Auxiliary data for improving performance of continuous glucose monitoring systems

Abstract

The present invention relates to auxiliary data for improving performance of a continuous glucose monitoring system. A method is provided, comprising: obtaining, from an analyte sensor, a first data stream corresponding to a concentration of an analyte in a biological fluid; converting the first data stream into an analyte value reflecting the concentration of the analyte; obtaining one or more additional data streams from one or more auxiliary sensors; inferring, based on the first data stream and the one or more additional data streams, that the conversion of the first data stream into the analyte value is predicted to be inaccurate; and taking a mitigation measure to avoid reporting the inaccurate analyte value to a user.

Description

[0001] This application is a divisional application of the invention patent application filed on January 22, 2021, with application number 202180023383.2 (international phase application number PCT / US2021 / 014768) and entitled "Auxiliary data for improving the performance of a continuous glucose monitoring system". Cross-references to related applications

[0002] This application claims priority to the earlier filing of U.S. Provisional Application No. 62 / 964,975, filed on January 23, 2020, which is incorporated herein by reference in its entirety. Technical Field

[0003] The embodiments described herein relate to the field of continuous analyte monitoring, and more specifically, to aspects of controlling the operation of a continuous analyte monitoring system, including estimating blood glucose concentrations based at least in part on auxiliary data. Background Technology

[0004] Blood sugar levels are primarily regulated by a hormone called insulin, secreted from the beta cells of the pancreas. In type 1 diabetes, insulin secretion is reduced due to an autoimmune process that disrupts beta cells. Type 1 diabetes is treated with lifelong insulin replacement therapy, which aims to keep blood sugar levels within a strict target range to avoid long-term macrovascular and microvascular complications. However, providing adequate insulin is challenging, partly due to the intermittent nature of traditional blood glucose meters (4 to 7 measurements per day). Blood sugar levels often fluctuate dramatically over short periods, leading to many unrecognized cases of hypoglycemia (low blood sugar levels) and hyperglycemia (high blood sugar levels). Similar problems are common in people with type 2 diabetes, where the body either resists the effects of insulin or cannot produce enough insulin to maintain normal blood sugar levels.

[0005] Continuous glucose monitoring (CGM) systems have been developed to measure blood glucose levels periodically (e.g., every 5 minutes), thus overcoming the shortcomings of traditional blood glucose meters. CGM systems can improve glycemic control and, when combined with insulin pumps, form an artificial pancreas system with the potential to revolutionize diabetes care. However, reliance on CGM systems inherently requires that the blood glucose values ​​determined by such systems accurately reflect the actual blood glucose levels present in the blood of the subjects using such systems. Therefore, it is necessary to identify specific physiological and / or environmental conditions that may adversely affect the accuracy of CGM systems and to provide solutions for correcting or otherwise compensating for these conditions to improve the overall operation of CGM systems. Summary of the Invention

[0006] According to an aspect of the invention, a method is provided, comprising: obtaining a first data stream corresponding to the concentration of an analyte in a biological fluid from an analyte sensor; converting the first data stream into an analyte value reflecting the concentration of the analyte; obtaining one or more additional data streams from one or more auxiliary sensors; inferring, based on the first data stream and one or more additional data streams, that the conversion of the first data stream to the analyte value is predicted to be inaccurate; and taking mitigation measures to avoid reporting inaccurate analyte values ​​to a user. Attached Figure Description

[0007] The embodiments will be readily understood from the following detailed description taken in conjunction with the accompanying drawings and claims. The embodiments are shown in the figures by way of example rather than limitation.

[0008] Figure 1 This is a schematic representation of an analytical material sensor system according to various embodiments;

[0009] Figure 2 This is a schematic representation of a networked continuous analyte monitoring (CAM) system used for implementing the methods disclosed herein;

[0010] Figure 3 High-level example methods for controlling the operation of a continuous analyte monitoring system according to various embodiments are shown;

[0011] Figure 4 A high-level example processing flow is shown for estimating analyte concentrations based on one or more of the analyte sensor, one or more auxiliary sensors, and / or other relevant historical data.

[0012] Figure 5 The physical location of the analyte sensor and its proximity to one or more auxiliary sensors on the user's body are shown.

[0013] Figure 6 An example timeline is depicted illustrating the control of actuators associated with a continuous glucose monitoring (CGM) system based on data obtained from one or more auxiliary sensors;

[0014] Figure 7 Advanced example methods for improving data quality in continuous analyte monitoring systems, according to various embodiments, are illustrated.

[0015] Figure 8 An example timeline is depicted illustrating the control of actuators associated with a CGM system based on data obtained from an accelerometer positioned at a predetermined distance from a continuous glucose sensor; and

[0016] Figures 9A to 9B It is shown in the first 24-hour period ( Figure 9A ) and the second 24-hour period ( Figure 9B A graph showing the combination of data obtained from the analyte sensor, temperature sensor, and accelerometer. Detailed Implementation

[0017] In the following detailed description, reference is made to the accompanying drawings, which form a part of this detailed description, and practical embodiments are illustrated in the drawings by way of illustration. It should be understood that other embodiments may be utilized and structural or logical changes may be made without departing from the scope of this description. Therefore, the following detailed description should not be construed as limiting.

[0018] Various operations can be described sequentially as a plurality of discrete operations in a manner that aids in understanding the implementation; however, the order of description should not be interpreted as implying that these operations are sequentially related.

[0019] Descriptions may use perspective-based descriptions, such as top / bottom, back / front, and top / bottom. Such descriptions are used only to facilitate discussion and are not intended to limit the application of the disclosed embodiments.

[0020] The terms “coupled” and “connected”, as well as their derivatives, may be used. It should be understood that these terms are not intended to be synonyms. Rather, in certain implementations, “connected” can be used to indicate that two or more elements are in direct physical or electrical contact with each other. “Coupled” can mean that two or more elements are in direct physical or electrical contact. However, “coupled” can also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0021] For descriptive purposes, the phrase “A / B” or “A and / or B” means (A), (B), or (A and B). For descriptive purposes, the phrase “at least one of A, B, and C” means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C). For descriptive purposes, the phrase “(A)B” means (B) or (AB), i.e., A is an optional element.

[0022] The description may use the terms "implementation" or "multiple implementations," which may each refer to one or more of the same or different implementations. Furthermore, terms such as "comprising," "including," "having," etc., used with respect to implementations are synonyms and are generally intended as "open" terms (e.g., the term "comprising" should be interpreted as "including but not limited to," the term "having" should be interpreted as "at least having," the term "including" should be interpreted as "including but not limited to," etc.).

[0023] Regarding the use of any plural and / or singular terms in this document, those skilled in the art can translate them from plural to singular and / or from singular to plural depending on the context and / or application. For clarity, various singular / plural permutations may be explicitly stated herein.

[0024] I. Overview of Several Implementation Methods

[0025] In one aspect, a method includes: obtaining a first data stream corresponding to the concentration of an analyte in a biological fluid from an analyte sensor; converting the first data stream into an analyte value reflecting the concentration of the analyte; obtaining one or more additional data streams from one or more auxiliary sensors; inferring, based on the first data stream and one or more additional data streams, that the conversion from the first data stream to the analyte value is predicted to be inaccurate; and taking mitigation measures to avoid reporting inaccurate analyte values ​​to a user. The one or more auxiliary sensors may be selected from pressure sensors, temperature sensors, accelerometers, and heart rate sensors.

[0026] In an implementation of this method, inferring that the prediction of an inaccurate transformation from the first data stream to the analyte value also includes comparing the first data stream and one or more additional data streams with a historical dataset. This historical dataset can be computationally processed to reveal data patterns corresponding to the analyte and auxiliary sensor data streams that indicate inaccurate transformations of the acquired data to the analyte value. In one example, computationally processing the historical dataset may further include performing one or more computational operations selected from supervised learning, unsupervised learning, and reinforcement learning on the historical dataset.

[0027] In an implementation of the method, mitigation measures may further include: applying a correction factor to a function that converts the first data stream into analyte values; and reporting the corrected analyte values ​​to the user. In an example, reporting the corrected analyte values ​​to the user may further include providing the user with an indication of the confidence level of the corrected analyte values.

[0028] In an embodiment of the method, the method may further include: preventing an alarm associated with the analyte sensor from being activated when the calibrated analyte value does not exceed one or more predetermined analyte value thresholds.

[0029] In an implementation of the method, mitigation measures may further include: alerting the user that the current analytical value is inaccurate; and providing the user with a request to obtain the analytical value via another method that does not involve the analytical sensor.

[0030] In an embodiment of this method, the analyte sensor is a continuous analyte sensor implanted in the user's skin. In one example, the analyte may be blood glucose. In such an example, the continuous analyte sensor may include a membrane system, defined herein as a permeable or semipermeable membrane, which may include two or more domains made of a material typically a few micrometers thick or greater (or smaller in some examples). At least a portion of the membrane is permeable to oxygen and optionally permeable to blood glucose. In one example, the membrane system includes a fixed glucose oxidase capable of undergoing an electrochemical reaction to measure blood glucose concentration.

[0031] In another aspect, a method for controlling an actuator associated with a continuous glucose sensor system is disclosed. The method may include: 1) predicting that the conversion of a raw data stream obtained from a continuous glucose sensor implanted in the user's skin is expected to result in an inaccurate glucose value report that does not represent the actual glucose concentration detected by the continuous glucose sensor; 2) applying a correction factor to a function that converts the raw data stream into a glucose value to obtain a corrected glucose value that more accurately reflects the actual glucose concentration sensed by the continuous glucose sensor within a predetermined error range; 3) controlling the actuator in a first mode when the corrected glucose value does not exceed one or more predetermined glucose value thresholds; and 4) controlling the actuator in a second mode when the corrected glucose value exceeds at least one of the predetermined glucose value thresholds.

[0032] In an implementation of this method, the actuator may be an auditory and / or vibratory alarm. Controlling the alarm in a first mode may include preventing the alarm from being activated. Controlling the alarm in a second mode may include activating the alarm to alert the user to a hypoglycemic or hyperglycemic event.

[0033] In another embodiment of the method, the actuator may be an insulin pump operatively coupled to a continuous glucose sensor system and capable of delivering variable amounts of insulin to the user based on a determined glucose level. In such an example, controlling the insulin pump in a first mode may include keeping the insulin pump off. Controlling the insulin pump in a second mode may include activating the insulin pump based on the degree to which a calibrated glucose level exceeds one of predetermined glucose level thresholds corresponding to a hyperglycemic event.

[0034] In an implementation of this method, the prediction is based at least in part on: 1) data currently acquired from the continuous glucose sensor and at least one auxiliary sensor; and 2) correlation data between the data currently acquired from both the continuous glucose sensor and at least one auxiliary sensor and previously acquired data, said previously acquired data including data acquired from at least one auxiliary sensor and the continuous glucose sensor, or other similar auxiliary sensors and continuous glucose sensors used in previous sensor phases. In one such example, one or more auxiliary sensors may include a pressure sensor, a temperature sensor, and an accelerometer. In the example, each of one or more auxiliary sensors and the continuous glucose sensor is located within the same region defined by a radius R on the user. In the example, the radius R may be 2 cm or less. In some examples, the method may also include processing the previously acquired data via a computational strategy capable of learning when a particular continuous glucose sensor data trend, combined with a particular auxiliary sensor data trend, leads to inaccurate glucose values ​​without a correction factor.

[0035] In embodiments of the method, the method further includes providing a confidence level reflecting the corrected blood glucose value. In some examples, the method includes adjusting one or more predetermined blood glucose value thresholds based on the confidence level of the corrected blood glucose value. For example, one or more thresholds may be adjusted to a larger extent when the confidence level is low, and to a smaller extent when the confidence level is high. In examples, adjusting one or more thresholds includes adjusting one or more thresholds to a more conservative threshold (e.g., lowering the threshold that could trigger an alarm based on a determined analyte concentration).

[0036] In another aspect, a blood glucose sensor system is disclosed herein. This blood glucose sensor system may include: a continuous blood glucose sensor for interstitial implantation in a user's skin; one or more auxiliary sensors selected from pressure sensors, temperature sensors, accelerometers, and heart rate sensors; and one or more actuable components. The system may further include a computing device storing instructions in a non-transitory memory, which, when executed, cause the computing device to: retrieve a first data stream from a continuous glucose sensor; retrieve one or more additional data streams from one or more auxiliary sensors; compare the first data stream and one or more additional data streams with a historical dataset including a learned association pattern of data corresponding to data previously acquired from the continuous glucose sensor and one or more auxiliary sensors, wherein the learned association pattern is related to situations where the conversion of the first data stream to a glucose value results in a glucose value that does not reflect the actual glucose concentration measured via the continuous glucose sensor; predict, based on the comparison, that the conversion of the first data stream to a glucose value is expected to result in a glucose value that does not reflect the actual glucose concentration measured via the continuous glucose sensor; initiate a compensation operation to generate a corrected glucose value that reflects the actual glucose concentration within a certain error range; and, if the compensation operation is able to generate a corrected glucose value that reflects the actual glucose concentration within the error range, control at least one of one or more actuable components based on the corrected glucose value.

[0037] In one implementation, the system may further include a display operatively linked to a computing device. In such an example, the computing device may store additional instructions to send a corrected blood glucose value, along with an indication that the value corresponds to a corrected blood glucose value, to the display device for viewing by a user. In this example, the indication that the value corresponds to a corrected blood glucose value includes one or more of the following: displaying the corrected blood glucose value in a flashing manner opposite to a stable mode; displaying the corrected blood glucose value in a color different from the color used when displaying an uncorrected blood glucose value; and displaying, along with the corrected blood glucose value, a message providing the user with information indicating that the displayed value corresponds to a corrected blood glucose value.

[0038] In one implementation of the system, the computing device stores additional instructions to prevent the calibration operation from being initiated during the time frame in which the first data stream is converted into a corrected blood glucose value via a compensation operation. The computing device may also store additional instructions to reschedule the calibration operation at a different time if the calibration operation was scheduled to occur during the time frame in which the first data stream is converted into a corrected blood glucose value.

[0039] In an implementation of the system, the computing device stores additional instructions to: assign confidence levels to the calibrated blood glucose values; and to control at least one of one or more actuable components, in part based on the confidence levels assigned to the calibrated blood glucose values.

[0040] In an implementation of this system, the actuable component may be an auditory and / or vibratory alarm configured to alert the user to biological events related to blood glucose levels. In such an example, the computing device may store additional instructions to prevent the alarm from being activated if the calibrated blood glucose value does not exceed one or more predetermined blood glucose value thresholds; and to activate the alarm in response to the calibrated blood glucose value exceeding one or more predetermined blood glucose value thresholds for a predetermined amount of time.

[0041] In an implementation of this system, the actuable component may be an insulin pump operatively linked to a computing device. In such an example, the computing device may store additional instructions to prevent the insulin pump from being activated if the calibrated blood glucose level does not exceed a hyperglycemic threshold; and to activate the insulin pump according to the stored instructions in response to the calibrated blood glucose level exceeding the hyperglycemic threshold for a predetermined amount of time.

[0042] In another embodiment of the system, the computing device stores additional instructions to compare a first data stream and one or more additional data streams with a historical dataset, wherein the historical dataset also includes learned correlation patterns of the data. The learned correlation patterns of the data can be correlated with blood glucose values ​​that, when the conversion of the first data stream to a blood glucose value results in a blood glucose value that accurately reflects the actual blood glucose concentration measured via a continuous glucose sensor. In such an example, the system can control at least one of one or more actuable components based on an uncorrected blood glucose value, provided that the prediction that the uncorrected blood glucose value reflects the actual blood glucose concentration is accurate.

[0043] In another aspect, a method for a continuous analyte sensor system includes: determining, based on a first data stream retrieved from a continuous analyte sensor and at least a second data stream retrieved from an auxiliary sensor, that a user of the continuous analyte sensor system has adopted a posture that causes the first data stream to inaccurately reflect the concentration of an analyte sensed by the continuous analyte sensor; providing, at least based on the first and second data streams, a compensated analyte value that accurately reflects the concentration of the analyte sensed by the continuous analyte sensor during the time period in which the user is adopting the posture; and controlling at least one actuator of the continuous analyte sensor system based on the compensated analyte value during the time period in which the user is adopting the posture.

[0044] In some implementations of this method, the auxiliary sensor is an accelerometer. In some examples, the accelerometer may include a chip (electronic chip) attached to a transmitter board circuit, which is included in a housing worn on the user's skin and located on top of the position where the continuous analyte sensor is inserted into the user's skin.

[0045] In implementations of this method, the auxiliary sensors include one or more pressure sensors. In some examples, one or more pressure sensors are coupled to an adhesive patch for securing the housing to the user's skin, and the housing is positioned on top of the location where the continuous analyte sensor is inserted into the user's skin.

[0046] In an embodiment of the method, the method may further include detecting, at least based on a first data stream and a second data stream, that the user is no longer taking the gesture. In response, the method may include providing an uncompensated analyte value that accurately reflects the concentration of the analyte sensed by the continuous analyte sensor.

[0047] In embodiments of the method, at least one actuator may include an alarm configured to alert a user to an adverse event related to the blood level of the analyte. In some examples, the method may also include preventing the alarm from notifying the user of an adverse event if the compensated analyte value does not exceed one or more predetermined analyte value thresholds.

[0048] In an implementation of this method, the analyte is blood glucose; and the continuous analyte sensor system is a continuous blood glucose monitoring system.

[0049] In an implementation of the method, the method may further include retrieving data from an auxiliary sensor at intervals between 10 and 20 seconds.

[0050] In another aspect, a method for a continuous analyte sensor system includes: retrieving a first data stream corresponding to a current reflecting the concentration of an analyte sensed by the continuous analyte sensor; converting the first data stream into an analyte value reflecting the concentration of the analyte sensed by the continuous analyte sensor; retrieving one or more additional data streams from one or more additional temperature sensors located within a predetermined distance of the continuous analyte sensor; determining, based on the one or more additional data streams, that the conversion of the first data stream is predicted to cause the analyte value to inaccurately reflect the concentration of the analyte sensed by the continuous analyte sensor; and providing, based on the one or more additional data streams, a compensated analyte value that more accurately reflects the concentration of the analyte within a predetermined threshold range of the concentration of the analyte sensed by the continuous analyte sensor.

[0051] In one embodiment of the method, one or more additional data streams may include a second data stream retrieved from a first temperature sensor positioned on a transmitter plate contained within a housing as part of a continuous analyte sensor system. The housing is configured to attach to a user's skin and is positioned on top of the continuous analyte sensor when it is inserted into the user's skin. In such an embodiment, providing compensated analyte values ​​may include utilizing characteristic temperature sensitivity of one or more temperature-sensitive electronic components that can adversely affect the first data stream and temperature values ​​corresponding to the second data stream in a model, which then outputs compensated analyte values.

[0052] In one embodiment of the method, one or more additional data streams may include a third data stream retrieved from a second temperature sensor positioned on the surface of the skin, within a predetermined distance of the continuous analyte sensor. In such an embodiment, providing compensated analyte values ​​may include incorporating a user-specific lag time into the model of the output compensated analyte value, the user-specific lag time corresponding to the time delay between when the plasma analyte value is reflected in an equivalent change in the interstitial fluid analyte level, the user-specific lag time being a function of the temperature value corresponding to the third data stream.

[0053] In one embodiment of the method, one or more additional data streams may include a fourth data stream retrieved from a third temperature sensor located on a portion of a continuous analyte sensor inserted into the user's skin. In such an embodiment, providing a compensated analyte value may include relying on the fourth data stream to infer the diffusion rate of the analyte into the sensor, and incorporating the inferred diffusion rate into a model that outputs the compensated analyte value.

[0054] In an implementation of this method, the analyte is blood glucose; and the continuous analyte system is a continuous blood glucose monitoring system.

[0055] In one or more or all embodiments of the method, the compensated analytical values ​​are provided at least in part based on the current corresponding to the first data stream.

[0056] In an implementation of this method, the predetermined distance is 2 cm or less.

[0057] In another aspect, a method for a continuous analyte sensor system includes: retrieving a first data stream from a continuous analyte sensor configured to sense the concentration of an analyte in a user's interstitial fluid; retrieving one or more additional data streams from one or more auxiliary sensors located within a predetermined distance from the continuous analyte sensor; comparing the first data stream and the additional data streams with a historical dataset that has been computationally processed to reveal data patterns corresponding to the first data stream and the additional data streams that indicate future events related to blood analyte levels; and providing the user with an alert that the future events are predicted to occur within a defined timeframe.

[0058] In this implementation of the method, the analyte is blood glucose; and the continuous analyte system is a continuous blood glucose monitoring system. In such an implementation, the future event can be either a hypoglycemic event or a hyperglycemic event.

[0059] In an implementation of this method, the determined time range can be between 30 minutes and 90 minutes.

[0060] In an implementation of this method, one or more auxiliary sensors may be selected from accelerometers, one or more temperature sensors, one or more pressure sensors, heart rate sensors, and blood pressure sensors.

[0061] These and other aspects of this disclosure will become more apparent after reading the following description.

[0062] II. Terminology

[0063] To facilitate understanding of the embodiments disclosed herein, a number of terms are defined below.

[0064] As used herein, the term "analyte" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, substances (e.g., chemical components) in biological fluids (e.g., blood, interstitial fluid, cerebrospinal fluid, lymph, urine, etc.) that can be analyzed (e.g., based on concentration per specific volume). Analytes can be naturally occurring, inherently artificial, metabolites, reaction products, etc. In a preferred embodiment, the analyte measured by the systems and methods of this disclosure is blood glucose. However, it is understood that the systems and methods disclosed herein are applicable to other analytes, including but not limited to: albumin, alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, bilirubin, blood urea nitrogen, calcium, CO2, chloride, creatinine, blood glucose, gamma-glutamyl transferase, hematocrit, lactate, lactate dehydrogenase, magnesium, oxygen, pH, phosphorus, potassium, sodium, total protein, uric acid, metabolic markers, acetaminophen, dopamine, terbutaline, ascorbate, uric acid, oxygen, d-amino acid oxidase, plasma amine oxidase, xanthine oxidase, NADPH oxidase, ethanol oxidase, and ethanol. Dehydrogenase, pyruvate dehydrogenase, glycol, Ros, NO, bilirubin, cholesterol, triglycerides, gentianic acid, ibuprofen, levodopa, methyldopa, salicylates, tetracycline, sulfamethoxazole, tolbutamide, prothrombin; acylcarnitine; adenine phosphoribosyltransferase; adenosine deaminase; albumin; alpha-fetoprotein; amino acid profile (arginine (Krebs cycle), histidine / uric acid, homocysteine, phenylalanine / tyrosine, tryptophan); androstenedione; antipyrine; arabinoyl alcohol enantiomers; arginase; biotinylate; biopterin; C-reactive protein; carnitine; carnosinase; CD4+ 4; ceruloplasmin; chenodeoxycholic acid; chloroquine; cholesterol; cholinesterase; conjugated 1-β-hydroxycholic acid; cortisol; creatine kinase; creatine kinase MM isoenzyme; cyclosporine A; d-penicillamine; deethylchloroquine; dehydroepiandrosterone sulfate; DNA (acetylation polymorphism, alcohol dehydrogenase, α1-antitrypsin, cystic fibrosis, Doppler / Beck muscular dystrophy, glucose 6-phosphate dehydrogenase, hemoglobin A, hemoglobin S, hemoglobin C, hemoglobin D, hemoglobin E, hemoglobin F, Punjab hemoglobin D, β-thalassemia, hepatitis B virus, HCMV, HIV-1, HTL V-1, Leber's hereditary optic neuropathy, MCAD, RNA, PKU, Plasmodium vivax, sexual differentiation, 21-deoxycortisol); debutylhalogenated pan-group; dihydropteridine reductase; diphtheria / tetanus antitoxin; erythrocyte arginase; erythrocyte proporphyrin; esterase D; fatty acid / acylglycine; free β-human chorionic gonadotropin; free erythrocyte porphyrin; free thyroxine (FT4); free triiodothyronine (FT3); corydaline acetylacetase; galactose / gal-1-phosphate; galactose-1-phosphate uridine transferase; gentamicin; glucose-6-phosphate dehydrogenase;Glutathione; Glutathione peroxidase; Glycinecholic acid; Glycosylated hemoglobin; Halopanatin; Hemoglobin variants; Hexosaminease A; Human erythrocyte carbonic anhydrase I; 17-α-hydroxyprogesterone; Hypoxanthine phosphoribosyltransferase; Immunoreactive trypsin; Lactate; Lead; Lipoproteins ((a), B / A-1, β); Lysozyme; Mefloquine; Netilmicin; Phenobarbital; Phenol; Phytanic acid / Tetradecanoic acid; Progesterone; Prolactin; Prolyase; Purine nucleoside phosphorylase; Quinine; Reverse triiodothyronine (rT3); Selenium; Serum pancreatic lipase; Sisomicin; Auxin C; Specific antibodies (Adenovirus, Antinuclear antibody, Antizeta antibody, Arbovirus, Oyesky virus, Dengue virus, Draconis mesenae, Echinococcus granulosus, Entamoeba histolytica, Enterovirus, Giardia lamblia, Helicobacter pylori, Type B) Hepatitis viruses, herpesviruses, HIV-1, IgE (atopic diseases), influenza viruses, Donovani Leishmania, Leptospira, measles / mumps / rubella, Mycobacterium leprae, Mycoplasma pneumoniae, myoglobin, Onchocerca salina, parainfluenza virus, Plasmodium falciparum, poliovirus, Pseudomonas aeruginosa, respiratory syncytial virus, Rickettsia (typhus), Schistosoma mansoni, Toxoplasma gondii, Treponema pallidum, Trypanosoma krusei / Langelly, vesicular stomatitis virus, Bancroftian virus, yellow fever virus; specific antigens (hepatitis B virus, HIV-1); succinylacetone; sulfadoxine; theophylline; thyroid-stimulating hormone (TSH); thyroxine (T4); thyroxine-binding globulin; trace elements; transferrin; UDP-galactose-4-epimerase; urea; uroporphyrinogen I synthase; vitamin A; leukocytes; and zinc protoporphyrin. In some embodiments, salts, sugars, proteins, fats, vitamins, and hormones naturally present in blood or interstitial fluid can also constitute the analyte. The analyte can be naturally present in biological fluids such as metabolites, hormones, antigens, antibodies, etc.

[0065] Alternatively, analytes may be introduced into the body, such as contrast agents for imaging, radioactive isotopes, chemical reagents, synthetic blood based on fluorocarbons, or drugs or pharmaceutical compositions, including but not limited to: insulin; ethanol; inhalants (nitrous oxide, amyl nitrite, butyl nitrite, chlorinated hydrocarbons, hydrocarbons); sedatives (barbiturates, methylquinolones, sedatives such as diazepam, nitrazepam, methylphenidate, oxazepam, methylbutazone, sanofi); hallucinogens (phencyclidine, lysergic acid, mescaline, cactus extract, psilocybin); anabolic steroids; and nicotine. Metabolites of drugs and pharmaceutical compositions are also considered analytes. It can also analyze analytes produced in the body, such as neurochemicals and other chemicals, such as ascorbic acid, uric acid, dopamine, norepinephrine, 3-methoxytyramine (3MT), 3,4-dihydroxyphenylacetic acid (DOPAC), homovanillic acid (HVA), serotonin (5HT), histamine, advanced glycation end products (AGEs), and 5-hydroxyindoleacetic acid (FHIAA).

[0066] As used herein, the terms “continuous analyte sensor” and “continuous glucose sensor” (also referred to as “continuous analyte monitor” or “continuous glucose monitor”) shall be given their common and customary meaning to those skilled in the art, and refer to, but not limited to, devices that continuously or persistently measure analyte / glucose concentrations and / or calibration devices at time intervals ranging from fractions of a second to, for example, 1 minute, 2 minutes, or 5 minutes or longer.

[0067] As used herein, the term “biological sample” will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, samples derived from the body or tissues of a host, such as, but not limited to, blood, interstitial fluid, cerebrospinal fluid, saliva, urine, tears, sweat, etc.

[0068] As used herein, the term “host” will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, animals, such as humans.

[0069] As used herein, the term “substantially” will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, the term “substantially” but not necessarily exactly as specified.

[0070] As used herein, the term “about” will be given its common and customary meaning to those skilled in the art, and when associated with any numerical value or range, it refers to, but is not limited to, the following understanding: that the amount or condition of a modification of a term may vary slightly beyond the specified amount, provided that the function of this disclosure is achieved.

[0071] As used herein, the terms “raw data stream” and “data stream” shall be given their common and customary meanings to those skilled in the art and refer to, but not limited to, analog or digital signals directly related to the concentration of an analyte measured by an analyte sensor. In one example, a data stream is digital data in units of counts converted from an analog signal (e.g., voltage or ampere) representing the concentration of the analyte by an analog-to-digital (A / D) converter. The term broadly covers multiple time-interval data points from a substantially continuous analyte sensor, including individual measurements taken at time intervals ranging from fractions of a second to, for example, one minute, two minutes, or five minutes or longer. As used herein, “acquiring a data stream” and “retrieving a data stream” refer to the process of acquiring a data stream from a sensor via a computing device (e.g., a computer) in a manner as disclosed herein, such that the data stream can be further processed, analyzed, visualized, etc.

[0072] As used herein, the term “number” will be given its common and customary meaning to those skilled in the art and is not limited to units of measurement for digital signals. In one example, a raw data stream measured in numbers is directly related to a voltage (e.g., the voltage converted by an A / D converter), which is directly related to the current from the working electrodes.

[0073] As used herein, the term "filter" or "filtering" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, modifying a set of data to make it smoother and more continuous and to remove or reduce outliers, for example, by performing a moving average on the original data stream. In the example, filtering refers to Kalman filtering, also known as linear quadratic estimation (LQE), which relies on a Kalman filter that operates in processes including: generating estimates of the current state variables (along with their uncertainties); observing subsequent measurements (which necessarily include a certain amount of error, said amount of error including random noise); and updating the estimates using a weighted average, where estimates with higher certainty are given greater weight.

[0074] As used herein, the term "algorithm" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, computational processing (e.g., a program) involved in, for example, using computer processing to transform information from one state to another. As used herein, "adaptive algorithm" or "learning algorithm" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, algorithms that can be trained on user-specific data (e.g., current and / or historical user-specific data). Adaptive algorithms can be used to ensure that: conditioning a particular dataset reflects the physiological conditions and / or known environmental conditions of a particular user.

[0075] As used herein, the term "adjunctive sensor" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, one or more sensors capable of acquiring data potentially related to data retrieved from the analyte sensor, such as sensors capable of retrieving information related to physiological and / or environmental conditions that may potentially affect (positively or negatively) the information acquired by the analyte sensor. Examples of adjunctive sensors relating to this disclosure include, but are not limited to, temperature sensors, accelerometers, pressure sensors, heart rate monitors, blood pressure monitors, etc. As used herein, the terms "adjunct sensor data" or "adjunctive sensor data" will be given its common and conventional meaning to those skilled in the art, and refer to, but is not limited to, any type of data / information that can be acquired via an adjunctive sensor. As used herein, the term "adjunctive data" need not be limited to the adjunctive sensor, but may include any readily available adjunctive data related to one or more operational aspects of the analyte sensor. Examples of ancillary data may include, but are not limited to, the impedance or conductivity of the user's tissue and other parameters related to the analyte sensor (e.g., the impedance of the analyte sensor itself). Since the analyte sensor analyte values ​​are related to factors such as the impedance and conductivity of the user's tissue, evaluating these factors can help correct for the analyte values ​​displayed by the system disclosed herein.

[0076] As used herein, the term "sensor electronics" will be given its common and customary meaning to those skilled in the art and refers to, but not limited to, components (e.g., hardware or software) of a computing device configured to process data. For example, in the case of an analyte sensor, the data may include biological information about the concentration of the analyte in a biological fluid obtained by the sensor.

[0077] As used herein, the term "operably connected" will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, linking one or more components to another in a manner that enables the transmission of signals between the components. For example, one or more electrodes may be used to detect the amount of blood glucose in a sample and convert that information into a signal. The signal can then be transmitted to electronic circuitry. In such an example, the electrodes are "operably linked" to electronic circuitry. These terms are broad enough to include both wired and wireless connections.

[0078] As used herein, the term "sensor data" will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, data received from sensors such as continuous analyzer sensors or auxiliary sensors in other examples. Such data may include sensor data points at one or more time intervals.

[0079] As used herein, the term "potentiostat" will be given its common and conventional meaning to those skilled in the art, and refers to, but is not limited to, an electrical system that applies a potential at a preset value between the working electrode and the reference electrode of a two- or three-electrode battery and measures the current flowing through the working electrode. Provided the required battery voltage and current do not exceed the potentiostat's compliance limits, the potentiostat forces any current to flow between the working electrode and the reverse electrode to maintain the desired potential.

[0080] As used herein, the term "calibration" will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, the process of determining the calibration of a sensor that provides a quantitative measurement (e.g., analyte concentration). As an example, calibration may be updated or recalibrated over time to account for changes associated with the sensor, such as variations in sensor sensitivity and sensor background. As used herein, the term "calibration" is not intended to be the same as "compensation" or "correction" for inaccurate analyte values. As used herein, the terms "compensation" or "correction" for inaccurate analyte values ​​will be given their common and customary meaning to those skilled in the art, and refer to the process of providing corrected analyte values ​​instead of reporting inaccurate analyte values, wherein the nature of the inaccurate analyte value is due to certain variables affecting the analyte sensor performance.

[0081] Compensating for or correcting inaccurate analyte values, compared to data quality without compensation or correction, broadly includes improving the data quality (e.g., reported analyte values) of the CAM system of this disclosure. For example, poor quality data may include reported analyte values ​​that are less accurate in terms of the actual concentration of the analyte sensed by a continuous analyte sensor, while higher quality data may include reported analyte values ​​that are more accurate in terms of the actual concentration of the analyte sensed by a continuous analyte sensor. Specifically, reported analyte values ​​with lower accuracy may differ significantly from the actual concentration of the analyte sensed by a continuous analyte sensor compared to reported analyte values ​​with higher accuracy.

[0082] As used herein, the term "inaccurate" with respect to reported analyte values ​​will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, a reported analyte value that differs from the actual analyte concentration sensed by a continuous analyte sensor by a predetermined threshold amount (e.g., an inaccurate analyte value could be a reported analyte value that exceeds a predetermined threshold range of the actual analyte concentration). Conversely, an accurate reported analyte value, as disclosed herein, refers to an analyte value that differs from the actual analyte concentration sensed by a continuous analyte sensor by no more than a predetermined threshold amount (e.g., an accurate analyte value could be a reported analyte value that does not exceed a predetermined threshold range of the actual analyte concentration). As used herein, the terms "inaccurate analyte value" or "inaccurate value" can also refer to an analyte value that, in the absence of variables affecting sensor performance, would otherwise be reported by exceeding a predetermined threshold amount (e.g., exceeding a threshold range). Such variables may include, but are not limited to, pressure changes near the analyte sensor, temperature changes near the analyte sensor, motion-induced artifacts, etc.

[0083] Examples of inaccurate analyte values ​​may be reported analyte values ​​that differ from the actual concentration of the analyte sensed by a continuous analyte sensor (or from a reported analyte value that would otherwise be reported in the absence of variables affecting sensor performance) by the following ranges: > 0.1%, > 0.5%, > 1%, or > 2%, or > 3%, or > 4%, or > 5%, or > 6%, or > 7%, or > 8%, or > 9%, or > 10%, or > 11%, or > 12%, or > 13%, or > 14%, or > 15%, or > 16%, or > 17%, or > 18%, or > 19%, or > 20%.

[0084] Examples of such variables affecting the performance of an analyte sensor may include, but are not limited to, temperature effects, pressure effects, motion effects, etc. As discussed herein, the process of providing corrected analyte values ​​involves learning situations / conditions in which inaccurate values ​​are expected or predicted to be reported; and providing corrected values ​​based on an analysis of a certain level of historical and / or current data trends (e.g., trends based on data retrieved from the analyte sensor and one or more auxiliary sensors) instead of reporting inaccurate values. For example, a sensor may be considered effectively calibrated, but a calibrated analyte sensor may still be prone to reporting inaccurate analyte values, depending on certain selection criteria disclosed herein. In such examples, reporting accurate analyte values ​​involves correcting or compensating for inaccurate values ​​and does not involve sensor calibration (or recalibration).

[0085] As used herein, the term “sensor phase” will be given its common and customary meaning to those skilled in the art, and refers to, but is not limited to, the time period during which a sensor is applied to (e.g., implanted) in the host or is being used to obtain sensor values. As an example, the sensor phase can extend from the time of sensor implantation (e.g., including inserting the sensor into subcutaneous tissue and establishing fluid communication between the sensor and the host's circulatory system) to the time when the sensor is removed.

[0086] III. Analyte Sensor System and Usage

[0087] Sensor system

[0088] Turning Figure 1 This diagram depicts a simplified representation of a sensor system 100 (e.g., a CGM system) including a computing device, such as computing device 110 (which can be any computing device, such as a stand-alone computing device), for estimating the concentration of an analyte (e.g., blood glucose) in the tissue of a subject, for example, based on an electrical signal, such as current, from an analyte sensor 150 (e.g., a blood glucose sensor) inserted into the tissue of the subject. The computing device 110 is broadly referred to herein as a sensor electronics device. Regarding... Figure 1In the remainder of the description, the analyte sensor 150 is referred to as glucose sensor 150, and the analyte is referred to as glucose. The system may include glucose sensor 150 and one or more auxiliary sensors such as accelerometer 160 and temperature sensor 170. In addition to the sensors shown, sensor system 100 may include one or more additional auxiliary sensors 180. Examples of additional sensors include a blood flow monitor based on optical assessment of the sensor area, which helps determine whether changes in blood flow around the sensor may result in a lower glucose diffusion rate at the sensor or may reduce available oxygen around the sensor. Other examples include, but are not limited to, heart rate monitors, blood pressure monitors, pressure sensors (e.g., potentiometric, inductive, capacitive, piezoelectric, strain gauge, variable magnetoresistive), etc.

[0089] In various embodiments, the computing device 110 includes several components, such as one or more processors 140 and at least one sensor communication module 142, which is capable of communicating with a blood glucose sensor 150, an accelerometer 160, and a temperature sensor 170 and / or one or more additional sensors 180, for example, via direct connection or via signals propagated through a transmitter and / or receiver. In various embodiments, each of the one or more processors 140 includes one or more processor cores. In various embodiments, at least one sensor communication module 142 is physically and electrically coupled to one or more processors 140. In various embodiments, at least one sensor communication module 142 is physically and / or electrically coupled to one or more sensors, such as a blood glucose sensor 150, an accelerometer 160, and a temperature sensor 170 and / or one or more additional sensors 180. In another implementation, the sensor communication module 142 is part of one or more processors 140. In various embodiments, the computing device 110 includes a printed circuit board (PCB) 155. In these implementations, one or more processors 140 and sensor communication modules 142 are disposed thereon. Depending on the application, the computing device 110 includes other components that may or may not be physically and electrically coupled to a PCB. These other components include, but are not limited to: a memory controller (not shown), volatile memory (e.g., dynamic random access memory (DRAM) (not shown), non-volatile memory such as read-only memory (ROM) (not shown), flash memory (not shown), I / O ports (not shown), (not shown), digital signal processor (not shown), cryptographic processor (not shown), graphics processor (not shown), one or more antennas (not shown), touchscreen display (not shown), touchscreen display controller (not shown), battery (not shown), audio codec (not shown), video codec (not shown), global positioning system (GPS) device (not shown), compass (not shown), accelerometer (not shown), gyroscope (not shown), (not shown), speaker (not shown), camera device (not shown), and mass storage devices (e.g., hard disk drive, solid-state drive, optical disc (CD) (not shown), digital versatile optical disc (DVD) (not shown), microphone (not shown), etc.

[0090] In some embodiments, one or more processors 140 are operatively coupled to system memory via one or more links (e.g., interconnects, buses, etc.). In these embodiments, the system memory is capable of storing information used by one or more processors 140 to operate and execute programs and operating systems, including computer-readable instructions for the methods disclosed herein. In different embodiments, the system memory is any available type of readable and writable memory, such as in the form of dynamic random access memory (DRAM). In these embodiments, the computing device 110 includes or is otherwise associated with various input and output / feedback devices to enable a user to interact with the computing device 110 and / or peripheral components or devices associated with the computing device 110 through one or more user interfaces or peripheral component interfaces. In these embodiments, the user interface includes, but is not limited to: a physical keyboard or keypad, a touchpad, a display device (touchscreen or non-touchscreen), a speaker, a microphone, sensors such as a blood glucose sensor 150, an accelerometer 160 and a temperature sensor and / or one or more additional sensors 180, haptic feedback devices and / or one or more actuators, etc.

[0091] In some embodiments, the computing device may include a memory element (not shown) that may reside within a removable smart chip or a secure digital (“SD”) card, or may be embedded within a fixed chip. In some example embodiments, a subscriber identity component (“SIM”) card may be used. In various embodiments, the memory element may allow software applications to reside on the device. In embodiments, the I / O link connecting the peripheral device to the computing device is protocol-specific, having a protocol-specific connector port that allows compatible peripheral devices to be attached to a protocol-specific connector port (i.e., a USB keyboard device would be plugged into a USB port, a router device into a LAN / Ethernet port, etc.) using a protocol-specific cable. Any single connector port will be limited to peripheral devices with compatible plugs and compatible protocols. Once a compatible peripheral device is plugged into a connector port, a communication link is established between the peripheral device and the protocol-specific controller.

[0092] In various implementations, non-protocol-specific connector ports are configured to couple I / O interconnects to the connector ports of computing device 110, thereby enabling multiple device types to be attached to computing device 110 via a single physical connector port. Furthermore, the I / O link between computing device 110 and the I / O complex is configured to simultaneously carry multiple I / O protocols (e.g., PCIExpress®, USB, DisplayPort, HDMI, etc.). In various implementations, the connector ports are capable of providing the full bandwidth of the link in both directions without sharing bandwidth between ports or between upstream and downstream directions. In various implementations, the connection between the I / O interconnects and computing device 110 supports electrical connections, optical connections, or both electrical and optical connections.

[0093] According to embodiments of this disclosure, in some embodiments, one or more processors 140, flash memory, and / or storage devices include associated firmware storing programming instructions configured to enable computing device 110 to implement all or selected aspects of a method for estimating blood glucose concentration in a subject's tissue by means of a sensor inserted into the subject's tissue in response to execution of the programming instructions by one or more processors.

[0094] In an implementation, the sensor communication module 142 is capable of wired and / or wireless communication to transmit data to and from the computing device 110, such as to one or more sensors (e.g., blood glucose sensor 150, accelerometer 160, and temperature sensor 170 and / or one or more additional sensors 180), transmitters, and / or transmitters / receivers coupled to (e.g., physically and / or electrically coupled to) one or more sensors such as blood glucose sensor 150, accelerometer 160, and temperature sensor 170 and / or one or more additional sensors 180.

[0095] In various embodiments, computing device 110 also includes a network interface configured to connect computing device 110 wirelessly and / or via a wired connection using a communication port to one or more network computing devices via a transmitter and receiver (or optionally a transceiver). In embodiments, the network interface and the transmitter / receiver and / or communication port are collectively referred to as a “communication module” (e.g., communication module 142). In embodiments, the wireless transmitter / receiver and / or transceiver may be configured to operate according to one or more wireless communication standards. The term “wireless” and its derivatives can be used to describe circuits, apparatus, systems, methods, techniques, communication channels, etc., that can transmit data through a non-solid medium using modulated electromagnetic radiation. This term does not imply that the associated devices do not contain any cables, although in some embodiments they may not contain any cables. In embodiments, computing device 110 includes a wireless communication module for sending and receiving data, such as for sending and receiving data from a network such as a telecommunications network. In the example, the communication module transmits data (including video data) via cellular or mobile networks such as: Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), cdmaOne, CDMA2000, Evolved Data Optimized (EV-DO), GSM Evolution Enhanced Data Rate (EDGE), Universal Mobile Telecommunications System (UMTS), Digital Enhanced Cordless Telecommunications (DECT), Digital AMPS (IS-136 / TDMA) and Integrated Digital Enhanced Network (iDEN), Long Term Evolution (LTE), 3G, 4G and / or 5G networks. In an implementation, computing device 110 is directly connected to one or more devices via a direct wireless connection using, for example, Bluetooth and / or BLE protocols, WiFi protocols, Infrared Data Association (IrDA) protocols, ANT and / or ANT+ protocols, LTE ProSe standards, etc. In implementations, the communication port is configured to operate according to one or more known wired communication protocols such as: serial communication protocols (e.g., Universal Serial Bus (USB), FireWire, Serial Digital Interface (SDI) and / or other similar serial communication protocols), parallel communication protocols (e.g., IEEE 1284, Computer Automatic Measurement and Control (CAMAC) and / or other similar parallel communication protocols) and / or network communication protocols (e.g., Ethernet, Token Ring, Fiber Distributed Data Interface (FDDI) and / or other similar network communication protocols).

[0096] In one embodiment, computing device 110 is configured to run, execute, or otherwise operate one or more applications, such as for estimating blood glucose concentrations in a subject's tissues. In another embodiment, applications include native applications, web applications, and hybrid applications. For example, a native application is used to operate computing device 110, sensors coupled to computing device 110, and other similar functions of computing device 110. In another embodiment, a native application is platform- or operating system (OS) specific or non-specific. In another embodiment, a native application is developed for a specific platform using platform-specific development tools, programming languages, etc. Such platform-specific development tools and / or programming languages ​​are provided by the platform vendor. In another embodiment, a native application is pre-installed on computing device 110 during manufacturing or provided to computing device 110 via a network by an application server. A web application is an application loaded into a web browser on computing device 110 in response to a request for a web application from a service provider. In another embodiment, a web application is a website designed or customized to run on the computing device by taking into account various computing device parameters such as resource availability, display size, touchscreen input, etc. In this way, a web application can provide an experience similar to a native application within a web browser. A web application can be any server-side application developed using any server-side development tools and / or programming languages ​​such as PHP, Node.js, ASP.NET, and / or any other similar technologies for rendering HTML. A hybrid application can be a combination of a native application and a web application. A hybrid application can be standalone, framework-based, or can load other similar application containers within an application container. Hybrid applications can be written using website development tools and / or programming languages ​​such as HTML5, CSS, JavaScript, etc.

[0097] In some implementations, the hybrid application uses the browser engine of computing device 110 instead of the web browser of computing device 110 to render the website's services locally. In some implementations, the hybrid application also accesses computing device capabilities not accessible in web applications, such as accelerometers, camera devices, local storage devices, etc. Any combination of one or more computer-usable or computer-readable media can be used with the implementations disclosed herein. Computer-usable or computer-readable media can be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, apparatuses, or propagation media. More specific examples of computer-readable media (a non-exhaustive list) will include the following: electrical connections with one or more cables, portable computer floppy disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage devices, transmission media such as transmission media supporting the Internet or intranet, or magnetic storage devices. Note that a computer-usable or computer-readable medium can even be paper or other suitable media on which a program is printed, because a program can be captured electronically via optical scanning of, for example, paper or other media, and then compiled, interpreted, or otherwise processed as appropriate, and then stored in computer memory. In the context of this document, a computer-usable or computer-readable medium can be any medium that can contain, store, transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-usable medium can include a propagated data signal containing computer-usable program code in baseband or as part of a carrier wave. Computer-usable program code can be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc.

[0098] Computer program code used to perform the operations of this disclosure can be written in any combination of one or more programming languages—including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computing device via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computing device (e.g., via the Internet provided by an Internet service provider) or a wireless network, as described above.

[0099] Furthermore, the example implementation can be carried out using hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware, or microcode, the program code or code segments used to perform the necessary tasks can be stored in a machine or computer-readable medium. Code segments can represent procedures, functions, subroutines, programs, routines, subroutines, modules, program code, software packages, classes, or any combination of instructions, data structures, program statements, etc.

[0100] In various embodiments, an article of manufacture may be employed to implement one or more methods disclosed herein. The article of manufacture may include a computer-readable non-transitory storage medium and a storage medium. According to embodiments of this disclosure, the storage medium may include programming instructions configured to enable a device to perform some or all aspects of a method for estimating blood glucose concentration in a subject's tissues using a computing device. The storage medium may represent a wide range of persistent storage media known in the art, including but not limited to flash memory, optical disks, or magnetic disks. In particular, the programming instructions may enable a device to perform various operations described herein in response to the device's execution of them. For example, according to embodiments of this disclosure, the storage medium may include programming instructions configured to enable a device to perform some or all aspects of a method for estimating blood glucose concentration in a subject's tissues using a computing device.

[0101] Networked Continuous Analyte Monitoring (CAM) System

[0102] Turning Figure 2 A networked CAM system 200 according to an embodiment herein is shown. The networked CAM system 200 includes a sensor system 100 in wireless (or wired) communication with it. For the corresponding Figure 2 The remainder of the description refers to the networked CAM system as a networked CGM system. The networked CGM system 200 also includes other networked devices 210 with which it can communicate via wired or wireless communication. In some embodiments, the sensor system 100 includes application software having executable instructions configured to transmit and receive information from and from the network 205. This information can be transmitted via the network to another device, such as one or more networked devices 210, and / or received via the network from another device, such as one or more networked devices 210. In some examples, the sensor system 100 is also capable of transmitting information about analyte measurements retrieved from one or more analyte sensors (e.g., 150) to one or more physicians or other healthcare practitioners.

[0103] like Figure 2As depicted, the CGM system 200 distributes information to and receives information from one or more networked devices 210 via one or more networks 205. According to various embodiments, network 205 can be any network enabling computers to exchange data, such as cloud-based storage for generated (historical and current) data and / or some, none, or even all, implementations of the methods disclosed herein. Figure 2 The image depicts database 280, which in some examples may include cloud-based data storage. In some embodiments, network 205 includes one or more network elements (not shown) capable of physically or logically connecting computers. Network 205 may include any suitable network, including intranets, the Internet, cellular networks, local area networks (LANs), wide area networks (WANs), personal networks, or any other such networks or combinations thereof. The components used for such a system may depend at least in part on the type of network and / or environment chosen. Protocols and components used for communication via such networks are well known and will not be discussed in detail herein. In embodiments, communication via network 205 is achieved through wired or wireless connections and combinations thereof. Each network 205 includes a wired or wireless telecommunications device through which the network system can transmit and exchange data. For example, each network 205 is implemented as or may be a subset of: Storage Area Network (SAN), Personal Area Network (PAN), Metropolitan Area Network (MAN), Local Area Network (LAN), Wide Area Network (WAN), Wireless Local Area Network (WLAN), Virtual Private Network (VPN), Intranet, Internet, Mobile phone networks such as Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), cdmaOne, CDMA2000, Evolved Data Optimized (EV-DO), GSM Evolution Enhanced Data Rate (EDGE), Universal Mobile Telecommunications System (UMTS), Digital Enhanced Cordless Telecommunications (DECT), Digital AMPS (IS-136 / TDMA) and Integrated Digital Enhanced Network (iDEN), Long Term Evolution (LTE), Third Generation Mobile Network (3G), Fourth Generation Mobile Network (4G), and / or Fifth Generation Mobile Network (5G) networks, Card Network, Bluetooth, Near Field Communication Network (NFC), any form of standardized radio frequency, or any combination thereof, or any other suitable architecture or system that facilitates the communication of signals, data, and / or messages (generally referred to as data). Throughout this specification, it should be understood that the terms “data” and “information” are used interchangeably herein to refer to text, images, audio, video, or any other form of information that may exist in a computer-based environment.

[0104] In an example implementation, each network system (including sensor system 100 and networked device 210) includes means having communication components capable of transmitting and / or receiving data via network 205. For example, networked device 210 may include a server, a personal computer, a mobile device (e.g., a laptop computer, tablet computer, netbook computer, personal digital assistant (PDA), video game device, GPS locator device, cellular phone, smartphone, or other mobile device), a television set in which one or more processors are embedded and / or coupled to it, or other suitable technologies including or coupled to a web browser or other applications for communicating via network 205.

[0105] In some embodiments where the CAM system 200 is configured as a CGM system, the system may include, in some examples, an insulin delivery unit 270. The insulin delivery unit 270 may consist of at least three parts, including but not limited to an insulin pump 271, tubing 272, and infusion device 273. In embodiments, the insulin pump 271 may be battery powered and may include (or be fluidly coupled to) an insulin reservoir (e.g., a container), a pumping mechanism (e.g., a pump driven by a small motor), and one or more buttons and / or a touchscreen (not shown) for programming insulin delivery. In some examples, the insulin pump 271 can be connected from a computing device 110 (see...). Figure 1 One of the networked devices 210 or 210 receives instructions for insulin delivery via network 205. These instructions may be based on the concentration of an analyte (e.g., blood glucose) obtained via sensor system 100. In such an example, it can be understood that insulin delivery unit 270 may be connected to other components of CGM system 200 (e.g., Figure 1 The computing device 110 and / or network device 210 operate in a closed-loop manner to mimic the function of the pancreas. It is understood that each of the insulin pump 271, tubing 272, and infusion device 273 can be coupled to each other to enable the insulin pump 271 to deliver insulin to the subject via tubing 272 and infusion device 273. While the insulin pump 271 can be battery powered, it is understood that in some additional or alternative examples, the insulin pump 271 can be powered by electrically coupling the insulin pump 271 to an external power source.

[0106] In some examples, insulin pump 271 may include buttons and / or a touchscreen (not shown) for programming insulin delivery parameters. In another additional or alternative example, as mentioned above, insulin pump 271 may receive instructions for insulin delivery via network 205. Therefore, in some examples, insulin pump 271 may include a communication module 276 (e.g., a receiver or transceiver) capable of receiving and / or transmitting information (wired or wirelessly) via network 205, printed circuit board 274, and microprocessor 275. Other components of insulin pump 271 (not shown) may include one or more of the following: memory controller, volatile memory (e.g., DRAM), non-volatile memory (e.g., ROM), flash memory, etc.

[0107] In some examples, tubing 272 may include a thin tube fluidly coupled to each of the insulin reservoir and infusion device 273. Tube 272 may be made of plastic, polytetrafluoroethylene (PTFE), etc. Infusion device 273 may include components made of PTFE and / or steel and may be attached to the subject's skin via an adhesive patch. Infusion device 273 may include a short thin tube (e.g., a cannula) inserted into the skin via a needle housed within a cannula. After insertion, the needle may be removed, and the thin cannula may remain under the skin. It is understood that the above description relates to an example infusion device, but other similar infusion devices may be used interchangeably without departing from the scope of this disclosure.

[0108] How to use

[0109] Turn now Figure 3 This describes various embodiments of a CAM system for controlling (e.g., Figure 2 A high-level example method for operating the CGM system 200. Method 300 may at least partially include storage on, for example, a computing device (e.g., Figure 1 The computing device 110 and / or Figure 2 Executable instructions on the memory of one or more networked devices 210. When executed, the instructions can cause changes in one or more operating states of the CGM system, such as physical changes in the manner of insulin delivery to the subject, changes in the manner of delivery from one or more analyte sensors (e.g., Figure 1 Analyte sensor 150) and / or one or more auxiliary sensors (e.g., Figure 1 Data obtained from the accelerometer 160 and temperature sensor 170 are used to estimate blood glucose levels, control alarms (e.g., auditory and / or vibration), and so on. The following description of method 300 is written for a CGM system, but it will be understood that the method is equally applicable to other CAM systems without departing from this disclosure.

[0110] At box 305, method 300 includes acquiring and processing historical data corresponding to one or more data streams related to the use of the CGM system. Historical data, as disclosed herein, refers to relevant data acquired and stored within a predetermined time period (e.g., 1 to 5 days, 5 to 10 days, 10 to 15 days, 15 to 30 days, 30 to 60 days, 60 to 120 days, 120 to 240 days, 240 to 365 days, or more). Relevant data includes any and all data that can be used to learn algorithms to correlate a specific data stream from the sensor or other acquired data / information (discussed below) with a time (e.g., a time period) that a blood glucose concentration estimate based on raw data acquired from the CGM sensor might be considered accurate or inaccurate. In implementations, this may not be as simple as "accurate" or "inaccurate," but may include confidence levels of the blood glucose concentration estimate (e.g., high confidence, medium confidence, low confidence). Learning algorithms, as disclosed herein, fall under, for example, artificial intelligence and encompass subsets thereof, including machine learning, deep learning, and neural networks.

[0111] Relevant data may include, but is not limited to: data from blood glucose sensors (e.g., Figure 1 Sensor data obtained from sensor 150 (or multiple blood glucose sensors in cases where historical data belongs to more than one sensor phase); sensor data obtained from one or more auxiliary sensors (e.g., Figure 1 Sensor data obtained from the accelerometer 160 and temperature sensor 170; actual blood glucose measurements obtained by pricking a finger and testing actual blood samples; and other physiological variables, including but not limited to heart rate patterns, blood pressure patterns, etc.

[0112] In some examples, the relevant data additionally or alternatively includes data provided by the user. For example, the data may be provided by the user via a user's computing device (e.g., Figure 2The data is provided by a software application running on a networked computing device 210, such as a smartphone. Such data may include, but is not limited to, information related to: when the user exercises (and the intensity of the exercise, such as light, moderate, or high intensity); the type of exercise (such as cardiovascular, strength training, walking, etc.); when the user is in a vehicle traveling to their destination; when the user sleeps; when the user sits / rests; when the user works; the type / quantity of food / meal or snack time; the time of day when the user takes prescription medications; the type and dosage of prescription medications taken by the user; the time of day when the user takes one or more supplements; the type and dosage of supplements taken by the user; the type of clothing the user is wearing (e.g., loose clothing, tight clothing, clothing that may create increased pressure near the blood glucose sensor, etc.); and any other variables that may be associated with how the CGM system and associated blood glucose sensors acquire and process information related to the blood glucose levels in the user's body.

[0113] In some examples, data may not be specifically entered by the user but can be inferred in other ways. For instance, a software application running on a user's computing device (e.g., a smartphone) can infer the user's current location (e.g., geolocation, proximity to a particular place / facility) and even what the user is currently doing (e.g., the likelihood / probability of the user engaging in a particular activity) from one or more other software applications. For example, a software application associated with a CGM system may be able to retrieve information stored on the user's device from one or more other applications to infer where the user is and what activity they are engaging in. In one example, a user might rely on a radio frequency identifier (RFID) stored on their device to enter a gym. An application associated with the CGM system can retrieve such information, along with other information such as current geolocation, to infer that the user is at the gym and may have been working out for some time. Another example includes indications of a user's location at a particular restaurant (e.g., retrieved from geolocation and / or social media platforms where the user has posted images or messages related to a particular dining experience). In some examples, this information might even include what type of food the user might be eating (if not specifically entered by the user). Examples include user instructions at ice cream shops (e.g., based on location tracking, credit card statements, etc.), rather than at health food locations.

[0114] The types of data discussed above can be, for example, in a database associated with the CGM system (e.g., Figure 2Data is obtained and stored in a database (280) at a specific location. In some examples, data may be obtained at regular intervals (e.g., every 1 to 60 seconds, every 1 to 5 minutes, every 5 to 10 minutes, every 10 to 20 minutes, every 20 to 30 minutes, every half hour to one hour, every 1 to 5 hours, every 5 to 10 hours, every 10 to 24 hours, every 24 hours to 2 days, etc.). For example, sensor data may be obtained more frequently than data related to user activity, dietary information, etc. The learning algorithm may reside on the user's computing device (e.g., ...). Figure 2 The algorithm can reside on the memory of the user device 210, or in some examples, in the cloud or in other similar databases that enable it to periodically perform operations to learn patterns from different types of data being acquired and stored for analysis.

[0115] As mentioned above, learning algorithms can operate on data acquired and stored for at least a predetermined period of time. In some implementations, data beyond the predetermined time period (and therefore patterns learned based on said data) can be periodically forgotten. In other implementations, such as incremental learning algorithms, the algorithm can adapt to newly acquired data without forgetting its existing knowledge. In one such example, the incremental learning algorithm may have some built-in parameters or assumptions controlling the relevance of older data.

[0116] As an example, the predetermined time amount involves a predetermined number of days, such as between 1 day and 365 days (e.g., between 1-2 days and 1 month, between 1-2 days and 2 months, between 1-2 days and 3 months, between 1-2 days and 4 months, between 1-2 days and 5 months, etc.). In another example, the predetermined time amount involves a predetermined number of sensor phases, such as between 1 and 50 sensor phases, where sensor phases occur at any time between 1 and 15 days, or even higher in some examples (e.g., 15 to 30 days). The predetermined time amount can include the amount of time it takes for the learning algorithm to reach a conclusion at a specific confidence level (e.g., medium to high confidence, or 7 to 10 confidence levels on a scale of 1 to 10, where lower numbers are associated with lower confidence). Such conclusions will be elaborated in more detail below, but relate to the ability to infer that CGM system blood glucose estimates are predicted as inaccurate, rather than other situations / conditions where CGM blood glucose estimates are predicted as accurate.

[0117] Incorrect blood glucose concentration estimates are a highly undesirable aspect of any CGM system, especially when paired with an insulin pump. Therefore, the ability to computationally learn and identify specific cases of inferring blood glucose concentration estimates based on historical data analysis represents an advantage that can be used to improve existing CGM systems, as elaborated in more detail below.

[0118] In implementation, historical data may not be limited to specific individuals but may include group-based data. As an example, data from at least two individuals, and in some examples, data from far more than two individuals (e.g., dozens, hundreds, or even thousands or more), can be fed into a learning algorithm to mine patterns in the group-based dataset. Such an approach can increase the confidence that a particular type of data can be associated with a specific event / condition. For example, this can enable the algorithm to infer patterns specific to a particular age group, gender, ethnicity, patterns specific to users using similar or identical medication regimens, patterns specific to users taking similar or identical supplements, patterns specific to geographic location (e.g., users might be more inclined to turn on their home heating in a colder climate compared to a milder climate), and so on.

[0119] Using the historical data acquired and processed at box 305, method 300 proceeds to box 310. At box 310, method 300 includes retrieving a data stream from a blood glucose sensor and retrieving one or more additional data streams from one or more auxiliary sensors. Although in Figure 3 While not explicitly shown, other types of data similar to those mentioned above as inputs to learning algorithms can be additionally obtained. For example, throughout a given day, raw data from a blood glucose sensor (e.g., current traces), raw data from other auxiliary sensors (e.g., data retrieved from an accelerometer, temperature sensor, pressure sensor, etc.), and other optional data inputs (e.g., data input by the user into the CGM software application, data retrieved by the CGM software application from one or more other software applications) can be obtained. Raw data streams from one or more sensors can be obtained at intervals of 1 to 2 milliseconds to 500 milliseconds, 500 milliseconds to 1 second, 1 second to 60 seconds, 1 minute to 5 minutes, 5 minutes to 10 minutes, etc. In some examples, the rate at which data is acquired from one sensor can differ from the rate at which data is acquired from another sensor. For example, data can be acquired from the CGM sensor every 30 seconds to 5 minutes, while data can be acquired from the temperature sensor at less frequent intervals (e.g., every 10 minutes to 20 minutes). It is understood that other data may be available where possible, such as data related to meal times and types of food consumed, which may only be available when the user inputs data into the CGM software application. Such examples are intended to be illustrative rather than limiting.

[0120] At box 315, method 300 includes monitoring events that are predicted / inferred to adversely affect the determination of CGM sensor blood glucose values, which have been learned via a learning algorithm based on historical data. Several examples of such events are now discussed. First, CGM sensors may be affected by pressure applied to the skin area to which they are attached. Pressure applied in such proximity can significantly affect the current transmitted via the CGM sensor to the sensor electronics, and therefore, the degraded signal may ultimately contribute to the degradation of the sensor's signal by the device (e.g., Figure 1 The computing device 110 or Figure 2 Any networked device (210) at the location could display an incorrect blood glucose value if the contributing event is not identified and, where possible, not compensated for. For example, a pressure change near the blood glucose sensor could cause the estimated blood glucose concentration to drop by as much as 80 mg / dL within just a few minutes. Of course, for blood glucose values ​​that are likely in the range of 90 mg / dL to 140 mg / dL, such a drop would be of great concern if it were indeed the case. Even for subjects with blood glucose values ​​exceeding the 140 mg / dL range, such a drop would still be of significant concern. In the example, this could lead the user to take unnecessary or even counterproductive actions to correct the situation, which in some cases could worsen the situation (e.g., ingesting blood glucose to compensate for a potentially hyperglycemic event).

[0121] The problem of pressure near the blood glucose sensor causing erroneous readings may be particularly relevant to sleep events. For example, a user of a CGM device may turn or roll over during sleep, in such a way that pressure is applied to the area of ​​the skin where the sensor is located. This pressure may cause changes in the raw data signal, which may then be reported as a drop in blood glucose concentration. Such a drop may trigger an alarm, which could unnecessarily wake the user, leading to an interrupted sleep pattern and potentially adversely exacerbating efforts to control blood glucose. Furthermore, similar to what has been discussed above, if the user interprets the alarm as indicating a genuine drop in blood glucose levels and takes compensatory actions, this could lead to undesirable consequences. In a closed-loop system, automatic interventions may occur, which could, of course, seriously impact the user's health. Other examples of pressure near the blood glucose sensor potentially causing reported lower blood glucose values ​​include, but are not limited to, situations where the user is wearing tight clothing (e.g., tight around the waist near the sensor) or when the user is fastening a seatbelt (e.g., in a car or airplane).

[0122] As another example, temperature variations near the CGM sensor can significantly impact sensor performance and, consequently, the reported blood glucose levels via the device. For instance, an increase in temperature might correspond to a corresponding increase in the amount of current transmitted to the sensor's electronics. Such an increase might be interpreted as an increase in blood glucose concentration and reported accordingly, even though the cause is not elevated blood glucose but rather a localized temperature rise. If this abnormal blood glucose reporting is not identified and compensated for where possible, it could lead the user to attempt to correct the problem by self-administering an insulin pill (or, in the case of a closed-loop CGM system, commanding the insulin pump to deliver the pill). In some examples, this could have the undesirable effect of significantly lowering blood glucose levels, thus risking the user entering a state of hypoglycemia. Furthermore, if the temperature rise occurs at night while the user is asleep, the abnormal increase in blood glucose could trigger an alarm, unintentionally waking the user and exacerbating blood glucose regulation problems in addition to other potential health effects caused by poor sleep quality.

[0123] As another example, blood glucose readings from a CGM device may become abnormal during periods of significant user activity. For instance, a data stream corresponding to user movement can be obtained via one or more accelerometers, preferably located close to the CGM sensor in the user's skin. Over time, specific movement patterns and / or the duration of said specific patterns can be learned and stored via a learning algorithm for comparison with the current level of activity. In this way, the CGM system can predict / infer when the user is engaging in activities that might lead to inaccurate blood glucose readings based on the learned movement patterns.

[0124] It is understandable that the process of learning various events / conditions in which blood glucose readings are expected to be accurate rather than inaccurate can rely on more than one type (e.g., multiple) of data. For example, to infer that a user is asleep, accelerometer data can be relied upon. If the accelerometer data shows little or no movement and the pressure data indicates a sudden or gradual increase, it can be inferred that the user is asleep and has rolled or turned to a location where a certain level of increased pressure is applied near the blood glucose sensor. In some examples, such a determination can additionally rely on data corresponding to heart rate, blood pressure, etc. In this way, the CGM system can increase the confidence in associating data with specific events.

[0125] As another example, one or more combinations of accelerometer data, heart rate data, blood pressure data, temperature data, and even other types of data can be used to infer that a user is exercising. When relying on combinations of data, it's even possible to learn what kind of exercise a user is engaging in. For example, learning patterns based on sensor data can infer whether a user is engaging in light exercise (e.g., walking) rather than higher-intensity exercise (e.g., running, swimming, etc.). Depending on the amount of data collected, the approximate duration of a user's participation in a particular activity can be predicted. For example, a user might go to the gym daily and engage in higher-intensity training during the first session on every other day, and lower-intensity training during the second session on other days. Such examples are meant to be illustrative.

[0126] The learning methods discussed in this paper can be understood as not relying on any actual blood glucose readings. Instead, the CGM system can accurately predict blood glucose values ​​during a specific period when the reported value has become incorrect, thus reporting a corrected value instead of an erroneous value, without requiring external input to the system regarding actual blood glucose measurements.

[0127] Therefore, at box 315, method 300 includes comparing the learned patterns of data obtained from the analysis of historical data with current datasets obtained from one or more sensors via the CGM system and / or data input via a CGM software application or otherwise obtained. Specifically, the comparison at box 315 may be able to determine whether the user is involved in some activity / situation in which CGM blood glucose readings may be inaccurate or may become inaccurate.

[0128] Therefore, at box 320, method 300 includes an indication of whether an adverse event has been identified, defined as a condition / situation / event where the reported CGM blood glucose reading is inaccurate or may become inaccurate. If no such event is identified, at box 325, method 300 continues to provide blood glucose readings without taking any compensatory measures (e.g., not correcting the reported blood glucose value). However, this does not mean that no measures can be taken at box 325. For example, certain operating parameters of the CGM system can be adjusted based on the data type and / or other auxiliary data retrieved from one or more sensors. As an example, in cases where the accelerometer data shows very little activity, filter parameters can be adjusted to allow the use of less averaging, and / or one or more settings associated with the Kalman filter can be changed. Other adjustments to operating parameters are within the scope of this disclosure. For example, in response to an indication that the user is sleeping, the rate of temperature or pressure readings can be increased, or in other examples decreased, in contrast to waking hours. Method 300 then continues to retrieve data from various sensor or other auxiliary data inputs and continues to monitor for events / situations where blood glucose values ​​may be inaccurate.

[0129] Returning to box 320, in response to the identification of an adverse event, method 300 proceeds to box 330. At box 330, method 300 includes determining whether the system can continue to provide accurate blood glucose values. Specifically, at box 330, method 300 determines whether the system has sufficient information (e.g., learned information) to report a corrected blood glucose value within an acceptable threshold of the actual blood glucose value. For example, a user may periodically turn over during sleep, causing pressure near the CGM sensor, resulting in inaccurate reported blood glucose values. This situation can be learned with high confidence over time, and in some examples, the algorithm may have sufficient information to infer what the reported blood glucose reading should actually be, and therefore can report a corrected value instead of an inaccurate value. If it is determined at box 335 that accurate values ​​can be provided, method 300 proceeds to box 335, where the corrected value is reported (e.g., displayed via CGM computing device 110 and / or via one or more other computing devices 210). This allows the CGM system to continue operating without triggering alarms (e.g., avoiding unnecessary user wake-ups) and prevents situations where the user or certain aspects of the CGM system (e.g., the insulin pump) take action based on inaccurate blood glucose values.

[0130] At box 335, in some examples, the system may provide some indication that the reported value includes a correction value, and therefore should be viewed with a degree of caution. For example, when displaying a correction value, the correction value may flash at a predetermined rate, as opposed to not flashing for an uncorrected value. In additional or alternative examples, an audible alarm may be triggered to indicate to the user that the reported value includes a correction value. In other examples, the alarm may include the reported correction value having a different color than the uncorrected value. Color options may be selected by the user, for example, based on preference. For example, blue or green may be used to report uncorrected values, and red may be used to report correction values. In some examples, the sensor system (e.g., Figure 1 Some aspect of the sensor system 100 or user computing device (e.g., networked device 210) may vibrate in a certain mode in response to a reported value including a correction value, and may vibrate in another certain mode when the reported value is no longer a correction value. Similarly, this feature may be user-defined.

[0131] In some examples of reported correction values, the system can provide some indication of the confidence level of the reported values. This can improve user satisfaction because they can avoid anxiety about whether the correction value might accurately reflect blood sugar levels. For example, different color schemes can be used to indicate high, medium, or low confidence levels of correction values. For instance, uncorrected values ​​could be blue, low-confidence correction values ​​could be red, medium-confidence correction values ​​could be yellow, and high-confidence correction values ​​could be green. Such examples are meant to be illustrative. In another additional or alternative example, wording can be displayed along with the reported values ​​to indicate that these values ​​are correction values ​​with a specific confidence level. The user can be alerted in some way (e.g., auditory, haptic, visual, etc.) that the reported values ​​include correction values, and then an additional layer of information about the confidence level of the correction values ​​can be conveyed to the user. In an example where the user is asleep, a reported correction value with medium or / or high confidence might prevent an alarm from triggering to wake the user, while a reported correction value with low confidence might trigger an alarm, informing the user of a potential adverse health condition.

[0132] In examples where the CGM system is operatively connected to an insulin pump, there may be situations where the insulin pump might continue operating with the calibration value, and other situations where it might be preferable to interrupt any closed-loop action (or any other aspect of closed-loop operation) involving control of the insulin pump based on the calibration analyte value. When establishing the calibration analyte value, in one example, closed-loop operation may be maintained at medium to high confidence, or in other examples, only at high confidence. If the calibration value is determined to have low confidence, or even in some examples, medium confidence, closed-loop operation may be interrupted so that the insulin pump is not triggered, for example, based on the calibration analyte value with low confidence.

[0133] Regarding low confidence values, the system can learn over time the factors that lead to low confidence values ​​in order to transform them into neutral or high confidence values. Specifically, the learning algorithm can be programmed to learn / evaluate what types of events lead to low confidence correction values, and based on other cases that report higher confidence correction values, the system can, over time, increase the confidence of correction values ​​reported for events previously associated with low-confidence corrected blood glucose values.

[0134] In response to the provision of a correction value, method 300 continues to box 340 and includes updating the CGM system parameters based on the event that led to the provision of the correction value. Updating the CGM system parameters may include, but is not limited to: storing additional data retrieved from any blood glucose and / or auxiliary sensors; storing an indication that a correction value will be provided for a specific duration; storing any actual blood glucose values ​​input into the system during and / or after the event that displays the correction value; updating any relevant filter parameters (e.g., filter parameters may be changed during a specific adverse event and then changed back or otherwise updated after the event has passed). It is understood that any and all updates to the CGM system parameters mentioned above may include feeding data back into the learning algorithm to enable the algorithm to continuously improve its ability to accurately assess situations where reported blood glucose values ​​may be inaccurate, and, where possible, to provide corrected blood glucose values ​​with increasing confidence.

[0135] Returning to box 330, this paper recognizes situations where a system may determine it cannot accurately provide corrected blood glucose values. In some examples, there may be multiple reasons why this might be the case. As an example, an adverse event could include events similar to other adverse events learned over time, but with a specific level of difference that prevents an accurate determination of what the corrected blood glucose value should be. As another example, the learning algorithm may not have processed enough information or been fed enough data to accurately predict the corrected blood glucose value. In some examples, there may be some possibility of degradation of the auxiliary sensor (or even the blood glucose sensor), which could affect the ability to accurately assess the type of event that actually occurred. As a specific example, a sudden drop in temperature during sleep or exercise without some other explanation might indicate a degraded temperature sensor, but could also have other potentially serious health effects. Such examples are not intended to be limiting, but are illustrative in nature. It is understood that in all cases, the user's health is the highest priority, and therefore, if there are indications that the corrected blood glucose value may not accurately reflect any underlying biological indications, other mitigation measures can be taken.

[0136] Specifically, at box 345, method 300 includes taking mitigation measures. Mitigation measures may include an alert / warning (e.g., visual, audible, vibratory, etc.) to the user that the reported CGM value cannot currently be trusted. In some examples, instead of displaying any reported value, the system may display an error message or other message to the user conveying the fact that the blood glucose value determined by the CGM system is currently impaired. For example, the error message might flash. In such cases, the user may be advised that using some other method to assess the current blood glucose level would be in their best interest. For example, the system may display a message requesting the user to rely on actual blood glucose readings over a defined time period. It is understood that these actual blood glucose readings may then be stored and used as supplementary data in learning algorithms in some examples.

[0137] If the system can no longer provide accurate analyte values ​​(e.g., the confidence level of the analyte value is low, or even much lower than the low value considered relevant to box 335), any closed-loop operation can be interrupted, and the user can be alerted to this fact. For example, reliance on an insulin pump can be interrupted, and any actions required to control blood glucose may have to be performed manually by the user. The user can then be alerted when closed-loop operation will resume, thus informing the user of this information and preventing them from continuing to manually manage blood glucose control.

[0138] As mentioned, in some examples, an adverse event might be caused by some degree of degradation of a particular sensor, resulting in what appears to be an adverse event that may actually be solely due to sensor degradation. In some examples, taking mitigation measures at box 345 could include the system requesting the user to take action, which in turn allows the system to assess whether one or more sensors are operating as expected or anticipated. For example, the system might infer that a pressure sensor has deteriorated. Therefore, the system could request the user to apply pressure near the pressure sensor, and this would allow the system to assess whether the pressure sensor is operating as expected. For example, the user could input information about the pressure they are about to apply into the system and confirm it after (or immediately after) applying pressure. The CGM system can then assess whether the pressure sensor is responding as expected, and this information can be used to determine the likelihood of pressure sensor degradation. In cases indicating pressure sensor degradation, the CGM system could request the user to replace the pressure sensor. Once action is taken, the user can input confirmation to the system that the sensor has been replaced.

[0139] Similar examples apply to other sensors. For instance, in response to an indication that an accelerometer might be operating erratically, a CGM system could request the user to perform a predetermined sequence of movements (e.g., bending and straightening one to three times or more, walking in a circle or square of approximate size, etc.). Regarding temperature sensors, the user might be asked to apply some form of heat or cold (e.g., a hot or cold towel) near the sensor to assess whether the temperature sensor is responding as expected. Other examples are within the scope of this disclosure. Similar examples apply to other types of sensors, including but not limited to heart rate monitors, blood pressure monitors, etc. For example, the system could request an alternative device to determine heart rate or blood pressure, which could then be input into the CGM system to enable the determination of whether a particular monitor is exhibiting degraded operation.

[0140] At box 350, method 300 includes updating CGM system parameters. For example, updating system parameters at 350 may include storing any data related to the current event, including but not limited to data retrieved from one or more of the CGM sensor and / or auxiliary sensors, the duration of the adverse event, whether any sensor needs to be replaced and / or whether any sensor has been replaced, any additional blood glucose readings obtained and input into the system, updating any relevant filter parameters, etc. It is understood that any and all data corresponding to the updated system parameters may be fed into the learning algorithm so that the algorithm can continue to improve its ability to accurately assess situations where reported blood glucose values ​​may be inaccurate, and, where possible, provide corrected blood glucose values ​​with increasingly higher confidence. Method 300 may then return to step 320 of method 300.

[0141] Although Figure 3 While not explicitly stated herein, it is recognized that the ability to predict / infer when analyte values ​​might be inaccurate and, more broadly, when they might be highly accurate, can be advantageous in specifying particular time periods for analyte sensor calibration operations. For example, any calibration operation performed within a timeframe where analyte values ​​might be inaccurate—even if these values ​​could be corrected in terms of display to the user—may degrade the effectiveness of the calibration operation. Therefore, this disclosure covers methods for predicting time periods in which analyte values ​​are predicted to be accurate and require no compensation, and for scheduling calibration operations within the timeframes covered by said predicted time periods. As disclosed herein, such prediction of time periods can be based on learned patterns of sensor operation derived from the analysis of historical data. However, it is recognized herein that in some examples, calibration operations may be possible during time periods when relying on corrected blood glucose values, for example, when the corrected blood glucose values ​​have a certain level of confidence (e.g., high).

[0142] Turn now Figure 4 The description is applicable to the above. Figure 3 The advanced processing flow 400 of the method discussed herein is illustrated. It includes a historical data module 405, a learning module 410, a data acquisition module 415, a pattern recognition module 420, a correction factor module 425, a transfer function module 430, and an output module 435. It can be understood that the processing flow 400 broadly encompasses the above-mentioned... Figure 3 The learning algorithms discussed here. For example, Figure 4 Each module shown may include a subset of the learning algorithm. However, it will be understood that additional modules or fewer modules are within the scope of this disclosure.

[0143] In short, the historical data module stores any and all relevant historical data used to predict / infer the time when the CGM system might potentially report inaccurate blood glucose values. This data may include, but is not limited to, data acquired from auxiliary sensors, data input by the user into, for example, software applications operatively linked to the CGM system, CGM sensor data acquired via the currently implanted CGM sensor and / or previously used CGM sensors, previous actual blood glucose measurements (along with relevant corresponding data, such as time of day, day of week, measurement time related to meals / snacks, etc.), and any other relevant data. Other relevant data may include, for example, data inferred by the software application based on geographic location or other information obtained from other software applications. In some examples, historical data corresponds to a single user; however, within the scope of this disclosure, historical data is not limited to a single user but can be a group of users.

[0144] Historical data module 405 provides historical data contained therein to learning module 410. Learning module 410 relies on some form of artificial intelligence to infer patterns in the historical data, particularly patterns in the environment that can predict with high accuracy when the CGM sensor becomes unreliable (e.g., may report inaccurate blood glucose values). In this example, learning module 410 relies on machine learning, which may include supervised learning, unsupervised learning, reinforcement learning, or some combination thereof. In addition to the learning environment where reported blood glucose sensor values ​​may be inaccurate, learning module 410 can be programmed to predict what blood glucose values ​​should actually be during the time period when reported values ​​become inaccurate. Specifically, learning module 410 can feed data to correction factor module 425, allowing appropriate correction factors to be determined for various situations where reported blood glucose values ​​are predicted to be inaccurate. In some examples, correction factor module 425 is therefore part of or a subset of learning module 410. Different correction factors may exist for different environments. In some examples, the same correction factor may be relied upon for multiple (e.g., more than one) different situations where reported blood glucose values ​​are predicted to be inaccurate in other ways. Correction factors can be used to compensate for errors in otherwise reported blood glucose values, thereby providing users with more accurate blood glucose values ​​instead. Specifically, correction factors can be used to ensure that the reported blood glucose value falls within an acceptable range (in the absence of influencing environmental / conditional factors that would cause inaccuracy).

[0145] Data acquisition module 415 can be understood as being able to retrieve newly acquired data from the CGM system, in order to... Figure 4 The data acquisition module is used in the processing flow 400. Therefore, the data acquisition module is operatively linked to the CGM system and is able to acquire (e.g., in real time) data from one or more sensors (e.g., CGM sensors and / or auxiliary sensors), data input to the CGM software application, and any other relevant data input to the CGM system.

[0146] The pattern recognition module 420 relies on information learned by the learning module 410, along with the data acquisition module 415 including newly acquired data, to predict / infer whether the current situation is one where the expected reported blood glucose value has become inaccurate. The meaning of "inaccurate" may vary in degree. For example, some situations might lead to a first level of inaccuracy in the reported blood glucose value, others might lead to a second level, still others might lead to a third level, and so on. For example, the first level could be less than the second level, and the second level could be less than the third level. Therefore, the correction factor module 425 may have to generate different correction factors for various learning environments, as mentioned above. Furthermore, in this example, the pattern recognition module may include some estimate of the probability that the newly acquired data via the data acquisition module 415 corresponds to a situation where the reported blood glucose value may be inaccurate (or accurate). (See also: Regarding...) Figure 3 The probability / likelihood discussed may affect some aspects of method 300, such as in assessing whether the compensated / corrected blood glucose value can be accurately reported to the user and / or what level of confidence the user should assume the corrected blood glucose value corresponds to.

[0147] Arrow 421 depicts the processing flow as a return to the learning module 410. This implies that newly acquired data and its relationship to predetermined data patterns consistent with situations where reported blood glucose values ​​may be inaccurate (or vice versa, reported blood glucose values ​​may be accurate) can be fed back into the learning module 410. In this way, the learning module can be continuously updated with newly acquired data and the relationship between the newly acquired data and previously established data patterns, which can be improved over time. Figure 4 The entire processing flow involves 400 operations.

[0148] The transfer function module 430 includes a function (e.g., a mathematical function) that transforms inputs fed into the module into outputs via the output module 435. In this example, the output refers to a blood glucose value, which can be understood to include, at least in some cases, values ​​related to blood glucose levels without... Figure 4 In the case of processing flow 400, the blood glucose value reported in other ways has been corrected / compensated to at least some degree compared to the blood glucose value already reported. As depicted, the transfer function module 430 can receive input from the correction factor module 425, meaning that the transfer function module 430 can be modified via one or more correction factors as determined by the correction factor module 425. In this way, for various environments where the reported blood glucose value may be inaccurate to some degree in other ways, an accurate blood glucose value can be output via the output module 435. The output module 435 can output the blood glucose value to, for example, a CGM calculation device (e.g., Figure 1The display associated with the computing device 110 and / or the user computing device (e.g., Figure 2 The networked device 210 is associated with a display, for example, output via a CGM software application.

[0149] Turn now Figure 5 This illustration depicts the torso 500 of a user of the CAM system of this disclosure. It is recognized herein that it may be advantageous for one or more auxiliary sensors to be in some proximity to the analyte sensor. Therefore, illustration 502 shows a close-up view of the location of the analyte sensor 150 embedded in the user's skin on the torso 500. A region 505 of radius r defines the area where at least one other auxiliary sensor is located. An accelerometer 160, a temperature sensor 170, and a pressure sensor 507 are shown. In the example, the radius r is 8 cm or less, such as 7 cm or less, 6 cm or less, 5 cm or less, 4 cm or less, 3 cm or less, 2 cm or less, or even 1 cm or less (e.g., within the range of 1 mm to 10 mm, 10 mm to 50 mm, 50 mm to 100 mm, 100 mm to 500 mm, 500 mm to 1000 mm). Figure 5 The housing containing the sensor electronics is not shown, such as the housing including the computing device 110. Figure 5The adhesive patch, which may include a backing of such a housing, can be used to adhere the housing to a user's skin. As illustrated below, in some examples, within the scope of this disclosure, one or more pressure sensors 507 may be incorporated into such an adhesive patch, and these one or more pressure sensors may include auxiliary sensors capable of reporting pressure changes near the analyte sensor. In some examples, within the scope of this disclosure, one or more auxiliary sensors, including but not limited to accelerometer 160, temperature sensor 170, and pressure sensor 507, may be included within or coupled to such a housing (e.g., positioned on the outer surface of such a housing). In examples, one or more auxiliary sensors are operatively linked to electronics corresponding to sensor electronics. In this way, sensor electronics capable of receiving and transmitting information related to analyte sensor 150 can similarly be capable of retrieving and transmitting information related to any operatively linked auxiliary sensor. In other examples, within the scope of this disclosure, one or more auxiliary sensors include independent sensors, each capable of retrieving and transmitting data independently of any operative link to sensor electronics. In one example, one or more auxiliary sensors are attached to the user's skin. In another example, the accelerometer may be integrated into the sensor electronics of the potentiostat that operates the CGM device. In yet another example, one or more auxiliary sensors may be positioned on a transmitter plate included within a housing (not shown). For example, as described in more detail below, in some embodiments, a temperature sensor may be positioned on the transmitter plate.

[0150] Figure 6 An example timeline 600 is depicted illustrating how the actuators of the CGM system of this disclosure can be controlled at the point in time when a blood glucose value reported to a user (e.g., via a display device) corresponds to a calibrated blood glucose value. In this example timeline, the actuators include an alarm (e.g., audible or visceral) that can be actuated in response to a blood glucose value (calibrated or uncalibrated) exceeding a predetermined threshold (e.g., a hyperglycemia or hypoglycemia threshold). Timeline 600 includes a curve 605 indicating whether the alarm is off (e.g., deactivated) or on (e.g., activated) over time. Timeline 600 also includes a curve 610 indicating the change of uncalibrated blood glucose values ​​over time and a curve 615 indicating the change of calibrated blood glucose values ​​over time. Timeline 600 also includes a curve 620 indicating the change of data corresponding to temperature recorded via an auxiliary temperature sensor over time. Timeline 600 also includes data points 625 corresponding to accelerometer data collected over time. Line 626 reflects “no movement” associated with the accelerometer data.

[0151] Between time t0 and t1, the CGM system relies on uncorrected blood glucose values. There are very small temperature changes sensed by the temperature sensor, and very small detectable movements associated with the user. Therefore, between time t0 and t1, the system predicts that the uncorrected value accurately reflects the blood glucose concentration sensed by the continuous blood glucose sensor within a predetermined threshold range.

[0152] Immediately after time t1, the temperature begins to increase (curve 620), and this increase is associated with some form of movement, as indicated by the accelerometer data (curve 625). Based at least on the accelerometer and temperature data, and a comparison of this data with historical data as discussed above, the system predicts that an event is occurring that is expected to result in inaccurate blood glucose values ​​that do not reflect the actual blood glucose concentration sensed by the continuous glucose sensor. The system may also consider other variables, such as the time of day, to infer whether the user might be sleeping or in a vehicle, etc. Between time t1 and t2, it can be seen that the uncorrected blood glucose values ​​begin to rise, accompanied by a noticeable movement and increasing temperature, as reported by the corresponding sensors.

[0153] Because the system can predict that a rise in blood glucose might be human-induced, such as a user turning over in their sleep and possibly covering themselves with a thick blanket, causing a temperature increase near the blood glucose sensor, at time t2, the system stops relying on the uncorrected blood glucose value (curve 610) and begins relying on the corrected blood glucose value (curve 615). In this example timeline, the uncorrected blood glucose value continues to be shown for reference during the period when the system relies on the corrected blood glucose value. However, in some examples, the uncorrected value can continue to be determined even during the period when the corrected value is used. This allows for a comparison between the corrected and uncorrected values, such that when the difference between the corrected and uncorrected values ​​is within a predetermined threshold (e.g., when the values ​​differ by 1% to 5%, such as 2%), the system can revert to relying on the uncorrected blood glucose value.

[0154] At time t3, without the correction value, the first blood glucose threshold (Th1, represented by line 611) would be exceeded. This would trigger an alarm. If the user is asleep, this would wake the user and could lead to inappropriate actions by the user to manage the assumed situation. However, because the correction value is relied upon at time t3, the alarm is not activated (curve 605).

[0155] Between times t3 and t4, the corrected blood glucose value remains below a second blood glucose threshold (Th2, represented by line 616). In this example timeline 600, the Th2 threshold is lower than the Th1 threshold, although both thresholds are related to when an alarm is triggered. The Th2 threshold is lower because a corrected blood glucose value is being used, which can include a confidence level lower than the confidence level of an uncorrected blood glucose value due to the computational operations associated with providing the corrected blood glucose value. To prioritize the user's health, the Th2 threshold can be lower than the Th1 threshold, causing the system to be biased towards detecting any conditions that may affect the user's health. In other words, the Th2 threshold represents a more conservative threshold than the Th1 threshold because the system relies on the corrected blood glucose value.

[0156] Just before time t4, there was detectable movement (data point 625) and the temperature sensed by the temperature sensor (curve 620) began to decrease. In this example timeline 600, this can be understood as being related to the user turning over again, thus freeing the blood glucose sensor from the environment that caused the temperature to rise.

[0157] At time t4, the system predicts that the uncorrected blood glucose value will accurately represent the actual blood glucose concentration sensed by the continuous glucose sensor. Therefore, at time t4, the system reverts to relying on the uncorrected blood glucose value.

[0158] The discussion of example timeline 600 illustrates an example where the blood glucose threshold used to set the alarm is adjusted based on whether it relies on a calibrated blood glucose value or an uncalibrated blood glucose value. In other examples, without departing from the scope of this disclosure, the threshold may not be adjusted between these two conditions.

[0159] Example timeline 600 only shows two auxiliary sensors (temperature and accelerometer), but it is understandable that any number of other auxiliary sensors and related data used to determine the conversion of raw data obtained from the continuous glucose sensor are expected to be inaccurate time periods.

[0160] Furthermore, while example timeline 600 depicts a manner for controlling alarms according to an embodiment of this disclosure, in other embodiments, the actuator may include, for example, an insulin pump included in a closed-loop CGM system. Similarly, it may be based on... Figure 6 The logic depicted by the timeline is similar to that of the insulin pump, which controls the insulin pump based on the correction value at the time when the uncorrected value is predicted to be inaccurate.

[0161] The above description addresses various scenarios where auxiliary sensor data is used in conjunction with a continuous analyte sensor to infer / predict that blood glucose values ​​might be incorrectly reported without adaptive correction. It is recognized in this paper that the combination of auxiliary sensor data with data retrieved from the continuous analyte sensor can be relied upon additionally or alternatively, in order to address the following... Figure 7 Other methods discussed to improve the quality of continuous analyte sensor data.

[0162] Figure 7 Various embodiments are described for improving the reporting to and / or reliance on for control of CAM systems (e.g., Figure 2 A high-level example method for improving the data quality of one or more actuators in a CGM system 200. Method 700 may at least partially include data stored in, for example, a computing device (e.g., Figure 1 The computing device 110 and / or Figure 2 Executable instructions are stored in the memory of one or more networked devices 210. When executed, the instructions can cause changes in one or more operating states of the CGM system, such as controlling one or more actuators of the CGM system (e.g., vibration and / or auditory alarms, insulin pumps, etc.). Method 700 is written for a CGM system, but it will be understood that the method is equally applicable to other CAM systems without departing from the scope of this disclosure.

[0163] Method 700 begins at block 705 and includes a sensor from the CGM sensor (e.g., Figure 1 The analyte sensor 150 retrieves the data stream. For example, method 700 can begin when the CGM sensor is inserted into the skin.

[0164] Proceeding to block 710, method 700 includes retrieving data streams from one or more temperature sensors. In cases where the CGM system includes more than one temperature sensor, it is understood that block 710 includes retrieving a separate data stream (e.g., a first data stream, a second data stream, a third data stream, etc.) from each respective temperature sensor. Temperature data can be retrieved at regular intervals, such as intervals between 1 second (or less) and 10 minutes. For example, temperature data can be retrieved at intervals between 1 second and 5 seconds, 5 seconds and 10 seconds, 10 seconds and 20 seconds, 20 seconds and 30 seconds, 30 seconds and 40 seconds, 40 seconds and 50 seconds, 50 seconds and 60 seconds, one minute and two minutes, two minutes and three minutes, three minutes and four minutes, four minutes and five minutes, or five minutes and ten minutes. In some examples, temperature data from at least one sensor is obtained at intervals including 50 seconds to 70 seconds, such as 60 seconds. This can save power and computational storage space for the CGM system while also providing sufficient temperature data for method 700. In some examples of retrieving data from more than one temperature sensor, the interval between data retrievals can be the same for each temperature sensor; however, in other examples, the interval can be different for different sensors.

[0165] In one example, the temperature sensor may be located on a computing device, for example, operatively linked to a CGM sensor (e.g., Figure 1 The temperature sensor is located on the transmitter plate of the computing device 110. It is recognized here that one advantage of positioning the temperature sensor on the transmitter plate is that the temperature sensor can be very close to the user's body and the CGM sensor, for example, when the housing (which houses the transmitter and associated computing device) is positioned on the user's skin.

[0166] In another additional or alternative example, the temperature sensor may be positioned below the transmitter housing and in direct contact with the skin. In such an example, the housing may include vents (e.g., openings, outlets, holes, gaps, orifices, etc.) to prevent insufficient ventilation from causing the temperature to not accurately reflect the actual increase in skin temperature.

[0167] In yet another additional or alternative example, the temperature sensor may be positioned on the user's skin, for example, within 2 cm of the CGM sensor, but not between the transmitter housing and the skin.

[0168] In yet another additional or alternative example, the temperature sensor may be positioned on the surface of the CGM sensor such that the temperature sensor is inserted into the skin along with the CGM sensor when the sensor is inserted.

[0169] In some examples, the CGM system has only one temperature sensor located at any one of the sites mentioned above; however, in other examples, the CGM system may include any number of temperature sensors located at two or more sites, such as three or even four sites, mentioned above. In a particular example, the CGM system includes three temperature sensors: one temperature sensor located on the transmitter plate, one temperature sensor located on the skin (between the housing and the skin or outside the housing), and one temperature sensor located on the CGM sensor inserted into the user's skin.

[0170] One advantage of positioning the temperature sensor at the transmitter is that the transmitter comprises multiple electronic components, each of which may be susceptible to temperature variations. For example, a resistor associated with the transmitter (e.g., a megohm resistor) may be susceptible to temperature changes. If the temperature of such a resistor changes significantly, this could affect the overall function of the CGM system, for example, by adversely affecting the overall function of the CGM system through a computing device that tracks current readings via which the transmitter is part (or operatively linked). The tracked current readings are ultimately converted into blood glucose values, so even a small change in the resistor's characteristics due to its temperature can lead to a change in the determined blood glucose value. By providing the ability to measure temperature at the transmitter board, temperature changes can be measured and correlated with the temperature sensitivity of the corresponding electronics (previously characterized), making it possible to compensate for any temperature-induced variations, thereby improving the quality and accuracy of the reported blood glucose values.

[0171] Regarding skin temperature, it reflects the amount of blood circulating through it. The more capillary blood circulates through the skin, the better the balance between plasma glucose and interstitial fluid glucose. Because the CGM sensor of this disclosure measures interstitial fluid glucose, a better balance between plasma and interstitial fluid glucose will result in a measurement that is closer to the actual blood glucose level.

[0172] Furthermore, skin temperature can affect lag time, which herein refers to the time difference when a change in plasma glucose is fully reflected (or approximately equivalent, e.g., in 1% or less, or 5% or less, or 10% or less) in an equivalent change in interstitial fluid glucose and thus in the glucose concentration reported via the CGM sensor / system of this disclosure. This lag time may vary from person to person but is generally understood to be between 2 and 7 minutes (although smaller and larger lag times are not outside the scope of this disclosure). In some examples, lag time may depend on the magnitude of the change in plasma glucose levels. Another variable that may affect lag time is blood circulation in the skin, which, as mentioned above, is a reflection of skin temperature. For example, colder skin temperatures may be associated with lower blood circulation, which may in turn increase lag time. Alternatively, higher skin temperatures may be associated with greater blood circulation, which may in turn decrease lag time. Therefore, it is recognized herein that such temperature data can be incorporated into algorithms that allow CGM values ​​to be based on recorded skin temperature and compensated as a function of a determined lag time. This can reduce the variability in the effect of skin temperature on lag time, thereby improving the quality and / or accuracy of CGM values ​​reported to users and / or relied upon for controlling one or more operational aspects of the CGM system. It is understood that because lag time can be user-specific, lag time as a function of skin temperature for a particular individual may need to be learned empirically (e.g., via learning algorithms such as those disclosed herein) or otherwise obtained to be effective. As an example, such compensation may consist of multiple components, including but not limited to the rate of change of blood glucose measured by the CGM, the skin temperature retrieved via a temperature sensor, and the lag time characteristics modeled as a function of the individual user's skin temperature.

[0173] Furthermore, skin temperature near the CGM sensor may affect glucose diffusion into the sensor. For example, CGM sensor glucose measurement is based on measuring glucose molecules that diffuse into the sensor, and after diffusion, the glucose reacts with an enzyme (e.g., glucose oxidase) to produce, for example, hydrogen peroxide. The hydrogen peroxide is then oxidized by the sensor's working electrode to generate a current reflecting the glucose concentration in the interstitial fluid. Glucose diffusion into the sensor becomes steady-state, and by measuring the steady-state at a specific glucose concentration, the glucose concentration in the interstitial fluid can be estimated. These diffusion characteristics of glucose into the sensor can be affected by temperature. At lower temperatures, the diffusion rate of glucose into the sensor may be lower, and therefore, at lower temperatures, the reported glucose value may be lower than the actual glucose concentration in the interstitial fluid. As a representative example, a 5°C temperature change near the sensor may have an effect of up to 10% to 12% on the reported glucose value. By providing a measurement of skin temperature, this data can be incorporated into an algorithm that considers the simulated glucose diffusion characteristics as a function of temperature, allowing for compensation of the glucose value to more accurately reflect the actual interstitial fluid glucose concentration sensed by the CGM sensor. Preferably, in order to measure the temperature effect that contributes to the blood glucose diffusion properties, the temperature sensor is positioned on the CGM sensor inserted into the user's skin. In other words, as the CGM sensor is inserted into the skin, the temperature sensor can also be inserted into the skin (not just remaining on the skin surface, but penetrating into the skin).

[0174] In some embodiments, the CGM system of this disclosure may include only one of the temperature sensors mentioned above, such as a temperature sensor located only on the transmitter plate, a temperature sensor located only on the skin surface, or a temperature sensor located only on the CGM sensor inserted into the user's skin. In other examples, the temperature sensor may be included at more than one of the temperature sensor locations mentioned above, such as two locations or even all three locations. In the case of the CGM system of this disclosure including multiple temperature sensors, this allows for multiple temperature-based calibrations to improve the quality and / or accuracy of the CGM sensor.

[0175] Therefore, at box 715, method 700 includes processing temperature data retrieved from one or more temperature sensors. As discussed, this can be accomplished by modeling specific variables that are associated with the effects of temperature, such as how electronic device temperature affects CGM current, how skin temperature affects hysteresis time, and how skin temperature affects glucose diffusion characteristics in the sensor. In some examples, a separate model (e.g., an algorithm) may be used for each different temperature sensor, or a single model that considers each temperature data stream may be used.

[0176] Returning to step 710, in some examples, the accelerometer may be additionally included in the CGM system. Therefore, at block 720, method 700 may include retrieving a data stream from the accelerometer. In a preferred example, the accelerometer may be attached to the CGM transmitter board circuitry, enabling data collection on three axes (e.g., x, y, z). It is recognized herein that including the accelerometer at its attachment point to the CGM transmitter board circuitry can provide unique advantages compared to other systems that may rely on an accelerometer positioned, for example, on the user's wrist. For example, including the accelerometer at the location where the sensor is located allows the data collected from the accelerometer to be precisely correlated with specific effects on the CGM sensor signal.

[0177] In one example, accelerometer data can be acquired from a user, stored, and analyzed about what the user is doing at a specific time (e.g., a specific activity). This data combination can correlate specific accelerometer data trends with specific user postures (e.g., bending over to tie shoelaces), and can further correlate them with relatively short time periods (e.g., less than 5 minutes, or less than 10 minutes, or less than 20 minutes, or less than 30 minutes, or less than 40 minutes, or less than 50 minutes, or less than 1 hour, or less than 2 hours, or less than 3 hours) when reported blood glucose values ​​do not accurately reflect the actual blood glucose concentration sensed by the CGM sensor.

[0178] Therefore, as discussed in this paper, accelerometer data can be used to determine a user's posture, which can be correlated with specific CGM sensor signal anomalies. As an example, a specific posture sensed by an accelerometer located at the CGM sensor position (e.g., coupled to the transmitter plate) may result in a pressure groove, the length and depth of which are easily observable in the current data being retrieved from the CGM sensor. As a representative example, this occurs when the user wears the sensor on the front of their abdomen (see...). Figure 5When a user is bent over while performing a task (at the location of the CGM sensor), this can cause pressure artifacts (e.g., pressure grooves). These pressure artifacts persist as long as the user is bent over in a particular position. Such pressure artifacts can cause current deflection of up to 20% or, in some cases, even higher (e.g., 30% or more). Such an effect on the current can cause reported blood glucose levels to vary anywhere from 10 mg / dL to 60 mg / dL, which is certainly undesirable and could trigger alarms to alert the user to events such as hypoglycemia. Because the actual blood glucose concentration has not decreased, this could cause the user to take unintended actions to compensate for this perceived drop in blood glucose levels. In other examples, changes in reported blood glucose levels that do not reflect the actual blood glucose concentration sensed by the CGM sensor can cause the insulin pump to be unintendedly activated (e.g., if postural instability causes what appears to be a hyperglycemic event, when in fact interstitial blood glucose levels have not increased).

[0179] Therefore, it is desirable to detect and interpret the occurrence of such signal artifacts using accelerometer data, and then take appropriate measures (e.g., not displaying blood glucose values ​​because they are unreliable, or correcting / compensating for the values ​​as a function of anomalies, so that the reported blood glucose values ​​accurately reflect the blood glucose concentration detected by the CGM sensor). In many cases, as discussed above, such tactile interferences that lead to CGM signal artifacts may be transient, such as 10 minutes or less, or even 5 minutes or less. Models (e.g., algorithms) can be used to adaptively track such situations and thus report corrected / compensated blood glucose values ​​that accurately reflect the blood glucose concentration sensed by the CGM sensor.

[0180] It is understandable that the ability to correct for posture interferences to CGM signals using accelerometer data, as mentioned above, is due to the position of the accelerometer relative to the CGM sensor (e.g., positioned on a transmitter plate in a housing located on top of the user's skin, with the CGM sensor implanted beneath it). For example, if the accelerometer were positioned differently, such as on the user's wrist (e.g., included as part of a watch) or as part of a computing device (e.g., carried by the user), associating accelerometer data with a specific posture and thus correcting for CGM signal interferences based on that specific posture determined by the accelerometer data might be infeasible (or potentially substantially more difficult).

[0181] In order to rely on such accelerometer data, the CGM system of this disclosure can correlate CGM-based current changes with auxiliary data provided by the accelerometer to assign specific time periods in which corrective measures can be taken to adaptively report corrected / compensated blood glucose values ​​instead of reporting blood glucose values ​​with artifacts caused by posture interference due to the CGM sensor function.

[0182] While the above description of attitude interference with CGM current signals relies on accelerometer data, within the scope of this disclosure, in addition to accelerometer data or alternatively, one or more pressure sensors can be used to obtain similar information. As an example, one or more pressure sensors may be mounted on an adhesive patch on the bottom of the body-wearing unit (e.g., the bottom of the housing housing the transmitter plate). In such an example, one or more temperature sensors may be additionally or alternatively attached to the adhesive patch.

[0183] Therefore, at block 725, method 700 includes processing accelerometer data retrieved from the accelerometer. This can be accomplished by considering a model that combines a predetermined pattern of the accelerometer data with a predetermined pattern of the current signal provided via the CGM sensor. Thus, the processing may involve allocating specific time periods to events including gesture disturbances affecting the CGM-based signal current, and adaptively correcting / compensating the reported blood glucose values ​​so that the reported blood glucose values ​​more accurately reflect the actual blood glucose concentration sensed by the CGM sensor.

[0184] Therefore, box 730 includes adaptively correcting / compensating the reported blood glucose value based on retrieved temperature data and / or accelerometer data combined with retrieved current CGM data. In some examples, adaptive compensation may consider more than one type of data, such as temperature sensor data and accelerometer data, because there may be situations where considering both accelerometer and temperature data can further improve the accuracy of the reported blood glucose value with respect to the actual blood glucose concentration sensed by the CGM sensor. In the example, adaptive compensation of the blood glucose value at box 730 relies on one or more correction factors derived from data acquired and processed prior to box 730.

[0185] At box 735, method 700 includes storing relevant data. For example, it can be understood that data collected from temperature sensors and accelerometers (and / or pressure sensors), combined with CGM current, can be used to improve the model used in method 700 and can be additionally or alternatively used for various aspects of CGM system operation. For example, in some examples, the collected data may include information on… Figure 3 The method uses useful historical data.

[0186] At box 740, method 700 includes controlling one or more actuators based on a calibrated / compensated blood glucose value. For example, similar to what has been discussed above, the calibrated blood glucose value can be used to prevent an alarm from being activated (e.g., auditory and / or vibratory) that would otherwise indicate a hyperglycemic or hypoglycemic event. For example, if the calibrated blood glucose value remains within a predetermined threshold, the alarm can be prevented from being activated, whereas it would otherwise be activated if the reported blood glucose value is not compensated. Similar logic applies, for example, to an insulin pump. For example, if the calibrated blood glucose value does not exceed a hyperglycemic threshold, the insulin pump may not be activated, whereas it might be activated to deliver insulin pills in the absence of the adaptive compensation method disclosed herein. Similar to what has been discussed above... Figure 3 As discussed in method 300, an indication may be provided to the user that the reported value includes a correction / compensation value. Examples may include, but are not limited to, a color change of the reported value displayed on a visual display, a flashing value compared to a non-flickering value, etc. In some examples, a descriptive phrase may be displayed to alert the user that the reported blood glucose value includes a correction / compensation value. Furthermore, the reported value may be associated with a specific confidence level (e.g., high, medium, or low) to inform the user how accurate the correction / compensation value may be. In some examples, one or more thresholds for controlling actuators (e.g., insulin pumps, alarms, etc.) may include adjustable thresholds that can be adjusted to a more conservative level during periods when the reported value includes the compensation value and to a lower conservative level during periods when no adaptive compensation / correction is applied to the value. In some examples, the degree to which one or more thresholds are adjusted may be a function of the confidence level of the corrected / compensated reported blood glucose value. For example, the higher the confidence level, the smaller the threshold can be adjusted.

[0187] At box 745, method 700 determines whether the CGM sensor has been removed or if any other affected issues have been detected (e.g., sensor degradation). If so, method 700 can terminate and then restart once the sensor is replaced. Alternatively, if the CGM sensor has not been removed and no affected issues have been detected, method 700 returns to step 705, where it repeats the process. Figure 7 The processing flow adaptively corrects temperature artifacts and / or pose artifacts associated with CGM sensor signals.

[0188] Figure 8An example timeline 800 is depicted illustrating how accelerometer data can be used with the CGM system of this disclosure to detect and compensate for CGM sensor signal artifacts caused by specific user postures or activities. In this example timeline, accelerometer data is used in conjunction with at least current CGM sensor data to compensate / correct reported blood glucose values, and consequently control alarms to alert the user to specific conditions (e.g., hyperglycemia or hypoglycemia events) based on the compensated / corrected blood glucose values.

[0189] Example timeline 800 includes curve 805 indicating whether an alarm (e.g., an audible and / or vibration alarm) is active (on) or deactivated (off) over time. Timeline 800 also includes curve 810 indicating CGM sensor current changes over time. Timeline 800 also includes curve 815 indicating uncompensated blood glucose values ​​changes over time and curve 820 indicating compensated blood glucose values ​​changes over time. Timeline 800 also includes indicators from a computing device located in relation to the wearable CGM device (e.g., Figure 1 The timeline 800 includes a curve 825 showing the change over time of accelerometer data retrieved from the accelerometer at the transmitter board associated with the computing device 110. The timeline 800 also includes a curve 830 indicating the change over time of data retrieved from a temperature sensor of the CGM system. In this example timeline, for clarity, only data from one temperature sensor is indicated, and the temperature sensor can be understood to include temperature sensors configured to monitor the temperature of electronics associated with the computing device (e.g., temperature sensors located at the transmitter board). In this example timeline, curve 820 includes two portions shown by dashed lines and one portion shown by solid lines. This is to indicate that during the time period when no CGM sensor signal artifact is detected, the compensated blood glucose value can be substantially the same as the uncompensated blood glucose value, but during the time period when a CGM sensor signal artifact is detected, it differs from the uncompensated blood glucose value. In this example timeline, CGM sensor signal artifacts are identified via a combination of at least CGM sensor current and accelerometer data, and data retrieved from the temperature sensor can be considered when determining signal artifacts. Therefore, regarding... Figure 8 The described signal artifacts can be understood as artifacts caused by the user's specific posture.

[0190] Between time t0 and t1, the alarm is off, and the accelerometer data is relatively stable (curve 825). The CGM sensor current (curve 810) is also relatively stable, reflecting the constant interstitial blood glucose concentration, and therefore the uncompensated blood glucose value (curve 815) accurately represents the blood glucose concentration sensed by the CGM sensor.

[0191] At time t1, the CGM sensor current (curve 810) is artificially influenced by the user's posture, reflected in the accelerometer data (curve 825). As indicated by curve 830, the current drop and the pattern in the accelerometer data, as well as the absence of temperature sensor variations, are interpreted as and characterized by a predetermined posture effect. Therefore, Figure 7 The method is used to adaptively correct / compensate reported blood glucose values ​​during a time period (time span t1 vs. t2) when the user is adopting a specific posture that causes artifacts in the CGM sensor current (see curve 820). Line 816 is depicted at time line 800, representing a low blood glucose threshold below which an alarm is activated. Line 821 represents the same threshold, but is replicated for clarity. Because the compensated blood glucose value remains above the threshold (line 821), the alarm is not activated; however, if the reported blood glucose value is not compensated based at least on CGM sensor current and accelerometer data, the alarm will be activated (see curve 815 relative to line 816). After time t2, it is determined that the event causing the posture-induced signal artifact no longer exists, and the reported blood glucose value again includes the uncompensated value.

[0192] In some examples, the CGM system of this disclosure may continuously generate both compensated and uncompensated values, and deviations exceeding a predetermined amount (e.g., a difference of more than 2%, or more than 5%, or more than 10%, etc.) may cause the system to rely on the compensated value instead of the uncompensated value.

[0193] The above description has illustrated how ancillary data can be used to improve the quality and accuracy of the CGM system of this disclosure by correcting / compensating for reported blood glucose values ​​that may not accurately reflect the actual blood glucose concentration sensed by the CGM sensor. However, it is recognized herein that there may be other uses for the ancillary data disclosed herein. Specifically, ancillary data can be useful in predicting blood glucose values ​​at future times. This type of data can include analysis of historical data trends as described in detail above, allowing data to be mined to predict specific combinations of data patterns retrieved from one or more ancillary sensors and CGM sensor current (or voltage) with respect to predicted future blood glucose values. Ancillary data in the context of such future predicted blood glucose values ​​can include any or all types of ancillary data disclosed herein (e.g., temperature sensor data, pressure sensor data, accelerometer data, heart rate sensor data, blood pressure sensor data, data such as geolocation data retrieved from software applications, etc.). Learning strategies based on historical data trends (e.g., AI-based learning strategies such as those in the machine learning category mentioned above) can be used to infer specific data patterns that predict future blood glucose values ​​with a certain level of confidence in the prediction. This can be particularly useful in controlling alarms / warnings.

[0194] For example, based on specific identification patterns and CGM current data (e.g., raw CGM data streams) retrieved from one or more auxiliary sensors, the CGM system of this disclosure can be able to predict when a user is likely to enter a hypoglycemic or hyperglycemic state. This type of prediction can be advantageous to the user because they can be alerted to such an impending condition, allowing them to take mitigating measures before the event occurs. For example, a meal or snack may take a certain amount of time to have a full impact on blood glucose levels, so the ability to roughly know (e.g., within 5 minutes or less, or within 10 minutes or less) when a hypoglycemic or hyperglycemic event is likely to occur, rather than the user being unaware of such an impending event, allows the user to take more appropriate mitigating measures. As an example, user activity data derived from accelerometer data can enable the CGM system of this disclosure to infer activity levels (e.g., high-intensity training) that indicate a significant impending change in blood glucose levels at a future predicted / inferred time. This may be particularly relevant to individuals with diabetes (e.g., type I or type II). Therefore, combining such data with predictive algorithms can provide users of the CGM system of this disclosure with significantly improved blood glucose predictions. For example, this type of predictive modeling may be more reliable than simply relying on the rate of change of blood glucose sensed by a CGM sensor, because such a rate of change measurement may track specific activities and, combined with lag time (the time it takes for plasma blood glucose to be fully reflected in an approximately equivalent change in interstitial fluid blood glucose), can lead to predictions of future blood glucose values ​​that may be inaccurate or useless to users of the CGM system.

[0195] Furthermore, it is recognized herein that ancillary data, as disclosed herein, can be used to improve data quality in ways that reduce noise in the system. One example of how noise in a CGM system can be reduced is through averaging methods. For example, in some cases, averaging over a longer time period helps reduce noise; however, a longer averaging time compared to blood glucose levels may undesirably introduce additional lag time into the reported CGM data. It is recognized herein that different noise filtering methods can be tailored for use during specific usage-based scenarios by relying on ancillary data combined with the raw CGM data stream. An example of a usage-based scenario might be very high levels of activity (e.g., high-intensity training), as identified by accelerometer data. In an implementation, upon detecting a specific activity pattern such as high-intensity training, the CGM system can switch to relying on noise reduction techniques (e.g., data filtering techniques) suitable for periods of high activity and potentially high levels of blood glucose variation. Then, as activity levels decrease and / or the rate of change in blood glucose levels decreases, the system can again switch to relying on different noise reduction techniques more suitable for periods of lower activity and / or lower levels of blood glucose variation.

[0196] Example

[0197] Example 1

[0198] This example demonstrates the correlation between data acquired via analyte sensors, accelerometers, and temperature sensors. Figure 9A and Figure 9B The diagram depicts current 902 corresponding to raw data obtained from the analyte sensor, temperature trajectory 904 corresponding to data obtained via a temperature sensor, and motion data 906 obtained from the accelerometer. Regarding the accelerometer data, an upper limit 910 and a lower limit 912 are shown, including operably defined boundaries. Figure 9A and Figure 9B In the diagram, the x-axis represents the number of hours in a day, and the y-axis represents the raw current in nA (left y-axis) and the temperature in °C (right y-axis). Figure 9A The data shows a 24-hour period corresponding to the 5th day after analyte sensor insertion, and Figure 9B The data shows a 24-hour period corresponding to the 6th day after the analyte sensor was inserted.

[0199] exist Figure 9A At this point, after the 20th hour, there was a sharp increase in temperature, corresponding to a corresponding increase in the current from the analyte sensor. Around 21 to 22 hours, both the increases in current and temperature tended to plateau. Figure 9B The temperature- and current-related patterns persisted until approximately 1.5 to 2 hours into the second day (day 6). Similarly, around the 20th hour of day 6, a similar increase in temperature and a corresponding increase in current associated with the analyte sensor were observed.

[0200] When correlated with accelerometer data, it is evident that the time periods during which temperature and analyte sensor current increase together correspond to periods of very low activity. Users confirm that these periods correspond to times when the user is asleep under a blanket. This, in turn, leads to an increase in temperature, and consequently, an increase in the current measured by the analyte sensor. Without correction, this could result in inaccurate blood glucose readings, as well as other undesirable problems such as triggering alarms and / or insulin pump activation. However, by using the methods disclosed herein, such activity patterns can be learned to include situations where the current increase does not reflect an actual increase in blood glucose, allowing for mitigation measures to avoid undesirable actions such as activating the insulin pump, triggering alarms, etc.

[0201] In this way, a CAM system (e.g., a CGM system) can operate with a corrected analyte value during periods when the predicted uncorrected analyte value may not reflect the actual analyte concentration sensed by a particular continuous analyte sensor. The technical advantage of predicting when a determined analyte value is predicted to be inaccurate is that it avoids several adverse consequences that might arise without such a strategy. For example, by employing the methods disclosed herein, users of a CAM system can avoid taking unnecessary steps to manage analyte levels at times when such actions are not actually required. This improves the safety characteristics associated with CAM systems as disclosed herein and thus increases user satisfaction. This method can further enhance user satisfaction by avoiding alarms, such as those that unnecessarily disturb the user. This is particularly relevant during periods of sleep or driving (as an example), where disturbances (if not representing underlying biological factors) could have adverse effects on the user's health and / or safety.

[0202] Although various example methods, apparatuses, systems, and articles of manufacture have been described herein, the scope of this disclosure is not limited thereto. Rather, this disclosure covers all methods, apparatuses, and articles of manufacture that fall fully within the scope of the appended claims, whether literally or under the doctrine of equivalents. For example, although example systems including components such as software or firmware executed on hardware are disclosed above, it should be noted that such systems are illustrative only and should not be considered restrictive. In particular, it is contemplated that any or all of the disclosed hardware, software, and / or firmware components may be implemented solely in hardware, solely in software, solely in firmware, or in some combination of hardware, software, and / or firmware.

[0203] Although certain embodiments have been shown and described herein, those skilled in the art will understand that numerous alternative and / or equivalent embodiments or implementations calculated to achieve the same purpose may replace the embodiments shown and described without departing from the scope. It will be readily understood by those skilled in the art that embodiments can be implemented in a very wide variety of ways. This application is intended to cover any modifications or variations of the embodiments discussed herein. Therefore, it is clearly intended that the embodiments be limited only to the claims and their equivalents.

[0204] Furthermore, according to embodiments of this disclosure, the following configurations 1-48 are provided:

[0205] 1. A method comprising:

[0206] A first data stream corresponding to the concentration of the analyte in the biofluid is obtained from the analyte sensor;

[0207] The first data stream is converted into analyte values ​​reflecting the concentration of the analyte;

[0208] Obtain one or more additional data streams from one or more auxiliary sensors;

[0209] Inferring the conversion from the first data stream to the analyte value based on the first data stream and the one or more additional data streams is predicted to be inaccurate; and

[0210] Take mitigation measures to avoid reporting inaccurate analytical values ​​to users.

[0211] 2. The method according to configuration 1, wherein the one or more auxiliary sensors are selected from pressure sensors, temperature sensors, accelerometers, and heart rate sensors.

[0212] 3. The method according to configuration 1, wherein inferring that the conversion from the first data stream to the analyzed value is predicted to be inaccurate further includes:

[0213] The first data stream and the one or more additional data streams are compared with a historical dataset that has been computed and processed to reveal data patterns corresponding to the analyte and auxiliary sensor data streams that indicate inaccurate conversions of the acquired data to analyte values.

[0214] 4. The method according to configuration 3, wherein processing the historical dataset further includes performing one or more computational operations selected from supervised learning, unsupervised learning, and reinforcement learning on the historical dataset.

[0215] 5. The method according to configuration 1, wherein taking mitigation measures further includes:

[0216] Apply a correction factor to the function that converts the first data stream into analytical values; and

[0217] Report the corrected analytical values ​​to the user.

[0218] 6. The method according to configuration 5, wherein reporting the corrected analytical values ​​to the user further includes:

[0219] Provide the user with an indication of the confidence level of the calibrated analytical value.

[0220] 7. The method according to configuration 5 further includes:

[0221] To prevent alarms associated with the analyte sensor from being activated when the calibrated analyte value does not exceed one or more predetermined analyte value thresholds.

[0222] 8. The method according to configuration 1, wherein taking mitigation measures further includes:

[0223] The user is warned that the analytical values ​​are currently inaccurate; and

[0224] The user is provided with a request to obtain the analyte value via another method that does not involve the analyte sensor.

[0225] 9. The method according to configuration 1, wherein the analyte sensor is a continuous analyte sensor implanted in the user's skin.

[0226] 10. The method according to configuration 1, wherein the analyte is blood glucose.

[0227] 11. A method for controlling an actuator associated with a continuous glucose sensor system, comprising:

[0228] The prediction of the transformation of the raw data stream obtained from the continuous glucose sensor implanted in the user's skin is expected to result in inaccurate blood glucose values ​​reported that do not represent the actual blood glucose concentration sensed by the continuous glucose sensor.

[0229] A correction factor is applied to the function that converts the raw data stream into blood glucose values ​​to obtain corrected blood glucose values ​​that more accurately reflect the actual blood glucose concentration sensed by the continuous blood glucose sensor within a predetermined threshold range of the actual concentration.

[0230] When the calibrated blood glucose value does not exceed one or more predetermined blood glucose value thresholds, the actuator is controlled in the first mode; and

[0231] When the corrected blood glucose value exceeds at least one of the predetermined blood glucose value thresholds, the actuator is controlled in the second mode.

[0232] 12. The method according to configuration 11, wherein the actuator is an auditory and / or vibratory alarm; and

[0233] In the first mode, controlling the alarm includes preventing the alarm from being activated, and in the second mode, controlling the alarm includes activating the alarm to alert the user to a hypoglycemic or hyperglycemic event.

[0234] 13. The method according to configuration 11, wherein the actuator is an insulin pump operatively coupled to the continuous glucose sensor system and capable of delivering variable amounts of insulin to the user based on a determined glucose level; and

[0235] In the first mode, controlling the insulin pump includes keeping the insulin pump off, and in the second mode, controlling the insulin pump includes activating the insulin pump based on the degree to which a corrected blood glucose value exceeds one of the predetermined blood glucose value thresholds corresponding to a hyperglycemic event.

[0236] 14. The method according to configuration 11, wherein the prediction is based at least in part on: data currently acquired from the continuous glucose sensor and at least one auxiliary sensor; and correlation data between the data currently acquired from both the continuous glucose sensor and the at least one auxiliary sensor and previously acquired data, the previously acquired data including data acquired from the at least one auxiliary sensor and the continuous glucose sensor or other similar auxiliary sensors and continuous glucose sensors used in previous sensor phases.

[0237] 15. The method according to configuration 14, wherein the one or more auxiliary sensors include a pressure sensor, a temperature sensor, and an accelerometer; and

[0238] Each of the one or more auxiliary sensors and the continuous blood glucose sensor is located on the user within the same area defined by a radius R, wherein the radius R is 2 cm or less.

[0239] 16. The method according to configuration 14 further includes processing the previously acquired data via a computational strategy capable of learning when a particular continuous glucose sensor data trend combined with a particular auxiliary sensor data trend results in inaccurate glucose values ​​in the absence of the correction factor.

[0240] 17. The method according to configuration 11 further includes providing a confidence level reflecting the corrected blood glucose value.

[0241] 18. The method according to configuration 17 further includes adjusting the one or more predetermined blood glucose thresholds based on a confidence level of the corrected blood glucose value.

[0242] 19. A blood glucose sensor system, comprising:

[0243] A continuous glucose sensor for use in mesotherapy implantation in the user's skin;

[0244] One or more auxiliary sensors selected from pressure sensors, temperature sensors, accelerometers, and heart rate sensors;

[0245] One or more actuable parts; and

[0246] A computing device that stores instructions in non-transitory memory, wherein the instructions, when executed, cause the computing device to:

[0247] Retrieve the first data stream from the continuous glucose sensor;

[0248] Retrieve one or more additional data streams from the one or more auxiliary sensors;

[0249] The first data stream and the one or more additional data streams are compared with a historical dataset, which includes learned association patterns of data corresponding to data previously acquired from the continuous glucose sensor and the one or more auxiliary sensors, wherein the learned association patterns are related to situations where the conversion of the first data stream to glucose values ​​results in glucose values ​​that do not reflect the actual glucose concentration measured via the continuous glucose sensor.

[0250] Based on the comparison, it is predicted that converting the first data stream into a blood glucose value would result in a blood glucose value that does not reflect the actual blood glucose concentration measured via the continuous blood glucose sensor.

[0251] Initiate a compensation operation to generate a corrected blood glucose value reflecting the actual blood glucose concentration, within a certain threshold range; and

[0252] If the compensation operation is able to generate a corrected blood glucose value that reflects the actual blood glucose concentration within a threshold of the actual blood glucose concentration, at least one of the one or more actuable components is controlled based on the corrected blood glucose value.

[0253] 20. The system according to configuration 19 further includes:

[0254] Operable to be linked to the display of the computing device; and

[0255] The computing device stores additional instructions to send the corrected blood glucose value, along with an indication that the value corresponds to the corrected blood glucose value, to the display device for the user to view.

[0256] 21. The system according to configuration 20, wherein the indication that the value corresponds to a calibrated blood glucose value includes one or more of the following: displaying the calibrated blood glucose value in a flashing manner opposite to a stable manner; displaying the calibrated blood glucose value in a color different from the color when displaying an uncalibrated blood glucose value; and displaying, together with the calibrated blood glucose value, a message providing the user with information indicating that the displayed value corresponds to a calibrated blood glucose value.

[0257] 22. The system according to configuration 19, wherein the computing device stores additional instructions to:

[0258] To prevent the calibration operation from being initiated during the time frame in which the first data stream is converted into a corrected blood glucose value via the compensation operation; and

[0259] The calibration operation is rescheduled at another time, provided that it is scheduled to occur during the time frame when the first data stream is converted into a corrected blood glucose value.

[0260] 23. The system according to configuration 19, wherein the computing device stores additional instructions to:

[0261] Assign confidence levels to adjusted blood glucose values; and

[0262] At least one of the one or more actuable components is controlled in part based on the confidence level assigned to the corrected blood glucose value.

[0263] 24. The system according to configuration 19, wherein the actuable component is an auditory and / or vibration alarm configured to alert the user to biological events related to blood glucose levels;

[0264] The computing device stores additional instructions to prevent the alarm from being activated if the corrected blood glucose value does not exceed one or more predetermined blood glucose value thresholds; and

[0265] The alarm is activated in response to a corrected blood glucose value exceeding one or more predetermined blood glucose value thresholds for a predetermined time period.

[0266] 25. The system according to configuration 19, wherein the actuable component is an insulin pump operatively linked to the computing device; and

[0267] The computing device stores additional instructions to prevent the insulin pump from being activated if the calibrated blood glucose level does not exceed a hyperglycemic threshold; and

[0268] The insulin pump is activated in response to a calibrated blood glucose level exceeding the hyperglycemia threshold for a predetermined time period, based on stored instructions.

[0269] 26. The system according to configuration 19, wherein the computing device stores additional instructions to:

[0270] The first data stream and the one or more additional data streams are compared with the historical dataset, which also includes learned association patterns of data relating to the conversion of the first data stream to blood glucose values, resulting in blood glucose values ​​that accurately reflect the actual blood glucose concentration measured via the continuous glucose sensor; and

[0271] When the predicted uncorrected blood glucose value reflects the actual blood glucose concentration, at least one of the one or more actuated components is controlled based on the uncorrected blood glucose value.

[0272] 27. A method for a continuous analyte sensor system, comprising:

[0273] Based on a first data stream retrieved from a continuous analyte sensor and at least a second data stream retrieved from an auxiliary sensor, it is determined that the user of the continuous analyte sensor system has adopted a posture that causes the first data stream to inaccurately reflect the concentration of the analyte sensed by the continuous analyte sensor.

[0274] During the time period in which the user is assuming the posture, a compensated analyte value accurately reflecting the concentration of the analyte sensed by the continuous analyte sensor is provided, based at least on the first data stream and the second data stream; and

[0275] During the time period in which the user is adopting the posture, at least one actuator of the continuous analyte sensor system is controlled based on the compensated analyte value.

[0276] 28. The method according to configuration 27, wherein the auxiliary sensor is an accelerometer.

[0277] 29. The method according to configuration 28, wherein the accelerometer includes a chip attached to a transmitter board circuit, the transmitter board circuit being included in a housing worn on the user's skin and located at a position on top of where the continuous analyte sensor is inserted into the user's skin.

[0278] 30. The method according to configuration 27, wherein the auxiliary sensor comprises one or more pressure sensors.

[0279] 31. The method according to configuration 30, wherein the one or more pressure sensors are coupled to an adhesive patch for securing the housing to the user's skin, and the housing is positioned on top of the location where the continuous analyte sensor is inserted into the user's skin.

[0280] 32. The method according to configuration 27 further includes detecting, at least based on the first data stream and the second data stream, that the user no longer performs the gesture; and

[0281] Provides an uncompensated analyte value that accurately reflects the concentration of the analyte detected by the continuous analyte sensor.

[0282] 33. The method according to configuration 27, wherein the at least one actuator includes an alarm configured to alert the user to an adverse event related to the blood level of the analyte.

[0283] 34. The method according to configuration 33 further includes preventing the alarm from notifying the user of the adverse event if the compensated analyte value does not exceed one or more predetermined analyte value thresholds.

[0284] 35. The method according to configuration 27, wherein the analyte is blood glucose; and

[0285] The continuous analyte sensor system is a continuous blood glucose monitoring system.

[0286] 36. The method according to configuration 27 further includes retrieving data from the auxiliary sensor at intervals between 10 and 20 seconds.

[0287] 37. A method for a continuous analyte sensor system, comprising:

[0288] Retrieve and reflect the first data stream corresponding to the current that reflects the concentration of the analyte sensed by the continuous analyte sensor;

[0289] The first data stream is converted into analyte values ​​that reflect the concentration of the analyte sensed by the continuous analyte sensor;

[0290] Retrieve one or more additional data streams from one or more additional temperature sensors located within a predetermined distance of the continuous analyte sensor;

[0291] Based on the one or more additional data streams, determine that the transformation of the first data stream is predicted to result in an analyte value that inaccurately reflects the concentration of the analyte sensed by the continuous analyte sensor; and

[0292] Based on the one or more additional data streams, a compensated analyte value is provided that more accurately reflects the concentration of the analyte within a predetermined threshold range of the concentration sensed by the continuous analyte sensor.

[0293] 38. The method according to configuration 37, wherein the one or more additional data streams include a second data stream retrieved from the first temperature sensor, the first temperature sensor being positioned on a transmitter plate, the transmitter plate being contained within a housing as part of the continuous analyte sensor system, the housing being configured to attach to the user's skin and being located on top of the continuous analyte sensor when the continuous analyte sensor is inserted into the user's skin; and

[0294] The provision of compensated analytical values ​​includes utilizing the characteristic temperature sensitivity of one or more temperature-sensitive electronic components that can adversely affect the first data stream and the temperature value corresponding to the second data stream in the model, and the model then outputs compensated analytical values.

[0295] 39. The method according to configuration 37, wherein the one or more additional data streams include a third data stream retrieved from a second temperature sensor positioned on the surface of the skin within a predetermined distance of the continuous analyte sensor; and

[0296] The provision of compensated analyte values ​​includes incorporating a user-specific lag time into the model that outputs the compensated analyte values. This user-specific lag time corresponds to the time delay between when the plasma analyte value is reflected in the equivalent change in the interstitial fluid analyte level, and is a function of the temperature value corresponding to the third data stream.

[0297] 40. The method according to configuration 37, wherein the one or more additional data streams include a fourth data stream retrieved from a third temperature sensor positioned on a portion of the continuous analyte sensor inserted into the user's skin; and

[0298] The provision of compensated analytical values ​​includes inferring the diffusion rate of the analyte into the sensor based on the fourth data stream, and incorporating the inferred diffusion rate into the model that outputs the compensated analytical values.

[0299] 41. The method according to configuration 37, wherein the analyte is blood glucose; and

[0300] The continuous analyte system is a continuous blood glucose monitoring system.

[0301] 42. The method according to configuration 37, wherein the compensated analytical values ​​are provided based at least in part on the current corresponding to the first data stream.

[0302] 43. The method according to configuration 37, wherein the predetermined distance is 2 cm or less.

[0303] 44. A method for a continuous analyte sensor system, comprising:

[0304] A first data stream is retrieved from a continuous analyte sensor configured to sense the concentration of analytes in the user's interstitial fluid;

[0305] Retrieve one or more additional data streams from one or more auxiliary sensors located within a predetermined distance from the continuous analyte sensor;

[0306] The first data stream and the one or more additional data streams are compared with a historical dataset, which has been computed and processed to reveal data patterns corresponding to the first data stream and the one or more additional data streams that indicate future events related to blood analyte levels; and

[0307] The user is provided with an alert that the future event is predicted to occur within a defined timeframe.

[0308] 45. The method according to configuration 44, wherein the analyte is blood glucose; and

[0309] The continuous analyte system is a continuous blood glucose monitoring system.

[0310] 46. ​​The method according to configuration 45, wherein the future event is one of a hypoglycemic event or a hyperglycemic event.

[0311] 47. The method according to configuration 44, wherein the determined time range is between 30 minutes and 90 minutes.

[0312] 48. The method according to configuration 44, wherein the one or more auxiliary sensors are selected from an accelerometer, one or more temperature sensors, one or more pressure sensors, a heart rate sensor, and a blood pressure sensor.

Claims

1. A method comprising: A first data stream corresponding to the concentration of the analyte in the biofluid is obtained from the analyte sensor; The first data stream is converted into analyte values ​​reflecting the concentration of the analyte; Obtain one or more additional data streams from one or more auxiliary sensors; Inferring the conversion of the first data stream to the analytical value based on the first data stream and the one or more additional data streams is inaccurate; as well as Take mitigation measures to avoid reporting inaccurate analytical values ​​to users.

Images