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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on June 11, 2026 has been entered.
Response to Amendment
Claims 1, 5, 7, 10-11, 15-16 and 19 have been amended changing the scope and contents of the claim.
Applicant’s amendment filed June 11, 2026 overcomes the following objection/rejection(s) from the last Office Action of January 27, 2026:
Rejections of claims 1-9 and 16-20 under 35 USC § 103
Response to Arguments
Claims 1-9 and 16-20:
Applicant’s arguments, see Remarks, pages 6-7, filed June 11, 2026, with respect to amending the independent claims to overcome the 35 USC § 103 rejections have been fully considered and are persuasive. The 35 USC § 103 rejections of claims 1 and 16 (and the respective dependent claims) has been withdrawn.
Claims 10-15:
Applicant’s arguments with respect to claim(s) 10-15 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. Further, the examiner notes applicant argues, “This model averaging approach, requiring two models, is not taught or suggested by the combination of Schmidt-Erfurth and Chen (page 7).” Claim 10 does not claim two models be present, nor there be a “model averaging” approach. Claim 10 simply requires that the predicted treatment outcome uses the first and second treatment outcomes, not that they are necessarily combined or averaged in any way. For example, one could read predicting a treatment outcome for the same patients at multiple times, and generating a graph across the multiple time points represents an overall predicted treatment outcome.
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.
Claim(s) 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over Schmidt-Erfurth, Ursula, et al. "Machine learning to analyze the prognostic value of current imaging biomarkers in neovascular age-related macular degeneration." Ophthalmology Retina 2.1 (2018): 24-30. (hereinafter Schmidt-Erfurth), and further in view of Chen, S.-C.; Chiu, H.-W.; Chen, C.-C.; Woung, L.-C.; Lo, C.-M. A Novel Machine Learning Algorithm to Automatically Predict Visual Outcomes in Intravitreal Ranibizumab-Treated Patients with Diabetic Macular Edema. J. Clin. Med. 2018, 7, 475. https://doi.org/10.3390/jcm7120475 (hereinafter Chen) and U.S. Patent No. 9,460,400 to DeBruin et al. (hereinafter DeBruin).
Regarding independent claim 10, the rejection of claim 1 applies directly. Additionally, Schmidt-Erfurth discloses A method for predicting a treatment outcome for a subject undergoing a treatment for neovascular age-related macular degeneration (nAMD) (abstract, “To evaluate the potential of machine learning to predict best-corrected visual acuity (BCVA) outcomes from structural and functional assessments during the initiation phase in patients receiving standardized ranibizumab therapy for neovascular age-related macular degeneration (AMD);” page 24, right column, “a more accurate functional prognosis in the management of neovascular AMD.5;” page 25, left column, “The aim of this study is to introduce machine learning methodology to, first, correlate morphologic OCT parameters at baseline to the corresponding visual function in active neovascular disease; and second, predict final BCVA levels after 1 year of standardized anti-VEGF therapy from functional and structural parameters acquired during the initiation phase in a large-scale randomized clinical trial setting”), the method comprising:
generating a first predicted treatment outcome using a deep learning system and three- dimensional imaging data for a retina of the subject (Figure 1, “machine learning;” abstract, “This system performs spatially resolved 3-dimensional segmentation of retinal layers, intraretinal cystoid fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachments (PED). The extracted quantitative OCT biomarkers and BCVA measurements at baseline and months 1, 2, and 3 were used to predict BCVA at 12 months using random forest machine learning”);
Schmidt-Erfurth fails to explicitly disclose as further recited. However, Chen discloses generating a second predicted treatment outcome using a symbolic model and baseline data for the subject (page 3, “The input variables to build a prediction model were sex, age, diabetes type, insulin use, glycated hemoglobin (HbA1c) level, hypertension under treatment, hypercholesterolemia under treatment, lens status, degree of diabetic severity, the baseline macular OCT value (central point, central, inner and outer superior/nasal/inferior/temporal part), the timetable of ranibizumab treatment and baseline visual acuity (Table 1). ”); and
predicting the treatment outcome for the subject undergoing the treatment for (page 2, “ We used ANNs to build decision-support models to predict visual acuity in patients with DME at 52, 78 and 104 weeks after ranibizumab treatment;” predicting of the overall outcome is read as the prediction of multiple time points (i.e. 52, 78 and 104); page 3, “The input variables to build a prediction model were sex, age, diabetes type, insulin use, glycated hemoglobin (HbA1c) level, hypertension under treatment, hypercholesterolemia under treatment, lens status, degree of diabetic severity, the baseline macular OCT value (central point, central, inner and outer superior/nasal/inferior/temporal part), the timetable of ranibizumab treatment and baseline visual acuity (Table 1). ”).
With regard to specifically predicting treatment outcomes for those undergoing nAMD treatment, Chen is directed more toward predicting macular edema treatment outcome. However, Chen clearly proves the base fact that baseline features and patient characteristics can be used to predict outcomes of eye disease treatment. One of ordinary skill in the art before the effective filing date of the invention would be aware the diseases are different, though the structure of the studies and treatment options could be the same. Said in laymans terms, treating one eye disease may lead to understandings of another eye disease. Additionally, Ranibizumab can be used to treat AMD, which one of ordinary skill in the art before the effective filing date would be aware of.
Schmidt-Erfurth is directed toward “the potential of machine learning to predict best-corrected visual acuity (BCVA) outcomes from structural and functional assessments during the initiation phase in patients receiving standardized ranibizumab therapy for neovascular age-related macular degeneration (AMD) (abstract).” Chen is directed toward “ANN-based machine learning algorithm to automatically predict visual outcomes after ranibizumab treatment in diabetic macular edema (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Schmidt-Erfurth and Chen are directed toward similar methods of endeavor of utilizing neural networks to predict outcomes for eye disease patients. Further, Chen allows for incorporating of additional clinical features into the prediction, as opposed to only image based features. It is well known in the art that factors such as age, sex, diabetes, hypertension and other values can have impacts on eye diseases. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to incorporate the teaching of Chen to ensure all features that may contribute to a predicted disease outcome are captured and utilized to generate the most accurate prediction.
Schmidt-Erfurth and Chen in the combination fail to explicitly disclose as further recited. However, DeBruin discloses predicting the treatment outcome for the subject undergoing the treatment for nAMD using the first predicted treatment outcome and the second predicted treatment outcome (column 8, line 52, “The present invention provides a “medical digital expert system”, that is a computer-based mathematical method capable of analyzing neurophysiological information plus a wide range of clinical and laboratory data to predict treatment outcome/efficacy and, optionally, to estimate diagnosis;” column 40, line 67, “For each patient, average of prediction values for all available eyes-open and eyes-closed sessions of EEG recordings are used as the final treatment-response prediction result.”).
As seen above, Schmidt-Erfurth and Chen are directed toward similar methods of endeavor of utilizing neural networks to predict outcomes for eye disease patients. DeBruin is directed toward “A medical digital expert system to predict a patient's response to a variety of treatments (using pre-treatment information) is described (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Schmidt-Erfurth, Chen and DeBruin are directed toward similar methods of endeavor of predicting outcomes. Further, DeBruin allows for analysis of multiple prediction values, to then generate one prediction (column 40, line 67). One of ordinary skill in the art before the effective filing date of the claimed invention would be easily aware averaging of data allows for limiting the impact of outliers. Said differently, one result may be an outlier and only outputting that may give an inaccurate prediction; whereas averaging allows the output to be more accurate. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of DeBruin in order to ensure accuracy of the prediction outcomes, while also limiting the impact of outlier data.
Regarding dependent claim 11, the rejection of claim 10 is incorporated herein. Additionally, DeBruin in the combination further discloses wherein the predicting comprises:
predicting the treatment outcome as a weighted average of the first predicted treatment outcome and the second predicted treatment outcome (column 8, line 52, “The present invention provides a “medical digital expert system”, that is a computer-based mathematical method capable of analyzing neurophysiological information plus a wide range of clinical and laboratory data to predict treatment outcome/efficacy and, optionally, to estimate diagnosis;” column 40, line 67, “For each patient, average of prediction values for all available eyes-open and eyes-closed sessions of EEG recordings are used as the final treatment-response prediction result;” weighted averaging is a type of averaging well known to one of ordinary skill in the art before the effective filing date of the claimed invention).
It is well known in the art before the effective filing date of the claimed invention weighted averaging allows impact of values to be controlled. If there was one prediction method that experts trusted in more, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to increase the weight for that value. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to incorporate the teaching of DeBruin in order to ensure the values which have the most trust or accuracy are weighted highest.
Regarding dependent claim 12, the rejection of claim 10 is incorporated herein. Additionally, Schmidt-Erfurth in the combination further discloses wherein the three-dimensional imaging data comprises optical coherence tomography (OCT) imaging data (Figure 1, “SD-OCT volume scans;” page 25, right column, “SD-OCT was performed by certified operators using the Cirrus HD-OCT III instrument”).
Regarding dependent claim 13, the rejection of claim 10 is incorporated herein. Additionally, Schmidt-Erfurth in the combination further discloses wherein the baseline data comprises at least one of demographic data, a baseline visual acuity measurement (abstract, “The extracted quantitative OCT biomarkers and BCVA measurements at baseline and months 1, 2, and 3 were used to predict BCVA at 12 months using random forest machine learning;” Figure 1, “clinical data; visual acuity”), a baseline central subfield thickness measurement, a baseline low-luminance deficit, or a treatment arm.
Regarding dependent claim 14, the rejection of claim 13 is incorporated herein. Additionally, Chen in the combination further discloses wherein the demographic data comprises at least one of age or gender (Table 1- sex and age are listed).
It is well known in the art that factors such as age, sex, diabetes, hypertension and other values can have impacts on eye diseases. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to incorporate the teaching of Chen to ensure all features that may contribute to a predicted disease outcome are captured and utilized to generate the most accurate prediction.
Claim(s) 15 is rejected under 35 U.S.C. 103 as being unpatentable over Schmidt-Erfurth, Chen and DeBruin as applied to claim 10 above, and further in view of U.S. Patent No. 10,468,142 to Abou Shousha et al. (hereinafter Abou Shousha).
Regarding dependent claim 15, the rejection of claim 10 is incorporated herein. Additionally, Schmidt-Erfurth, Chen and DeBruin in the combination fail to explicitly disclose wherein each of the first predicted treatment outcome, the second predicted treatment outcome, and the treatment outcome includes at least one of a predicted visual acuity measurement, a predicted change in visual acuity, a predicted central subfield thickness, or a predicted reduction in central subfield thickness.
However, Abou Shousha discloses wherein each of the first predicted treatment outcome, the second predicted treatment outcome, and the treatment outcome includes at least one of a predicted visual acuity measurement, a predicted change in visual acuity, a predicted central subfield thickness, or a predicted reduction in central subfield thickness (Figure 11A, two networks are used to combine two different values processed from different inputs to generate one output; paragraph 0131, "As shown in FIG. 11A, the demographic network is configured to receive input data comprising patient data or demographic data and to generate output weights W with respect to one, more, or all y outputs. The final output, which may be generated by a combined output layer for both networks or by an analysis subsystem, as described herein, may be determined by calculating an element-wise product to weight each prediction value y with a prediction value W determined from the patient network taking as input data the patient related data;" paragraph 0130, "FIGS. 11A-11C schematically illustrates embodiments of the system 10 that include augmentation of the AI model 12 with patient data according to various embodiments. Such an AI model 12 may be implemented with or may be included in AI model 12 described with respect to FIGS. 1H & 1J. The patient data may include any type of patient data, such as demographic data or medical data. The AI model 12 has been trained and tuned to process input data to generate a desired output prediction, such as a category likelihood (see, e.g., FIG. 4), a disease prediction (see, e.g., FIG. 5), a severity prediction (see, e.g., FIG. 6), a severity score (see, e.g., FIG. 7), a risk prediction (see, e.g., FIG. 8), an action prediction (see, e.g., FIG. 9), or a treatment prediction (see, e.g., FIG. 10), for example. The input data may include images such as B-scans, color images, thickness maps, heat maps, bullseye maps, structure maps, and/or other input data described herein.")
As noted above, Schmidt-Erfurth, Chen and DeBruin are directed toward predicting outcomes of eye diseases. Further, Schmidt-Erfurth is directed toward "To evaluate the potential of machine learning to predict best-corrected visual acuity (BCVA) outcomes from structural and functional assessments during the initiation phase in patients receiving standardized ranibizumab therapy for neovascular age-related macular degeneration (AMD) (abstract)." Abou Shousha is directed toward "a likelihood that the cornea or anterior segment of the eye represented in the input data will respond favorably or unfavorably to treatment for the predicted corneal or anterior segment condition or disease (paragraph 20). As can be easily seen by one of ordinary skill in the art, Schmidt-Erfurth, Chen, DeBruin and Abou Shousha are directed toward similar methods of endeavor of image analysis for treatment prediction. Further, it is well known in the art at the time of filing the claimed invention that treatment success for a specific treatment can be based on a plurality of features; for example, initial health state, gender, age, sex, etc. Each feature can contribute respectively to an overall treatment success or failure. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Abou Shousha in order to ensure each feature is able to contribute to the overall score, while allowing a user to understand the impact each feature has.
Allowable Subject Matter
Claims 1-9 and 16-20 are allowed.
Claims 1-9 and 16-20:
The following is an examiner’s statement of reasons for allowance: the closest prior arts of record teach methods of performing treatment predictions for patients undergoing nAMD treatment using trained models. However, none of them alone or in any combination teaches generating a first predicted treatment outcome using a deep learning model and 3D imaging data, inputting the first predicted treatment outcome and baseline data into a symbolic model, to then predict a second treatment outcome for a patient being treated for nAMD.
The closest prior art being Schmidt-Erfurth discloses, “machine learning to predict best-corrected visual acuity (BCVA) outcomes from structural and functional assessments during the initiation phase in patients receiving standardized ranibizumab therapy for neovascular age-related macular degeneration (AMD) (abstract).” Further, Schmidt-Erfurth discloses, “The extracted quantitative OCT biomarkers and BCVA measurements at baseline and months 1, 2, and 3 were used to predict BCVA at 12 months using random forest machine learning (abstract).” These values are not combined, and further an initial prediction is not made that is then input into a downstream network and combined with baseline data to generate a second prediction.
Thus, Schmidt-Erfurth fails to disclose generating a first predicted treatment outcome using a deep learning model and 3D imaging data, inputting the first predicted treatment outcome and baseline data into a symbolic model, to then predict a second treatment outcome for a patient being treated for nAMD.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Courtney J. Windsor whose telephone number is (571)272-3956. The examiner can normally be reached Monday - Friday 8:00 - 4:00.
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, John Villecco can be reached at 571-272-7319. 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.
/COURTNEY JOAN NELSON/Primary Examiner, Art Unit 2661
Prosecution Insights