[0050] The methodologies and systems for Fetal GlyHb testing, described in this patent application, are particularly relevant for infants, who are known to have high levels of fetal hemoglobin (HbF) in their blood for six months or more after birth. Specific populations of infants, such as preterm infants and those born to diabetic mothers, are at especially high risk for dysglycemia and stand to benefit significantly from the methodologies disclosed herein.

[0051] In addition to infants, patients with HbF-associated conditions will also greatly benefit; these conditions include, but are not limited to, Hereditary Persistence of Fetal Hemoglobin, Thalassemias, Neonatal Diabetes, Sickle Cell Disease, Myeloproliferative Disorders (i.e. polycythemia and myelofibrosis), Leukemias (i.e. chronic myeloid leukemia and acute myeloid leukemia), Diamond-Blackfan Anemia, Aplastic Anemia, Congenital Dyserthropoietic Anemia, Paroxysmal Nocturnal Hemoglobinuria and Stress Erythropoiesis.

[0052] Some implementations of this disclosure are useful for assessing glucose control during pregnancy since HbF levels increase in maternal blood and other methodologies for assessing glycated hemoglobin, such as A1C testing, are known to be inaccurate during pregnancy.

[0053] Some implementations of this disclosure are especially tailored for individuals (who are suitable for Fetal GlyHb testing) who have received blood transfusions. These specific implementations address the challenge of assessing glycated hemoglobin levels in blood that contains a mixture of recipient and donor blood, effectively overcoming the complicating factors involved.

[0054] The methods described herein rely upon analysis of a blood sample. As used herein, ‘blood sample’ means a sample of whole blood, or fraction there from (such as serum or plasma), collected from a person (or animal). The blood sample may be provided in any suitable form, including liquid or dried blood. The blood sample may be freshly drawn or stored. For example,in obtaining dried blood spots, the collected blood is spotted onto fdter paper, dried, and then stored for processing later.7The content of the dried blood spot could be eluted into a liquid fluid to perform the analyses. The blood could be drawn from the patient using any suitable technique, such as venipuncture or skin puncture for capillary blood (e.g. finger stick).

[0055] The methods described herein can be applied to sequential samples (repeat testing at different times) from the same individual to diagnose and then monitor the condition. For example, results from an initial blood sample, or one of the person's blood samples, can be used to diagnose abnormal glucose control, establish a baseline glucose level, or create a treatment plan. Subsequent samples, taken at different times, can then be compared to monitor changes in the person’s glucose status, which, in turn, can be used to alter treatment. Beside human blood, the methods can also be applied to animal blood (assuming the presence of fetal hemoglobin in the blood).I: Example System & Network Environment for Fetal GlyHb Determination

[0056] FIG. 1 is a block diagram of an example network system which is designed to support a range of functionalities, including the determination of Fetal GlyHb. This system 100 consists of server systems 102 and client devices 120, 122, 124, 126 interconnected via a network. The server system 102 includes a server device 104, a database 106, and specialized applications such as the glycated fetal hemoglobin determination application 108. this network environment 100 provides a comprehensive and versatile platform that not only supports the determination of Fetal GlyHb through advanced data processing and algorithmic analysis but also facilitates a wide array of user interactions and services, all connected through a robust and flexible network infrastructure.

[0057] Client devices 120, 122, 124, 126, which encompass a variety of electronic devices such as desktop computers, smartphones, wearable devices, and more, communicate with the server system 102 and with each other through the network 130. The network 130 supports various communication protocols, including Internet, LAN, wireless networks, and peer-to-peer communication.

[0058] Fetal GlyHb is determined by extracting relevant information from one or more technologies within this network environment. These technologies process data, utilizing algorithms that integrate inputs from server systems, client devices, and potentially other externaldata sources. The extracted data is stored and processed within server systems and databases, and the algorithmic computations involved are facilitated by the system's computational resources.(0059] User interactions within this network environment are facilitated by a user interface, which can be displayed on client devices 120, 122, 124, 126 or via server-side software. This interface allows users to access and manage data, including the results of Fetal GlyHb determination, and to communicate and share content. The network 130 supports a range of user activities, from messaging and social networking to content sharing and live interactions, all of which are integrated into the system's overall functionality.

[0060] The server system 102 can communicate with a network 130, for example. Server system 102 can include a server device 104, a database 106 or other data store or data storage device, and glycated fetal hemoglobin determination application 108. Network system 100 also can include one or more client devices, e.g., client devices 120, 122, 124, and 126, which may communicate with each other and / or with server system 102 via network 130. Network 130 can be any type of communication network, including one or more of the Internet, local area networks (LAN), wireless networks, switch or hub connections, etc. In some implementations, network 130 can include peer-to-peer communication 132 between devices, e.g., using peer-to-peer wireless protocols.(0061 ] For ease of illustration, FIG. 1 shows one block for server system 102, server device 104, and database 106, and shows four blocks for client devices 120, 122, 124, and 126. Some blocks (e.g., 102, 104, and 106) may represent multiple systems, server devices, and network databases, and the blocks can be provided in different configurations than shown. For example, server system 102 can represent multiple server systems that can communicate with other server systems via the network 130. In some examples, database 106 and / or other storage devices can be provided in server system block(s) that are separate from server device 104 and can communicate with server device 104 and other server systems via network 130. Also, there may be any number of client devices. Each client device 120, 122, 124, 126 can be any type of electronic device, e.g., desktop computer, laptop computer, portable or mobile device, camera, cell phone, smart phone, tablet computer, television, TV set top box or entertainment device, wearable devices (e.g., display glasses or goggles, head-mounted display (HMD), wristwatch, headset, armband, jewelry, etc.),virtual reality (VR) and / or augmented reality (AR) enabled devices, personal digital assistant (PDA), media player, game device, etc. Some client devices may also have a local database similar to database 106 or other storage. In other implementations, network environment 100 may not have all of the components shown and / or may have other elements including other types of elements instead of, or in addition to, those described herein.

[0062] In various implementations, end-users Ul, U2, U3, and U4 may communicate with server system 102 and / or each other using respective client devices 120, 122, 124, and 126. In some examples, users Ul, U2, U3, and U4 may interact with each other via applications running on respective client devices and / or server system 102, and / or via a network service, e.g., an image sharing service, a messaging service, a social network service or other type of network service, implemented on server system 102. For example, respective client devices 120, 122, 124, and 126 may communicate data to and from one or more server systems (e g., server system 102). In some implementations, the server system 102 may provide appropriate data to the client devices such that each client device can receive communicated content or shared content uploaded to the server system 102 and / or network service. In some examples, the users can interact via audio or video conferencing, audio, video, or text chat, or other communication modes or applications. In some examples, the network service can include any system allowing users to perform a variety of communications, form links and associations, upload and post shared content such as images, image compositions (e g., albums that include one or more images, image collages, videos, etc.), audio data, and other types of content, receive various forms of data, and / or perform socially related functions. For example, the network service can allow a user to send messages to particular or multiple other users, form social links in the form of associations to other users within the network service, group other users in user lists, friends lists, or other user groups, post or send content including text, images, image compositions, audio sequences or recordings, or other types of content for access by designated sets of users of the network service, participate in live video, audio, and / or text videoconferences or chat with other users of the service, etc. In some implementations, a “user” can include one or more programs or virtual entities, as well as persons that interface with the system or network.

[0063] A user interface can enable display of images, image compositions, data, and other content as well as communications, privacy settings, notifications, and other data on client devices120, 122, 124, and 126 (or alternatively on server system 102). Such an interface can be displayed using software on the client device, software on the server device, and / or a combination of client software and server software executing on server device 104, e.g., application software or client software in communication with server system 102. The user interface can be displayed by a display device of a client device or server device, e.g., a display screen, projector, etc. In some implementations, application programs running on a server system can communicate with a client device to receive user input at the client device and to output data such as visual data, audio data, etc. at the client device.

[0009] In some implementations, server system 102 and / or one or more client devices 120-126 can provide glycated fetal hemoglobin determination functions as described herein.II: Parameters For Fetal GlyHb Determination

[0064] Depending on the specific implementation described herein, the measurement or assessment of one or more of the following parameters are required to determine Fetal GlyHb: Total Glycated Hemoglobin (Total GlyHb), Adult Glycated Hemoglobin (Adult GlyHb), Total Fetal Hemoglobin (Total HbF), Total Adult Hemoglobin (Total HbA). Each parameter will be defined and described in turn below.

[0065] Total Glycated Hemoglobin (Total GlyHb)

[0066] Total GlyHb is the percentage of all glycated hemoglobin (both fetal and adult) relative to the total hemoglobin in a blood sample. It is measured using boronate affinity chromatography (BAC). The Trinity Biotech Premier 9210 is an example of a technology that measures Total GlyHb via BAC. Although Total GlyHb represents a percentage, throughout this document, Total GlyHb will be presented (and treated) as a numerical value.

[0067] The Total GlyHb measurement reflects combined contributions of Fetal Glycated Hemoglobin (Fetal GlyHb) and Adult Glycated Hemoglobin (Adult GlyHb) in the blood sample. In other words, the contribution of Fetal GlyHb plus the contribution of Adult GlyHb equals the Total GlyHb. These contributions are based on their respective proportions in the sample; the percentage of Fetal GlyHb plus the percentage of Adult GlyHb should together equal 100%.

[0068] To determine each type of glycated hemoglobin's contribution to Total GlyHb, multiply the Fetal GlyHb or Adult GlyHb by the percentage of its respective hemoglobin type (fetal or adult hemoglobin) in the sample. For example, if in a blood sample, Fetal GlyHb = 4; Adult GlyHb =8 and that the Total fetal hemoglobin in the sample is 75% and the Total adult hemoglobin is 25%. The contributions are calculated as follows: contribution of Fetal GlyHb to Total GlyHb: 4x0.75=3 and contribution of Adult GlyHb to Total GlyHb: 8x0.25=2. Therefore, the Total GlyHb in the example blood sample (composed of 75% HbF and 25% HbA) is 5, calculated as the sum of 3 and 2.

[0069] In some implementations, the Total GlyHb measurement is converted into a standard A1C value. Subsequent to that, the standard A1C value, rather than the original Total GlyHb measurement, is used in an algorithm to determine Fetal GlyHb levels as will be described in further detail in section II.

[0070] It is important to note that the empirical formula for converting Total GlyHb to standard A1C is validated for adult blood, which does not contain fetal hemoglobin (HbF). However, the blood samples may contain HbF, which affects the standard A1C value derived from Total GlyHb; in other words, the standard A1C value derived from Total GlyHb is biased, meaning that it is influenced by the fetal hemoglobin in the blood sample. The biased A1C result is used because it includes implicit information about both Adult GlyHb and Fetal GlyHb levels. The methodologies presented in this application leverage this embedded information to accurately determine Fetal GlyHb levels.

[0071] Glycated Adult Hemoglobin (Adult GlyHb)

[0072] Adult GlyHb is the percentage of adult hemoglobin in the blood that is glycated relative to the total adult hemoglobin present. Although it represents a percentage, throughout this document, Adult GlyHb will be presented as a numerical value.

[0073] In the embodiments described herein, accurate measurement of adult GlyHb followed by its conversion into a standard Ale value that is unaffected by the presence of HbF in the sample may be utilized. This differs from the approach for Total GlyHb, where biased Ale values wereintentionally sought. In other words, unbiased Ale values should be used to represent Adult GlyHb in the computational algorithms described herein.(0074] Achieving unbiased Ale results necessitates careful selection of the measurement technology. While HPLC is appropriate, only specific high-resolution HPLC instruments can ensure the necessary separation between HbF and Ale peaks on the chromatograph, thereby avoiding bias. Standard HPLC technologies often result in peak overlap, leading to biased outcomes and are therefore unsuitable.

[0075] High-resolution HPLC technologies, such as the Trinity Premier Resolution, are suitable because they effectively minimize overlap between HbF and Ale peaks, ensuring that the Ale value accurately reflects the adult GlyHb component without HbF interference.10076] Total Fetal Hemoglobin (Total HbF)(0077] Total HbF is the total percentage of all modified and unmodified fetal hemoglobin relative to the total hemoglobin in the blood. Total HbF is an important parameter used in the computational algorithms for assessing Fetal GlyHb. The value of Total HbF is treated as a percentage in all computations, and “Total HbF” is used interchangeably with “%Total HbF.”

[0078] In an example embodiment for determining Total HbF, Total HbF can be accurately determined as follows: a blood sample can be processed via high resolution HPLC. The noncalibrated area percentages for all HbF-associated peaks (i.e., all peaks specifically related to unmodified HbF and modified HbF products) on the chromatograph may be summed. That is, Total HbF can be determined by adding together the non-calibrated values for all HbF associated peaks, which include the primary HbF peak, acetylated HbF peak, glycated HbF peak, etc., degradation peaks specifically associated with HbF may be optionally included among the modified HbF peaks.|0079| The area of each chromatograph peak is directly proportional to the concentration of the corresponding hemoglobin variant in the blood. For example, if the area under the acetylated HbF peak is 10%, then acetylated HbF constitutes 10% of the total hemoglobin in the blood. This is because the approximate total sum of all peak areas — representing total hemoglobin-is 100%; however, the total sum is 100% only when raw data (non-calibrated values) are used. If calibratedpeak values are used, the sum of all peaks may exceed or fall short of 100%, potentially affecting the accuracy of Total HbF results.(0080] The embodiment described above requires identification of all HbF -associated peaks. To achieve this, chromatographs of neonatal blood, such as cord blood, processed using high- resolution HPLC technologies, may be examined. Since nearly all cord blood contains an adult hemoglobin (HbA) component, any peaks on the neonatal blood chromatogram that also appear on the chromatogram of pure adult blood (e.g., A1C Rome Control blood, which is 100% adult blood) may be excluded from the set of specific HbF-associated peaks. In other words, HbF- associated peaks are those that appear on neonatal blood chromatographs but not on pure adult blood chromatographs.(00811 With approximate retention times (RTs) in accordance with Premier Resolution, a complete set of HbF-associated peaks are Fetal region (F-region) peaks located at F 0.29, F 0.31, F 0.32, F 0.46 [Acetylated HbF peak], F 0.52, F 0.57, F 0 .73, F 1.0 [primary HbF peak]. Notably, F-region peaks at F 0.31, F 0.52, F 0.57, F 0 .73 are being disclosed as modified HbF products for the first time. If other HPLC instruments are used, HbF-associated products should remain the same, but their RTs may differ.

[0082] In another example, for determining Total HbF, the same protocol as described above may be utilized. The protocol may be altered such that Calibrated HbF (e.g. HbF that has been measured and adjusted for precision) can be used as an estimate of Total HbF. However, as already explained, the Calibrated HbF may not always accurately represent Total HbF, as calibrated HbF measurements may not include all modified HbF forms (such as acetylated HbF, glycated HbF, etc.).

[0083] In yet another embodiment, for determining Total HbF, the same protocol as described above may be utilized. The protocol may be altered such that calibrated HPLC peak values (when available) are summed together as an estimate of Total HbF (though may not be as accurate as non-calibrated peak values as discussed above).

[0084] In yet another embodiment, for determining Total HbF, the same protocol as described above may be utilized. The protocol may be altered such that only the Calibrated HbF peak value and the Fetal GlyHb peak value are summed together as an estimate of Total HbF.

[0085] Besides HPLC, other methodologies to measure Total HbF include Flow Cytometry, Alkali Denaturation Test (Betke-Kleihauer Test), Capillary Electrophoresis, Isoelectric Focusing (IEF), Enzyme-Linked Immunosorbent Assay (ELISA) and MALDLTOF Mass Spectrometry.

[0086] Total Adult Hemoglobin (Total HbA)

[0087] Total HbA is the total percentage of all unmodified and modified HbA relative to the total hemoglobin in the blood. In certain implementations disclosed herein, Total HbA is an important parameter used in the computational algorithms for assessing Fetal GlyHb. Throughout this document, Total HbA is treated as a percentage in all computational algorithms, and “Total HbA” is used interchangeably with “%Total HbA.”

[0088] Various methods may be used for determining Total HbA. For example, after determining Total HbF as mentioned above, software can be configured to determine Total HbA by subtracting Total HbF from 100% (i.e., 100% is equal to the sum of all fetal and adult peaks). The algorithm can be expressed as Total HbA= 100 - Total HbF. There are variations on determination of Total HbA and Total HbF. For example, a blood sample can be analyzed by HPLC and then Total HbA can be determined by summing together all HbA-associated peaks (via a similar method as that described for determining Total HbF). Total HbF can then be determined from Total HbA (i.e. 100-Total HbA=Total HbF). When other hemoglobin variants are present (such as Hb S), they need to be included in the sum total of peak areas.Ill: A First Methodology for Fetal GlyHb Determination

[0089] In an embodiment, a first methodology indirectly assesses Fetal GlyHb through a subtractive process. In brief, the Total Glycated Hemoglobin (Total GlyHb) in a blood sample is first measured, and then the adult glycated component is subtracted, leaving the remainder as Fetal GlyHb. For this subtraction to be accurate, both Total GlyHb and Adult GlyHb must be expressed using the same denominator, achieved by converting both Total GlyHb and Adult GlyHb into their standard A1C values.

[0090] The rationale for using a biased Al C value for Total GlyHb, but not for Adult GlyHb, is as follows: The biased A1C value for Total GlyHb contains information about both fetal and adult glycated hemoglobin, while the unbiased Al C for Adult GlyHb reflects only the adult glycated component. By using a biased A1C value for Total GlyHb and an unbiased A1C value for Adult GlyHb, the subtraction process accurately isolates the Fetal GlyHb component. (See Part II above for more information on biased and unbiased A1C values.)

[0091] FIG. 2 illustrates an example flowchart illustrating the first methodology. Processing begins at 202 when a whole blood sample is collected from a person (over 6 months of age) or from a newborn (less than 6 months old) who has received one or more blood transfusions. Processing continues at 204

[0092] At 204, the first methodology continues with the step of dividing the blood sample into two parts. Prepare the first part of the blood sample for processing via boronate affinity chromatography (BAC), in accordance with manufacturer’s instructions. (Retain the other part of the sample for HPLC processing during later steps). Processing continues at 206.

[0093] At 206, the first methodology continues with the step of measuring the Total GlyHb in the part of the blood sample prepared at step 204, with BAC technology in accordance with manufacturer’s instructions for the BAC processing. The Trinity Biotech Premier 9210 A1C Analyzer is an example of BAC technology that can be utilized. Processing continues at 208

[0094] At 208, the first methodology continues with the step of converting the Total GlyHb measurement to its standard value with an empiric formula as would be determined by someone skilled in the art. Processing continues at 210.

[0095] At 210, the first methodology continues with the step of preparing the second part (i.e. the remainder) of the original sample for high performance liquid chromatography (HPLC) in accordance with the HPLC manufacturer’s instructions. Processing continues at 212.[0096| At 212, the first methodology continues with the step of processing the prepared blood sample (from step 210) with a high resolution HPLC instrument in accordance with the manufacturer’s instructions and obtain the HPLC chromatograph. This chromatograph will be used to determine Total HbF (at step 214), Total HbA (at step 216) and Adult GlyHb (at step 218).The Trinity Premier Resolution is an example of high resolution HPLC technology that can be utilized. Processing continues at 214.(0097] At 214, the first methodology continues with the step of determining Total HbF (the total of all modified and unmodified fetal hemoglobin in the blood sample). Software, for example, can be configured to determine Total HbF by summing together the NON-calibrated values of all HbF- associated peaks on the HPLC chromatograph. Processing continues at 216.

[0098] At 216, the first methodology continues with the step of determining Total HbA (the total of all modified and unmodified adult hemoglobin in the blood sample): Software, for example, software can be configured to determine %Total HbA value by subtracting Total HbF from 100% (i.e., 100% is equal to the sum of all fetal and adult peaks). Processing continues at 218.|0099| Variations on determination of Total HbA and Total HbF may be utilized. For example, Total HbA can be determined by summing together all HbA-associated peaks. Total HbF can then be determined from Total HbA (i.e. 100-Total HbA=Total HbF). When other hemoglobin variants are present (i.e., Hb S), they need to be included in the sum total of peak areas.(0100] At 218, the first methodology continues with the step of determining Adult GlyHb measurement, for example, by configuring software to divide the A1C peak value by Total HbA (AlC / Total HbA= Adult GlyHb measurement). Processing continues at 220. It should be noted that the A1C peak should be divided by Total HbA (rather than Total Hemoglobin), as A1C should be assessed in the blood sample relative to Total HbA in the same sample.

[0101] At 220, the first methodology continues with the step of converting the Adult GlyHb HPLC measurement to its standard A1C value with an empiric formula (determined by someone skilled in the art). Processing Continues at Step 222.(0102] At 222, the first methodology continues with the step of determining Fetal GlyHb. As example, software can be configured to determine Fetal GlyHb as follows: multiply %Total HbA by Adult GlyHb (using standard A1C value for Adult GlyHbO), subtract the above product from Total GlyHb (using standard A1C value for Total GlyHb), divide the above difference by %Total HbF; the quotient represents Fetal GlyHb.

[0103] The algorithm can be visually summarized as follows; use the standard A1 C value for Total GlyHb (from step 208), the standard A1C value for Adult GlyHb (from step 220), the %Total HbF value from Step 214 and the %Total HbA from Step 216. The algorithm is represented by Equation 1 :Equation 1:Fetal GlyHb = (Total GlyHb - (%Total HbA* Adult GlyHb)) / (% Total HbF)

[0104] In an example, the standard A1C value of Total GlyHb in the blood sample may be 7 and the standard A1C value of Adult GlyHb may be 8. Total HbF may be 25% and Total HbA may be 75%. (Note that Total GlyHb and Adult GlyHb are treated as numerical values while Total HbF and Total HbA are treated as percentages.). In such an example, Fetal GlyHb = (7- (.75 *8)) / (0.25) = 1 / (0.25) =4

[0105] At 224, the first methodology continues with the step of determining an interpretation of Fetal GlyHb value (such as high, normal, low) relevant to clinical care, dependent upon comparison to reference ranges, appropriate for the targeted disease (such as neonatal diabetes) or population (such as the population of preterm infants). Treatment may subsequently be provided, based on Fetal GlyHb value, as needed.

[0106] All the prior steps can be repeated with different blood samples from the same patient taken at different time points to monitor the patient’s glucose control over time and to adjust treatment as needed.

[0107] Because Total GlyHb and Adult GlyHb are in their standard A1C format, Fetal GlyHb is also in an A1C format. However, because the percentage of Total HbF in the blood is accounted for in the computational process, the A1C denominator of Fetal GlyHb reflects total hemoglobin as if it were composed entirely of fetal hemoglobin.

[0108] There are variations to how Fetal GlyHb could be derived with this methodology. For example, Total GlyHb and Adult GlyHb could be expressed in formats other than standard A1C formats. These types of variations should be considered within the realm and spirit of the invented entity.

[0109] The first methodology may be utilized for Fetal GlyHb Determination for newborns, at any time after birth, who have received blood transfusion. The blood of a transfused newborn comprises a blend of their own hemoglobin (which is primarily fetal hemoglobin) together with hemoglobin sourced externally from blood donors. Typically, newborns undergoing transfusions receive adult blood. In such instances, this methodology removes the adult component of glycated hemoglobin, which represents the transfused blood. Thus, this methodology permits the system to precisely evaluate the glucose control in a transfused infant, leveraging the fetal hemoglobin inherent to the infant’s physiology.101101 The first methodology may be utilized for Fetal GlyHb Determination for a person with an HbF-associated condition who has received blood transfusions. Certain HbF-associated disorder such as prematurity, sickle cell disease, beta-thalassemia, and hereditary persistence of fetal hemoglobin, often require transfusions. Transfusions distort the results of standard A1C testing, because they introduce adult red blood cells with varying levels of glycation and different lifespans into the recipient's bloodstream. Since fetal hemoglobin is typically absent in donor blood, the assessment of fetal glycated hemoglobin (Fetal GlyHb) is not influenced by transfusions. Consequently, Fetal GlyHb determinations are particularly valuable for patients with HbF-associated conditions who have undergone transfusions.

[0111] The first methodology may be utilized for Fetal GlyHb Determination for a person who is pregnant. During pregnancy, the shortened half-life of adult blood affects the interpretation of A1C levels. Therefore, it is advantageous to use this methodology, which eliminates the adult component of the blood (i.e., Subtract off Adult GlyHb) and focuses on the glycation of fetal hemoglobin, a process specifically suited for pregnancy.

[0112] The first methodology is also appropriate for use in any individual (over 6 months of age) with any HbF-associated condition, regardless of whether patient has received blood transfusion.IV: A Second Methodology for Fetal GlyHb Determination

[0113] In another embodiment, a second methodology for Fetal GlyHb determination includes indirectly assessing Fetal GlyHb in a process involving the measurement of Adult GlyHb and Total Fetal Hemoglobin. In contrast to the first methodology, the second methodology requires only thehigh resolution HPLC technology for its measurements, rather than the combination of two separate technologies.(0114] Similarly to the first methodology, the determination of Fetal GlyHb in the second methodology is dependent upon an accurate assessment of Adult GlyHb (A1C) in a sample with mixed fetal and adult hemoglobin. To accomplish this, Total HbA is derived from (100- Total HbF) in which the Total HbF is determined utilizing the methods described earlier above.

[0115] FIG. 3 is a flowchart illustrating the second methodology. Processing begins at 302 when a whole blood sample is collected from a person (over 6 months of age) or from a newborn (e.g., less than 6 months old) who has received one or more blood transfusion. Processing continues at 304.101161 At 304, the second methodology continues with the step of preparing the blood sample for high performance liquid chromatography (HPLC) processing in accordance with manufacturer’s instructions. Processing continues at 306.

[0117] At 306, the second methodology continues with the step of processing the prepared blood sample with the HPLC instrument, in accordance with the manufacturer’s instructions. The Trinity Premier Resolution is one example of a high resolution HPLC technology that can be utilized. When step 306 is complete, obtain the HPLC chromatograph. Processing continues at 308.|0118] At 308, the second methodology continues with the step of determining total HbF (the total of all modified and unmodified fetal hemoglobin in the blood sample). Software, for example, can be configured to determine Total HbF by summing together the values, preferably the noncalibrated values, of all HbF-associated peaks on the HPLC chromatograph. Processing continues at 310.10.1.1.9] At 310, the second methodology continues with the step of determining Total HbA. Software, for example, can be configured to determine Total HbA by subtracting Total HbF from 100 (i.e. 100-Total HbF). Processing continues at 312.

[0120] At 312, the second methodology continues with the step of determining Adult GlyHb measurement, for example, by configuring software, to divide the A1C peak value by Total HbA (i.e. AlC / Total HbA= Adult GlyHb measurement). Processing continues at 314.[0.1.21] At 314, the second methodology continues with the step of converting the Adult GlyHb measurement to a Fetal GlyHb equivalent value (based on reference levels of glycated Fetal Hemoglobin in a specific population such as preterm infants (e.g., by preconfigured software). Processing continues at 316.

[0122] At 316, the second methodology continues with the step of determining an interpretation of Fetal GlyHb Value (such as high, normal, low) relevant to clinical care, dependent upon comparison to reference ranges, appropriate for the targeted disease (such as neonatal diabetes) or population (such as the population of preterm infants). This value serves as the patient’s baseline.

[0123] All the prior steps can be repeated with different blood samples from the same patient taken at different time points to monitor the patient’s glucose control over time and to adjust treatment as needed.V: A third methodology for Fetal GlyHb Determination

[0124] Like the first and second methodologies, a third methodology may indirectly assess Fetal GlyHb using multiple technologies and a computational process. However, the third methodology employs a different algorithm from those used in the first and second methodologies. The third methodology relies on a known, constant difference (“K”) in glycation rates between adult and fetal hemoglobin. The third methodology’s algorithm effectively uses the known differences in glycation rates along with the varying percentages of fetal and adult hemoglobin in the blood sample.

[0125] As with the prior methodologies, Total GlyHb (representing the glycation of both fetal and adult hemoglobin in the sample) must be measured, along with Total HbF and Total HbA. Total GlyHb is then converted to its Standard A1C value for use in the third methodology’s algorithm. Unlike the first and second methodologies, the third methodology does not require a direct measurement of Adult GlyHb. It is important to note that this method is suitable only for patients who have not received any recent transfusions (such as within the past 60 days).

[0126] FIG. 4 is flowchart illustrating the third methodology. Processing begins at 402 when a whole blood sample is collected from a person, preferably a person who has not received any recent transfusions (i.e. no transfusion in prior 45-60 days). Processing continues at 404[0.1.27] At 404, the third methodology continues with the step of dividing the blood sample into two parts. The first part of the blood sample is prepared for processing via boronate affinity chromatography (BAC), in accordance with manufacturer’s instructions. The other part of the sample for HPLC is retained processing during later steps. Processing continues at 406.

[0128] At 406, the third methodology continues with the step of, using the part of the sample prepared above (at step 404), measuring Total GlyHb, by BAC, in accordance with manufacturer’s instructions for the BAC processing. The Trinity Biotech Premier 9210 A1C Analyzer is an example of BAC technology that can be utilized. Processing continues at 408

[0129] At 408, the third methodology continues with the step of, with a suitable empiric formula, converting the Total GlyHb measurement to a standard A1C value. Processing continues at 410.

[0130] At 410, the third methodology continues with the step of preparing the second part of the original sample (e.g. the remainder of the original sample) for high performance liquid chromatography (HPLC) in accordance with the HPLC manufacturer’s instructions. Processing continues at 412.101311 At 412, the third methodology continues with the step of processing the prepared blood sample (from step 410) with a high resolution HPLC instrument, in accordance with the manufacturer’s instructions. The Trinity Premier Resolution is an example of HPLC technology that can be utilized. When step 412 is complete, HPLC chromatograph is obtained. This chromatograph will be used to determine Total HbF (at step 414) and Total HbA (at step 416). Processing continues at 414.|0132| At 414, the third methodology continues with the step of determine Total HbF (i.e. total of all modified and unmodified fetal hemoglobin); for example, software can be configured to determine the Total HbF by summing together the non-calibrated values of all HbF-associated peaks on the HPLC chromatograph. Processing continues at 416

[0133] At 416, the third methodology continues with the step of determining Total HbA. For example, software can be configured to determine %Total HbA value by subtracting %Total HbF from 100% (i.e. 100% is equal to the sum of the areas of all fetal and adult peaks on an HPLC chromatograph). Processing continues at 418. Additionally, or alternatively, Total HbA can be determined by summing together all HbA-associated peaks. Total HbF can then be determined from Total HbA (i.e. 100-Total HbA=Total HbF). When other hemoglobin variants are present (i.e., HbS), they need to be included in the sum total of peak areas. A person skilled in the art will know how to make the proper adjustments in this regard.|0.134] At 418, the third methodology continues with the step of determining Fetal GlyHb. Software can be configured to carry out the algorithmic steps as follows: Multiply %Total HbA by the pre-determined constant difference in glycation rate between HbA and HbF, called “K,” add the product (from above) to %Total HbF, use the standard A1C value (from step 408) for the value of Total GlyHb; divide Total GlyHb by the sum from above; the quotient represents Fetal GlyHb. This computational algorithm can be visually summarized as follows: Fetal GlyHb= (Total GlyHb) / [ (K * %Total HbA) + (%Total HbF)].

[0135] As an example, in a scenario where adult and fetal hemoglobin components of the blood were exposed to identical physiologic conditions (i.e. no transfusions occurred) and the difference in rate between the adult and fetal Hb is known to be 2.7; therefore, K=2.7, and that in the blood sample, the standard A1C value (derived from Total GlyHb) is 4, Total HbA is 25% and Total HbF is 0.75. Then, Fetal GlyHb = 4 / [ (2.7 *0.25) + (0.75)] = 4 / 1.4= 2.8.

[0136] At 420, the third methodology continues with the step of interpreting the Fetal GlyHb value, with its relevance to clinical care, dependent upon comparison to reference ranges appropriate for the targeted disease (such as neonatal diabetes) or population (such as the population of preterm infants).

[0137] All the prior steps can be repeated with different blood samples from the same patient taken at different time points to monitor the Fetal GlyHb Value over time to adjust treatment as needed.

[0138] The third methodology requires the presence of a constant pre-determined difference in glycation rate between adult and fetal hemoglobin. Under normal physiological conditions, the glycation rate of fetal hemoglobin (HbF) is approximately 37% that of adult hemoglobin (e.g. A1C). In other words, A1C glycates at about 2.7 times the rate of HbF. This consistent difference in glycation rates is observed only when both types of hemoglobin are exposed to identical physiological conditions, with no recent blood transfusions.

[0139] The third methodology may be utilized for determining Fetal GlyHb when the difference in glycation rates between adult hemoglobin (HbA) and fetal hemoglobin (HbF) is a predetermined constant ("K") or the adult and fetal hemoglobin components of the blood have been exposed to identical physiological conditions (e.g., no blood transfusions involved).

[0140] Similar to the first and second methodologies, the Fetal GlyHb in the third methodology is presented in an A1C format, with the denominator adjusted for the percentage of fetal hemoglobin in the sample. Therefore, the Fetal GlyHb value from the third methodology can be directly compared with Fetal GlyHb values from the first and second methodologies.VI: A Fourth Methodology for Fetal GlyHb Determination

[0141] In contrast to the first, second, and third methodologies, this approach utilizes high- resolution HPLC to directly quantify Fetal GlyHb in a blood sample. The Fetal GlyHb peak on the chromatograph is normalized to the total amount of HbF in the sample. For clinical application, the HPLC instrument, such as the Trinity Premier Resolution, must be calibrated specifically for Fetal GlyHb measurement. This calibration process involves, but is not limited to, selecting the appropriate column and optimizing the mobile phase, flow rate, column temperature, and sample preparation. This methodology is most effective when the blood sample has a high percentage of fetal hemoglobin (e.g., >60%). If HbF percentages are lower, the Fetal GlyHb concentration may fall below the detection limits of the technology.

[0142] FIG. 5 is a flowchart illustrating the fourth methodology. Processing begins at 502 when a whole blood sample is collected, for example, from a newborn or a person with a HbF-associated condition or disorder. Processing continues at 504

[0143] At 504, the fourth methodology continues with the step of preparing the blood sample for high performance liquid chromatography (HPLC) processing in accordance with manufacturer’s instructions. Processing continues at 506.[0.1.44] At 506, the fourth methodology continues with the step of processing the prepared blood sample with a high resolution HPLC instrument, in accordance with the manufacturer’s instructions. The Trinity Premier Resolution is an example of high resolution HPLC technology that can be utilized. When step 506 is complete the HPLC chromatograph is obtained. Processing continues at 508.

[0145] At 508, the fourth methodology continues with the step of determining Total HbF (the total of all modified and unmodified fetal hemoglobin in the blood sample): Software, for example, can be configured to determine Total HbF by summing together the values, preferably the noncalibrated values, of all HbF-associated peaks on the HPLC chromatograph. Processing continues at 510. Additionally, or alternatively, Total HbA can be determined by summing together all HbA- associated peaks. Total HbF can then be determined from Total HbA (i.e. 100-Total HbA=Total HbF). When other hemoglobin variants are present (i.e. HbS), they need to be included in the sum total of peak areas. A person skilled in the art will know how to make the proper adjustments in this regard.

[0146] At 510, the fourth methodology continues with the step of utilizing the HPLC chromatograph to assess the value (i.e. percentage area) of the Fetal GlyHb peak. Processing continues at 512[0.1.47] At 512, the fourth methodology continues with the step of determining Fetal GlyHb in relation to Total Fetal Hemoglobin in the blood sample. Software, for example, can be configured to divide Fetal GlyHb by Total HbF value (i.e., Fetal GlyHb / Total HbF) in the blood sample (which can then be multiplied by 100). The quotient represents Fetal GlyHb normalized for Total HbF in the blood sample. As an example, in a newborn blood sample, Fetal GlyHb peak is 1.2% (of total hemoglobin), Total HbF is 85% (of total hemoglobin), the quotient (Fetal GlyHb / Total HbF) is.012 / 85 which equals .0141. After multiplying by 100, Fetal GlyHb is equal 1.41%. Treating Fetal GlyHb as a numerical value, Fetal GlyHb = 1.41

[0148] At 514, the fourth methodology continues with the step of interpreting the Fetal GlyHb value, with its relevance to clinical care, dependent upon comparison to reference ranges appropriate for the targeted disease (such as neonatal diabetes) or population (such as the population of preterm infants).

[0149] All the prior steps can be repeated with different blood samples from the same patient taken at different time points to monitor the Fetal GlyHb Value over time to adjust treatment as needed.

[0150] Graph 1 illustrates example testing data from a Trinity Premier Resolution chromatography utilizing the fourth methodology. On the Trinity Premier Resolution chromatograph, the Fetal GlyHb peak is the Fetal region peak, with retention time (RT) at approximately F 0.73To demonstrate that F 0.73 represents Fetal GlyHb. The test involved analyzing correlation between the area of peak F 0.73 (normalized to Total HbF) and Fetal GlyHb assessed using the second methodology. Utilizing data from 48 infant blood samples (N=48), a Pearson correlation analysis was conducted between these two variables. The Premier Resolution had not been optimized for peak F 0.73 measurement. Nevertheless, the results showed a correlation coefficient r= 0.64 (p<0.0001) Therefore, despite suboptimal measurement of peak F 0.73, there is a moderate positive correlation of high statistical significance. This suggests that peak F 0.73 (on Premier Resolution chromatograph) represents Fetal GlyHb. The retention time of the equivalent peak on alternative HPLC chromatographs is likely to differ somewhat.Graph 1

[0151] According to the test performed, Total GlyHb of samples with >95% HbF on the Premier 9210 (Boronate Affinity Chromotography) correlates with direct measurement of glycated fetal hemoglobin on the premier resolution. The Pearson correlation coefficient is 0.689, p<0.00001, N=32. Utilizing premier 9210, Total Glycated Hb mean is 3.549. standard deviation is 0.253, minimum is 3.130, and maximum is 4.230. utilizing premier resolution, glycated fetal Hb mean is 1.409, standard deviation is 0.234, minimum is 1.100, and maximum is 1.800.

[0152] The linear regression model fitted to predict GF73 from TotGlyHb provides the following insights: the equation of the line is Fetal GlyHb = -0.855 + 0.638 * TotGlyHb. R-squared is 0.474, indicating that about 47.4% of the variability in FetalGlyHb can be explained by TotGlyHb.VII: A fifth methodology for using determined glycated fetal hemoglobin for diagnosing gestational diabetes or monitoring maternal glucose control during pregnancy

[0153] Fetal GlyHb, measured in neonatal or cord blood, has been proposed as a biomarker for evaluating glucose control in neonates. In addition to neonatal use, some implementations described herein include a new use of Fetal GlyHb in maternal blood, to diagnose gestational diabetes and / or monitor glucose control of the pregnant women.To date, there is no glucose control biomarker to accurately assess longitudinal glucose control in pregnancy or blood test biomarker to diagnose gestational diabetes. This is because the natural state of established glycated hemoglobin biomarkers, such as A1C, align with non-pregnant conditions. Pregnancy triggers an increase in red blood cell turnover, thereby altering the lifespan of red blood cells. Changes in red blood cell turnover during pregnancy disrupt the accurate interpretation of A1C, often causing A1C value during pregnancy to under-estimate actual maternal glucose levels. In contrast to this, the natural state of Glycated Fetal Hemoglobin is inherently linked to pregnancy. Thus, fetal glycated Hb in maternal blood can be used to estimate glucose control in the mother.

[0154] A1C, rather than Fetal GlyHb, is the predominant form of glycation in adult blood. Therefore, glycated fetal Hb is generally not utilized as a marker of maternal glucose control. However, percentage of HbF increases in the maternal circulation, particularly during the secondtrimester. Yet, HbF remains as a minor component (between 2% to 5%) of the pregnant woman’s hemoglobin. Despite its low percentage of total hemoglobin during pregnancy, the high accuracy, precision and the reproducibility of the component measurements when performed with the examples described herein are leveraged. This permits Fetal GlyHb assessment in maternal blood through the methodology outlined herein.

[0155] In an example, determined Fetal GlyHb can be used to assess glucose control in various HbF-associated disorders and transfusion-related hemoglobinopathies affecting both children and adults. Examples of HbF-associated disorders and conditions are described above.

[0156] FIG. 6 is a flowchart illustrating the fifth methodology. Processing begins at 602, where a maternal blood sample is obtained. Processing continues to 604.|0157| At 604, the fifth methodology continues with the step of determining Fetal GlyHb in the maternal blood (e.g., using one of the first, second, third, or fourth methodologies described herein). Processing continues to 606.

[0158] At 606, the fifth methodology continues with the step of using Fetal GlyHb to estimate maternal glucose control or for other purposes using Fetal GlyHb determinations (in coordination with Device of Fig 7). The interpretation of the Fetal GlyHb in maternal blood will depend upon comparison of the values to reference ranges appropriate to pregnant women as known.|0159[ To monitor glucose control during pregnancy, the fifth methodology can be repeated every 2 to 4 weeks, that is, approximately 2-4 times per trimester.VIII: Example Computing Device

[0160] Various implementations of features described herein can use any type of system and / or service. Any type of electronic device can make use of the features described herein. Some implementations can provide one or more features described herein on client or server devices disconnected from or intermittently connected to computer networks. A description of a computing system helpful for Fetal GlyHb determination is provided herein. It can run standalone programs, web applications, or mobile apps, handling different computations either on the device itself or in collaboration with servers.

[0161] FIG. 7 illustrates an example computing device 700 which may store software as described above executable to carry out any of the first, second, third, fourth, or fifth methodologies. The device 700 includes a processor 702. The processor 702 is a versatile processing unit capable of executing various tasks, including neural network processing and handling probabilistic outputs. It can include multiple cores, GPUs, or specialized hardware for specific functions. The computing device 700 includes a memory 704. The memory 704 may provide storage for software and data as described above, including operating systems, machinelearning applications, and specific applications like glycated fetal hemoglobin determination. The memory 704 stores both temporary and permanent data and instructions. The computing device 700 includes an I / O interface 706. The I / O interface 706 facilitates communication with other devices and systems, supporting input / output devices like keyboards, displays, and sensors. Sensors (not numbered) may collect the data (e g., hemoglobin levels) utilized in any of the methodologies described above.|O162| The device includes software and applications such as a machine-learning application 730. The Machine-learning application 730 includes models for tasks such as glycated fetal hemoglobin determination, using various machine learning techniques like supervised and unsupervised learning. The machine-learning application 730 supports different neural network structures and can generate outputs such as predictions, classifications, and knowledge representations. The machine-learning application 736 may further include an interface engine 736. The interface engine 736 applies trained models to input data, generating inferences for further processing or output.

[0163] The device 700 can be used in various configurations, including offline and online modes, and can adapt to different computational environments and resources. The machine-learning applications 730 can handle different data types and generate outputs related to Fetal GlyHb across various formats and applications. Overall, this setup provides a robust and adaptable environment for implementing advanced computing tasks, leveraging modem machine-learning techniques and accommodating a variety of devices and user interactions.

[0164] In one example, the device 700 may be used to implement a client device, e.g., any of client devices 120-126 shown in Fig. 1. Alternatively, device 700 can implement a server device,e.g., server device 104, etc. In some implementations, device 700 may be used to implement a client device, a server device, or a combination of the above. Device 700 can be any suitable computer system, server, or other electronic or hardware device as described above.

[0165] One or more methods described herein (e.g., any of the first, second, third, fourth, or fifth methodologies) can be run in a standalone program that can be executed on any type of computing device, a program run on a web browser, a mobile application (“app”) run on a mobile computing device (e.g., cell phone, smart phone, tablet computer, wearable device (wristwatch, armband, jewelry, headwear, virtual reality goggles or glasses, augmented reality goggles or glasses, head mounted display, etc.), laptop computer, etc.).

[0166] In one example, a client / server architecture can be used, e g., a mobile computing device (as a client device) sends user input data to a server device and receives from the server the final output data for output (e.g., for display). In another example, all computations can be performed within the mobile app (and / or other apps) on the mobile computing device. In another example, computations can be split between the mobile computing device and one or more server devices.

[0167] In some implementations, device 700 includes a processor 702, a memory 704, and I / O interface 706. Processor 702 can be one or more processors and / or processing circuits to execute program code and control basic operations of the device 700. A “processor” includes any suitable hardware system, mechanism or component that processes data, signals or other information. A processor may include a system with a general-purpose central processing unit (CPU) with one or more cores (e.g., in a single-core, dual-core, or multi-core configuration), multiple processing units (e g., in a multiprocessor configuration), a graphics processing unit (GPU), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a complex programmable logic device (CPLD), dedicated circuitry for achieving functionality, a special-purpose processor to implement neural network model-based processing, neural circuits, processors optimized for matrix computations (e.g., matrix multiplication), or other systems.

[0168] In some implementations, processor 702 may include one or more co-processors that implement neural -network processing. In some implementations, processor 702 may be a processor that processes data to produce probabilistic output, e.g., the output produced by processor 702 may be imprecise or may be accurate within a range from an expected output.Processing need not be limited to a particular geographic location or have temporal limitations. For example, a processor may perform its functions in “real-time,” “offline,” in a “batch mode,” etc. Portions of processing may be performed at different times and at different locations, by different (or the same) processing systems. A computer may be any processor in communication with a memory.

[0169] Memory 704 is typically provided in device 700 for access by the processor 702 and may be any suitable processor-readable storage medium, such as random-access memory (RAM), readonly memory (ROM), Electrically Erasable Read-only Memory (EEPROM), Flash memory, etc., suitable for storing instructions for execution by the processor, and located separate from processor 702 and / or integrated therewith. Memory 704 can store software operating on the server device 700 by the processor 702, including an operating system 708, machine-learning application 730, glycated fetal hemoglobin determination application 710, and application data 712. Other applications may include applications such as a data display engine, web hosting engine, image display engine, notification engine, social networking engine, etc. In some implementations, the machine-learning application 730 and glycated fetal hemoglobin determination application 710 can each include instructions that enable processor 702 to perform functions described herein, e.g., some or all of the first, second, third, fourth, or fifth methodologies.

[0170] The machine-learning application 730 can include one or more named entity recognition (NER) implementations for which supervised and / or unsupervised learning can be used. The machine learning models can include multi-task learning based models, residual task bidirectional LSTM (long short-term memory) with conditional random fields, statistical NER, etc. The Device can also include a glycated fetal hemoglobin determination application 710 as described herein and other applications. One or more methods disclosed herein can operate in several environments and platforms, e.g., as a stand-alone computer program that can run on any type of computing device, as a web application having web pages, as a mobile application (“app”) run on a mobile computing device, etc.

[0171] In various implementations, machine-learning application 730 may utilize Bayesian classifiers, support vector machines, neural networks, or other learning techniques. In some implementations, machine-learning application 730 may include a trained model 734, an inferenceengine 736, and data 732. In some implementations, data 732 may include training data, e.g., data used to generate trained model 734. For example, training data may include any type of data suitable for training a model for glycated fetal hemoglobin determination tasks, such as images, labels, thresholds, etc. associated with glycated fetal hemoglobin determination functions described herein. Training data may be obtained from any source, e g., a data repository specifically marked for training, data for which permission is provided for use as training data for machine-learning, etc. In implementations where one or more users permit use of their respective user data to train a machine-learning model, e.g., trained model 734, training data may include such user data. In implementations where users permit use of their respective user data, data 732 may include permitted data.

[0172] In some implementations, data 732 may include collected data such as the blood measurements described herein. In some implementations, training data may include synthetic data generated for the purpose of training, such as data that is not based on user input or activity in the context that is being trained, e.g., data generated from simulated conversations, computergenerated images, etc. In some implementations, machine-learning application 730 excludes data 732. For example, in these implementations, the trained model 734 may be generated, e.g., on a different device, and be provided as part of machine-learning application 730. In various implementations, the trained model 734 may be provided as a data file that includes a model structure or form, and associated weights. Inference engine 736 may read the data file for trained model 734 and implement a neural network with node connectivity, layers, and weights based on the model structure or form specified in trained model 734.

[0173] Machine-learning application 730 also includes a trained model 734. In some implementations, the trained model 734 may include one or more model forms or structures. For example, model forms or structures can include any type of neural -network, such as a linear network, a deep neural network that implements a plurality of layers (e.g., “hidden layers” between an input layer and an output layer, with each layer being a linear network), a convolutional neural network (e.g., a network that splits or partitions input data into multiple parts or tiles, processes each tile separately using one or more neural -network layers, and aggregates the results from the processing of each tile), a sequence-to-sequence neural network (e g., a network that takes as inputsequential data, such as words in a sentence, frames in a video, etc. and produces as output a result sequence), etc.(0174] The model form or structure may specify connectivity between various nodes and organization of nodes into layers. For example, nodes of a first layer (e.g., input layer) may receive data as input data 732 or application data 712. Such data can include, for example, images, e.g., when the trained model is used for glycated fetal hemoglobin determination functions. Subsequent intermediate layers may receive as input output of nodes of a previous layer per the connectivity specified in the model form or structure. These layers may also be referred to as hidden layers. A final layer (e.g., output layer) produces an output of the machine-learning application. In some implementations, model form or structure also specifies a number and / or type of nodes in each layer.

[0175] In different implementations, the trained model 734 can include a plurality of nodes, arranged into layers per the model structure or form. In some implementations, the nodes may be computational nodes with no memory, e.g., configured to process one unit of input to produce one unit of output. Computation performed by a node may include, for example, multiplying each of a plurality of node inputs by a weight, obtaining a weighted sum, and adjusting the weighted sum with a bias or intercept value to produce the node output.

[0176] In some implementations, the computation performed by a node may also include applying a step / activation function to the adjusted weighted sum. In some implementations, the step / activation function may be a nonlinear function. In various implementations, such computation may include operations such as matrix multiplication. In some implementations, computations by the plurality of nodes may be performed in parallel, e.g., using multiple processors cores of a multicore processor, using individual processing units of a GPU, or specialpurpose neural circuitry. In some implementations, nodes may include memory, e.g., may be able to store and use one or more earlier inputs in processing a subsequent input. For example, nodes with memory may include long short-term memory (LSTM) nodes. LSTM nodes may use the memory to maintain “state” that permits the node to act like a finite state machine (FSM). Models with such nodes may be useful in processing sequential data, e.g., words in a sentence or a paragraph, frames in a video, speech or other audio, etc.

[0177] In some implementations, trained model 734 may include embeddings or weights for individual nodes. For example, a model may be initiated as a plurality of nodes organized into layers as specified by the model form or structure. At initialization, a respective weight may be applied to a connection between each pair of nodes that are connected per the model form, e.g., nodes in successive layers of the neural network. For example, the respective weights may be randomly assigned, or initialized to default values. The model may then be trained, e.g., using data 732, to produce a result.

[0178] For example, training may include applying supervised learning techniques. In supervised learning, the training data can include a plurality of inputs (e.g., a set of images) and a corresponding expected output for each input. Based on a comparison of the output of the model with the expected output, values of the weights are automatically adjusted, e.g., in a manner that increases a probability that the model produces the expected output when provided similar input.

[0179] In some implementations, training may include applying unsupervised learning techniques. In unsupervised learning, only input data may be provided, and the model may be trained to differentiate data, e.g., to cluster input data into a plurality of groups, where each group includes input data that are similar in some manner.

[0180] In another example, a model trained using unsupervised learning may cluster words based on the use of the words in data sources. In some implementations, unsupervised learning may be used to produce knowledge representations, e.g., that may be used by machine-learning application 730. In various implementations, a trained model includes a set of weights, or embeddings, corresponding to the model structure. In implementations where data 732 is omitted, machinelearning application 730 may include trained model 734 that is based on prior training, e.g., by a developer of the machine-learning application 730, by a third-party, etc. In some implementations, trained model 734 may include a set of weights that are fixed, e.g., downloaded from a server that provides the weights.|0181| Machine-learning application 730 also includes an inference engine 736. Inference engine 736 is configured to apply the trained model 734 to data, such as application data 714, to provide an inference. In some implementations, inference engine 736 may include software code to be executed by processor 702. In some implementations, inference engine 736 may specify circuitconfiguration (e.g., for a programmable processor, for a field programmable gate array (FPGA), etc.) enabling processor 702 to apply the trained model. In some implementations, inference engine 736 may include software instructions, hardware instructions, or a combination. In some implementations, inference engine 736 may offer an application programming interface (API) that can be used by operating system 708 and / or glycated fetal hemoglobin determination application 710 to invoke inference engine 736, e.g., to apply trained model 734 to application data 714 to generate an inference.

[0182] Machine-learning application 730 may provide several technical advantages. For example, when trained model 734 is generated based on unsupervised learning, trained model 734 can be applied by inference engine 736 to produce knowledge representations (e.g., numeric representations) from input data, e g., application data 712. For example, a model trained for glycated fetal hemoglobin determination tasks may produce predictions and confidences for given input information about glycated fetal hemoglobin determination. In some implementations, such representations may be helpful to reduce processing cost (e.g., computational cost, memory usage, etc.) to generate an output (e.g., a suggestion, a prediction, a classification, etc.). In some implementations, such representations may be provided as input to a different machine-learning application that produces output from the output of inference engine 736.

[0183] In some implementations, knowledge representations generated by machine-learning application 730 may be provided to a different device that conducts further processing, e.g., over a network. In such implementations, providing the knowledge representations rather than the images may provide a technical benefit, e.g., enable faster data transmission with reduced cost. In another example, a model trained for glycated fetal hemoglobin determination may produce a glycated fetal hemoglobin determination signal for one or more blood sample measurements being processed by the model.

[0184] In some implementations, machine-learning application 730 may be implemented in an offline manner. In these implementations, trained model 734 may be generated in a first stage and provided as part of machine-learning application 730. In some implementations, machine-learning application 730 may be implemented in an online manner. For example, in such implementations, an application that invokes machine-learning application 730 (e.g., operating system 708, one ormore of glycated fetal hemoglobin determination application 710 or other applications) may utilize an inference produced by machine-learning application 730, e.g., provide the inference to a user, and may generate system logs (e.g., if permitted by the user, an action taken by the user based on the inference; or if utilized as input for further processing, a result of the further processing). System logs may be produced periodically, e.g., hourly, monthly, quarterly, etc. and may be used, with user permission, to update trained model 734, e.g., to update embeddings for trained model 734.

[0185] In some implementations, machine-learning application 730 may be implemented in a manner that can adapt to particular configuration of device 700 on which the machine-learning application 730 is executed. For example, machine-learning application 730 may determine a computational graph that utilizes available computational resources, e.g., processor 702. For example, if machine-learning application 730 is implemented as a distributed application on multiple devices, machine-learning application 730 may determine computations to be carried out on individual devices in a manner that optimizes computation. In another example, machinelearning application 730 may determine that processor 702 includes a GPU with a particular number of GPU cores (e.g., 1000) and implement the inference engine accordingly (e.g., as 1000 individual processes or threads).

[0186] In some implementations, machine-learning application 730 may implement an ensemble of trained models. For example, trained model 734 may include a plurality of trained models that are each applicable to same input data. In these implementations, machine-learning application 730 may choose a particular trained model, e.g., based on available computational resources, success rate with prior inferences, etc. In some implementations, machine-learning application 730 may execute inference engine 736 such that a plurality of trained models is applied. In these implementations, machine-learning application 730 may combine outputs from applying individual models, e.g., using a voting-technique that scores individual outputs from applying each trained model, or by choosing one or more particular outputs. Further, in these implementations, machine-learning applications may apply a time threshold for applying individual trained models (e g., 0.5 ms) and utilize only those individual outputs that are available within the time threshold. Outputs that are not received within the time threshold may not be utilized, e.g., discarded. For example, such approaches may be suitable when there is a time limit specified while invoking themachine-learning application, e.g., by operating system 708 or one or more other applications, e.g., glycated fetal hemoglobin determination application 710.(0187] In different implementations, machine-learning application 730 can produce different types of outputs. For example, machine-learning application 730 can provide representations or clusters (e.g., numeric representations of input data), labels (e.g., for input data that includes images, documents, etc.), phrases or sentences (e.g., descriptive of an image or video, suitable for use as a response to an input sentence, suitable for use to determine context during a conversation, etc ), images (e.g., generated by the machine-learning application in response to input), audio or video (e.g., in response an input video, machine-learning application 730 may produce an output video with a particular effect applied, e.g., rendered in a comic-book or particular artist’s style, when trained model 734 is trained using training data from the comic book or particular artist, etc. In some implementations, machine-learning application 730 may produce an output based on a format specified by an invoking application, e.g. operating system 708 or one or more applications, e.g., glycated fetal hemoglobin determination application 710. In some implementations, an invoking application may be another machine-learning application. For example, such configurations may be used in generative adversarial networks, where an invoking machinelearning application is trained using output from machine-learning application 730 and vice versa.

[0188] Any software in memory 704 can alternatively be stored on any other suitable storage location or computer-readable medium. In addition, memory 704 (and / or other connected storage device(s)) can store one or more messages, one or more taxonomies, electronic encyclopedia, dictionaries, thesauruses, knowledge bases, message data, grammars, user preferences, and / or other instructions and data used in the features described herein. Memory 704 and any other type of storage (magnetic disk, optical disk, magnetic tape, or other tangible media) can be considered "storage" or "storage devices."|0189| I / O interface 706 can provide functions to enable interfacing the server device 700 with other systems and devices. Interfaced devices can be included as part of the device 700 or can be separate and communicate with the device 700. For example, network communication devices, storage devices (e.g., memory and / or database), and input / output devices can communicate via VO interface 706. In some implementations, the I / O interface can connect to interface devices such asinput devices (keyboard, pointing device, touchscreen, microphone, camera, scanner, sensors, etc.) and / or output devices (display devices, speaker devices, printers, motors, etc.).(0190] Some examples of interfaced devices that can connect to I / O interface 706 can include one or more display devices 720 and one or more data stores 738 (as discussed above). The display devices 720 that can be used to display content, e.g., a user interface of an output application as described herein. Display device 720 can be connected to device 700 via local connections (e.g., display bus) and / or via networked connections and can be any suitable display device. Display device 720 can include any suitable display device such as an LCD, LED, or plasma display screen, CRT, television, monitor, touchscreen, 3-D display screen, or other visual display device. For example, display device 720 can be a flat display screen provided on a mobile device, multiple display screens provided in a goggles or headset device, or a monitor screen for a computer device.(0191 ] The I / O interface 706 can interface to other input and output devices. Some examples include one or more cameras which can capture images. Some implementations can provide a microphone for capturing sound (e g., as a part of captured images, voice commands, etc.), audio speaker devices for outputting sound, or other input and output devices.|0192| For ease of illustration, FIG. 7 shows one block for each of processor 702, memory 704, I / O interface 706, and software blocks 708, 712, 732 and 738. These blocks may represent one or more processors or processing circuitries, operating systems, memories, I / O interfaces, applications, and / or software modules. In other implementations, device 700 may not have all of the components shown and / or may have other elements including other types of elements instead of, or in addition to, those shown herein. While some components are described as performing blocks and operations as described in some implementations herein, any suitable component or combination of components of environment 100, device 700, similar systems, or any suitable processor or processors associated with such a system, may perform the blocks and operations described.|0193| In some implementations, logistic regression can be used for personalization. In some implementations, the prediction model can be handcrafted including hand selected labels and thresholds. The mapping (or calibration) from ICA space to a predicted precision within a space can be performed using a piecewise linear model.

[0194] In some implementations, the glycated fetal hemoglobin determination system could include a machine-learning model (as described herein) for tuning the system to potentially provide improved accuracy. Inputs to the machine learning model can include ICA labels, a descriptor vector that describes and includes semantic information about glycated fetal hemoglobin determination. Example machine-learning model input can include labels for a simple implementation and can be augmented with descriptor vector features for a more advanced implementation. Output of the machine-learning module can include a prediction of diagnostic, treatment, or other parameters associated with glycated fetal hemoglobin determination.|0.195] One or more methods described herein (e.g., the first, second, third, fourth, or fifth methodologies) can be implemented by computer program instructions or code, which can be executed on a computer. For example, the code can be implemented by one or more digital processors (e.g., microprocessors or other processing circuitry), and can be stored on a computer program product including a non-transitory computer readable medium (e.g., storage medium), e.g., a magnetic, optical, electromagnetic, or semiconductor storage medium, including semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), flash memory, a rigid magnetic disk, an optical disk, a solid-state memory drive, etc. The program instructions can also be contained in, and provided as, an electronic signal, for example in the form of software as a service (SaaS) delivered from a server (e.g., a distributed system and / or a cloud computing system). Alternatively, one or more methods can be implemented in hardware (logic gates, etc.), or in a combination of hardware and software. Example hardware can be programmable processors (e.g. Field- Programmable Gate Array (FPGA), Complex Programmable Logic Device), general purpose processors, graphics processors, Application Specific Integrated Circuits (ASICs), and the like. One or more methods can be performed as part of or component of an application running on the system, or as an application or software running in conjunction with other applications and operating system.

[0196] One or more methods described herein can be run in a standalone program that can be run on any type of computing device, a program run on a web browser, a mobile application (“app”) run on a mobile computing device (e.g., cell phone, smart phone, tablet computer, wearable device (wristwatch, armband ewelry, headwear, goggles, glasses, etc.), laptop computer, etc.). Inone example, a client / server architecture can be used, e.g., a mobile computing device (as a client device) sends user input data to a server device and receives from the server the final output data for output (e.g., for display). In another example, all computations can be performed within the mobile app (and / or other apps) on the mobile computing device. In another example, computations can be split between the mobile computing device and one or more server devices.

[0197] Although the description has been described with respect to particular implementations thereof, these particular implementations are merely illustrative, and not restrictive. Concepts illustrated in the examples may be applied to other examples and implementations.

[0198] Note that the functional blocks, operations, features, methods, devices, and systems described in the present disclosure may be integrated or divided into different combinations of systems, devices, and functional blocks. Any suitable programming language and programming techniques may be used to implement the routines of particular implementations. Different programming techniques may be employed, e.g., procedural or object-oriented. The routines may be executed on a single processing device or multiple processors. Although the steps, operations, or computations may be presented in a specific order, the order may be changed in different particular implementations. In some implementations, multiple steps or operations shown as sequential in this specification may be performed at the same time.

[0199] Part IX: Diagnostic and Treatment Options

[0200] When performing glycated fetal hemoglobin determination functions, it may be beneficial for a system to suggest diagnostic or treatment options and / or to make predictions about patient physiological parameters such as glucose control. To make predictions or suggestions, a probabilistic model (e.g., implemented on the device 700) can be used to make an inference (or prediction) about aspects of glycated fetal hemoglobin determination.

[0201] Since fetal hemoglobin has a shorter half-life than adult hemoglobin, Fetal GlyHb assessments should be performed more frequently than A1C testing, for example, Fet GlyHb testing once per month is reasonable since Fet GlyHb determinations represents approximately 2 to 4 weeks of glucose control. For example, for newborns, Fet GlyHb determinations can be performed at or near birth, 3 to 4 weeks old, 6 to 8 weeks old, 10 to 12 weeks old, etc. In pregnancy,Fetal GlyHb assessments can be performed a few times per trimester. For other HbF associated conditions, the frequency of Fet GlyHb will depend on the clinical circumstances.(0202] In some embodiments, the method further comprises treating the person based on the diagnosis or risk of a glucose disorder based on the Fetal GlyHb Determination. In premature infants and newborn infants of diabetic mothers, acute hypoglycemia (diagnosed by actual blood glucose level) is more common than acute hyperglycemia. Because of this, hospitalized newborns may receive intravenous glucose solutions to boost their blood glucose levels. The glucose solutions are usually administered, knowing the acute glucose status, but without knowledge of the patient’s chronic glucose status. The two common choices for fluid administration are D5W (dextrose 5% in water) and D10W (dextrose 10% in water). Of note, dextrose is a crystalline form of glucose that raises blood glucose. Herein, in reference to glucose supplementation (whether oral, enteral, parenteral, topical, or by any other route of administration), the terms “glucose” and “dextrose” will be used interchangeably.

[0203] For a particular embodiment, the treatment is made in the setting where the infant is receiving intravenous fluid containing dextrose for fluid management. The treatment can be adjusted or changed to help normalize the infant’s glucose trajectory. In cases where the glucose control indicator indicates chronic hyperglycemia, the treatment would be to change to a different intravenous fluid containing a lower concentration of dextrose (e.g. switching from DI 0W to D5W (D5W), or eliminating dextrose from the intravenous fluid, or reducing the rate of fluid infusion containing the dextrose,) or shortening the duration of the dextrose fluid infusion. In some cases, the infant is treated with a glucose lowering medication (e.g. insulin). In cases where the glucose control indicator indicates chronic hypoglycemia, the treatment would be to change to a different intravenous fluid containing a higher concentration of dextrose (e.g. switching from D5W to D10W), or increasing the rate of fluid infusion containing the dextrose, or prolonging the duration of dextrose fluid infusion. Another treatment for chronic hypoglycemia in infants is the use of a neonatal dextrose gel.

[0204] Treatment for a pregnant woman may be selected or modified if the Fetal GlyHb determination is diagnostic or suggestive of a glucose disorder such as gestational diabetes. For example, the mother may begin treatment with a glucose lowering medication (e.g. insulin) or havethe dosage of such medicine increased. Or the mother may be prescribed an appropriate diet and exercise regimen with repeat risk assessments of gestational diabetes to monitor the condition.(0205] Treatment regiments for patients with other HbF associated conditions will depend on the particular clinical scenario. In accordance with this disclosure, in situations where circumstances warrant, any suitable treatment for hyperglycemia or reducing glucose levels may be used. Examples include initiating a glucose lowering medication (e.g. insulin or oral antihyperglycemic agents), increasing the dosage thereof, or making recommendations for an appropriate diet and exercise regimen. Other examples include modifying, reducing, or eliminating any form of glucose nourishment that the person is receiving. Examples of glucose nourishment include intravenous fluids containing dextrose or glucose supplementation by any route of administration, such as oral, enteral, parenteral, or topical. In situations where circumstances warrant, any suitable treatment for hypoglycemia or raising glucose levels may be used. Examples include initiating administration of glucose nourishment or increasing the amount thereof (e.g. changing to intravenous fluid containing a higher dextrose concentration or administering a glucose supplement by oral, enteral, parenteral, topical, or any other route of administration.)

[0206] Features illustrated or described in connection with one figure may be combined with features shown in one or more other figures to create additional embodiments not explicitly depicted or discussed. The illustrated combinations represent example configurations suitable for typical applications. However, alternative combinations and modifications of the disclosed features, consistent with the principles outlined in this disclosure, may be more appropriate for specific use cases or implementations.

[0207] While example embodiments have been described above, they are not intended to encompass all possible implementations. The language used in the specification is intended as a description rather than a limitation, and various modifications may be made without departing from the spirit and scope of the subject matter disclosed. Additionally, features from different embodiments may be combined to create further implementations within the scope of the claims.

Claims

1. A method for assessing glycated fetal hemoglobin comprising: measuring one or more forms of glycated hemoglobin in a blood sample; determining a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin in the blood sample; subtracting the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value; determining a glycated fetal hemoglobin value in the blood sample based at least two of: a total glycated hemoglobin measurement, a glycated adult hemoglobin measurement, a glycated fetal hemoglobin measurement, a total adult hemoglobin measurement, and a total fetal hemoglobin measurement; comparing the glycated fetal hemoglobin value to a reference range to obtain a comparison; determining a baseline glucose control value based on the comparison; and outputting the baseline glucose control value and the comparison to a display for medical evaluation.

2. The method of Claim 1, wherein determining the glycated fetal hemoglobin value includes multiplying the total adult hemoglobin measurement and the glycated adult hemoglobin measurement to obtain a first result, subtracting from the total glycated hemoglobin measurement, and dividing by the total fetal hemoglobin measurement.

3. The method of Claim 1, further comprising determining the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement prior to outputting the glycated fetal hemoglobin measurement relative to the total fetal hemoglobin measurement based on the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement.

4. The method of Claim 1, wherein determining the glycated fetal hemoglobin measurement includes dividing the total glycated hemoglobin measurement by a multiplicativeresult of a known constant and the total adult hemoglobin measurement added to the total fetal hemoglobin measurement.

5. The method of claim 4, wherein the known constant corrects for a difference in glycation rate between the adult hemoglobin measurement and the total fetal hemoglobin measurement.

6. The method of Claim 1, further comprising dividing the glycated fetal hemoglobin measurement by the total fetal hemoglobin measurement.

7. The method of Claim 1, further comprising identifying gestational diabetes based on a deviation of the glycated fetal hemoglobin measurement outside of a threshold range of the reference range.

8. The method of Claim 1, wherein the blood sample includes fetal hemoglobin and adult hemoglobin.

9. The method of Claim 1, wherein the peak area summation is based on noncalibrated peak areas.

10. The method of claim 1, further comprising determining a patient treatment plan based on a plurality of blood samples.

11. A hemoglobin measuring device, comprising: a plurality of sensors; a display configured to present information; and a computing device in communication with the sensors and display and having a processor and a memory, the memory storing instructions executable by the processor to: receive, from the sensors, measurements of one or more forms of glycated hemoglobin in a blood sample;determine a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin in the blood sample; subtract the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value; determine a glycated fetal hemoglobin value in the blood sample based at least two of: a total glycated hemoglobin measurement, a glycated adult hemoglobin measurement, a glycated fetal hemoglobin measurement, a total adult hemoglobin measurement, and a total fetal hemoglobin measurement; compare the glycated fetal hemoglobin value to a reference range to obtain a comparison; determine a baseline glucose control value based on the comparison; and output the baseline glucose control value and the comparison to a display for medical evaluation.

12. The device of Claim 11, wherein determining the glycated fetal hemoglobin value includes multiplying the total adult hemoglobin measurement and the glycated adult hemoglobin measurement to obtain a first result, subtracting from the total glycated hemoglobin measurement, and dividing by the total fetal hemoglobin measurement.

13. The device of claim 11, the instructions including further instructions to determine the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement prior to outputting the glycated fetal hemoglobin measurement relative to the total fetal hemoglobin measurement based on the glycated adult hemoglobin measurement relative to the total adult hemoglobin measurement.

14. The device of Claim 1, wherein the processor is further programmed to determine the glycated fetal hemoglobin measurement by dividing the total glycated hemoglobin measurement by a multiplicative result of a known constant and the total adult hemoglobin measurement added to the total fetal hemoglobin measurement.

15. The device of claim 14, wherein the known constant corrects for a difference in glycation rate between the adult hemoglobin measurement and the total fetal hemoglobin measurement.

16. The device of Claim 1, wherein the processor is further programmed to divide the glycated fetal hemoglobin measurement by the total fetal hemoglobin measurement.

17. The device of Claim 1, wherein the processor is further programmed to identify gestational diabetes based on a deviation of the glycated fetal hemoglobin measurement outside of a threshold range of the reference range.

18. The device of Claim 1, wherein the blood sample includes fetal hemoglobin and adult hemoglobin.

19. The device of Claim 1, wherein the peak area summation is based on non-calibrated peak areas.

20. The device of claim 1, wherein the processor is further programmed to determine a patient treatment plan based on, the baseline glucose control value.

Images