Linguamatics is pleased to announce the latest release of its award-winning natural language processing (NLP)-based text mining and analytics platform, I2E 4.4.

This latest release expands the range of online content access available through I2E OnDemand to include FDA AERS data, from the US Food and Drug Administration’s Adverse Events Reporting System.
 

Software enhancements

I2E 4.4 also adds a number of important software enhancements, including an NLP plugin framework to support non-English languages, enhanced capabilities for viewing chemical structures, better extraction of information from tables, and a new human - readable query language.

FDA AERS is typically used to monitor and discover safety issues in drugs released for public use. This new addition to Linguamatics’ cloud based I2E OnDemand platform allows users to immediately start mining this valuable safety data source without the overhead of downloading, processing and maintaining the information themselves.

The availability of a new multi-language plug-in framework in I2E 4.4 builds on the theme of this release to extend text mining to a wider range of content.

Text miners can now analyze documents written in a new language by plugging in an appropriate third-party language module.
 

Extended support for PowerPoint, Word and Excel

I2E 4.4 also delivers a number of further improvements, such as extended support for Microsoft PowerPoint, Word and Excel documents. This allows efficient review of document repositories, including extraction of information from tables.
 


A new speaker has just been announced for the annual Text Mining Conference hosted in Cambridge, UK. This annual conference has been running for over 10 years and features text analytics use cases particularly across pharma and life science. Information professionals across top 100 pharma and life science organizations gather to share insight, best practice and discuss the future of text mining technology.

Eleanor Yelland will be presenting on: I2E in mental health: Analysis of online transcripts used in cognitive behavioural therapy.

Eleanor is a PhD Student in the Division of Psychiatry at University College London. Her PhD is a partnership with Linguamatics and Ieso Digital Health, who provide text-based online cognitive behavioural therapy.

The project focuses on the language within the treatment sessions and how text mining methods can be applied to best use this to learn about and improve treatment provision. The work primarily involves identifying potentially relevant linguistic characteristics, measuring these and building statistical models of their relationship with therapy outcome scores.  

This adds to a world-class list of speakers across pharma and healthcare who will be presenting at the conference, including:

Jonathan Hartmann, Georgetown University Medical Center: Evolution of I2E to improve patient care

Thierry Breyette, Novo Nordisk: Generating Actionable Insights from Real World Data

Cassie Gregson, AstraZeneca: Application of Text Mining to Clinical Research


Reading some of the FDA blogs reviewing 2015, I was interested to read that "for the second consecutive year, [the FDA] approved more drugs to treat rare diseases than any previous year in our history." This is great news for the patients affected by these rare or orphan diseases, and there is of course potential for applications of such drugs and the knowledge around these diseases across the wider population and in broader healthcare.

Text analytics can play a part in developing better understanding around the biology of these rare diseases. There's a great example of this application of text mining from Madhusudan Natarajan at Shire Pharmaceuticals. Shire develops and provides healthcare in the areas of behavioural health, gastrointestinal conditions, rare diseases, and regenerative medicine, and Madhu has presented his research using text analytics to uncover disease severity and genotype-phenotype associations for Hunter Syndrome (also known as Mucopolysaccharidosis II).

We recently hosted a webinar with Madhu. In this webinar, he illustrates some of the challenges for R&D for orphan diseases, particularly around text mining for mutation and variant patterns, which can be reported in so many different ways in the literature. 

Webinar: A systematic examination of gene-disease associations through text mining approaches


Animal models are crucial in the understanding of disease, the underlying pathways and the gene targets that play a role. One tool that has shown great value is the knockout mouse model.

The number of KO mouse models has increased massively since the first one in 1989, and mice models have been used successfully in increasing our understanding of diseases as varied as different cancers, diabetes, obesity, blindness, Huntington's disease, aggressive behaviour, and even drug addiction.

Understanding the landscape of KO mouse models for any particular disease area is important, and curated databases (e.g. IMPC or MGI) provide valuable data, but keeping track of new KO mouse models published in the scientific literature is challenging.

Peng Zhang, ‎Senior Staff Scientist at Regeneron Pharmaceuticals, uses Linguamatics I2E to tackle this challenge, and he presented on “Text Mining for Knockout Mice and Phenotypes” earlier this year.

 Diagram showing the set of KO genes involved in autoimmune phenotypes. All hits from both I2E and MGI were manually curated and only 479 unique KO genes were considered “true positive”. 61% true positives only came from I2E query and were not covered by MGI.


CMIOs-Importance-of-Clinical-NLP

 

The transition to new value-based payment models is spurring provider demand for technologies that enhance patient care and minimize safety risks, and in turn reduce costs. Of particular interest are tools to help providers predict the likelihood of potentially avoidable outcomes, such as a hospital readmission, pulmonary nodules turning cancerous or the contraction of sepsis.

According to a recent Linguamatics survey, most hospital CMIOs support the use of predictive models to improve the quality of care. In addition, CMIOs believe that these models can be enhanced with the use of Natural Language Processing (NLP) to access insightful data from unstructured chart notes.