Optum, Inc.

The Collaborative Group, Ltd.

Phase Forward Inc.

Paul Bleicher

Vijay S Nori

Christopher A Hane

Paul John Wallace

Carol Jean Simon

John Edward Hargraves

Nicholas Stamos

Adam Russell

Myra L Patchen

Sanjeeva L Fernando

Kemeng Li

Richard M Dale

Jeffrey P Klofft

Various embodiments of the disclosure provide apparatuses, systems, and computer program products for predictive data labelling using a dual-model system. Embodiments provide various advantages in accuracy of predicted labels, for example in various contexts such as medical data analysis for difficult to diagnose diseases. An example provided apparatus is configured to generate a positive, neutral, and negative candidate identifier sets and corresponding positive, neutral, and negative candidate index sets based in part on applying a candidate selection rule set to a candidate data set; train a candidate label probabilistic model based at least in part on a candidate label training subset associated with the candidate data set associated with the positive and negative candidate identifiers; generate a candidate positive-label probability set using at least the candidate label probabilistic model; train a historical record prediction model to predict the candidate positive-label probability set; and utilize the historical record prediction model.

Apparatus, computer program product, and method for predictive data labelling using a dual-prediction model system

An analytics platform and architecture is disclosed that improves the capture, extraction, and reporting of data required for certain measures, provides real-time data surveillance, dashboards, tracking lists, and alerts for specific, high-priority data, and offers dynamic, ad-hoc reporting capabilities. The platform includes a data extraction facility that gathers data from numerous sources, a data mapping facility that identifies and maps key data elements and links data over time, a data normalization facility to normalize the data and, optionally, de-identify the data, a flexible data warehouse for storing raw data or longitudinal data, an analytics facility for data mining, analytic model building, risk identification, benchmarking and tracking. The improved platform and architecture integrates social networking technology and analysis (SNA) on data to cluster data for more efficient, technically improved and focused processing.

Data processing systems and methods implementing improved analytics platform and networked information systems

A system and method for identifying relationships and correlations between community healthcare attributes includes automatically displays relationships between selected community health measures. A correlation tool automatically computes correlations between a selected main measure and each other measures in a set of community health measures for selected communities. The correlation tool automatically displays a ranked list of the other community health measures based on their correlation to the selected main measure. A relationship tool automatically computes correlations between selected measures in the set of community health measures for selected communities. The relationship tool displays a correlation graph indicating values of the selected measures for each of a selected set of communities. An adjusted correlation graph is automatically displayed to indicate adjusted values of the selected measures to accommodate a selected third measure as a control variable.

System and method for identifying relationships in community healthcare measures

A system and method for scoring and comparing communities includes the development of community health measures by on combining and supplementing healthcare data and community data from numerous sources. The community health measures may be stored in a community health measures database and may be accessed by interactive tools to generate customized representations of healthcare measures for selected communities. The representations are automatically computed in response to interactive user selections. Geographic map representation, heat map representations and data tables may be automatically generated to identify correlations between health outcomes and population attributes in different communities.

Community health scoring tool

A system and method for managing clinical trial data includes dynamically generating, at a server, a data entry form to be displayed at a client. The data entry form is generated dynamically in a SGML-derived language. Control elements within the form comprise images which are used to construct the control elements and larger controls. The form is generated from a protocol database and a context received from the client, is populated from the data database, and is published to the client. Templates based on the protocol database comprise several frames including intermediate frames for displaying frame borders which are non-horizontal and non-vertical. If the trial protocol changes during a trial, the generated form is based on the protocol version active at the time data was entered into the form. Inadvertent use of the application is discouraged requiring an authentication procedure and displaying a picture of the authenticated user. Furthermore, help is provided by creating a link between the text or each question and information about the question. The source of help may be any or all of a protocol document, an investigative brochure, and a study guide. In addition, a user, upon logging in, is presented with a dashboard screen which provides information or links to information such as trial-related news, alerts, statistical information, progress reports and a list of work to be completed.

Clinical trial data management system and method

Methods for inducing mobilization of peripheral blood precursor cells, for elevating levels of peripheral blood precursor cells and facilitating hematopoietic reconstitution in a mammal are disclosed, comprising administering to the mammal an effective amount of an underivatized, aqueous soluble .beta.(1,3)-glucan in a triple helix conformation, which does not stimulate or prime the production of proinflammatory cytokines in vitro.

Growing community of inventors

Newton, MA, United States of America

Paul Bleicher