DETAILED ACTION
This is responsive to application 19/324,713 filed on 09/10/2025 in which claims 1-14 are presented for examination.
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 .
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.
Claim 2 is 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 2 recite “by masking at least one grid, among grids”. It is not clear which grids are being pointed here, as there is no mention of “grids” in claim, or in claim that it depends on (claim 1). Basically, a grid is being masked among the grids, but there is no discussion of any sort of grids among, which one grid is masked.
Claims 3 and 11 are rejected based on respected rejected base claim 2.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 1:
Step 1: Is the claim to a process, machine, manufacture or composition of matter?” Yes, it’s a machine(device).
Step 2a Prong 1 (judicial exception)
Step 2A (1): “Does the claim recite an abstract idea, law of nature, or natural phenomenon? Yes , the claim comes under mental processes and mathematical concepts.
Claim 1 recites:
“ A path estimation device comprising: at least one memory storing instructions; and at least one processor configured to access the at least one memory and execute the instructions to: acquire health-related data of a plurality of persons; generate an occurrence probability distribution of health-related data, based on the health-related data at a plurality of time points of each of the plurality of persons; estimate a path between pieces of health-related data of a target person at different time points, on the generated occurrence probability distribution; and output information regarding the estimated path.”
All the limitations above are abstract idea related to the mental process (concepts performed in the human mind (including an observation, evaluation, judgment, opinion)) with the exception of bold and underlined limitations. Claim language pertains to analyzing patient’s data to estimate best path for health improvement. Patient data can be acquired and probability of different health improvements options can be calculated and best path can be estimated(mathematical concept) in a clinical setting. All of this can be easily done using pen and paper and in mind. The process can be done for single or multiple patients.
Step 2A(2): Prong Two: evaluate whether the claim recites additional elements that integrate the exception into a practical application of the exception. NO
The claim does recite additional elements; however they don’t integrate the exception into a practical application of the exception.
path estimation device (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f))
acquire health-related data (Adding insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g) )
memory (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f))
processor (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f))
Step 2B: evaluate whether the claim recites additional elements that amount to an inventive concept (aka “significantly more”) than the recited judicial exception? NO
As discussed previously with respect to Step 2A Prong Two, the additional element in the claim amounts to no more than mere instructions to apply the exception using a generic computer component.
Regarding the claim limitation,“ acquire health-related data” the courts have recognized the computer functions as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (“i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information”); See, MPEP 2106.05 (d)(II)
The same analysis applies here in 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Dependent claims 2-12, further narrows the abstract idea and add the additional elements of “machine learning model”. The probability calculation /generation comes under mathematical concepts.
Under step 2A, prong two, the additional elements don’t integrate the exception into a practical application of the exception as merely adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).
As discussed previously with respect to Step 2A Prong Two, the additional elements in the claim amounts to no more than mere instructions to apply the exception using a generic computer component.
The same analysis applies here in 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Regarding claim 13, it is rejected under the same rationale as claim 1. It is a method claim .
Regarding claim 14, it is rejected under the same rationale as claim 1. In addition , it adds the additional elements of “non-transitory recording medium”, “computer”.
Under step 2A, prong two, the additional elements don’t integrate the exception into a practical application of the exception as merely adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).
As discussed previously with respect to Step 2A Prong Two, the additional elements in the claim amounts to no more than mere instructions to apply the exception using a generic computer component.
The same analysis applies here in 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1,4-6, 8, 10 and 13-14 are rejected under 35 U.S.C. 102a(1) as anticipated by KUNZ et al. ( US 20230386031 A1)
Regarding claim 1, KUNZ teaches a path estimation device comprising:
at least one memory storing instructions(see para 0015);
and at least one processor configured to access the at least one memory and execute the instructions to(see para 0015):
acquire health-related data of a plurality of persons(para, “[0094] At step 406, the system may generate and train the machine learning system using the training data. For example, the machine learning system may use the plurality of training data subsets to learn how histological morphology changes over time (e.g., a histological morphology trajectory) based on ground truth labels, e.g., the digital image(s), associated patient clinical data and, if available, the noninvasive measurements associated with the patient's health and environment, in order to predict one or more unknown histological morphologies and/or an image (e.g., an artificial WSI) representing the one or more unknown histological morphologies at a current time point and/or future time point(s). The training data may comprise morphology images of multiple time points for given patients, which may allow the machine learning system to learn associations between earlier and later morphologies, prognosis, recurrence timelines, diagnosis, mortality risk, etc......”);
generate an occurrence probability distribution of health-related data, based on the health-related data at a plurality of time points of each of the plurality of persons(para, “[0102] At step 458, the digital image(s) and patient clinical data for the target patient may be provided as input to the trained machine learning system determined at step 452. Additionally, the noninvasive measurements associated with the target patient's health and/or environment and/or the risk settings, may be provided to the trained machine learning system if optionally received. Based on the input, the trained machine learning system may at least predict one or more histological morphologies at a current and/or future time point (e.g., predict a current histological morphology trajectory). The predicted one or more histological morphologies may be in accordance with the risk setting provided as input or a default risk setting (e.g., the most likely outcome or the worst outcome, among other examples). A probability may be associated with each of the one or more histological morphologies predicted. In some examples, the trained machine learning system may predict an image representing the current histological morphology trajectory. Additionally or alternatively, in some aspects, the machine learning system may predict one or more histological morphologies at one or more future time points (e.g., predict histological morphology trajectories over time).;
estimate a path between pieces of health-related data of a target person at different time points, on the generated occurrence probability distribution(para, “[0103] For example, a likeliest development of the input variables at the future times points may be estimated (e.g., using a confidence interval of a mean for each variable based on historical data for the target patient) and provided as input to the to the machine learning system to predict one or more histological morphologies for the future time points in accordance with the risk setting (e.g., provided as input or a default risk setting). In some examples, the trained machine learning system may predict images representing the histological morphology trajectories over time. By predicting histological morphologies for the future time points, a user (e.g., a pathologist) may be enabled to adjust one or more values and/or confidence intervals of the input variables to see how the adjustment to the variable effects how the histological morphology changes over time, as described in more detail below. Additionally, the risk setting may be adjustable. The histological morphologies predicted for the current and/or future time point(s) may be associated with a particular region of the tissue, such as an area surrounding the site of biopsy or resection associated with the one or more WSIs received. In other examples, morphology of the whole organ tissue may be predicted to give macro scale and heterogeneity insights (e.g., if input further includes other WSIs of tissue extracted or resected from different areas of the organ and/or or medical images of varying locations of the organ).”
Also, para “[0126] FIGS. 7A-7D illustrate an exemplary graph 700 of a histological trajectory prediction, according to techniques presented herein. The exemplary graph may be for a prostate cancer prediction. The exemplary graph may have an x-axis 702 that indicates time and a y-axis 704 that indicates the particular histological prediction (e.g., a prostrate grade). The graph 700 may depict the histological morphology trajectory that, for example the histology morphology prediction module 206 performs.” Note: Also, see para 0090);
and output information regarding the estimated path(para, “[0090]....... The model described herein may be capable of generating a prediction and expected image at any selected time point. For example, a pathologist may be able to input one or more time points to see predictions for various selected time points. A trajectory vector may define a likeliest path (e.g., prediction) for a given patient. The predicted images at various points of the vector may semantically show a direction of disease progression similar to the actual progression that a patient may have. The outputted model may be a close estimate to a future time point measurement. The predicted trajectory may include estimated values of observed variables such as images or test results at various time points. In one example, the trajectory vector may not be outputted to a user, but rather internally used by the system. In another example, the trajectory vector may be output to a user. In some examples, an image representing the histological morphology trajectory may be predicted.”)
Regarding claim 4, KUNZ teaches The path estimation device according to claim 1. KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: estimate a path to a target point of the health-related data of the target person on the occurrence probability distribution, based on the occurrence probability distribution and a medical care cost estimated in each grid on the occurrence probability distribution(para, “[0102] At step 458, the digital image(s) and patient clinical data for the target patient may be provided as input to the trained machine learning system determined at step 452. Additionally, the noninvasive measurements associated with the target patient's health and/or environment and/or the risk settings, may be provided to the trained machine learning system if optionally received. Based on the input, the trained machine learning system may at least predict one or more histological morphologies at a current and/or future time point (e.g., predict a current histological morphology trajectory). The predicted one or more histological morphologies may be in accordance with the risk setting provided as input or a default risk setting (e.g., the most likely outcome or the worst outcome, among other examples). A probability may be associated with each of the one or more histological morphologies predicted......” Note: Also, see para 0088)
Also, para “[0044]....... As part of patient monitoring, follow up appointments for screening and/or additional biopsies may be scheduled and may range from month intervals (e.g., three, six, nine months) to year intervals dependent on a type of the cancer and a current state of the cancer and/or time elapsed since treatment. Reducing the number of visits or having a large time interval between visits reduces costs, but also increases the chance that the cancer, if it has progressed and/or has recurred, will be detected in a later stage. Also, in addition to clinical factors, a variety of non-clinical factors, such as air quality, water quality, sun exposure, population density, activity level, tobacco use, and/or diet, among other examples, may influence the trajectory of the cancer over time, and thus may be important to account for when monitoring patients. Therefore, a system for automatically predicting the state of the disease over time that accounts for the wide range of factors influencing the trajectory of the disease may be desirable to assist in more effective patient monitoring, including proactive scheduling of follow-up appointments, screenings, and/or procedures.”)
Also, para “[0141] As previously discussed, follow-up visits are a common feature of patient monitoring for various disease types such as cancer. Reducing the number of visits or having a large time interval between visits reduces costs, but also increases the chance that the cancer, if it has progressed and/or has recurred, will be detected in a later stage. The alert generation system may provide an optimal bridge by allowing for a reduced number of visits with larger time intervals in between when there are no indications of progression, but avoiding the consequences of later stage detection by proactively initiating a follow-up (e.g., more frequent than the time interval) when a sign of progression is predicted.”)
Regarding claim 5, KUNZ teaches the path estimation device according to claim 1.
KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: estimate a plurality of paths to a target point of the health-related data of the target person on the occurrence probability distribution( para, “[0102] At step 458, the digital image(s) and patient clinical data for the target patient may be provided as input to the trained machine learning system determined at step 452. Additionally, the noninvasive measurements associated with the target patient's health and/or environment and/or the risk settings, may be provided to the trained machine learning system if optionally received. Based on the input, the trained machine learning system may at least predict one or more histological morphologies at a current and/or future time point (e.g., predict a current histological morphology trajectory). The predicted one or more histological morphologies may be in accordance with the risk setting provided as input or a default risk setting (e.g., the most likely outcome or the worst outcome, among other examples). A probability may be associated with each of the one or more histological morphologies predicted. In some examples, the trained machine learning system may predict an image representing the current histological morphology trajectory. Additionally or alternatively, in some aspects, the machine learning system may predict one or more histological morphologies at one or more future time points (e.g., predict histological morphology trajectories over time).”)
Regarding claim 6, KUNZ teaches the path estimation device according to claim 1.
KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: estimate a path to each of a plurality of target points of the health- related data of the target person on the occurrence probability distribution(para, “[0092] .....The training data may include a plurality of training data subsets. Each training data subset may represent data from a plurality of time points throughout a patient journey (e.g., from screening to diagnosis to treatment, if any, to outcome) for a patient having been monitored for a particular type of disease, such as a particular type of cancer, affecting one or more organs. The training data subset may include digital images. The digital images may include one or more WSIs of histopathological slides prepared from tissue extracted during one or more biopsies and/or one or more resections of the affected organ(s) of the patient throughout the patient journey. Additionally or alternatively, the digital images may also include other types of images (e.g., MRI, CT, PET, mammogram, ultrasound, X-ray, photographs of external anatomy such as skin) of the affected organ(s) and/or region of the affected organ(s) from which the tissue is extracted and/or resected. In some examples, the digital images may be annotated. The training data subset may also include data patient clinical data, such as screening measures taken, diagnosis, treatment(s) (e.g., including type of treatment(s) and dosage, if applicable), outcomes (e.g., remission, recurrence, survival, death), and the like......”)
Regarding claim 8, KUNZ teaches the path estimation device according to claim 1.
KUNZ further teaches further comprising: the at least one processor is further configured to execute the instructions to:
estimate time-series data of the health-related data of each of the plurality of persons, using a machine learning model that estimates time- series data of health-related data at a later time point than input data in chronological order from input health-related data(para, “[0094] At step 406, the system may generate and train the machine learning system using the training data. For example, the machine learning system may use the plurality of training data subsets to learn how histological morphology changes over time (e.g., a histological morphology trajectory) based on ground truth labels, e.g., the digital image(s), associated patient clinical data and, if available, the noninvasive measurements associated with the patient's health and environment, in order to predict one or more unknown histological morphologies and/or an image (e.g., an artificial WSI) representing the one or more unknown histological morphologies at a current time point and/or future time point(s). The training data may comprise morphology images of multiple time points for given patients, which may allow the machine learning system to learn associations between earlier and later morphologies, prognosis, recurrence timelines, diagnosis, mortality risk, etc....”;
and generate an occurrence probability distribution of the health- related data of the plurality of persons, based on the time-series data of the health-related data of each of the plurality of persons(para, “[0094] At step 406, the system may generate and train the machine learning system using the training data. For example, the machine learning system may use the plurality of training data subsets to learn how histological morphology changes over time (e.g., a histological morphology trajectory) based on ground truth labels, e.g., the digital image(s), associated patient clinical data and, if available, the noninvasive measurements associated with the patient's health and environment, in order to predict one or more unknown histological morphologies and/or an image (e.g., an artificial WSI) representing the one or more unknown histological morphologies at a current time point and/or future time point(s). The training data may comprise morphology images of multiple time points for given patients, which may allow the machine learning system to learn associations between earlier and later morphologies, prognosis, recurrence timelines, diagnosis, mortality risk, etc....”)
Regarding claim 10, KUNZ teaches the path estimation device according to claim 1. KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: output a candidate of the estimated path, based on a probability of passing through each path(para, “[0129] The line 714 may be between a confidence bound indicated by line 720 and line 718. The line 714 may correspond to a highest confidence value prediction. The confidence bound may show potential histological morphologies at points within a particular confidence range. For example, the line 714 may correspond to an exemplary highest confidence value of 0.8. The line 720 and line 718 may indicate the highest and lowest histology prediction (e.g., a grade of cancer) within a selected confidence score such as 0.7. The inner area 716 between the lines 720 and line 718 may represent predictions within the selected confidence score. The user may select/set the confidence score, or the system may automatically assign this value such as 0.7.” Note: Also, see para 0127)
Regarding claim 13, KUNZ teaches a path estimation method comprising:
acquiring health-related data of a plurality of persons( para, “[0094] At step 406, the system may generate and train the machine learning system using the training data. For example, the machine learning system may use the plurality of training data subsets to learn how histological morphology changes over time (e.g., a histological morphology trajectory) based on ground truth labels, e.g., the digital image(s), associated patient clinical data and, if available, the noninvasive measurements associated with the patient's health and environment, in order to predict one or more unknown histological morphologies and/or an image (e.g., an artificial WSI) representing the one or more unknown histological morphologies at a current time point and/or future time point(s). The training data may comprise morphology images of multiple time points for given patients, which may allow the machine learning system to learn associations between earlier and later morphologies, prognosis, recurrence timelines, diagnosis, mortality risk, etc......”););
generating an occurrence probability distribution of health-related data, based on the health-related data at a plurality of time points of each of the plurality of persons(para, “[0102] At step 458, the digital image(s) and patient clinical data for the target patient may be provided as input to the trained machine learning system determined at step 452. Additionally, the noninvasive measurements associated with the target patient's health and/or environment and/or the risk settings, may be provided to the trained machine learning system if optionally received. Based on the input, the trained machine learning system may at least predict one or more histological morphologies at a current and/or future time point (e.g., predict a current histological morphology trajectory). The predicted one or more histological morphologies may be in accordance with the risk setting provided as input or a default risk setting (e.g., the most likely outcome or the worst outcome, among other examples). A probability may be associated with each of the one or more histological morphologies predicted. In some examples, the trained machine learning system may predict an image representing the current histological morphology trajectory. Additionally or alternatively, in some aspects, the machine learning system may predict one or more histological morphologies at one or more future time points (e.g., predict histological morphology trajectories over time));
estimating a path between pieces of health-related data of a target person at different time points, on the generated occurrence probability distribution(para, “[0103] For example, a likeliest development of the input variables at the future times points may be estimated (e.g., using a confidence interval of a mean for each variable based on historical data for the target patient) and provided as input to the to the machine learning system to predict one or more histological morphologies for the future time points in accordance with the risk setting (e.g., provided as input or a default risk setting). In some examples, the trained machine learning system may predict images representing the histological morphology trajectories over time. By predicting histological morphologies for the future time points, a user (e.g., a pathologist) may be enabled to adjust one or more values and/or confidence intervals of the input variables to see how the adjustment to the variable effects how the histological morphology changes over time, as described in more detail below. Additionally, the risk setting may be adjustable. The histological morphologies predicted for the current and/or future time point(s) may be associated with a particular region of the tissue, such as an area surrounding the site of biopsy or resection associated with the one or more WSIs received. In other examples, morphology of the whole organ tissue may be predicted to give macro scale and heterogeneity insights (e.g., if input further includes other WSIs of tissue extracted or resected from different areas of the organ and/or or medical images of varying locations of the organ).”
Also, para “[0126] FIGS. 7A-7D illustrate an exemplary graph 700 of a histological trajectory prediction, according to techniques presented herein. The exemplary graph may be for a prostate cancer prediction. The exemplary graph may have an x-axis 702 that indicates time and a y-axis 704 that indicates the particular histological prediction (e.g., a prostrate grade). The graph 700 may depict the histological morphology trajectory that, for example the histology morphology prediction module 206 performs.”);
and outputting information regarding the estimated path(para, “[0090]....... The model described herein may be capable of generating a prediction and expected image at any selected time point. For example, a pathologist may be able to input one or more time points to see predictions for various selected time points. A trajectory vector may define a likeliest path (e.g., prediction) for a given patient. The predicted images at various points of the vector may semantically show a direction of disease progression similar to the actual progression that a patient may have. The outputted model may be a close estimate to a future time point measurement. The predicted trajectory may include estimated values of observed variables such as images or test results at various time points. In one example, the trajectory vector may not be outputted to a user, but rather internally used by the system. In another example, the trajectory vector may be output to a user. In some examples, an image representing the histological morphology trajectory may be predicted.”)
Regarding claim 14, KUNZ teaches a non-transitory recording medium recording a path estimation program for causing a computer to execute:
processing for acquiring health-related data of a plurality of persons(para, “[0094] At step 406, the system may generate and train the machine learning system using the training data. For example, the machine learning system may use the plurality of training data subsets to learn how histological morphology changes over time (e.g., a histological morphology trajectory) based on ground truth labels, e.g., the digital image(s), associated patient clinical data and, if available, the noninvasive measurements associated with the patient's health and environment, in order to predict one or more unknown histological morphologies and/or an image (e.g., an artificial WSI) representing the one or more unknown histological morphologies at a current time point and/or future time point(s). The training data may comprise morphology images of multiple time points for given patients, which may allow the machine learning system to learn associations between earlier and later morphologies, prognosis, recurrence timelines, diagnosis, mortality risk, etc......”);
processing for generating an occurrence probability distribution of health-related data, based on the health-related data at a plurality of time points of each of the plurality of persons((para, “[0102] At step 458, the digital image(s) and patient clinical data for the target patient may be provided as input to the trained machine learning system determined at step 452. Additionally, the noninvasive measurements associated with the target patient's health and/or environment and/or the risk settings, may be provided to the trained machine learning system if optionally received. Based on the input, the trained machine learning system may at least predict one or more histological morphologies at a current and/or future time point (e.g., predict a current histological morphology trajectory). The predicted one or more histological morphologies may be in accordance with the risk setting provided as input or a default risk setting (e.g., the most likely outcome or the worst outcome, among other examples). A probability may be associated with each of the one or more histological morphologies predicted. In some examples, the trained machine learning system may predict an image representing the current histological morphology trajectory. Additionally or alternatively, in some aspects, the machine learning system may predict one or more histological morphologies at one or more future time points (e.g., predict histological morphology trajectories over time).;
processing for estimating a path between pieces of health-related data of a target person at different time points, on the generated occurrence probability distribution(para, “[0103] For example, a likeliest development of the input variables at the future times points may be estimated (e.g., using a confidence interval of a mean for each variable based on historical data for the target patient) and provided as input to the to the machine learning system to predict one or more histological morphologies for the future time points in accordance with the risk setting (e.g., provided as input or a default risk setting). In some examples, the trained machine learning system may predict images representing the histological morphology trajectories over time. By predicting histological morphologies for the future time points, a user (e.g., a pathologist) may be enabled to adjust one or more values and/or confidence intervals of the input variables to see how the adjustment to the variable effects how the histological morphology changes over time, as described in more detail below. Additionally, the risk setting may be adjustable. The histological morphologies predicted for the current and/or future time point(s) may be associated with a particular region of the tissue, such as an area surrounding the site of biopsy or resection associated with the one or more WSIs received. In other examples, morphology of the whole organ tissue may be predicted to give macro scale and heterogeneity insights (e.g., if input further includes other WSIs of tissue extracted or resected from different areas of the organ and/or or medical images of varying locations of the organ).”
Also, para “[0126] FIGS. 7A-7D illustrate an exemplary graph 700 of a histological trajectory prediction, according to techniques presented herein. The exemplary graph may be for a prostate cancer prediction. The exemplary graph may have an x-axis 702 that indicates time and a y-axis 704 that indicates the particular histological prediction (e.g., a prostrate grade). The graph 700 may depict the histological morphology trajectory that, for example the histology morphology prediction module 206 performs.”);
and processing for outputting information regarding the estimated path para, “[0090]....... The model described herein may be capable of generating a prediction and expected image at any selected time point. For example, a pathologist may be able to input one or more time points to see predictions for various selected time points. A trajectory vector may define a likeliest path (e.g., prediction) for a given patient. The predicted images at various points of the vector may semantically show a direction of disease progression similar to the actual progression that a patient may have. The outputted model may be a close estimate to a future time point measurement. The predicted trajectory may include estimated values of observed variables such as images or test results at various time points. In one example, the trajectory vector may not be outputted to a user, but rather internally used by the system. In another example, the trajectory vector may be output to a user. In some examples, an image representing the histological morphology trajectory may be predicted.”)
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 7 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over KUNZ in view of Epstein (US 20240203600 A1)
Regarding claim 7 , KUNZ teaches the path estimation device according to claim 1.
KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: [superimpose the estimated path on the occurrence probability distribution and] outputs the estimated path and the occurrence probability distribution(para, “[0090]..... A trajectory vector may define a likeliest path (e.g., prediction) for a given patient. The predicted images at various points of the vector may semantically show a direction of disease progression similar to the actual progression that a patient may have. The outputted model may be a close estimate to a future time point measurement. The predicted trajectory may include estimated values of observed variables such as images or test results at various time points. In one example, the trajectory vector may not be outputted to a user, but rather internally used by the system. In another example, the trajectory vector may be output to a user. In some examples, an image representing the histological morphology trajectory may be predicted.”)
KUNZ does not explicitly teach superimpose the estimated path on the occurrence probability distribution [and outputs the estimated path and the occurrence probability distribution]
Epstein teaches superimpose the estimated path on the occurrence probability distribution [and outputs the estimated path and the occurrence probability distribution](para, “[0069] Note that the patient path may be represented in the form of a directed graph. In some embodiments, the path is stored and processed as a graph. This creates multiple possible “actual paths” through the graph. One possible advantage of this is that it allows for competing or overlapping but distinct diagnoses to exist; another is that it can represent uncertainty. Furthermore, the branching possibilities become important when revisiting hypotheticals, and in extending the patient path into the future, where multiple branches exist within the model based on outcomes of processes that might only be described statistically, such as with decision state space exploration, described below. Nothing in the term “patient path” should be used to require that the path be a linear chain: the term path is borrowed from the notion of the path integral in quantum physics, which is really a way of representing all possible state transitions. In the simplest case, such as shown in FIG. 6, the multiple graphs are parallel but non-intersecting, and represent different hypotheses chains. Each actual action that occurs is appended to the tail of each chain, thus producing multiple competing adjusted odds or probabilities (600-635 is one chain, 650-675 is the other). In these embodiments, the likelihood adjustments may be different based on the different suspected diagnoses. In the example, the hypothesis of “Only Nasal Bleeding” 600-635 has different L+/L− adjustments than that of “Broken Nose” 650-675, as the path leads towards confirmation of one and rejection of the other. The chains need not be merely dedicated to diagnosis. There are other ways of storing these effects. In another embodiment, the prior probabilities are stored as proper distributions rather than just as one number ....”)
It would have been obvious for a person of ordinary skill in the art to superimposing a path teachings of Epstein into the teachings of KUNZ at the time the application was filed in order for distinct diagnosis to exist. (para, “0069] Note that the patient path may be represented in the form of a directed graph. In some embodiments, the path is stored and processed as a graph. This creates multiple possible “actual paths” through the graph. One possible advantage of this is that it allows for competing or overlapping but distinct diagnoses to exist; another is that it can represent uncertainty....”)
Regarding claim 12 , KUNZ teaches the path estimation device according to claim 1.
KUNZ further teaches wherein the at least one processor is further configured to execute the instructions to: [superimpose a target path of the target person on the occurrence probability distribution and] outputs the target path and the occurrence probability distribution(para, “[0090]..... A trajectory vector may define a likeliest path (e.g., prediction) for a given patient. The predicted images at various points of the vector may semantically show a direction of disease progression similar to the actual progression that a patient may have. The outputted model may be a close estimate to a future time point measurement. The predicted trajectory may include estimated values of observed variables such as images or test results at various time points. In one example, the trajectory vector may not be outputted to a user, but rather internally used by the system. In another example, the trajectory vector may be output to a user. In some examples, an image representing the histological morphology trajectory may be predicted.”)
KUNZ does not explicitly teach superimpose a target path of the target person on the occurrence probability distribution [and outputs the target path and the occurrence probability distribution]
Epstein teaches superimpose a target path of the target person on the occurrence probability distribution [and outputs the target path and the occurrence probability distribution]( (para, “[0069] Note that the patient path may be represented in the form of a directed graph. In some embodiments, the path is stored and processed as a graph. This creates multiple possible “actual paths” through the graph. One possible advantage of this is that it allows for competing or overlapping but distinct diagnoses to exist; another is that it can represent uncertainty. Furthermore, the branching possibilities become important when revisiting hypotheticals, and in extending the patient path into the future, where multiple branches exist within the model based on outcomes of processes that might only be described statistically, such as with decision state space exploration, described below. Nothing in the term “patient path” should be used to require that the path be a linear chain: the term path is borrowed from the notion of the path integral in quantum physics, which is really a way of representing all possible state transitions. In the simplest case, such as shown in FIG. 6, the multiple graphs are parallel but non-intersecting, and represent different hypotheses chains. Each actual action that occurs is appended to the tail of each chain, thus producing multiple competing adjusted odds or probabilities (600-635 is one chain, 650-675 is the other). In these embodiments, the likelihood adjustments may be different based on the different suspected diagnoses. In the example, the hypothesis of “Only Nasal Bleeding” 600-635 has different L+/L− adjustments than that of “Broken Nose” 650-675, as the path leads towards confirmation of one and rejection of the other. The chains need not be merely dedicated to diagnosis. There are other ways of storing these effects. In another embodiment, the prior probabilities are stored as proper distributions rather than just as one number ....”)
It would have been obvious for a person of ordinary skill in the art to superimposing a path teachings of Epstein into the teachings of KUNZ at the time the application was filed in order for distinct diagnosis to exist. (para, “0069] Note that the patient path may be represented in the form of a directed graph. In some embodiments, the path is stored and processed as a graph. This creates multiple possible “actual paths” through the graph. One possible advantage of this is that it allows for competing or overlapping but distinct diagnoses to exist; another is that it can represent uncertainty....”)
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over KUNZ in view of Camacho et al. (US 20130191135 A1)
Regarding claim 9 , KUNZ teaches the path estimation device according to claim 4.
KUNZ does not explicitly teach wherein the at least one processor is further configured to execute the instructions to: estimate a path of which an estimated value of the medical care cost is lower than other paths.(Note: KUNZ does talk about lower cost paths , but for explicit teaching of cost trajectory/path Camacho reference is introduced.
Camacho teaches estimate a path of which an estimated value of the medical care cost is lower than other paths(para, “[0054] As such, FIG. 9B depicts an example healthcare path optimization procedure in connection with the healthcare path shown in FIG. 9A. Steps 901 through 905 correspond with selections 911 through 915, respectively. Based on the information made available through the systems and methods of cost estimation discussed above, professionals that have been found to perform high quality care at relatively low cost, or "optimal professionals" 921 and facilities that have been found to perform high quality care at relatively low cost, or "optimal facilities" 922 may be selected as shown. For example, at selection 911, three optimal preventive care providers are available. Further, at selection 912, two optimal radiological facilities are available. Similar availabilities are shown with respect to surgeons, surgery facilities, and physical therapy (913-915). As such, the wide variety of options is reduced down to a handful of optimal care paths 923 (bold arrows), which may be provided to the healthcare consumer for selection there among. These care paths reflect professional referral patterns and consumer usage patterns. Based on these paths, an optimal path is defined.”)
Also, para “[0040] Various medical treatment paths, or healthcare paths, will now be discussed with respect to the systems and methods of the present disclosure. An example series of treatment paths is shown in FIG. 4A, which depicts a current health state 401, and a desired health state 402. The healthcare consumer, as shown in this figure, is currently at current health state 401, and is desirous of medical treatment that will bring such consumer to desired health state 402. In order to achieve desired health state 402, one of three, for example, series of treatments is possible, shown in the figure as treatment path 410, treatment path 420, and treatment path 430. As previously discussed, any treatment path may have one or more individual treatments, each having its own costs and potential outcome, and may be available at a plurality of service providers by a plurality of healthcare professionals. For example, as shown in FIG. 4A, treatment path 410 includes individual treatments 431 and 432. Treatment path 420 includes just one treatment 433. Further, treatment path 430 includes individual treatments 434 and 435. FIG. 4A merely provides an example depiction of treatment options, and it will be appreciated that the path from a current health state to a desired health state may include more or fewer than three options, each comprising more or fewer than the number of individual treatments shown.”)
It would have been obvious for a person of ordinary skill in the art to incorporate medical care cost teachings of Camacho into the teachings of KUNZ at the time the application was filed in order to select treatment options based on cost estimation. (Abstract, “In one embodiment, disclosed herein is a method for selecting a treatment care path. The method includes receiving identification of a health condition and at least one medical outcome after treatment of the health condition. Further, the method includes identifying at least one medical treatment to achieve the medical outcome, the treatment care path including the at least one or medical treatment. Additionally, the method includes identifying one or more treatment options for each of the at least one medical treatment; and providing a cost estimate for each of the one or more treatment options. Finally, the method includes optimizing the treatment care path by, for each of the at least one medical treatments, selecting one or more treatment options based on the cost estimate thereof.”)
Allowable Subject Matter
Claims 2-3, and 11 are allowed over the prior art. Regarding claim 2 the closest prior art “Brandt (US 20200105405 A1) “ Fig. 3B teaches user selecting/filtering certain cells and as a result disease is predicted. “[0048] Although the user selects a single cell from the available options, the inventive systems and methods consider all cells that have the same or lower probability and risk as the user's choice as selected by the user. For example, if a user selected cell 304 as shown in FIG. 3B, the cells 300, 302, and 304 would be considered to have been selected for purposes of comparing the user's determination with those of another user. This selection corresponds to the shaded area in FIG. 3B which denotes a diagnosis with a high risk but low probability. For example, if a patient complains of chest pain, one of the differential diagnoses might include Acute Coronary Syndrome, or “heart attack.” Although the risk of this possible explanation is high as depicted we subsequently learn that the patient is 14 years old and thus the probability that this is the correct diagnosis may be determined to be low.”
However, the reference doesn’t get into the details of “estimate a new path, by masking at least one grid, among grids on the occurrence probability distribution through which the estimated path passes.” In the context of claimed invention.
Claim 3 inherits all the limitations of claim 2, thus allowable over the prior art for the same rational, and Claim 11 inherits all the limitations of claim 3, thus allowable over the prior art for the same rational.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 11557394 B2 “A Systems, methods, and computer-readable media for providing a decision support solution to medical professionals to optimize medical care through data monitoring and feedback treatment are provided herein. In another embodiment, a computer-implemented method for modeling patient outcomes resulting from treatment in a specific medical area includes receiving patient-specific data associated with a patient, determining a plurality of possible patient states under which the patient can be categorized, a current patient state under which the patient can be categorized and determining probabilities of the patient transitioning from any of the possible patient states to every other possible patient state.”
.Any inquiry concerning this communication or earlier communications from the examiner should be directed to HUMA WASEEM whose telephone number is (571)272-1316. The examiner can normally be reached Monday-Friday(9:00 am - 5 pm) EST.
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, Jason B. Dunham can be reached on (571) 272-8109. 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.
/HUMA WASEEM/Examiner, Art Unit 3686
/JASON B DUNHAM/Supervisory Patent Examiner, Art Unit 3686
Prosecution Insights