Current Report on Form 8-K
UNITED
STATES
SECURITIES
AND EXCHANGE COMMISSION
WASHINGTON,
D.C. 20549
FORM
8-K
CURRENT
REPORT
Pursuant
to Section 13 or 15(d) of the
Securities
Exchange Act of 1934
Date
of
report (Date of earliest event reported): October 4, 2006
Health
Discovery Corporation
(Exact
name of registrant as specified in charter)
|
Texas
|
333-62216
|
74--3002154
|
|
(State
of incorporation)
|
(Commission
File Number)
|
(IRS
Employer
Identification
No.)
|
5501
½ Abercorn Street, Savannah, GA 31405
(Address
of principal executive offices / Zip Code)
912-352-7488
(Registrant’s
telephone number, including area code)
Check
the appropriate box below if the Form 8-K filing is intended to simultaneously
satisfy the filing obligation of the registrant under any of the following
provisions:
|
|
o |
Written communications
pursuant to Rule 425 under the Securities
Act.
|
|
|
o |
Soliciting material
pursuant to Rule 14a-12 under the Exchange
Act.
|
| |
o |
Pre-commencement
communications pursuant to Rule 14d—2(b) under the Exchange
Act.
|
| |
o |
Pre-commencement
communications pursuant to Rule 13e—4(c) under the Exchange
Act.
|
Item
8.01 Other Events.
On
October 4, 2006, the U.S. Patent and Trademark Office issued to Health Discovery
Corporation ("HDC") Patent No. 7,117,188, entitled “Methods of Identifying
Patterns in Biological Systems and Uses Thereof” covering the use of recursive
feature elimination ("RFE") using the support vector machine ("SVM"). RFE is
a
mathematical filtering process by which features within input data can be
identified as being more significant for use in classifying the data by rank
order using an SVM. When analyzing large volumes of data, eliminating features
that are non-critical to the successful rank order classification of the data
improves accuracy and reduces processing time. RFE is a particularly powerful
tool for achieving feature reduction because it takes into account dependencies
between features and is therefore considered more sophisticated than other
methods that evaluate and eliminate such features independently. No RFE patent
has ever been issued to another party in the United States.
Reported
applications of RFE-SVMs include gene expression and mass spectrometry analysis
for biomarker identification and medical diagnostics, predicting antisense
oligonucleotide efficacy, discriminating classes of toxicants, text and image
recognition, and evaluating beef cattle quality, and others.
While
the
title of the patent suggests that the scope of the technology is limited to
biological data, the basic claims encompass the application of the RFE-SVM
method to all data types. Dependent claims are directed to the use of RFE-SVM
for identifying patterns in biological data and for use in diagnosis, prognosis
or treatment of a disease.
The
RFE
method was first reported in 2002 in an article by inventors Isabelle Guyon,
a
member of HDC’s Scientific Advisory Board, Stephen Barnhill, HDC’s Chairman and
CEO, and Jason Weston, together with co-author Vladimir Vapnik, also a member
of
HDC’s Scientific Advisory Board. The article, entitled “Gene Selection for
Cancer Classification Using Support Vector Machines”, published in the journal
Machine Learning, has been broadly cited in subsequent publications by hundreds
of researchers worldwide, demonstrating the significance and widespread use
of
the RFE method within the SVM field.
In
addition to this newly issued RFE-SVM patent, HDC now holds the exclusive rights
to 17 issued U.S. and foreign patents covering uses of SVMs for discovery of
knowledge from large data sets. The issued patents cover methods and systems
for
pre-processing of data to enhance knowledge discovery using SVMs, analysis
of
data using multiple SVMs and for multiple data sets, providing SVM analysis
services over the Internet, use of SVMs for digital image analysis, and new
kernels for machine learning. HDC’s pending U.S. and foreign patent applications
cover numerous improvements to and applications of SVMs including computer-aided
image analysis using SVMs, with particular application to diagnosis using
medical images, methods of feature selection for enhanced SVM efficiency and
biomarkers for colon cancer, prostate cancer and renal cancer discovered with
these methods, and use of SVMs for analysis of spectral data such as data
generated in mass spectrometry.
SIGNATURES
Pursuant
to the requirements of the Securities Exchange Act of 1934, the registrant
has
duly caused this report to be signed on its behalf by the undersigned thereunto
duly authorized.
| |
HEALTH
DISCOVERY CORPORATION
|
| |
|
|
Dated:
October 11, 2006
|
By: /s/ Daniel
Furth
|
| |
Daniel
Furth
|
| |
Principal
Financial Officer
|
3