Automated Insulin Delivery Systems

Predicting meal and exercise events for a user with diabetes using their historical glucose and insulin data to improve insulin delivery. The method involves calculating residuals between actual and predicted glucose values over time. Positive residual rates indicate a meal event and negative rates indicate exercise. This allows the insulin pump to respond appropriately to meals and exercise without manual input.

Source

The systems, devices, and methods described herein for providing medication dose guidance, particularly insulin dose guidance, for diabetes management. The dose guidance is based on analyzing a user's historical and real-time physiological data, like glucose levels, diet, activity, etc., to determine optimal insulin doses. The guidance can also account for factors like hypoglycemic risk, glucose dysregulation, and low alarm frequency. The goal is to provide personalized and safe insulin dose recommendations without requiring users to manually analyze their data.

Source

Determining optimal basal insulin infusion rates for diabetes management using a CGM system that accounts for sensor reliability. The method involves calculating an adjustment to the basal rate based on a current risk metric indicating hypo/hyper risk and a control-to-range algorithm with an aggressiveness parameter. This allows customizing the basal rate response to the sensor data quality. If sensor reliability is low, the aggressiveness parameter reduces the basal rate adjustment to prevent over-correction. Conversely, if sensor reliability is high, the parameter allows more aggressive adjustments for better glucose control.

Source

Method to accelerate rate of adaptivity of automated insulin delivery (AID) systems for people with diabetes who experience significant variations in insulin needs. The method involves calculating a modification coefficient using a ratio of current insulin variability to historical variability. This coefficient is used to generate a faster adaptive rate for calculating daily insulin requirements. This allows the AID system to more quickly respond to user's changing insulin needs, reducing time in hyper/hypoglycemia when they experience sudden spikes or drops in sensitivity.

Source

Robust method for optimizing insulin dosing to achieve target glucose levels in diabetes patients. It involves using historical autonomous glucose measurements and insulin infusions to calculate glycemic risk and insulin sensitivity factors for a patient. These factors are then used to generate a personalized basal rate titration plan and fasting glucose profile model. The plan guides insulin adjustments during future time periods to minimize risks and maintain target fasting glucose.

Source

Self-learning insulin dose supervision system for diabetes patients that uses machine learning to calculate personalized insulin doses based on a patient's blood sugar levels and meal parameters. The system acquires patient data, learns the relationship between blood sugar, carbs, insulin, and post-meal levels, and generates a dynamic medication adjustment model for that patient. It then calculates the pre-meal insulin dose using the model and alerts the patient if the calculated dose exceeds the doctor's limits or changes too much. This allows personalized insulin adjustment and monitoring beyond what a doctor can provide.

Source

Automatically determining the user's risk of hypoglycemia or hyperglycemia based on factors calculated using data available in an insulin pump or diabetes management system. The system analyzes factors like current glucose, insulin delivery history, and other datasets to calculate a risk. It provides real-time alerts to the user when the risk is indicated, along with recommendations for mitigating the risk. The risk calculation can also be adjusted based on factors like exercise to account for how activities affect glucose levels. Machine learning can further improve the risk calculation by weighting factors based on accuracy.

Source

A glucose level control system for diabetes management that can adapt insulin dosing based on long-acting insulin administration. The system determines a long-acting insulin dose recommendation based on fast-acting insulin during a first therapy period. During a second therapy period after long-acting insulin administration, it modifies fast-acting insulin dosing based on the recommendation. This enables optimization of overall insulin therapy when both fast-acting and long-acting insulins are used.

Source

A system and method for intelligent insulin dosing using a pen-based insulin delivery device. The system estimates insulin sensitivity adaptively to improve accuracy of insulin dose recommendations. It uses a Gaussian process model trained on patient data to predict blood sugar levels considering insulin sensitivity. A classifier based on physiological scenes like exercise, emotion, and ketosis relief further refines the prediction. This adaptive insulin sensitivity estimation significantly improves blood sugar prediction for better dosing decisions.

Source

Integrated diabetes management system that connects glucose monitoring devices, insulin pens, and other devices to a central reader and displays a unified view of glucose levels, insulin doses, and other data. The system aims to provide better diabetes management by allowing users to view and analyze glucose and insulin data in a more actionable and correlated way. It also enables automated data transfer from devices like insulin pens to the central reader. The system can display metrics like average glucose, low glucose events, insulin amounts, and carbohydrate intake over time. It can also provide alerts for missed doses or high glucose levels. The centralized view and analytics aim to provide more insights and enable better diabetes management compared to viewing device-specific logs separately.

Source

Customizing a glucose prediction model in an insulin delivery device to accurately predict glucose levels for users with insulin sensitivity or insulin insensitivity. The customization is done based on the user's past glucose readings using regression analysis to determine weightings for those readings. These weightings are then used to predict future glucose levels for the user. This customized prediction model provides more accurate glucose predictions for users with varying insulin sensitivity, improving insulin dosing decisions.

Source

CGM-based automated basal insulin titration for Type 2 Diabetes patients uses historical CGM data, basal insulin doses, hypoglycemia reports, and past recommendations to generate adjusted insulin doses that minimize hypoglycemia risk and avoid overdosing. The method involves estimating personalized dose-response models from CGM metrics, regularizing fits in the early days, incorporating glucose variability, and ensuring safe dose changes. By leveraging CGM's comprehensive view of glucose levels, this approach aims to improve insulin titration compared to fingerstick-based manual titration, reducing the risk of overdosing and minimizing hypoglycemia.

Source

An automated insulin dosing system for diabetes patients using subcutaneous insulin pumps operates via a central server that receives blood glucose data from glucose meters. The server calculates optimal insulin dosages based on aggregated glucose trends and transmits them to the patient's insulin pump. This system enables personalized insulin dosing based on historical glucose patterns rather than relying solely on current measurements.

Source

Managing diabetes using personalized machine learning algorithms and patient data to recommend and automatically administer insulin and carbohydrates. The system collects continuous glucose monitor (CGM) data, processes it, and uses machine learning to predict optimal treatments. It provides real-time updates to patients and caregivers and allows remote intervention. The algorithms are personalized based on factors like activities, foods, and weight. The system also facilitates communication between patients, caregivers, and providers.

Source

Apparatus to optimize insulin dosage regimen for diabetes patients between clinic visits. The device analyzes patient blood glucose data and adjusts insulin dosages to maintain future levels within a range. It uses algorithms to determine how much to vary long-acting, meal, and correction insulin based on past glucose trends. The device stores the initial insulin regimen set by the doctor, and then continually evaluates if adjustments are needed based on new glucose readings. It can also suggest immediate insulin corrections for high glucose readings.

Source

Allowing users of insulin pumps to customize insulin delivery parameters in a way that is easier and more intuitive compared to traditional methods. It presents a user interface with input devices for subjective parameters like "insulin need" that are interpreted by the pump's automatic insulin delivery algorithm. When the user inputs a subjective insulin need, it modifies a coefficient value used in the algorithm's calculations. This allows users to adjust a key parameter without having to understand the complex factors used by the algorithm. The pump then collects physiological data and determines insulin dosage based on the modified coefficient value and the collected data. This provides personalized insulin delivery that adapts to the user's specific needs and conditions.

Source

Self-adaptive insulin infusion method and system for closed-loop artificial pancreas that can complete insulin bolus infusion even if blood glucose detection signal is lost. The method involves calculating a blood glucose estimate based on the last detected value and derivatives. When conditions trigger, a corrected bolus is calculated and split into fast and slow infusions. This ensures insulin delivery during meals despite sensor loss.

Source

Automated blood glucose control system that uses a predictive algorithm with adaptive parameters to optimize insulin delivery based on subject-specific factors. The system calculates insulin doses using a pharmacokinetic (PK) model with control parameters that can change over time for each subject. These parameters, like absorption time constants, are adapted based on factors like insulin type, blood glucose level, subject characteristics, etc. The system uses sensors and user input to modify the PK model parameters to better match the subject's insulin response. This allows personalized insulin delivery that accounts for subject-specific factors to more accurately control blood glucose levels.

Source

Automated insulin delivery system that anticipates and responds to glycemic disturbances like meals and exercise using historical data. The system generates disturbance profiles from patient history that represent deviations from target glucose levels. Current patient data is compared to the profiles and probabilities are calculated to assess likelihood of matching. An anticipated disturbance profile is determined based on the probabilities. Insulin dosage is then calculated based on the anticipated disturbance profile. This allows the system to proactively adjust insulin delivery to mitigate glycemic excursions.

Source

Predicting blood glucose levels in people with Type 1 diabetes using a deep learning model trained on historical data. The model takes in inputs like meal intake, insulin doses, and baseline glucose levels to predict future glucose levels. This enables personalized insulin dosing schedules based on predicted glucose levels. The model uses a convolutional neural network (CNN) for feature extraction and a long short-term memory (LSTM) network for temporal dynamics. The goal is to accurately forecast glucose levels multiple steps ahead to better manage insulin administration for people with Type 1 diabetes.

Source

A feature for closed-loop insulin pumps to better handle meals and prevent high post-meal glucose levels. It allows the user to activate an "Eating Soon" mode when they anticipate eating soon. This mode lowers the insulin target range and delivers a correction bolus to reduce glucose levels before the meal. After a period or meal entry, normal target range resumes. This prevents overcorrecting or undercorrecting for meals.

Source

System for providing accurate insulin dose recommendations to patients with diabetes based on real-time blood glucose levels. The system allows healthcare providers to prescribe insulin dose plans for stabilizing blood glucose. Patients input their blood glucose levels and insulin doses. The system calculates optimized insulin doses based on rules in the plan. It displays the recommended doses to the patient and provides reminders to administer insulin. This helps patients follow complex insulin regimens for better glucose control.

Source

Adapting insulin requirements during pregnancy for people with Type 1 diabetes using an automatic insulin delivery system. The method involves scaling the pre-pregnancy total daily insulin requirement based on progress of the pregnancy cycle. This scaled requirement is used to calculate basal and bolus doses. Automatic bolus doses are administered in response to meal detection. The scaling factor varies week-by-week based on departure from a reference schedule.

Source

A diabetes management system that predicts future blood glucose levels and recommends corrective actions to prevent hypo or hyperglycemia. The system involves a local glucose monitor, a remote device, and a database. The user's current glucose is wirelessly transmitted to the remote device which calculates an insulin dosage based on historical data. The remote device then sends the suggested insulin back to the user's pump or provides recommendations for manual injections.

Source

Adaptive insulin infusion adjustment method for artificial pancreas devices to improve blood sugar control. The method involves generating an insulin infusion scheme for a user based on their current blood sugar state and a policy function. The scheme is then executed. The policy function is adaptively adjusted over time using user interaction data to better match individual insulin needs. This allows dynamically optimized insulin delivery based on real-time blood sugar levels.

Source

An artificial pancreas system for automated insulin delivery to manage diabetes. It uses machine learning algorithms to optimize insulin dosing based on continuous glucose monitoring. The system comprises a wearable glucose monitor, insulin pump, and a computing device. The computing device learns personalized insulin response characteristics from historical data. It calculates insulin doses in real-time to maintain glucose levels within a target range. The insulin pump delivers the calculated dose. The closed-loop system eliminates manual insulin selection and dosing.

Source

Customizing basal insulin delivery in automated insulin pumps to better regulate blood glucose levels for users. The system adaptively adjusts the basal insulin rate based on actual total daily insulin (TDI) needs rather than assuming 50%. It calculates the average actual TDI over a period and then updates the basal rate to match a fraction of that average. This provides more personalized basal delivery compared to the fixed 50% assumption.

Source

Glucose level management for diabetes without relying on patient input of carbohydrate intake. The technique involves predicting the glucose response to a meal based on contextual information like meal type, portion size, cooking method, etc. Instead of having the patient manually enter carbohydrate counts, the system uses machine learning to correlate contextual data with glucose absorption. This allows determining insulin doses without relying on patient input.

Source

Glucose level management for diabetes without relying on carbohydrate counting. The technique involves predicting the amount of glucose that will be absorbed into a patient's bloodstream over time based on meal context. It leverages machine learning to determine insulin doses based on meal information instead of relying on user input of carbohydrate amounts. This aims to provide more accurate insulin dosing without the burden and potential errors of manually counting carbs.

Source

Automated insulin delivery system for diabetes treatment that can increase insulin delivery limits when it detects signs of missed meal boluses. The system uses a closed loop algorithm to automatically adjust insulin delivery based on CGM readings. It has a limiter function to prevent excessive insulin increases. If the CGM indicates high glucose, rising levels, and possibly missed meal bolus, the limiter is increased to allow more aggressive insulin spikes. This helps address forgotten boluses and prevents hyperglycemia.

Source

Preprandial insulin dose optimization system for diabetics with few samples using machine learning and expert input. The system learns individualized insulin dose recommendations based on historical data, evaluates the credibility of predictions with few samples, and falls back to expert advice when predictions are unreliable. It also has safety constraints to prevent hypoglycemia. The system continuously learns and adapts insulin dose optimization over time.

Source

Intelligent medicine administering system that calculates insulin doses to optimize diabetes management. The system uses a pen device and companion app to calculate doses that account for factors like glucose trends, recent carbs, and insulin on board. It aims to provide more accurate dosing recommendations by compensating for factors beyond just current glucose levels. The app also optimizes finger stick vs CGM scans for BG control.

Source

Optimizing insulin dosing for diabetes patients using machine learning to analyze daily insulin patterns and glucose data. The method involves assessing glycemic risk, quantifying daily insulin aspects, and recommending changes to basal and bolus insulin based on target ratios and risk thresholds. It also accounts for outlier data and variability. The system aims to balance basal and bolus insulin while minimizing hypo/hyperglycemia risks.

Source

Individualized decision-making system for preprandial insulin dosage using Gaussian processes to improve postprandial blood sugar management for people with diabetes. The system learns patient-specific models of blood glucose metabolism from historical data, uses risk-sensitive control to determine insulin doses, and optimizes using Bayesian methods. It predicts postprandial blood sugar levels based on premeal values and insulin infusion, with a goal of reducing hyperglycemia and hypoglycemia risk.

Source

Optimizing insulin dosing for diabetes patients using a system that leverages patient input, sensors, and correction factors to determine and adjust insulin doses. The system receives a blood glucose status input from a patient device, calculates an initial insulin dose, and optimizes it based on correction factors. This optimized dose is then facilitated to the patient's insulin pump or pen. The system can also measure impedance in the patient's tissue to proactively control insulin delivery.

Source

Automatic insulin delivery system for diabetes management that responds to meal announcements to estimate and deliver insulin without requiring user input of carbohydrate intake. The system estimates meal-related insulin needs based on factors like recent insulin delivery, current glucose, and meal announcement time. It adapts insulin delivery based on glucose trends after meals. This allows automated insulin dosing without user carb entry for meal compensation.

Source

Automatic monitoring system for optimizing diabetes treatment based on insulin injections. The system analyzes raw glucose data and existing insulin plans to recommend personalized insulin dosing and management tips. It identifies basal patterns, bolus needs, and event correlations from the raw data. This allows adjusting the insulin plans to better fit the user's routine and glucose trends. The system can also validate existing plans if glucose levels are good.

Source

Closed-loop insulin infusion systems using orthogonally redundant glucose sensors for improved accuracy and reliability. The system has two glucose sensors, one optical and one electrochemical, to provide orthogonal redundancy. An algorithm combines the sensor data to improve accuracy and reliability. If one sensor fails, the other can provide glucose values. The sensors have features like distributed electrodes and membrane barriers to reduce drift and fouling. The system uses on-demand calibration rather than frequent fingersticks.

Source

Preemptively alerting a user during operation of a fluid infusion device like an insulin pump to avoid hypoglycemic or hyperglycemic events. It calculates a homeostasis metric based on current glucose, insulin, and future insulin deliveries. If the metric indicates excess insulin, it alerts the user to potential hypoglycemia even if current glucose is normal. Similarly, if the metric indicates insufficient insulin, it alerts for potential hyperglycemia even if current glucose is high. This provides actionable alerts before events occur, versus waiting for glucose to change.

Source

Detecting missed bolus insulin injections and meal sizes to improve diabetes treatment. It uses machine learning to analyze blood glucose, insulin, and carb intake data to generate probabilities of meals and missed boluses. This allows for detecting missed injections and estimating meal sizes. The detection can trigger alerts, adjustments to insulin dosing, and recommendations.

Source

Detecting missed insulin doses and meal ingestion in people with diabetes using machine learning techniques. The method involves generating a meal size propensity record based on historical insulin doses and carb announcements. It classifies time periods based on glucose and dose to identify meal start times. By analyzing regressions, it associates missed doses with meals. This data can then be used for diabetes treatment adjustments.

Source

Modifying closed-loop insulin delivery algorithms to prevent glucose oscillations during eating periods when a meal announcement is received. Instead of just increasing the basal rate, the insulin on board (IOB) target is increased. This is done by activating a pre-meal scale that modifies the inner IOB loop of the closed-loop algorithm. This scale increases the IOB target when a meal announcement is received. This allows the system to account for the unknown carb intake and prevent glucose spikes/crashes.

Source

Medical device and method for determining insulin doses for diabetes management with improved glycemic control and safety features. The device has functions to modify initial dose settings, calculate stepwise dose adjustments, and terminate dose increases based on glycemic events. It protects against unauthorized changes and provides alerts when doses are not appropriate. This aims to prevent overdosing or underdosing by adaptive dose progression and termination triggered by events like hypoglycemia.

Source

Optimizing insulin delivery for new diabetes patients using automatic insulin delivery systems. The technique involves setting an initial total daily insulin dose based on user weight and reducing factors, then adjusting it over time based on HbA1c levels. It allows customizing insulin needs for newly diagnosed diabetics without historical data. The system calculates an initial adjusted total daily insulin factor based on user weight and reduction factors. It checks if this exceeds a maximum algorithm threshold. If so, it sets a lower total daily insulin dose. It then monitors glucose levels over time and adjusts the insulin dose based on HbA1c levels. This allows tailoring insulin delivery for new diabetics during the honeymoon phase when insulin needs fluctuate rapidly.

Source

Autonomous glucose control system that allows users to manually input insulin doses in addition to the system's automated dosing. The system generates a control signal based on real-time glucose levels to regulate insulin delivery. It also provides an interface for users to enter dose amounts. The system attempts to deliver the user-specified dose and incorporates it into subsequent autonomous dosing calculations. This allows users to manually input meal insulin doses while the system handles bolus and basal insulin. The user-entered dose bounds are enforced to prevent overdosing.

Source

Personalized blood glucose regulation for optimizing diabetes management using AI models trained on individual data. The method involves generating a personalized blood glucose regulation model for a diabetic patient based on their historical data. This model is then used to predict blood glucose levels, identify risks of excursions, and provide personalized insulin dosing recommendations to optimize regulation. The models can be generated locally or remotely by a server. The personalized models account for factors like diet, activity, and infection to improve accuracy compared to generic protocols.

Source

Glucose management system for insulin delivery that reduces user burden and error by avoiding the need for manual input of physiological and behavioral data. The system calculates insulin doses based on previous delivery and estimated glucose without using recent user-entered data. This allows automated insulin delivery without requiring users to constantly monitor and provide their own data. The system can still adapt insulin delivery without user input to bring glucose closer to target levels. It can also avoid alerting users when glucose is trending low or high.

Source

Determining insulin dosing recommendations for diabetes management using a method called Linear Quadratic (LQ) control. The method involves estimating the patient's physiological state from real-time glucose measurements using an adaptive filter, then using LQ optimization to calculate the optimal insulin dosage based on that estimated state. The LQ control provides a data-driven, personalized insulin dosing recommendation that takes into account the patient's unique physiology and glucose dynamics.

Source

Improving automated insulin delivery systems for people with type 1 diabetes through personalized adjustments based on user data beyond just CGM glucose readings. The technique leverages underutilized data streams like sensor errors, user interaction, and bolus estimates to better reflect user physiology and behavior. It adjusts insulin delivery recommendations based on factors like sensor site issues, user concern levels, and bolus accuracy estimates. This enables more accurate and optimized insulin delivery tailored to individual users beyond relying solely on CGM glucose readings.

Source

Blood glucose management system for diabetes patients using reinforcement learning. The system involves training a decision network model based on reinforcement learning to determine optimal insulin doses for diabetes patients. The model learns from historical state data of blood glucose, insulin, and carb intake. The current state is fed to the model to predict the next insulin dose. This allows personalized closed-loop blood glucose control without modeling the glucose-insulin dynamics. The model is trained over a set of interactions with patients until performance metrics meet thresholds.

Source