Last year Georgetown University Medical Center launched the Center for Innovation in Leadership and Education (CENTILE).

In June I presented a poster at the first CENTILE  Colloquium for GUMC Educators in the Health Professions.

My poster Using iPads to Enhance Teaching and Learning on Patient Rounds explained how I have used iPads over the last four years on patient rounds to improve the education of medical students and residents at GUMC. I plan to continue to be involved with CENTILE in the future as I explore further innovative uses of technology in education.

View the original post.


It’s always good to see NLP being used in a clinical care, a recent story about Microsoft and Washington University in Seattle using NLP in pneumonia detection in the ICU is a good example of this.

The project, called deCIPHER, uses a combination of Microsoft linguistics and machine learning to assess clinical information from electronic medical records and derive a diagnosis.

The system was trained against a cohort of 100 patients who had already been diagnosed with pneumonia and used a machine learning framework to build a predictive model based on extracted clinical factors. The system accurately predicted 84% of positive patients and the team are assessing incorporating the model into an ICU dashboard.

Last year Kaiser Permanente also published a paper on pneumonia diagnosis in relation to the ICU and using chest radiograph reports, using Linguamatics I2E for information extraction and also applying machine learning to the resulting clinical factors.

From a total of 194,615 ICU reports, Kaiser Permanente empirically developed a lexicon to categorize pneumonia-relevant terms and uncertainty profiles.


A recent customer project highlighted to me the importance of being able to apply NLP to cohort selection to support medical research, clinical trials recruitment and outcomes analysis.

A new customer of ours was setting up a study into patients with HIV and Hepatitis C and needed to identify potential subjects from their AllScripts EHR. As many organizations do, they had five medical students spend four months trawling through patient records to identify 700 potential study candidates.

The process was particularly painful because simply looking for the ICD-9 codes for HIV and Hepatitis C in structured fields was missing significant numbers of potential subjects. This was caused by variations in where the data was recorded; sometimes it was coded in structured fields; sometimes it was written in the patient narrative that he or she was positive for HIV or Hepatitis C; sometimes it was both.

Assessing the narrative is always a problem with variations in patient history vs family history and “tested for HIV, negative result” and “positive for HIV” requiring careful reading.

Our customer had recently installed our I2E NLP platform and had indexed a large collection of patient records by extracting documents from AllScripts via their analytical data warehouse.

The data sets were indexed with the usual domain ontologies covering diseases, medications, procedures etc. to support rapid searching in I2E.


More than 35,000 healthcare industry professionals are expected to attend the 2014 Annual HIMSS Conference & Exhibition in Orlando to discuss health IT issues and view innovative solutions designed to transform healthcare.

Linguamatics is proud to be an exhibitor at this annual event that helps health IT professionals find the right solutions for their organizations.

Hillary Clinton, 67th Secretary of State of the United States, leads a keynote roster that also includes Mark Bertolini, chairman, CEO and president of AETNA, and Erik Weihenmayer, a world-class blind adventurer.

On the exhibit floor, the enhanced HIMSS Interoperability Showcase will feature an interactive environment where health IT solution providers can collaborate to maximize the collective impact of their technologies and connect with decision makers.

Linguamatics will showcase its leading clinical Natural Language Processing platform, which transforms the unstructured text from electronic health records into patient insights. Demonstrations include information extraction from pathology reports and patient narratives, and matching patients to clinical trials based on inclusion and exclusion criteria.

To learn more about Linguamatics, visit us at booth #1794 during HIMSS14, February 23-27, 2014, at the Orange County Convention or take a look through our website.

For more information about HIMSS14 and to register, visit www.himssconference.org.


(Cambridge, England and Boston, USA – November, 18 2013) Linguamatics, the market-leader in natural language processing-based (NLP) text mining and analytics, today announced the launch of Linguamatics Health, a new clinical NLP suite that enables hospitals and research organizations to harness the information contained in unstructured fields of EHRs and patient narratives to drive healthcare analytics, advanced research and improved patient outcomes. 

Linguamatics Health provides the technology needed to extract meaningful information from the mass of data located in complex patient documentation such as pathology and radiology reports, physician notes, and discharge reports. The information is then used in data warehouses, predictive models and dashboards to improve hospital efficiency and support Meaningful Use initiatives.

The information can also be used to populate clinical annotations for biobanks and provide data for Clinical Trial Management Systems to improve disease understanding and clinical trial recruitment. 

“While the rapid adoption of EHRs in recent years has integrated many data silos together, healthcare providers are still faced with a large proportion of their data in unstructured form.

"To achieve the improvements in hospital efficiency and patient outcomes required to cope with rising costs and an aging patient population, hospitals, payers and other healthcare organizations need to make better use of unstructured text,” said Phil Hastings, Senior Vice President, Sales and Marketing, at Linguamatics.