Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for automated contact tracing using multiple data sources. In some implementations, a system uses location data generated based on one or more types of signals, such as GPS signals, WI-FI signals, signals from cellular base stations, signals from short-range wireless technology (e.g., BLUETOOTH), and so on. The system also prompts users for information regarding their locations and the conditions present at the locations, either at the time a user is present or later. With this information, the system compares the tracked locations for different individuals to identify instances of contacts in which criteria for disease transmission potential are met, e.g., when two individuals have certain levels of proximity and timing. Detected instances of contacts can be used to inform individuals of exposure to a disease, as well as to notify public health authorities.

Abstract: In some implementations, a user interface for designing a health management module is provided by a server system. The user interface identifies a plurality of health management templates. The server system initially receives data indicating a user input received through the user interface that selects one of the plurality of module templates. The server system also receives customization parameters that customize the selected module template for a particular organization. The server system then generates a customized health management module for the particular organization based on the selected template and the customization parameters. The server system finally publishes the customized health management module for the particular organization that includes instructions configuring an application provided by a third-party application store.

Abstract: In some implementations, one or more computing devices receive data indicating selection criteria for a cohort through an interface. The one or more computing devices determine a first set of candidates classified as having attributes that satisfy the selection criteria. The one or more computing devices also determine a second set of candidates that satisfy a subset of the selection criteria and are determined to not satisfy a same one or more criteria of the selection criteria. The one or more computing devices provide output data through the interface that includes (i) data indicating the first set of candidates, (ii) data indicating the second set of candidates, and (iii) data indicating the one or more selection criteria not satisfied by the members of the second set of candidates.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for collecting monitoring data and predicting outcomes for communities. In some implementations, monitoring data is received, including location tracking data that indicates locations visited by individuals in a community. Community data for the community that describes characteristics of the community and a geographic region associated with the community is received. One or more predictive models are used to evaluate regions for potential for transmission of a disease based on behavior patterns of individuals in the community. The one or more predictive models can be models trained based on training data describing a plurality of different communities and behavior patterns and disease outcomes of individuals in the different communities over time.

Abstract: In some implementations, a system provides a user interface for creating a customized module to customize behavior of an application. The user interface identifies templates that each specify one or more user forms. The system receives data indicating a user input received through the user interface that selects of one of the templates to be used in generating the customized module. The system receives customization data entered using the user interface, where the customization data specifies one or more changes to the content that the selected template specifies for the application to present. The system generates the customized module based on the selected template and the customization data. The system provides the customized module over a computer network, the customized module being configured to cause a device having the application installed to present the first user form customized according to the customization data.

Abstract: In some implementations, a system causes electronic devices to initiate different types of interactions with users of the electronic devices, the interactions being initiated based on rules to selectively cause initiation of the interactions for the users. The system receives user action data from electronic devices that are associated with a particular program. The system generates log data that tracks instances in which conditions or triggers of the rules of the particular program are satisfied. Based on the user action data of the multiple users and the log data, the system evaluates effectiveness of the rules in maintaining or improving engagement of the users with the particular program. The system generates rule adjustment information for the particular program, such as information indicating one or more changes to the rules of the particular program or one or more new rules for initiating interactions.

Abstract: In some implementations, a system provides an interface for receiving input for creating a customized module configured to provide a customized set of interactions through an application. The system receives data indicating desired functionality to be provided by the application after receiving the customized module. The system identifies one or more elements from a repository and a particular set of existing features of the application. The system generates a customized module to cause the application to provide the desired functionality indicated by the user input. The system provides the customized module to a client device that has the application installed, wherein the customized module adds the identified one or more elements to the installed application and causes the installed application to enable the particular set of the existing features.

Abstract: Methods, systems, and apparatus, including computer-readable media, for machine learning in a multi-tenant data sharing platform. In some implementations, a server system provides a multi-tenant data sharing platform configured to selectively use stored data collected for different tenant organizations according to policy data for the respective tenant organizations. A request from one organization is received to perform a machine learning task involving a data set of a different tenant organization. The server system uses stored policy data to determine an applicable data policy, and based on the determination, the server system performs the machine learning task and provides the results of the machine learning task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for remotely managing and adapting monitoring programs using machine learning predictions. In some implementations, data describing a monitoring program that involves collecting data over a period of time from geographically distributed devices is accessed. Composition characteristics of the monitoring pro group for the monitoring program are determined. Predicted composition characteristics are generated for a portion of the monitoring group predicted to comply with the monitoring program requirements for the period of time. It is determined whether the predicted composition characteristics indicate at least a minimum level of diversity among the portion of the monitoring group. One or more devices associated with the monitoring program are communicated with.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for machine learning to select digital therapeutics. In some implementations, a machine learning model is trained to generate scores that indicate the level of applicability of different digital therapeutics based on input data for a person. A computer system monitors health of an individual using surveys and sensor measurements. The computer system identifies one or more signs or symptoms of a disease based on the monitoring data for the individual. The computer system uses output of the machine learning model to select a digital therapeutic intervention for the user. The computer system cause one or more devices to deliver the selected digital therapeutic intervention to the individual, monitor a response of the individual to the selected digital therapeutic intervention, and adjust characteristics of the digital therapeutic intervention based on the monitored response.

Abstract: Systems, methods, and apparatus, including computer-readable media for managing and adapting monitoring programs. In some implementations, a system accesses data describing a monitoring program that involves collecting data over a period of time from a monitoring group comprising geographically distributed devices. The system classifies the devices in the monitoring group into different groups for the categories based on the attributes associated with the devices. The system monitoring performance of the devices in the different groups and determines a performance score for each group. The system adjusts administration of the monitoring program based on the performance scores, including performing one or more actions to improve diversity in the monitoring group.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for improving distributed monitoring using different groups of remote devices. In some implementations, a system communicates with a set of remote devices involved in a first monitoring program that involves collection of data from the remote devices over a communication network. The system identifies a pattern or similarity among monitoring data collected from a subset of the remote devices involved in the first monitoring program. The system determines that the identified pattern or similarity satisfies one or more criteria for initiating additional monitoring. In response, the system determines parameters specifying second types of data to collect in a second monitoring program. The system configures one or more devices to perform monitoring for the second monitoring program including acquiring data for the second types of data and providing the acquired data to a server over the communication network.

Abstract: In some implementations, a system dynamically adjusts an electronic form of an application based on user data and form data specified for the electronic form. Form data that specifies characteristics of the electronic form is initially received by a computing device. The form data specifies one or more rules configured to vary the content of the electronic form that is presented for different users. User data indicating characteristics of a user is then obtained by the computing device. An interactive element is then selected from among a set of multiple interactive elements based on the received user data and the rules in the received form data. A view of the electronic form is customized for the user by including, in the customized view, the interactive element. The view of the customized electronic form is then displayed by the computing device.

Abstract: Systems and methods for using a reconfigurable multi-manager observer system to identify markers are provided. The system allows for easy collaboration among users of the system and with subjects. Systems and methods may comprise receiving subject data, selecting predictor and outcome variable classes based on the data, generating a predictor score based on the data and a predictor rule, generating an outcome score based on the data and an outcome rule, generating a marker score based on the predictor score and a marker rule, generating a marker metric based on the outcome score, the marker score, and a marker relationship, and, optionally, taking an action based on the predictor score, the outcome score, the marker score, or the marker metric.

Abstract: In some implementations, a system includes a database comprising program data for each of a plurality of programs that involve monitoring using remote devices. The system includes a server system configured to selectively distribute the configuration data for the respective programs to remote devices over a communication network and monitor incoming data received from the remote devices over the communication network to determine changes to programs active for the remote devices. The server system can be configured to collect, from the respective remote devices, monitoring data that is generated by the programs active for the remote devices and is provided over the communication network. The server system can compare the collected monitoring data with reference levels, select one or more program changes, and distribute, to various remote devices, data indicating appropriate program changes for the remote devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for assessing and adjusting the composition of groups for monitoring programs. In some implementations, a computer system determines a target level of diversity for a monitoring program based on a composition of a reference group. The system determines a group level of diversity for a group based on the composition of the group, wherein the group comprises at least one of candidates or participants for the monitoring program. The system determines that the group level of diversity does not provide the target level of diversity, and in response, selects one or more actions that are configured to adjust the composition of the group to achieve the target level of diversity in the group. The system provides output data that indicates the selected one or more actions to adjust the composition of the group toward the target level of diversity for the group.

Abstract: A system and method for an adjustable bio-stream self-selecting system. Through a plethora of inputs, the system associates therapeutic recipes and associated biomarker in a personalized approach to recommending an individual to a specific therapeutic program. Therapeutic programs operate in accordance with personalized inputs suggested by the user and through digital markers and biomarkers, which trigger new recommendations by “knowing” the individual. Each bio-stream contains information utilized within these biomarkers to trigger additional therapy recommendations. Because of the complexity of the plurality of inputs, these biomarkers are managed in a way that enables low latency detections, low bandwidth needs, low processing needs, and less battery needs. The pre-processing of these biomarkers helps additional therapy management and precision medicine across larger global population needs of the system.

Abstract: In some implementations, a system adaptively adapts engagement between a user and an application based on prior user interactions and context data associated with the user. A performance category for which performance is tracked for a user of the application is initially identified. Context data indicating a current context of the user is received from a client device associated with the user. One or more responsiveness scores indicating actions of the user with respect to the performance category following the previous communications through the application are determined. A communication is then selected from among communications of multiple types based on the context data for the user and the one or more responsiveness scores for the user. A time to provide the communication to the user is determined based on the context data. The selected communication is provided for output by the client device at the determined time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using machine learning to generate precision predictions of readiness. In some implementations, a database is accessed to obtain status data that indicates activities or attributes of a subject. A set of feature scores is derived from the status data for the subject, the set of feature scores including values indicative of attributes or activities of the subject. The set of feature scores to one or more models that have been configured to predict readiness of subjects to satisfy one or more readiness criteria. The one or models can be models configured using machine learning training. Based on processing performed using the one or more machine learning models and the set of feature scores, a prediction regarding the subject's ability to achieve readiness to satisfy the one or more readiness criteria is generated.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using machine learning to improve processes for achieving readiness. In some implementations, a database is accessed to obtain status data that indicates activities or attributes of a subject. One or more readiness scores indicating a level of capability of the subject to satisfy one or more readiness criteria are generated. Data is accessed indicating multiple candidate actions for improving capability of the subject to satisfy one or more readiness criteria. A subset of the candidate actions for the subject are selected based on the one or more readiness scores generated using the one or more models. Output is provided to cause one or more of the actions in the selected subset to be performed or cause an indication one or more of the actions in the selected subset to be presented on a user interface.