Past Events

Organizations frequently have to deal with documents received as images: for example, scanned, photographed, or faxed documents. In order to include such documents in your analysis and automate processes, you first need to convert them to a machine readable form. Megaputer offers a solution for converting images to electronic text.

Megaputer provides a text analysis solution that simplifies knowledge discovery in customer communications data.  The solution provides clustering and classification of documents, extraction of facts and patterns of interest, and elaborate sentiment analysis capabilities. It performs joint analysis of textual and structured data to determine key trends, relationships, and emerging patterns and then summarizes key findings in customizable graphical reports.

This webinar will present a live demonstration. To efficiently process adverse event (AE) reports, patient safety professionals encounter a number of challenges. First, they need to convert documents to a machine readable format. Second, it is not easy to identify and classify the actual adverse events related to specific medications, differentiating them from the indications the medications were prescribed for. And third, it is necessary to isolate serious adverse events that might affect patient safety and thus require immediate attention. Join us as we present a solution that efficiently handles all these tasks.

Time is of the essence when detecting emerging issues. This solution performs the analysis of customer feedback and service notes to identify patterns and trends in issues related to specific products. It detects previously unknown issues that have consistent growth over a sufficient period of time and reports them as emerging issues. The solution presented can also discern a weak but growing signal against the background noise of already known issues.

Discover how text analysis solutions can scout external sources, fetch documents of potential interest, and perform sophisticated analysis to extract relevant entities, facts and relationships with high recall and precision. See how you can timely reveal information about emerging technologies, growing negative impact signifiers, maneuvering of competitors, changing structure of corporate ownership, along with new acquisitions, partnerships, investments, and much more.

The analysis of data from online sources could enable an organization to learn about existing threats and opportunities from a global community of interested individuals. Such analysis requires accurate categorization of textual posts and detection of sentiment toward numerous discussed topics. The advent of adequate tools for text clustering and classification combined with sentiment analysis helps to generate more timely insights based on the analysis of all available data.

What if you could automatically reveal key researchers by analyzing a large collection of journal articles related to your topics of interest? Explore a system that determines the role and relative importance of each individual author and presents the results in both graphical and tabular formats.

Megaputer is proud to present a solution for performing quick and precise extraction of complex information patterns from various pre-indexed data sources including PubMed, ClinicalTrials.gov, FAERS, FDA Drug Labels and USPTO. Researchers may either create their own semantic queries or select from pre-set queries that can be expanded through various medical ontologies from a supplied library (MeSH, SNOMED CT, RxNorm, Genes, and MedDRA). The extracted elements of information are presented to the user in the form of tables with preset attributes. This solution is well poised for handling data curation tasks of nearly any complexity.

Patient electronic medical records (EMRs) contain a wealth of information that is of high value to pharma companies. But even when you can gain access to EMRs, the task or accurately extracting relevant information remains as a challenge. Megaputer provides a solution to this challenge. The solution extracts from EMRs important clinical findings, information about medications taken, efficiency of the treatment, and possible adverse events. It can classify different illnesses, medications, and adverse events in accordance with industry standard ontologies, such MeSH, SNOMED CT, RxNorm, and MedDRA.