Abstract: A method, a system, and a computer program product are provided. Electronic health records of patients, indicating encounters with healthcare providers for medical conditions, are analyzed to determine networks of healthcare providers. Based on the analyzing, healthcare provider network data corresponding to a graphical representation of the determined networks of healthcare providers are generated. The healthcare provider network data includes multiple paths, each of which indicates a series of healthcare providers. Based on the generated healthcare provider network data, a path indicating a series of healthcare providers within the healthcare provider network data and corresponding to at least one medical condition indicated by an electronic health record of a patient is identified. An action for the patient and a corresponding healthcare provider to perform the action is determined based on the identified path.

Abstract: A system and method of visually displaying healthcare protocols to a user receives from the user, via an electronic communications network, search term(s) associated with a health-related condition. A corpus of document(s) stored in an electronic format is identified with a computer and, based on the search term(s), at least one of the document(s) is analyzed with the computer for a treatment protocol associated with the health-related condition. First content for presentation to the user is determined with the computer, the first content including at least a portion of the treatment protocol associated with the health-related condition. A risk value indicative of risk(s) associated with the first content is determined. In response to a determination that the risk value exceeds the risk threshold, second content for presentation is determined by reformatting the first content. A message is sent causing the second content to be visually displayed to the user.

Abstract: A method, computer system, and a computer program product for recasting repetitive messages is provided. Embodiments may include receiving, by a processor, a message. Embodiments may include determining, by the processor, whether the received message is repetitive. Embodiments may include rating, by the processor, an importance level of the received message. Embodiments may include determining a preference for recasting the received message.

Abstract: A method, computer system, and computer program product for determining an engagement level of an individual is provided. The present invention may include capturing a plurality of image data depicting a relative location of a user. The present invention may also include identifying an individual within the captured image data. The present invention may further include gathering a plurality of engagement level indicator data associated with the identified individual. The present invention may also include calculating a current engagement level of the identified individual using the plurality of gathered engagement level indicator data.

Abstract: A method, system and computer program product for displaying content without obscuring key details on a computer screen. After the computing system detects the display of overlapping application windows, objects in the application windows are detected using an object recognition service. A determination is then made as to which of these detected objects correspond to objects that are being focused by the user, will be focused by the user and/or have been focused by the user based on the tracking of the eye gaze of the user and/or prior recorded patterns of activity. A score may then be generated for each of these focused objects indicating a level of obstruction using the location of the focused objects, the location of overlays and/or prior recorded patterns of activity. An optimal layout of the overlapped application windows is determined in response to the score for the focused object(s) exceeding a threshold value.

Abstract: A method, system and computer program product for improving the discoverability of messages on a social network. The creation of a proposed message that requests a response from a target audience is detected. The social network is then searched to identify search terms and posts related to the proposed message. Upon identifying the search terms, the search terms are ranked in order of usage among the identified posts. A list of identified search terms in order of rank is then presented to the user to modify the proposed message. The proposed message is modified using a search term selected by the user from the list of search terms. The modified message is then posted on the social network. In this manner, the message created by the user has been modified to improve the discoverability of the message on the social network and to increase responses from an appropriate target audience.

Abstract: Disclosed embodiments provide techniques for identifying gaps in health management data, and combining an estimated data subset with the health management data to fill in gaps in the health management data. The health management data can be derived from a wearable electronic fitness tracking device such as a smart watch or pedometer. The estimated data subset can be derived based on historical data for the individual, average data for a demographic group, crowdsourced, or estimated based on user profile information, and/or portable electronic device information, such as from a smartphone belonging to a user. The estimated data subset is combined with the health management data to form a revised health parameter dataset. The estimated data subset may be sent to a wearable electronic fitness tracking device, which causes the wearable electronic fitness tracking device to initiate a fitness program adjustment based on the revised health parameter dataset.

Abstract: According to one embodiment, a method, computer system, and computer program product for improving a user's dwell time on streaming media is provided. The present invention may include receiving user information; receiving access to a media stream; analyzing the media stream for stream information; evaluating user activity for abandonment; predicting, based on user information, stream information, and user activity, likely points of abandonment; identifying, based on user information and stream information, points of interest within the media stream; generating, based on the points of interest, the likely points of abandonment, or the user activity, one or more interactive elements, where the one or more interactive elements inform the viewer of the one or more points of interest.

Abstract: A computer system provides access to data during an outage. A plurality of data records are analyzed to identify entities whose data records indicate that a service is within an upcoming time period. A data resource is generated for each identified entity and the data resources for the identified entities are stored within a repository, wherein each data resource includes data obtained from a data record of a corresponding identified entity that is relevant to the service. The data resource of an identified entity is accessed with a corresponding recovery key during the outage and transform the data resource into one or more printable forms. The one or more printable forms are transmitted to one or more providers of the service. Embodiments of the present invention further include a method and program product for providing access to data during an outage in substantially the same manner described above.

Abstract: Disclosed embodiments provide techniques for identifying gaps in health management data, and combining an estimated data subset with the health management data to fill in gaps in the health management data. The health management data can be derived from a wearable electronic fitness tracking device such as a smart watch or pedometer. The estimated data subset can be derived based on historical data for the individual, average data for a demographic group, crowdsourced, or estimated based on user profile information, and/or portable electronic device information, such as from a smartphone belonging to a user. The estimated data subset is combined with the health management data to form a revised health parameter dataset. The estimated data subset may be sent to a wearable electronic fitness tracking device, which causes the wearable electronic fitness tracking device to initiate a fitness program adjustment based on the revised health parameter dataset.

Abstract: A method, computer system, and computer program product for determining an engagement level of an individual is provided. The present invention may include capturing a plurality of image data depicting a relative location of a user. The present invention may also include identifying an individual within the captured image data. The present invention may further include gathering a plurality of engagement level indicator data associated with the identified individual. The present invention may also include calculating a current engagement level of the identified individual using the plurality of gathered engagement level indicator data.

Abstract: A method includes receiving one or more updates in a social networking system corresponding to one or more topics, determining one or more constraints corresponding to the received one or more updates, updating a threshold value associated with each of the one or more determined user constraints, calculating a constraint score corresponding to each constraint of the one or more constraints, determining whether each constraint score meets a selected threshold value, and presenting the update responsive to determining that each constraint score meets a selected threshold value. A computer program product and computer system corresponding to the method are also disclosed.

Abstract: Presenting a lens-focused channel can include determining a state of a separate channel hosted on a data communications network. A topic-specific lens for federating a plurality of topic-specific messages conveyed over the data communications network can be configured in response to a predetermined condition indicated by the state of the channel. A lens-focused channel can be generated for presenting the plurality of topic-specific messages, as federated by the topic-specific lens, to a user over the data communications network.

Abstract: A system for user-processing of data includes a processor, computer readable storage medium, and a program for generating an authorized response to a message in a network. Messages with content that relates to a group, sent by an originator via a network, are detected. The computer system determines that the message relates to the group by analyzing the message content. Members of the group are selected as designated senders to contribute to an authorized response for the group by analyzing the message. Selected designated senders are notified that they are selected to contribute to the authorized response. Initial responses to the originator from the designated senders are intercepted. The computer system combines the initial responses from the designated senders for generating a combined response as an authorized response for the group and sends the combined response to the originator via the network as the authorized response for the group.

Abstract: In a computer system implemented method for generating an authorized response to a message in a network, messages with content that relates to a group are sent by an originator via a network are detected. The computer system determines that the message relates to the group by analyzing the message content. Members of the group are selected as designated senders to contribute to an authorized response to the message for the group by analyzing the message. Selected designated senders are notified that they are selected to contribute to the authorized response and initial responses to the originator from the designated senders are intercepted. The computer system combines the initial responses from the designated senders for generating a combined response as an authorized response for the group and sends the combined response to the originator via the network as the authorized response for the group.

Abstract: A processor may analyze one or more social media messages from one or more social media platforms. Each of the one or more social media messages may include a generalized metadata tag and the one or more social media messages may be categorized as a generalized group. The processor may determine, from the generalized group, that the one or more social media messages exceeds a generalized threshold. The processor may generate a first specialized metadata tag for a first set of social media messages included in the one or more social media messages. The processor may partition, based on the first specialized metadata tag, the first set of the one or more social media messages into a specialized group within the generalized group. The processor may direct one or more users associated with the first set of social media messages to the specialized group.

Abstract: A computer system processes data requests using a data delivery queue. A query received from a client is processed to generate response data, wherein the response data is held in a queue prior to transmitting to the client. The response data in the queue is iteratively divided into a plurality of blocks, wherein each block of the plurality of blocks is compressed prior to transmitting to the client, and wherein a block size of a given block is determined based on an amount of time to compress and transmit a preceding block. The plurality of blocks are transmitted to the client. Embodiments of the present invention further include a method and program product for processing data requests using a data delivery queue in substantially the same manner described above.

Abstract: Conversation slipstream propagation can include using machine learning to construct a conversations graph representing conversations conducted over an electronic communications network by a plurality of participants and collected from one or more messaging platforms. A conversation slipstream comprising one or more communications extracted from the conversations can be generated in response to receiving a secondary communication over the electronic communications network. Each of the one or more communications extracted is represented by a sub-graph of the conversations graph, each sub-graph corresponding to a graph of the secondary communication. The conversation slipstream can be presented to at least one participant to the secondary communication.

Abstract: The method, computer program product and computer system may include computing device which may collect message data containing one or more metadata tags from one or more collaboration and social media communication networks. The computing device may load the message data into a datastore. The computing device may determine the utility of the one or more metadata tags contained within the message data. The computing device may determine the effectiveness of the one or more metadata tags contained within the message data. The computing device may combine the calculated frequency and the calculated information gain of the one or more metadata tags using regression analysis and may activate a metadata tag management routine for the one or more metadata tags if the combined frequency and information gain falls below a threshold value.

Abstract: The method, computer program product and computer system may include computing device which may collect application data from an application and archive the application data into a datastore. The computing device may generate a network graph based on the archived application data. The computing device may detect a new message, containing content on one or more topics, posted in the application by an author. The computing device may determine familiarity of an anticipated user with the content of the new message and associate the new message with a message history in the application based on the anticipated user. The computing device may generate a message content summary of the new message based on the message history and present message content summary to the anticipated user.