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 .
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 .
Status of Claims
This action is a final rejection
Claims 1, 3-11, 13-20 are pending
Claims 2, 12 were cancelled
Claims 1, 3, 11, 13 were amended
Claims 1, 3-11, 13-20 are rejected under 35 USC § 101
Claims 1, 3-11, 13-20 are rejected under 35 USC § 103
Priority
Acknowledgement is made of Applicant’s claim for a domestic priority date of 12-22-2023
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12-22-2023, 7-22-2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner
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, 3-11, 13-20 are not patent eligible because the claimed invention is directed to an abstract idea without significantly more.
Analysis
First, claims are directed to one or more of the following statutory categories: a process, a machine, a manufacture, and a composition of matter. Regarding claims 1, 3-11, 13-20 the claims recite an abstract idea of “synthesizing time series data and diagnostic data, and generating annotations for electronic records”.
Independent Claims 1 and 11 are rejected under 35 U.S.C 101 based on the following analysis.
-Step 1 (Does the claim fall within a statutory category? YES): claim 1 and 11 recite an apparatus and method for synthesizing time series data and diagnostic data, and generating annotations for electronic records.
-Step 2A Prong One (Does the claim fall within at least one of the groupings of abstract ideas?: YES): The claimed invention:
receive time series data including electrocardiogram (ECG) data;
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly, generating at least one time series label as a function of the time series data comprises generating a first time series label;
comprises using first machine-learning model training data … comprising time series data, … and … comprising at least one time series label
generating a second time series label … comprises second machine learning training data comprising the time series label output … correlated to a second time series label output
generate a first confidence score for the first time series label;
generate a second confidence score for the second time series label;
normalize the first time series label based on the first confidence score;
normalize the second time series label based on the second confidence
determine, using a ... model, at least one recommendation datum for each of the first and second time series label;
generate a time series model comprising the ECG data; and
overlay the at least one recommendation datum onto the time series model wherein overlaying the at least one recommendation datum onto the time series model comprises superimposing information onto a visual representation of a physical model.
and circle, ..., a portion of the time series model as a function of the anomaly
belong to the grouping of mental processes under concepts performed in the human mind (including an observation, evaluation, judgement, opinion) as it recites “synthesizing time series data and diagnostic data, and generating annotations for electronic records”. Alternatively the claims belong to certain methods of organizing human activity under managing personal behavior or relationships or interrelations between people as it recites “synthesizing time series data and diagnostic data, and generating annotations for electronic records”. The justification for the latter is that the claim invention is a method that allows users to access patient’s medical records and receive updated patient information in real time from other users which is a method of managing interactions between people similar to claim 1 of example 42. (refer to MPP 2106.04(a)(2)). Accordingly this claim recites an abstract idea.
-Step 2A Prong Two (Are there additional elements in the claim that imposes a meaningful limit on the abstract idea? NO).
Claim 1 recites:
a memory communicatively connected to the at least a processor, wherein the memory containing instructions configuring the at least a processor
a sensor;
Claim 11 recites:
electronic records
Claims 1 and 11 recite:
a processor
using a first label machine- learning model;
training the first label machine-learning …comprising an input of nodes … one or more intermediate layers of nodes, and an output layer of nodes
using a second label machine learning model,
training a second label machine learning model … from the first label machine-learning model;
using a recommendation machine-learning model;
Amounting to mere instructions to implement an abstract idea on a computer, or merely use a computer as a tool to implement the abstract idea. (refer to MPEP 2106.05(f)). Accordingly, these additional elements, when considered separately and as an ordered combination do not integrate the judicial exception/abstract idea into a “practical application” of the judicial exception because they do not impose any meaningful limit on practicing the judicial exception. Support for this can be found in the specification, paragraphs (0007-0010).
-Step 2B (Does the additional elements of the claim provide an inventive concept?: NO. As discussed previously with respect to Step 2A Prong Two, claim 1 recites:
Claim 1 recites:
a memory communicatively connected to the at least a processor, wherein the memory containing instructions configuring the at least a processor
a sensor
Claim 11 recites:
electronic records
Claims 1 and 11 recite:
a processor
using a first label machine- learning model;
training the first label machine-learning …comprising an input of nodes … one or more intermediate layers of nodes, and an output layer of nodes
using a second label machine learning model,
training a second label machine learning model … from the first label machine-learning model;
using a recommendation machine-learning model;
Amounting to mere instructions to implement an abstract idea on a computer, or merely use a computer as a tool to implement the abstract idea. (refer to MPEP 2106.05(f)) Accordingly, even when viewed as a whole the claim does not provide an inventive concept (significantly more than the abstract idea) and hence the claim is ineligible.
Dependent Claims:
Step 2A Prong One: The following dependent claims recites additional limitations that further define the abstract idea of “synthesizing time series data and diagnostic data, and generating annotations for electronic records”. The claim limitations include:
Claim 4 & 14: wherein determining the at least one recommendation datum comprises generating a recommendation score for each recommendation datum of the at least one recommendation datum;
Claim 5 & 15: wherein each recommendation datum of the at least one recommendation datum comprises at least one affliction datum;
Claim 6 & 16: wherein determining the at least one recommendation datum comprises: generating the at least one affliction datum;
Claim 7 & 17: receive a user input comprising at least one annotation for the time series data;
Claim 8 & 18: wherein overlaying the at least one recommendation datum onto the time series model comprises overlaying, by the at least a processor, the at least one annotation onto the time series model;
Claim 9 & 19: wherein overlaying the at least one recommendation datum onto the time series model comprises overlaying, by the at least a processor, a confidence score for the at least one recommendation;
Claim 10 & 20: wherein overlaying the at least one recommendation datum onto the time series model comprises overlaying a first recommendation datum relating to the first time series label and overlaying a second recommendation datum relating to the second time series label;
Step 2A Prong Two (Are there additional elements in the claim that imposes a meaningful limit on the abstract idea? NO). The following dependent claims recite mere instructions to implement an abstract idea on a computer, or merely use a computer as a tool to implement the abstract idea. (refer to MPEP 2106.05(f)). Accordingly, the claims as a whole do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims include:
Claim 3 & 13: wherein determining the at least one recommendation datum as a function the at least one time series label comprises:
training the recommendation machine leaning model as a function of recommendation training data; and
determining the at least one recommendation datum as a function of the trained recommendation machine learning model;
Claim 6 & 16:
training an affliction machine leaning model as a function of affliction training data;
as a function of the trained affliction machine learning model
Claim 9 & 19: by the at least a processor;
Step 2B (Does the additional elements of the claim provide an inventive concept?: NO). As discussed previously with respect to Step 2A Prong Two, the following dependent claims recite mere instructions to implement an abstract idea on a computer, or merely use a computer as a tool to implement the abstract idea. (refer to MPEP 2106.05(f)). Accordingly, the claim does not provide an inventive concept (significantly more than the abstract idea) and hence the claim is ineligible. The claims include:
Claim 3 & 13: wherein determining the at least one recommendation datum as a function the at least one time series label comprises:
training the recommendation machine leaning model as a function of recommendation training data; and
determining the at least one recommendation datum as a function of the trained recommendation machine learning model;
Claim 6 & 16:
training an affliction machine leaning model as a function of affliction training data;
as a function of the trained affliction machine learning model
Claim 9 & 19: by the at least a processor;
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or
non-obviousness.
Claims 1-20 are rejected under 35 U.S.C. 103 as being un-patentable by Neuman et.al. (US 20200294665 A1) hereinafter “Neuman” in view of Davies et.al (US 20180292978 A1) hereinafter “Davies”; in further view of Dunn et.al (WO 2021050928 A1) hereinafter “Dunn”
Regarding claims 1 & 11 Neuman teaches:
Receive from a sensor (receiving a signal from .. a sensor ) time series data (temporally ordered series of data) [including electrocardiogram (ECG) data]; (See at least [0023] via: “…receive a first training set 108 including a plurality of first data entries, each first data entry of the first training set 108 including at least an element of physiological state data 112…”; in addition see at least [0081] via: “… longitudinal data 816 may include a temporally ordered series of data concerning the same person, …; for instance, longitudinal data 816 may describe a series of blood samples taken one day or one month apart over the course of a year. Longitudinal data 816 may related to a series of samples tracking response of one or more elements of physiological data recorded regarding a person undergoing one or more ameliorative processes…”; in addition see at least [0045] via: “… A physiological sample database 200 may include a plurality of data entries and/or records corresponding to elements of physiological data …”; in addition see at least [0047] via: “…physiological sample database 200 may include a sensor data table 308, which may list samples acquired using one or more sensors..”; in addition see at least [0063] via: “…a physiological test sample may include a signal from at least a sensor configured to detect physiological data of a user and recording the at least a physiological test sample as a function of the signal. At least a sensor 144 may include any electromagnetic sensor, including without limitation electroencephalographic sensors, magnetoencephalographic sensors, electrocardiographic sensors, electromyographic sensors, or the like. …”; in addition see at least [0088] via: “… Recording at least a physiological test sample further comprises receiving a signal from at least a sensor 144 configured to detect physiological data of a user and recording the at least a physiological test sample as a function of the signal; this may be accomplished using any sensor suitable for use as at least a sensor 144 …”).
generate at least one time series label (prognostic labels) as a function of the time series data (first training set 108 including .. physiological state data 112), wherein, the at least one time series label indicates an anomaly generating at least one time series label as a function of the time series data comprises generating a first time series label using a first label machine- learning model (prognostic label learner…using machine-learning processes ) and generating a second time series label (ameliorative process label.. using machine-learning processes) using a second label machine learning model (ameliorative process label learner); (See at least [0023] via: “…receive a first training set 108 including a plurality of first data entries, each first data entry of the first training set 108 including at least an element of physiological state data 112…”; in addition see at least [0038] via: “… classification device 104 may detect further significant categories of physiological data, relationships of such categories to prognostic labels, and/or categories of prognostic labels using machine-learning processes, including without limitation unsupervised machine-learning processes..”; in addition see at least [0039] via: “…classification device 104 may be configured, for instance as part of receiving the first training set 108, to associate at least correlated first prognostic label 116 with at least a category from a list of significant categories of prognostic labels. Significant categories of prognostic labels may be acquired, determined, and/or ranked ... As a non-limiting example, prognostic labels may be organized according to relevance to and/or association with a list of significant conditions…”; in addition see at least [0070] via: “…prognostic label learner 148 and/or classification device 104 may perform an unsupervised machine learning process on first training set 108, which may cluster data of first training set 108 according to detected relationships between elements of the first training set 108, including without limitation correlations of elements of physiological state data 112 to each other and correlations of prognostic labels to each other; such relations may then be combined with supervised machine learning results to add new criteria for prognostic label learner 148 to apply in relating physiological state data 112 to prognostic labels…”; in addition see at least [0074] via: “…continuing to refer to FIG. 1, prognostic label learner 148 may generate a plurality of prognostic labels having different implications for a particular person..”; in addition see at least [0027] via: “…A prognostic label, as described herein, is an element of data identifying and/or describing a current, incipient, or probable future medical condition affecting a person; medical condition may include a particular disease, one or more symptoms associated with a syndrome, a syndrome, and/or any other measure of current or future health and/or healthy aging. At least a prognostic label may be associated with a physical and/or somatic condition, a mental condition such as a mental illness, neurosis, or the like, or any other condition affecting human health that may be associated with one or more elements of physiological state data 112 as described in further detail below. Conditions associated with prognostic labels may include, without limitation one or more diseases, defined for purposes herein as conditions that negatively affect structure and/or function of part or all of an organism. Conditions associated with prognostic labels may include, without limitation, acute or chronic infections, including without limitation infections by bacteria, archaea, viruses, viroids, prions, single-celled eukaryotic organisms such as amoeba, paramecia, trypanosomes, plasmodia, leishmania, and/or fungi, and/or multicellular parasites such as nematodes, arthropods, fungi, or the like. Prognostic labels may be associated with one or more immune disorders, including without limitation immunodeficiencies and/or auto-immune conditions. Prognostic labels may be associated with one or more metabolic disorders. Prognostic labels may be associated with one or more endocrinal disorders. Prognostic labels may be associated with one or more cardiovascular disorders. Prognostic labels may be associated with one or more respiratory disorders. Prognostic labels may be associated with one or more disorders affecting connective tissue. Prognostic labels may be associated with one or more digestive disorders. Prognostic labels may be associated with one or more neurological disorders such as neuromuscular disorders, dementia, or the like. Prognostic labels may be associated with one or more disorders of the excretory system, including without limitation nephrological disorders. Prognostic labels may be associated with one or more liver disorders. Prognostic labels may be associated with one or more disorders of the bones such as osteoporosis. Prognostic labels may be associated with one or more disorders affecting joints, such as osteoarthritis, gout, and/or rheumatoid arthritis. Prognostic labels be associated with one or more cancers, including without limitation carcinomas, lymphomas, leukemias, germ cell tumor cancers, blastomas, and/or sarcomas. Prognostic labels may include descriptors of latent, dormant, and/or apparent disorders, diseases, and/or conditions. Prognostic labels may include descriptors of conditions for which a person may have a higher than average probability of development, such as a condition for which a person may have a “risk factor”; for instance, a person currently suffering from abdominal obesity may have a higher than average probability of developing type II diabetes...”; in addition see at least [0040] via: “…referring to FIG. 1, classification device 104 is designed and configured to receive a second training set 128 including a plurality of second data entries. Each second data entry of the second training set 128 includes at least a second prognostic label 132; at least a second prognostic label 132 may include any label suitable for use as at least a first prognostic label 116 as described above. Each second data entry of the second training set 128 includes at least an ameliorative process label 136 correlated with the at least a second prognostic label 132, where correlation may include any correlation suitable for correlation of at least a first prognostic label 116 to at least an element of physiological data ... As used herein, an ameliorative process label 136 is an identifier, which may include any form of identifier suitable for use as a prognostic label as described above, identifying a process that tends to improve a physical condition of a user, where a physical condition of a user may include, without limitation, any physical condition identifiable using a prognostic label…”; in addition see at least [0075] via: “…ameliorative process label learner 156 may perform any machine-learning process or combination of processes suitable for use by a prognostic label learner 148 as described above..”; in addition see at least [0080] via: “…referring to FIG. 8, ameliorative process label learner 156 may generate a plurality of ameliorative process labels having different implications for a particular person. For instance, where a prognostic label indicates that a person has a magnesium deficiency, various dietary choices may be generated as ameliorative labels associated with correcting the deficiency, such as ameliorative labels associated with consumption of almonds, spinach, and/or dark chocolate, as well as ameliorative labels associated with consumption of magnesium supplements. In such a situation, ameliorative process label learner 156 and/or classification device 104 may perform additional processes to resolve ambiguity)
wherein training the first label machine-learning model comprises using first machine-learning model training data comprising an input of nodes comprising time series data, one or more intermediate layers of nodes, and an output layer of nodes comprising at least one time series label and; (See at least [0086] via: “…Referring now to FIG. 9, an exemplary embodiment of a method 900 of classification to prognostic labels is illustrated. At step 905, a classification device 104 receives training data. Training data includes a first training set 108 including a plurality of first data entries, each first data entry of the first training set 108 including at least an element of physiological state data 112 and at least a correlated prognostic label. In an embodiment, receiving the first training set 108 may include associating the at least an element of physiological state data 112 with at least a category from a list of significant categories of physiological state data 112. Receiving the list of significant categories from at least an expert. Receiving the first training set 108 may include associating the at least correlated first prognostic label 116 with at least a category from a list of significant categories of prognostic labels….”; in addition see at least [0087] via: “…reference to FIG. 9, training data includes a second training set 128 including a plurality of second data entries, each second data entry of the first training set 108 including at least a prognostic label and at least a correlated ameliorative process label 136. In an embodiment, receiving second training set 128 may include associating at least second prognostic label 132 with at least a category from a list of significant categories of prognostic labels. Receiving second training set 128 may include associating at least correlated ameliorative process label 136 with at least a category from a list of significant categories of ameliorative process labels 136. Receiving the second training set 128 may include receiving at least a document describing at least a medical history and extracting at least a second data entry of the plurality of second data entries from the at least a document. Receiving the second training set 128 may include receiving, from at least an expert, at least a second data entry of the plurality of second data entries…”; in addition see at least [0089] via: “…generating the at least a prognostic output may include creating a first machine-learning model 152 relating physiological state data 112 to prognostic labels using the first training set 108 and generating the at least a prognostic output using the first machine-learning model 152…”; in addition see at least [0091] via: “…referring to FIG. 9, generating the at least an ameliorative output may include creating a second machine-learning model 160 relating prognostic labels to ameliorative labels using the second training set 128 and generating the at least an ameliorative output using the second machine-learning model 160. This may be implemented, for instance, as described above in reference to FIG. 1…”; in addition see at least [0020] via: “…referring to FIG. 1, classification device 104 and/or one or more modules operating thereon may be designed and/or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, classification device 104 may be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Classification device 104 may perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations…”; in addition see at least [0083] via: “…reference to FIG. 1, classification device 104 may be configured to display one or more follow-up suggestions at a user output device 164. One of more follow-up suggestions may include, without limitation, suggestions for acquisition of an additional physiological test sample; in an embodiment, additional physiological test sample may be provided to classification device 104, which may trigger repetition of one or more processes as described above, including without limitation generation of prognostic output, refinement or elimination of ambiguous prognostic labels of prognostic output, generation of ameliorative output, and/or refinement or elimination of ambiguous ameliorative labels of ameliorative output. For instance, where a pegboard test result suggests possible diagnoses of Parkinson's disease, Huntington's disease, ALS, and MS as described above, follow-up suggestions may include suggestions to perform endocrinal tests, genetic tests, and/or electromyographic tests; results of such tests may eliminate one or more of the possible diagnoses, such that a subsequently displayed output only lists conditions that have not been eliminated by the follow-up test. Follow-up tests may include any receipt of any physiological sample as described above…”; in addition see at least [0068] via: “…referring to FIG. 1, prognostic label learner 148 may generate prognostic output using alternatively or additional artificial intelligence methods, including without limitation by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created via the process of “training” the network, in which elements from a training dataset are applied to the input nodes, a suitable training algorithm (such as Leyenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning. This network may be trained using first training set 108; the trained network may then be used to apply detected relationships between elements of physiological. state data 112 and prognostic labels..”)
generate a first confidence score for the first time series label; (See at least [0082] via: “….Where output includes multiple prognostic labels … classification device 104 may cause to a user output device 164 to display the multiple labels and/or display data associated therewith; labels may be displayed according to rankings as described above, including without limitation rankings of prognostic labels according to probability of correctness, …. Significance scores, as calculated above, may be used to filter outputs as described in further detail below; for instance, where a number of outputs are generated and automated selection of a smaller number of outputs is desired, outputs corresponding to higher significance scores may be identified as more probable and/or selected for presentation while other outputs corresponding to lower significance scores may be eliminated…”)
generate a second confidence score for the second time series label; (See at least [0080] via: “…ameliorative process label learner 156 may perform one or more lazy learning processes using a more comprehensive set of user data to identify a more probably correct result of the multiple results. Results may be presented and/or retained with rankings, for instance to advise a medical professional of the relative probabilities of various ameliorative labels being correct or ideal choices for a given person; alternatively or additionally, ameliorative labels associated with a probability of success or suitability below a given threshold and/or ameliorative labels contradicting results of the additional process, may be eliminated…”; in addition see at least [0081] via: “….Functions may be compared to each other to rank ameliorative processes; for instance, an ameliorative process associated with a steeper slope in curve representing improvement in a physiological data element, and/or a shallower slope in a curve representing a slower decline, may be ranked higher than an ameliorative process associated with a less steep slope for an improvement curve or a steeper slope for a curve marking a decline. Ameliorative processes associated with a curve and/or terminal data point representing a value that does not associate with a previously detected prognostic label may be ranked higher than one that is not so associated…”; in addition see at least [0082] via: “….Where output includes …multiple ameliorative labels, classification device 104 may cause to a user output device 164 to display the multiple labels and/or display data associated therewith; labels may be displayed according to rankings as described above, including without limitation …, ranking of ameliorative labels according to probability of efficacy, or the like. Significance scores, as calculated above, may be used to filter outputs as described in further detail below; for instance, where a number of outputs are generated and automated selection of a smaller number of outputs is desired, outputs corresponding to higher significance scores may be identified as more probable and/or selected for presentation while other outputs corresponding to lower significance scores may be eliminated…”)
determine, using a recommendation machine-learning model at least one recommendation datum (prognostic output/ ameliorative output) for each of the first and second time series label (prognostic and ameliorative labels); (See at least [0066] via: “…referring to FIG. 1, prognostic label learner 148 may be designed and configured to generate at least a prognostic output by creating at least a first machine-learning model 152 relating physiological state data 112 to prognostic labels using the first training set 108 and generating the at least a prognostic output using the first machine-learning model 152; at least a first machine-learning model 152 may include one or more models that determine a mathematical relationship between physiological state data 112 and prognostic labels…; in addition see at least [0091] via: “…referring to FIG. 9, generating the at least an ameliorative output may include creating a second machine learning model 160 relating prognostic labels to ameliorative labels using the second training set 128 and generating the at least an ameliorative output using the second machine-learning model 160. This may be implemented, for instance, as described above in reference to FIG. 1…”)
generate a time series model (creating a first machine-learning model 152/ creating a second machine-learning model 160; relating physiological state data 112 to prognostic labels/ relating prognostic labels to ameliorative labels ) [comprising the ECG data; (See at least [0075] via: “…generating the at least a prognostic output may include creating a first machine-learning model 152 relating physiological state data 112 to prognostic labels using the first training set 108 and generating the at least a prognostic output using the first machine-learning model 152 …”; in addition see at least [0091] via: “…creating a second machine-learning model 160 relating prognostic labels to ameliorative labels using the second training set 128 and generating the at least an ameliorative output using the second machine-learning model 160 relating prognostic labels to ameliorative labels using the second training set 128 and generate the at least an ameliorative output using the second machine-learning model 160;… ameliorative process label learner 156 may use data from first training set 108 ..”)
However, Neuman is silent regarding the following limitations that are taught by Davies
electrocardiogram (ECG) data (See at least [0042] via: “…The set of electrocardiogram (ECG) data 64 comprises data obtained from an ECG at an associated time, which may be a time at which data acquisition started. …The set of echocardiogram imaging data 66 comprises data obtained from an echocardiogram at an associated time. Each of the ECG data 64, … and echocardiogram imaging data 6 is positioned relative to the time line axis 60 in accordance with its associated time. This data is primarily relevant for a cardiology patient...”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Neuman to incorporate the teachings of Davies. Those in the art would have recognized that Neuman’s teaching regarding a classification device configured to receive training data including a first training set composed of physiological state data and a correlated prognostic labels and a second training set composed of a second prognostic label correlated with an ameliorative process label which subsequently, by use of machine learning models, transmit an output including at least a prognostic output and at least an ameliorative output to a user device, could be modified to include Davies’ teaching regarding electrocardiogram (ECG) data 64 comprises data obtained from an ECG to obtain medical data relating to a patient’s heart condition. This combination would be beneficial to medical personnel when reviewing the heart condition of a patient that includes recommendation regarding the prognosis and ameliorative actions regarding the patient in time.
overlay the at least one recommendation datum (clinical notes) onto the time series (echocardiogram imaging data ) model wherein overlaying the at least one recommendation datum onto the time series model comprises superimposing information onto a visual representation of a physical model. (See at least [0095] via: “…FIG. 4 shows a display of medical data in a plurality of different views, which in the embodiment of FIG. 4 comprise a plurality of presentation panels 110, 112, 114, 116, 118..,”; in addition see at least [0097] via: “…Presentation panel 112 is a table of clinical notes. A simplified version of the table of clinical notes is shown in FIG. 4. In practice the clinical notes may be considerable longer and more detailed. Column 120 shows the date and time of each clinical note. Column 122 shows the clinician who recorded the clinical note. Column 124 shows the narrative text of the clinical note...”; in addition see at least [0098] via: “…Presentation panel 114 is a plot of blood chloride results. Presentation panel 118 is a plot of blood pressure results. Presentation panel 118 shows patient identifying information. Presentation panels 110, 114, 116, 118 are similar to presentation panels 50, 54, 56, 58 of FIG. 3..”; in addition see at least [0099] via: “…In the embodiment of FIG. 4, a user indicates a reference to a vital sign measurement of presentation panel 112 by using a cursor 100 to hover over the reference to the vital sign measurement in one of the clinical notes shown on presentation panel 112..”; in addition see at least [0100] via: “…The selection circuitry 24 receives the selection of the vital sign measurement. The vital signal measurement has a corresponding time of record, which may be referred to as a timestamp. The highlighting circuitry highlights the time of record on other panels that show a time based display, which in the embodiment of FIG. 4 are the time line view of presentation panel 110, and the plots of presentation panels 114 and 116. The time of record is highlighted on the other time based panels for comparison of different clinical data at the same point in time…”; in addition see at least [0101] via: “…The time of record is shown in each of presentation panels 110, 114 and 116 using a dotted line 126. In other embodiments, any suitable indicator may be used to indicate the time of record..”; in addition see at least [0039] via: “… shown in FIG. 3, the boxes representing the medical records comprise boxes representing clinical notes 62; nursing notes 63; sets of imaging data (electrocardiogram data 64, chest X-ray imaging data 65 and echocardiogram data 66); sets of imaging measurement data 67; and sets of lab result data 68. In the description below, references to the medical records 62, 63, . . . 68 in the first presentation panel 50 may refer both to the medical records themselves and to the boxes representative of those medical records in the first presentation panel 50. The diamonds shown in the figure in this embodiment indicate a giving of medication to the patient or a change in any kind of medicine administration..”; in addition see at least [0040] via: “…Each clinical note 62 comprises text information regarding an encounter between the patient and a clinician or regarding any other suitable event or analysis, for example text information relating to test results received from a laboratory or other testing facility. The text information is not shown in presentation panel 50, which shows each clinical note 62 as a respective box. Each nursing note 63 comprises text information regarding an encounter between the patient and a nurse. In other embodiments, the term clinical note or medical note may encompass nursing notes or notes recorded by any medical professional..”; in addition see at least [0041] via: “…Each clinical note 62 or nursing note 83 has at least one associated time, for example the time at which the encounter recorded in the note took place and/or the time at which the note was recorded. The clinical notes 62 and nursing notes 63 are positioned relative to the time line axis 60 in accordance with their associated times…”; in addition see at least [0042] via: “…The set of electrocardiogram (ECG) data 64 comprises data obtained from an ECG at an associated time, which may be a time at which data acquisition started. The set of chest X-ray imaging data 65 comprises data obtained from a chest X-ray at an associated time. The set of echocardiogram imaging data 66 comprises data obtained from an echocardiogram at an associated time. Each of the ECG data 64, chest X-ray imaging data 65, and echocardiogram imaging data 6 is positioned relative to the time line axis 60 in accordance with its associated time. This data is primarily relevant for a cardiology patient. Different types of data may be presented for different clinical cases, for example stroke patients..”) The Examiner notes that Davies’ art teaches an apparatus for the presentation of medical data. In the case of figures 3 and figure 4 the panels to the left of the chart relate to clinical notes that relate to the charts showing concentration of chlorine and blood pressure vs time. This represents an overlay of recommendation datum onto the time series chart. The clinical notes related to the EKG chart would be obtained by selecting clinical notes 62; nursing notes 63; sets of imaging data (electrocardiogram data 64, chest X-ray imaging data 65 and echocardiogram data 66) as shown in fig. 3.
PNG
media_image1.png
814
552
media_image1.png
Greyscale
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Neuman to incorporate the teachings of Davies. Those in the art would have recognized that Neuman’s teaching regarding a classification device configured to receive training data including a first training set composed of physiological state data and a correlated prognostic labels and a second training set composed of a second prognostic label correlated with an ameliorative process label which subsequently, by use of machine learning models, transmit an output including at least a prognostic output and at least an ameliorative output to a user device, could be modified to include Davies’ teaching regarding a medical data presentation apparatus used to obtain medical data relating to a patient and to display some of the medical data. This combination would be very beneficial to medical personnel when reviewing patient, in helping them obtain in an efficient manner information about a patient that includes a plot of the time series test results together with recommendation and annotated notes regarding the prognosis and ameliorative actions regarding the patient.
and circle, using the at least a processor, a portion of the time series model as a function of the anomaly (See at least [117] via: “...FIG. 6 shows a plurality of presentation panels 140, 142, 144, 146, 148, which are similar to the presentation panels 110, 112, 114, 116 and 118 but represent a different range of time. Presentation panel 144 shows a different lab result (platelet count) from that shown in presentation panel 114...”; in addition see at least [118] via: “...In the embodiment of FIG. 6, upon hovering on a lab record 68 using cursor 100 in the time line of presentation panel 140, a clinical note referring to the same record is highlighted. In response to the selection, the highlighting circuitry 28 searches for references to the lab record 68 and finds a text reference in the clinical notes of presentation panel 142 and a data point in the plot of presentation panel 144...”; in addition see at least [119] via: “...The highlighting circuitry 28 highlights the text reference by changing the background color of a region 150 surrounding the text reference. In the present embodiment, the text reference within the clinical note is highlighted. In other embodiments, the entire clinical note may be highlighted. However, by highlighting the text reference instead of or in addition to the entire clinical note, the clinician may find it easier to navigate the data provided (especially since in practice the clinical notes may be much longer than the clinical notes shown in FIG. 6). In some embodiments, natural language processing may be used to generate text for output based on the clinical note or a part of the clinical note...”; in addition see at least [120] via: “...The highlighting circuitry 28 also highlights the data point in presentation panel 144 by using a flashing pulse, which is represented on FIG. 6 by circle 102..”) The Examiner interprets circle 102 in panel 144 as an anomaly since it represent an abnormal and anomalous platelet count as described in panel 150
[AltContent: arrow]
PNG
media_image2.png
605
159
media_image2.png
Greyscale
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Neuman to incorporate the teachings of Davies. Those in the art would have recognized that Neuman’s teaching regarding a classification device configured to receive training data including a first training set composed of physiological state data and a correlated prognostic labels and a second training set composed of a second prognostic label correlated with an ameliorative process label which subsequently, by use of machine learning models, transmit an output including at least a prognostic output and at least an ameliorative output to a user device, could be modified to include Davies’ teaching regarding a medical data presentation apparatus used to obtain medical data relating to a patient and to display some of the medical data including the highlighting of anomalous data points. This combination would be very beneficial to medical personnel when reviewing patient, in helping them obtain in an efficient manner information about a patient that includes a plot of the time series test results together with highlighted areas related to anomalous data together with recommendation and annotated notes regarding the prognosis and ameliorative actions regarding the patient.
However, Neuman and Davies are silent regarding normalizing labels based on the confidence scores which is taught by Dunn
normalize the first time series label (labeling data received from …first labeler) based on the first confidence score (confidence values ranging from one to five); normalize the second time series label (labeling data received from …second labeler) based on the second confidence score (confidence values ranging from one to three) (See at least [46] via: “…The diagnostic system can standardize and/or normalize the labeling data received from the plurality of labelers. For example, for a given case, if a first labeler supplies confidence values ranging from one to five and the second labeler supplies confidence values ranging from one to three, the diagnostic system can scale all values in both sets to a value between zero and one…”)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Neuman and Davies to incorporate the teachings of Dunn. Those in the art would have recognized that Neuman’s teaching regarding a classification device configured to receive training data including a first training set composed of physiological state data and a correlated prognostic labels and a second training set composed of a second prognostic label correlated with an ameliorative process label which subsequently, by use of machine learning models, transmit an output including at least a prognostic output and at least an ameliorative output to a user device, could be modified to include Dunn’ teaching regarding standardizing and/or normalizing labeling data based on confidence values. This combination would be beneficial to medical personnel when reviewing patient data so that recommendation data of patient can be based on labels that describe prognostic data and ameliorative data that are on the same scale for easier comparison.
Regarding claims 3 & 13 Neuman, Davies and Dunn teach the invention as detailed above with respect to claims 1 and 11 respectively. Neuman also teaches:
wherein determining the at least one recommendation datum comprises: training a recommendation machine leaning model (Ameliorative label learner 156 ) as a function of recommendation training data (first training set 108 as well as data from second training set 128); and determining the at least one recommendation datum (ameliorative labels ) as a function of the trained recommendation machine learning model (second machine-learning model 160). (See at least [0075] via: “…Referring again to FIG. 1, classification device 104 includes an ameliorative process label learner 156 operating on the classification device 104, the ameliorative process label learner 156 designed and configured to generate the at least an ameliorative output as a function of the second training set 128 and the at least a prognostic output. Ameliorative process label learner 156 may include any hardware or software module suitable for use as a prognostic label learner 148 as described above. Ameliorative process label learner 156 is a machine-learning module as described above; ameliorative process label learner 156 may perform any machine-learning process or combination of processes suitable for use by a prognostic label learner 148 as described above. For instance, and without limitation, and ameliorative process label learner 156 may be configured to create a second machine learning model 160 relating prognostic labels to ameliorative labels using the seco