DETAILED ACTION
This action is in response to the original filing on January 8, 2024. Claims 1-20 are pending and have been considered below. Claims 1, 11, and 15 are independent claims.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
Claims 1 (and its respective dependent claims 2-10) and 11 (and its respective dependent claims 12-14) in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
Such claim limitations are:
“a model configured to receive as input clinical data… and provide as output a score” in claim 1 (and its respective dependent claims 2-10). Here, “a model” is a generic placeholder (prong 1), modified by the function “configured to receive” (prong 2) and not modified by sufficient structure to perform the claimed function (prong 3). Specifically, the claimed “model” is not sufficient structure to perform the function of receiving “clinical data” and outputting “a score.” The “model” is interpreted to mean “any collection of one or more algorithms and/or machine-readable code… may include one or more mathematical algorithms, optimization or a statistical ranking algorithms… artificial intelligence or machine learning models… that can be trained in accordance with data received” (¶57).
a model configured to receive as input clinical data… and provide as output a score” in claim 11 (and its respective dependent claims 12-14). Here, “a model” is a generic placeholder (prong 1), modified by the function “configured to receive” (prong 2) and not modified by sufficient structure to perform the claimed function (prong 3). Specifically, the claimed “model” is not sufficient structure to perform the function of receiving “clinical data” and outputting “a score.” The “model” is interpreted to mean “any collection of one or more algorithms and/or machine-readable code… may include one or more mathematical algorithms, optimization or a statistical ranking algorithms… artificial intelligence or machine learning models… that can be trained in accordance with data received” (¶57).
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 2-4, 9, and 12-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 2:
Step 1 – Claim 2 is directed to a method: The method of claim 1…
Step 2A, Prong 1 – A judicial exception is recited in this claim as it recites a mental process (see MPEP 2106.04(a)(2)(III)):
determining… whether the score exceeds a threshold… A human can reasonably determine whether a score exceeds a threshold within the human mind.
Step 2A, Prong 2 – The following limitations are additional elements that fail to implement the abstract idea into a practical application:
(inherited from claim 1) receiving, by a processor from a plurality of data sources, clinical data for a plurality of medical personnel, the clinical data identifying a timing of one or more prescriptions of each of the plurality of medical personnel relative to a launch of a type of medical product… receiving data is data gathering (see MPEP 2106.05(g)).
(inherited from claim 1) training, by the processor, using machine learning applied to the clinical data, a model configured to receive as input clinical data of a medical personnel and a type of medical product and provide as output a score identifying a likelihood of the medical personnel to prescribe a medical product of the type of medical product within a defined time period relative to a launch of the medical product… training a model configured to receive input data is data gathering (see MPEP 2106.05(g)).
(inherited from claim 1) providing, by the processor, clinical data of a first medical personnel and a first type of medical product to the model… inputting data to a model is data gathering (see MPEP 2106.05(g)).
(inherited from claim 1) receiving, by the processor from the model, a score indicating a likelihood of the first medical personnel to prescribe the first type of medical product within the defined time period relative to a launch of the first type of medical product… receiving an output from a model is data outputting (see MPEP 2106.05(g)).
(inherited from claim 1) causing, by the processor, a display at a client device based on the score… displaying the model output is data outputting (see MPEP 2106.05(g)).
determining, by the processor… a processor used as a mere tool to apply an exception is a generic element for performing or applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
wherein the causing the display based on the score is based on the determining as to whether the score exceeds the threshold… displaying an output is data outputting (see MPEP 2106.05(g)).
Step 2B: These elements are recited at such a high level of generality that they fail to integrate the abstract idea into a practical application, since they provide nothing more than mere instructions to implement an abstract idea on a generic computer (MPEP 2106.05(f)) or only amount to data gathering or outputting (MPEP 2106.05(g)) without significantly more. These limitations, taken either alone or in combination, fail to provide an inventive concept. Thus, the claim is not patent eligible.
Regarding claim 3:
Step 1 – Claim 3 is directed to a method: The method of claim 1…
Step 2A, Prong 1 – A judicial exception is recited in this claim as it recites mental processes (see MPEP 2106.04(a)(2)(III)):
ranking… a score for each of the plurality of medical personnel… A human can reasonably perform ranking scores within the human mind or with the aid of a pen and paper.
selecting… the first medical personnel for the display based on the rankings… A human can reasonably perform “selecting” within the human mind or with the aid of a pen and paper.
Step 2A, Prong 2 – The following limitations are additional elements that fail to implement the abstract idea into a practical application:
All additional elements inherited from claim 1 amount to data gathering and outputting (as explained above with respect to claim 2).
providing, by the processor, clinical data of a plurality of medical personnel and the first type of medical product to the model, the plurality of medical personnel comprising the first medical personnel… providing data to the model is data gathering (see MPEP 2106.05(g)).
receiving, by the processor, a score for each of the plurality of medical personnel… receiving data is data gathering (see MPEP 2106.05(g)).
ranking/selecting, by the processor… a processor used as a mere tool to apply an exception is a generic element for performing or applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
Step 2B: These elements are recited at such a high level of generality that they fail to integrate the abstract idea into a practical application, since they provide nothing more than mere instructions to implement an abstract idea on a generic computer (MPEP 2106.05(f)) or only amount to data gathering or outputting (MPEP 2106.05(g)) without significantly more. These limitations, taken either alone or in combination, fail to provide an inventive concept. Thus, the claim is not patent eligible.
Claim 4 recites limitations which further narrow the abstract idea of claim 3 by specifying more details of the mental processes that occur:
Regarding claim 4, describing comprising: receiving, by the processor, a request from a client device, the request comprising the first type of medical product, wherein providing the clinical data of the plurality of medical personnel to the model is performed in response to receipt of the request, and wherein causing the display at the client device comprises displaying the first medical personnel on a user interface at the client device… receiving a request, providing data to a model based on the request, and displaying data based on the model output still amounts to data gathering and outputting (see MPEP 2106.05(g)).
Regarding claim 9:
Step 1 – Claim 9 is directed to a method: The method of claim 5…
Step 2A, Prong 1 – A judicial exception is recited in this claim as it recites a mental process (see MPEP 2106.04(a)(2)(III)):
comparing… the composite score to a threshold… A human can reasonably compare a score to a threshold within the human mind.
Step 2A, Prong 2 – The following limitations are additional elements that fail to implement the abstract idea into a practical application:
All additional elements inherited from claim 1 amount to data gathering and outputting (as explained above with respect to claim 2).
(inherited from claim 5) comprising: executing, by the processor, a plurality of models using the clinical data of the first medical personnel as input into each of the plurality of models to obtain a plurality of metrics… executing the models using clinical data as input to generate metrics as output is data gathering and outputting (see MPEP 2106.05(g)).
(inherited from claim 5) and generating, by the processor, a profile for the first medical personnel in memory by inserting the score and the plurality of metrics into the profile… generating a profile and storing data in memory is data gathering and outputting (see MPEP 2106.05(g)).
(inherited from claim 8) comprising: executing, by the processor, a model trained to generate composite scores for medical personnel, using each of the plurality of metrics and the score as input to obtain a composite score for the first medical personnel, wherein causing the display at the client device comprises causing, by the processor, the display based on the composite score… executing a model by using the score and metrics as input and outputting a composite score before displaying the output is data gathering and outputting (see MPEP 2106.05(g)).
comparing, by the processor… a processor used as a mere tool to apply an exception is a generic element for performing or applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
wherein causing the display at the client device comprises causing, by the processor, the display based on the comparing the composite score to the threshold… displaying an output is data outputting (see MPEP 2106.05(g)).
Step 2B: These elements are recited at such a high level of generality that they fail to integrate the abstract idea into a practical application, since they provide nothing more than mere instructions to implement an abstract idea on a generic computer (MPEP 2106.05(f)) or only amount to data gathering or outputting (MPEP 2106.05(g)) without significantly more. These limitations, taken either alone or in combination, fail to provide an inventive concept. Thus, the claim is not patent eligible.
Claims 12-14 recite a system claim that parallels the methods of claims 2-4, respectively. Therefore, claims 12-14 are rejected under substantially the same rationale as claims 2-4, respectively.
Regarding claim 15:
Step 1 – Claim 15 is directed to a method: A method for training a model for medical product early adopter prediction…
Step 2A, Prong 1 – A judicial exception is recited in this claim as it recites mental processes (see MPEP 2106.04(a)(2)(III)):
identifying… a timestamp of the launch of the medical product and a timestamp of each of the one or more prescriptions for the medical product by each of the plurality of medical personnel… a human can reasonably identify timestamps within the human mind or with the aid of a pen and paper.
determining… one or more differences between the timestamp of the launch of the medical product and one or more timestamps of the one or more prescriptions… a human can reasonably determine differences between timestamps within the human mind or with the aid of a pen and paper.
Step 2A, Prong 2 – The following limitations are additional elements that fail to implement the abstract idea into a practical application:
comprising: receiving, by a processor and from a plurality of data sources, clinical data for a plurality of medical personnel, the clinical data identifying a timing of one or more prescriptions of each of the plurality of medical personnel relative to a launch of a medical product… receiving data is data gathering (see MPEP 2106.05(g)).
identifying/determining, by the processor… a processor used as a mere tool to apply an exception is a generic element for performing or applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
generating, by the processor, a training data set according to the one or more differences… generating a dataset is data outputting (see MPEP 2106.05(g)).
training, by the processor, the model with the training data set using machine learning… inputting a training dataset into a model is data gathering (see MPEP 2106.05(g)).
Step 2B: These elements are recited at such a high level of generality that they fail to integrate the abstract idea into a practical application, since they provide nothing more than mere instructions to implement an abstract idea on a generic computer (MPEP 2106.05(f)) or only amount to data gathering or outputting (MPEP 2106.05(g)) without significantly more. These limitations, taken either alone or in combination, fail to provide an inventive concept. Thus, the claim is not patent eligible.
Claims 16-20 recite limitations which further narrow the abstract idea of claim 3 by specifying more details of the mental processes that occur:
Regarding claim 16, this claim further limits the abstract idea of claim 15 to be based on a mental process: labeling… the feature vector according to at least one of the one or more differences associated with the medical personnel… A human can reasonably perform labeling a feature vector according to “the one or more differences” within the human mind or with the aid of a pen and paper. Furthermore, labeling, by the processor… is still applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)). Furthermore, wherein generating the training data set comprises generating, by the processor, a training data set by, for each of the plurality of medical personnel: generating, by the processor, a feature vector for the medical personnel, the feature vector comprising clinical data regarding the medical personnel… generating a feature vector based on a training dataset is still data outputting (see MPEP 2106.05(g)).
Regarding claim 17, this claim further limits the abstract idea of claim 16 to be based on a mental process: identifying… a plurality of differences between timestamps of a plurality of launches of medical products and timestamps of a plurality of prescriptions of the plurality of medical personnel for a plurality of medical products of a first product type… and determining… a first value as a function of the plurality of differences, wherein labeling the feature vector according to the one or more of the plurality of differences comprises labeling the feature vector according to the first value… A human can reasonably perform identifying differences between timestamps and determining a first value as a function of the differences within the human mind or with the aid of a pen and paper. Furthermore, identifying/determining, by the processor… is still applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
Regarding claim 18, this claim further limits the abstract idea of claim 17 to be based on a mathematical concept (see MPEP 2106.04(a)(2)(III)): wherein determining the first value comprises determining… an average or a median of the plurality of differences… determining an average or a median is a mathematical calculation. Furthermore, determining, by the processor… is still applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
Regarding claim 19, this claim further limits the abstract idea of claim 17 to be based on a mental process: comprising: determining… whether the first value exceeds a threshold, wherein labeling the feature vector according to the one or more of the plurality of differences comprises labeling, by the processor, the feature vector according to the determining of whether the first value exceeds the threshold… A human can reasonably determine whether a value exceeds a threshold within the human mind. Furthermore, determining, by the processor… is still applying the abstract idea using a generic computing environment (see MPEP 2106.05(f)).
Regarding claim 20, specifying wherein generating the feature vector comprises inserting a type of the medical product into the feature vector in this manner does not overcome the rejection of claim 16 as modifying “the feature vector” does not make “labeling” to not be a mental process.
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.
Claims 1-2, 5, 7, 10, 11-12, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Naveh (US 20160371595 A1, hereinafter Naveh) in view of Rusak (US 20210225495 A1, hereinafter Rusak).
Regarding claim 1:
Regarding the limitation a method, comprising: receiving, by a processor from a plurality of data sources, clinical data for a plurality of medical personnel, the clinical data identifying a timing of one or more prescriptions of each of the plurality of medical personnel relative to a launch of a type of medical product, Naveh teaches a method, comprising: receiving, by a processor (¶78 “a computer program product comprising a computer-readable medium containing computer program code, which may be executed by a computer processor for performing any or all of the steps, operations, or processes described”) from a plurality of data sources …data for a plurality of users, the… data identifying a timing of one or more actions of each of the plurality of users relative to a lunch of a type of… product (Fig. 1 – 110, 140, Fig. 2 – 205, 210, 220, ¶20 “The client devices 110 are one or more computing devices… allowing a user of the client device 110 to interact with the online system 140,” ¶24 “Each user of the online system 140 is associated with a user profile, which is stored in the user profile store 205. A user profile includes declarative information about the user that was explicitly shared by the user and may also include profile information inferred by the online system 140… A user profile in the user profile store 205 may also maintain references to actions by the corresponding user performed on content items in the content store 210 and stored in the action log 220,” ¶28 “Examples of interactions with objects include: commenting on posts, sharing links, checking-in to physical locations via a client device 110,” ¶30 “Example actions describing adoption of an innovation in a subject area include: purchasing a new product in a subject area (e.g., buying a new smartphone), upgrading to a new version of a product in the subject area… providing messages to other users regarding an innovation in the subject area, receiving messages from additional users or from the online system 140 regarding the innovation in the subject area, or other suitable actions,” wherein a “subject area” encompasses a type of… product, ¶35 “Retrieved information associated with actions describing the user's adoption of innovations in the subject area includes times associated with the actions specifying times when the user performed the actions… a retrieved action describing a purchase of a new product associated with a subject area includes a time when the user purchased the product,” ¶42 “each action describing adoption of an innovation in the subject area by the user includes a time when the action was initially capable of being performed (e.g., a time when a product or service was initially available for purchase, a time when a product or service was initially available to be reserved)”). However, Naveh fails to teach clinical data, medical personnel, prescriptions, and medical product.
Rusak, in the same field of endeavor, teaches clinical data (¶58 “The interaction journey denotes, for example, what buttons the healthcare provider pressed on the medical device, the sequence of actions the healthcare provider performed on the medical device, what data the healthcare provider selected for viewing on the medical device, and what data the healthcare provider entered via the medical device,” ¶83 “data that may be indirectly related to treatment of the patient, in particular, at least the interaction journey of the healthcare provider with one or more medical devices storing data of the target patient and/or monitoring the target patient, and/or other contextual data, for example, clinical information, electronic medical record data… pharmacy record, a profile of the user (e.g. treating healthcare worker)… medical publications, nursing publications, other publications… research, and/or research in medicine… other scientific or non-scientific fields that may be relevant to the treatment of the present patient”), medical personnel (¶170 “An identity profile of the healthcare provider. The identity profile may include, for example: position of the healthcare provider (e.g., nurse, medical student, resident, staff physician)”), prescriptions (¶93 “aspects of the treatment, for example but not limited to medications that were prescribed to the patient… the personnel that examine this particular patient, their experiences, skills, etc. the physicians' train of thoughts as reflected on tests, medications, assumptions, way of examination”), and medical product (¶210 “previous treatment attempts for treatment of diabetes mellitus (e.g., unsuccessful treatment using gabapentin and lyrica, suggested treatments with limited side effects including amitryiptyline, lidocaine, and IVIG infusion)”).
Regarding the limitation training, by the processor, using machine learning applied to the clinical data, a model configured to receive as input clinical data of a medical personnel and a type of medical product and provide as output a score identifying a likelihood of the medical personnel to prescribe a medical product of the type of medical product within a defined time period relative to a launch of the medical product, Naveh teaches a model configured to receive as input… data of a user and a type of… product and provide as output a score identifying a likelihood of the user to adopt a… product of the type of… product within a defined time period relative to the launch of the… product (¶37 “one or more machine learned models are applied to characteristics of the actions describing user adoption of innovations associated with the subject area and characteristics of content associated with innovations associated with the subject area provided by the user… the model determines a score for the pairing of user and subject area based on times associated with actions describing the user adopting one or more innovations in the subject area and times when a described action was initially able to be performed,” wherein “machine learned models” encompass a model configured to… as explained above in the interpretations under 112(f), Fig. 3 – 340-350, ¶63 “the online system 140 associates different innovation adoption labels with different ranges of scores, and generates 350 an innovation adoption label for the pairing of the user and the subject area that corresponds to a range of scores including the score determined 340 for the pairing of the user and the subject area… different ranges of scores are associated with innovation adoption labels of ‘innovator,’ ‘early adopter,’ ‘early majority,’ ‘late majority,’ and ‘laggard,’” Fig. 4, ¶69 “The curve shown in FIG. 4 is… defined for technology adoption cycle that labels the user based on their propensity to adopt innovations at different times after the innovations are available,” ¶70 “i.e., users likely to adopt an innovation in the subject area within a threshold time of the innovation becoming available”). However, Naveh fails to teach training, by the processor, using machine learning applied to the clinical data, a model… and clinical data, medical personnel, and to prescribe a medical product.
Rusak teaches training, by the processor (¶71 “The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention”), using machine learning applied to the clinical data, a model (Fig. 1 – 150, ¶130 “a model is trained and/or provided. The model is trained according to computed correlations between interaction journeys of one or more subject healthcare providers,” ¶131 “the model may be customized per patient or by the patient, by learning the interactions for the user treating the specific patient,” ¶139 “Exemplary models may include one or more statistical classifiers, one or more neural networks of various architectures”), and clinical data (¶¶58, 83), medical personnel (¶208 “users such as physicians, nurses, researchers and other caregivers to develop software and/or hardware to extend the model and/or use the data the model outputs”), and to prescribe a medical product (¶215 “the alert ‘patient with G6PD deficiency prescribed optalgin. Consult physician before dispensing’ is presented when the model has learned that optalgin is not prescribed for patients with G6PD deficiency (or has no such learned correlation) and the current user has performed the correlation of interaction journey to prescribe optalgin to a patient with G6PD deficiency”).
Regarding the limitation providing, by the processor, clinical data of a first medical personnel and a first type of medical product to the model, Naveh teaches providing, by the processor, … data of a first user and a first type of… product to the model (¶37 “one or more machine learned models are applied to characteristics of the actions describing user adoption of innovations associated with the subject area and characteristics of content associated with innovations associated with the subject area provided by the user,” ¶41 “a subject area refers to a field of knowledge or field of topics. Example subject areas include technology, music, food… and the like… the maintained information includes one or more actions describing the user's adoption of innovations in the subject area. Example actions describing the user's adoption of innovations in the subject area include: the user purchasing a new product or service in the subject area,” ¶6 “actions describing the user adopting innovations in a subject area of technology include actions where the user ordering or purchasing a product including a new or upgraded technology (e.g., buying a new smartphone)”). However, Naveh fails to teach clinical data, medical personnel, and type of medical product.
Rusak teaches clinical data (¶¶58, 83), medical personnel (¶¶170, 208), and type of medical product (¶¶210, 215).
Regarding the limitation receiving, by the processor from the model, a score indicating a likelihood of the first medical personnel to prescribe the first type of medical product within the defined time period relative to a launch of the first type of medical product, Naveh teaches receiving, by the processor from the model, a score indicating a likelihood of the first user to use the first type of… product within the defined time period relative to a launch of the first type of… product (Fig. 3 – 340-350, ¶62 “Different scores may be determined 340 for pairings of the user and different subject areas,” ¶63 “different ranges of scores are associated with innovation adoption labels,” Fig. 4, ¶¶70-71 “Innovators: Users who are willing to take highest amount of risk in adopting innovations at a very early stage (i.e., users likely to adopt an innovation in the subject area within a threshold time of the innovation becoming available). Early Adopters: Users who are willing to take high risk but not as high as innovators, and are more discreet in adopting innovations than innovators (i.e., users likely to adopt the innovation in the subject area after the threshold time but before an additional time after the innovation becomes available)”). However, Naveh fails to teach medical personnel to prescribe the first type of medical product… and the first type of medical product.
Rusak teaches medical personnel to prescribe a first type of medical product (¶208 “users such as physicians, nurses, researchers and other caregivers,” ¶215 “the current user has performed the correlation of interaction journey to prescribe optalgin to a patient with G6PD deficiency”).
Regarding the limitation causing, by the processor, a display at a client device based on the score, Naveh teaches the score (Fig. 3 – 340, ¶37 “the model determines a score for the pairing of user and subject area based on times associated with actions”). However, Naveh fails to teach causing, by the processor, a display at a client device based on the score.
Rusak teaches causing, by the processor (¶71), a display at a client device based on scores (¶5 “a method of adapting a user interface (UI) for presenting medical data of a target patient, comprises: monitoring an interaction journey of a healthcare provider,” Fig. 12A, ¶209 “FIGS. 12A-E… are exemplary schematics of the UI adapted based on output of the model fed the interaction journey and patient parameter(s),” ¶210 “scores… are outputted by the model and presented”).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the training of a model, display at a client device, and the medical domain of Rusak with the early adopter detection methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Regarding claim 2, Naveh in view of Rusak teaches the method of claim 1 (and thus the rejection of claim 1 is incorporated).
Naveh teaches comprising: determining, by the processor, whether the score exceeds a threshold (Fig. 1 – 140, Fig. 4 – 410-440, ¶68 “FIG. 4 shows four threshold propensities 410, 420, 430, and 440 that define five ranges of propensities,” ¶75 “the online system 140 generates the innovation adoption labels of FIG. 4 for a user by comparing the determined scores for the user and the subject area with that of the ranges of scores specified by the threshold propensities 410, 420, 430, 440”).
Regarding the limitation wherein the causing the display based on the score is based on the determining as to whether the score exceeds the threshold, Naveh teaches the score (Fig. 3 – 340, ¶37) and the determining as to whether the score exceeds the threshold (Fig. 1 – 140, Fig. 4 – 410-440, ¶¶68, 75). However, Naveh fails to teach wherein the causing the display based on the score is based on the determining as to whether the score exceeds the threshold.
Rusak teaches wherein the causing the display based on scores is based on determining success of previous treatment attempts (¶5, Fig. 12A, ¶209, ¶210 “scores and/or indications of success of previous treatment attempts… are outputted by the model and presented”).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the displaying of scores and medical domain of Rusak with the score/threshold comparisons of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Regarding claim 5, Naveh in view of Rusak teaches the method of claim 1 (and thus the rejection of claim 1 is incorporated).
Regarding the limitation comprising: executing, by the processor, a plurality of models using the clinical data of the first medical personnel as input into each of the plurality of models to obtain a plurality of metrics, Naveh teaches comprising: executing, by the processor, a model using the… data of the first user as input into the model to obtain a plurality of metrics (¶37, ¶11 “The online system may determine scores associated with parings of the user and different subject areas… a score for a pairing of the user and technology indicates the user has a high propensity for adopting innovations in technology, while a score for a pairing of the user and music indicates the user has a low propensity for adopting innovations, or changes, in music,” wherein “scores” associating a user with “different subject areas” encompasses a plurality of metrics). However, Naveh fails to teach executing… a plurality of models and clinical data, medical personnel, and each of the plurality of models.
Rusak teaches executing a plurality of models (¶138 “the model is trained by training sub-components at each of multiple different entities, for example, hospitals, clinical, health maintenance organizations (HMO), and nursing homes… some or all the models of the sub-components benefits from and encapsulates the data and interaction journeys at all of the participating organizations”) and clinical data (¶¶58, 83), medical personnel (¶¶170, 208), and inputting data to each of the plurality of models to obtain metrics (¶181 “the interaction journey and/or one or more of the patient parameters and/or the other data are distributed and fed to multiple sub-components… Outputs of multiple sub-components may be aggregated”).
Regarding the limitation and generating, by the processor, a profile for the first medical personnel in memory by inserting the score and the plurality of metrics into the profile, Naveh teaches and generating, by the processor, a profile for the first user in memory by inserting the score and the plurality of metrics into the profile (Fig. 1 – 140, Fig. 2 – 205, 230, Fig. 3 – 350, ¶24 “Each user of the online system 140 is associated with a user profile, which is stored in the user profile store 205,” ¶38 “Scores associated with various pairings of the user and subject areas are stored by the innovation adoption classifier 230 in the user profile associated with the user,” ¶65 “The online system 140 may generate 350 different innovation adoption labels for different pairings of the user and different subject areas,” wherein storing in memory is implicit). However, Naveh fails to teach medical personnel.
Rusak teaches medical personnel (¶¶170, 208).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the plurality of models and medical domain of Rusak with the plurality of metrics and methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Regarding claim 7, Naveh in view of Rusak teaches the method of claim 5 (and thus the rejection of claim 5 is incorporated).
Regarding the limitation wherein causing the display at the client device comprises causing, by the processor, the display based on the score and the plurality of metrics at the client device, Naveh teaches the score and the plurality of metrics (¶37, ¶11 ““The online system may determine scores associated with parings of the user and different subject areas”). However, Naveh fails to teach wherein causing the display at the client device comprises causing, by the processor, the display based on the score and the plurality of metrics at the client device.
Rusak teaches wherein causing the display at the client device comprises causing, by the processor, the display based on a plurality of scores at the client device (¶5, Fig. 12A, ¶209, ¶210 “treatment suggestions are computed and presented based on output of the model. Optionally, scores and/or indications of success of previous treatment attempts… are outputted by the model and presented”).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the displaying of scores of Rusak with the score and metrics of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Regarding claim 10, Naveh in view of Rusak teaches the method of claim 1 (and thus the rejection of claim 1 is incorporated).
Regarding the limitation comprising: executing, by the processor, the model using the clinical data of the first medical personnel as input to the model to output the score, Naveh teaches comprising: executing, by the processor, the model using the… data of the first user as input to the model to output the score (¶37). However, Naveh fails to teach clinical data and medical personnel.
Rusak teaches clinical data (¶¶58, 83) and medical personnel (¶¶170, 208).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain of Rusak with the methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Regarding claim 11:
Naveh teaches a system comprising a server (Fig. 1 – 110, 130-140, Fig. 2 – 210, 235, ¶39 “web server 235 links the online system 140 via the network 120 to the one or more client devices 110, as well as to the one or more third party systems 130. The web server 235 serves web pages, as well as other content… The web server 235 may receive and route messages between the online system 140 and the client device 110… A user may send a request to the web server 235 to upload information (e.g., images or videos) that are stored in the content store 210”) comprising a processor and a non-transitory computer-readable medium containing instruction that when executed by the processor, causes the processor to perform operations comprising: receiving (¶78 “Any of the steps, operations, or processes described herein may be performed or implemented with one or more hardware or software modules… a software module is implemented with a computer program product comprising a computer-readable medium containing computer program code, which may be executed by a computer processor for performing any or all of the steps, operations, or processes described”)…
Claims 11-12 recite a system claim that parallels the methods of claims 1-2, respectively. Therefore, claims 11-12 are rejected under substantially the same rationale as claims 1-2, respectively.
Regarding claim 15:
Regarding the limitation a method for training a model for medical product early adopter prediction, comprising: receiving, by a processor and from a plurality of data sources, clinical data for a plurality of medical personnel, the clinical data identifying a timing of one or more prescriptions of each of the plurality of medical personnel relative to a launch of a medical product, Naveh teaches a method… for product early adopter prediction (Abstract: “An online system classifies users based on their propensity to adopt one or more innovations”), comprising: receiving, by a processor (¶78) and from a plurality of data sources, … data for a plurality of users, the… data identifying a timing of one or more actions of each of the plurality of users relative to a launch of a… product (Fig. 1 – 110, 140, Fig. 2 – 205, 210, 220, ¶¶20, 24, 28, 30, 35, 42 all as explained above with respect to claim 1). However, Naveh fails to teach a method for training a model and clinical data, medical personnel, prescriptions, and medical product.
Rusak teaches a method for training a model (¶58 “The interaction journey and one or more patient parameters are fed into a model (e.g., machine learning model, machine learning classifier, statistical model, etc.) that is trained according to computed correlations, computed interactions, computed differences, etc., between interaction journeys of multiple other sample healthcare providers”) and clinical data (¶¶58, 83), medical personnel (¶¶170, 208), prescriptions (¶¶93, 208, 215), and medical product (¶¶210, 215).
Regarding the limitation identifying, by the processor and from the clinical data, a timestamp of the launch of the medical product and a timestamp of each of the one or more prescriptions for the medical product by each of the plurality of medical personnel, Naveh teaches identifying, by the processor and from the… data, a timestamp of the launch of the… product and a timestamp of each of the one or more interactions for the… product by each of the plurality of users (¶35 “Retrieved information associated with actions describing the user's adoption of innovations in the subject area includes times associated with the actions specifying times when the user performed the actions,” ¶42 “each action describing adoption of an innovation in the subject area by the user includes a time when the action was initially capable of being performed (e.g., a time when a product or service was initially available for purchase, a time when a product or service was initially available to be reserved)”). However, Naveh fails to teach clinical data, medical product, prescriptions, and medical personnel.
Rusak teaches clinical data (¶¶58, 83), medical product (¶¶210, 215), prescriptions (¶¶93, 208, 215), and medical personnel (¶¶170, 208).
Regarding the limitation determining, by the processor, one or more differences between the timestamp of the launch of the medical product and one or more timestamps of the one or more prescriptions, Naveh teaches determining, by the processor, one or more differences between the timestamp of the launch of the… product and one or more timestamps of the one or more actions (¶42 “an action describing adoption of one or more innovations in the subject area also identifies a time when the action was initially capable of being performed (e.g., a release date of a product or a service) or a difference between a time when the action was performed and the time when the action was initially capable of being performed”). However, Naveh fails to teach medical product and prescriptions.
Rusak teaches medical product (¶¶210, 215) and prescriptions (¶¶93, 208, 215).
Regarding the limitation generating, by the processor, a training data set according to the one or more differences, Naveh teaches the one or more differences (¶42 “a difference between a time when the action was performed and the time when the action was initially capable of being performed”). However, Naveh fails to teach generating, by the processor, a training data set according to the one or more differences.
Rusak teaches generating, by the processor (¶71), a training data set according to correlations within clinical data (¶58 “The interaction journey denotes… the sequence of actions the healthcare provider performed on the medical device…,” ¶28 “the plurality of patient parameters obtained from the plurality of non-physiological data sources are selected from the group consisting of: patient demographics, identity profile of healthcare providing team members, history of the present illness, prior medical history, prior treatments…,” ¶83 “data that may be indirectly related to treatment of the patient, in particular, at least the interaction journey of the healthcare provider with one or more medical devices storing data of the target patient and/or monitoring the target patient, and/or other contextual data, for example, clinical information…,” ¶130 “The model is trained according to computed correlations between interaction journeys of one or more subject healthcare providers… and one or more patient parameter of one or more subject patients”).
Naveh fails to teach and training, by the processor, the model with the training data set using machine learning. However, Rusak teaches this limitation (¶130).
Naveh and Rusak are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the training data and medical domain of Rusak with the data and methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”).
Claims 3-4, 6, 8-9, and 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Naveh in view of Rusak and further in view of Rice (US 20220108790 A1, hereinafter Rice).
Regarding claim 3, Naveh in view of Rusak teaches the method of claim 1 (and thus the rejection of claim 1 is incorporated).
Regarding the limitation comprising: providing, by the processor, clinical data of a plurality of medical personnel and the first type of medical product to the model, the plurality of medical personnel comprising the first medical personnel, Naveh teaches comprising: providing, by the processor, … data of a plurality of users (¶27 “a number of actions may involve an object and one or more particular users”) and the first type of… product to the model, the plurality of users comprising the first user (¶¶6, 37, 41). However, Naveh fails to teach clinical data, medical personnel, and the first type of medical product.
Rusak teaches clinical data (¶¶58, 83), medical personnel (¶¶170, 208), and a type of medical product (¶¶210, 215).
Regarding the limitation receiving, by the processor, a score for each of the plurality of medical personnel, Naveh teaches receiving, by the processor, a score for each of the plurality of users (Fig. 1 – 140, Fig. 3 – 340, ¶53 “the online system 140 determines 340 a score for a pairing of the user and the subject area… based on the retrieved actions and the retrieved content provided by the user”). However, Naveh fails to teach medical personnel.
Rusak teaches medical personnel (¶¶170, 208).
Regarding the limitation ranking, by the processor, the plurality of medical personnel according to the scores, Naveh teaches ranking, by the processor, the plurality of users according to the scores (¶68 “FIG. 4 shows four threshold propensities 410, 420, 430, and 440 that define five ranges of propensities,” ¶69 “the user's propensity to adopt one or more innovations in a subject area is represented by a score determined for a pairing of the user and the subject area… innovation labels for the example classification shown in FIG. 4 include “innovators,” “early adopters,” “early majority,” “late majority,” and “laggards.” The curve shown in FIG. 4 is similar to the Rogers bell curve defined for technology adoption cycle that labels the user based on their propensity to adopt innovations at different times after the innovations are available,” Fig. 4 – 410-440 depicts organizing users into a “bell curve” and labelling them so that each “range of propensities” has a percentage of users in accordance with “the Rogers bell curve defined for technology adoption,” for example having 2.5% of users be labelled as “Innovators,” and 13.5% of users be “Early Adopters,” and so on; one of ordinary skill in the art would recognize that ranking the users according to the scores is implicit for these operations). However, Naveh fails to teach the plurality of medical personnel.
Rusak teaches a plurality of medical personnel (¶136 “the plurality of sample healthcare providers”).
Regarding the limitation and selecting, by the processor, the first medical personnel for the display based on the rankings, Naveh teaches the rankings (Fig. 4, ¶¶68-69). However, the combination of Naveh and Rusak fails to teach and selecting, by the processor, the first medical personnel for the display based on the rankings.
Rice, in the same field of endeavor, teaches and selecting, by the processor (¶28 “The processor may then execute… instructions causing the server computer(s) to complete the disclosed method steps”), the first medical personnel for the display based on rankings (Fig. 1 – 102, 106, Fig. 2 – 208-210, ¶84 “potential physicians… may then be ranked at process block 208… the potential physicians may be ranked according to the number of times a particular physician has been saved as a favorite physician… the highest ranking physician would be the physician that is the most popular among patients or potential patients,” ¶87 “After ranking the physicians at process block 208, the recommendation module 106 may display or output a list of recommended physicians to the user at process block 210. The list of recommended physicians may be displayed on the interface 102… with the highest ranking physician as the first entry”).
Naveh, Rusak, and Rice are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain of Rusak and the ranking and display of Rice with the ranking and methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and to “automatically assign… higher weights to the identified most desirable [healthcare provider] attributes” (Rice, ¶81).
Regarding claim 4, Naveh in view of Rusak and further in view of Rice teaches the method of claim 3 (and thus the rejection of claim 3 is incorporated).
Regarding the limitation comprising: receiving, by the processor, a request from a client device, the request comprising the first type of medical product, wherein providing the clinical data of the plurality of medical personnel to the model is performed in response to the request, Naveh teaches the first type of… product (¶¶6, 41) and providing the… data of the plurality of users to the model (¶37). However, Naveh fails to teach comprising: receiving, by the processor, a request from a client device, the request comprising the first type of medical product, wherein providing the clinical data of the plurality of medical personnel to the model is performed in response to the request.
Rusak teaches a type of medical product (¶¶210, 215), clinical data (¶¶58, 83) and medical personnel (¶136). However, Rusak fails to teach comprising: receiving, by the processor, a request from a client device, the request comprising the first type of medical product, wherein providing the clinical data of the plurality of medical personnel to the model is performed in response to the request.
Rice teaches comprising: receiving by the processor, a request from a client device, the request comprising a type of medical product (Fig. 1 – 108, ¶53 “user may input their responses… These responses may then be stored in database 108,” ¶54 “Questionnaire Responses for Questions in the Health Care Preference Category: … I’m interested in alternative medicine,” ¶63 “the API may receive third party data feeds in the form of patient data from a medical data database… In addition to identifying providers that are a match for the patient's current needs, the disclosed system may therefore also analyze the user's request for a matching provider in the context of these additional health conditions, and provide recommendations according to a network of preferred providers”), wherein machine learning is performed in response to the request (Fig. 4A, ¶74 “A first way the data between patients and providers may be matched is by direct matching… Certain questions within a patient's profile have a direct correlation to related questions within a provider's profile. Matches are determined based on a one to one match between the correlated question sets. Additional weighting is applied to matched/unmatched attributes based on three factors… using these factors as input/training data into a machine learning algorithm… gives a higher weight to those factors which contributed the most to the favorable health care outcomes”).
Rice further teaches and wherein causing the display at the client device comprises displaying the first medical personnel on a user interface at the client device (Fig. 1 – 102, 106, Fig. 2 – 208-210, ¶¶84, 87).
Naveh, Rusak, and Rice are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain of Rusak and the request and display of Rice with the machine learning methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and to “automatically assign… higher weights to the identified most desirable [healthcare provider] attributes” (Rice, ¶81).
Regarding claim 6, Naveh in view of Rusak teaches the method of claim 5 (and thus the rejection of claim 5 is incorporated).
Regarding the limitation wherein generating the profile for the first medical personnel comprises inserting, by the processor, the score and the plurality of metrics into separate cells of a table, Naveh teaches generating the profile for the first user (Fig. 1 – 140, Fig. 2 – 205, 230, Fig. 3 – 350, ¶¶24, 38, 65 as explained above with respect to claim 5) and the score and the plurality of metrics (¶37, ¶11 ““The online system may determine scores associated with parings of the user and different subject areas”). However, Naveh fails to teach wherein generating the profile for the first medical personnel comprises inserting, by the processor, the score and the plurality of metrics into separate cells of a table.
Rusak teaches medical personnel (¶¶170, 208). However, the combination of Naveh and Rusak fails to teach wherein generating the profile for the first medical personnel comprises inserting, by the processor, the score and the plurality of metrics into separate cells of a table.
Rice teaches wherein generating a medical personnel profile comprises inserting attributes into separate cells of a table (Fig. 3 – 300, 330, 515, 525, 530, ¶33 “related flow charts… for creating an account profile 330, a patient profile 525, and/or a service profile 530… the input may be received by any means known in the art, such as via an RPC to an API providing and/or generating a baseline set of information… a user, such as a patient, provider or consumer, may access the user interface,” ¶34 “a complimentary or analogous provider profile creation step may exist,” ¶53 “The user may input their responses, possibly including a value and weight for each response, into the user interface,” ¶¶54-55 “TABLE 1… TABLE 2,” ¶67 “Provider profiles may be created (analogous to process block 515) and stored (analogous to process block 525) in a similar manner and the stored provider profile data 525 and service profile data 530 may be analogous to those stored for the patient profile data 525 and service data 530. The physician data for each of the physicians in the database may be obtained through a user interface presented to the physician,” ¶78 “FIG. 5A is a visualization used to show the overlapping individual traits/attributes (e.g., attributes where the patient profile attribute and provider profile attribute are common), derived through the patient and provider profile questionnaires, or other matching techniques,” Fig. 5A depicts inserting attributes into separate cells of a table according to a “provider profile questionnaire” in which responses are weighted).
Naveh, Rusak, and Rice are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain of Rusak and the medical personnel table of Rice with the profile consisting of a score and metrics of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and to “automatically assign… higher weights to the identified most desirable [healthcare provider] attributes” (Rice, ¶81).
Regarding claim 8, Naveh in view of Rusak teaches the method of claim 5 (and thus the rejection of claim 5 is incorporated).
Regarding the limitation comprising: executing, by the processor, a model trained to generate composite scores for medical personnel, using each of the plurality of metrics and the score as input to obtain a composite score for the first medical personnel, Naveh teaches the plurality of metrics and the score (¶37, ¶11 “The online system may determine scores associated with parings of the user and different subject areas”). However, Naveh fails to teach comprising: executing, by the processor, a model trained to generate composite scores for medical personnel, using each of the plurality of metrics and the score as input to obtain a composite score for the first medical personnel.
Rusak teaches comprising: executing, by the processor, a model trained to generate composite scores (¶138 “the model is trained by training sub-components at each of multiple different entities, for example, hospitals, clinical, health maintenance organizations (HMO), and nursing homes… A central model may be created by aggregating the sub-components and creating a new, more general aggregated model… The aggregated model learned from some or all the models of the sub-components benefits from and encapsulates the data and interaction journeys at all of the participating organizations and enables a better model,” ¶¶181-182 “Outputs of multiple sub-components may be aggregated into a single output of an adaptation to the UI… A central model may be created by aggregating the sub-components,” ¶210 “scores… are outputted by the model and presented,” wherein outputs that are “aggregated into a single output” encompass composite scores) and using multiple model outputs as input to obtain a composite score (¶¶138, 181-182, 210, ¶212 “an indication of satisfaction, success, and/or side-effect score is computed for the treatment which was found to be successful… by the model and presented in the UI”). However, Rusak fails to teach composite scores for medical personnel and a composite score for the first medical personnel.
Rice teaches composite scores for medical personnel (Fig. 3 – 300, 330, 515, 525, 530, ¶¶33-34, 53-55, 67 all as explained above with respect to claim 6, Fig. 5B, ¶80 “FIG. 5B demonstrates how the server computer(s) calculate a match confidence percentage between the patient attributes for each of the categories and the provider attributes for each of the categories… the number of overlapping attributes represents the percentage of match confidence for each of the four categories, and as a whole,” wherein a “percentage” calculated from various attributes of a “provider” encompasses a composite score for medical personnel, as depicted in Fig. 5B) and a composite score for the first medical personnel (¶80 “The match confidence percentage then determines… the order that matching providers are presented,” Fig. 5B depicts a “Match Ordering” with three providers, among which is “Match #1” with the highest “Match Confidence” or the highest composite score for the first matched provider or for the first medical personnel).
Rice further teaches wherein causing the display at the client device comprises causing, by the processor, the display based on the composite score (Fig. 5C – 1420, 1430, ¶82 “After running the match ordering analysis, the one or more software modules may then rerun the match ordering algorithm, but weight the match confidence level according to the weighting of the attributes shown to show more favorable results and/or those attributes weighted as more desirable by the patient… the match may then be reordered according to any weighting, and may then be presented to the user or output for use by additional software or database applications,” Fig. 1 – 102, ¶87 “The list of recommended physicians may be displayed on the interface 102, or output for use by an additional software or database application”).
Naveh, Rusak, and Rice are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain and the composite model outputs of Rusak and composite scores for medical personnel and display of Rice with the score and metrics of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and to “automatically assign… higher weights to the identified most desirable [healthcare provider] attributes” (Rice, ¶81).
Regarding claim 9, Naveh in view of Rusak and further in view of Rice teaches the method of claim 8 (and thus the rejection of claim 8 is incorporated).
Rice further teaches comparing, by the processor, the composite score to a threshold (¶80 “The match confidence percentage then determines whether providers are a match above the threshold”).
Rice further teaches wherein causing the display at the client device comprises causing, by the processor, the display based on comparing the composite score to the threshold (¶80 “The match confidence percentage then determines whether providers are a match above the threshold and the order that matching providers are presented to the user,” Fig. 1 – 102, Fig. 5C – 1420, 1430, ¶¶82, 87).
Naveh and Rice are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the composite scores, threshold, and display of Rusak with the methodology of Naveh. The motivation to do so is to use machine learning to “automatically assign… higher weights to the identified most desirable [healthcare provider] attributes” (Rice, ¶81).
Claims 13-14 recite a system claim that parallels the methods of claims 3-4, respectively. Therefore, claims 13-14 are rejected under substantially the same rationale as claims 3-4, respectively.
Claims 16-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Naveh in view of Rusak and further in view of Yellowlees et al. (US 20250054623 A1, hereinafter Yellowlees).
Regarding claim 16, Naveh in view of Rusak teaches the method of claim 15 (and thus the rejection of claim 15 is incorporated).
Regarding the limitation wherein generating the training dataset comprises generating, by the processor, a training dataset by, for each of the plurality of medical personnel: generating, by the processor, a feature vector of the medical personnel, the feature vector comprising clinical data regarding the medical personnel, Rusak teaches wherein generating the training dataset comprises generating, by the processor, a training dataset by, for each of the plurality of medical personnel (¶¶28, 58, 83, 130) and clinical data regarding the medical personnel (¶¶58, 83). However, the combination of Naveh and Rusak fails to teach generating, by the processor, a feature vector of the medical personnel, the feature vector comprising clinical data regarding the medical personnel.
Yellowlees, in the same field of endeavor, teaches generating, by the processor, a feature vector of the medical personnel, the feature vector comprising clinical data regarding the medical personnel (Fig. 5 – 502, 518, ¶105 “data processing system may receive audio data and video data of a clinical encounter. The clinical encounter may be an instance of a patient speaking with a doctor or physician about a medical visit (e.g., psychotherapy visit, a visit at a medical clinic, or any other medical visit) discussing medical or other issues the patient may be experiencing,” ¶119 “data processing system may additionally include words or values converted from words spoken by… the physician… in separate index values of the feature vector”).
Regarding the limitation labeling, by the processor, the feature vector according to at least one of the one or more differences associated with the medical personnel, Naveh teaches labeling, by the processor, a user profile according to at least one of the one or more differences associated with the user (¶54 “score may be based at least in part on differences between times when various retrieved actions (e.g., when the user obtained a product or a service) were performed and times when the retrieved actions were initially capable of being performed (e.g., when the product or service was additionally available)… smaller differences between times when retrieved actions were performed and times when the retrieved actions were initially capable of being performed increase the score for the pairing of the user and the subject area,” ¶63 “higher scores for the pairing of the user and the subject area indicate a greater propensity for adopting innovations in the subject area, so innovation labels corresponding to higher ranges of scores indicate the user is more likely to adopt innovations in the subject area,” Fig. 1 – 140, ¶65 “An innovation adoption label for a pairing of the user and the subject area is stored in a user profile associated with the user by the online system 140, allowing subsequent use of the innovation adoption label”). However, Naveh fails to teach the feature vector and medical personnel.
Rusak teaches medical personnel (¶170, ¶208). However, Rusak fails to teach the feature vector.
Yellowlees teaches the feature vector (¶119, ¶142 “the processor is further configured to label a feature vector comprising the words of the audio data and the retrieved clinical data with the indication of the selected clinical diagnosis”).
Naveh, Rusak, and Yellowlees are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain and training dataset for medical personnel of Rusak and the generating of a feature vector for medical personnel of Yellowlees with the methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and “to train the model for more accurate predictions” (Yellowlees, ¶132).
Regarding claim 17, Naveh in view of Rusak and further in view of Yellowlees teaches the method of claim 16 (and thus the rejection of claim 16 is incorporated).
Regarding the limitation comprising: identifying, by the processor, a plurality of differences between timestamps of a plurality of launches of medical products and timestamps of a plurality of prescriptions of the plurality of medical personnel for a plurality of medical products of a first product type, Naveh teaches comprising: identifying, by the processor, a plurality of differences between timestamps of a plurality of launches of… products and timestamps of a plurality of interactions of the plurality of users for a plurality of… products (¶11 “The online system may determine scores associated with parings of the user and different subject areas… a score for a pairing of the user and technology indicates the user has a high propensity for adopting innovations in technology, while a score for a pairing of the user and music indicates the user has a low propensity for adopting innovations, or changes, in music,” ¶¶35, 42) of a first product type (¶41 “a subject area refers to a field of knowledge or field of topics. Example subject areas include technology, music, food… and the like… the maintained information includes one or more actions describing the user's adoption of innovations in the subject area. Example actions describing the user's adoption of innovations in the subject area include: the user purchasing a new product or service in the subject area,” ¶6 “actions describing the user adopting innovations in a subject area of technology include actions where the user ordering or purchasing a product including a new or upgraded technology (e.g., buying a new smartphone),” ¶¶48-49 “a retrieved user action associated with a purchase of a new technology product includes a time when the user purchased the new technology product… an action describing adoption of one or more innovations in the subject area also identifies a time when the action was initially capable of being performed (e.g., a release date of a product or a service) or a difference between a time when the action was performed and the time when the action was initially capable of being performed”). However, Naveh fails to teach medical products, prescriptions, medical personnel, and medical products of a first product type.
Rusak teaches medical products (¶¶210, 215), prescriptions (¶¶93, 208, 215), medical personnel (¶170, ¶208), and medical products of a first product type (¶210 “treatment attempts for treatment of diabetes mellitus (e.g., unsuccessful treatment using gabapentin and lyrica, suggested treatments with limited side effects including amitryiptyline, lidocaine, and IVIG infusion),” ¶215 “the model has learned that optalgin is not prescribed for patients with G6PD deficiency (or has no such learned correlation) and the current user has performed the correlation of interaction journey to prescribe optalgin to a patient with G6PD deficiency”).
Regarding the limitation and determining, by the processor, a first value as a function of the plurality of differences, wherein labeling the feature vector according to the one or more of the plurality of differences comprises labeling the feature vector according to the first value, Naveh teaches and determining, by the processor, a first value as a function of the plurality of differences (Fig. 3 – 340, ¶54 “the score for the pairing of the user and the subject area is determined 340 based at least in part on times associated with the retrieved one or more actions and on one or more characteristics of the retrieved content associated with the one or more innovations in the subject area… The score may be based at least in part on differences between times when various retrieved actions… were performed and times when the retrieved actions were initially capable of being performed”), wherein labeling the profile according to the one or more plurality of differences comprises labeling the profile according to the first value (Fig. 1 – 140, Fig. 2 – 230, Fig. 3 – 350, ¶63 “Based on the determined score for the pairing of the user and the subject area, the online system 140 generates 350 an innovation adoption label for the pairing of the user and the subject area,” ¶38 “Scores associated with various pairings of the user and subject areas are stored by the innovation adoption classifier 230 in the user profile associated with the user,” ¶65 “An innovation adoption label for a pairing of the user and the subject area is stored in a user profile associated with the use”). However, the combination of Naveh and Rusak fails to teach the feature vector.
Yellowlees teaches the feature vector (¶119, ¶142).
Naveh, Rusak, and Yellowlees are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the medical domain and training dataset for medical personnel of Rusak and the generating of a feature vector for medical personnel of Yellowlees with the methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and “to train the model for more accurate predictions” (Yellowlees, ¶132).
Regarding claim 19, Naveh in view of Rusak and further in view of Yellowlees teaches the method of claim 17 (and thus the rejection of claim 17 is incorporated).
Regarding the limitation comprising: determining, by the processor, whether the first value exceeds a threshold, wherein labeling the feature vector according to the one or more of the plurality of differences comprises labeling, by the processor, the feature vector according to the determining of whether the first value exceeds the threshold, Naveh teaches comprising: determining, by the processor, whether the first value exceeds a threshold (Fig. 1 – 140, Fig. 4 – 410-440, ¶68 “FIG. 4 shows four threshold propensities 410, 420, 430, and 440 that define five ranges of propensities,” ¶75 “the online system 140 generates the innovation adoption labels of FIG. 4 for a user by comparing the determined scores for the user and the subject area with that of the ranges of scores specified by the threshold propensities 410, 420, 430, 440”), wherein labeling the profile according to the one or more of the plurality of differences comprises labeling, by the processor, the profile according to the determining of whether the first value exceeds the threshold (Fig. 1 – 140, Fig. 4 – 410-440, ¶75 “if the online system 140 determines that the determined score for the user for the technology subject area is between threshold scores corresponding to threshold propensities 420 and 430, the online system 140 generates the innovation adoption label corresponding to the range between threshold propensities 420 and 430, which is an innovation adoption label of ‘early majority’”). However, the combination of Naveh and Rusak fails to teach the feature vector.
Yellowlees teaches the feature vector (¶119, ¶142).
Naveh and Yellowlees are analogous art to the claimed invention as both are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the feature vector of Yellowlees with the labeling methodology of Naveh. The motivation to do so is to use machine learning “to train the model for more accurate predictions” (Yellowlees, ¶132).
Regarding claim 20, Naveh in view of Rusak and further in view of Yellowlees teaches the method of claim 16 (and thus the rejection of claim 16 is incorporated).
Regarding the limitation wherein generating the feature vector comprises inserting a type of the medical product into the feature vector, Rusak teaches a type of the medical product (¶¶210, 215). However, the combination of Naveh and Rusak fails to teach wherein generating the feature vector comprises inserting a type of the medical product into the feature vector.
Yellowlees teaches wherein generating the feature vector comprises inserting a diagnosis into the feature vector (¶67 “The analytics server may receive values of characteristics of the patient and/or the diagnosis options from a user (e.g., a clinician, doctor, or the patient themselves) via a user interface and generate a feature vector that includes the values”).
Naveh, Rusak, and Yellowlees are analogous art to the claimed invention as all are in the same field of endeavor of machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the type of medical product prescribed by medical personnel of Rusak and the generating of a feature vector for medical personnel of Yellowlees with the methodology of Naveh. The motivation to do so is to apply machine learning strategies in order to perform advanced analysis on medical data (Rusak, ¶143 “machine learning strategies… regression, statistics, and/or other strategies may be used to achieve advanced analysis”) and “to train the model for more accurate predictions” (Yellowlees, ¶132).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Naveh in view of Rusak and further in view of Yellowlees, and further in view of Choi (US 20200034857 A1, hereinafter Choi).
Regarding claim 18, Naveh in view of Rusak and further in view of Yellowlees teaches the method of claim 17 (and thus the rejection of claim 17 is incorporated).
Regarding the limitation wherein determining the first value comprises determining, by the processor, an average or a median of the plurality of differences, Naveh teaches determining the first value (Fig. 3 – 340, ¶54) and the plurality of differences (¶¶35, 41-42, 48-49). However, the combination of Naveh, Rusak, and Yellowlees fails to teach wherein determining the first value comprises determining, by the processor, an average or a median of the plurality of differences.
Choi, in the same field of endeavor, teaches wherein determining early adopters comprises determining, by the processor (Fig. 14 – 1400, 1402, ¶¶135-136 “FIG. 14 illustrates a detailed view of an exemplary computing device 1400 that can be used to implement the various apparatus and/or methods described herein… the computing device 1400 can include a processor 1402 that represents a microprocessor or controller for controlling the overall operation of computing device 1400”), an average or median of a plurality of differences in time (¶110 “A breakout date can be identified utilizing one of a variety of analytical methods… the historical download data is analyzed to determine on which date or range of dates the average number of downloads exceeds a specified level of daily downloads… a baseline level of 1,000 downloads per day can be specified as an indication of a breakout date. A window of particular size can be specified, such as a 7-day window, a 10-day window, a 30-day window… the historical download data can be analyzed within a moving window across a full date range of the historical download data for the digital asset to compare an average number of daily downloads within the window to the baseline level… the average number of daily downloads is calculated within a 10-day window, the average number of daily downloads being compared to the 1,000 download threshold to determine if the 10-day window is associated with a breakout date. If the average number of daily downloads exceeds the threshold value (e.g., the baseline value), then the 10-day window is associated with a breakout date, and the breakout date is identified within the 10-day window, such as selecting the earliest date within the 10-day window, the day within the 10-day window having the highest number of downloads, or the latest date within the 10-day window, for example,” ¶117 “for each digital asset in the set of digital assets where a breakout date has been identified, a list of early adopters that downloaded the digital asset prior to a corresponding breakout date for the digital asset are identified. The number of times a particular user is included in the list of early adopters across the set of digital assets having a breakout date can be counted and compared with a threshold value. If the number exceeds the threshold value, then that user can be identified as a trendsetter for that particular category of digital assets”).
Naveh and Choi are analogous art to the claimed invention as both are from the same field of endeavor of identifying early adopters. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the analytical methods of Choi with the methodology of Naveh. The motivation to do so is “to increase or reduce the desired number of trendsetters identified within a particular category of digital assets” (Choi, ¶117).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM M LEE whose telephone number is (571)272-4761. The examiner can normally be reached Mon-Fri. 8am-5pm.
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, Cesar Paula can be reached at (571)272-4128. 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.
/WILLIAM M LEE/
Examiner, Art Unit 2145
/CESAR B PAULA/Supervisory Patent Examiner, Art Unit 2145
Prosecution Insights