Cloud-Connected Glucose Monitors for Remote Health Tracking

Glucose level deviation detection for continuous glucose monitoring devices to improve user understanding and management of their glucose levels. The technique analyzes glucose measurements over time to detect deviations from past levels. It generates aggregated metrics for a user's glucose levels during specific time periods, like a day or multiple days. Deviations from expected levels are identified by comparing the aggregated metrics to previous periods. Users are alerted to deviations to help them recognize unusual patterns and take action.

Source

Enhancing wearable devices for monitoring analytes like glucose by adding supplementary sensors to provide additional physiological data. The additional sensors are integrated into separate wearable devices that can be connected to the primary analyte monitoring device. The primary device collects analyte data and the supplementary devices collect additional physiological data. Both datasets are transmitted to a central hub for analysis. This allows enhancing the analyte data with complementary physiological information without modifying the primary device. The supplementary devices can have different form factors and sensors compared to the primary device.

Source

A real-time, continuous glucose monitoring system for diabetes management that uses a microcontroller, glucose sensor, and Wi-Fi module to transmit glucose data to the cloud. The system allows individuals with diabetes to track their glucose levels in real-time and in real flow, improving the reliability and accuracy of the data compared to fingerstick testing. The system can also provide tailored healthcare solutions by allowing healthcare practitioners to access the real-time glucose data to improve treatment regimens. The use of the Internet of Things (IoT) and cloud computing enables continuous glucose monitoring without the need for frequent fingerstick tests.

Source

Instantaneous dynamic blood glucose monitor with an alarm function to improve the timeliness of glucose level alerts. The monitor has a sensor with a detection module to collect blood glucose data and a communication module to send it to a terminal. The terminal has a storage module, processing module, and separate alarm module. This allows the sensor to continuously send real-time glucose readings to the terminal which can process and analyze them. If a critical glucose level is detected, the alarm module can immediately trigger an alert without relying on the user to check the monitor.

Source

Remote monitoring system for diabetic patients that uses a communication system to collect physiological measurements from devices on the patient. A neural network analyzes the time series data to detect risks of hyperglycemia or hypoglycemia. If an alert is generated, it notifies the patient and/or offers insulin/carbohydrate recommendations to prevent blood sugar issues. The system allows remote monitoring of diabetic patients to detect and address potential glucose extremes outside of medical settings.

Source

Enabling secure and convenient transfer of glucose monitoring data to external systems like EMRs without requiring a wired connection or user account setup. The glucose monitoring system receives a request from an external system like an EMR to establish a connection for data sharing. It compares patient identifiers to confirm the requesting patient has glucose monitoring data. If so, it generates an association and sends a confirmation. If not, it denies the request. This allows external systems to request and receive glucose data without direct device connectivity or user account setup.

Source

Reducing blanking of sensor glucose signals in continuous glucose monitoring (CGM) systems by using multiple machine learning models trained for specific conditions. The CGM device inputs sensor data into multiple models, each trained for different data characteristics or abnormal conditions. The models generate predicted glucose values. The device combines the predictions to generate the displayed glucose value. This improves accuracy and reduces blanking compared to using a single model.

Source

Blood sugar management system that provides secure, scalable, and real-time blood glucose monitoring for artificial pancreas devices. The system uses a dedicated portable device for blood sugar management that communicates with a glucose monitor and insulin pump. The device has a processor, memory, and wireless modules for local glucose sensing, insulin dosing, and public network connectivity. This allows updating algorithms, receiving external data, and transmitting glucose/insulin info. The dedicated device provides secure, continuous, and scalable blood sugar management compared to smartphone apps or built-in pump algorithms.

Source

A real-time dynamic blood glucose monitoring system leverages cloud big data to enhance the accuracy of implantable glucose sensors by considering individual differences. The system collects historical glucose measurements from a user's finger meter and cloud server. It employs machine learning algorithms to establish a regression equation that links sensor signals, impedance, and historical glucose values. This approach enables the system to compensate for variations and adjust the sensor output to align with the user's specific glucose response.

Source

Enabling remote monitoring of health data like glucose levels from continuous sensors by allowing authorized users to access and view the data from a separate device. The system uses a primary sensor on the person being monitored, like a continuous glucose monitor, to send data to a server. Remote monitors, like family members or caregivers, receive notifications when events like low glucose are detected. They can then log in to the server to view the full sensor data and settings. This allows remote monitoring without needing separate sensors on each person.

Source

Smart watch with blood glucose monitoring that accurately detects and alerts on blood sugar levels while accounting for external factors that can affect the accuracy of wearable devices. The watch uses a multi-stage data processing method to analyze and correct blood sugar readings based on factors like skin transparency, sensor sensitivity, and ambient light. This mitigates the impact of external influences on the detection and provides more accurate blood sugar readings. The watch also predicts and alerts on abnormal blood sugar trends to enable proactive intervention before critical levels are reached.

Source

Transferring sensor context information between disposable devices in a glucose monitoring system to improve continuity and convenience when replacing expired devices. The system involves packaging and uploading sensor characteristics like calibration, communication settings, and conversion parameters from one disposable device to another during replacement. This allows the new device to seamlessly connect and continue monitoring without user calibration or configuration.

Source

Ecosystem that enables interconnection and data exchange between a blood glucose monitor and a continuous glucose monitor to provide improved glucose monitoring for diabetes management. The blood glucose monitor can request measurements from the continuous glucose monitor when discrepancies exceed thresholds. This allows cross-validation and verification of readings. The continuous glucose monitor can also generate alerts based on its data that are output by the blood glucose monitor. This provides suggestions for actions to take at times of high glucose levels based on trends identified from the continuous monitoring.

Source

An in vivo glucose monitoring system provides critical alerts for hypoglycemia and impending hypoglycemia while keeping communication dormant otherwise. The system features a transcutaneous glucose sensor with electronics that continuously monitor glucose levels. It detects hypoglycemic conditions based on glucose trends and generates alerts. Rather than constantly transmitting glucose data, the system waits for a request from a reader device. When an alert is active, a separate RF module is activated to send the alert specifically. This approach conserves power and communication bandwidth. Additionally, each alert reduces the sensor's lifespan by a fixed amount.

Source

Securely transmitting and managing glucose monitoring data from continuous glucose monitors to enable selective access for different purposes while protecting patient privacy. The data is classified into restricted and less-restricted categories based on sensitivity. Devices transmit data to a cloud infrastructure, which stores it separately. Applications request access to specific categories. This allows controlling who can view glucose levels versus diagnostics without revealing patient identity.

Source

A wearable medical device that can adjust the frequency of glucose measurements from a continuous glucose monitor (CGM) based on the user's glucose trend. The device processes the CGM data to determine the rate of change in glucose levels over time. If the rate indicates a rapid change, the device instructs the CGM to provide more frequent glucose readings. This allows faster detection of extreme glucose events to enable timely intervention. The device can also suspend insulin delivery based on the CGM data.

Source

Adaptive continuous glucose monitoring (CGM) system that improves CGM accuracy by accounting for modifications like sensor replacement and site location. The system receives glucose data from a CGM sensor inserted at a specific site. It uses historical data to build probabilistic models linking factors like carbohydrate intake, heart rate variability, and step count to glucose levels. When a new sensor is inserted at a different site, the system adjusts the user's glucose values based on the site's impact as estimated by the models. This compensates for location-specific errors and provides more accurate glucose readings.

Source

A machine learning blood sugar monitoring system using a continuous glucose monitoring (CGM) sensor that provides real-time, personalized blood sugar monitoring without frequent finger pricks. The system involves a patient app, CGM sensor, medical app, and server. The patient app collects CGM data, sets state info (meds, diet, exercise), and does OGTT tests. The app interacts with the server to process, analyze, and display the data. Unsupervised learning is used to extract features from the preprocessed CGM and state data. This allows tracking of integrated blood sugar trends, medication, diet, and exercise impact.

Source

A medical blood glucose monitoring system that enables more effective management and analysis of continuous glucose monitoring (CGM) data for diabetes patients. The system involves a sensor, transmitter, data receiving terminal, cloud server, and medical monitoring terminal. The sensor and transmitter communicate to send CGM data wirelessly to the terminal. The terminal uploads the data to the cloud, where it's correlated with user-inputted events like medication, diet, exercise, etc. The cloud then returns the event-associated CGM data to the terminal for display. This allows visualizing glucose trends with events overlaid. The system also calculates metrics like A1C and daily glucose variability.

Source

A continuous glucose monitoring system combines invasive and non-invasive measurements to deliver more accurate and continuous glucose level data. The system simultaneously takes an invasive blood glucose measurement and a non-invasive interstitial fluid glucose measurement. It then analyzes data from both sources to provide more reliable glucose estimates than using either method alone. The invasive measurement sets an initial baseline, while non-invasive measurements track changes. This approach helps address issues like time delay and hydration variability that affect non-invasive monitoring. Additionally, the system uses machine learning to predict future glucose levels based on historical data and user activity.

Source