Monthly Archives: February, 2012

ONC to Survey Patients About EHR Privacy

February 17th, 2012 Posted by News No Comment yet

“The Office of the National Coordinator for HIT will launch a five-year national survey, totaling 10,000 interviews, to assess patient attitudes about the privacy and security of electronic health records and health information exchange.”

This is an important topic when considering the accessibility and usefullness of electronic healthcare data for clinical research purposes. It will be interested to see the results of this study. Read full article here:

New data shows hospital readiness for Stage 1 MU increasing

February 17th, 2012 Posted by News No Comment yet

“A comparison of HIMSS Analytics data from September 2011 to December 2011 suggests that a number of hospital segments showed increased capability to achieve Stage 1 of meaningful use.”

We look forward to these advances in the use of EHR data, which will lead to more accessible and usable data for clinical research. Read more here:

Patient Recruitment via Social Media: Lessons Learned

February 13th, 2012 Posted by News No Comment yet

“All-told the Mayo Clinic’s recent pilot study on clinical trial patient recruitment recruitment using social media and online networks not only helped researchers assemble large and demographically diverse patient groups more quickly, but also they did it less expensively than they could through other means.

“This study is a prime example of patient-initiated research that could be used by other health care professionals and institutions,” conclude the authors of the Mayo report.

But can the Mayo Clinic’s pilot study really be used “by other health care professionals and institutions?” Was the success of their social media recruitment so easily translatable? Or was their pilot study the result of a perfect storm— a series of factors coming together to make it just the right opportunity for social media recruitment, and anything but commonplace.”

Read full article here:

Natural Language Processing (NLP)

February 2nd, 2012 Posted by Services No Comment yet

The majority of electronic clinical documentation is stored as “free text” rather than as structured, coded data. An advantage of free text is that it gives clinical authors autonomy in expressing their thoughts. The variety of ways used to express information in text means that although this data is rich and descriptive, it is locked away, unable to be used in computerized research and decision support. To leverage text data, we employ a variety of natural language processing (NLP) methods to extract concepts, context, and relationships found in narrative text.

While NLP is not a “solved” science, there are many tasks that NLP can do very reliably.  Extracting concepts (symptoms, diseases, medications) and values (ejection fracture value, lab values, vital signs) that are stored in the text.  More complex tasks, such as determining what caused an event of interest or why a patient discontinued a medication can be conducted to answer specific study questions.

Anolinx uses advanced NLP technology. In our projects, specific NLP tools are developed, tested and optimized for accuracy and reliability, according to the definitions for the cohort criteria and/or outcomes of interest.

Use of NLP in our projects often includes:

  1. (a) defining each symptom/outcome in detail by a qualified clinician specialist and NLP expert
  2. (b) developing the NLP tools based on the detailed definitions
  3. (c) training the NLP tools using information from the clinical notes
  4. (d) testing the NLP tools for accuracy & reliability against a manually annotated sample of the clinical notes

The gold standard for validation of the NLP tools is manual chart review. This process results in a validated tool to accurately and reliably identify patients and outcomes of interest.


February 1st, 2012 Posted by Services No Comment yet

Outcomes Research

February 1st, 2012 Posted by Services No Comment yet