Prosecution Insights
Last updated: April 19, 2026
Application No. 17/116,905

TWELVE-LEAD ELECTROCARDIOGRAM USING A THREE-ELECTRODE DEVICE

Non-Final OA §103
Filed
Dec 09, 2020
Examiner
TEHRANI, DANIEL
Art Unit
3792
Tech Center
3700 — Mechanical Engineering & Manufacturing
Assignee
AliveCor, Inc.
OA Round
7 (Non-Final)
58%
Grant Probability
Moderate
7-8
OA Rounds
3y 9m
To Grant
99%
With Interview

Examiner Intelligence

Grants 58% of resolved cases
58%
Career Allow Rate
28 granted / 48 resolved
-11.7% vs TC avg
Strong +44% interview lift
Without
With
+43.8%
Interview Lift
resolved cases with interview
Typical timeline
3y 9m
Avg Prosecution
35 currently pending
Career history
83
Total Applications
across all art units

Statute-Specific Performance

§101
5.5%
-34.5% vs TC avg
§103
47.3%
+7.3% vs TC avg
§102
21.2%
-18.8% vs TC avg
§112
22.6%
-17.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 48 resolved cases

Office Action

§103
Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Response to Amendment 2. This action is responsive to the amendments filed 12/10/2025. Claims 1, 9, and 17 have been amended. No claims were newly added or have been canceled. Response to Arguments 3. Applicant’s arguments filed on 12/10/2025 with respect to the art rejections have been fully considered but they are not persuasive. In substance, applicant argues that A) Any groupings in Meij are based solely on general categories and not a value of the characteristic that is specific to the individual (i.e. a particular age, weight, height). In response to A), the Examiner respectfully disagrees.At the onset, it should be noted there is no definition of the “characteristic of the individual”. The broadest reasonable interpretation of a characteristic of the individual is anything that characterizes an individual such as their sex, age group, weight, cardiac health, and more. The characteristics of the patient in paragraph 0057 of Meij is read as applicant’s characteristic specific to the individual. With regards to applicant’s assertion that the claims require a particular age, weight, height of the individual, the Examiner notes that none of these characteristics are recited in the claims. It is noted that the features upon which applicant relies (i.e., a particular age, weight, height) are not recited in the rejected claims. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Furthermore, applicant’s own disclosure includes an individual’s sex as a characteristic as disclosed in paragraph 00366, “If the individual identifies as male, the twelve-lead ECG data may be preprocessed to only include data corresponding to male subject”. Meiji still meets the scope of the limitations because it still characterizes the groups based on characteristics of the individual (see paragraph 0057). Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-2, 4-6, 9-10, 12-14, and 17-20 are rejected under 35 U.S.C 103 as being unpatentable over Thomson et al. (US Pub.: 2015/0018660, – Previously cited) and further in view of Albert et al. (US Pub.: 2014/0228665 A1,– Previously Cited) and further in view of Meij et al. (US Pub.: 2002/0035334 A1, – Previously Cited) and further in view of Lee et al. (NPL reference, “Reconstruction of Precordial Lead Electrocardiogram”, – Previously Cited) and further in view of Wang et al. (NPL reference, “A novel method…for deriving standard 12-lead ECG”, – Previously Cited). Regarding claim 1, Thomson teaches an apparatus (e.g. paragraph 0048), comprising: an electrocardiograph device (e.g. paragraph 0115) having first, second, and third electrode assemblies with first, second, and third electrodes adapted to measure electrical activity at first, second, and third locations of an individual, respectively (e.g. paragraph 0028, – “The first, second, and third electrode leads may be used concurrently to generate one or more of a Lead I, a Lead II, or a Lead III ECG for example. The first electrode lead may be configured to contact a right arm of the user, the second electrode lead may be configured to contact a left arm of the user, and the third electrode lead may be configured to contact a left leg of the user”); a key (e.g. paragraph 0086, – an encryption key); and a processing device (e.g. paragraph 0049) to: determine a Lead I contemporaneously with a Lead II based on a first measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); determine the Lead I contemporaneously with a Lead III based on a second measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); analyze an analog waveform corresponding to the set of Leads to extract properties of the analog waveform (e.g. paragraphs 0109, 0342); digitally encode the properties of the analog waveform to generate digital information (e.g. paragraphs 0122-0123 ); compress the analog waveform to increase an amount of analog waveform data that can be transmitted (e.g. paragraph 0272, – “In any of the systems, device, or methods described herein data (including digital, analog, and/or hybrid digital/analog data) may be compressed before it is encrypted. Any appropriate data compression technique may be used”); append the analog waveform to the digital information to generate a hybrid waveform (e.g. paragraphs 0289-0291, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information… There are many potential benefits to transmitting a hybrid analog/digital signal that can be read and understood by the telecommunications device”); encrypt the hybrid waveform so that it can be decrypted using the key (e.g. paragraph 0086); and transmit the hybrid waveform (e.g. paragraph 0126, – “the processor may be configured to encode the signals to be transmitted as hybrid signals comprising digital information appended to an analog signal”). Thomson teaches augmented limb leads (leads aVR, AVL, and aVF) are derivable from limb leads I, II, and III and that two of limb leads (i.e. lead I, II, and III) can be used to derive the third if necessary (e.g. paragraphs 0011-0012). However, Thomson does not explicitly teach time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement; preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Albert, in a same field of endeavor of twelve-lead electrocardiograms, discloses time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement (The Examiner notes that as currently claimed, the first measurement and second measurement would always be common to itself and are thus time-aligned; e.g. paragraphs 0014, 0054, 0063, – time alignment of ECG (heartbeat) signals). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the apparatus of Thomson to incorporate time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement, as taught and suggested by Albert, in order to more accurately/effectively calculate and display the augmented Leads (i.e. aVR, aVL, and aVF) when using limb Leads I, II, and III (Albert, paragraph 0014). However, Thomson in view of Albert does not explicitly teach preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Meij, in a same field of endeavor of twelve-lead electrocardiograms, discloses preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual (e.g. paragraphs 0056-0057). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson and Albert to incorporate preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual, as taught and suggest by Meij, for the purpose of increasing the efficiency and organization of the system as well as having higher quality data. However, Thomson in view of Albert in view of Meij does not explicitly teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determine, using the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Lee, in a same field of endeavor of electrocardiogram reconstruction, discloses determining leads V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads (e.g. pg. 820). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, and Meij to incorporate the twelve-lead ECG reconstruction method for determining leads V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads, as taught and suggested by Lee, for the purpose of reconstructing twelve-lead ECGs from only three leads (Lee, pg. 819). However, Thomson in view of Albert in view of Meij in view of Lee does not teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model a set of leads. Wang, in a same field of endeavor of twelve-lead electrocardiograms, discloses training a machine learning model using the preprocessed measured twelve-lead ECG data (e.g. Fig. 7; pg. 407, Data Preprocessing Heading; pg. 408, Synthesis based on convolutional neural networks Heading, – convolutional neural network (CNN) is a machine learning model); determining, using the machine learning model a set of leads (e.g. Fig. 7; pg. 407, 409, – the convolutional neural network is trained using several recordings that are preprocessed and includes Leads common to the measured twelve-lead ECG data in order to synthesize the missing leads). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, and Lee to incorporate training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model a set of leads, as taught and suggested by Wang, for the purpose of synthesizing a standard 12-lead from a reduced lead-set ECG recording more quickly and accurately (Wang, abstract). Regarding claim 2, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the apparatus of claim 1 as discussed above, and Thomson further teaches wherein the processing device (e.g. paragraph 0049) is further configured to: generate a header comprising the digital information, and wherein to append the analog waveform to the digital information, the processing device appends the analog waveform to the header (e.g. paragraph 0289, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information, such as the duration, pulse rate, information about the ECG waveform (if pre-analyzed), such as interval data, etc”). Regarding claim 4, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the apparatus of claim 2 as discussed above, and Thomson further teaches wherein the properties of the analog waveform comprise a maximum value and a minimum value of the analog waveform, a duration of the analog waveform, an average value of the analog waveform, (e.g. paragraph 0255, – “information extracted from the analog signal such as the scaling (e.g., max and/or minimum values), duration, average, etc.)”) a type of the analog waveform, timing data of the analog waveform, and a time stamp of the analog waveform (e.g. paragraph 0295, – “additional data 0909 on the analog signal (e.g., type, timing, data stamp/time stamp, etc.)”). Regarding claim 5, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the apparatus of claim 4 as discussed above, and Thomson further teaches wherein the processing device digitally encodes the properties of the analog waveform so that the digital information comprises (e.g. paragraphs 0122-0123, – “the processor is configured to encode the signals to be transmitted as digital signals, as discussed above”): a start bit or one or more start bytes (e.g. paragraphs 0090, 0295, – “the signal includes a start bit or bytes”); a sequence of calibration data comprising the maximum value and the minimum value of the analog waveform, the duration of the analog waveform (e.g. paragraph 0109, – “comprises calibration data for the analog data (e.g., minimum, maximum, variable interval (e.g., time interval), scale, etc.)”), and the average value of the analog waveform; and additional data comprising the type of the analog waveform (e.g. paragraphs 0109, 0255), the timing data of the analog waveform, and the time stamp of the analog waveform (e.g. paragraph 0295, – “(e.g., type, timing, data stamp/time stamp, etc.)”). Regarding claim 6, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the apparatus of claim 5 as discussed above, and Wang further teaches wherein the processing device is further configured to: train the machine learning model to predict the set of Leads using the preprocessed measured twelve-lead ECG data (e.g. pg. 408-409). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to incorporate training the machine learning model to predict the set of leads using the preprocessed measured twelve-lead ECG data, as taught and suggested by Wang, for the purpose of making the twelve-lead ECG reconstruction quicker and more accurate. Regarding claim 9, Thomson teaches a method for generating a 12-lead electrocardiogram (e.g. Fig. 7; paragraph 0048), the method comprising: obtaining, using an electrocardiograph device, a first measurement and a second measurement of electrical activity at first, second, and third locations of an individual (e.g. paragraphs 0028; 0039); determining a Lead I contemporaneously with a Lead II based on a first measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); determine the Lead I contemporaneously with a Lead III based on the second measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); analyzing an analog waveform corresponding to the set of Leads to extract properties of the analog waveform (e.g. paragraphs 0109, 0342); digitally encoding the properties of the analog waveform to generate digital information (e.g. paragraphs 0122-0123); compressing the analog waveform to increase an amount of analog waveform data that can be transmitted (e.g. paragraph 0272, – “In any of the systems, device, or methods described herein data (including digital, analog, and/or hybrid digital/analog data) may be compressed before it is encrypted. Any appropriate data compression technique may be used”); appending the analog waveform to the digital information to generate a hybrid waveform (e.g. paragraphs 0289-0291, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information… There are many potential benefits to transmitting a hybrid analog/digital signal that can be read and understood by the telecommunications device”); encrypting the hybrid waveform so that it can be decrypted using a key located on the electrocardiograph device (e.g. paragraph 0086); and transmitting the hybrid waveform (e.g. paragraph 0126, – “the processor may be configured to encode the signals to be transmitted as hybrid signals comprising digital information appended to an analog signal”). Thomson teaches augmented limb leads (leads aVR, AVL, and aVF) are derivable from limb leads I, II, and III and that two of limb leads (i.e. lead I, II, and III) can be used to derive the third if necessary (e.g. paragraphs 0011-0012). In addition, Thomson teaches a processing device (e.g. paragraphs 0049, 0089). However, Thomson does not explicitly teach time align the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement; preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, by a processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Albert, in a same field of endeavor of twelve-lead electrocardiograms, discloses time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement (The Examiner notes that as currently claimed, the first measurement and second measurement would always be common to itself and are thus time-aligned; e.g. paragraphs 0014, 0054, 0063, – time alignment of ECG (heartbeat) signals). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Thomson to incorporate time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement, as taught and suggested by Albert, in order to more accurately/effectively calculate and display the augmented Leads (i.e. aVR, aVL, and aVF) when using limb Leads I, II, and III (Albert, paragraph 0014). However, Thomson in view of Albert does not explicitly teach preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, by a processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Meij, in a same field of endeavor of twelve-lead electrocardiograms, discloses preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual (e.g. paragraphs 0056-0057). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson and Albert to incorporate preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual, as taught and suggest by Meij, for the purpose of increasing the efficiency and organization of the system as well as having higher quality data. However, Thomson in view of Albert in view of Meij does not explicitly teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, by a processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads. Lee, in a same field of endeavor of electrocardiogram reconstruction, discloses using measured twelve-lead ECG data to determine leads V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads (e.g. pg. 820). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, and Meij to incorporate the twelve-lead ECG reconstruction method for determining leads V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads, as taught and suggested by Lee, for the purpose of reconstructing twelve-lead ECGs from only three leads (Lee, pg. 819). However, Thomson in view of Albert in view of Meij in view of Lee does not teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, by a processing device executing the machine learning model a set of leads. Wang, in a same field of endeavor of twelve-lead electrocardiograms, discloses training a machine learning model using the preprocessed measured twelve-lead ECG data (e.g. Fig. 7; pg. 407, Data Preprocessing Heading; pg. 408, Synthesis based on convolutional neural networks Heading, – convolutional neural network (CNN) is a machine learning model); determining, using the machine learning model a set of leads (e.g. Fig. 7; pg. 407, 409, – the convolutional neural network is trained using several recordings that are preprocessed and includes leads common to the measured twelve-lead ECG data in order to synthesize the missing leads). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, and Lee to incorporate training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model a set of leads, as taught and suggested by Wang, for the purpose of synthesizing a standard 12-lead from a reduced lead-set ECG recording more quickly and accurately (Wang, abstract). Regarding claim 10, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the method of claim 9 as discussed above, and Thomson further teaches further comprising: generating a header comprising the digital information, and wherein to append the analog waveform to the digital information, the processing device appends the analog waveform to the header (e.g. paragraph 0289, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information, such as the duration, pulse rate, information about the ECG waveform (if pre-analyzed), such as interval data, etc”). Regarding claim 12, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the method of claim 10 as discussed above, and Thomson further teaches wherein the properties of the analog waveform comprise a maximum value and a minimum value of the analog waveform, a duration of the analog waveform, an average value of the analog waveform, (e.g. paragraph 0255, – “information extracted from the analog signal such as the scaling (e.g., max and/or minimum values), duration, average, etc.)”) a type of the analog waveform, timing data of the analog waveform, and a time stamp of the analog waveform (e.g. paragraph 0295, – “additional data 0909 on the analog signal (e.g., type, timing, data stamp/time stamp, etc.)”). Regarding claim 13, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the method of claim 12 as discussed above, and Thomson further teaches wherein the processing device digitally encodes the properties of the analog waveform so that the digital information comprises (e.g. paragraphs 0122-0123, – “the processor is configured to encode the signals to be transmitted as digital signals, as discussed above”): a start bit or one or more start bytes (e.g. paragraphs 0090, 0295, – “the signal includes a start bit or bytes”); a sequence of calibration data comprising the maximum value and the minimum value of the analog waveform, the duration of the analog waveform (e.g. paragraph 0109, – “comprises calibration data for the analog data (e.g., minimum, maximum, variable interval (e.g., time interval), scale, etc.)”), and the average value of the analog waveform (e.g. paragraphs 0109, 0255); and additional data comprising the type of the analog waveform (e.g. paragraphs 0109, 0255), the timing data of the analog waveform, and the time stamp of the analog waveform (e.g. paragraph 0295, – “(e.g., type, timing, data stamp/time stamp, etc.)”). Regarding claim 14, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the method of claim 13 as discussed above, and Wang further teaches further comprising: training the machine learning model to predict the set of Leads using the preprocessed measured twelve-lead ECG data (e.g. pg. 408-409). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to incorporate training the machine learning model to predict the set of Leads using the preprocessed measured twelve-lead ECG data, as taught and suggested by Wang, for the purpose of making the twelve-lead ECG reconstruction quicker and more accurate. Regarding claim 17, Thomson teaches a non-transitory computer-readable storage medium storing instructions, which when executed by a processing device, cause the processing device to (e.g. paragraphs 0132, 0182): obtain, using an electrocardiograph device, a first measurement and a second measurement of electrical activity at first, second, and third locations of an individual (e.g. paragraphs 0028, 0034; 0039); determine a Lead I contemporaneously with a Lead II based on the first measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); determine the Lead I contemporaneously with a Lead III based on the second measurement of electrical activity at the first, second, and third locations (e.g. paragraphs 0028, 0034, 0039); determine a V Lead from a fourth electrical signal measured using the electrocardiograph device (e.g. Fig. 7-8; paragraphs 0009-0011); analyzing an analog waveform corresponding to the set of Leads to extract properties of the analog waveform (e.g. paragraphs 0109, 0342); digitally encoding the properties of the analog waveform to generate digital information (e.g. paragraphs 0122-0123); compressing the analog waveform to increase an amount of analog waveform data that can be transmitted (e.g. paragraph 0272, – “In any of the systems, device, or methods described herein data (including digital, analog, and/or hybrid digital/analog data) may be compressed before it is encrypted. Any appropriate data compression technique may be used”); appending the analog waveform to the digital information to generate a hybrid waveform (e.g. paragraphs 0289-0291, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information… There are many potential benefits to transmitting a hybrid analog/digital signal that can be read and understood by the telecommunications device”); and transmitting the hybrid waveform (e.g. paragraph 0126, – “the processor may be configured to encode the signals to be transmitted as hybrid signals comprising digital information appended to an analog signal”). Thomson teaches augmented limb leads (leads aVR, AVL, and aVF) are derivable from limb leads I, II, and III and that two of limb leads (i.e. lead I, II, and III) can be used to derive the third if necessary (e.g. paragraphs 0011-0012). However, Thomson does not explicitly teach time align the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement; preprocess measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; train a machine learning model using the preprocessed measured twelve-lead ECG data; determine, by the processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, and remaining V Leads based on the Lead I, the Lead II, the Lead III, and the V Lead, wherein the Lead I, the Lead II, the Lead III, and the V lead are included within the set of Leads. Albert, in a same field of endeavor of twelve-lead electrocardiograms, discloses time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement (The Examiner notes that as currently claimed, the first measurement and second measurement would always be common to itself and are thus time-aligned; e.g. paragraphs 0014, 0054, 0063, – time alignment of ECG (heartbeat) signals). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the non-transitory computer-readable storage medium of Thomson to incorporate time aligning the first measurement and the second measurement based on the Lead I that is common to the first measurement and the second measurement, as taught and suggested by Albert, in order to more accurately/effectively calculate and display the augmented Leads (i.e. aVR, aVL, and aVF) when using limb Leads I, II, and III (Albert, paragraph 0014). However, Thomson in view of Albert does not explicitly teach preprocess measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual; train a machine learning model using the preprocessed measured twelve-lead ECG data; determine, by the processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, and remaining V Leads based on the Lead I, the Lead II, the Lead III, and the V Lead, wherein the Lead I, the Lead II, the Lead III, and the V lead are included within the set of Leads. Meij, in a same field of endeavor of twelve-lead electrocardiograms, discloses preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual (e.g. paragraphs 0056-0057). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson and Albert to incorporate preprocessing measured twelve-lead ECG data corresponding to a population of individuals to categorize the measured twelve-lead ECG data based on a characteristic of the population of individuals, wherein the population of individuals includes the individual and wherein the characteristic of the population of individuals comprises a characteristic of the individual, and wherein the measured twelve-lead ECG data is categorized based on a value of the characteristic that is specific to the individual, as taught and suggest by Meij, for the purpose of increasing the efficiency and organization of the system as well as having higher quality data. However, Thomson in view of Albert in view of Meij does not explicitly teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, by the processing device executing the machine learning model, a set of Leads including aVR, aVL, aVF, and remaining V Leads based on the Lead I, the Lead II, the Lead III, and the V Lead, wherein the Lead I, the Lead II, the Lead III, and the V lead are included within the set of Leads. Lee, in a same field of endeavor of electrocardiogram reconstruction, discloses using measured twelve-lead ECG data, a set of Leads including aVR, aVL, aVF, and remaining V Leads based on the Lead I, the Lead II, the Lead III, and the V Lead, wherein the Lead I, the Lead II, the Lead III, and the V lead are included within the set of Leads (e.g. pg. 820). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, and Meij to incorporate the twelve-lead ECG reconstruction method for determining leads V1, V2, V3, V4, V5, and V6 based on the Lead I, the Lead II, and the Lead III, wherein the Lead I, the Lead II, and the Lead III are included within the set of Leads, as taught and suggested by Lee, for the purpose of reconstructing twelve-lead ECGs from three leads (Lee, pg. 819). However, Thomson in view of Albert in view of Meij in view of Lee does not teach training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model a set of leads. Wang, in a same field of endeavor of twelve-lead electrocardiograms, discloses training a machine learning model using the preprocessed measured twelve-lead ECG data (e.g. Fig. 7; pg. 407, Data Preprocessing Heading; pg. 408, Synthesis based on convolutional neural networks Heading, – convolutional neural network (CNN) is a machine learning model); determining, using the machine learning model a set of leads (e.g. Fig. 7; pg. 407, 409, – the convolutional neural network is trained using several recordings that are preprocessed and includes Leads common to the measured twelve-lead ECG data in order to synthesize the missing leads). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, and Lee to incorporate training a machine learning model using the preprocessed measured twelve-lead ECG data; determining, using the machine learning model a set of leads, as taught and suggested by Wang, for the purpose of synthesizing a standard 12-lead from a reduced lead-set ECG recording more quickly and accurately (Wang, abstract). Regarding claim 18, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the non-transitory computer-readable storage medium of claim 17 as discussed above, and Thomson further teaches wherein the processing device (e.g. paragraph 0049) is further to: generate a header comprising the digital information, and wherein to append the analog waveform to the digital information, the processing device appends the analog waveform to the header (e.g. paragraph 0289, – “The ECG header information may include digital information about the analog waveform that is appended to the digital information, such as the duration, pulse rate, information about the ECG waveform (if pre-analyzed), such as interval data, etc”). Regarding claim 19, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the non-transitory computer-readable storage medium of claim 17 as discussed above, and Wang further teaches wherein the processing device is further to: train the machine learning model to predict the set of Leads using the preprocessed measured twelve-lead ECG data (e.g. pg. 408-409). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to incorporate training the machine learning model to predict the set of Leads using the preprocessed measured twelve-lead ECG data, as taught and suggested by Wang, for the purpose of making the twelve-lead ECG reconstruction quicker and more accurate. Regarding claim 20, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the non-transitory computer-readable storage medium of claim 19 as discussed above, and Wang further teaches wherein the V Lead is at least one of Lead V2 or Lead V5 (e.g. 408-409). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to include wherein the V Lead is at least one of Lead V2 or Lead V5, as taught and suggested by Wang, for the purpose of being able to more effectively reconstruct the precordial leads when performing reconstruction of the twelve-lead ECG. 7. Claims 8 and 16 are rejected under 35 U.S.C 103 as being unpatentable over Thomson and further in view of Albert and further in view of Meij and further in view of Lee and further in view of Wang and further in view of Atoui et al. (NPL reference, “A novel…for deriving standard 12-lead ECGs”, – Previously Cited). Regarding claim 8, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the apparatus of claim 6 as discussed above. However, Thomson in view of Albert in view of Meij in view of Lee in view of Wang does not explicitly teach wherein the processing device trains the machine learning model using only the measured twelve-lead ECG data corresponding to the individual. Atoui, in a same field of endeavor of electrocardiograms, discloses wherein the processing device trains the machine learning model using only the measured twelve-lead ECG data corresponding to the individual (e.g. pg. 885-886). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to incorporate wherein the processing device trains the machine learning model using only the measured twelve-lead ECG data corresponding to the individual, as taught and suggested by Atoui, for the purpose of being able to tailor ECG results and findings to a specific person. Regarding claim 16, Thomson in view of Albert in view of Meij in view of Lee in view of Wang teaches the method of claim 14 as discussed above. However, Thomson in view of Albert in view of Meij in view of Lee in view of Wang does not explicitly teach wherein the machine learning model is trained using only the twelve-lead ECG data corresponding to the individual. Atoui, in a same field of endeavor of electrocardiograms, discloses wherein the machine learning model is trained using only the twelve-lead ECG data corresponding to the individual (e.g. pg. 885-886). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Thomson, Albert, Meij, Lee, and Wang to incorporate wherein the processing device trains the machine learning model using only the measured twelve-lead ECG data corresponding to the individual, as taught and suggested by Atoui, for the purpose of being able to tailor ECG results and findings to a specific person. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL TEHRANI whose telephone number is (571)270-0697. The examiner can normally be reached 9:00am-5:00pm. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Benjamin Klein can be reached at 571-270-5213. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /D.T./Examiner, Art Unit 3792 /Benjamin J Klein/Supervisory Patent Examiner, Art Unit 3792
Read full office action

Prosecution Timeline

Dec 09, 2020
Application Filed
Jun 02, 2023
Non-Final Rejection — §103
Aug 28, 2023
Examiner Interview Summary
Aug 28, 2023
Applicant Interview (Telephonic)
Sep 08, 2023
Response Filed
Nov 13, 2023
Final Rejection — §103
Feb 07, 2024
Examiner Interview Summary
Feb 07, 2024
Applicant Interview (Telephonic)
Feb 23, 2024
Request for Continued Examination
Mar 05, 2024
Response after Non-Final Action
Apr 03, 2024
Non-Final Rejection — §103
Aug 06, 2024
Examiner Interview Summary
Aug 06, 2024
Applicant Interview (Telephonic)
Aug 07, 2024
Response Filed
Aug 31, 2024
Final Rejection — §103
Dec 10, 2024
Interview Requested
Dec 18, 2024
Applicant Interview (Telephonic)
Dec 18, 2024
Examiner Interview Summary
Jan 09, 2025
Response after Non-Final Action
Feb 04, 2025
Request for Continued Examination
Feb 06, 2025
Response after Non-Final Action
Mar 01, 2025
Non-Final Rejection — §103
Jul 15, 2025
Response Filed
Aug 09, 2025
Final Rejection — §103
Dec 10, 2025
Request for Continued Examination
Dec 14, 2025
Response after Non-Final Action
Dec 20, 2025
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12599764
HEADER ASSEMBLY HAVING CONTROLLED THERAPEUTIC AGENT RELEASE
2y 5m to grant Granted Apr 14, 2026
Patent 12558546
DORSAL ROOT GANGLION STIMULATION IN INFLUENCING ORGAN FUNCTION
2y 5m to grant Granted Feb 24, 2026
Patent 12539420
Deep Brain Stimulation Using Artificial Neural Networks
2y 5m to grant Granted Feb 03, 2026
Patent 12508432
Configurable Replacement Mechanism for Leadless Pacemaker System
2y 5m to grant Granted Dec 30, 2025
Patent 12502238
SURGICAL APPARATUS INCLUDING A STERILE ADAPTER HAVING MECHANICAL LOCKOUTS
2y 5m to grant Granted Dec 23, 2025
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

7-8
Expected OA Rounds
58%
Grant Probability
99%
With Interview (+43.8%)
3y 9m
Median Time to Grant
High
PTA Risk
Based on 48 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month