Communications - June 2012

tient privacy and who should be able to contribute to health records, bioinfor-maticists are researching how to perfect NLP capabilities.

One NLP issue, says Denny, is that the majority of natural language processing technology has been created for dictated speech, but electronic health records are often typed.

“Typed documents are more ambig-
uous because there are more abbrevia-
tions and acronyms, and the documents
usually contain more misspellings,”
says Denny. “You don’t describe things
in as much detail, so that hinders a lit-
tle bit the richness of what can be done
with natural language processing. May-
be speech-recognition technology will
move forward fast enough that we’ll
move toward documents that look like
dictated documents, and the problems
won’t be as big.”
William Cohen, research professor
of machine learning at Carnegie Mel-
lon University, is currently research-
ing the creation of a domain-specific
version of the Never Ending Language
Learner (NELL), refining its general-
purpose Web-crawling algorithm for
use in published biomedical litera-
ture called BioNELL. While BioNELL
is focused on published biomedical
literature rather than on-the-fly clini-
cal notes, Cohen says such domain-
specific, rank-and-learn principles
might be useful for organizations’ in-
house lexicons while wider standards
are being crafted.

“The exciting thing I find about

one nLP issue, says
Joshua C. Denny,
is that the majority
of nLP technology
has been created
for dictated speech,
but electronic
health records
are often typed.

BioNELL is taking the existing struc-
tured databases and using them to
kick-start an NLP system,” Cohen
says. “Symmetrically, you might want
to take a natural language corpus and
use that to kick-start understanding a
sensor database.”
Brunak says that while the attention
paid to his group’s Computational Biol-
ogy paper about unlikely comorbidities
was interesting, the broader message
should be that examining more hith-
erto machine-unreadable data could
alter the practice of medicine.

“Real patients have more than one disease,” says Brunak, “and the patient records give us an opportunity to discover comorbidities and disease correlations—not only those that co-

news

occur but also disease trajectories, that is, those that come before others. The message should be that we can start disease profiles of real patients instead of doing what medicine has done for hundreds of years, studying people disease by disease.”

Milestones

Computer Science Awards

the american academy of arts and sciences, John simon Guggenheim Memorial foundation, national science foundation, and the franklin Institute recently honored leading computer scientists.

AMeRiCAn ACADeMy MeMBeRs
the american academy of arts
and sciences named seven
new members in the section of
computer sciences (including
artificial intelligence and
information technologies).
they are Arvind, Massachusetts
Institute of technology; Robert
P. Colwell, r&e Colwell &
associates, Inc.; Irene Greif, IBM;
M. Frans Kaashoek, Massachusetts
Institute of technology;
Michael Kearns, University
of pennsylvania; Judea Pearl,
University of California, los
angeles; and Jeffrey D. Ullman,
stanford University.

GuGGenheiM feLLo W John simon Guggenheim Memorial foundation selected Susan Landau, a visiting scholar at harvard University, as a 2012 fellow in the category of computer science.

ALAn T. WATeRMAn AWARD the national science foundation (nsf) named Robert Wood, an associate professor in harvard University’s school of engineering and applied sciences, and Scott Aaronson, an associate professor of electrical engineering and computer science at the Massachusetts Institute of technology, to receive the 2012 alan t. Waterman award, which “recognizes an outstanding researcher under the age of 35 in any field of science or engineering nsf supports.”

BenJAMin fRAnkLin MeDAL

the franklin Institute awarded
the Benjamin franklin Medal
in Computer and Cognitive
science to Vladimir Vapnik,
who is a professor of computer
science and statistics at royal
holloway, University of london,
and holds a professorship in
computer science at Columbia
University. vapnik was recognized
for “his fundamental contribu-
tions to our understanding of
machine learning” and “his
invention of widely used
machine learning techniques.”
—Jack Rosenberger