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
The amendment filed on 7/31/2026 has been entered. Claims 1-20 remain pending in the application. Applicant’s amendments to the Specification and Claims have overcome the objections previously set forth in the Non-Final Office Action mailed 4/15/2026
Response to Arguments/Remarks re. 35 U.S.C. § 101 Rejections
Applicant’s arguments have been fully considered and are persuasive. The rejection of claims under 35 U.S.C. § 101 has been withdrawn.
Response to Arguments/Remarks re. 35 U.S.C. § 102/103 Rejections
Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Objections
Claim 1 is objected to for the following informalities: “based on the at patient” reads as a typographical error for “based on the patient information”
Claim 8 is objected to for the following informalities: the claim recites “wherein generating the medical prediction is performed by using a second artificial intelligence model trained to output a medical prediction from an input of the second artificial intelligence model”. However, claim 7 recites “generating, using the medical prediction model, a medical prediction”. As such, claim 8 could be interpreted as conflicting with claim 7 (which states the generation is performed using the medical prediction model). The word “further comprising” was not used in claim 8, and as such claim 8 may read as an omission of an element (replacing the usage of the medical prediction model with the usage of a second artificial intelligence model in the generation of “the medical prediction”), which would be improper. See MPEP § 608.01(n)(III), “For example, a dependent claim must be rejected under 35 U.S.C. § 112(d) if it omits an element from the claim upon which it depends…”
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.
Claims 1-20 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
With respect to claim 1, the claim recites “generate…a medical prediction…based on the patient information and the medical image”. The patient information was previously recited as including both the inferred disease risk factor and the medical image. Therefore, it is unclear whether two instances of the same medical image are used by the medical prediction model, or if the model is merely utilizing the medical image within the patient information. For the purposes of compact prosecution, the examiner will read both interpretations as applicable to the prior art.
With respect to claim 7, the claim recites “inputting patient information”, and later recites “based on patient information”. As the second instance of “patient information” is not referred to with antecedent terms, an ambiguity is presented as to whether this constitutes a new class of patient information or the previously referred to patient information. In addition, the claim features a similar problem as claim 1, as the claim recites “patient information and the at least one inferred disease risk factor”, when the prior recited “patient information” already included the inferred disease risk factor. For the purposes of compact prosecution, the examiner will read all possible interpretations as applicable to the prior art.
With respect to claim 16, the same issue of claim 1 is noted.
With respect to claims 2-6, 8-15 and 17-20, they are rejected by virtue of their dependencies on claims 1, 7 and 16 respectively.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 7-8, 10, and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage et. al Mini-DDSM: Mammography-based Automatic Age Estimation (Hereinafter, “Lekemlage”) in view of He et. al A Deep Learning-Based Decision Support Tool for Precision Risk Assessment of Breast Cancer (Hereinafter, “He”)
With respect to claim 1, Lekemlage teaches:
A prediction device comprising:
a memory configured to store instructions ([3])
at least one processor configured to execute the instructions ([3])
wherein the at least one processor is configured to execute the instructions to ([3]):
receive a medical image ([Abstract]; [1]; [2])
input the medical image to a risk factor inference model implemented with a first artificial intelligence model trained to infer at least one disease risk factor for a disease from an input image ([Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; [1]; [2]; Fig. 1)
infer, using the risk factor inference model, at least one disease risk factor for the disease risk based on the medical image ([1] “Age is an important factor in risk prediction of breast cancer”; read in line with page 7, lines 15-20 of the claimed invention’s specification; [2]; [3]; Fig. 1)
output, by the risk factor inference model, the at least one inferred disease risk factor inferred from the medical image (Fig. 3; [3])
Lekemlage does not explicitly teach:
input patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model
generate, using the medical prediction model, a medical prediction including a disease risk of the disease based on the patient information and the medical image
output using the medical prediction model, the medical prediction
However, He, in the same field of endeavor of medical prediction, teaches:
a memory configured to store instructions
at least one processor configured to execute the instructions
wherein the at least one processor is configured to execute the instructions to ([Results] “MATLAB-based method”):
receive a medical image (Fig. 2; [Methods])
input patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model (Fig. 2; [Introduction “Moreover, our observation is that images alone do not capture all necessary information to predict cancer risk”; [Methods, Model Development]; Table 1, “Age”)
generate, using the medical prediction model, a medical prediction including a disease risk of the disease based on the patient information and the medical image (Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Results] “In the validation, we evaluated the model by comparing its predictive accuracy with BI-RADS 4 patient pathology reports”)
output using the medical prediction model, the medical prediction ([Introduction] “We describe the Breast Cancer Risk Calculator (BRISK) tool that outputs a risk assessment and measure to aid in breast cancer biopsy risk assessment and decision in BI-RADS 4 patients”; Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Discussion] “We present the BRISK tool…to achieve precise breast cancer biopsy risk assessment and decision support”; [Conclusion] “BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy”)
PNG
media_image1.png
986
1011
media_image1.png
Greyscale
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage to include the limitations of medical prediction, as taught by He. Doing so would involve using information Lekemlage is already configured to output (e.g., age), and putting it to a further use under a second conventional system. See MPEP § 2143(I)(D) – “Applying a known technique to a known device ready for improvement to yield predictable results”.
Under the plain language of the claim structure recited, the system can be thought of as using a first model to output an age from an image, and then using a second model to output a prediction from the derived age information and image. In other words, the first model merely serves as a specific means by which to obtain the age information. Otherwise, the second model processes the age and image information in a conventional manner. The systems readily integrate, as both are otherwise configured to process mammogram image information (Lekemlage, [Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; He, [Methods, Model Development] “We refer to the first autoencoder as the image autoencoder deep network used for dimension reduction while maintaining the features from the original images (mammogram and ultrasound images))”. A person of ordinary skill in the art would be motivated to combine these systems, for the advantage of utilizing age information where it is otherwise unavailable or unreliable (Lekemlage, [3.2] “Since MIAS has no age values associated with its mammograms, we used our developed model to estimate the age and simulate the missing age entries”).
With respect to claim 2, Lekemlage/He teaches:
The prediction device of claim 1, wherein
the medical prediction model is implemented with a second artificial intelligence model trained to output a medical prediction from an input of the second artificial intelligence model (He, Fig. 2, noting multiple sub-models), or a statistical model configured to output a calculated medical prediction from an input of the statistical model
With respect to claim 3, Lekemlage/He teaches:
The prediction device of claim 1, wherein
the patient factor further includes at least one of a first risk factor input on an interface screen provided to a user terminal, or a second risk factor fetched from a database (He, [Methods, Data]; He, [Methods, Model Development]; He, Fig. 1; He, Fig. 2)
With respect to claim 7, Lekemlage teaches:
A method of operating a prediction device operated by at least one processor ([3]), the method comprising:
receiving a medical image ([Abstract]; Fig. 1; [1]; [2])
inputting the medical image to a risk factor inference model implemented with a first artificial intelligence model trained to infer at least one disease risk factor for a disease from an input image ([Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; [1]; [2]; Fig. 1)
inferring, using the risk factor inference model, at least one inferred disease risk factor inferred from the medical image ([1] “Age is an important factor in risk prediction of breast cancer”; read in line with page 7, lines 15-20 of the claimed invention’s specification; Fig. 1; [2]; [3])
outputting, by the risk factor inference model, the at least one inferred disease risk factor inferred from the medical image (Fig. 3; [3])
Lekemlage does not explicitly teach:
inputting patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model
generating, using the medical prediction model, a medical prediction including a disease risk of the disease based on patient information and the at least one inferred disease risk factor
outputting using the medical prediction model, the medical prediction
However, He, in the same field of endeavor of medical prediction, teaches:
A method of operating a prediction device operated by at least one processor ([Results]), the method comprising:
receiving a medical image (Fig. 2; [Methods])
inputting patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model (Fig. 2; [Introduction “Moreover, our observation is that images alone do not capture all necessary information to predict cancer risk”; [Methods, Model Development]; Table 1, “Age”)
generating, using the medical prediction model, a medical prediction including a disease risk of the disease based on the patient information and at least one inferred disease risk factor (Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Results] “In the validation, we evaluated the model by comparing its predictive accuracy with BI-RADS 4 patient pathology reports”; [Methods])
outputting, using the medical prediction model, the medical prediction ([Introduction] “We describe the Breast Cancer Risk Calculator (BRISK) tool that outputs a risk assessment and measure to aid in breast cancer biopsy risk assessment and decision in BI-RADS 4 patients”; Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Discussion] “We present the BRISK tool…to achieve precise breast cancer biopsy risk assessment and decision support”; [Conclusion] “BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage to include the limitations of medical prediction, as taught by He. Doing so would involve using information Lekemlage is already configured to output (e.g., age), and putting it to a further use under a second conventional system. See MPEP § 2143(I)(D) – “Applying a known technique to a known device ready for improvement to yield predictable results”.
Under the plain language of the claim structure recited, the system can be thought of as using a first model to output an age from an image, and then using a second model to output a prediction from the derived age information and image. In other words, the first model merely serves as a specific means by which to obtain the age information. Otherwise, the second model processes the age and image information in a conventional manner. The systems readily integrate, as both are otherwise configured to process mammogram image information (Lekemlage, [Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; He, [Methods, Model Development] “We refer to the first autoencoder as the image autoencoder deep network used for dimension reduction while maintaining the features from the original images (mammogram and ultrasound images))”. A person of ordinary skill in the art would be motivated to combine these systems, for the advantage of utilizing age information where it is otherwise unavailable or unreliable (Lekemlage, [3.2] “Since MIAS has no age values associated with its mammograms, we used our developed model to estimate the age and simulate the missing age entries”).
With respect to claim 8, Lekemlage/He teaches:
The method of claim 7, wherein
the generating the medical prediction is performed by using a second artificial intelligence model trained to output a medical prediction from an input of the second artificial intelligence (He, Fig. 2) or a statistical model configured to output a calculated medical prediction from an input of the statistical model
With respect to claim 10, Lekemlage/He teaches:
The method of claim 7, further comprising:
adding at least one additional risk factor fetched from a database to the patient information (He, [Methods, Data]; He, [Methods, Model Development]; He, Fig. 1; He, Fig. 2)
With respect to claim 16, Lekemlage teaches:
A computing apparatus, comprising:
a memory configured to store instructions ([3])
at least one processor ([3]) configured to:
receive a medical image ([Abstract]; Fig. 1; [1]; [2])
input the medical image to a risk factor inference model implemented with a first artificial intelligence model trained to infer at least one disease risk factor for a disease from an input image ([Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; [1]; [2]; Fig. 1)
infer, using the risk factor inference model, at least one inferred disease risk factor for the disease based on the medical image ([1] “Age is an important factor in risk prediction of breast cancer”; read in line with page 7, lines 15-20 of the claimed invention’s specification; Fig. 1; [2]; [3])
Lekemlage does not explicitly teach:
input patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model
predict, using the medical prediction model, a disease risk indicating likelihood of disease development of the disease based on the patient information and the medical image
However, He, in the same field of endeavor of medical prediction, teaches:
A computing apparatus, comprising:
a memory configured to store instructions ([Results])
at least one processor configured to ([Results])
receive a medical image (Fig. 2; [Methods])
input patient information including the at least one inferred disease risk factor and the medical image to a medical prediction model (Fig. 2; [Introduction “Moreover, our observation is that images alone do not capture all necessary information to predict cancer risk”; [Methods, Model Development]; Table 1, “Age”)
predict, using the medical prediction model, a disease risk indicating likelihood of disease development of the disease based on the patient information and the medical image (Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Results] “In the validation, we evaluated the model by comparing its predictive accuracy with BI-RADS 4 patient pathology reports”; [Methods]; [Introduction] “We describe the Breast Cancer Risk Calculator (BRISK) tool that outputs a risk assessment and measure to aid in breast cancer biopsy risk assessment and decision in BI-RADS 4 patients”; Fig. 2, “The deep learning architecture of the Breast Cancer Risk Calculator system”; [Discussion] “We present the BRISK tool…to achieve precise breast cancer biopsy risk assessment and decision support”; [Conclusion] “BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy”)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage to include the limitations of medical prediction, as taught by He. Doing so would involve using information Lekemlage is already configured to output (e.g., age), and putting it to a further use under a second conventional system. See MPEP § 2143(I)(D) – “Applying a known technique to a known device ready for improvement to yield predictable results”.
Under the plain language of the claim structure recited, the system can be thought of as using a first model to output an age from an image, and then using a second model to output a prediction from the derived age information and image. In other words, the first model merely serves as a specific means by which to obtain the age information. Otherwise, the second model processes the age and image information in a conventional manner. The systems readily integrate, as both are otherwise configured to process mammogram image information (Lekemlage, [Abstract] “The purpose of this study is to devise an AI-based model for estimating age from mammogram images”; He, [Methods, Model Development] “We refer to the first autoencoder as the image autoencoder deep network used for dimension reduction while maintaining the features from the original images (mammogram and ultrasound images))”. A person of ordinary skill in the art would be motivated to combine these systems, for the advantage of utilizing age information where it is otherwise unavailable or unreliable (Lekemlage, [3.2] “Since MIAS has no age values associated with its mammograms, we used our developed model to estimate the age and simulate the missing age entries”).
With respect to claim 17, Lekemlage/He teaches:
The computing apparatus of claim 16, wherein
the at least one processor is further configured to predict the disease risk, by inputting the at least one inferred disease risk factor to a second artificial intelligence model trained to output a medical prediction from an input of the second artificial intelligence model (He, Fig. 2, wherein any of the three models may be construed as a “second artificial intelligence model” accordingly within the broader “medical prediction model”) or a statistical model configured to output a calculated medical prediction from an input of the statistical model.
With respect to claim 18, Lekemlage/He teaches:
The computing apparatus of claim 16, wherein
the at least one processor is further configured to predict the disease risk by using at least one of: (i) at least one first risk factor input from an interface screen provided to a user terminal, (ii) at least one second risk factor fetched from a database (He, [Methods, Data]; He, [Methods, Model Development]; He, Fig. 1; He, Fig. 2), or (iii) disease information inferred from the medical image, together with the at least one inferred disease risk factor
Claims 4 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Trivizakis et. al A novel deep learning architecture outperforming ‘off-the-shelf’ transfer learning and feature-based methods in the automated assessment of mammographic breast density (Hereinafter, “Trivizakis”)
With respect to claim 4, Lekemlage/He teaches the device of claim 1.
Lekemlage/He does not explicitly teach the further limitations of claim 4.
However, Trivizakis, in the same field of endeavor of medical prediction, teaches:
the patient information further includes disease information inferred from the medical image ([Title]; [Abstract], “In this study, we propose and evaluate advanced machine learning methodologies aiming at an objective and reliable method for breast density scoring from routine mammographic images”; Fig. 2)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to include the limitations of disease information inference. Doing so provides an additional means to obtain additional disease information when it is otherwise unavailable. The systems readily integrate, as mammogram density is yet another consideration of He, Fig. 2 (He, Fig. 2; He, Table 1).
With respect to claim 11, Lekemlage/He teaches:
The method of claim 7, further comprising:
adding disease information (He, [Methods]; He, Fig. 2)
Lekemlage/He does not explicitly teach:
inferred from the medical image to the patient information
However, Trivizakis, in the same field of endeavor of medical prediction, teaches:
inferred from the medical image to the patient information ([Title]; [Abstract], “In this study, we propose and evaluate advanced machine learning methodologies aiming at an objective and reliable method for breast density scoring from routine mammographic images”; Fig. 2)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to include the limitations of disease information inference. Doing so provides an additional means to obtain additional disease information when it is otherwise unavailable. The systems readily integrate, as mammogram density is yet another consideration of He, Fig. 2 (He, Fig. 2; He, Table 1).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Trivizakis and Dudley et. al A Review of User Interface Design for Interacive Machine Learning (Hereinafter, “Dudley”)
With respect to claim 5, Lekemlage/He teaches the device of claim 1.
Lekemlage/He does not explicitly teach the further limitations of claim 5.
However, Trivizakis, in the same field of endeavor of medical prediction, teaches:
The medical prediction model is further configured to receive the at least one inferred disease risk factor after the at least one inferred disease risk factor is confirmed and/or corrected by a user terminal ([Patients and methods, Hyperparameter optimization]; [Results]; discussing training, with understanding that a training process to ensure that the model correctly outputs a disease risk factor involves a “confirm[ation] and/or correct[ion]”)
To the extent Trivizakis does not explicitly teach “by a user terminal”, Dudley ([1]) evidences the possibility of user interaction in the training of a machine learning model via a user interface. It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage/He/Trivizakis to include the limitations of human oversight, as taught by Dudley, for the advantage of increased supervision and human influence in the training process.
Claims 6 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Maher et. al (US 20210166813 A1) (Hereinafter, “Maher”)
With respect to claim 6, Lekemlage/He teaches the device of claim 1
Lekemlage/He does not explicitly teach the further limitations of claim 6
However, Maher, in the same field of endeavor of medical prediction, teaches:
the medical prediction further includes at least one of a recommended scan personalized based on the disease risk and the patient information or timing for performing the recommended scan ([0183])
It would have been obvious to one of ordinary skill in the art, to modify Lekemlage/He to include the limitations of personalized scan recommendations, as taught by Maher. Doing so would provide additional functionality in scheduling, and result in a more complete output to a care provider and patient. The systems are readily compatible, as Maher represents an additional stage after the main processing of Lekemlage/He has already been performed. Maher further integrates with a goal of He – reducing overtreatment through additional scrutiny of results (He, [Discussion] “Finally, we plan to extend these integrative artificial intelligence tools to reduce overdiagnosis and overtreatment of other types of cancer”)
With respect to claim 19, Lekemlage/He teaches the computing apparatus of claim 16
Lekemlage/He does not explicitly teach the further limitations of claim 19
However, Maher teaches:
the at least one processor is further configured to provide at least one of a recommended scan personalized based on the disease risk and patient information including the at least one inferred disease risk factor or timing for performing the recommended scan ([0183])
It would have been obvious to one of ordinary skill in the art, to modify Lekemlage/He to include the limitations of personalized scan recommendations, as taught by Maher. Doing so would provide additional functionality in scheduling, and result in a more complete output to a care provider and patient. The systems are readily compatible, as Maher represents an additional stage after the main processing of Lekemlage/He has already been performed. Maher further integrates with a goal of He – reducing overtreatment through additional scrutiny of results (He, [Discussion] “Finally, we plan to extend these integrative artificial intelligence tools to reduce overdiagnosis and overtreatment of other types of cancer”)
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Nischelwitzer et. al Design and Development of a Mobile Medical Application for the Management of Chronic Diseases: Methods of Improved Data Input for Older People (Hereinafter, “Nischelwitzer)
With regards to claim 9, Lekemlage/He teaches the method of claim 7
Lekemlage/He teaches:
adding the at least one additional risk factor to the patient information (He, [Methods]; He, Fig. 1; He, Fig. 2; He, Table 1)
Lekemlage/He does not explicitly teach:
receiving at least one additional risk factor through an interface screen provided on a user terminal
However, Nischelwitzer, in the same field of endeavor of medical data management, teaches:
receiving at least one additional risk factor through an interface screen provided on a user terminal ([Abstract]; Fig. 2; [3]; [3.2])
adding the at least one additional risk factor to the patient information ([Abstract]; Fig. 2; [3]; [3.2])
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekelmlage/He to include the limitations of user interface input, as taught by Nischelwitzer. Doing so would provide a means for increased patient interaction, and greater facilitate implementation within a personal care system. The systems readily integrate, as Nischelwitzer is configured to receive risk factors already considered by the system of Lekemlage/He (Nischelwitzer, [3.2] “Besides the possibility of enter objectively measured data (body weight…); He, Table 1)
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Trivizakis, Dudley, and Nischelwitzer.
With respect to claim 12, Lekemlage teaches the method of claim 7
Lekemlage/He does not explicitly teach the further limitations of claim 12.
However, Trivizakis, in the same field of endeavor of medical prediction, teaches:
providing the at least one inferred disease risk factor to a user terminal ([Patients and methods, Hyperparameter optimization]; [Results])
wherein generating the medical prediction further comprises confirming and/or correcting the at least one inferred disease risk factor by the user terminal ([Patients and methods, Hyperparameter optimization]; [Results]; discussing training, with understanding that a training process to ensure that the model correctly outputs a disease risk factor involves a “confirm[ation] and/or correct[ion]”)
To the extent Trivizakis does not explicitly teach “by a user terminal”, Dudley ([1]) evidences the possibility of user interaction in the training of a machine learning model via a user interface. It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage/He/Trivizakis to include the limitations of human oversight, as taught by Dudley, for the advantage of increased supervision and human influence in the training process.
To the extent Lekemlage/He/Trivizakis/Dudley does not explicitly teach “to a user terminal”, Nischelwitzer teaches the same ([Abstract]; Fig. 2; [3]; [3.2]). It would have been further obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage/He/Trivizakis/Dudley to include the limitations of user input, as taught by Nischelwitzer, for the advantage of allowing patients to contribute data for the training process of an artificial intelligence.
Claims 13 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Cohen et. al (US 20180068083 A1) (Hereinafter, “Cohen”)
With respect to claim 13, Lekemlage/He teaches the method of claim 7.
Lekemlage/He does not explicitly teach the further limitations of claim 13.
However, Cohen, in the same field of endeavor of medical prediction, teaches:
providing a patient report written based on the medical prediction (Fig. 1B, 180; [0179])
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to include the limitations of written report generation, as taught by Cohen. Doing so would provide an easily distributable summary of results to a care provider, a patient, and any other relevant parties. The systems are readily integrated as this information is capable of being generated by the system of Lekemlage/He and constitutes an after-solution post-processing output.
With respect to claim 15, Lekemlage/He/Cohen teaches:
The method of claim 13, wherein
the patient report further includes
a risk group classified based on the disease risk (Cohen, Fig. 10; Cohen, [0375])
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Lekemlage/He/Cohen in view of Maher.
With respect to claim 14, Lekemlage/He/Cohen teaches the device of claim 13
Lekemlage/He/Cohen does not explicitly teach the further limitations of claim 14
However, Maher, in the same field of endeavor of medical prediction, teaches:
the patient report further includes
at least one of a recommended scan personalized based on the disease risk and the patient information or timing for performing a recommended scan ([0183])
It would have been obvious to one of ordinary skill in the art, to modify Lekemlage/He to include the limitations of personalized scan recommendations, as taught by Maher. Doing so would provide additional functionality in scheduling, and result in a more complete output to a care provider and patient. The systems are readily compatible, as Maher represents an additional stage after the main processing of Lekemlage/He has already been performed. Maher further integrates with a goal of He – reducing overtreatment through additional scrutiny of results (He, [Discussion] “Finally, we plan to extend these integrative artificial intelligence tools to reduce overdiagnosis and overtreatment of other types of cancer”)
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over in view of Lekemlage/He in view of Xu et. al Advances in Smartphone-Based Point-of-Care Diagnostics (Hereinafter, “Xu”)
With respect to claim 20, Lekemlage/He teaches the computing apparatus of claim 16
Lekemlage/He does not explicitly teach the further limitations of claim 20
However, Xu, in the same field of medical information, teaches:
the at least one processor is further configured to provide the at least one inferred disease risk factor and/or the disease risk to a user terminal ([4] “Therefore, in cases where off-site diagnosis and decision-making is needed, smartphone can collect on-site disease data, transmit it to a health center, and receive analytical results”; Fig. 6)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify Lekemlage/He to include the limitations of user terminal interaction, as taught by Xu. Doing so would allow for patients to receive results even when they are physically remote. The systems readily integrate, as the methods of Xu represent a post-processing stage of information Lekemlage/He is already configured to output.
Conclusion
Applicant’s amendment necessitated the new grounds 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 NOAH WILLIAM BOYAR whose telephone number is 571-272- 8392. The examiner can normally be reached 10:00 AM – 6:00 PM EST, 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, Chan Park can be reached at 571-272-7409. 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.
/NOAH W BOYAR/
Examiner, Art Unit 2669
/CHAN S PARK/Supervisory Patent Examiner, Art Unit 2669
Prosecution Insights