Ex Parte Bashour et al

Patent Trial and Appeal Board

Sep 8, 2016

13419463 (P.T.A.B. Sep. 8, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR
13/419,463 03/14/2012 C. Allen Bashour
26294 7590 09/12/2016
TAROLLI, SUNDHEIM, COVELL & TUMMINO L.L.P.
1300EASTNINTH STREET, SUITE 1700
CLEVELAND, OH 44114
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www .uspto.gov
ATTORNEY DOCKET NO. CONFIRMATION NO.
CCF-8331-US-CON-l 7969
EXAMINER
BAYS,PAMELAM
ART UNIT PAPER NUMBER
3766
NOTIFICATION DATE DELIVERY MODE
09/12/2016 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address( es):
rkline@tarolli.com
docketing@tarolli.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte C. ALLEN BASH OUR, BALA GOP AKUMARAN NAIR,
MIRELA VISINESCU, MENG XU, LIANG LI, and
MOHAMED H. BAKRI1
Appeal2014-009777
Application 13/419,463
Technology Center 3700
Before DANIELS. SONG, KEN B. BARRETT, and
FREDRICK C. LANEY, Administrative Patent Judges.
SONG, Administrative Patent Judge.
DECISION ON APPEAL
1 The real party in interest is Cleveland Clinic Foundation (Appeal Brief
(hereinafter "App. Br.") 3).
Appeal2014-009777
Application 13/419,463
STATEMENT OF THE CASE
The Appellants appeal under 35 U.S.C. § 134 the Examiner's final
rejection of claims 8, 10-14, and 21 in the present application, various other
claims having been either cancelled or withdrawn (App. Br. 3). In addition
to its Appeal Brief, the Appellants rely on a Reply Brief (hereinafter "Reply
Br."). We have jurisdiction under 35 U.S.C. §§ 6(b) and 134.
We REVERSE.
The claimed invention is generally directed to predicting the onset of
atrial fibrillation (Title, Abstract). The sole independent claim on appeal
reads as follows (App. Br. 14, Claims App., emphasis added):
8. A non-transitory computer readable medium containing
computer executable instructions that can be executed by a
processor to predict the onset of atrial fibrillation (AF) from
electrocardiogram (ECG) data representing a patient, the
executable instructions comprising:
a signal processing component that determines
parameters representing the activity of the heart of the patient
from the ECG data, the signal processing component
comprising a premature atrial contraction (PAC) detection
system that identifies premature atrial contractions represented
by the ECG data;
a feature extraction component that calculates a plurality
of features from the determined parameters, at least one feature
being calculated from the detected premature atrial
contractions; and
a classification component that determines an AF index
for the patient, representing the likelihood that the patient will
experience AF, from the calculated plurality of features.
2
Appeal2014-009777
Application 13/419,463
The Examiner rejects claims 8, 10-14, and 21under35 U.S.C.
§102(b) as anticipated by Ritscher. 2
ANALYSIS
The Examiner rejects claims 8, 10-14, and 21 as anticipated by
Ritscher, specifically finding that the limitations of claim 8 pertaining to "a
feature extraction component," and "a classification component" are
disclosed in Ritscher (Final Act. 2-3, citing Ritscher i-fi-14, 5, 27, 41, 44, 61-
62, 108, and 125). The Appellants argue that Ritscher fails to disclose
predicting "the onset of postoperative atrial fibrillation (AF) from
electrocardiogram (ECG) data," or the limitations pertaining to the "feature
extraction component," and the "classification component" as recited in
independent claim 8 (App. Br. 7-9). Based on the preponderance of the
evidence, we agree with the Appellants that the Examiner erred in finding
that Ritscher anticipates claim 8, and address the findings and arguments
necessary to decide this appeal below.
The Appellants argue, inter alia, that the system disclosed in Ritscher
does not determine an atrial fibrillation index "representing the likelihood
that the patient will experience AF" as recited by claim 8, but merely detects
"atrial arrhythmias, particularly atrial fibrillation (AF) and atrial flutter
(APL) using discriminatory signatures of the ventricular cycle lengths."
(App. Br. 7-8, quoting Ritscher i-f l ). In discussing various portions of
Ritscher, the Appellants summarize that "Ritscher describes algorithms for
2 U.S. Patent Application Publication No. US 2004/0092836 Al, published
May 13, 2004 to Ritscher et al.
3
Appeal2014-009777
Application 13/419,463
discriminating, detection and/ or characterization of atrial arrhythmia by
identifying formations in a scatter plot derived from ventricular beats."
(App. Br. 8, citing Ritscher i-fi-1 31-33; see also App. Br. 11, citing Ritscher
i-fi-131-33, 61---65, 103-105). The Appellants explain that in Ritscher,
Lorentz plots of ventricular signals are used to "detect episodes of AF that
have already occurred, discriminating among various possible cardiac
physiological conditions, whereas the AF index calculated in claim 8 deals
with the likelihood of future episodes of AF." (Reply Br. 2-3, citing
Ritscher i-fi-1 61, 62, 66).
The Appellants conclude that in contrast to claim 8, which "recites a
classification component that determines an AF index for the patient,
representing a likelihood that the patient will experience AF," Ritscher
"merely provides a likelihood only of whether or not an AF has happened
during the collected data period." (App. Br. 10; see also Reply Br. 2). A
preponderance of the evidence indicates that the Appellants are correct in
their understanding of Ritscher.
The Examiner finds that Ritscher "explicitly discloses that the system
and algorithm may be used to predict atrial arrhythmias, including atrial
fibrillation or AF, and thus would read on the limitation, 'likelihood that the
patient will experience AF'." (Ans. 5). The Examiner's finding is based on
Ritscher' s disclosure, which states:
The algorithms of the present invention can also be
incorporated into a processor readable medium containing
instructions to cause the processor to utilize ventricular signals
to access atrial patterns for predicting, monitoring, diagnosing
and treating atrial arrhythmias.
(Ritscher i1 44; see also id. i-f 130; Final Act 5).
4
Appeal2014-009777
Application 13/419,463
However, as the Appellants correctly argue, "Ritscher provides no
further explanation as to prediction .... Ritscher fails to disclose which atrial
arrhythmia is to be predicted, what prediction model is to be employed, or
which of the 'atrial patterns' are used or even important to such a
prediction." (App. Br. 11). Indeed, when this passage is considered in
context of the disclosure of Ritscher as a whole, it merely suggests that the
disclosed algorithms can be incorporated and used in some undisclosed
processor readable medium containing instructions for causing the processor
to predict atrial arrhythmias. Such suggestion of using the disclosed
algorithms is not the same as disclosing such a medium that is executable to
determine an index that represents "the likelihood that a patient will
experience AF" as required by claim 8.
The Examiner further finds that Ritscher specifically discloses that
"[a] high NND metric value signifies the likelihood of AF." (Ans. 5---6,
quoting Ritscher i-f 69). However, as the Appellants point out (Reply Br. 4),
the full content of the quoted paragraph states that if the nearest neighbor
distance information (NND) meets the AF signature metric, "AF is declared"
by the NND algorithm disclosed (Ritscher i-f 69; see also Ritscher i-f 71
(stating that "NND algorithm identifies or declares episodes of AF.")). In
addition, while Ritscher further discloses that "very, very low iNND metric
value signifies a likelihood of AF," this again appears to be referring to the
decision/determination by the disclosed algorithm that the electrocardiogram
data indicates atrial fibrillation has occurred as opposed to some other atrial
arrhythmia (Ritscher i-fi-1 69-71; see also Reply Br. 4 ).
5
Appeal2014-009777
Application 13/419,463
The Examiner further finds that "[d]etermining the onset of AF
through predictive values (Paragraph 0004, 0044, 0125) would read on the
limitation 'predict[ing] the onset of atrial fibrillation' as required by Claim
8." (Final Act. 5; Ans. 5). The "predictive value" referenced by the
Examiner is mentioned in paragraph 125 of Ritscher, which states:
The recordings for each patient were analyzed by each of
the algorithms of [the] present invention resulting in decisions
reached for each analyzed two-minute segment. The decisions
reached by each algorithm were compared to the truth for each
such two-minute segment, and ROC curves, sensitivity curves,
specificity curves, positive predictive value, and negative
predictive value were calculated employing standard
techniques.
(Ritscher i-f 125).
The Examiner again does not appear to consider the context of the
cited passage. We understand the above cited paragraph as merely
indicating that the results attained using the algorithms disclosed in Ritscher
(i.e., decisions/determinations as to what arrhythmic condition occurred)
were evaluated for accuracy, and based thereon, a metric (i.e., "predictive
value") was calculated so as to provide an indication as to the level of
confidence that can be afforded to the decisions made by the algorithms.
Therefore, in view of the above considerations, we are persuaded that
the Examiner has not adequately established that Ritscher discloses each and
every limitation recited in independent claim 8. Correspondingly, we
reverse the Examiner's anticipation rejection of independent claim 8. The
remaining arguments between the Appellants and the Examiner as to
whether Ritscher discloses the recited "feature extraction component" are
moot. Finally, claims 10-14 and 21 depend from independent claim 8 and
6
Appeal2014-009777
Application 13/419,463
therefore contain the same pertinent limitations discussed above. Hence, we
also reverse the Examiner's anticipation rejection of these dependent claims
as well.
ORDER
The Examiner's rejection is REVERSED.
REVERSED
7