Abstract: Disclosed here is a computer-based device and related methodology that manages use of a dual-mode insulin infusion device. The infusion device operates in a manual insulin delivery mode or an automated closed-loop insulin delivery mode. The methodology receives closed-loop pump data for a user of the infusion device, the closed-loop pump data including data indicating basal insulin delivered by the infusion device during operation in the automated closed-loop insulin delivery mode for at least one defined period of time. The methodology analyzes the closed-loop pump data to generate updated basal rate data for the user, and generates, from the updated basal rate data, a recommendation to adjust a manual-mode basal rate setting of the infusion device. In certain scenarios, the infusion device is controlled such that the manual-mode basal rate setting is adjusted in accordance with the recommendation.

Abstract: A processor-implemented method includes obtaining measurement data indicative of a physiological condition measured by a sensing arrangement located at a site on a body, determining a lag associated with the sensing arrangement based on a relationship between the measurement data and reference data, and identifying, based on the lag, the site at which the sensing arrangement is located from a plurality of sites on the body.

Abstract: A method for providing blood glucose data is provided. In response to a suspension of a continuous basal insulin delivery, by an insulin delivery pump, the method identifies a condition indicating continuing hypoglycemia that continues when basal insulin delivery is suspended; and performs an action, by the insulin delivery pump, based on identifying the condition.

Abstract: An insulin infusion device and related operating methods are disclosed. An operating method maintains a configurable, patient-specific, target glucose setpoint for a user of the insulin infusion device, collects historical data associated with operation of the insulin infusion device, and calculates, from the historical data, a target glucose setpoint profile for the user of the insulin infusion device. A current target glucose setpoint value is automatically adjusted over time during a closed-loop operating mode of the insulin infusion device, in accordance with the calculated target glucose setpoint profile. In certain embodiments, the historical data is analyzed to determine a clinically preferred target glucose setpoint value for the user, which is stored for use during the closed-loop operating mode.

Abstract: A system includes one or more processors and one or more processor-readable storage media storing instructions which, when executed by the one or more processors, cause performance of: associating a medical device with an intermediate device, obtaining, from the medical device via the intermediate device, measurement data correlative to a condition of a user, determining updated control information for the medical device based at least in part on the measurement data, and streaming the updated control information to the medical device via the intermediate device.

Abstract: Medical devices and related systems and operating methods are provided. A method of operating an infusion device capable of delivering fluid influencing a physiological condition to a patient involves obtaining an event indication, such as a meal indication, determining an initial bolus amount based on the event indication, and determining predicted values for the physiological condition of the patient during a time window into the future based at least in part on the initial bolus amount. When the predicted values violate a threshold during the time window, the control system identifies an adjusted bolus amount that results in the predicted values for the physiological condition satisfying the threshold during the time window from within a search space defined by the initial bolus amount and operates an actuation arrangement of the infusion device to deliver the adjusted bolus amount of the fluid to the patient.

Abstract: An insulin infusion device and a related operating method are disclosed. The method obtains a blood glucose (BG) measurement of a blood sample from a user, displays the BG measurement on a display element of the infusion device, and receives a confirmation input that indicates user acceptance of the displayed BG measurement. In response to the confirmation input, a glucose sensor calibration routine is automatically initiated, and an insulin bolus calculation is automatically initiated. The calibration routine and the bolus calculation use the confirmed BG measurement. The method continues by controlling delivery of insulin, in accordance with the calculated insulin bolus, from a fluid reservoir of the insulin infusion device. The sensor calibration routine and the insulin bolus calculation are both performed without any additional user involvement or interaction with the user interface other than the user acceptance of the displayed BG measurement.

Abstract: As disclosed herein, a non-volatile memory circuit includes an array of memory cells. The non-volatile memory circuit also includes circuitry for performing a hard write to selective bits of addressed cells simultaneously with a normal write to the other bits of the addressed cells during a write operation to the addressed cells.

Abstract: A magnetoresistive random access memory (MRAM) array has a corresponding MRAM cell, including a Magnetic Tunnel Junction (MTJ), at an intersection of each row and column. A first row of the array is configured as a single one-time-programmable (OTP) row, wherein a first MRAM cell in a first column is connected to a second MRAM cell in a second column. A first MTJ of the first MRAM cell is connected to a first bit line of the first column, and a second MTJ of the second MRAM cell is not connected to a second bit line of the second column. During a write to the first MRAM cell, write circuitry is configured to connect the first and second bit lines and the corresponding source lines such that the select transistors in the first and second MRAM cells are connected in parallel to drive a write current through the first MTJ.

Abstract: This disclosure describes machine learning techniques for capturing human knowledge for performing a task. In one example, a video device obtains video data of a first user performing the task and one or more sensors generate sensor data during performance of the task. An audio device obtains audio data describing performance of the task. A computation engine applies a machine learning system to correlate the video data to the audio data and sensor data to identify portions of the video, sensor, and audio data that depict a same step of a plurality of steps for performing the task. The machine learning system further processes the correlated data to update a domain model defining performance of the task. A training unit applies the domain model to generate training information for performing the task. An output device outputs the training information for use in training a second user to perform the task.

Abstract: Methods, systems and computer-readable media are provided for controlling insulin delivery to a specific user by a medical device based on detected events associated with the specific user. An event combination or combination of the detected events can be determined and a database of classified outputs corresponding to event combinations can be accessed. A classified output corresponding to the event combination can be retrieved. A controller of the medical device can generate, based on the classified output, controller tuning instructions that influence delivery of insulin via the medical device to either decrease the insulin delivery to the specific user, increase the insulin delivery to the specific user, or maintain the insulin delivery to the specific user at the ordinary level by maintaining the insulin delivery in a nominal state.

Abstract: Technologies are provided for training a mathematical model based on labeled events and/or labeled event combinations. A database can store detected events as labeled events and different combinations of the detected events as labeled event combinations. Each can include a label and a probability of an increased insulin delivery demand or a decreased insulin delivery demand for that particular detected event or that particular combination of detected events. An adaptation process can retrieve selected ones of the labeled events and the labeled event combinations from the database. A mathematical model can be trained based on the selected ones of the labeled events and the labeled event combinations to generate an adapted mathematical model of the user that simulates a physiological blood glucose response of the user in response to the selected ones of the labeled events and labeled event combinations.

Abstract: Technologies are provided for classifying detected events as labeled event combinations. Input data for different combinations of detected events are received at a server system, and each combination of detected events is processed at the server system. Processing can include classifying that combination of detected events at a classifier to map that combination of detected events to a probability of an increased insulin delivery demand or a probability of a decreased insulin delivery demand, and labeling each classified combination of detected events with a label to generate a corresponding labeled event combination that has the probability of the increased insulin delivery demand or the probability of the decreased insulin delivery demand. Each labeled event combination can be stored in storage as a database of labeled event combinations, and selected ones of the labeled event combinations can be processed at a client application to generate an output result.

Abstract: Infusion systems, infusion devices, and related operating methods are provided. An exemplary method of providing site rotation feedback pertaining to a sensing arrangement providing sensed measurements of a physiological condition in a body of a user involves obtaining one or more reference measurements of the physiological condition in the body of the user, determining a lag associated with the sensing arrangement based on a relationship between the one or more reference measurements and one or more of the sensed measurements, identifying a current site location on the body of the user associated with the sensing arrangement from among a plurality of site locations based on the lag, determining one or more performance metrics associated with the current site location, and providing sensor site feedback in a manner that is influenced by the one or more performance metrics.

Abstract: Apparatus are provided for medical devices and related operating systems and methods. An exemplary medical device includes a motor, one or more data storage elements to maintain control information, and a control module coupled to the motor and the one or more data storage elements. The control module is configured to obtain updated control information via a peer-to-peer communication session over a network, store the updated control information in the one or more data storage elements, and thereafter operate the motor based at least in part on the updated control information.

Abstract: Infusion systems, infusion devices, and related operating methods are provided. An exemplary method of operating an infusion device to deliver fluid to a body of a user involves obtaining measurement values for a physiological condition influenced by the fluid, autonomously operating the infusion device to deliver the fluid based at least in part on the measurement values, and detecting a nonactionable condition based on the measurement values. In response to detecting the nonactionable condition, delivery of the fluid is limited while maintaining autonomous operation of the infusion device. In one exemplary embodiment, the nonactionable condition is a rescue condition indicative of the user having consumed fast-acting carbohydrates, and thus insulin delivery may be automatically limited in response to detecting the rescue carbohydrate consumption.

Abstract: As disclosed herein, a non-volatile memory circuit includes an array of memory cells. The non-volatile memory circuit also includes circuitry for performing a hard write to selective bits of addressed cells simultaneously with a normal write to the other bits of the addressed cells during a write operation to the addressed cells.

Abstract: Medical devices and related systems and operating methods are provided. A method of operating an infusion device capable of delivering fluid influencing a physiological condition to a patient involves obtaining an event indication, such as a meal indication, determining an initial bolus amount based on the event indication, and determining predicted values for the physiological condition of the patient during a time window into the future based at least in part on the initial bolus amount. When the predicted values violate a threshold during the time window, the control system identifies an adjusted bolus amount that results in the predicted values for the physiological condition satisfying the threshold during the time window from within a search space defined by the initial bolus amount and operates an actuation arrangement of the infusion device to deliver the adjusted bolus amount of the fluid to the patient.

Abstract: A method of controlling an insulin infusion device involves controlling the device to operate in an automatic basal insulin delivery mode, obtaining a blood glucose measurement for the user, and initiating a correction bolus procedure when: the measurement exceeds a correction bolus threshold value; and a maximum basal insulin infusion rate is reached during the automatic basal insulin delivery mode. The correction bolus procedure calculates an initial correction bolus amount, and scales the initial amount to obtain a final correction bolus amount, such that a predicted future blood glucose level resulting from simulated delivery of the final correction bolus amount exceeds a low blood glucose threshold level. The final amount is delivered to the user during operation in the automatic basal insulin delivery mode.

Abstract: A semiconductor device and methods for making the same are disclosed. The device may include: a first transistor structure; a second transistor structure; a capacitor structure comprising a trench in the substrate between the first and second transistor structures, the capacitor structure further comprising a doped layer over the substrate, a dielectric layer over the doped layer, and a conductive fill material over the dielectric layer; a first conductive contact from the first transistor structure to a first bit line; a second conductive contact from the second transistor to a non-volatile memory element; and a third conductive contact from the non-volatile memory element to a second bit line.