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 .
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 63/319,738, 29/830,662, 63/424,048, 18/183,932, and 18/409,744, fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application. The Applications do not provide support for independent claim limitations, “fine-tune the at least one deep learning model based on at least one of the received patient-reported symptoms, patient records, sensor data, provider notes, and received provider feedback using a reinforcement learning approach; and update at least one of model parameters and the training data for the at least one deep learning model based on at least one of the received patient-reported symptoms, patient records, sensor data, provider notes, and received provider feedback.” (emphasis added). Note the explanation above of claim interpretation according to the Superguide decision.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-19 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-19, respectively, of U.S. Patent No. 12,381,009. Although the claims at issue are not identical, they are not patentably distinct from each other because limitations of the application claims are all present in the corresponding patent claims.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The 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) 1, 3, 12, 10, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over US 20190348178 A1 (Eleftherou) in view of US 20110119212 A1 (De Bruin).
As per claim 1, Eleftherou teaches a computing system for assisting a provider with differential diagnosis and standard of care (Eleftherou: para 2: “differential diagnosis, in which several possible diagnoses are compared and contrasted, must be performed.”;
para 17: “the models 103 may include an associated uncertainty measure, and the diagnosis system 102 may need to determine the current state of a patient through abduction reasoning and/or differential diagnosis performed by the reasoning component 106 to produce the most likely diagnoses to describe the current state of the patient.”), the computing system comprising:
at least one computing processor; and memory comprising instructions that, when executed by the at least one computing processor, enable the computing system to (Eleftherou: Fig. 7: mainly 704, 706, 102, 708, 103):
receive patient information including at least two of patient-reported symptoms, provider notes, patient records, or sensor data from a medical device (Eleftherou: Fig. 1: mainly 110, 111, 112; Figs. 2A, 2B: mainly 201; Fig. 4: mainly 410; Fig. 7: mainly 110;
para 3: “data received from a plurality of data sources… the data comprises medical history data of the patient and observation data received by the computing system during observation of at least one medical professional”;
Para 13: “different data sources, including medical history data, clinical studies, and live settings where medical professionals interact with patients and colleagues”;
Para 16: “The patient data 111 includes data describing a plurality of patients, including without limitation, electronic health records, lab tests, scans, observed parameters, disorders, diseases, and the like. The patient data 111 may include historical data as well as data observed in real time. The interaction data 112 is representative of data observed by the diagnosis system 102 while interacting with medical professionals, such as audio recordings of a doctor speaking to residents captured by a microphone of the computing system 101, clinical notes written by the doctor, images captured by a camera of the computing system, and the like.”;
Para 21 (as shown below): “based on a medical health record in the patient data 111 that a patient's symptoms include hip pain”;
Para 33: “receives input data from the data sources 110_1-N. The input data includes, without limitation, data describing the patient, e.g., patient history data 111. The diagnosis system 102 may also group patient symptoms”;
PNG
media_image1.png
382
830
media_image1.png
Greyscale
Para 24: “input data is received by the diagnosis system 102 from the data sources 110 1_N" For example, the input data may include patient data 111 (e.g., patient complaints, systems, medical history data, etc.), as well as interaction data 112 (e.g., a recording of a case summary presented by
one or more medical professionals)…
the medical professional may dictate notes describing the evaluation of the patient, from which the diagnosis system 102 may extract concepts, grammatical features, and the like…
At block 203, results of one or more patient examinations are received (e.g., lab results, ultrasounds, scans, etc.) by the diagnosis system 102.”;
Para 29 (as shown below): “The diagnosis system 102 is configured to record the audio of the expert conference via a microphone, perform speech to text conversion of the recorded audio, and apply natural language processing (NLP) algorithms to the converted text. Similarly, the diagnosis system 102 may capture images of the expert conference (which may include images of the patient). The diagnosis system 102 may perform analysis of the images to extract information regarding the patient and/or the conference.”;
: The above excerpts show plurality of each of patient-reported symptoms, provider notes, patient records, and sensor data from a medical);
process the patient information using at least one deep learning model to generate a (Eleftherou: paras 2 and 17 (referenced above): “differential diagnosis”;
para 3: “generating, by the computing system and based on the model applied to the received data, a plurality of candidate diagnoses for the patient”;
Para 13: “The models may generally be used to generate candidate diagnoses and/or candidate treatments for patients… deep learning”;
Para 16: “As used herein, a "model" refers to any type of data model, such as machine learning (ML) models, neural networks, decision trees, classifiers, and the like”;
Para 17: “the diagnosis component 105 generates the models 103 based on one or more learning algorithms (e.g., machine learning algorithms, etc.) applied to the data describing the patient attributes and. As such, the models 103 may include an associated uncertainty measure, and the diagnosis system 102 may need to determine the current state of a patient through abduction reasoning and/or differential diagnosis performed by the reasoning component 106 to produce the most likely diagnoses to describe the current state of the patient.”: The features are input into the model which provides differential diagnosis to produce the most likely diagnoses;
Para 18: “The diagnosis component 105 may generally leverage the models 103 to determine one or more candidate diagnoses for a patient, as well as one or more candidate treatments for each candidate diagnosis”;
Para 20 (shown below): “generate one or more candidate diagnoses, and compute a score for each candidate diagnosis. The computed score reflects a degree of confidence that each diagnosis is correct and/or reduces the uncertainty measure associated with the model 103 of the patient.”
Para 35: “deep learning”;
PNG
media_image2.png
351
710
media_image2.png
Greyscale
);
provide the (Eleftherou:
PNG
media_image3.png
574
830
media_image3.png
Greyscale
PNG
media_image4.png
800
830
media_image4.png
Greyscale
Para 22 (as shown above): “output the candidate diagnoses, candidate treatment plans, and the additional data needed to a medical professional for review… diagnosis system 102 is configured to ask questions of the medical professional (e.g., to discuss the additional data needed, etc.) who may then provide responses as interaction data 112.”: This is indicative of an interactive user interface.
PNG
media_image5.png
958
730
media_image5.png
Greyscale
PNG
media_image6.png
421
712
media_image6.png
Greyscale
Para 30: “At block 256, the medical professional selects a diagnosis from the candidate diagnoses, and provides an indication of the selected diagnosis to the diagnosis system 102.”);
receive feedback from the provider indicating an appropriateness of the potential diagnoses and any additional insights (Eleftherou: Para 13 (as referenced below): “the underlying diagnosis model is updated through reinforcement learning, capturing the experience of every encounter by the system with patients and/or medical professionals”;
Para 22 (as shown above): “The medical professional may then select one or more candidate diagnoses, treatments, and additional data observations”;
Para 23 (as shown below): “The reinforcement component 107 applies reinforcement learning to continuously revise the models 103, including the patient state models, to reduce the accuracy and/or uncertainty of the models 103 by interacting with one or more medical professionals and the observed interaction data 112”
PNG
media_image7.png
761
710
media_image7.png
Greyscale
);
fine-tune the at least one deep learning model using a reinforcement learning approach, wherein the fine-tuning is based on the patient information (Eleftherou: Para 13: “a medical diagnosis system which continuously learns based on different data sources, including medical history data, clinical studies, and live settings where medical professionals interact with patients and colleagues. The medical diagnosis system is initially configured with high-quality explicit training to generate one or more models…
The medical diagnosis system continuously updates the diagnosis of a patient based on existing disease models and reasoning as new information about the patient is received. Simultaneously, the underlying diagnosis model is updated through reinforcement learning, capturing the experience of every encounter by the system with patients and/or medical professionals. By using deep learning, abduction reasoning, and reinforcement learning algorithms, the medical diagnosis systems disclosed herein achieve improved performance in diagnosing patients and generating candidate treatments across any number of medical domains.”
Para 14: “the diagnosis system 102 updates the data model of the patient using reinforcement learning based on the results of the emulation and the generated treatment option”;
Para 15: “The reasoning component 106 may update the models 103 using abductive reasoning. The
reinforcement component 107 applies reinforcement learning to revise the models 103 by increasing the accuracy and/or reducing the uncertainty of each model”;
Para 21: “Based on the received data, the diagnosis component 105 may refine the model 103 for the patient to include a current time vector for the patient describing the above attributes as well as any other attributes of the patient.”
PNG
media_image8.png
840
831
media_image8.png
Greyscale
PNG
media_image9.png
639
710
media_image9.png
Greyscale
Para 24: “the process 200 may be repeatedly performed over time to allow the diagnosis system 102 to generate candidate diagnoses and/or treatments as well as refine the models 103…
The diagnosis system 102 may generate (or refine) a model 103 for the patient based on the input data, the professional evaluation, and the examination results”;
Para 27: “The diagnosis system 102 may refine the model 103 of the patient based on the continued monitoring, patient data, tests, and interaction data.”
Para 28: “The diagnosis system 102 may generate (or refine) a model 103 for the patient based on the input data, the professional evaluation, and the examination results”;
Para 32: “One or more learning algorithms may process the data to generate one or more models 103, which may subsequently be revised and refined using reinforcement learning and new data…
At block 330, the diagnosis system 102 applies reinforcement learning to revise the models 103.”;
: the refining, here, is the claimed “fine-tuning”. This involves reinforcement learning based on provider feedback as well as the input patient data referenced above
PNG
media_image10.png
608
826
media_image10.png
Greyscale
PNG
media_image11.png
288
755
media_image11.png
Greyscale
),
wherein the reinforcement learning approach comprises: defining a reward function based on the appropriateness of the potential diagnoses and/or the efficiency of the diagnostic process (Eleftherou: para 13: “the underlying diagnosis model is updated through reinforcement learning, capturing the experience of every encounter by the system with patients and/or medical professionals. By using deep learning, abduction reasoning, and reinforcement learning algorithms, the medical diagnosis systems disclosed herein achieve improved performance in diagnosing patients”;
para 23: “The reinforcement component 107 applies reinforcement learning to continuously revise the models 103, including the patient state models, to reduce the accuracy and/or uncertainty of the models 103 by interacting with one or more medical professionals and the observed interaction data 112.…
the reinforcement component 107 may retrain the models 103 to reflect that a candidate diagnosis of metastatic prostate cancer was indeed correct based on observed data (e.g., the biopsy confirming the cancer).” : the appropriateness (i.e. correct candidate diagnosis) of the potential diagnoses is the reward function;
Para 36: “apply reinforcement learning to revise machine learning models, according to one embodiment. As shown, the method 600 begins at block 610, where the diagnosis system 102 receives input data describing the patient, including any patient history data 111, which may include the candidate diagnoses”;
: the appropriateness of the potential diagnoses is the reward function.
PNG
media_image12.png
413
699
media_image12.png
Greyscale
PNG
media_image13.png
817
705
media_image13.png
Greyscale
PNG
media_image14.png
546
707
media_image14.png
Greyscale
PNG
media_image15.png
367
757
media_image15.png
Greyscale
), and
updating the model parameters to maximize the expected cumulative reward over time (Eleftherou: para 15: “The reinforcement component 107 applies reinforcement learning to revise the models 103 by increasing the accuracy and/or reducing the uncertainty of each model”;
para 23 (excerpt shown above);
para 32: “learning algorithms may process the data to generate one or more models 103, which may subsequently be revised and refined using reinforcement learning and new data”;
para 36: “apply reinforcement learning to revise machine learning models”); and
update at least one of model parameters or training data for the at least one deep learning model based on the patient information and/or the fine-tuning (Eleftherou:
Paras 13, 14, 15, 21 (as referenced above);
Para 17: “the diagnosis component 105 generates the models 103 based on one or more learning algorithms (e.g., machine learning algorithms, etc.) applied to the data describing the patient attributes”;
Para 24: “The diagnosis system 102 may generate (or refine) a model 103 for the patient based on the input data, the professional evaluation, and the examination results”;
Para 28: “The diagnosis system 102 may generate (or refine) a model 103 for the patient based on the input data, the professional evaluation, and the examination results”;
Para 32: “diagnosis system 102 receives explicit training to generate the models 103…
One or more learning algorithms may process the data to generate one or more models 103, which may subsequently be revised and refined using reinforcement learning and new data”;
: Training for generating a deep learning model involves iteratively updating the weights (i.e. parameters). The Professional evaluation results and examination results comprise updated training data for training the model. This also involves the input patient data referenced above
PNG
media_image16.png
571
828
media_image16.png
Greyscale
).
Eleftherou does not teach ranked.
De Bruin teaches ranked list of potential diagnoses and a likelihood score for each potential diagnosis (De Bruin: Para 69: “a machine learning and inference process … a list of diagnostic possibilities rank-ordered by likelihood. The list of recommended treatments with associated response probabilities, and optionally, a list of diagnostic possibilities rank-ordered by probability or likelihood, is then sent to the physician”;
Para 71: “using machine learning and inference methods to estimate the probability of response to a range of treatment possibilities appropriate for the illness diagnosed, and, optionally, to provide a list of diagnostic possibilities rank-ordered by likelihood/probability”;
Para 79: “machine learning… For each patient, it uses the available neuro-psycho-biological information and makes the treatment response prediction to a variety of therapies and, optionally, makes a rank-ordered estimate of diagnosis… a rank-ordered list of diagnostic possibilities”;
Para 81: “a rank-ordered estimate of diagnosis will be sent to the physician/clinician.”).
Thus, it would have been obvious for one of ordinary skill in the art, prior to filing, to implement the teachings of De Bruin into Eleftherou since both Eleftherou and De Bruin suggest a practical solution and field of endeavor of a machine learning system for presenting diagnoses to a physician in general and De Bruin additionally provides teachings that can be incorporated into Eleftherou in that the list of diagnoses is ranked as “to enhance the effectiveness of the physician” (De Bruin: para 71). The teachings of De Bruin can be incorporated into Eleftherou in that the list of diagnoses is ranked. Furthermore, one of ordinary skill in the art could have combined the elements as claimed by known methods and, in combination, each component functions the same as it does separately. One of ordinary skill in the art would have recognized that the results of the combination would be predictable.
As per claim 3, Eleftherou in view De Bruin teaches the system of claim 1, wherein the instructions further cause the system to:
retrieve, for each potential diagnosis, a set of recommended next steps based on a dynamically updated standard of care knowledge base (Eleftherou: See arguments and citations offered in rejecting claim 1 above; Para 14: “The diagnosis system 102 may then emulate a plurality of "what-if' scenarios by applying treatments having known effects to the patient, where the patient is associated with a set of observed conditions. The emulation may further include emulating the treatments and generating an uncertainty measure relative to an unknown future model of the patient (e.g., the patient's condition in the future). The diagnosis system 102 may then generate a
treatment option that minimizes the uncertainty measure and to improve the adjusted risk outcome for the patient.”
Para 18: “The diagnosis component 105 may generally leverage the models 103 to determine one or more candidate diagnoses for a patient, as well as one or more candidate treatments for each candidate diagnosis”;);
prioritize the recommended next steps based on patient-specific factors and the likelihood scores of the potential diagnoses (Eleftherou: See arguments and citations offered in rejecting claim 1 above; Para 14 (as referenced above);
Para 15: “The diagnosis component 105 is representative of a closed-loop system that receives data describing a patient, generates a model 103 for the patient including a diagnosis for the patient, emulates the potential outcomes of different treatments, and selects the best treatment for a diagnosed condition. The "best" treatment may be the treatment that minimizes the uncertainty of the patient model 103 (e.g., reduces the uncertainty below a threshold uncertainty value). The diagnosis component 105 may refine and/or change the treatment over time as the patient is treated, e.g., if a first treatment does not work as desired, the diagnosis component 105 may generate a second treatment for a patient based on the model 103. The reasoning component 106 is configured to apply abduction reasoning to generate hypotheses that can explain known observations, e.g., to generate candidate diagnoses and/or treatments based on a patient's state.”); and
provide the prioritized recommended next steps to the provider via the interactive user interface (Eleftherou: See arguments and citations offered in rejecting claim 1 above;
PNG
media_image4.png
800
830
media_image4.png
Greyscale
PNG
media_image17.png
529
829
media_image17.png
Greyscale
Para 30: “At block 259, the medical professional prescribes a selected one of the candidate treatments, which are provided to the patient”).
As per claim(s) 10 and 12, arguments made in rejecting claim(s) 1 and 3 are analogous, respectively.
As per claim(s) 19, arguments made in rejecting claim(s) 1 are analogous. Eleftherou also teaches a non-transitory computer readable medium comprising instructions that when executed by a processor enable the processor (Eleftherou: See arguments and citations offered in rejecting claim 1 above; Fig. 7: mainly 704, 706, 102, 708, 103).
Claim(s) 2 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Eleftherou in view of De Bruin as applied to claims 1 and 10 above, and further in view of US 20240029901 A1 (Ezhov).
As per claim 2, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the at least one deep learning model comprises at least one of (only one of the following items of the list are required) a convolutional neural network, a recurrent neural network, or a transformer model.
Ezhov teaches these limitations (Ezhov: Para 18: “account for variations in image value intensity depending on at least one of an input or output of volumetric image. In one embodiment, localization is achieved using any one of a fully convolutional network (FCN) or plain classification convolutional neural network (CNN)”;
Para 19: “detect or classify the conditions for each defined anatomical structure within the cropped image by a detection module or classification layer. In one embodiment, the classification is achieved using any one of a fully convolutional network or plain classification convolutional neural network (FCN/CNN)”;
Para 84: “localization is achieved using any one of fully convolutional network or plain classification convolutional neural network (FCN/CNN), such as a V-Net-based fully convolutional neural network.”;
Para 86: “the classification is achieved using any one of a FCN/CNN, such as a DenseNet 3-D convolutional neural network”;
Para 88: “utilizes fully-convolutional network. In another embodiment, the system works on downscaled images”;
Para 90: “a recurrent neural network could be used for step by step prediction of tooth, and keep track of the teeth that were outputted a step before”;
Para 217: “a transformer model during training, generates a script based on the context and relationships of words in the conversations between the practitioner and patient”;
Para 219: “This process is similar to the learning and predicting process of the transformer model, where the system analyzes the input (practitioner-patient conversation), generates a prediction (code or script) and then applies the prediction (personalized medical summary”;
Para 220: “the DAIM module may use large language models or generative AI foundational principles such as principles of transformer architecture, and reinforcement learning to generate a PMS based on transcribed practitioner-patient conversations.”).
Thus, it would have been obvious for one of ordinary skill in the art, prior to filing, to implement the teachings of Ezhov into Eleftherou in view of De Bruin since both Eleftherou in view of De Bruin and Ezhov suggest a practical solution and field of endeavor of a machine learning system for presenting diagnoses to a physician and revising the machine learning mode using reinforcement learning based on the physician feedback in general and Ezhov additionally provides teachings that can be incorporated into Eleftherou in view of De Bruin in that the machine learning model comprises a convolutional neural network, a recurrent neural network, or a transformer model so that “localization is achieved” (para 84), since they are “state-of-the-art 2D instance segmentation deep learning models” (Ezhov: para 123), and “generate personalized medical summary unique to a patient” (para 217). The teachings of Ezhov can be incorporated into Eleftherou in view of De Bruin in that the machine learning model comprises a convolutional neural network, a recurrent neural network, or a transformer model. Furthermore, one of ordinary skill in the art could have combined the elements as claimed by known methods and, in combination, each component functions the same as it does separately. One of ordinary skill in the art would have recognized that the results of the combination would be predictable.
As per claim(s) 11, arguments made in rejecting claim(s) 2 are analogous.
Claim(s) 4-9 and 13-18 are rejected under 35 U.S.C. 103 as being unpatentable over Eleftherou in view of De Bruin as applied to claims 1 and 10 above, and further in view of Official Notice.
As per claim 4, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the sensor data includes at least one of (only one of the following items of the list are required) electrocardiogram, heart rate, blood glucose, blood oxygen percentage/saturation, body temperature, blood pressure, respiratory rate, respiratory volume, heart/lung/abdominal sounds, body fat, muscle tone, images and/or video of the ear/nose/throat, images and/or video of the outer eye or skin and body temperature data.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage of providing common medical sensors important for diagnostics. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that the sensors listed could be incorporated into a device.
As per claim 5, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach preprocessing the patient information further includes:
identifying and correcting errors and inconsistencies in the patient information;
normalizing numerical values to a common scale; and
encoding categorical variables as binary vectors.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage of formatting data to be suitable for applying deep learning. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that preprocessing the patient information further includes: identifying and correcting errors and inconsistencies in the patient information; normalizing numerical values to a common scale; and encoding categorical variables as binary vectors.
As per claim 6, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the instructions further cause the system to:
securely transmit the patient information and provider feedback to a centralized server for aggregation with data from multiple healthcare providers and/or patients; and
periodically update the at least one deep learning model with the aggregated data.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage efficient data handling. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that the data is transmitted as recited above.
As per claim 7, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the visualization of the key factors contributing to each diagnosis includes an attention map highlighting the most relevant features of the patient information for each diagnosis.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage of effective user informing and interaction. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that the user interface is configured as recited above.
As per claim 8, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the interactive user interface allows the provider to adjust the likelihood score threshold for displaying potential diagnoses, and/or at least one of (only one of the following items of the list are required) manually add, remove, upvote or downvote diagnoses from the ranked list.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage of effective user informing and interaction. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that the user interface is configured as recited above.
As per claim 9, Eleftherou in view of De Bruin teaches the system of claim 1. Eleftherou in view of De Bruin does not teach the instructions further cause the system to:
continuously monitor real-time sensor data for signs of patient deterioration; and
alert a provider if the patient's condition deviates from an expected trajectory based on the current diagnosis and treatment plan.
Examiner provides Official Notice that these limitations were well known prior to filing.
One of ordinary skill in the art, prior to filing, would have recognized the advantage of effective user informing and interaction. The teachings of the prior art could have been incorporated into Eleftherou in view of De Bruin in that the user interface is configured as recited above.
As per claim(s) 13-18, arguments made in rejecting claim(s) 4-9 are analogous, respectively.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Atiba Fitzpatrick whose telephone number is (571) 270-5255. The examiner can normally be reached on M-F 10:00am-6pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached on (571) 270-5183. The fax phone number for Atiba Fitzpatrick is (571) 270-6255.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
Atiba Fitzpatrick
/ATIBA O FITZPATRICK/
Primary Examiner, Art Unit 2677
Prosecution Insights