Ex Parte Farooq et al

Patent Trial and Appeal Board

Sep 19, 2018

13153526 (P.T.A.B. Sep. 19, 2018)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
13/153,526 06/06/2011
46169 7590 09/21/2018
SHOOK, HARDY & BACON L.L.P.
(Cerner Corporation)
Intellectual Property Department
2555 GRAND BOULEVARD
KANSAS CITY, MO 64108-2613
FIRST NAMED INVENTOR
Faisal Farooq
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.
CRNI.224510 9250
EXAMINER
MOLL, NITHYA JANAKIRAMAN
ART UNIT PAPER NUMBER
2128
NOTIFICATION DATE DELIVERY MODE
09/21/2018 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):
IPDOCKET@SHB.COM
IPRCDKT@SHB.COM
BPARKERSON@SHB.COM
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte FAISAL F AROOQ, ROMER E. ROSALES, SHIPENG YU,
BALAJI KRISHNAPURAM, and BHARAT R. RAO
Appeal 2018-002141
Application 13/153,526 1
Technology Center 2100
Before JOHN A. JEFFERY, BRUCE R. WINSOR, and
JUSTIN BUSCH, Administrative Patent Judges.
WINSOR, Administrative Patent Judge.
DECISION ON APPEAL
Pursuant to 35 U.S.C. § 134(a), Appellants appeal from the
Examiner's final decision to reject claims 15, 16, 18, 19, and 26-35. We
have jurisdiction under 35 U.S.C. § 6(b). Claims 1-14, 17, and 20-25 have
been cancelled.
We AFFIRM.
1 Appellants identify Cemer Innovation, Inc. as the real party in interest.
Br. 3.
Appeal 2018-002141
Application 13/153,526
STATEMENT OF THE CASE
Appellants' disclosed invention "[relates] to predicting risk of adverse
events in healthcare patients and/or providing valuable information to
potentially prevent adverse events." Spec. ,r 2. Claim 15, which is
illustrative, reads as follows:
15. A system for predicting or preventing adverse events
associated with a first medical entity, the system comprising:
at least one memory operable to store patient data for a
plurality of patients previously treated at the first medical entity,
where the plurality of patients have had an adverse event during
or after a stay at the first medical entity; and
a first processor configured to:
mine the patient data including mining unstructured
information comprising collections of information without
defined fields for an input of text, the mining providing
values for variables based on the patients previously
treated at the first medical entity, the values inferred from
different possible values in the data and probabilities
assigned to the possible values;
identify, by training a first medical entity-specific
predictor of adverse events using the values of the
variables as training data, the variables contributing to the
adverse events for the patients of the first medical entity,
the identification based on use of the mined patient data
for the plurality of the patients of the first medical entity
as the training data of the predictor;
incorporate the variables into a first predictor for
predicting one or more adverse events of a first type for a
future patient of the first medical entity; and
incorporate the variables into a second predictor for
predicting one or more adverse events of a second type for
the future patient of the first medical entity.
2
Appeal 2018-002141
Application 13/153,526
Claims 15, 16, 18, 26, and 31 stand rejected under 35 U.S.C. § I03(a)2
as being unpatentable over Kehr et al. (US 2003/0036683 Al; published
Feb. 20, 2003; hereinafter "Kehr") and Roberts (US 6,056,690; issued May
2, 2000). See Final Act. 3-14.
Claims 19 and 32 stand rejected under 35 U.S.C. § I03(a) as being
unpatentable over Kehr, Roberts, and Selker et al. (US 6,067,466; issued
May 23, 2000; hereinafter "Selker"). See Final Act. 14--15.
Claim 27-30 stand rejected under 35 U.S.C. § I03(a) as being
unpatentable over Kehr, Roberts, and Mebane (US 5,486,999; issued Jan.
23, 1996). See Final Act. 15-18.
Claims 33 and 34 stand rejected under 35 U.S.C. § I03(a) as being
unpatentable over Kehr, Roberts, and Walker et al. (US 6,302,844 Bl;
issued Oct. 16, 2001; hereinafter "Walker"). See Final Act. 18-24.
Claim 35 stands rejected under 35 U.S.C. § I03(a) as being
unpatentable over Kehr, Roberts, Walker, and Selker. See Final Act. 24--25.
Rather than repeat the arguments here, we refer to the Appeal Brief
(filed June 14, 2017, "Br.") for Appellants' positions; the Final Office
Action (mailed Dec. 14, 2016, "Final Act.") and Examiner's Answer (mailed
Oct. 19, 2017, "Ans.") for the reasoning, findings, and conclusions of the
Examiner; and the Specification ( filed June 6, 2011, amended June 9, 2011
"Spec."). Only those arguments actually made by Appellants have been
considered in this decision. Arguments that Appellants did not make in the
2 All rejections are under the provisions of 35 U.S.C. in effect before the
effective date of the Leahy-Smith America Invents Act of 2011 ("Pre-AIA").
Final Act. 2.
3
Appeal 2018-002141
Application 13/153,526
Brief have not been considered and are deemed to be waived. See 37 C.F.R.
§ 4I.37(c)(l)(iv) (2016).
ANALYSIS
Claims 15, 16, 18, 19 and 26-32
On this record, we see no error in the Examiner's obviousness
rejection of claim 15.
Appellants argue that Kehr does not teach "mining information from
unstructured information." Br. 11. According to Appellants,
Id.
[ d]ata is not mined in Kehr until after it is communicated to a
medical database and stored as structured data in the fields of
the medical database. Thus, Kehr only describes mining
structured data from the structured medical database. Even if
the original source of data were unstructured in Kehr, the
mining in Kehr is only from the structured medical database
and is not from the unstructured source.
In the rejection, the Examiner relies on Kehr for teaching many
elements of claim 15, including mining patient data that includes
unstructured information. Final Act. 4--5 (citing Kehr ,r,r 180,228); Ans. 4--
5.
We find Appellants' argument unpersuasive of error because it is not
commensurate with the broadest reasonable interpretation of claim 15.
Claim 15 broadly recites "mine the patient data including mining
unstructured information, comprising collections of information without
defined fields for an input of text." Br. 16 (Claims App.). Claim 15 does
not recite any limitations as to what type of source the unstructured
information is from. Therefore, we agree with the Examiner that the
4
Appeal 2018-002141
Application 13/153,526
broadest reasonable interpretation of "unstructured information" ( claim 15)
reads on (1) Kehr' s messages presented in textual, graphical, pictorial, or
voice formats; and included as raw patient data (Kehr ,r 180); and (2) Kehr's
graphic, auditory, real-time communications presented to a patient (id.
,r 228). See Ans. 4--5. Furthermore, nothing in the claim precludes
structuring originally unstructured data as a step in the process of mining the
unstructured data.
Appellants argue Kehr "does not teach separate training of
predictors/classifiers for different adverse events," (Br. 11 ), and Roberts
"does not teach or suggest incorporating variables into two separate
classifiers for predicting risk of two separate adverse events." Id. at 12.
We find Appellants' argument unpersuasive of error. The Examiner
finds Kehr' s mined patient data provides values for variables based on
patients previously treated at a first medical entity. Final Act. 4--5 (citing
Kehr ,r,r 60, 180, 228). The Examiner further finds Kehr teaches identifying,
by using the values of the variables as training data to train a first medical
entity-specific predictor of adverse events, the variables contributing to
adverse events for patients of a first medical entity. Id. at 5-6 (citing Kehr
,r,r 171, 316). Although the Examiner finds Kehr incorporates the variables
into a first predictor for predicting adverse events of a first type for a future
patient, (id. at 6 ( citing Kehr ,r,r 23 8, 316) ), the Examiner acknowledges
Kehr does not incorporate the variables into a second predictor for predicting
adverse events of a second type for the future patient. Id. at 7. The
Examiner, however, cites Roberts for teaching this feature in concluding that
the claim would have been obvious. Id. at 7-8 ( citing Roberts cols. 7-8).
Therefore, Appellants' arguments regarding Kehr's (Br. 10) and Roberts'
5
Appeal 2018-002141
Application 13/153,526
(id. at 12) alleged individual shortcomings pertaining to the recited separate
first and second predictors for predicting adverse events of different types
are unpersuasive where, as here, the rejection is not based solely on Kehr or
Roberts, but rather on the combination of Kehr and Roberts. See In re
Merck & Co., Inc., 800 F.2d 1091, 1097 (Fed. Cir. 1986). We note, for
emphasis, that it would have been obvious to one of ordinary skill in the art
to extend the incorporation of variables into a predictor to a second predictor
( or more). To do so would be no more than a duplication of elements, which
has no patentable significance where, as here, no new and unexpected result
is produced. See In re Harza, 274 F.2d 669, 671 (CCPA 1960); see also In
re Marcum, 47 F.2d 377, 378 (CCPA 1931) (citing Topliff v. Topliff, 145
U.S. 156, 163 (1892)) (A "mere duplication of parts" is not invention.).
Further, it is no more than a "combination of familiar elements according to
known methods [that] does no more than yield predictable results." KSR
Int'! Co. v. Teleflex Inc., 550 U.S. 398,416 (2007).
Appellants further argue Kehr does not teach either incorporating
variables into a first predictor for predicting one or more adverse events of a
first type, or a second predictor for predicting one or more adverse events of
a second type, for a future patient of a first medical entity. Br. 11.
According to Appellants, "Kehr mines for statistical analysis across a
population and does not provide for pieces of information for a given value
of a given variable for a patient. Kehr is merely directed to populations, not
to combining multiple pieces of information into a value of a variable for a
patient." Id. (emphasis added).
We find Appellants' argument unpersuasive of error because it is not
commensurate with the broadest reasonable interpretation of claim 15.
6
Appeal 2018-002141
Application 13/153,526
Claim 15 recites "incorporate the variables into a first predictor for
predicting one or more adverse events of a first type for a future patient of
the first medical entity." Id. at 16 (Claims App.). Claim 15 does not recite
that the first predictor is a value of a variable for a patient.
Kehr teaches analyzing dose-specific effects of medications upon a
particular patient or population of patients by mining data from a medical
database. Kehr ,r 228. Kehr teaches that the knowledge gained from the
data analysis and mining is used to adjust dosing recommendations of
medications to eliminate adverse drug events. Id. ,r 239. Kehr's medical
monitoring device monitors for adverse drug events an individual patient
may experience in real-time in response to a medication. Id. ,r,r 59, 228,
305. Thus, contrary to Appellants' arguments, Kehr, then, by monitoring an
individual patient for an adverse drug event to medications the individual
patient may experience based on knowledge gained from the data analysis
and mining, at least suggests incorporating the medications ( the claimed
"variables") that contribute to the adverse drug events into a first predictor
for predicting the known adverse drug events (the claimed "one or more
adverse events of a first type"). See Br. 11.
The arguments presented by Appellants do not persuade us of error in
the rejection under section 103(a) of independent claim 15. See Ex parte
Frye, 94 USPQ2d 1072, 1075 (BPAI 2010) (precedential). Accordingly, we
sustain the rejections of: (1) independent claim 15; (2) independent claim
26, which is argued relying on the arguments made for claim 15 (see Br. 12);
and (3) claims 16, 18, 19, and 27-32, which variously depend from claims
15 and 26, and were not separately argued with particularity (see id. at 10-
12, 15).
7
Appeal 2018-002141
Application 13/153,526
Claims 33-35
We sustain the Examiner's obviousness rejection of independent
claim 33 as being unpatentable over Kehr, Roberts, and Walker. Final
Act. 18-23. To the extent Appellants' arguments regarding claim 15 apply
to claim 33, we find them unpersuasive of Examiner error for the same
reasons as for claim 15. Claim 33 recites, in pertinent part,
[a] incorporating the variables into a predictor that predicts a
probability of adverse events for a future patient of the first
medical entity, the predictor resulting from the machine learning,
[b] wherein the probability of at least one of the adverse events
predicted by the predictor includes a risk of a patient fall.
Br. 19-20 (Claims App.)
The Examiner finds Kehr teaches step [a]. Final Act. 21 ( citing Kehr
,r 238). Regarding step [b ], the Examiner finds "Kehr and Roberts do not
teach: a patient fall. Walker does teach a patient fall." Id. at 22-23 ( citing
Walker col. 5, 11. 3-25). Thus, Appellants' argument that Kehr and Roberts
do not mention the patient fall of step [b ], (Br. 13) is unavailing because this
argument is not germane to the teachings for which Kehr and Roberts were
cited.
Nor do we find availing Appellants' argument that Walker does not
teach predicting a probability of a risk of a fall because Roberts' fall has
already occurred, or the predicted probability calculated by a programmed
processor, (id. at 13-14 (citing Walker col. 5, 11. 12-16)), because this
argument is not germane to the limited purpose for which Walker was cited,
namely that a patient fall is a known adverse event.
8
Appeal 2018-002141
Application 13/153,526
Nor do we find availing Appellants' argument that Walker's teaching
of a patient fall cannot be used in combination with Kehr and Roberts to
teach steps [a] and [b]. Id. at 13. As discussed above, Kehr at least suggests
incorporating medications (the claimed "variables") into a first predictor for
predicting adverse drug events (the claimed "adverse events of a first type").
The Examiner finds, and Appellants admit, Walker teaches a patient fall.
Final Act. 23; Br. 13. Thus, Appellants do not persuasively rebut the
Examiner's finding that including in Kehr's probability, or risk, of adverse
events predicted by the predictor a patient fall, such as that taught by
Roberts, would have been at least an obvious variation.
Accordingly, we sustain the rejections of: (1) independent claim 33;
and (2) claims 34 and 35, which depend from claim 33, and were not
separately argued with particularity (see Br. 14, 15).
CONCLUSION
Appellants have not demonstrated that the Examiner erred in rejecting
claims 15, 16, 18, 19, and 26-35 under section 103.
DECISION3
The Examiner's decision to reject claims 15, 16, 18, 19, and 26-35 is
affirmed.
3 In the event of further prosecution, the Examiner may wish to consider
whether claims 15, 16, 18, 19, 26-35 are directed to ineligible subject matter
under 35 U.S.C. § 101. In particular, the Examiner may wish to consider
whether the claims meet the Supreme Court's two-step test as articulated in
Alice Corp. Pty. Ltd. v. CLS Bank International, 134 S.Ct. 2347 (2014).
Subsequently, the Federal Circuit in Electric Power Group, LLC v. Alstom
9
Appeal 2018-002141
Application 13/153,526
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(l). See 37 C.F.R.
§§ 41.50(±), 4I.52(b).
AFFIRMED
S.A., 830 F.3d 1350 (Fed. Cir. 2016) held that merely collecting and
analyzing information is within the realm of abstract ideas. See Elec. Power,
830 F.3d at 1353-54. We note that, e.g., independent claim 15 similarly
recites collecting and analyzing information. Although the Board is
authorized under 37 C.F.R. § 4I.50(b) to reject claims, no inference should
be drawn when the Board elects not to do so. See MPEP § 1213.02.
10