Methods and apparatus, including computer program products, are provided for processing analyte data. In some example implementations, a method may include generating glucose sensor data indicative of a host's glucose concentration using a glucose sensor; calculating a glycemic variability index (GVI) value based on the glucose sensor data; and providing output to a user responsive to the calculated glycemic variability index value. The GVI may be a ratio of a length of a line representative of the sensor data and an ideal length of the line. Related systems, methods, and articles of manufacture are also disclosed.

A method of distinguishing sleep period states that a person experiences during a sleep period, the method comprising: using a non-contact microphone to acquire a sleep sound signal representing sounds made by a person during sleep; segmenting the sleep sound signals into epochs; generating a sleep sound feature vector for each epoch; providing a first model that gives a probability that a given sleep period state experienced by the person in a given epoch exhibits a given sleep sound feature vector; providing a second model that gives a probability that a first sleep period state associated with a first epoch transitions to a second sleep period state associated with a subsequent second epoch; and processing the feature vectors using the first and second models to determine a sleep period state of the person from a plurality of possible sleep period states for each of the epochs.

A method of distinguishing sleep period states that a person experiences during a sleep period, the method comprising: using a non-contact microphone to acquire a sleep sound signal representing sounds made by a person during sleep; segmenting the sleep sound signals into epochs; generating a sleep sound feature vector for each epoch; providing a first model that gives a probability that a given sleep period state experienced by the person in a given epoch exhibits a given sleep sound feature vector; providing a second model that gives a probability that a first sleep period state associated with a first epoch transitions to a second sleep period state associated with a subsequent second epoch; and processing the feature vectors using the first and second models to determine a sleep period state of the person from a plurality of possible sleep period states for each of the epochs.

A computer-implemented method for creating an activity-optimized cutting guides for surgical procedures includes receiving one or more pre-operative images depicting one or more anatomical joints of a patient, and creating a three-dimensional anatomical model of the one or more anatomical joints based on the one or more pre-operative images. One or more patient-specific anatomical measurements are determined based on the three-dimensional anatomical model. A statistical model of joint performance is applied to the patient-specific anatomical measurements to identify one or more cut angles for performing a surgical procedure. A patient-specific cutting guide is created that comprises one or more apertures positioned based on the one or more cut angles.

An aspect of the present invention is a loss-of-consciousness estimation apparatus including: an out-of-range data determination unit configured to execute out-of-range data determination processing for, using an amount correlated with a cerebral blood flow rate of an estimation target as a cerebral blood flow correlation amount, a time series of the cerebral blood flow correlation amount as a cerebral blood flow correlation amount time series, and a position in a time axis direction of data of the cerebral blood flow correlation amount time series as a time position, determining whether or not the cerebral blood flow correlation amount indicated by each piece of the data is out of range of a threshold region, which is a range corresponding to the time position of each piece of the data, based on the cerebral blood flow correlation amount time series; and a ventricular state estimation unit configured to estimate a ventricular state of the estimation target based on the determination result of the out-of-range data determination unit, in which, before the execution of the out-of-range data determination processing, the out-of-range data determination unit executes processing for determining the threshold region of each time position, which is processing for determining the threshold region that is to be determined according to a distribution of the data in a first period, which is a period of a first length including the time position at which the threshold region is determined.

The user is to be informed of the reliability of the machine-learned model based on the current input relative to the training data used to train the model or the model itself. In a medical situation, the data for a current patient is compared to the training data used to train a prediction model and/or to a decision function of the prediction model. The comparison indicates the training content relative to the current patient, so provides a user with information on the reliability of the prediction for the current situation. The indication deals with the variation of the data of the current patient from the training data or relative to the prediction model, allowing the user to see how well trained the predication model is relative to the current patient. This indication is in addition to any global confidence output through application of the prediction model to the data of the current patient.

The user is to be informed of the reliability of the machine-learned model based on the current input relative to the training data used to train the model or the model itself. In a medical situation, the data for a current patient is compared to the training data used to train a prediction model and/or to a decision function of the prediction model. The comparison indicates the training content relative to the current patient, so provides a user with information on the reliability of the prediction for the current situation. The indication deals with the variation of the data of the current patient from the training data or relative to the prediction model, allowing the user to see how well trained the predication model is relative to the current patient. This indication is in addition to any global confidence output through application of the prediction model to the data of the current patient.

The present disclosure relates to a cardiorespiratory analysis system that includes, in at least one embodiment, a conformal patch with a compressible viscoelastic interface and an array of sensors, including, but not limited to a photoplethysmography (PPG) sensor, a 3-axis accelerometer, and an electrocardiogram (ECG) sensor. In at least one embodiment, the system includes a microcontroller wired to the array of sensors. According to at least one embodiment, the system uses computing techniques to derive features from the array of sensors and determines one or cardiorespiratory characteristics of a patient based on the derived features.

Intraoral electronic sensing for health monitoring is disclosed. Wireless connectivity is provided between a processor and a wireless transmitting device. The wireless transmitting device is embedded in an intraoral sensing interface for use in a person. Sensors are coupled to the wireless transmitting device, wherein the sensors are attached to the intraoral sensing interface. The sensors include a photoplethysmography (PPG) sensor to detect cardiac activity, a breathing sensor to detect pulmonary function, an inertial measurement unit (IMU) sensor to detect three-dimensional motion, and a temperature sensor to monitor body temperature. Further sensors include an electroencephalogram sensor to detect brain activity. Health data about the person is provided to a receiving device, based on data from one or more of the PPG sensor, the breathing sensor, the IMU sensor, and the temperature sensor. The health data is provided using the wireless connectivity.

Methods, systems, and devices for application personalization are described. The method may include receiving physiological data from a wearable device associated with a user and receiving data associated with previous user engagement by the user with user interface features of an application associated with the wearable device. The method may include determining a content layout of the user interface features within the application based on an output of a predictive model. The predictive model may use at least the received physiological data as input and be configured to increase future user engagement with the user interface features based on the received data associated with previous user engagement. In some cases, the method may include causing a graphical user interface of the user device to display the determined content layout of the user interface features.