Ex Parte Koll et al

Patent Trial and Appeal Board

Feb 28, 2013

11766780 (P.T.A.B. Feb. 28, 2013)

UNITED STATES PATENT AND TRADEMARK OFFICE
________________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
________________

Ex parte DETLEF KOLL and MICHAEL FINKE
________________

Appeal 2010-008396
Application 11/766,780
Technology Center 2600
________________

Before ALLEN R. MacDONALD, JASON V. MORGAN, and
JOHN G. NEW, Administrative Patent Judges.

NEW Administrative Patent Judge.

DECISION ON APPEAL

Appeal 2011-003316
Application 10/665,394

2
SUMMARY
Appellants file this appeal under 35 U.S.C. § 134(a) from the
Examiner’s Final Rejection of claims 1-5, 9-19, 23-29, and 34-47 as
unpatentable under 35 U.S.C. § 103(a) as being obvious over the
combination of Heinze et al. (US 6,915,254 B1, July 5, 2003) (“Heinze”)
and Iliff (US 2008/0059232 Al, March 6, 2008) (“Iliff”).
1

We have jurisdiction under 35 U.S.C. § 6(b).
We affirm.

STATEMENT OF THE CASE
Appellants’ invention is directed to a computer-implemented method
wherein speech is transcribed to produce a transcript; at least some of the
text in the transcript is encoded as data. These codings may be verified for
accuracy and corrected if inaccurate and the resulting transcript is provided
to a decision support system to perform functions such as checking for drug-
drug, drug-allergy, and drug-procedure interactions, and checking against
clinical performance measures (such as recommended treatments). Alerts
and other information output by the decision support system are associated
with the transcript. The transcript and associated decision support output are
provided to a physician to assist the physician in reviewing the transcript and
in taking an appropriate action in response to the transcript. Abstract.

1
Claims 6-8, 20-22, and 30-33 were canceled prior to the instant appeal.
App. Br. 46, 50, 52.
Appeal 2011-003316
Application 10/665,394

3
GROUPING OF CLAIMS

Appellants argue that the Examiner rejected claims 1-5, 9-15, 18, 19,
23, 24, 27-29, and 34-47 for substantially the same reasons, and we therefore
select claim 1 as representative. App. Br. 29. Claim 1 recites:
Claim 1. A computer-implemented method comprising:

(A) applying an automatic speech recognizer to a spoken
audio stream to produce a first document including first
codings associated with text in the first document;

(B) providing the first document to an automatic decision
support system;

(C) receiving, from the automatic decision support system,
decision support output derived from the first document;

(D) verifying accuracy of the first document to produce a
verified document; and

(E) transmitting to a recipient the verified document and the
decision support output.

App. Br. 45.
Appellants argue that the Examiner rejected claims 16 and 25 for
substantially the same reasons, and we therefore select claim 16 as
representative. App. Br. 29. Claim 16 recites:
Claim 16. The method of claim 15, wherein (B) comprises
determining whether the first document indicates at least one of
a drug-drug, drug-allergy, and drug-procedure interaction.

App. Br. 49.
Appeal 2011-003316
Application 10/665,394

4
Appellants argue that the Examiner rejected claims 17 and 26 for
substantially the same reasons, and we therefore select claim 17 as
representative. App. Br. 30. Claim 17 recites:
Claim 17. The method of claim 15, wherein (B) comprises
determining whether the first document indicates satisfaction of
a clinical performance measure.

App. Br. 49.
ISSUES AND ANALYSES
Claim 1
Issue 1
Appellants argue that the Examiner erred in finding that the
combination of Heinze and Iliff teaches or suggests the limitation of claim 1
reciting “providing the first document to an automatic decision support
system.” App. Br. 34. We therefore address the issue of whether the
Examiner so erred.

Analysis
Appellants argue that, contra the Examiner, Iliff teaches that the
“computer supports access to statistics, databases, decision-making,
scheduling,” but does not disclose that a document is provided to an
automatic decision support system. App. Br. 35 (quoting Iliff, ¶ [0337]).
According to Appellants, Iliff’s disclosure of “decision-making” does not
disclose a method which is used to support decision making by physicians or
others, i.e., decision support. App. Br. 35.
Appellants argue further that Heinze does not cure this deficiency,
allegedly teaching only that a flagged note/file/document and codes are sent
to a recipient to improve system reliability. App. Br. 36 (citing Heinze, col.
Appeal 2011-003316
Application 10/665,394

5
5. ll. 5-38). Appellants contend that Heinze does not teach or suggest that
the flagged note may be sent to an automatic decision support system,
whether implemented in software or otherwise, but teaches only that the note
is displayed to a human. App. Br. 36.
The Examiner responds that Iliff teaches or suggests an automated
disease management system to diagnose and treat user symptoms which
operates by receiving user speech and transcribing this speech to text for
further processing by the system. Ans. 8-9 (citing Iliff, Abstract). The
Examiner finds that voice recognition, which generates resultant text, is by
definition a document. Ans. 9 (citing Iliff, Fig. 1 (elements 114, 124); ¶
[0080]). The Examiner finds that symptoms in the document are then
encoded using a PQRST (pain code) array encoding scheme, and is then
forwarded to a diagnostic or disease management system. Ans. 9 (citing
Iliff, ¶¶ [0129]; [0231]-[0245]; [0337]; [0109]-[0112]; [0130]). The
Examiner finds that, in the diagnostic system, the PQRST array is used for
determining and looking up a corresponding disease for the encoded
document, whereas in the disease management system, a health assessment
task evaluates the coded document and determines the progress of treatment
and what the next action the system should take, such as adjusting therapy or
giving medical advice Ans. 9 (citing Iliff, Fig. 22b; ¶¶ [0253]; [0119];
[0130]-[0133]). The Examiner thus finds that both the diagnostic and
disease management systems make a health decision to support the user
based upon the encoded document and that, therefore, a document is
provided to an “automatic decision support system.” App. Br. 9.
We agree with the Examiner’s position and adopt it as our own.
Appellants’ Specification refers numerous times to a “document” as the
Appeal 2011-003316
Application 10/665,394

6
electronic output from a voice recognition device and we find that Iliff
teaches or suggests a document that is produced via a voice recognition
device and encoded via a PQRST array encoding scheme which corresponds
to such a document. Ans. 9; Iliff, ¶ [0129] Spec., 4 (“[O]ne embodiment of
the present invention is a computer-implemented method comprising: (A)
applying an automatic speech recognizer to a spoken audio
stream to produce a first document including first codings associated with
text in the first document”). Moreover, we agree with the Examiner’s
findings that the diagnostic and disease management systems taught by Iliff
correspond to the limitation of claim 1 reciting an “automatic decision
support system.” Ans. 9. We therefore conclude that the Examiner did not
err in finding that the combination of Heinze and Iliff teaches or suggests the
limitation of claim 1 reciting “providing the first document to an automatic
decision support system.”

Issue 2
Appellants argue that the Examiner erred in finding that the
combination of Heinze and Iliff teaches or suggests the limitation of claim 1
reciting “transmitting to a recipient the verified document and the decision
support output.” App. Br. 36-37. We therefore address the issue of whether
the Examiner so erred.

Analysis
Appellants argue that even if the “output record” taught by Heinze
corresponds to the “verified document” recited in claim 1, Heinze does not
Appeal 2011-003316
Application 10/665,394

7
teach or suggest transmitting both the output record and decision support
output (i.e., the output of the automatic decision support system) to a
recipient. App. Br. 37 (citing Heinze, col. 5, ll. 33-39). According to
Appellants, Heinze teaches or suggests sending to a recipient at most a note,
but not the other recited claim element of the decision support output. App.
Br. 37-38.
The Examiner responds that Iliff teaches or suggests that, during
interaction with the system, the user is given feedback such as a diagnosis
and medical advice (decision support output). Ans. 9 (citing Iliff, ¶¶ [0119],
[0253]). The Examiner finds further that, after the user has chosen to end
the session the user is presented with a summary of all the advice the system
has given the user, and that his summary is transmitted to the patient or
doctor through facsimile or e-mail. Ans. 9 (citing Iliff, ¶ [0118]).
We are persuaded by the Examiner’s reasoning and adopt it as our
own. Iliff teaches or suggests that:
[b]efore the system 100 ends the consultation with the patient, it
presents a summary of all the advice it has given. In a
telephonic session, the patient is asked to write down and repeat
back the key points. The system 100 then gives the patient the
option of receiving a summary of the consultation session and
specific recommendations. The system 100 then gives the
patient the option of receiving a summary of the consultation
session and specific recommendations provided by the system
via facsimile, electronic mail (E-mail) or a mail service, such as
first-class mail.

Ans. 9; Iliff, ¶ [0118]. The writing and read back requirements for the
recipient correspond to the limitations requirement of a verified message.
Id. Moreover, the consultation with the present incorporates information
from the diagnostic and disease management systems (i.e., the automated
Appeal 2011-003316
Application 10/665,394

8
decision support system) as discussed supra. We therefore conclude that the
Examiner did not err in finding that the combination of Heinze and Iliff
teaches or suggests the limitation of claim 1 reciting “transmitting to a
recipient the verified document and the decision support output.”

Claim 16
Issue
Appellant argues that the Examiner erred in finding that the
combination of Heinze and Iliff teaches the limitation of claim 16 reciting
“determining whether the first document indicates at least one of a drug-
drug, drug-allergy, and drug procedure interaction.” App. Br. 39-40. We
therefore address the issue of whether the Examiner so erred.

Analysis
Appellants argue that Iliff teaches using a Disease Management
Module (DMM) to “gradually titrate the dose of a medication until the
benefit/side effect ratio is maximized.” App. Br. 40. Appellants contend that
Iliff thereby discloses applying medications to a patient, observing the
effects of the medication on the patient, and modifying the dosage in
response to those effects. Id. Appellants argue that Iliff does not disclose
determining whether a document indicates an interaction, such as a drug-
drug, drug-allergy, or drug-procedure interaction, as expressly recited by the
disputed limitation. App. Br. 40-41.
Furthermore, Appellants maintain that the drug database taught by
Heinze might, for example, merely encode names of drugs; such information
would not indicate drug-drug, drug-allergy, or drug-procedure interactions.
Appeal 2011-003316
Application 10/665,394

9
Ans. 41. Appellants argue further that, regardless of the content of Heinze's
drug database, Heinze does not teach that such a database may be used to
perform the express action recited by claim 16, viz., determining whether a
document indicates at least one of a drug-drug, drug-allergy, and drug-
procedure interaction. Id.
The Examiner responds that Heinze teaches or suggests a system for
assigning medical codes to documents. Ans. 10 (citing Heinze, Abstract).
The Examiner finds that the determination of whether a phrase should be
assigned a code is performed by matching the parsed items of a document
against different databases of knowledge-based vectors including drugs.
Ans. 10-11 (citing Heinze, col. 4, ll. 43-55; col. 17, ll. 18-38). The
Examiner finds that the vectors represent diagnoses and procedures in “is-a,”
“synonymy” and “part/whole” relationships. Ans. 11 (citing Heinze, col. 4,
ll. 43-50). Therefore, finds the Examiner, drug vectors represent
relationships of drugs with other medical terms such as other drugs (hence a
drug-drug interaction). Ans. 11.
We are persuaded by the Examiner’s reasoning. Heinze teaches that:
The complexity of medical decision making is determined
from: the actual and possible diagnoses considered by the
physician along with the possible management options; the
amount and complexity of medical records, diagnostic tests,
and/or other information that must be obtained, reviewed, and
analyzed; the risk of significant complications, morbidity,
and/or mortality, as well as co-morbidities, associated with the
patient’s presenting problem(s), the diagnostic procedure(s)
and/or the possible management options. Vector databases are
defined to cover the second area of review and consultation.

Heinze, col. 17, ll. 19-29; Ans. 11. We find that “the amount and
complexity of medical records, diagnostic tests, and/or other information
Appeal 2011-003316
Application 10/665,394

10
that must be reviewed, and analyzed” would teach or suggest, to an artisan
of ordinary skill in the contemporaneous art, the determination of drug-drug,
drug-allergy, and drug procedure interaction, as recited in the disputed
limitation of claim 16. We therefore conclude that the Examiner did not err
in finding that the combination of Iliff teaches or suggests the limitations of
claim 16.

Claim 17
Issue
Appellants argue that the Examiner erred in finding that the
combination of Heinze and Iliff teaches or suggests the limitation of claim
17 reciting “determining whether the first document indicates satisfaction of
a clinical performance measure.” App. Br. 42. We therefore address
whether the Examiner so erred.

Analysis
Appellants argue that, rather than teaching or suggesting the disputed
limitation, Iliff describes a situation in which a headache specialist has made
a diagnosis after a full and complete examination, thereby indicating that the
diagnosis is highly reliable or, if the reliability is too low, that the patient
will be scheduled for re-evaluation. App. Br. 42-43 (citing Iliff, ¶ [0324]).
Therefore, according to Appellants, Iliff discloses determining whether the
reliability of a diagnosis is too low, but neither teaches nor suggests
determining whether a document indicates whether a clinical performance
measure has been satisfied. App. Br. 43.
Appeal 2011-003316
Application 10/665,394

11
Appellants also argue that the teaching or suggestion of Heinze that
obtaining the correct results are important (Heinze, col. 22, l. 46-54) and that
the procedure must be justified or verified (Heinze, cols. 23-24, ll. 61-34)
does not teach or suggest determining whether a document indicates whether
a clinical performance measure has been satisfied. App. Br. 43.
The Examiner responds that Iliff teaches that, in the diagnostic
system, the PQRST array is used for determining and looking up a
corresponding disease for the encoded document. Ans. 11 (citing Iliff, Fig.
22b; ¶ [0253]). The Examiner finds that the disease database indexes
diseases based upon different aspects of pain that the user may experience.
Ans. 11 (citing Iliff, Fig. 22b, element 262). Therefore, finds the Examiner,
the diagnosis module determines if the document satisfies one of the
diseases in the database accessed by pain. The Examiner finds that the
storing of a disease with common indicators of that disease (types of pain) is
a “clinical performance measure.”
We agree with the Examiner. Iliff teaches, by way of example, that
once a coded document is generated:
a suitably formatted Structured Query Language (SQL)
statement; another example is a simple array of disease names
or pointer that is accessed using the index position of each
element. Process 1170 receives control at start node 1172.
Then process 1170 passes control to step 1174, which loads a
copy of the PQRST Array to be used to select the diagnosis
from database 262 …. Next, process 1170 passes control to
terminal node 1180, which returns control to the calling
process.

Iliff, ¶ [0253], see also Fig. 22b; Ans. 11. We find that the Iliff’s teaching
and suggestion of making and recording of a diagnosis would, to a person of
Appeal 2011-003316
Application 10/665,394

12
ordinary skill in the art, correspond to the language of claim 17 reciting
“satisfaction of a clinical performance measure.” We consequently conclude
that the Examiner did not err in finding that the combination of Heinze and
Iliff teaches or suggests the limitation of claim 17.

DECISION
The Examiner’s rejection of claims 1-5, 9-19, 23-29, and 34-47 as
unpatentable under 35 U.S.C. §103(a) is affirmed.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a).

AFFIRMED

ELD