International Business Machines Corporation

Merative US L.p.

Adrian Vrouwenvelder

Barry Joseph Pellas

James D Creasman

Nathan A Baker

Kimberly Diane Kenna

Stephen Carraway

John Hefferman

Fernando Jose Suarez Saiz

Vamshi Krishna Thotempudi

Masaaki Takamiya

Anthony Castrati

Jordan S Simpson

Gregory Chatham

Thomas J Reedy

Balakrisna Kolla

Thatta V Premnath

A method, computing platform, and computer program product are provided for evaluating data quality during a clinical trial. A computing platform receives, for a clinical trial, study design information including a set of parameters and corresponding parameter values related to data quality of the clinical trial. During the clinical trial, the computing platform receives query-related information associated with queries from at least some of a plurality of participants of the clinical trial. The computing platform applies the study design information and the query-related information to at least one trained machine learning model to calculate a predicted data quality score indicating data quality for the clinical trial. At least one suggestion for improving the data quality is determined and the predicted data quality score and the at least one suggestion for improving the data quality are output.

Using machine learning to evaluate data quality during a clinical trial based on participant queries

A method, computing platform, and computer program product are provided. A computing platform receives, for a clinical trial, study design information including a set of parameters related to a success of a clinical trial and factors related to a relevance of the parameters. The computing platform provides multiple sets of varying parameter values. At least one trained machine learning model is applied to the study design information including the sets of parameter values to predict multiple success scores including a predicted overall success score. The computing platform outputs the provided set of values for the set of parameters that are associated with the at least one trained machine learning model predicting a best overall success score for the clinical trial.

Using machine learning to facilitate design and implementation of a clinical trial with a high likelihood of success

A method, computing platform, and computer program product are provided for monitoring a clinical trial. A computer platform receives, for the clinical trial, study design information including a set of parameters and corresponding parameter values related to travel constraints of a subject for the clinical trial. The computer platform applies the study design information and the corresponding parameter values to a trained machine learning model to calculate a predicted travel score indicative of a travel burden for the subject. When the travel score fails to satisfy a travel score threshold, the computer platform determines at least one suggestion for adjusting the travel score and the at least one suggestion is output. The computer platform outputs the predicted travel score.

Using machine learning to evaluate patients and control a clinical trial

Mechanisms are provided for integrating a legacy static data storage system with an event based data storage system. Catch-up logic generates, for pre-existing legacy data in the legacy static data storage system, catch-up events for integrating the legacy data in the event based data storage system. A trigger processor generates, at approximately a same time that the catch-up events are generated, triggered events in response to one or more database triggers of the event based data storage system being activated. Both the catch-up events and the one or more triggered events are stored in an event log data structure. An event log monitor processes the catch-up events in the event log data structure to integrate the pre-existing legacy data into the event based data storage system. The event log monitor processes the one or more triggered events after all catch-up events in the event log data structure have been processed.

Integrating a legacy static system with an event-based system

A mechanism is provided for interactively indicating information associated with a patient on a hospital garment. A set of questions is identified utilizing a set of information received from a plurality of sources within a medical facility. The set of information is analyzed for a set of key elements. The set of key elements is utilized to identify one or more questions from a search question database. The one or more questions are submitted to a request processing pipeline implemented by a healthcare cognitive system. Responsive to receiving a response from the request processing pipeline, one or more communications are identified to be sent to one or more hospital garments associated with the patient and/or medical staff. The one or more communications are sent to the one or more hospital garments to cause the one or more hospital garments to change a visual cue.

Cognitively integrated indicating system

A mobile device controls content partitioning at a separate renderable content storage device of an item of renderable content into multiple partitioned content segments that are each less in size than the entire item of renderable content and that each fit within available memory of the mobile device. The mobile device renders on a display device of the mobile device multiple received content partition identifiers that each identify one partitioned content segment. The mobile device retrieves from the separate renderable content storage device a partitioned content segment of the item of renderable content identified by a user-selected content partition identifier. The mobile device renders the partitioned content segment. The mobile device automatically retrieves, in response to completion of rendering of the partitioned content segment, a second partitioned content segment using a second content partition identifier of the received multiple content partition identifiers.

Renderable content partitioning and portability

A storable duration of renderable content, based upon available memory for storage of renderable content associated with a mobile device, is determined in response to detecting a request for a portion of renderable content via an input device. The request for the portion of the renderable content based upon the storable duration is sent to a renderable content storage device, where the renderable content is identified by a content identifier. A content partition identifier and the portion of the renderable content having a duration less than or equal to the storable duration is received at the mobile device in response to the request. The content identifier, the content partition identifier, and the portion of the renderable content are stored within the available memory for storage of renderable content associated with the mobile device.

A service, which in one embodiment is a fashion social network, applies pre-defined criteria to items proposed for selection by a user, in order to determine if the proposed items are compatible with descriptive attributes and/or current possessions of the user.

Coherency of related objects

A method for automatically retrieving interaction information between objects, including: with a server, transforming a first image and a second image submitted to said server from a source into first and second sets of parameters, respectively; searching a database for an interaction relationship between the first and second images using the first and second sets of parameters; and returning a representation of the interaction relationship to the source.

Growing community of inventors

Chapel Hill, NC, United States of America

Adrian Vrouwenvelder