40 results about "Insulin dose" patented technology

A processor-implemented method comprises obtaining measured glucose values of a person, fitting a physiological model to a portion of the measured glucose values within a time window after a start of a meal to determine meal-specific values of parameters of the physiological model that characterizes the person's glycemic response to the meal, estimating an amount of residual glucose or residual carbohydrate of the meal that would not be counteracted by insulin already delivered to the person using the physiological model and the meal-specific values of the parameters of the physiological model, and determining a dose of a correction bolus to be delivered to the person based on the amount of residual glucose or residual carbohydrate of the meal.

A diabetes management system optimizes glucoregulatory hormone delivery using a connected glucoregulatory hormone delivery system and a computing device with a processor and non-transitory memory. The system receives glucose management data (glucose, insulin delivery, heart rate, or carbohydrate consumption data) from sensors. A digital twin metabolic model is selected and initialized based on the received data. The system simulates diabetes treatment interventions to predict glucose dynamics and determines an optimized glucoregulatory hormone parameter (e.g., insulin dose or increment that minimizes hyperglycemia and hypoglycemia risk). The determined glucoregulatory hormone parameter is transmitted to the connected glucoregulatory hormone delivery system, which may include an automated insulin delivery (AID) system or a connected insulin pen system, for implementation. By integrating real-time physiological data with predictive metabolic modeling, the system enhances glucoregulatory hormone therapy, providing personalized adjustments to improve glucose control.

Disclosed are systems and methods for determining a dose of insulin that compensates for past carbohydrates consumed, adjusts for blood glucose (BG) trend as well as BG value, and mitigates potential inaccuracies associated with double-counting or overcorrecting, where safeguards are applied to the determination of the insulin dose.

The invention discloses an insulin injection data management system, which relates to the technical field of medical health information and comprises a data acquisition module for acquiring injection operation data and blood sugar data from an insulin injection pen and lifestyle data input by a user; the intelligent analysis module is used for generating insulin dose recommendation information through a predefined dose calculation model on the basis of the injection operation data, the blood glucose data and the life style data, and generating injection site rotation recommendation information on the basis of injection site information in the injection operation data; the early warning prompt module is used for generating and outputting a dose early warning and a failure early warning based on dose information and temperature information in the injection operation data; and the medical care collaboration module is used for providing a data access interface for authorized medical care personnel and adjusting parameters of the dose calculation model based on remote instructions of the medical care personnel. And accurate and dynamic recommendation of dosage, scientific alternating guidance of injection parts and active early warning of dosage and failure are realized.

Systems and methods are provided for reconciling untrusted data of a subject using trusted data pertaining to the subject. Systems and methods are directed to evaluating differences in predicted data with respect to corresponding received data. Systems and methods estimate metabolic states from a combination of trusted and untrusted metabolic inputs, along with optionally using a personalized mathematical model with parameter optimization. Systems and methods provide for reconciled untrusted inputs with their measured impact of the glycemic signals that is consistent with a metabolic model. Estimation of future metabolic states for decision support and automated insulin dosing is enabled. Replay of scenarios with estimated or reconciled data is also provided.

A medical device and method for determining a basal dose of insulin and a bolus dose of insulin to be administered for glycemic control is provided. The medical device includes an insulin pump, a control interface including a button configured to select one of a plurality of present bolus insulin doses based on input from a user (e.g., a patient), and a controller configured for executing instructions to determine a basal insulin delivery rate based, at least in part, on a total daily basal insulin dose and to determine the plurality of preset bolus insulin doses based, at least in part, on a total daily bolus insulin dose.

In the present invention, a program causes a computer to execute processing for: acquiring time series data indicating the glucose level and the lactate level of a patient in a time series; estimating the blood glucose level of the patient after a prescribed period of time on the basis of the time series data of the glucose level and the lactate level; and determining a dosage of insulin to the patient on the basis of the estimated blood glucose level. Preferably, the program estimates the blood glucose level after a prescribed period of time by inputting the acquired time-series data of the glucose level and the lactate value into a model trained so as to estimate the blood glucose level after the prescribed period of time when the time-series data of the glucose level and the lactate level is input.

Methods, systems, and apparatuses are provided for dynamically adjusting the sensitivity of a computer-implemented detector for detecting missed insulin boluses. The disclosed methods, systems, and apparatuses receive blood glucose measurements and insulin dosing information for a user and analyze the received information to detect whether the user likely ingested food without taking an insulin bolus. The sensitivity level of the detector can be dynamically adjusted based on contextual information about the user to adjust for the user's context, environment, and / or conditions. If the detector detects a likely missed bolus, the detector can generate a user notification.

This invention relates to the field of clinical medical and nursing device technology, specifically to an auxiliary turntable for blood glucose management and insulin dose adjustment in critically ill patients. It includes a base and a recommendation component. A support column is fixedly connected to the top of the base. The recommendation component includes a recommendation disc fitted outside the support column. A judgment component, including a judgment disc fitted outside the support column, is fitted outside the support column and is located on top of the recommendation cover. An identification component, including an identification disc fitted outside the support column, is fitted outside the support column. A base component, including a base disc fitted outside the support column, is located on top of the identification cover. Through the base, support column, and four sets of adjustment components, standardized and visual matching of multiple blood glucose indicators and insulin adjustment recommendations is achieved. Combined with three-color risk label strips, it quickly identifies abnormal blood glucose levels and fluctuation risks, enabling early detection and intervention, and reducing dose adjustment errors due to experience.

A reinforcement learning process with self attention is used for insulin dosing decisions in an automated medical system. The State-Action-Reward-Next State (SARS) sequence is used. The state represents the current condition, including recent continuous glucose monitoring readings, insulin doses, meal information, and potentially other relevant factors like time of day or physical activity levels. Based on this state, the agent takes an action by deciding on an insulin dose. It then receives a reward, a numerical value quantifying the quality of the action, based on resulting glucose levels and their proximity to the target range. This leads to a new state, and the process repeats. Through this iterative process, the algorithm updates the neural network weights, allowing the agent to learn which actions lead to better outcomes in different states.

The application relates to the field of medical health data processing, and specifically provides a personalized insulin dose recommendation method and device for a diabetes patient, which has the following steps: S1, multi-source data preprocessing: collecting real-time dynamic data and static personalized parameters of the patient, performing outlier elimination, missing value completion, timestamp alignment and feature standardization processing on the data, and generating a time sequence matrix for input of an adaptive model; S2, constructing and training an LSTM-GRU blood glucose prediction model; S3, constructing and training a reinforcement learning dose decision model; and S4, closed-loop optimization and dose recommendation. Compared with the prior art, the application can significantly improve the accuracy and personalization degree of insulin dose recommendation, and provides reliable technical support for precise blood glucose management of the diabetes patient.

A method of improving insulin delivery includes detecting a dosing event of an upcoming insulin dose, identifying a next injection site to recommend to a user for the upcoming insulin dose, and transmitting a recommended injection site to a delivery device to be displayed on the delivery device. The method further includes receiving a user selection of a plurality of injection sites to include within an injection site recommendation profile, receiving a user selection of an injection cycle to utilize within the injection site recommendation profile, and generating an injection site recommendation profile.

A technique for treating diabetes that recognizes patient insulin sensitivity is a time-varying physiological parameter. The described techniques for treating diabetes include measuring interstitial fluid glucose concentration, reading insulin delivery data, determining patient insulin sensitivity based on the interstitial fluid glucose concentration and insulin delivery data, and a time-varying physiological parameter, and dispensing an insulin dose from an insulin delivery device based on the determined patient insulin sensitivity.

The present disclosure describes a closed-loop control system based on glucose prediction, and related methods and apparatus, a control device of the closed-loop control system configured to determine a current glucose concentration, detect a training condition, retrieve stored glucose data for a first predetermined period of time in response to triggering of the training condition, and control the stored glucose data for a second predetermined period of time. Retrieving insulin delivery data in a second predetermined time period, processing the heart rate data in the first predetermined time period to obtain a heart rate statistical value, processing the body temperature data in the first predetermined time period to obtain a body temperature statistical value, and updating a prediction model based on the stored glucose data, the insulin delivery data, the heart rate statistical value and the body temperature statistical value, based on the current glucose concentration, the data related to the current glucose concentration and the updated prediction model, a glucose prediction value corresponding to the current glucose concentration is obtained, and the insulin dosage provided by the infusion device is determined based on the glucose prediction value. According to the invention, the correctness of the insulin dosage can be improved.

A continuous glucose monitor (CGM)-driven basal insulin titration system and method for patients with Type 2 Diabetes can be adapted to the needs and concerns of subjects just starting on basal insulin therapy. The method uses as inputs historical CGM data, basal insulin dose information, reports of hypoglycemia, and past recommendations and generates an adjusted insulin dose along with a report advising whether to continue the titration process, or to stop. The method can generate a new recommendation on a regular basis (e.g., each day) until it determines an adequate, consistent dose size.

A technique for treating diabetes that recognizes patient insulin sensitivity is a time-varying physiological parameter. The described techniques for treating diabetes include measuring interstitial fluid glucose concentration, reading insulin delivery data, determining patient insulin sensitivity based on the interstitial fluid glucose concentration and insulin delivery data, and a time-varying physiological parameter, and dispensing an insulin dose from an insulin delivery device based on the determined patient insulin sensitivity.

A method, system, and computer readable medium for implementing the Adaptive Bio-Behavioral Control concept, which allows for bi-directional, human-machine co-regulation of metabolic disorders, such as diabetes mellitus. The Adaptive Bio-Behavioral Control concept may encompass, but is not limited thereto, three modules: a) a Physiological Adaptation Module which processes a user's historical data to estimate a personalized model of the user's glucose metabolism and to calculate suggested in-sulin-dosing parameters; b) a Behavioral Adaptation Module which assists the user's adaptation to the treatment action by determining a plurality of actionable information and risk assessments based on the user's glucose monitoring records; and c) a Replay Module which computes a simulation of effects from hypothetical changes to the user's treatment or behavior based on a personalized model of the user's glucose metabolism.

The invention belongs to the field of biological information, and relates to a blood glucose time sequence data analysis-based insulin dose automatic recommendation system, which comprises input data, a codec and a classifier, and is characterized in that the codec is used for sequence compression and recovery; the classifier is used for insulin prescription recommendation. Based on an artificial intelligence technology, by using big data and a machine learning algorithm, differences between different patients can be better understood, features can be more accurately extracted from changes of blood glucose levels of the patients, personalized treatment schemes are provided for the patients, doctors are helped to better manage illness states, the treatment effect is improved, and the treatment effect is improved. And the living quality of the patient is improved. According to the method, the features are automatically extracted from the data through the algorithm, intervention of doctors and experts is not needed, a new solution is brought to treatment of diabetes, the application prospect is wide, and better medical health care service is expected to be brought to diabetic patients in the global range.

The invention discloses an insulin accurate adjustment method and system based on artificial intelligence, and the method comprises the steps: collecting monitoring data and physiological parameter data of a preset target, and carrying out the preprocessing of the monitoring data and physiological parameters; constructing a time sequence blood glucose curve according to the monitoring data and the physiological parameters to obtain a personalized metabolic map, and performing time sequence change analysis according to the personalized metabolic map and the insulin concentration to obtain insulin sensitivity; calculating a target insulin dosage according to the monitoring data and the insulin sensitivity, performing personalized correction on the target insulin dosage according to personalized data to obtain a corrected dosage, and constructing a blood glucose prediction model based on machine learning according to the monitoring data to obtain predicted blood glucose data; and according to the corrected dose and the predicted blood glucose data, constructing a diabetes insulin accurate regulation model, inputting to-be-regulated data into the diabetes insulin accurate regulation model, and outputting a regulation result.

The invention discloses an endocrinology department medication dosage reminder with a blood glucose monitoring function, and relates to the technical field of medical auxiliary equipment, the endocrinology department medication dosage reminder comprises a wearable equipment shell, and a multi-mode physiological monitoring module, a medication management module, a core processing module, a man-machine interaction module, a data communication module and a power management module are integrated in the wearable equipment shell; the multi-modal physiological monitoring module is used for collecting multi-dimensional data and dynamically correcting the medication dosage, the timeliness of medication dosage reminding is improved, the carbohydrate intake of a user is accurately obtained through the image recognition and manual input functions of the diet recording module, and the user experience is improved. The insulin dosage during meal is calculated in real time according to the insulin-carbohydrate ratio, postprandial hyperglycemia caused by diet fluctuation is avoided, in addition, through bidirectional interaction of the data communication module, the cloud end and the doctor end and the near-infrared sensor array design of the noninvasive blood glucose monitoring unit, the blood glucose detection accuracy and the anti-jamming capability are improved.

A system for titrating a basal insulin dose that includes a glucose monitoring device configured to collect glucose data of a user, processors in communication with the glucose monitoring device, and a memory coupled to the processors. The processors are configured to determine an initial basal insulin dose, receive insulin data and glucose data during a titration period. The validity of each day is assessed, and a titration glucose level is determined for each valid day. The titration glucose level for each day is compared to glucose level thresholds, and a recommended adjustment to the basal insulin dose is determined based on the comparison.

A system for predicting blood-glucose concentration includes a blood-glucose monitoring device including a sensor configured to capture blood-glucose levels, a processor, and a memory. The memory includes instructions, which, when executed by the processor, cause the system to: access data of meal intake for a person with type 1 diabetes, data of insulin doses administered to the person, data corresponding to a physical activity of the person, and data of blood-glucose levels in the person, captured by the sensor; predict by a deep learning network blood-glucose concentration levels for the person at predetermined time intervals based on the accessed data of meal intake, data of insulin doses, data corresponding to the physical activity, and data of blood-glucose levels in the person; and determine an insulin administration schedule based on the predicted blood-glucose concentration levels for the person, the insulin administration schedule including a dosing schedule.

Disclosed are examples that include receiving information related to ingestion of a meal. The information may include a coarse indication of a size of the meal, a relative time of ingestion of the meal, and a general composition indication of the meal. A blood glucose measurement value received within a predetermined time range of a relative time of ingestion of the meal may be identified. Settings for a delay and an extend parameter and a delivery constraint may be determined. A meal model may be modified using the determined settings for the delay parameter, the extend parameter, and the delivery constraint. The modified meal model may be used to determine a dose of insulin to be delivered in response to the received information. An instruction indicates a determined dose of insulin to be delivered may be output for delivery to a drug delivery device.

Systems, devices, and techniques are disclosed for providing personalized insulin dose recommendations for a patient. In some aspects, a method includes generating a physiological model for estimating glucose values of a patient based on historical data including a history of glucose values and a history of insulin doses over a window of time during which the patient ingests multiple meals. The method may also include estimating an effect of the plurality of meals on the glucose value of the patient using the physiological model and the historical data, and receiving a first meal size indication for a first meal ingested by the patient. The method may also include outputting a first meal-time bolus insulin dose recommendation based on the effect of the multiple meals on the glucose value of the patient and the first meal size indication.

A system for monitoring a patient includes one or more processors and a sensor device implemented in circuitry. The system is configured to measure, using the sensor device, a blood glucose status of the patient, and determine, using one or more processors, an initial insulin dose for the patient based on the blood glucose status of the patient. The system is further configured to optimize the initial insulin dose for the patient, based at least in part on a correction factor, to create an optimized insulin dose for the patient. The system is configured to facilitate therapy, using the one or more processors, based on the determined optimized insulin dose.

This application discloses an insulin pump dose adjustment method, system, device, and storage medium. The insulin pump dose adjustment method includes acquiring the target user's electronic health record, real-time blood glucose data, and perioperative stress index data, wherein the perioperative stress index data includes the target user's surgical type and anesthesia method; inputting the electronic health record, real-time blood glucose data, and perioperative stress index data into a trained insulin pump dose prediction model to obtain the insulin dose prediction result output by the trained insulin dose prediction model; and converting the insulin dose prediction result according to a preset standardized format to obtain a standardized insulin dose prediction result, which meets the blood glucose management needs of the user during the perioperative period.

Systems and methods are provided for reconciling untrusted data of a subject using trusted data pertaining to the subject. Systems and methods are directed to evaluating differences in predicted data with respect to corresponding received data. Systems and methods estimate metabolic states from a combination of trusted and untrusted metabolic inputs, along with optionally using a personalized mathematical model with parameter optimization. Systems and methods provide for reconciled untrusted inputs with their measured impact of the glycemic signals that is consistent with a metabolic model. Estimation of future metabolic states for decision support and automated insulin dosing is enabled. Replay of scenarios with estimated or reconciled data is also provided.

To provide machine learning in an artificial pancreas.SOLUTION: The artificial pancreas system may include a wearable blood glucose monitoring device 104, an insulin delivery system 106, and a computing device 108. In general, wearable blood glucose monitoring devices continuously provide blood glucose measurements of a person. An artificial pancreas algorithm, which may be implemented in a computing device, determines a dosage of insulin to deliver to the person based on various aspects in order to maintain the person's blood glucose within a target range, as indicated by their blood glucose measurements. The insulin delivery system then delivers those determined dosages to the person. As the artificial pancreas algorithm determines the insulin dosage of the person over time and the effectiveness of the insulin dosage to maintain the blood glucose level of the person in the target range is observed, the model underlying the artificial pancreas algorithm may be updated to better determine the insulin dosage.SELECTED DRAWING: Figure 1