Abstract: Embodiments include methods and systems for automated eating detection. Systems comprise a continuous glucose monitor (CGM), accelerometer, and processing unit. During a first time period, the processing unit receives glucose readings and a first set of acceleration readings. The processing unit identifies an eating episode if the glucose readings satisfy one or more criteria. Using the identified eating episode and first set of acceleration readings, the processing unit generates an individual model that identifies eating episodes using acceleration readings without using glucose readings. During a second time period, a processing unit uses the individual model and a second set of acceleration readings to identify a second eating episode. Some embodiments may use additional sensor types (for example, PPG or heart rate) to identify eating episodes in the first or second time period, generate the individual model, or any combination thereof.

Abstract: This disclosure is directed to devices, systems, and techniques for determining when to deploy sensors. Processing circuitry of an example medical device system is configured to receive first sensor data. The processing circuitry is configured to determine, based on the first sensor data, a likelihood that a heart failure decompensation event of a patient is impending. The processing circuitry is configured to compare the likelihood to a first threshold. The processing circuitry is configured to, based on the likelihood satisfying the first threshold, at least one of a) generate a first instruction for output to a user to deploy one or more biochemical or bacterial sensors, or b) control an implantable medical device to automatically deploy one or more biochemical or bacterial sensors.

Abstract: Embodiments include methods and systems for automated eating detection. Systems comprise a continuous glucose monitor (CGM), accelerometer, and processing unit. During a first time period, the processing unit receives glucose readings and a first set of acceleration readings. The processing unit identifies an eating episode if the glucose readings satisfy one or more criteria. Using the identified eating episode and first set of acceleration readings, the processing unit generates an individual model that identifies eating episodes using acceleration readings without using glucose readings. During a second time period, a processing unit uses the individual model and a second set of acceleration readings to identify a second eating episode. Some embodiments may use additional sensor types (for example, PPG or heart rate) to identify eating episodes in the first or second time period, generate the individual model, or any combination thereof.

Abstract: Embodiments include methods and systems for automated eating detection. Systems comprise a continuous glucose monitor (CGM), accelerometer, and processing unit. During a first time period, the processing unit receives glucose readings and a first set of acceleration readings. The processing unit identifies an eating episode if the glucose readings satisfy one or more criteria. Using the identified eating episode and first set of acceleration readings, the processing unit generates an individual model that identifies eating episodes using acceleration readings without using glucose readings. During a second time period, a processing unit uses the individual model and a second set of acceleration readings to identify a second eating episode. Some embodiments may use additional sensor types (for example, PPG or heart rate) to identify eating episodes in the first or second time period, generate the individual model, or any combination thereof.

Abstract: An apparatus comprises an input configured to receive electrocardiogram (ECG) data detected by a patient monitoring device, the ECG data containing a physiologic signal and one or more segments of noise within the ECG data. A scrubber comprises a plurality of scrubbing modules each configured to process the ECG data and noise in a manner differing from other scrubbing modules. The scrubber is configured to filter the one or more noise segments that overlap with the physiologic signal, and consolidate the ECG data to eliminate the one or more noise segments that are non-overlapping with the physiologic signal. An output is configured to output scrubbed ECG data.

Abstract: Embodiments include methods and systems for automated eating detection. Systems comprise a continuous glucose monitor (CGM), accelerometer, and processing unit. During a first time period, the processing unit receives glucose readings and a first set of acceleration readings. The processing unit identifies an eating episode if the glucose readings satisfy one or more criteria. Using the identified eating episode and first set of acceleration readings, the processing unit generates an individual model that identifies eating episodes using acceleration readings without using glucose readings. During a second time period, a processing unit uses the individual model and a second set of acceleration readings to identify a second eating episode. Some embodiments may use additional sensor types (for example, PPG or heart rate) to identify eating episodes in the first or second time period, generate the individual model, or any combination thereof.

Abstract: Embodiments include methods and systems for automated eating detection. Systems comprise a continuous glucose monitor (CGM), accelerometer, and processing unit. During a first time period, the processing unit receives glucose readings and a first set of acceleration readings. The processing unit identifies an eating episode if the glucose readings satisfy one or more criteria. Using the identified eating episode and first set of acceleration readings, the processing unit generates an individual model that identifies eating episodes using acceleration readings without using glucose readings. During a second time period, a processing unit uses the individual model and a second set of acceleration readings to identify a second eating episode. Some embodiments may use additional sensor types (for example, PPG or heart rate) to identify eating episodes in the first or second time period, generate the individual model, or any combination thereof.

Abstract: An apparatus comprises an input configured to receive electrocardiogram (ECG) data detected by a patient monitoring device, the ECG data containing a physiologic signal and one or more segments of noise within the ECG data. A scrubber comprises a plurality of scrubbing modules each configured to process the ECG data and noise in a manner differing from other scrubbing modules. The scrubber is configured to filter the one or more noise segments that overlap with the physiologic signal, and consolidate the ECG data to eliminate the one or more noise segments that are non-overlapping with the physiologic signal. An output is configured to output scrubbed ECG data.