# US 12,765,808 B2 · Techniques for image-based monitoring of blood glucose status > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,765,808 B2 - Document ID: US12765808B2 - Status: Granted - Kind: B2 - Application number: 17/003,854 - Filed: 2020-08-26 - Published: 2022-03-03 - Granted: 2026-10-20 - Earliest claimed: 2020-08-26 - Assignees: Insulet Corporation - Applicants: Insulet Corporation - Inventors: Ashutosh Zade; Joon Bok Lee; Yibin Zheng; Steven Cardinali - Web page: https://patentgrep.com/patent/US12765808B2 ## CPC - A61B 5/14532: {for measuring glucose, e.g. by tissue impedance measurement} - A61B 5/4839: {combined with drug delivery} - A61B 5/4848: {Monitoring or testing the effects of treatment, e.g. of medication} - A61B 5/7221: {Determining signal validity, reliability or quality (preventing, reducing or removing noise induced by motion artefacts A61B5/7207; noise originating from a therapeutic or surgical apparatus A61B5/7217)} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor} - A61B 5/7282: {Event detection, e.g. detecting unique waveforms indicative of a medical condition (cough events A61B5/0823; seizures A61B5/4094; sleep apnoea A61B5/4818)} - A61B 5/743: {Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots} - A61K 38/28: Insulins - A61M 5/1723: {using feedback of body parameters, e.g. blood sugar or pressure} - A61M 5/14248: {of the skin patch type} - A61M 2205/18: with alarm - A61M 2205/502: User interfaces, e.g. screens or keyboards - A61M 2205/52: with memories providing a history of measured variating parameters of apparatus or patient - A61M 2205/581: by audible feedback - A61M 2205/582: by tactile feedback - A61M 2205/583: by visual feedback - A61M 2230/201: Glucose concentration - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - A61K: PREPARATIONS FOR MEDICAL, DENTAL OR TOILETRY PURPOSES (devices or methods specially adapted for bringing pharmaceutical products into particular physical or administering forms A61J3/00; chemical aspects of, or use of materials for deodorisation of air, for disinfection or sterilisation, or for bandages, dressings, absorbent pads or surgical articles A61L; soap compositions C11D) - A61M: DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY (introducing media into or onto the bodies of animals A61D7/00; means for inserting tampons A61F13/26; devices for administering food or medicines orally A61J; containers for collecting, storing or administering blood or medical fluids A61J1/05); DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY (surgery A61B; chemical aspects of surgical articles A61L); DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR {(Electrotherapy, e.g. producing anaesthesia by the use of alternating or intermittent currents A61N1/36021)} ## Abstract Methods and apparatuses for performing a blood glucose monitoring process are described. For example, an apparatus may include at least one memory and logic coupled to the at least one memory. The logic may operate to determine patient monitoring information associated with a diabetic treatment of a patient, generate at least one monitoring information structure based on the patient monitoring information, generate at least one monitoring information image based on at least a portion of the at least one monitoring information structure, and process the at least one monitoring information image using a computational model to determine a blood glucose condition of the patient. Other embodiments are described. ## Claims ### Claim 1 An apparatus, comprising: at least one memory; and logic coupled to the at least one memory, the logic to: receive, as an input, quantitative patient monitoring information associated with a diabetic treatment of a patient, the patient monitoring information comprising at least one of a blood glucose level information, insulin dosage information, or insulin-on-board (IOB) information, generate a graph from the patient monitoring information, the graph comprising a temporal axis identifying historical readings of the patient monitoring information and a dependent axis showing the patient monitoring information for the historical readings, generate an image of at least a portion of the graph, the image comprising at least one digital image of the graph at a region of interest, process the image of the at least a portion of the graph using a computational model to determine, as an output, a predicted blood glucose condition of the patient, the blood glucose condition comprising one or more of a hypoglycemic episode, a hyperglycemic episode, a low blood sugar episode, a high blood sugar episode, or a normal blood sugar episode, the computational model configured based on historical monitoring information graph images to identify features representing an imminent blood glucose condition, and the processing comprising applying a filter to the image of the graph at the region of interest to determine if a trend in the graph at the region of interest matches the features, and administer a medicament with the apparatus based on the determined blood glucose condition. ### Claim 2 (depends on 1) The apparatus of claim 1, the computational model comprising a convoluted neural network (CNN). ### Claim 3 (depends on 1) The apparatus of claim 1, the blood glucose condition comprising a prediction of a future blood glucose level. ### Claim 4 (depends on 3) The apparatus of claim 3, the prediction comprising a level of confidence in the prediction. ### Claim 5 A computer-implemented method, comprising, via a processor of a computing device: receiving, as an input, quantitative patient monitoring information associated with a diabetic treatment of a patient, the patient monitoring information comprising at least one of a blood glucose level information, insulin dosage information, or insulin-on-board (IOB) information, generating a graph from the patient monitoring information, the graph comprising a temporal axis identifying historical readings of the patient monitoring information and a dependent axis showing the patient monitoring information for the historical readings, generating an image of at least a portion of the graph, the image comprising at least one digital image of the graph at a region of interest, processing the image of the at least a portion of the graph using a computational model to determine, as an output, a predicted blood glucose condition of the patient, the blood glucose condition comprising one or more of a hypoglycemic episode, a hyperglycemic episode, a low blood sugar episode, a high blood sugar episode, or a normal blood sugar episode, the computational model configured based on historical monitoring information graph images to identify features representing an imminent blood glucose condition, and the processing comprising applying a filter to the image of the graph at the region of interest to determine if a trend in the graph at the region of interest matches the features, and administering a medicament with an apparatus based on the determined blood glucose condition. ### Claim 6 (depends on 5) The method of claim 5, the computational model comprising a convoluted neural network (CNN). ### Claim 7 (depends on 5) The method of claim 5, the blood glucose condition comprising a prediction of a future blood glucose level. ### Claim 8 (depends on 7) The method of claim 7, the prediction comprising a level of confidence in the prediction.