International Business Machines Corporation

Merative US L.p.

Kimberly Diane Kenna

Robert Charles Leah

Niraj P Joshi

Nathanael Ferguson Ehrich

James Corvin Fletcher

Wayne B Riley

Adrian Vrouwenvelder

Stephen Carraway

John Hefferman

Adam Clark

Eric W Will

Ryan Alexander Boyles

Andrew Ronald Freed

Martin Miles Wattenberg

David Phillip Johnson

John Junior Boezeman

Isa M Torres

Jesse Holton Kriss

Fernanda B Viegas

Matthew Mehall McKeon

John H Fraleigh

Frank J Van Ham

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 service identifies a level of specificity of one or more identified entities in a user input comprising a query, within one of multiple levels of a hierarchy of a hierarchical coding system. Responsive to determining that additional levels of specificity beyond the identified level of specificity are recommended to return a minimum answer set to the query, the service returns one or more answers requesting one or more additional inputs refining the query based on one or more values identified in a next level. Responsive to determining that no additional levels of specificity beyond the identified level of specificity are recommended to return the minimum answer set to the query, the service returns an answer set comprising a selection of information for the current level of specificity from an ingested corpus of knowledge mapped to the hierarchical coding system.

Automatically refining application of a hierarchical coding system to optimize conversation system dialog-based responses to a user

Methods and apparatuses for performing clinical trial editing using machine learning are provided. One example method generally includes receiving information of a first clinical trial that is being drafted and identifying, in a corpus of literature, a plurality of documents that are relevant to the first clinical trial, based on the title of the first clinical trial. The method further includes providing the plurality of documents and the plurality of criteria to a machine learning model configured to output for each respective criterion of the plurality of criteria, a confidence value for the respective criterion, receiving as output from the machine learning model the confidence value for each respective criterion and, upon determining that a first criterion has a first confidence value below a predefined threshold, prompting a user to verify the first criterion.

Clinical trial editing using machine learning

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

A method and apparatus for filtering clinical trials using machine learning techniques is disclosed. An example method generally includes receiving a first set of filters that were applied to a first plurality of clinical trials with respect to a first patient. A system determines one or more attributes of the first patient and trains a machine learning (ML) model based on the first set of filters and the one or more attributes of the first patient. The system receives a selection of a second patient, determines one or more attributes of the second patient, and generates a second set of filters by processing the one or more attributes of the second patient using the trained ML model.

Methods and systems for recommending filters to apply to clinical trial search results using machine learning techniques

Techniques are disclosed for providing autonomic content load balancing. A programmatic selection is made from among alternative content versions based upon current conditions. Preferably, the alternative selectable versions specify content to be used in a Web page, and a version is selected responsive to receiving a request for the Web page. The selectable version may comprise the Web page, or a component of a Web page may have selectable versions. Optionally, the Web page may include more than one component with dynamically-selectable content. In this case, the versions may be selectable independently of one another.

Autonomic content load balancing

A mashup page presents link help information for logical links that pass context between widgets on the mashup page.

Help information for links in a mashup page

A computer program product for discovering and distributing relevant business information contained in a mashup comprises computer usable program code is configured to interrogate a mashup maker to discover the elements, relationships, and dependencies embodied by a mashup page; assemble this information into a data structure; and make the data structure accessible. A method for updating a configuration management database, where an end user creates a mashup page that embodies the end user's knowledge about the elements and processes required to fulfill a specific task, comprises deriving elements, relationships, and dependencies from the mashup page; creating a data structure representing this information, and communicating this data structure to the configuration management database.

Discovery and management of configuration data contained within mashups

A dependency hierarchy of resources can be determined for a dynamic mashup. The dependency hierarchy can specify dependency relationships among a set of resources. A set of views that correspond to the set of resources can be ascertained. For each view, a view template can be determined that is to be applied to that view. The mashup can be dynamically created that includes the views, each of which is configured in accordance with the associated view template. The created mashup can also include content defined by the set of resources that is configured in a manner consistent with the dependency relationships of the dependency hierarchy.

Dynamic mashup creation from a set of resources and resource relationships

A request for a mashup widget having multiple versions from an identifiable source can be identified. A data store can be queried to determine if a previous request for the mashup widget was made by the identifiable source. When the previous request exists, a version of the mashup widget used to handle the previous request can be automatically determined. The determined version can be one of many versions of the mashup widget. The determined version of the mashup widget can be used to generate a response to the request. When the previous request is not found when querying the data store, one of the mashup versions that is to be used can be determined based upon a programmatic rule. Historical data regarding widget version use can be saved in the data store and used to determine which widget version is to be selected to handle future requests.

Automatically managing versioning of mashup widgets

Embodiments of the present invention provide a method, system and computer program product for the collaborative development of a visualization dashboard. In an embodiment of the invention, a method for collaboratively developing a visualization dashboard can be provided. The method can include identifying an extended Wiki directive within a Wiki artifact for a visualization dashboard. The method further can include retrieving data referenced by the extended Wiki directive and one or more visual display elements referenced by the extended Wiki directive to visualize portions of the retrieved data. The method yet further can include mapping the visual display elements referenced by the extended Wiki directive to components requisite to programmatically rendering the visual display elements in the visualization dashboard. The method even yet further can include arranging the components in the visualization dashboard and linking the components to the retrieved data. Finally, the method can include displaying the visualization dashboard.

Collaborative development of visualization dashboards

A method for providing information associated with configuration changes to a computer system is provided. The method includes receiving a description of a starting configuration and a description of a configuration change. The method further includes linking the description of the starting configuration and the description of the configuration change and reading a record linked to the description of a configuration change, wherein the record includes advice about the configuration change and a total result value indicating a rate of success of the configuration change when the advice is followed. The method further includes receiving a first result value from the user indicating a result of the configuration change in light of the advice and calculating a new total result value that indicates a rate of success of the configuration change based on the total result value and the first result value.

Change management using collective data

Under the present invention, when a user resizes or otherwise hides a column in the electronic table, a graphical indicia is displayed that represents the hidden column(s). If a user interacts with the indicia (e.g., by hovering a mouse/input device over it), a pop-window will be displayed that identifies the hidden column(s). The pop-up window can include icons representing each hidden column or an associated function. By manipulating the listing contained in the pop-up window, the user can un-hide the hidden table column(s), change their order in the electronic table, etc. In addition, the indicia can be formatted (e.g., boldfaced, colored, or otherwise altered) to reflect a status of an entry or cell in one of the hidden column(s).

Growing community of inventors

Cary, NC, United States of America

Kimberly Diane Kenna