Methods, devices and systems for acquiring information useful to support a patient in implementing and adhering to a medically prescribed therapy plan are provided. The therapy may incorporate biofeedback methods and/or personalized therapy aspects. A method includes steps of receiving, by a receiving device, biometric information associated with an ingestible event marker; analyzing, by a computing device having a microprocessor configured to perform a biometric information analysis, the biometric information; and determining a therapeutic recommendation at least partly on the basis of the analysis and/or integrating biofeedback techniques into patient therapy or activity. A system includes a biometric information module to receive biometric information associated with an ingestible event marker; an analysis module to analyze the biometric information; and a determination module to optionally determine and communicate a therapeutic recommendation at least partly on the basis of the analysis.

Numerous aspects of communication devices, methods, and systems are described in this application. One aspect is an apparatus comprising an energy generator comprising a plurality of generator elements operable to output a plurality of different energy types in a signal direction toward the skin. Each generator element of the plurality of generator elements may be independently operable, when the energy generator is positioned relative to skin, to communicate with different nerves associated with the skin by outputting a different portion of an energy signal in the signal direction toward the skin with one energy type of the plurality of different energy types.

The present disclosure describes a sleep staging system. The system comprises: one or more sensors configured to generate output signals conveying information related to breathing parameters of subject during a respiratory therapy session; and one or more physical computer processors configured by computer readable instructions to: determine, based on the output signals, one or more breathing features of individual breaths of the subject; determine a distribution of the one or more breathing features over a plurality of time windows, at least one of the time windows having a length of at least 60 seconds; determine sleep states of the subject by mapping the distribution of the breathing features to one or more sleep states using a sleep stage classifier model, the sleep stage classifier model configured to determine the sleep states; and provide feedback indicating the sleep states during the respiratory sleep session.

An oral care implement including a handle and an oral care refill head. The handle has a gripping portion, an engagement component coupled to a distal end of the gripping portion, and a stem. The engagement component includes a plate portion and a first engagement feature. The stem extends through an opening in the engagement component and protrudes from the plate portion. The oral care refill head includes an oral care treatment portion and a sleeve portion. The sleeve portion has an inner surface that defines a sleeve cavity having a cavity axis and a second engagement feature. When the oral care refill head is detachably coupled to the handle, the first and second engagement features mate with one another to at least one of: (1) position the oral care refill head and the handle in an operational alignment; and (2) lock the oral care refill head to the handle.

A method for providing treatment recommendations for a patient to a physician is disclosed. The method includes receiving health information associated with the patient, determining a first risk score for the patient based on the health information using a trained predictor model, determining a second risk score for the patient based on the health information and at least one artificially closed care gap included in the health information using the predictor model, determining a predicted risk reduction score based on the first risk score and the second risk score, determining a patient classification based on the predicted risk reduction score, and outputting a report based on at least one of the first risk score, the second risk score, or the predicted risk reduction score.

An arousal level prediction apparatus and method are disclosed. The arousal level prediction apparatus obtains first biological information indicating current biological information of the user, obtains first environment information indicating a current environment around the user, and obtains living information of the user indicating an activity history of the user. The arousal level predication apparatus includes a process that calculates a first arousal level indicating a current arousal level of the user based on the first biological information, predicts a second arousal level, which is an arousal level of the user at a certain period of time later, based on the first arousal level, the first environment information and the living information, and outputs the second arousal level.

A method, apparatus and device for obtaining a blood glucose measurement result. A neural network model is trained by using the following method, so as to obtain a trained first neural network model: acquiring a first invasive blood glucose measurement result of a tested object (101); forming a group of new training data by means of same and characteristic values of the most recent PPG signals of the tested object (102); training the neural network model with the training data, so as to obtain a trained first neural network model (106); and after a group of new PPG signals is acquired, extracting characteristic values of the new PPG signals, and inputting the characteristic values into the trained first neural network model, so as to obtain a target blood glucose measurement result (107).

An alignment system that monitors posture and provides alignment feedback about the monitored posture to an individual is described. This alignment system may include an alignment device that is worn or remateably attached to the body of the individual, e.g., in or near a midline (such as at or near a midpoint between the Iliac Fossa) of the posterior lumbar or sacral region. The alignment device may include one or more alignment sensors and/or may communicate with one or more separate alignment sensors that monitor the alignment of the individual's pelvis. This alignment data may be analyzed by the alignment device or another electronic device (such as an application executed on the other electronic device and/or a remotely located computer). Then, based at least in part on the analysis, the alignment device may selectively provide the alignment feedback to the individual (e.g., when misalignment is detected or determined).

A system may obtain a set of features characterizing a segment of inertial measurement unit (IMU) data generated by an IMU of an ear-wearable device. The system may apply a machine learning model (MLM) that takes the features characterizing the segment of the IMU data as input. The system may determine, based on output values produced by the MLM, whether a user of the ear-wearable device has potentially been subject to physical abuse. The system may then perform an action in response to determining that the user of the ear-wearable device has potentially been subject to physical abuse.

A rehabilitation system includes left-hand and right-hand rehabilitation apparatuses that cooperate with programming instructions operating on a patient computer and on a therapist computer that is remote from the patient computer. Each apparatus includes a hand section with movement sensors supported on the backside of the hand of the patient from which patient hand movements can be derived, finger sections moveable relative to the hand section with sensors to track flexing and movement of the finger sections relative to the hand, a wrist section supporting vital sign sensors communicating with the patient, and adjustable resistive elements applied to the finger or hand movements. The system enables a therapist to communicate target movements to the user, as well as allowing the comparison between patient movements conducted at different times or with different hands. Sensor data can be used to measure patient performance that is provided to the patient and the therapist.