DETAILED ACTION
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
This action is responsive to the amendments and remarks received 16 July 2026. Claims 1 - 20 are currently pending.
Information Disclosure Statement
The information disclosure statement filed 17 July 2026 fails to comply with 37 CFR 1.98(a)(2), which requires a legible copy of each cited foreign patent document; each non-patent literature publication or that portion which caused it to be listed; and all other information or that portion which caused it to be listed. It has been placed in the application file, but the information referred to therein has not been considered.
Claim Objections
Claim 11 is objected to because of the following informalities: Lines 5 - 6 of claim 11 recite, in part, “wherein each of the pixels of the human-indecipherable image” which appears to a minor informality. The Examiner suggests amending the claim to --wherein each of the plurality of pixels of the human-indecipherable image-- in order to maintain consistency with lines 4 - 5 of claim 11 and to improve the clarity and precision of the claim. Appropriate correction is required.
The objections to claims 1, 7 and 18, due to minor informalities, are hereby withdrawn in view of the amendments and remarks received 16 July 2026.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 6, 7 and 17 - 19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 6 recites the limitation "the value for the patient data represented by the first channel" in line 2. There is insufficient antecedent basis for this limitation in the claim. The Examiner suggests amending line 2 of claim 6 to --the first value for the patient data represented by the first channel value-- in order to maintain consistency with lines 6 - 7 of claim 1.
Claim 17 recites the limitation "the patient" in line 12. There is insufficient antecedent basis for this limitation in the claim.
Claims 7, 18 and 19 are also rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, due to being dependent upon a rejected base claim(s) but would be withdrawn from the rejection if their base claim(s) overcome the rejection(s).
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1 - 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 3 - 6 of U.S. Patent No. 12,061,670. Although the claims at issue are not identical, they are not patentably distinct from each other because instant claims 1 - 20 would have been obvious over and/or obvious variations of claims 3 - 6 of U.S. Patent No. 12,061,670.
a. With regards to instant claim 1; Instant claim 1 differs from claim 3 of U.S. Patent No. 12,061,670 in that claim 3 of U.S. Patent No. 12,061,670 includes additional limitations that are not required by instant claim 1. However, the Examiner asserts that instant claim 1 which recites the opened ended transitional phrase "comprising", does not preclude the additional limitation(s) recited in claim 3 of U.S. Patent No. 12,061,670. Therefore, instant claim 1 is found to be anticipated by claim 3 of U.S. Patent No. 12,061,670; anticipation is "the ultimate or epitome of obviousness" (In re Kalm, 154 USPQ 10 (CCPA 1967), also In re Dailey, 178 USPQ 293 (CCPA 1973) and In re Pearson, 181 USPQ 641 (CCPA 1974)).
b. With regards to instant claim 2; Instant claim 2 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the ventilatory data. Including a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the ventilatory data would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the ventilatory data.
c. With regards to instant claim 3; Instant claim 3 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data. Including at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data.
d. With regards to instant claim 8; Instant claim 8 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “acquiring control parameters during the time period, wherein the control parameters are also converted into the human-indecipherable image.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include acquiring control parameters during the time period and also converting the acquired control parameters into the human-indecipherable image. Acquiring control parameters during the time period and also converting the acquired control parameters into the human-indecipherable image would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include acquiring control parameters during the time period and also converting the acquired control parameters into the human-indecipherable image.
e. With regards to instant claim 9; Instant claim 9 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the human-indecipherable image has a size of less than 4000 pixels.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 4000 pixels for the human-indecipherable image. Utilizing a size of less than 4000 pixels for the human-indecipherable image would enhance claim 3 of U.S. Patent No. 12,061,670 by decreasing the amount of memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 4000 pixels for the human-indecipherable image.
f. With regards to instant claim 10; Instant claim 10 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the human-indecipherable image has a size of less than 1600 pixels.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 1600 pixels for the human-indecipherable image. Utilizing a size of less than 1600 pixels for the human-indecipherable image would enhance claim 3 of U.S. Patent No. 12,061,670 by decreasing the amount of memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 1600 pixels for the human-indecipherable image.
g. With regards to instant claim 11; Instant claim 11 differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires that received control parameters are converted to the human-indecipherable image, that the human-indecipherable image has a defined layout and that “the trained machine learning model was trained based on images having the defined layout”. However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include converting received control parameters into the human-indecipherable image, utilizing a defined layout for the human-indecipherable image and training the trained machine learning model based on images having the defined layout. Converting received control parameters into the human-indecipherable image, utilizing a defined layout for the human-indecipherable image and training the trained machine learning model based on images having the defined layout would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data and by ensuring that the trained machine learning model is adequately and properly trained to accurately and reliably recognize conditions of patients based on the human-indecipherable images. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include converting received control parameters into the human-indecipherable image, utilizing a defined layout for the human-indecipherable image and training the trained machine learning model based on images having the defined layout.
h. With regards to instant claim 12; Instant claim 12 additionally differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data. Including at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data.
i. With regards to instant claim 13; Instant claim 13 additionally differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW t in the ventilatory data. Including a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the ventilatory data would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the ventilatory data.
j. With regards to instant claim 16; Instant claim 16 additionally differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the human-indecipherable image has a size of less than 4000 pixels.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 4000 pixels for the human-indecipherable image. Utilizing a size of less than 4000 pixels for the human-indecipherable image would enhance claim 3 of U.S. Patent No. 12,061,670 by decreasing the amount of memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include utilizing a size of less than 4000 pixels for the human-indecipherable image.
k. With regards to instant claim 17; Instant claim 17 differs from claim 3 of U.S. Patent No. 12,061,670 in slight variations in wording and in that claim 3 of U.S. Patent No. 12,061,670 includes additional limitations that are not required by instant claim 17. However, the Examiner asserts that instant claim 17 which recites the opened ended transitional phrase "comprising", does not preclude the additional limitation(s) recited in claim 3 of U.S. Patent No. 12,061,670. Therefore, instant claim 17 is found to be anticipated by claim 3 of U.S. Patent No. 12,061,670; anticipation is "the ultimate or epitome of obviousness" (In re Kalm, 154 USPQ 10 (CCPA 1967), also In re Dailey, 178 USPQ 293 (CCPA 1973) and In re Pearson, 181 USPQ 641 (CCPA 1974)).
l. With regards to instant claim 20; Instant claim 20 additionally differs from claim 3 of U.S. Patent No. 12,061,670 in that it additionally requires “wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement.” However, the Examiner asserts that it would have been obvious to one of ordinary skill in the art before the effective filing date to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data. Including at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data would enhance claim 3 of U.S. Patent No. 12,061,670 by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to modify claim 3 of U.S. Patent No. 12,061,670 to include at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the ventilatory data.
The Examiner notes that the table provided herein below identifies the corresponding conflicting claim relationships between the instant application and U.S. Patent No. 12,061,670.
18/760,968
12,061,670
Claim 1
Claim 3
Claim 2
Claim 3
Claim 3
Claim 3
Claim 4
Claims 3 and/or 4
Claim 5
Claim 4
Claim 6
Claim 5
Claim 7
Claim 6
Claim 8
Claim 3
Claim 9
Claim 3
Claim 10
Claim 3
Claim 11
Claim 3
Claim 12
Claim 3
Claim 13
Claim 3
Claim 14
Claims 3 and/or 4
Claim 15
Claim 4
Claim 16
Claim 3
Claim 17
Claim 3
Claim 18
Claims 3 and/or 4
Claim 19
Claims 3 and/or 4
Claim 20
Claim 3
Response to Arguments
Applicant's arguments filed 16 July 2026 have been fully considered but they are not persuasive.
On page 7 of the remarks the Applicant’s Representative argues that the rejections to claims 1 - 20 on the ground of non-statutory obviousness type double patenting should be withdrawn since Applicant is filing a terminal disclaimer herewith.
The Examiner respectfully disagrees.
The Examiner asserts that the rejections to claims 1 - 20 on the ground of nonstatutory double patenting are still applicable for the reasons provided herein above in section 12 of the instant Office Action and because no terminal disclaimer has been received in the instant application.
b. On pages 8 - 10 of the remarks the Applicant’s Representative argues that “the cited references fail to teach at least ‘converting the patient data to a human-indecipherable image having a plurality of pixels, wherein each of the plurality of pixels of the human-indecipherable image is defined by at least a first color channel and a second color channel, wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for the patient data and a second channel value of the first pixel represents a second value for the patient data.’” In particular, the Applicant’s Representative argues that there “is no reason that a person of ordinary skill in the art would have modified Raghu's EEG spectrum data with the imaging co-registration technology of Khamene ‘in the normal course of research and development to yield the claimed invention.’ Unigene, 655 F.3d at 1360.” The Applicant’s Representative argues that the use of spectrogram image data for CNN seizure classification by Raghu et al., “even if displayed in color, does not suggest replacing or modifying the asserted image-generation process so that a second channel value of a first pixel represents another portion of a patient-data value and a third channel value represents the sign of that patient-data value.” Furthermore, the Applicant’s Representative argues that the use of RGBA channels by Khamene et al. for graphics-hardware calculations does not teach that those channels should be repurposed to encode different values of patient data. Therefore, the Applicant’s Representative argues that the instant claims are allowable over the previously cited references.
The Examiner respectfully disagrees.
Initially, in response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
The Examiner asserts that one of ordinary skill in the art would have been motivated to modify the teachings of Raghu et al. with the well-known and applicable technique(s) of Khamene et al. at the very least to facilitate generating, processing and analyzing the color spectrogram images of Raghu et al. that are obtained from electroencephalogram (EEG) signal recordings. The Examiner asserts that at least figures 1 and 2 of Raghu et al. explicitly depict that EEG signal recordings, patient data, are converted into color spectrogram images and one of ordinary skill in the art would understand that pixels of color images are commonly defined by values of red, green and blue color channels. Furthermore, the Examiner asserts that Khamene et al. disclose that their invention is generally related to processor-based imaging, medical imaging applications and merging multiple pieces of medical data into a single image representation, see at least page 1 paragraphs 0003 - 0007 and page 2 paragraphs 0030 - 0032 of Khamene et al. Thus, the Examiner asserts that Khamene et al. is related and applicable to the teachings of Raghu et al. since Raghu et al. disclose that a spectrogram image is obtained by generating a spectrogram stack from 19 channels of EEG signals and concatenating the spectrogram of all the 19 channels to form the final spectrogram image, see at least figures 1 and 2 and section 2.1 - section 2.3.2 of Raghu et al. Additionally, the Examiner asserts that the color spectrogram images of Raghu et al. at least suggests that second and third channel values of a first pixel represent another portion and/or sign of a patient-data value at least because the color spectrogram images of Raghu et al. are obtained from EEG signal recordings, patient data, and thus each pixel of the color spectrogram image, which is defined by a plurality of color channels and values, corresponds to a portion of the patient data and at least because EEG signal recordings may comprise negative values. Lastly, the Examiner asserts that Khamene et al. at least suggest that their RGBA channels can be utilized to encode different values of patient data at least because Khamene et al. disclose that their invention is related to medical imaging applications and merging multiple pieces of medical data into a single image representation and that color channels of pixels can be utilized to store multiple gray scale image values and/or computed gradient values, see at least page 1 paragraphs 0003 - 0007, page 2 paragraphs 0030 - 0032, page 8 paragraph 0099 - page 9 paragraph 0105 and page 13 paragraphs 0148 - 0149 and 0156 - 0157 of Khamene et al. Therefore, the Examiner asserts that a person of ordinary skill in the art would have modified the combined teachings of Raghu et al. in view of Jacobson et al., the combined teachings of Raghu et al. in view of Teixeira in view of Jacobson et al. and the teachings of Raghu et al. with the well-known and applicable teachings of Khamene et al. to yield the claimed invention.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1, 4 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1.
- With regards to claim 1, Raghu et al. disclose a computer-implemented method for recognition of conditions, (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 205 Figs. 1 & 2, Pg. 210 Right-Hand Column First-Full Paragraph - § 5) the method comprising: acquiring patient data for a patient during a time period; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.1 - § 2.2, Pg. 204 Table 1, Pg. 210 § 5) converting the patient data to an image having a plurality of pixels, (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2) wherein each of the plurality of pixels of the image is defined by at least a first color channel, wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for the patient data and a second channel value represents a second value for the patient data; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2 [The Examiner asserts that the spectrogram image data of Raghu et al. comprises a plurality of pixels that are each defined by at least a first color channel value.]) providing, as input into a trained machine learning model, the image; (Raghu et al., Pg. 202 Abstract, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) and based on output from the trained machine learning model, generating a predicted condition of the patient. (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 Left-Hand Column First-Full Paragraph - § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) Raghu et al. fail to disclose expressly a human-indecipherable image, wherein each of the plurality of pixels is defined by a second color channel, and a second channel value of the first pixel. Pertaining to analogous art, Jacobson et al. disclose a computer-implemented method for recognition of conditions, (Jacobson et al., Figs. 1, 6 & 7, Pg. 1 ¶ 0018 - 0019, Pg. 3 ¶ 0041 - 0042, Pg. 4 ¶ 0044, Pg. 5 ¶ 0067 - 0073, Pg. 7 ¶ 0081) the method comprising: converting the patient data to a human-indecipherable image having a plurality of pixels, (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) wherein each of the pixels of the human-indecipherable image is defined by at least a first channel, and a first channel value of a first pixel represents at least a portion of a value for the patient data; (Jacobson et al., Figs. 2 & 3, Pg. 1 ¶ 0019, Pg. 3 ¶ 0033, 0037 - 0040 and 0042, Pg. 4 ¶ 0044 and 0055 - 0056, Pg. 5 ¶ 0067 - 0070 [The Examiner asserts that pixels of an image are defined by at least a first channel value.]) providing, as input into a trained machine learning model, the human-indecipherable image; (Jacobson et al., Figs. 1 - 3, Pg. 2 ¶ 0020 - 0021, Pg. 3 ¶ 0033 - 0042, Pg. 4 ¶ 0047, Pg. 5 ¶ 0067 - 0070) and based on output from the trained machine learning model, generating a predicted condition of the patient. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0019 - Pg. 2 ¶ 0021, Pg. 2 ¶ 0030, Pg. 3 ¶ 0036 - 0040 and 0042, Pg. 4 ¶ 0044, 0047 and 0055, Pg. 5 ¶ 0067 - 0070) Jacobson et al. fail to disclose expressly wherein each of the plurality of pixels is defined by a second color channel, and a second channel value of the first pixel. Pertaining to analogous art, Khamene et al. disclose an image having a plurality of pixels, (Khamene et al., Pg. 1 ¶ 0007, Pg. 7 ¶ 0089, Pg. 8 ¶ 0096 - 0099, Pg. 9 ¶ 0105 - 0110, Pg. 12 ¶ 0145, Pg. 13 ¶ 0148 - 0151) wherein each of the plurality of pixels of the image is defined by at least a first color channel and a second color channel, (Khamene et al., Pg. 7 ¶ 0089, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 9 ¶ 0109 and 0112, Pg. 12 ¶ 0134, 0140 and 0145, Pg. 13 ¶ 0148 - 0149, 0151 and 0157) wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for data and a second channel value of the first pixel represents a second value for the data. (Khamene et al., Pg. 1 ¶ 0003 - 0007, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 12 ¶ 0134 and 0145, Pg. 13 ¶ 0148 - 0151 and 0157 [“Graphics hardware is designed to compute color intensities meant to be displayed on a screen (i.e., light intensities for different color channels)”, “Store the fixed image on the GPU using a texture object with four color channels (i.e., RGBA texture)”, “The result will be written to the COLOR-buffer, which stores four values for each pixel, one for each color channel” and “To further speed up these very simple measures, one could also use all four color channels to store the image intensities (i.e., the first gray-scale image value goes into the first pixel's red channel, the second gray-scale value into the green channel, the third goes into the blue channel, the fourth into the alpha channel, the fifth again into the red channel of the second pixel and so on), which results in a texture only one quarter the size of the original image.”]) Raghu et al. and Jacobson et al. are combinable because they are both directed towards medical data processing systems that utilize machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Raghu et al. with the teachings of Jacobson et al. This modification would have been prompted in order to enhance the base device of Raghu et al. with the well-known and applicable technique Jacobson et al. applied to a similar device. Converting the patient data to a human-indecipherable image, as taught by Jacobson et al., would enhance the base device of Raghu et al. by helping safeguard the privacy and security of confidential medical data of patients thereby improving its compliance with the HIPAA privacy rule and enabling it to utilize remote computing resources for various reasons, such as to perform any computationally intensive processing tasks. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the base device of Raghu et al. would convert the patient data into a human-indecipherable image so as to help safeguard the privacy and security of confidential medical data of patients and enable it to safely utilize remote computing resources for various tasks. In addition, Raghu et al. in view of Jacobson et al. and Khamene et al. are combinable because they are all directed towards medical image processing systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. with the teachings of Khamene et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. with the well-known and applicable technique of Khamene et al. Defining each of the plurality of pixels by a plurality of color channels and color channel values, as taught by Khamene et al., would enhance the combined base device by improving its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate, such as color spectrogram images, as well as expand the number of various types of features it can extract and analyses it can perform on the patient data thereby improving its ability to accurately and reliably recognize conditions of patients. Furthermore, this modification would enhance the combined base device by facilitating its ability to generate, process and analyze color spectrogram images, such as the spectrogram images of Raghu et al., since pixels of the images would be defined by information necessary to depict and represent color data, i.e., a plurality of color channels and color channel values. Moreover, this modification would have been prompted by figures 1, 2 and 5 of Raghu et al. that depict the generated spectrogram image data in color since one of ordinary skill in the art would understand that pixels of color images are commonly represented by values for red, green and blue color channels. In addition, this modification would have been prompted by the teachings and suggestions of Raghu et al. that features such as edges, gradients and textures are extracted from the generated spectrogram image data, see at least page 204 section 2.3, and page 209 left-hand column first-full paragraph - subsection 6 of Raghu et al. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that each of the plurality of pixels of the combined base device would be defined by a plurality of color channels and color channel values in order to improve its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate, such as colorized spectrogram images, and expand the number of various types of features it can extract from the patient data and thereby enhance its ability to accurately and reliably recognize conditions of patients. Therefore, it would have been obvious to combine Raghu et al. with Jacobson et al. and Khamene et al. to obtain the invention as specified in claim 1.
- With regards to claim 4, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose expressly wherein the first pixel is further defined by a third channel value. Pertaining to analogous art, Khamene et al. disclose wherein the first pixel is further defined by a third channel value. (Khamene et al., Pg. 7 ¶ 0089, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 9 ¶ 0109 and 0112, Pg. 12 ¶ 0134, 0140 and 0145, Pg. 13 ¶ 0148, 0151 and 0157)
- With regards to claim 5, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 4. Raghu et al. fail to disclose explicitly wherein the third channel value represents a sign for the patient data. Pertaining to analogous art, Khamene et al. disclose wherein the third channel value represents a sign for the patient data. (Khamene et al., Pg. 8 ¶ 0099 - 0102, Pg. 9 ¶ 0105, Pg. 13 ¶ 0157)
Claims 2, 3 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1 as applied to claim 1 above, and further in view of Teixeira U.S. Publication No. 2012/0022350 A1.
- With regards to claim 2, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose explicitly wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW. Pertaining to analogous art, Teixeira discloses wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW. (Teixeira, Figs. 14 - 18, Pg. 4 ¶ 0111 - 0112, Pg. 14 ¶ 0260 - 0261, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0341, 0351, 0357, 0359 and 0361 [“if the second instrument 1420 is an electrocardiograph device, then output from the electrocardiograph device as input to the probabilistic processor 200 optionally includes one or more of: raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as an indication of a previous heart attack” and “electrocardiograph meter 1520 additionally provides time dependent values to the probabilistic processor 200, such as raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as a previous heart attack indication. The pulse oximeter 1510 data and electrocardiograph device 1520 data are optionally fused, as described supra. As discussed, infra, additional input data is provided to the probabilistic processor 200, such as data from an accelerometer 1530, data from a time meter 1550, and/or data from an environment meter 1540, such as temperature, pressure, vibration, humidity, and/or position information. The data is at least partially fused into fused sensor data 1450”]) Raghu et al. in view of Jacobson et al. in view of Khamene et al. and Teixeira are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al. and Jacobson et al., Teixeira is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the teachings of Teixeira. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Teixeira applied to a similar device. Including a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW in the patient data, as taught by Teixeira, would enhance the combined base device by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data, as taught and suggested by Teixeira, see at least page 4 paragraphs 0102 - 0108, page 14 paragraphs 0254 - 0258, page 16 paragraphs 0309 - 0311 and page 17 paragraphs 0313 - 0324 of Teixeira. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW would be included in the patient data so as to improve the ability of the combined base device to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. with Teixeira to obtain the invention as specified in claim 2.
- With regards to claim 3, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose explicitly wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. Pertaining to analogous art, Teixeira discloses wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. (Teixeira, Figs. 8, 9B, 9E, 9F & 15, Pg. 4 ¶ 0074 - 0082, Pg. 8 ¶ 0167 - 0174, Pg. 10 ¶ 0204 - 0205, Pg. 14 ¶ 0260 - 0261, Pg. 16 ¶ 0286 - 0299, Pg. 18 ¶ 0340 - 0341, 0345 and 0355) Raghu et al. in view of Jacobson et al. in view of Khamene et al. and Teixeira are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al. and Jacobson et al., Teixeira is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the teachings of Teixeira. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Teixeira applied to a similar device. Including at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the patient data, as taught by Teixeira, would enhance the combined base device by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data, as taught and suggested by Teixeira, see at least page 4 paragraphs 0102 - 0108, page 14 paragraphs 0254 - 0258, page 16 paragraphs 0309 - 0311 and page 17 paragraphs 0313 - 0324 of Teixeira. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement would be included in the patient data so as to improve the ability of the combined base device to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. with Teixeira to obtain the invention as specified in claim 3.
- With regards to claim 8, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose explicitly acquiring control parameters during the time period, wherein the control parameters are also converted into the human-indecipherable image. Pertaining to analogous art, Jacobson et al. disclose the human-indecipherable image. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) Jacobson et al. fail to disclose explicitly acquiring control parameters during the time period, wherein the control parameters are also converted into the image. Pertaining to analogous art, Teixeira discloses acquiring control parameters during the time period, (Teixeira, Figs. 14 - 18, Pg. 14 ¶ 0254 - 0261, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0340 - 0343, 0351, 0357 and 0359 - 0361, Pg. 19 ¶ 0367 - 0372) wherein the control parameters are also converted into the image. (Teixeira, Figs. 14 - 18, Pg. 14 ¶ 0254 - 0261, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0340 - 0343, 0351, 0357 and 0359 - 0361, Pg. 19 ¶ 0367 - 0372 [“if the second instrument 1420 is an electrocardiograph device, then output from the electrocardiograph device as input to the probabilistic processor 200 optionally includes one or more of: raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as an indication of a previous heart attack”, “fused sensor data 1450 refers to any form, matrix, concatenation, combination, union, representation, or mathematical combination of the data from the multiple instruments 1405” and “electrocardiograph meter 1520 additionally provides time dependent values to the probabilistic processor 200, such as raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as a previous heart attack indication. The pulse oximeter 1510 data and electrocardiograph device 1520 data are optionally fused, as described supra. As discussed, infra, additional input data is provided to the probabilistic processor 200, such as data from an accelerometer 1530, data from a time meter 1550, and/or data from an environment meter 1540, such as temperature, pressure, vibration, humidity, and/or position information. The data is at least partially fused into fused sensor data 1450”]) Raghu et al. in view of Jacobson et al. in view of Khamene et al. and Teixeira are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al. and Jacobson et al., Teixeira is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the teachings of Teixeira. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Teixeira applied to a similar device. Additionally acquiring and incorporating control parameters into the image, as taught by Teixeira, would enhance the combined base device by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data, as taught and suggested by Teixeira, see at least page 4 paragraphs 0102 - 0108, page 14 paragraphs 0254 - 0258, page 16 paragraphs 0309 - 0311 and page 17 paragraphs 0313 - 0324 of Teixeira. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that control parameters would additionally be acquired and incorporated into the image data so as to improve the ability of the combined base device to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. with Teixeira to obtain the invention as specified in claim 8.
Claims 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1 as applied to claim 1 above, and further in view of Murat Aykanat, Özkan Kılıç, Bahar Kurt, and Sevgi Saryal, “Classification of lung sounds using convolutional neural networks”, EURASIP Journal on Image and Video Processing, Vol. 2017, No. 65, Sept. 2017, pages 1 - 9, herein referred to as “Aykanat et al.”.
- With regards to claim 9, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose explicitly wherein the human-indecipherable image has a size of less than 4000 pixels. Pertaining to analogous art, Jacobson et al. disclose the human-indecipherable image. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) Jacobson et al. fail to disclose explicitly wherein the image has a size of less than 4000 pixels. Pertaining to analogous art, Aykanat et al. disclose wherein the image has a size of less than 4000 pixels. (Aykanat et al., Pg. 4 § 2.4 ¶ 1 - 5, Pg. 4 Figs. 3 & 4, Pg. 5 Figs. 5 & 6) Raghu et al. in view of Jacobson et al. in view of Khamene et al. and Aykanat et al. are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al. and Jacobson et al., Aykanat et al. is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the teachings of Aykanat et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Aykanat et al. applied to a similar device. Utilizing a size of less than 4000 pixels for the image, as taught by Aykanat et al., would enhance the combined base device by decreasing the amount of computer memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Furthermore, this modification would have been prompted by the teachings and suggestions of Raghu et al. that the image is resized and that a convolutional neural network (CNN) with pooling layers, such as Vgg16 and Vgg19 CNN models, was utilized since each pooling layer would further reduce the size of the image, see at least page 204 section 2.3 - 2.3.2 and page 206 table 2 of Raghu et al. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the human-indecipherable image would have a size of less than 4000 pixels so as to decrease the amount of computer memory needed to store and process the generated images and reduce the number of computations required to evaluate input patient data in order to improve the ability of the combined base device to quickly and efficiently recognize conditions of patients and facilitate its use on local and/or low-powered computer systems. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. with Aykanat et al. to obtain the invention as specified in claim 9.
- With regards to claim 10, Raghu et al. in view of Jacobson et al. in view of Khamene et al. disclose the method of claim 1. Raghu et al. fail to disclose explicitly wherein the human-indecipherable image has a size of less than 1600 pixels. Pertaining to analogous art, Jacobson et al. disclose the human-indecipherable image. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) Jacobson et al. fail to disclose explicitly wherein the image has a size of less than 1600 pixels. Pertaining to analogous art, Aykanat et al. disclose wherein the image has a size of less than 1600 pixels. (Aykanat et al., Pg. 4 § 2.4 ¶ 1 - 5, Pg. 4 Figs. 3 & 4, Pg. 5 Figs. 5 & 6) Raghu et al. in view of Jacobson et al. in view of Khamene et al. and Aykanat et al. are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al. and Jacobson et al., Aykanat et al. is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the teachings of Aykanat et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Aykanat et al. applied to a similar device. Utilizing a size of less than 1600 pixels for the image, as taught by Aykanat et al., would enhance the combined base device by decreasing the amount of computer memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Furthermore, this modification would have been prompted by the teachings and suggestions of Raghu et al. that the image is resized and that a convolutional neural network (CNN) with pooling layers, such as Vgg16 and Vgg19 CNN models, was utilized since each pooling layer would further reduce the size of the image, see at least page 204 section 2.3 - 2.3.2 and page 206 table 2 of Raghu et al. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the human-indecipherable image would have a size of less than 1600 pixels so as to decrease the amount of computer memory needed to store and process the generated images and reduce the number of computations required to evaluate input patient data in order to improve the ability of the combined base device to quickly and efficiently recognize conditions of patients and facilitate its use on local and/or low-powered computer systems. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. with Aykanat et al. to obtain the invention as specified in claim 10.
Claims 11 - 15 are rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Teixeira U.S. Publication No. 2012/0022350 A1 in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1.
- With regards to claim 11, Raghu et al. disclose a computer-implemented method for recognition of a condition, (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 205 Figs. 1 & 2, Pg. 210 Right-Hand Column First-Full Paragraph - § 5) the method comprising: receiving patient data for a patient during a time period; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.1 - § 2.2, Pg. 204 Table 1, Pg. 210 § 5) converting the patient data to an image having a defined layout and a plurality of pixels, (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2) wherein each of the pixels of the image is defined by at least a first color channel, wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for the patient data and a second channel value represents a second value for the patient data; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2 [The Examiner asserts that the spectrogram image data of Raghu et al. comprises a plurality of pixels that are each defined by at least a first color channel value.]) providing, as input into a trained machine learning model, the image, (Raghu et al., Pg. 202 Abstract, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) wherein the trained machine learning model was trained based on images having the defined layout; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 204 § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) and based on output from the trained machine learning model, generating a predicted condition of the patient. (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 Left-Hand Column First-Full Paragraph - § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) Raghu et al. fail to disclose explicitly receiving control parameters for a patient; converting the control parameters to a human-indecipherable image, wherein each of the pixels is defined by a second color channel, and a second channel value of the first pixel. Pertaining to analogous art, Teixeira discloses a computer-implemented method for recognition of a condition, (Teixeira, Figs. 1 & 19, Pg. 3 ¶ 0063 - 0070, Pg. 4 ¶ 0090 - 0094 and 0110 - 0112, Pg. 7 ¶ 0146 - 054, Pg. 11 ¶ 0222 - 0225, Pg. 17 ¶ 0325 - 0326, Pg. 19 ¶ 0372) the method comprising: receiving patient data and control parameters for a patient during a time period; (Teixeira, Figs. 1 & 14 - 18, Pg. 4 ¶ 0074 - 0082, 0085 - 0090 and, 0105 - 0112, Pg. 7 ¶ 0156 - 0157, Pg. 10 ¶ 0204 - Pg. 11 ¶ 0208, Pg. 14 ¶ 0259 - 0261, Pg. 16 ¶ 0286 - 0305, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0340 - 0345, 0351 - 0352 and 0355 - 0361, Pg. 19 ¶ 0367 - 0372) and converting the patient data and the control parameters to an image. (Teixeira, Figs. 14 - 18, Pg. 14 ¶ 0254 - 0261, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0340 - 0343, 0351, 0357 and 0359 - 0361, Pg. 19 ¶ 0367 - 0372 [“if the second instrument 1420 is an electrocardiograph device, then output from the electrocardiograph device as input to the probabilistic processor 200 optionally includes one or more of: raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as an indication of a previous heart attack”, “fused sensor data 1450 refers to any form, matrix, concatenation, combination, union, representation, or mathematical combination of the data from the multiple instruments 1405” and “electrocardiograph meter 1520 additionally provides time dependent values to the probabilistic processor 200, such as raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as a previous heart attack indication. The pulse oximeter 1510 data and electrocardiograph device 1520 data are optionally fused, as described supra. As discussed, infra, additional input data is provided to the probabilistic processor 200, such as data from an accelerometer 1530, data from a time meter 1550, and/or data from an environment meter 1540, such as temperature, pressure, vibration, humidity, and/or position information. The data is at least partially fused into fused sensor data 1450”]) Teixeira fails to disclose explicitly a human-indecipherable image, wherein each of the pixels is defined by a second color channel, and a second channel value of the first pixel. Pertaining to analogous art, Jacobson et al. disclose a computer-implemented method for recognition of a condition, (Jacobson et al., Figs. 1, 6 & 7, Pg. 1 ¶ 0018 - 0019, Pg. 3 ¶ 0041 - 0042, Pg. 4 ¶ 0044, Pg. 5 ¶ 0067 - 0073, Pg. 7 ¶ 0081) the method comprising: converting the patient data to a human-indecipherable image having a defined layout and a plurality of pixels, (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) wherein each of the pixels of the human-indecipherable image is defined by at least a first channel, wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for the patient data and a second channel value represents a second value for the patient data; (Jacobson et al., Figs. 2 & 3, Pg. 1 ¶ 0019, Pg. 3 ¶ 0033, 0037 - 0040 and 0042, Pg. 4 ¶ 0044 and 0055 - 0056, Pg. 5 ¶ 0067 - 0070 [The Examiner asserts that pixels of an image are defined by at least a first color channel value.]) providing, as input into a trained machine learning model, the human-indecipherable image, (Jacobson et al., Figs. 1 - 3, Pg. 2 ¶ 0020 - 0021, Pg. 3 ¶ 0033 - 0042, Pg. 4 ¶ 0047, Pg. 5 ¶ 0067 - 0070) wherein the trained machine learning model was trained based on images having the defined layout; (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0019 - Pg. 2 ¶ 0021, Pg. 2 ¶ 0029 - 0030, Pg. 3 ¶ 0033 - 0042, Pg. 4 ¶ 0044 and 0047, Pg. 4 ¶ 0054 - Pg. 5 ¶ 0060) and based on output from the trained machine learning model, generating a predicted condition of the patient. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0019 - Pg. 2 ¶ 0021, Pg. 2 ¶ 0030, Pg. 3 ¶ 0036 - 0040 and 0042, Pg. 4 ¶ 0044, 0047 and 0055, Pg. 5 ¶ 0067 - 0070) Jacobson et al. fail to disclose expressly wherein each of the plurality of pixels is defined by a second color channel, and a second channel value of the first pixel. Pertaining to analogous art, Khamene et al. disclose an image having a plurality of pixels, (Khamene et al., Pg. 1 ¶ 0007, Pg. 7 ¶ 0089, Pg. 8 ¶ 0096 - 0099, Pg. 9 ¶ 0105 - 0110, Pg. 12 ¶ 0145, Pg. 13 ¶ 0148 - 0151) wherein each of the pixels of the image is defined by at least a first color channel and a second color channel, (Khamene et al., Pg. 7 ¶ 0089, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 9 ¶ 0109 and 0112, Pg. 12 ¶ 0134, 0140 and 0145, Pg. 13 ¶ 0148 - 0149, 0151 and 0157) wherein a first channel value of a first pixel, of the plurality of pixels, represents a first value for data and a second channel value of the first pixel represents a second value for the data. (Khamene et al., Pg. 1 ¶ 0003 - 0007, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 12 ¶ 0134 and 0145, Pg. 13 ¶ 0148 - 0151 and 0157 [“Graphics hardware is designed to compute color intensities meant to be displayed on a screen (i.e., light intensities for different color channels)”, “Store the fixed image on the GPU using a texture object with four color channels (i.e., RGBA texture)”, “The result will be written to the COLOR-buffer, which stores four values for each pixel, one for each color channel” and “To further speed up these very simple measures, one could also use all four color channels to store the image intensities (i.e., the first gray-scale image value goes into the first pixel's red channel, the second gray-scale value into the green channel, the third goes into the blue channel, the fourth into the alpha channel, the fifth again into the red channel of the second pixel and so on), which results in a texture only one quarter the size of the original image.”]) Raghu et al. and Teixeira are combinable because they are both directed towards medical data processing systems that utilize machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Raghu et al. with the teachings of Teixeira. This modification would have been prompted in order to enhance the base device of Raghu et al. with the well-known and applicable technique Teixeira applied to a similar device. Additionally acquiring and incorporating control parameters into the image, as taught by Teixeira, would enhance the base device of Raghu et al. by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data, as taught and suggested by Teixeira, see at least page 4 paragraphs 0102 - 0108, page 14 paragraphs 0254 - 0258, page 16 paragraphs 0309 - 0311 and page 17 paragraphs 0313 - 0324 of Teixeira. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that control parameters would additionally be acquired and incorporated into the image data so as to improve the ability of the base device of Raghu et al. to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. In addition, Raghu et al. in view of Teixeira and Jacobson et al. are combinable because they are all directed towards medical data processing systems that utilize machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Teixeira with the teachings of Jacobson et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Teixeira with the well-known and applicable technique Jacobson et al. applied to a similar device. Converting the patient data to a human-indecipherable image, as taught by Jacobson et al., would enhance the combined base device by helping safeguard the privacy and security of confidential medical data of patients thereby improving its compliance with the HIPAA privacy rule and enabling it to utilize remote computing resources for various reasons, such as to perform any computationally intensive processing tasks. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the combined base device would convert the patient and control data into a human-indecipherable image so as to help safeguard the privacy and security of confidential medical data of patients and enable it to safely utilize remote computing resources for various tasks. Additionally, Raghu et al. in view of Teixeira in view of Jacobson et al. and Khamene et al. are combinable because they are all directed towards medical data and image processing systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Teixeira in view of Jacobson et al. with the teachings of Khamene et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Teixeira in view of Jacobson et al. with the well-known and applicable technique of Khamene et al. Defining each of the pixels by a plurality of color channels and color channel values, as taught by Khamene et al., would enhance the combined base device by improving its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate as well as expand the number of various types of features it can extract and analyses it can perform on the patient data thereby improving its ability to accurately and reliably recognize conditions of patients. Furthermore, this modification would enhance the combined base device by facilitating its ability to generate, process and analyze color spectrogram images, such as the spectrogram images of Raghu et al., since pixels of the images would be defined by information necessary to depict and represent color data, i.e., a plurality of color channels and color channel values. Moreover, this modification would have been prompted by figures 1, 2 and 5 of Raghu et al. that depict the generated spectrogram image data in color since one of ordinary skill in the art would understand that pixels of color images are commonly represented by values for red, green and blue color channels. In addition, this modification would have been prompted by the teachings and suggestions of Raghu et al. that features such as edges, gradients and textures are extracted from the generated spectrogram image data, see at least page 204 section 2.3, and page 209 left-hand column first-full paragraph - subsection 6 of Raghu et al. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that each of the plurality of pixels of the combined base device would be defined by a plurality of color channels and color channel values in order to improve its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate, such as colorized spectrogram images, and expand the number of various types of features it can extract from the patient data and thereby enhance its ability to accurately and reliably recognize conditions of patients. Therefore, it would have been obvious to combine Raghu et al. with Teixeira, Jacobson et al. and Khamene et al. to obtain the invention as specified in claim 11.
- With regards to claim 12, Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. disclose the computer-implemented method of claim 11. Raghu et al. fail to disclose explicitly wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. Pertaining to analogous art, Teixeira discloses wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. (Teixeira, Figs. 8, 9B, 9E, 9F & 15, Pg. 4 ¶ 0074 - 0082, Pg. 8 ¶ 0167 - 0174, Pg. 10 ¶ 0204 - 0205, Pg. 14 ¶ 0260 - 0261, Pg. 16 ¶ 0286 - 0299, Pg. 18 ¶ 0340 - 0341, 0345 and 0355)
- With regards to claim 13, Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. disclose the computer-implemented method of claim 11. Raghu et al. fail to disclose explicitly wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW. Pertaining to analogous art, Teixeira discloses wherein the patient data includes a mass of the patient, a patient type, a predicted body weight (PBW) of the patient, or an absolute tidal volume limit based on PBW. (Teixeira, Figs. 14 - 18, Pg. 4 ¶ 0111 - 0112, Pg. 14 ¶ 0260 - 0261, Pg. 17 ¶ 0317 - 0321, Pg. 18 ¶ 0341, 0351, 0357, 0359 and 0361 [“if the second instrument 1420 is an electrocardiograph device, then output from the electrocardiograph device as input to the probabilistic processor 200 optionally includes one or more of: raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as an indication of a previous heart attack” and “electrocardiograph meter 1520 additionally provides time dependent values to the probabilistic processor 200, such as raw sensor data, current, voltage, resistance, processed electrocardiograph device signal, and/or an outcome, such as a previous heart attack indication. The pulse oximeter 1510 data and electrocardiograph device 1520 data are optionally fused, as described supra. As discussed, infra, additional input data is provided to the probabilistic processor 200, such as data from an accelerometer 1530, data from a time meter 1550, and/or data from an environment meter 1540, such as temperature, pressure, vibration, humidity, and/or position information. The data is at least partially fused into fused sensor data 1450”])
- With regards to claim 14, Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. disclose the computer-implemented method of claim 11. Raghu et al. fail to disclose expressly wherein the first pixel is further defined by a third channel value. Pertaining to analogous art, Khamene et al. disclose wherein the first pixel is further defined by a third channel value. (Khamene et al., Pg. 7 ¶ 0089, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 9 ¶ 0109 and 0112, Pg. 12 ¶ 0134, 0140 and 0145, Pg. 13 ¶ 0148, 0151 and 0157)
- With regards to claim 15, Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. disclose the computer-implemented method of claim 14. Raghu et al. fail to disclose explicitly wherein the third channel value represents a sign for the patient data. Pertaining to analogous art, Khamene et al. disclose wherein the third channel value represents a sign for the patient data. (Khamene et al., Pg. 8 ¶ 0099 - 0102, Pg. 9 ¶ 0105, Pg. 13 ¶ 0157)
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Teixeira U.S. Publication No. 2012/0022350 A1 in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1 as applied to claim 11 above, and further in view of Murat Aykanat, Özkan Kılıç, Bahar Kurt, and Sevgi Saryal, “Classification of lung sounds using convolutional neural networks”, EURASIP Journal on Image and Video Processing, Vol. 2017, No. 65, Sept. 2017, pages 1 - 9, herein referred to as “Aykanat et al.”.
- With regards to claim 16, Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. disclose the computer-implemented method of claim 11. Raghu et al. fail to disclose explicitly wherein the human-indecipherable image has a size of less than 4000 pixels. Pertaining to analogous art, Jacobson et al. disclose the human-indecipherable image. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) Jacobson et al. fail to disclose explicitly wherein the image has a size of less than 4000 pixels. Pertaining to analogous art, Aykanat et al. disclose wherein the image has a size of less than 4000 pixels. (Aykanat et al., Pg. 4 § 2.4 ¶ 1 - 5, Pg. 4 Figs. 3 & 4, Pg. 5 Figs. 5 & 6) Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. and Aykanat et al. are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al., Teixeira and Jacobson et al., Aykanat et al. is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. with the teachings of Aykanat et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. with the well-known and applicable technique Aykanat et al. applied to a similar device. Utilizing a size of less than 4000 pixels for the image, as taught by Aykanat et al., would enhance the combined base device by decreasing the amount of computer memory needed to store the images generated from various sets of patient data and by reducing the number of computations required to evaluate input patient data thereby improving its ability to quickly and efficiently recognize conditions of patients and enabling it to maintain and process large amounts of patient data on local and/or low-powered computer systems. Furthermore, this modification would have been prompted by the teachings and suggestions of Raghu et al. that the image is resized and that a convolutional neural network (CNN) with pooling layers, such as Vgg16 and Vgg19 CNN models, was utilized since each pooling layer would further reduce the size of the image, see at least page 204 section 2.3 - 2.3.2 and page 206 table 2 of Raghu et al. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the human-indecipherable image would have a size of less than 4000 pixels so as to decrease the amount of computer memory needed to store and process the generated images and reduce the number of computations required to evaluate input patient data in order to improve the ability of the combined base device to quickly and efficiently recognize conditions of patients and facilitate its use on local and/or low-powered computer systems. Therefore, it would have been obvious to combine Raghu et al. in view of Teixeira in view of Jacobson et al. in view of Khamene et al. with Aykanat et al. to obtain the invention as specified in claim 16.
Claims 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Khamene et al. U.S. Publication No. 2005/0271302 A1.
- With regards to claim 17, Raghu et al. disclose a computer-implemented method for recognition of conditions, (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 205 Figs. 1 & 2, Pg. 210 Right-Hand Column First-Full Paragraph - § 5) the method comprising: acquiring patient data during a time period; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.1 - § 2.2, Pg. 204 Table 1, Pg. 210 § 5) generating an image based on the acquired patient data, (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2) wherein the image comprises a pixel having a first color channel, (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2) wherein the first color channel represents a first value of the patient data and a second color channel represents a second value of the patient data; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 203 § 2.3.2, Pg. 205 Figs. 1 & 2, Pg. 206 Table 2 [The Examiner asserts that the spectrogram image data of Raghu et al. comprises a plurality of pixels that are each defined by at least a color channel.]) providing, as input into a trained machine learning model, the generated image, (Raghu et al., Pg. 202 Abstract, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) wherein the trained machine learning model was trained based on images having a same type as the generated image; (Raghu et al., Pg. 202 Abstract, Pg. 203 § 2.2 - Pg. 204 § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) and based on output from the trained machine learning model, generating a predicted condition of the patient. (Raghu et al., Pg. 202 Abstract, Pg. 202 § 1 ¶ 2, Pg. 204 § 2.3 - § 2.4, Pg. 205 Figs. 1 & 2, Pg. 206 Left-Hand Column First-Full Paragraph - § 4 ¶ 1, Pg. 208 Fig. 5, Pg. 210 § 5) Raghu et al. fail to disclose expressly a pixel having a first color channel and a second color channel, wherein the second color channel represents a second value of data. Pertaining to analogous art, Khamene et al. disclose wherein the image comprises a pixel having a first color channel and a second color channel, (Khamene et al., Pg. 7 ¶ 0089, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 9 ¶ 0109 and 0112, Pg. 12 ¶ 0134, 0140 and 0145, Pg. 13 ¶ 0148 - 0149, 0151 and 0157) wherein the first color channel represents a first value of data and the second color channel represents a second value of the data. (Khamene et al., Pg. 1 ¶ 0003 - 0007, Pg. 8 ¶ 0099 - Pg. 9 ¶ 0105, Pg. 12 ¶ 0134 and 0145, Pg. 13 ¶ 0148 - 0151 and 0157 [“Graphics hardware is designed to compute color intensities meant to be displayed on a screen (i.e., light intensities for different color channels)”, “Store the fixed image on the GPU using a texture object with four color channels (i.e., RGBA texture)”, “The result will be written to the COLOR-buffer, which stores four values for each pixel, one for each color channel” and “To further speed up these very simple measures, one could also use all four color channels to store the image intensities (i.e., the first gray-scale image value goes into the first pixel's red channel, the second gray-scale value into the green channel, the third goes into the blue channel, the fourth into the alpha channel, the fifth again into the red channel of the second pixel and so on), which results in a texture only one quarter the size of the original image.”]) Raghu et al. and Khamene et al. are combinable because they are both directed towards medical data and image processing systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Raghu et al. with the teachings of Khamene et al. This modification would have been prompted in order to enhance the base device of Raghu et al. with the well-known and applicable technique of Khamene et al. Utilizing pixels having first and second color channels representing first and second values, respectively, of data, as taught by Khamene et al., would enhance the base device of Raghu et al. by improving its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate, such as color spectrogram images, as well as expand the number of various types of features it can extract and analyses it can perform on the patient data thereby improving its ability to accurately and reliably recognize conditions of patients. Furthermore, this modification would enhance the base device of Raghu et al. by facilitating its ability to generate, process and analyze its color spectrogram images since pixels of image would be defined by information necessary to depict and represent color data, i.e., a plurality of color channels. Moreover, this modification would have been prompted by figures 1, 2 and 5 of Raghu et al. that depict the generated spectrogram image data in color since one of ordinary skill in the art would understand that pixels of color images are commonly represented by values for red, green and blue color channels. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that pixels having at least first and second color channels to respectively represent first and second values of data would be utilized by the base device of Raghu et al. in order to improve its ability to precisely and dependably convert various types and/or values of patient data into an image so as to increase the number of different types of patient data it is able to evaluate, such as colorized spectrogram images, and expand the number of various types of features it can extract from the patient data and thereby enhance its ability to accurately and reliably recognize conditions of patients. Therefore, it would have been obvious to combine Raghu et al. with Khamene et al. to obtain the invention as specified in claim 17.
- With regards to claim 19, Raghu et al. in view of Khamene et al. disclose the computer-implemented method of claim 17, wherein the patient data includes data generated from a sensor. (Raghu et al., Pg. 203 § 2.1, Pg. 204 Table 1)
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Khamene et al. U.S. Publication No. 2005/0271302 A1 as applied to claim 17 above, and further in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1.
- With regards to claim 18, Raghu et al. in view of Khamene et al. disclose the computer-implemented method of claim 17. Raghu et al. fail to disclose expressly wherein the generated image is a human-indecipherable image. Pertaining to analogous art, Jacobson et al. disclose wherein the generated image is a human-indecipherable image. (Jacobson et al., Figs. 1 - 3, Pg. 1 ¶ 0018 - Pg. 2 ¶ 0026, Pg. 3 ¶ 0033, 0036 - 0040 and 0042, Pg. 4 ¶ 0044 - 0046 and 0055 - 0056) Raghu et al. in view of Khamene et al. and Jacobson et al. are combinable because they are all directed towards medical data and image processing systems and, similar to Raghu et al., Jacobson et al. is also directed towards utilizing machine learning models to recognize a condition of a patient. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Khamene et al. with the teachings of Jacobson et al. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Khamene et al. with the well-known and applicable technique Jacobson et al. applied to a similar device. Converting the patient data to a human-indecipherable image, as taught by Jacobson et al., would enhance the combined base device by helping safeguard the privacy and security of confidential medical data of patients thereby improving its compliance with the HIPAA privacy rule and enabling it to utilize remote computing resources for various reasons, such as to perform any computationally intensive processing tasks. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that the combined base device would convert the patient data into a human-indecipherable image so as to help safeguard the privacy and security of confidential medical data of patients and enable it to safely utilize remote computing resources for various tasks. Therefore, it would have been obvious to combine Raghu et al. in view of Khamene et al. with Jacobson et al. to obtain the invention as specified in claim 18.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over S. Raghu, Natarajan Sriraam, Yasin Temel, Shyam Vasudeva Rao, and Pieter L. Kubben. "EEG based multi-class seizure type classification using convolutional neural network and transfer learning", Neural Networks, Vol. 124, Apr. 2020, pages 202 - 212, herein after referred to as “Raghu et al.”, in view of Jacobson et al. U.S. Publication No. 2021/0073393 A1 in view of Khamene et al. U.S. Publication No. 2005/0271302 A1 in view of Murat Aykanat, Özkan Kılıç, Bahar Kurt, and Sevgi Saryal, “Classification of lung sounds using convolutional neural networks”, EURASIP Journal on Image and Video Processing, Vol. 2017, No. 65, Sept. 2017, pages 1 - 9, herein referred to as “Aykanat et al.”, as applied to claim 9 above, and further in view of Teixeira U.S. Publication No. 2012/0022350 A1.
- With regards to claim 20, Raghu et al. in view of Jacobson et al. in view of Khamene et al. in view of Aykanat et al. disclose the computer-implemented method of claim 9. Raghu et al. fail to disclose explicitly wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. Pertaining to analogous art, Teixeira discloses wherein the patient data includes at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement. (Teixeira, Figs. 8, 9B, 9E, 9F & 15, Pg. 4 ¶ 0074 - 0082, Pg. 8 ¶ 0167 - 0174, Pg. 10 ¶ 0204 - 0205, Pg. 14 ¶ 0260 - 0261, Pg. 16 ¶ 0286 - 0299, Pg. 18 ¶ 0340 - 0341, 0345 and 0355) Raghu et al. in view of Jacobson et al. in view of Khamene et al. in view of Aykanat et al. and Teixeira are combinable because they are all directed towards medical data processing systems and, similar to Raghu et al., Jacobson et al. and Aykanat et al., Teixeira is also directed towards utilizing machine learning models to recognize medical conditions. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined teachings of Raghu et al. in view of Jacobson et al. in view of Khamene et al. in view of Aykanat et al. with the teachings of Teixeira. This modification would have been prompted in order to enhance the combined base device of Raghu et al. in view of Jacobson et al. in view of Khamene et al. in view of Aykanat et al. with the well-known and applicable technique Teixeira applied to a similar device. Including at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement in the patient data, as taught by Teixeira, would enhance the combined base device by improving its ability to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data, as taught and suggested by Teixeira, see at least page 4 paragraphs 0102 - 0108, page 14 paragraphs 0254 - 0258, page 16 paragraphs 0309 - 0311 and page 17 paragraphs 0313 - 0324 of Teixeira. This combination could be completed according to well-known techniques in the art and would likely yield predictable results, in that at least one of a carbon dioxide measurement of air exhaled from the patient, a fractional oxygen measurement (FiO2), a heart rate measurement, a blood pressure measurement, or a blood oxygen saturation (SpO2) measurement would be included in the patient data so as to improve the ability of the combined base device to accurately and reliably recognize a condition of a patient since additional data would be available to aid in analysis of the condition of the patient and/or to recognize false positive signals, false negative signals and/or noise in the patient data. Therefore, it would have been obvious to combine Raghu et al. in view of Jacobson et al. in view of Khamene et al. in view of Aykanat et al. with Teixeira to obtain the invention as specified in claim 20.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC RUSH whose telephone number is (571) 270-3017. The examiner can normally be reached 9am - 5pm Monday - Friday.
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, Andrew Bee can be reached at (571) 270 - 5183. 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.
/ERIC RUSH/Primary Examiner, Art Unit 2677
Prosecution Insights