Abstract: Systems and methods for de-identifying patient data are disclosed herein. In some embodiments, a method for de-identifying patient data includes receiving a patient record including one or more identifiers. The method can include generating a first de-identified record from the patient record using a first de-identification process. The first de-identification process can be configured to produce a first re-identification risk score. The method can further include receiving a request from a data recipient to access the first de-identified record. The method can also include generating a second de-identified record from the first de-identified record by using a second de-identification process. The second de-identification process can be configured to produce a second re-identification risk score lower than the first re-identification risk score.

Abstract: Systems and methods for indexing and searching health data are disclosed herein. In some embodiments, a method for querying patient records includes receiving a search input that specifies a plurality of events, one or more temporal relationships between the events, and inclusion and/or exclusion criteria. An index query is constructed based at least in part on the plurality of events within the search input. The index query is then executed against an inverted index to identify matching patient records. One or more temporal constraints can be solved against the identified patient records. Finally, patient records satisfying the constraint(s) are returned.

Abstract: Systems and methods for data normalization are disclosed. The disclosed systems and methods train one or more machine learning model based on a plurality of annotated records and apply these trained models to new or updated records. The models are configured to analyze the records and generate classifications or concepts from the records and corresponding confidence scores. If the confidence scores exceed a threshold, the corresponding classifications or concepts are appended to the appropriate record.

Abstract: Aspects provided herein are relevant to systems, methods, and techniques for classifying relationships between people (e.g., users of a platform or ecosystem) based on relationship data. In an example, the relationship data can be provided as input into a two-layer classification framework in which the first layer acts a filter for the second layer. The framework can identify relationships such as a self-relationship (e.g., two different accounts on the platform are operated by the same person), a non-self, family-member relationship (e.g., two users are different people but part of the same family), and a non-family-member relationship (e.g., the two users are different people and not part of the same family, such as coworkers or roommates).

Abstract: Concepts and technologies are described herein for multi-mode text input. In accordance with the concepts and technologies disclosed herein, content is received. The content can include one or more input indicators. The input indicators can indicate that user input can be used in conjunction with consumption or use of the content. The application is configured to analyze the content to determine context associated with the content and/or the client device executing the application. The application also is configured to determine, based upon the content and/or the contextual information, which input device to use to obtain input associated with use or consumption of the content. Input captured with the input device can be converted to text and used during use or consumption of the content.

Abstract: Concepts and technologies are described herein for multi-mode text input. In accordance with the concepts and technologies disclosed herein, content is received. The content can include one or more input indicators. The input indicators can indicate that user input can be used in conjunction with consumption or use of the content. The application is configured to analyze the content to determine context associated with the content and/or the client device executing the application. The application also is configured to determine, based upon the content and/or the contextual information, which input device to use to obtain input associated with use or consumption of the content. Input captured with the input device can be converted to text and used during use or consumption of the content.

Abstract: Concepts and technologies are described herein for multi-mode text input. In accordance with the concepts and technologies disclosed herein, content is received. The content can include one or more input indicators. The input indicators can indicate that user input can be used in conjunction with consumption or use of the content. The application is configured to analyze the content to determine context associated with the content and/or the client device executing the application. The application also is configured to determine, based upon the content and/or the contextual information, which input device to use to obtain input associated with use or consumption of the content. Input captured with the input device can be converted to text and used during use or consumption of the content.