Ex Parte Verbeek

Patent Trial and Appeal Board

Apr 24, 2017

13992845 (P.T.A.B. Apr. 24, 2017)

United States Patent and Trademark Office
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
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
13/992,845 06/10/2013 Alexander Adrianus Martinus Verbeek 2010P01213WOUS 6181
24737 7590 04/26/2017
PTTTT TPS TNTFT T FfTTTAT PROPFRTY fr STANDARDS
EXAMINER
465 Columbus Avenue BUSS, BENJAMIN J
Suite 340
Valhalla, NY 10595 ART UNIT PAPER NUMBER
2129
NOTIFICATION DATE DELIVERY MODE
04/26/2017 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):
marianne. fox @ philips, com
debbie.henn @philips .com
patti. demichele @ Philips, com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte ALEXANDER ADRIANUS MARTINUS VERBEEK
Appeal 2017-002576
Application 13/992,8451
Technology Center 2100
Before LINZY T. McCARTNEY, NATHAN A. ENGELS, and
JAMES W. DEJMEK, Administrative Patent Judges.
ENGELS, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Appellant appeals under 35 U.S.C. § 134(a) from a final rejection of
claims 1—3, 5—14, and 16—21. The Examiner withdrew the rejection of
claims 9 and 20 in the Examiner’s Answer. See Ans. 8. Accordingly, the
Examiner’s rejections of claims 1—3, 5—8, 10-14, 16—19, and 21 are before
us on appeal. We have jurisdiction under 35 U.S.C. § 6(b). Claims 4 and 15
are canceled. See App. Br. 12, 14.
We affirm.
1 Appellants identify Koninklijke Philips Electronics N.V. as the real party in
interest. App. Br. 2.
Appeal 2017-002576
Application 13/992,845
ILLUSTRATIVE CLAIM
Claims 1, 14, and 16 are independent claims. Claim 1, reproduced
below, is illustrative of the claimed subject matter:
1. A system for detecting an irregularity in a patient’s
medical record, comprising a medical knowledge base
comprising a collection of knowledge-base expressions and a
collection of knowledge-base relations between the knowledge­
base expressions;
a database comprising the patient’s medical record,
including one or more free-text documents comprising
information relating to the patient;
a natural language processor that extracts patient record
expressions from the free-text documents and determines patient
record relations between the patient record expressions;
an analysis engine that analyzes the patient record
expressions and the patient record relations based on the
knowledge-base expressions and the knowledge-base relations to
detect an irregularity in the patient record, wherein the
knowledge-base relations define constraints on the patient record
relations and patient record expressions, and the irregularity
comprises a violation of at least one of the constraints; and
a notifier that provides a notification on a display that the
irregularity has been detected in the patient record.
App. Br. 11 (Claims App’x).
THE REJECTIONS2
Claims 1—3, 5—6, 8, 10—14, 16—19, and 21 stand rejected under
2 In the final rejection, the Examiner rejected claim 14 under 35 U.S.C.
§ 112(b) as being indefinite because the term “the error” lacked sufficient
antecedent basis. See Final Act. 2—3. After the final rejection, Appellant
amended claim 14 in attempt to remedy the § 112 rejection, including the
deletion of the word “error” from the claim. See Response to Final Office
2
Appeal 2017-002576
Application 13/992,845
35 U.S.C. § 103(a) as unpatentable over Rubin* * 3 and Maimon.4
Claim 7 stands rejected under 35 U.S.C. § 103(a) as unpatentable over
Rubin, Maimon, and Ploesser.5
ANALYSIS
Claims 1—3, 5—6, 8, 10—14, 16—19, and 21
Appellant contends the Examiner erred in finding the combination of
Rubin and Maimon teaches or suggests the “analysis engine” element of
claim 1. See App. Br. 6—7; Reply Br. 2—5. More specifically, Appellant
argues Rubin does not analyze a patient’s medical records but instead,
merely “analyzes a clinical trial procedure (protocol). . . before the clinical
trial is implemented, and before actual patients are selected for participation
in the trial.” Reply Br. 2; see also App. Br. 6. Appellant further argues
“Maimon discloses extracting medical data from a patient’s record using
natural language processing .... [and] processing [] this data to select
Action 5, 8 (filed March 28, 2016). The Examiner agreed to enter the
amendment (see Adv. Act. 2) but did not formally withdraw the § 112
rejection in either the Advisory Action or the Examiner’s Answer. See Adv.
Act. 1—3; Ans. 2—8. Nevertheless, because (1) the term “the error,” which
was the basis for the § 112 rejection, is no longer recited in claim 14, and (2)
the Examiner’s restatement of the grounds of rejection in the Examiner’s
Answer does not include the § 112 rejection, we treat the rejection of claim
14 under 35 U.S.C. § 112(b) as having been withdrawn.
3 Daniel L. Rubin et al., Knowledge Representation and Tool Support for
Critiquing Clinical Trial Protocols, Proc. American Medical Informatics
Symposium (AMIA) 724—28 (2000) (“Rubin”).
4 Maimon et al. (US 2003/0154208 Al; published Aug. 14, 2003)
(“Maimon”).
5 Ploesser et al. (US 2009/0113380 Al; published Apr. 30, 2009)
(“Ploesser”).
3
Appeal 2017-002576
Application 13/992,845
patients to participate in clinical research. . . . [But] Maimon, like Rubin, is
silent with respect to finding irregularities in a patient’s record” (App. Br. 7).
Finally, with respect to the combination of Rubin and Maimon, Appellant
argues “one of skill in the art would not be lead [sic] to the combination
proposed by the Examiner because the only motivation to use a knowledge
base to identify irregularities in a patient’s record is found in the applicant’s
disclosure” (App. Br. 9).
Having considered the Examiner’s rejections in light of each of
Appellant’s arguments and the evidence of record, we agree with the
Examiner that the “analysis engine” element of claim 1 would have been
obvious in view of the combination of Rubin and Maimon. We agree with
the Examiner that Rubin’s Protocol Inspection and Critiquing Tool of Study
Structure (“PICASSO”) teaches the entirety of the claimed “analysis engine”
element and its recited functionality except that Rubin’s medical records are
not explicitly “patient” medical records. See Ans. 3 (citing Rubin at 724,
725, 727); see also id. at 10 (citing Rubin at 726); Rubin at 728. We also
agree with the Examiner that Maimon explicitly discloses “patient” medical
records. See Ans. 3^4 (citing Maimon || 45, 50-62, 104, 139, 152—66, 169,
184—89).
More specifically, as found by the Examiner, Rubin’s PICASSO
automatically evaluates and critiques the procedural and medical aspects of a
clinical trial protocol design by using medical knowledge, clinical trial
protocol knowledge, and formal constraints that describe the sorts of errors
that are desired to be found in a protocol. See Ans. 3 (citing Rubin at 724,
725, 727); see id. at 10 (finding that Rubin discloses constraints including:
“(1) Do not prescribe contraindicated drugs, (2) Include all required
4
Appeal 2017-002576
Application 13/992,845
monitoring actions for each of the drug treatments, and (3) Do not prescribe
interacting drugs.”); Rubin at 726. By applying these formal constraints,
Rubin’s PICASSO detects constraint violations and notifies the user of any
corresponding inconsistencies or errors in the protocol, for example (1) that
the drug treatments listed in the protocol include contraindicated or
interacting drugs or (2) that all required monitoring actions for a certain drug
treatment were not listed in the protocol. See Ans. 10; Rubin at 726; see
also Rubin at 724 (“We also developed a set of constraints, expressed in a
formal language, that describe appropriate practices for authoring clinical
trials. If a clinical trial designed with PICASSO violates any of these
constraints, PICASSO generates a message to the user and a list of
inconsistencies for each violated constraint.”), 727 (“We undertook this
study to develop a tool that uncovers semantic errors in clinical trial
protocols by evaluating their medical and procedural contents.”). Further,
PICASSO’s detection of errors and inconsistencies is consistent with
Appellant’s disclosure of an “irregularity,” which similarly “comprises a
violation of at least one of the constraints” and can reflect an error,
inconsistency, or incompletion in a medical record (see Spec. 1:10-17, 3:3—
8, 25—29). Accordingly, we agree with the Examiner that PICASSO’s
ability to detect constraint violations in a protocol and medical-knowledge
base and notify a user of corresponding inconsistencies or errors in the
protocol teaches or suggests “an analysis engine that analyzes the . . .record
expressions and . . . relations based on the knowledge-base expressions and .
. . relations to detect an irregularity in the .. . record.” We also agree with
the Examiner that Maimon explicitly discloses storing and analyzing
“patient” medical records. See Ans. 3^4 (citing Maimon || 45, 50-62, 104,
5
Appeal 2017-002576
Application 13/992,845
139, 152—66, 169, 184—89); see also Maimon Figs. 2A—D, showing medical
record tables for particular patients, including Patient ID, First Name, Last
Name, Birth Date, Height, Weight, Diagnoses, Medications, and
Treatments).
Accordingly, contrary to Appellant’s arguments, we agree with the
Examiner that:
it would have been obvious to one of ordinary skill in the art at
the time of the invention to modify the teachings of Rubin by
applying the constraint violation analysis of Rubin to the
extracted patient relationships from free text documents included
in patient medical records as taught by Maimon for the benefit of
combining these known prior art elements with the expectation
of yielding predictable results.
Ans. 4 (emphasis omitted). Combining the cited disclosures of Rubin and
Maimon to arrive at the disputed “analysis engine” element would have been
a straightforward combination of well-known elements that a person of
ordinary skill in the art could have combined as an exercise of routine skill
with predictable results. See Ans. 4; KSR Int 7 Co. v. Teleflex Inc., 550 U.S.
398, 417 (2007) (“[W]hen a patent ‘simply arranges old elements with each
performing the same function it had been known to perform’ and yields no
more than one would expect from such an arrangement, the combination is
obvious.”). Evidencing the predictability of this combination is the
Examiner’s finding that Rubin’s PICASSO is similar to another expert
system, HyperCritic, which advises in the management of hypertensive
patients. See Ans. 3 (citing Rubin at 727), 12. In addition, Rubin suggests
that its software is compatible with “patient” medical records by disclosing
the development of tools using Protege software (for which PICASSO is a
6
Appeal 2017-002576
Application 13/992,845
plug-in) that screen patients, match patients to clinical trials, and monitor
patients enrolled in clinical trials. See Rubin at 728.
For the reasons stated above, Appellant has not persuaded us
the Examiner erred in rejecting claim 1. We adopt as our own the
Examiner’s findings, conclusions, and reasoning consistent with the
analysis above. See Final Act. 4—8; Ans. 2—5, 9-13. We sustain the
Examiner’s rejection of claim 1, as well as the rejections of claims 2,
3, 5, 6, 8, 10-14, 16—19, and 21, which were not argued separately
with particularity beyond the arguments advanced for claim 1. See
App. Br. 6—9; Reply Br. 2—6.
Claim 7
As an initial matter, Appellant refers to the arguments advanced
against the rejection of independent claim 1 as evidence that the Examiner
also erred in rejecting dependent claim 7. See Reply Br. 6. We find these
arguments unpersuasive for the reasons discussed above with respect to
claim 1. Appellant contends the Examiner further erred because the
combination of Rubin and Maimon does not teach or suggest “wherein the
analysis engine determines a severity level of the irregularity,” as recited in
claim 7. See App. Br. 9-10. More specifically, Appellant argues “[t]he final
Office action makes no reference to a severity level of the irregularity”
(App. Br. 10). We find Appellant’s argument unpersuasive because the
argument mischaracterizes the Examiner’s rejection. Contrary to
Appellant’s argument, the Examiner found that Ploesser teaches or suggests
determining “a severity level of the irregularity” by determining “constraint
violation severity levels.” See Ans. 8 (citing Ploesser || 24—25, Table 1).
7
Appeal 2017-002576
Application 13/992,845
Moreover, Appellant does not specifically address or rebut this finding of
the Examiner in the briefings (see App. Br. 9—10; Reply Br. 6).
Accordingly, we sustain the Examiner’s rejection of claim 7.
DECISION
We affirm the decision of the Examiner to reject claims 1—3, 5—8, 10—
14, 16-19, and 21.
No time period for taking any subsequent action in connection with this
appeal may be extended under 37 C.F.R. § 1.136(a)(1). See 37 C.F.R. §§
41.50(f), 41.52(b).
AFFIRMED
8