`
`UNITED STATES PATENT AND TRADEMARK OFFICE
`
`
`
`
`
`
`
`
`
`
`BEFORE THE PATENT TRIAL AND APPEAL BOARD
`
`
`
`
`
`
`
`
`
`
`
`
`
`
`APPLE INC.,
`Petitioner,
`
`v.
`
`ALIVECOR, INC.,
`Patent Owner.
`
`
`
`
`
`
`
`
`
`
`
`
`IPR2021-00971
`Patent 10,595,731
`
`
`
`
`
`
`
`
`
`PETITIONER’S REPLY TO
`PATENT OWNER’S RESPONSE
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`
`
`LIST OF EXHIBITS
`
`APPLE-1001
`
`U.S. Pat. No. 10,595,731 to Gopalakrishnan (“the ’731 patent”)
`
`APPLE-1002
`
`Excerpts from the Prosecution History of the ’731 patent (“the
`Prosecution History”)
`
`APPLE-1003
`
`Declaration of Dr. Bernard A. Chaitman
`
`APPLE-1004
`
` PCT Patent Publication WO2012/140559 (“Shmueli”)
`
`APPLE-1005
`
` U.S. Patent Publication 2014/0275840 (“Osorio”)
`
`APPLE-1006
`
` Li Q, Clifford GD, “Signal quality and data fusion for false
`alarm reduction in the intensive care unit,” J Electrocardiol.
`2012 Nov-Dec; 45(6):596-603 (“Li-2012”)
`
`APPLE-1007
`
` U.S. Patent Publication 2008/0004904 (“Tran”)
`
`APPLE-1008
`
` U.S. Patent Publication 2014/0107493 (“Yuen”)
`
`APPLE-1009
`
` U.S. Patent Publication 2015/0119725 (“Martin”)
`
`APPLE-1010
`
` U.S. Provisional Application No. 61/794,540 (“Osorio
`Provisional”)
`
`APPLE-1011
`
` Lee J, Reyes BA, McManus DD, Mathias O, Chon KH. Atrial
`fibrillation detection using a smart phone. International Journal
`of Bioelectromagnetism, Vol. 15, No. 1, pp. 26 - 29, 2013
`(“Lee 2013”)
`
`APPLE-1012
`
` Tsipouras MG, Fotiadis DI. Automatic arrhythmia detection
`based on time and time-frequency analysis of heart rate
`variability. Comput Methods Programs Biomed. 2004 May;
`74(2):95-108 (“Tsipouras 2004”)
`
`APPLE-1013
`
` Lu S, Zhao H, Ju K, Shin K, Lee M, Shelley K, Chon KH. Can
`
`i
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`photoplethysmography variability serve as an alternative
`approach to obtain heart rate variability information? J Clin
`Monit Comput. 2008 Feb; 22(1):23-9 (“Lu 2008”)
`
`APPLE-1014
`
` Selvaraj N, Jaryal A, Santhosh J, Deepak KK, Anand S.
`Assessment of heart rate variability derived from finger-tip
`photoplethysmography as compared to electrocardiography. J
`Med Eng Technol. 2008 Nov-Dec; 32(6):479-84 (“Selvaraj
`2008”)
`
`APPLE-1015
`
` Lu G, Yang F, Taylor JA, Stein JF. A comparison of
`photoplethysmography and ECG recording to analyse heart rate
`variability in healthy subjects. J Med Eng Technol. 2009;
`33(8):634-41 (“Lu 2009”)
`
`APPLE-1016
`
` Suzuki T, Kameyama K, Tamura T. Development of the
`irregular pulse detection method in daily life using wearable
`photoplethysmographic sensor. Annu Int Conf IEEE Eng Med
`Biol Soc. 2009; 2009:6080-3 (“Suzuki 2009”)
`
`APPLE-1017
`
` Reed MJ, Robertson CE, Addison PS. Heart rate variability
`measurements and the prediction of ventricular arrhythmias.
`QJM. 2005 Feb; 98(2):87-95 (“Reed 2005”)
`
`APPLE-1018
`
` Schäfer A, Vagedes J. How accurate is pulse rate variability as
`an estimate of heart rate variability? A review on studies
`comparing photoplethysmographic technology with an
`electrocardiogram. Int J Cardiol. 2013 Jun 5; 166(1):15-29
`(“Schafer 2013”)
`
`APPLE-1019
`
` K. Douglas Wilkinson, “The Clinical Use of the
`Sphygmomanometer,” The British Medical Journal, 1189-90
`(Dec. 27, 1924) (“Wilkinson”)
`
`APPLE-1020
`
` U.S. Pat. No. 6,095,984 (“Amano”)
`
`APPLE-1021
`
` B.K. Bootsma et. al, “Analysis of R-R intervals in patients with
`atrial fibrillation at rest and during exercise.” Circulation 1970;
`41:783-794
`
`ii
`
`
`
`APPLE-1022
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
` Frits L. Meijler and Fred H. M. Wittkampf, “Role of the
`Atrioventricular Node in Atrial Fibrillation” Atrial Fibrillation:
`Mechanisms and Management, 2nd ed. 1997 (“Meijler”)
`
`APPLE-1023
`
` Heart Diseases _ Definition of Heart Diseases by Merriam-
`Webster
`
`APPLE-1024
`
` Acharya UR, Joseph KP, Kannathal N, Lim CM, Suri JS. Heart
`rate variability: a review. Med Biol Eng Comput. 2006 Dec;
`44(12):1031-51 (“Acharya 2006”)
`
`APPLE-1025
`
` Saime Akdemir Akar, Sadık Kara, Fatma Latifoğlu, Vedat
`Bilgiç. Spectral analysis of photoplethysmographic signals: The
`importance of preprocessing. Biomedical Signal Processing and
`Control, 2013; 8(1):16-22 (Akar 2013)
`
`APPLE-1026
`
` U.S. Provisional Application No. 61/915,113
`
`APPLE-1027
`
` U.S. Provisional Application No. 61/953,616
`
`APPLE-1028
`
` U.S. Provisional Application No. 61/969,019
`
`APPLE-1029
`
` U.S. Provisional Application No. 61/970,551
`
`APPLE-1030
`
` U.S. Provisional Application No. 62/014516
`
`APPLE-1031
`
` U.S. Patent Publication No. 2012/0203491 (“Sun”)
`
`APPLE-1032
`
` U.S. Patent No. 9,808,206 (“Zhao”)
`
`APPLE-1033
`
` Kleiger RE, Stein PK, Bigger JT Jr. Heart rate variability:
`measurement and clinical utility. Ann Noninvasive
`Electrocardiol. 2005 Jan; 10(1):88-101 (“Kleiger 2005”)
`
`APPLE-1034
`
` Chen Z, Brown EN, Barbieri R. Characterizing nonlinear
`heartbeat dynamics within a point process framework. IEEE
`Trans Biomed Eng. 2010 Jun; 57(6):1335-47 (“Chen 2010”)
`
`iii
`
`
`
`APPLE-1035
`
`APPLE-1036
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
` Karvonen, J., Vuorimaa, T. Heart Rate and Exercise Intensity
`During Sports Activities. Sports Medicine 5, 303–311 (1988)
`(“Karvonen 1988”)
`
` Yu C, Liu Z, McKenna T, Reisner AT, Reifman J. A method
`for automatic identification of reliable heart rates calculated
`from ECG and PPG waveforms. J Am Med Inform Assoc. 2006
`May-Jun; 13(3):309-20 (“Yu 2006”)
`
`APPLE-1037
`
` AliveCor v Apple ITC Complaint Exhibit 11 (499 Infringement
`Chart)
`
`APPLE-1038
`
` Tavassoli, M, Ebadzadeh, MM, Malek H. (2012). Classification
`of cardiac arrhythmia with respect to ECG and HRV signal by
`genetic programming. Canadian Journal on Artificial
`Intelligence, Machine Learning and Pattern Recognition. 3. 1-
`13 (“TavassoLi-2012”)
`
`APPLE-1039
`
` Asl BM, Setarehdan SK, Mohebbi M. Support vector machine-
`based arrhythmia classification using reduced features of heart
`rate variability signal. Artif Intell Med. 2008 Sep; 44(1):51-64
`(“Asl 2008”)
`
`APPLE-1040
`
` Yaghouby F., Ayatollahi A. (2009) An Arrhythmia
`Classification Method Based on Selected Features of Heart
`Rate Variability Signal and Support Vector Machine-Based
`Classifier. In: Dössel O., Schlegel W.C. (eds) World Congress
`on Medical Physics and Biomedical Engineering, September 7 -
`12, 2009, Munich, Germany. IFMBE Proceedings, vol 25/4.
`Springer, Berlin, Heidelberg (“Yaghouby 2009”)
`
`APPLE-1041
`
` Dallali, A, Kachouri, A, Samet, M. (2011). Integration of HRV,
`WT and neural networks for ECG arrhythmias classification.
`ARPN Journal of Engineering and Applied Sciences. VOL. 6.
`74-82 (“Dallali 2011”)
`
`APPLE-1042
`
` Sajda P. Machine learning for detection and diagnosis of
`disease. Annu Rev Biomed Eng. 2006; 8:537-65 (“Sajda 2006”)
`
`iv
`
`
`
`APPLE-1043
`
`APPLE-1044
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
` Aaron Smith. Smartphone Ownership – 2013 Update. Pew
`Research Center. June 5, 2013 (“Smith 2013”)
`
` C. Narayanaswami and M. T. Raghunath, “Application design
`for a smart watch with a high resolution display,” Digest of
`Papers. Fourth International Symposium on Wearable
`Computers, 2000, pp. 7-14 (“Narayanaswami 2000”)
`
`APPLE-1045
`
` Thong, YK, Woolfson, M, Crowe, JA, Hayes-Gill, B, Challis,
`R. (2002). Dependence of inertial measurements of distance on
`accelerometer noise, Meas. Measurement Science and
`Technology. 13. 1163 (“Thong 2002”)
`
`APPLE-1046
`
` AliveCor’s ITC Complaint filed on April 20, 2021 in “Certain
`Wearable Electronic Devices With ECG Capability and
`Components Thereof” ITC-337-3545-20210420 (“ITC
`Complaint”)
`
`
`APPLE-1047
`
` Excerpts from Marcovitch, Harvey. Black’s Medical
`Dictionary. London: A. & C. Black, 2005
`
`APPLE-1048
`
` U.S. Pat. No. 7,894,888 (“Chan”)
`
`APPLE-1049
`
` Hu YH, Palreddy S, Tompkins WJ. A patient-adaptable ECG
`beat classifier using a mixture of experts approach. IEEE
`Transactions on Bio-medical Engineering. 1997 Sep;
`44(9):891-900 (“Hu-1997”)
`
`APPLE-1050
`
` Strath SJ, Swartz AM, Bassett DR Jr, et al. Evaluation of heart
`rate as a method for assessing moderate intensity physical
`activity. Medicine and Science in Sports and Exercise. 2000
`Sep; 32(9 Suppl):S465-70 (“Strath 2000”)
`
`APPLE-1051
`
`Letter from Michael Amon re Conditional Stipulation dated
`June 4, 2021
`
`APPLE-1052
`
`Declaration of Mr. Jacob Munford
`
`
`
`v
`
`
`
`APPLE-1053
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
` Order Staying Case Pending Institution of And/Or Final
`Determination in Parallel ITC Matter (AliveCor Inc. v. Apple
`Inc., 6:20-cv-01112-26 (W.D.Tex. May 6, 2021)
`
`APPLE-1054
`
` U.S. Provisional Application No. 61/895,995 (“Martin
`Provisional”)
`
`APPLE-1055
`
` AliveCor’s District Court Complaint filed on May 25, 2021 in
`AliveCor, Inc. v. Apple Inc., 3:21-cv-03958 (N.D.Cal. May 25,
`2021) (“Antitrust Complaint”)
`
`APPLE-1056
`
` Apple’s Rebuttal Markman Brief of October 13, 2021
`
`APPLE-1057
`
` Email from Jeremy Monaldo re Prior Art Narrowing dated
`November 17, 2021
`
`APPLE-1058
`
` Declaration of Michael Amon
`
`APPLE-1059
`
` Declaration of Noah Graubart
`
`APPLE-1060
`
` U.S. Pat. No. 5,176,137 to Erickson et al. (“Erickson”)
`
`APPLE-1061
`
` U.S. Pat. No. 7,598,878 to Goldreich (“Goldreich”)
`
`APPLE-1062
`
` U.S. Pat. App. Pub. No. 2005/0177051 to Almen (“Almen”)
`
`APPLE-1063
`
` U.S. Pat. App. Pub. No. 2019/0376014 to Efimov (“Efimov”)
`
`APPLE-1064
`
`
`
`International App. Pub. No. WO 2005/110238 to Goldreich
`(“Goldreich-2”)
`
`
`
`APPLE-1065
`
` Yang et al., “Hardware-Mappable Cellular Neural Networks for
`Distributed Wavefront Detection in Next-Generation Cardiac
`Implant,” Adv. Intell. Syst. 2022, 2200032 (2022)
`
`APPLE-1066
`
`
`
`“Atrial fibrillation (part 1) – When the heart loses its rhythm,”
`https://www.hirslanden.com/en/international/private-hospital-
`
`vi
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`group/news/artikel-vorhofflimmern-i.html, accessed June 2,
`2022
`
`APPLE-1067
`
`
`
`“Holter heart monitor,”
`https://medlineplus.gov/ency/imagepages/8810.htm, accessed
`June 2, 2022
`
`APPLE-1068
`
`“Holter monitor (24h),” https://www.mountsinai.org/health-
`library/tests/holter-monitor-24h, accessed June 22, 2022
`
`APPLE-1069
`
`
`
`June 3, 2022 Deposition Transcript of Dr. Igor Efimov
`
`APPLE-1070
`
` AliveCor’s ITC Post-Hearing Brief (CBI Redacted), dated
`April 15, 2022
`
`APPLE-1071
`
`
`
`January 31, 2022 ITC Deposition Transcript of Dr. Igor Efimov
`
`APPLE-1072
`
` Excerpts from Transcript of Conference in Certain Wearable
`Electronic Devices with ECG Functionality and Components
`Thereof, 337-TA-1266, dated March 31, 2022 (pages 828-1101)
`
`APPLE-1073
`
` Excerpts from Transcript of Conference in Certain Wearable
`Electronic Devices with ECG Functionality and Components
`Thereof, 337-TA-1266, dated April 1, 2022 (pages 1102-1375)
`
`APPLE-1074
`
` Li, Qiao, and Gari D. Clifford. "Dynamic time warping and
`machine learning for signal quality assessment of pulsatile
`signals." Physiological measurement 33.9 (2012): 1491 (“Li
`and Clifford”).
`
`APPLE-1075
`
` Schlesinger, Daphne E., and Collin M. Stultz. "Deep learning
`for cardiovascular risk stratification." Current Treatment
`Options in Cardiovascular Medicine 22.8 (2020): 1-14.
`
`APPLE-1076
`
` D’Agostino Sr, Ralph B., et al. "General cardiovascular risk
`profile for use in primary care: the Framingham Heart Study."
`Circulation 117.6 (2008): 743-753.
`
`vii
`
`
`
`APPLE-1077
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
` Antman, Elliott M., et al. "The TIMI risk score for unstable
`angina/non–ST elevation MI: a method for prognostication and
`therapeutic decision making." Jama 284.7 (2000): 835-842.
`
`APPLE-1078
`
` Morrow, David A., et al. "Application of the TIMI risk score
`for ST-elevation MI in the National Registry of Myocardial
`Infarction 3." Jama 286.11 (2001): 1356-1359.
`
`APPLE-1079
`
` Pocock, Stuart J., et al. "Predicting survival in heart failure: a
`risk score based on 39 372 patients from 30 studies." European
`heart journal 34.19 (2013): 1404-1413.
`
`APPLE-1080
`
` Yu, Chenggang, et al. "A method for automatic identification of
`reliable heart rates calculated from ECG and PPG waveforms."
`Journal of the American Medical Informatics Association 13.3
`(2006): 309-320.
`
`APPLE-1081
`
` December 22, 2021 Collin Stultz ITC Invalidity Report
`(Redacted)
`
`APPLE-1082
`
` February 3, 2022 Deposition Transcript of Collin Stultz (ITC)
`
`APPLE-1083
`
` RDX-0003 Stultz Demonstratives (ITC)
`
`APPLE-1084
`
` APPLE’s ITC Post-Hearing Brief (CBI Redacted), dated April
`15, 2022
`
`APPLE-1085
`
` Bansal, Nikhil, Avrim Blum, and Shuchi Chawla. "Correlation
`clustering." Machine learning 56.1 (2004): 89-113.
`
`
`
`
`
`
`
`
`
`viii
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`
`
`
`TABLE OF CONTENTS
`
`I.
`II.
`
`1.
`2.
`3.
`
`B.
`
`1.
`2.
`III.
`
`INTRODUCTION ........................................................................................... 1
`THE PRIOR ART RENDERS ARRHYTHMIA DETECTION OBVIOUS .. 3
`A.
`Record Evidence Confirms Obviousness .............................................. 3
`Testimony From Both Experts Reinforce the Petition .......................... 3
`Shmueli And The ’731 Patent Both Reinforce The Petition ................. 6
`Secondary Evidence Also Reinforces The Petition .............................. 8
`AliveCor’s Response Arguments Fail ................................................... 9
`AliveCor’s Interpretation of Shmueli Deviates From its Disclosure .... 9
`AliveCor Ignores Non-Limiting Language in Osorio ......................... 11
`SHMUELI RENDERS “CONFIRMATION” OBVIOUS ............................ 13
`A.
`Shmueli Renders Obvious “Confirming” Based on ECG Data .......... 14
`B.
`Shmueli Correlates ECG Data and SpO2/PPG Data ........................... 15
`C.
`Shmueli’s Continued SpO2/PPG Monitoring Is Limited to
`Embodiments ....................................................................................... 16
`Shmueli Is Not Limited to Remote ECG Analysis ............................. 17
`D.
`IV. A POSITA WOULD HAVE BEEN MOTIVATED TO COMBINE
`SHMUELI AND OSORIO ............................................................................ 17
`SHMUELI-OSORIO-LI 2012 RENDERS OBVIOUS MACHINE
`LEARNING ................................................................................................... 18
`A.
`Li 2012 Renders Obvious Machine Learning Detection .................... 21
`B.
`Li 2012 Suggests Applying Machine Learning to Shmueli’s
`SpO2/PPG Data .................................................................................... 23
`Shmueli’s Learning of New Detection Parameters Renders Obvious
`Machine Learning ................................................................................ 25
`VI. ALIVECOR’S “POSITA” DEFINITION IS WRONG ................................ 27
`VII. CONCLUSION .............................................................................................. 29
`
`V.
`
`C.
`
`ix
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`
`I.
`
`INTRODUCTION
`For the independent claims, AliveCor repeats the same three arguments that
`
`were raised pre-institution and that were rejected. AliveCor contends that the post-
`
`institution record warrants reconsideration. Not so. If anything, the record
`
`reinforces the obviousness arguments provisionally adopted at Institution.
`
`Testimony from AliveCor’s own expert, Igor Efimov, includes several admissions
`
`that contradict each of AliveCor’s primary arguments. The record evidence
`
`therefore confirms that the asserted prior art demonstrates unpatentability.
`
`AliveCor’s first argument is premised on a superficial distinction between
`
`Shmueli’s “irregular heart condition” and the claim term “arrhythmia.” AliveCor
`
`criticizes Shmueli for not using the claim term within its disclosure, but AliveCor’s
`
`analysis either overlooks or ignores several teachings that demonstrate
`
`obviousness. Indeed, AliveCor’s Dr. Efimov admitted that a POSITA would have
`
`understood that “irregular heart condition” included arrhythmia. APPLE-1069,
`
`27:17-18.
`
`Dr. Efimov also contradicted his opinions regarding Osorio. APPLE-1069,
`
`56:23-59:9. Specifically, he recognized that Osorio detects arrhythmias, but failed
`
`to offer any justification for the position that Osorio’s detection of arrhythmias is
`
`somehow diminished as part of its process of detecting neurological conditions.
`
`Id., 68:6-70:7. Osorio describes detecting “any pathological condition” and it is
`
`1
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`undisputed that “arrhythmia” is a pathological condition. Id., 50:17-22; 51:6-10.
`
`AliveCor’s second argument attempts to distinguish the “confirm”
`
`limitations from the prior art. Despite acknowledging that ECG is the gold
`
`standard for detecting arrhythmias (Resp. 10; APPLE-1071, 19:12-18), AliveCor
`
`argues that Shmueli limits its detection of heart conditions to SpO2/PPG data, even
`
`when the gold standard of ECG is available. This belies common sense—Shmueli
`
`instructs a user to take an ECG when a problem is identified by SpO2/PPG so that
`
`the ECG can confirm whether or not the SpO2/PPG detection was accurate. Pet. 12,
`
`26-28; APPLE-1003, ¶51 and ¶¶109-113; APPLE-1004, Abstract, 3:15-20, 9:21-
`
`29, 12:22-31; 14:16-29, FIG. 7. AliveCor also ignores Shmueli’s disclosure that,
`
`when a potential irregular heart condition is detected by SpO2/PPG monitoring, the
`
`system prompts the user to take an ECG and analyzes the ECG data alone or in
`
`correlation with the SpO2/PPG to confirm the detection. APPLE-1004, 15:1-3;
`
`12:22-31.
`
`AliveCor’s third argument against the combination of Shmueli-Osorio
`
`combination is similarly deficient. AliveCor does not dispute or rebut the Petition’s
`
`primary motivation for the combinations—benefits of activity monitoring to detect
`
`pathological conditions, which again would have included arrhythmias. Pet., 43,
`
`50-54. AliveCor instead argues that Shmueli and Osorio are non-analogous—
`
`relying on an unreasonably narrow view of Osorio and on AliveCor’s incorrect
`
`2
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`argument that neither Shmueli nor Osorio disclose arrhythmia detection.
`
`AliveCor’s last argument focuses on “machine learning” claims, which only
`
`apply generic machine learning algorithms to detect arrhythmia. As acknowledged
`
`by Dr. Efimov, the disclosed machine learning algorithms were well-known by
`
`December 2013. In view of machine learning’s advantages, a POSITA would have
`
`been motivated to optimize the multifactor analysis of the Shmueli-Osorio device
`
`using machine learning to achieve better accuracy.
`
`II. THE PRIOR ART RENDERS ARRHYTHMIA DETECTION
`OBVIOUS
`A. Record Evidence Confirms Obviousness
`Despite AliveCor’s pre-institution argument, the Institution Decision
`
`recognized that irregular heart condition “at a minimum, encompass[es]—
`
`arrhythmia.” Dec., 34. The post-institution record reinforces this preliminary
`
`finding.
`
`Testimony From Both Experts Reinforce the Petition
`1.
`AliveCor’s position relies principally on declaration testimony from Dr.
`
`Efimov. Resp., 42-47 (citing Ex. 2016, ¶¶68-73). In deposition, however, Dr.
`
`Efimov admitted that an irregular heart condition is a “general category” and that
`
`3
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`arrhythmia is a “subcategory.” APPLE-1069, 28:3-24.1
`
`Dr. Chaitman’s testimony on Shmueli’s use of “irregular heart condition,” in
`
`contrast, is unrebutted; AliveCor failed to produce any evidence to the contrary. It
`
`instead concludes—without even citing to the record—that “Dr. Chaitman
`
`admitted in cross-examination that the detection in Shmueli is performed based on
`
`the SpO2 measurement and the SpO2 measurement only…” Resp., 3. This
`
`mischaracterizes Dr. Chaitman’s testimony since AliveCor’s questions were
`
`limited to specific embodiments of Shmueli, not its entire disclosure. Ex. 2017,
`
`71:31-90:12.
`
`With its narrow focus on SpO2 measurement, AliveCor appears to argue that
`
`Shmueli’s detection of irregular heart conditions is based exclusively on
`
`monitoring blood gas composition. Resp., 3 (citing Ex. 2016, ¶49); Ex. 2016, ¶49.
`
`However, Shmueli’s title includes “pulse oximetry,” indicating that its disclosure
`
`is not limited only to oxygen saturation measurements. This is reinforced by
`
`Shmueli’s reference to “pulse oximeter” and “photoplethysmography,” which both
`
`
`1 Dr. Efimov also made several factually incorrect statements. He testified that
`
`sinus tachycardia is “a symptom of a neurological system but not an arrhythmia per
`
`se[,]” which contradicts undisputed disclosures in the ’731 patent. Compare
`
`APPLE-1069, 58:1-2 and APPLE-1001, 1:40-51, Table 2.
`
`4
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`have uses beyond just oxygen saturation measurements. APPLE-1004, 8:24-30.
`
`Indeed, Dr. Efimov testified that a POSITA would have understood that a “pulse
`
`oximeter” includes both PPG and SpO2 sensors, and measures both pulse and
`
`blood gas. APPLE-1069, 83:11-25, 84:16-85:2. This is consistent with Shmueli’s
`
`teaching that its device can derive “physiological parameters such as pulse rate,
`
`pulse amplitude, pulse shape, rate of blood flow etc.” and “scan the derived
`
`physiological parameters to detect various irregularities of the heart condition.”
`
`Id., 13:14-22. To the extent that AliveCor’s position is that Shmueli’s detection of
`
`irregular heart condition is based only on blood gas composition measurements,
`
`Shmueli’s disclosure and Dr. Efimov’s testimony refute it. APPLE-1069, 120:6-
`
`13.
`
`AliveCor also is wrong in saying that Shmueli’s “SpO2 measurements”
`
`necessarily precludes arrhythmia detection. Dr. Efimov admitted that pulse (and
`
`thus, heart rate) can be derived from pulse oximeters and SpO2 sensors. It is
`
`undisputed that heart rate data is used to detect arrhythmia. APPLE-1069, 84:4-12,
`
`120:6-13, 121:2-17. Dr. Chaitman similarly confirmed that physiological
`
`parameters used for arrhythmia detection (pulse rate, pulse amplitude, etc.) can be
`
`derived from Shmueli’s SpO2 measurements. Ex. 2017, 90:5-12. Both parties’
`
`experts therefore agree that data used to detect arrhythmia is derived from
`
`Shmueli’s SpO2 measurements using a pulse oximeter sensor. APPLE-1069,
`
`5
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`
`120:6-13.
`
`Thus, the expert testimony contradicts AliveCor’s incorrect view of
`
`Shmueli’s SpO2 measurements, and also contradicts AliveCor’s conclusion that
`
`arrhythmia detection is necessarily precluded.
`
`Beyond expert testimony, AliveCor’s position fails to rebut or even address
`
`other evidence that reinforces the Petition: (1) disclosures in Shmueli and the ’731
`
`patent specification, and (2) secondary evidence.
`
`Shmueli And The ’731 Patent Both Reinforce The Petition
`2.
`AliveCor broadly alleges that “Shmueli does not give a POSITA any
`
`direction indicating to a POSITA that arrhythmias are included in the context of its
`
`discussion.” Resp., 45. This attempt to narrow Shmueli runs contrary to its
`
`express disclosure. AliveCor attempts to avoid this disclosure by denying that
`
`Shmueli provides an “expansive definition.” Resp., 44 (fn 2) (citing APPLE-1004,
`
`16:3-5). AliveCor’s analysis is incomplete—ignoring an earlier clause in Shmueli
`
`stating that “the scope of the terms herein, particularly of the term irregular heart
`
`condition are intended to include all such new technologies a priori.” APPLE-
`
`1004, 16:3-5. Through this reference to “irregular heart condition,” Shmueli
`
`makes clear that the term is not limited in the manner that AliveCor suggests (i.e.,
`
`excluding arrhythmia).
`
`AliveCor’s myopic view of Shmueli also causes it to ignore key discussion
`
`6
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`of other relevant terminology. Specifically, Shmueli teaches “intermittent” heart
`
`conditions. APPLE-1004, 9:24-29, 3:4-9. Dr. Efimov also confirmed that
`
`intermittently-occurring heart conditions are types of arrhythmias. APPLE-1069,
`
`23:25-24:14; 30:1-5.
`
`Moreover, Shmueli reinforces the Petition through disclosures of the
`
`challenges imposed by continuous cardiac monitoring. APPLE-1004, 9:21-23.
`
`Shmueli “resolves this problem by providing a combined oximetry and
`
`electrocardiogram measuring device” in which “oximetry measurement is
`
`performed continuously and/or repeatedly…” Id., 8:24-29. Shmueli uses
`
`oximetry measurement to detect intermittent irregular heart-related events “without
`
`requiring the fixed wiring of the ECG device to the patient.” Id. Discussion of the
`
`problem of cardiac monitoring associated with detecting intermittent heart
`
`conditions—requiring continuous monitoring by ECG—confirms that Shmueli
`
`contemplates techniques for detecting cardiac arrhythmias. In fact, the ’731 patent
`
`specification describes devices “configured to continuously measure one or more
`
`physiological signals of a user.” APPLE-1001, 2:39-3:3. This is precisely the type
`
`of device disclosed in Shmueli, which “preferably performs measurements of
`
`intermittent irregular heart-related events without requiring the fixed wiring of the
`
`ECG device to the patient.” APPLE-1004, 9:24-29.
`
`Moreover, both Shmueli and the ’731 patent discuss the limitations of Holter
`
`7
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`devices, further suggesting a similar focus on arrhythmia detection. APPLE-1004,
`
`2:21-3:3; APPLE-1001, 1:66-2:13. Both Dr. Efimov’s declaration and deposition
`
`testimony confirm that Holter devices are used to detect arrhythmia. APPLE-1069,
`
`30:24-31:9; Exhibit 2016, ¶7. Thus, there is no doubt that Shmueli is directed to
`
`arrhythmia detection.
`
`Secondary Evidence Also Reinforces The Petition
`3.
`AliveCor concedes “an arrhythmia might be an irregular heart condition.”
`
`Resp. 43. But it still contends that arrhythmia “cannot be an ‘irregular heart
`
`condition’ as that phrase is used in Shmueli.” Id. However, secondary evidence
`
`contradicts AliveCor’s interpretation of Shmueli’s use of “irregular heart
`
`condition” as excluding arrhythmia.
`
`APPLE-1066 references “irregular activity” in discussing “atrial
`
`fibrillation,” which is the most common type of diagnosed arrhythmia. APPLE-
`
`1066, 4; APPLE-1069, 23:5-9. Similarly, APPLE-1067 and APPLE-1068 use the
`
`term “irregular heart activity” in reference to Holter devices, which both experts
`
`agree are used for arrhythmia detection. APPLE-1067, 1; APPLE-1068 at 1.
`
`Shmueli also cites to several background references that relate to arrhythmia
`
`detection and describes them as “the most relevant prior art.” APPLE-1004, 3:10-
`
`13, 9:1-29; APPLE-1061, 13:23-29, 16:54-58, Claim 5; APPLE-1062, [0014],
`
`[0051], [0055], [0062].
`
`8
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`B. AliveCor’s Response Arguments Fail
`1.
`AliveCor’s Interpretation of Shmueli Deviates From its
`Disclosure
`AliveCor’s position is untenable as it requires every example of “irregular
`
`heart condition” to exclude arrhythmia. Otherwise, Shmueli renders the recited
`
`arrhythmia detection obvious since the term “at a minimum, encompass[es]”
`
`arrhythmia. Dec., 34. AliveCor’s three key arguments lack evidentiary support and
`
`therefore fail to rebut the Petition. Resp. 42-47.
`
`a)
`
`AliveCor’s First Argument Confirms The Breadth of
`“Irregular Heart Condition”
`AliveCor states that “there is no evidence a POSITA at the time of the
`
`invention of the ’731 Patent, reading Shmueli, would have understood Shmueli’s
`
`use of the phrase ‘irregular heart condition’ to include arrhythmias…” Resp., 44.
`
`As discussed in Section II.A, this is wrong based on the cited evidence. Beyond
`
`Shmueli, AliveCor confirms the breadth of “irregular heart conditions” since it
`
`states “there are numerous other irregular heart conditions…” Resp., 43-44. If
`
`“irregular heart conditions” is understood to include “numerous” conditions and
`
`Shmueli discloses detecting “various irregular heart conditions,” then it would
`
`have been obvious that arrhythmia (which is the most common type of heart
`
`condition) is one example detected by Shmueli. APPLE-1004, 12:29-31.
`
`AliveCor even states that irregular heart condition is a “genus” of arrhythmia.
`
`Resp., 44.
`
`9
`
`
`
`b)
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`AliveCor’s Second Argument Contradicts Record
`Evidence Of Oximetry Measurements Being Used For
`Arrhythmia Detection
`AliveCor’s second argument is conclusory; it assumes no possible
`
`configuration for using SpO2 (PPG or oximetry) measurements for arrhythmia
`
`detection exists. AliveCor merely posits that “PPG was a ‘suboptimal’ tool for
`
`measuring arrhythmias” but fails to set forth meaningful evidence of
`
`incompatibility. Resp., 46. This is not surprising since several references teach the
`
`use of pulse oximetry for arrhythmia detection. APPLE-1020, Abstract, FIG. 3,
`
`3:58-4:3.
`
`AliveCor ignores Shmueli’s disclosure of deriving “physiological
`
`parameters such as pulse rate, pulse amplitude, pulse shape,….” APPLE-1004,
`
`13:14-22. Dr. Efimov confirmed that these parameters can be used to determine
`
`parameters (heart rate, heart rate variability) used to detect arrhythmia. APPLE-
`
`1069, 120:17-122:8. AliveCor also fails to acknowledge or address that Shmueli is
`
`titled “Pulse Oximetry Measurement Triggering ECG Measurement,” and Dr.
`
`Efimov’s testimony that “pulse oximetry” includes both pulse and blood gas
`
`measurements. Id., 83:6-7.
`
`AliveCor repeatedly alleges that Shmueli is focused on detecting other
`
`conditions, such as “heart attacks or acute heart failure.” Resp., 40, 42, 46.
`
`However, neither “heart attacks” nor “acute heart failure” are discussed in
`
`10
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`Shmueli, which Dr. Efimov confirmed. APPLE-1069, 122:22-123:15.
`
`c)
`
`AliveCor’s Third Argument Is Limited to Specific
`Embodiments of Shmueli
`Shmueli’s disclosure includes clear language that CO2 measurements are
`
`used in specific embodiments, and thus, not limiting: “instead of, or in addition to,
`
`the oximetry (SpO2) measuring unit the heart monitoring device may include a unit
`
`for measuring CO2 content in the blood.” APPLE-1004, 10:17-19 (cited in Resp.,
`
`46).
`
`AliveCor Ignores Non-Limiting Language in Osorio
`2.
`AliveCor characterizes Osorio as “directed to detecting epileptic seizures—a
`
`neurological event—does not disclose detecting arrhythmias—a cardiac
`
`condition.” Resp., 47. This interpretation is at odds with three aspects of Osorio:
`
`(1) its descriptions of epileptic seizures, (2) its claim structure, and (3) its
`
`description of arrhythmia detection.
`
`a)
`
`Osorio Confirms Epileptic Seizures are Exemplary and
`Not Limiting
`AliveCor posits that “Osorio consistently teaches using [] [body data
`
`variable] analysis to detect the presence of epileptic seizures…” Resp., 48-49.
`
`AliveCor overlooks Osorio’s consistent use of permissive language to indicate that
`
`its teachings for epileptic seizures are merely exemplary. APPLE-1005, [0002];
`
`[0037]; [0046]. This language counsels against limiting Osorio’s disclosure to
`
`epileptic seizures, and yet that is exactly the error AliveCor commits in citing these
`
`11
`
`
`
`Case IPR2021-00971
`Attorney Docket No: 50095-0033IP1
`
`paragraphs.
`
`AliveCor also ignores several key disclosures that do not reference
`
`“epileptic seizures,” including paragraphs addressing the invention as a whole
`
`(APPLE-1005, [0027]-[0031]) and descriptions of the overall system (id., [0033]).
`
`When questioned, Dr. Efimov was unable to explain AliveCor’s basis for
`
`narrowing Osorio and resorted instead to providing non-responsive, conclusory
`
`testimony. APPLE-1069, 67:10-20; 68:6-70:7.
`
`Osorio also teaches the detection of several types of body indices, including
`
`“heart rate,” “heart rhythm,” and “heart rate variability.” APPLE-1005, [0042].
`
`Osorio broadly describes that “[a]n occurrence of any pathological state … may
`
`be determined by the pathological state occurrence module 290.” Id., [0044].
`
`b)
`
`Osorio’s Claims Confirm AliveCor’s Interpretation Is
`Unduly Narrow
`Independent claim 1 of Osorio recites “a pathological body state of a
`
`patient.” APPLE-1005, Cl. 1. Claim 7, which depends from claim 1, recites that
`
`“said pathological state is an epileptic event.” Through claim differentiation,
`
`“e