Abstract: A method for determining a treatment recommendation using a multi-armed bandit (MAB) model can include receiving first patient information, determining, using the MAB model, the treatment recommendation based on the first patient information, wherein the MAB model is trained based on a MAB treatment recommendation determined by the MAB model using second patient information and a clinical treatment recommendation determined according to clinical guidelines based on the second patient information, and providing the treatment recommendation.

Abstract: A method comprises obtaining data characterizing a given subject over time, applying at least a portion of the obtained data to a generative adversarial network adapted to generate a prediction of at least one change in at least one of behavior and physiology of the given subject from the obtained data, and executing at least one automated remedial action relating to the given subject based at least in part on the generated prediction. The generative adversarial network is configured to implement multi-task learning, across a plurality of subjects, in which changes in multiple distinct features are treated as separate but linked tasks. The generative adversarial network comprises separate discriminators for each of the multiple distinct features and separate discriminators for each of a plurality of different clusters of respective subsets of the plurality of subjects, and combines outputs of respective ones of the discriminators for the features and the clusters in generating the prediction.

Abstract: A method in an illustrative embodiment comprises obtaining data characterizing a given subject over time, applying at least a portion of the obtained data to an encoder-decoder neural network adapted to generate a prediction of at least one change in at least one of behavior and physiology of the given subject from the obtained data, and executing at least one automated remedial action relating to the given subject based at least in part on the generated prediction. The encoder-decoder neural network is configured to learn one or more subject-specific anomaly thresholds based at least in part on reconstruction error of the encoder-decoder neural network. The encoder-decoder neural network is illustratively implemented utilizing at least one of a fully-connected neural network autoencoder architecture and a gated recurrent unit sequence-to-sequence architecture. Other illustrative embodiments include systems and computer program products.

Abstract: Methods, systems, and devices are disclosed for passively monitoring a health condition of a subject using a mobile device. In some aspects, a method includes producing a set of quantitative metrics based on one or more parameters including location, movement, and sound obtained from the mobile device, where the produced set of quantitative metrics includes a location cluster value, a travel distance value, a frequency of conversation value, and an activity value, each of the quantitative metrics over a respective predetermined time period; and processing the set of quantitative metrics to determine a metric indicative of a current clinical state of the subject in connection with one or more measures including daily routines, mood or energy of the subject. Using the sensed parameters, rhythmicity markers and/or departure from stability can be predicted to alert a caregiver of the patient's health status, such as a current mental health state.

Abstract: Persuasive technologies aim to influence user's behaviors. In order to be effective, many of the persuasive technologies developed so far relies on user's motivation and ability, which is highly variable and often the reason behind the failure of such technology. Mindless Computing, a new approach to persuasive technology design, is presented. Mindless Computing leverages theories and concepts from psychology and behavioral economics into the design of technologies for behavior change. Most of the current persuasive technologies do not utilize the fast and automatic mental processes for behavioral change and there is an opportunity for persuasive technology designers to develop systems that are less reliant on user's motivation and ability.

Abstract: Methods, systems, and devices are disclosed for passively monitoring a health condition of a subject using a mobile device. In some aspects, a method includes producing a set of quantitative metrics based on one or more parameters including location, movement, and sound obtained from the mobile device, where the produced set of quantitative metrics includes a location cluster value, a travel distance value, a frequency of conversation value, and an activity value, each of the quantitative metrics over a respective predetermined time period; and processing the set of quantitative metrics to determine a metric indicative of a current clinical state of the subject in connection with one or more measures including daily routines, mood or energy of the subject. Using the sensed parameters, rhythmicity markers and/or departure from stability can be predicted to alert a caregiver of the patient's health status, such as a current mental health state.

Abstract: Methods, systems, and devices are disclosed for implementing mobile sensing of non-speech sounds from a human. In one aspect, a mobile sensing system includes a microphone to capture a diverse set of body sounds while dampening external sounds and ambient noises, wherein the captured diverse set of body sounds are not speech. The mobile sensing system includes a micro-controller in communication with the microphone to perform an algorithm for signal processing and machine learning using the captured diverse set of body sounds.

Abstract: Techniques involving messaging applications are disclosed. For example, an apparatus may include a presence determination module and a publication module. The presence determination module may infer one or more presence indicators regarding a user. These inference(s) may be based on sensor data. In addition, these inference(s) may be based on position information, and device activity data. The publication module publishes the one or more presence indicators to a messaging server. These presence indicator(s) may indicate an activity and/or a location context of the user.

Abstract: Embodiments of methods and apparatus for operating an ensemble of wireless electronic devices based on user activity are generally described herein. Other embodiments may be described and claimed.