DETAILED ACTION
This nonfinal action is in response to application 18/477,359 filed on 09/28/2023 with priority to provisional application 63/578,521 filed on 08/24/2023.
Claims 1-20 are pending in the application. Claims 1, 10, 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 Objections
Claims 1, 4, 10-11, 15, and 17 are objected to because of the following informalities:
In claims 1, 10, and 15, “generating, by the one or more processors and using the machine learning model, one or more prediction scores for one or more prediction encounter data elements associated with the target classification based on one or more input temporal sequence of encounters data records comprising respective one or more input encounter data elements” should read ““generating, by the one or more processors and using the machine learning model, one or more prediction scores for one or more prediction encounter data elements associated with the target classification based on one or more input temporal sequences of encounters data records each comprising a respective one or more input encounter data elements” or be likewise amended to improve grammatical clarity.
In claims 4, 11, and 17, “determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers” should read “determining one or more maximum score feature values for a respective one or more of a plurality of scoring identifiers” to improve grammatical clarity.
Appropriate corrections are required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 4, 11, and 17 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 4, 11, and 17, they recite the limitation “determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of score feature values based on an exponential function comprising the plurality of maximum decile values”. There is insufficient antecedent basis for “the plurality of score feature values” in the claims. It is unclear if the “plurality of score feature values” is intended to refer to the previously recited “plurality of scores”, “one or more maximum score feature values”, or entirely different set of values. Consequently, one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
For purposes of examination, the limitation is interpreted as “determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of scores based on an exponential function comprising the plurality of maximum decile values”.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The analysis of the claims will follow the 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50 (“2019 PEG”).
Independent Claims (Claim 1, Claim 10, Claim 15):
Step 1: Claim 1 is drawn to a method, claim 10 is drawn to a system/apparatus, and claim 15 is drawn to a product. Therefore, each of these claims falls under one of the four categories of statutory subject matter (process/method, machine/apparatus, manufacture/product, or composition of matter).
Step 2A Prong 1: Claims 1, 10, and 15 each recite a judicially recognized exception of an abstract idea.
Claim 1 recites, inter alia:
generating a plurality of training embeddings based on a pre-training dataset, wherein the plurality of training embeddings comprises one or more of descriptive embeddings, sequential ordering embeddings, age/time embeddings, locale embeddings, or encounter number embeddings; – This limitation recites a generic transformation of dataset elements based on observation of values, and therefore recites a process of evaluation that a human could reasonably perform using pen and paper.
generating one or more prediction scores for one or more prediction encounter data elements associated with the target classification based on one or more input temporal sequence of encounters data records comprising respective one or more input encounter data elements – This limitation recites a determination of “score” values based on observation of data, and therefore recites a process of evaluation that a human could reasonably perform using pen and paper.
initiating the performance of one or more prediction-based actions based on the one or more prediction scores – This limitation recites performance of generic actions in response to calculated scores, and therefore recites a process of evaluation that a human could reasonably perform in the mind or using pen and paper.
Claims 10 and 15 recite substantially similar abstract idea limitations to those found in claim 1, and therefore recite the same abstract idea.
Step 2A Prong 2: The following additional elements recited in claims 1, 10, and 15 also do not integrate the recited judicial exceptions into a practical application.
Claim 1 additionally recites:
A computer-implemented method comprising: [generating/initiating] by one or more processors – This limitation amounts to mere instructions to implement an abstract idea on a computer or computer components.
generating one or more initialized weights associated with respective one or more layers of a machine learning model based on the plurality of training embeddings; generating one or more fine-tuned weights for the machine learning model by updating at least a portion of the one or more initialized weights using a fine-tuning dataset associated with a target classification; [generating one or more prediction scores] using the machine learning model – These limitations do no more than generically invoke a machine learning (ML) model architecture as a tool to perform an abstract procedure, and therefore amount to mere instructions to “apply” an exception.
Claims 10 and 15 recite substantially similar additional elements to those found in claim 1, and therefore also do not integrate the recited judicial exceptions into a practical application.
Step 2B: The additional elements recited in claims 1, 10, and 15 viewed individually or as an ordered combination, do not provide an inventive concept or otherwise amount to significantly more than the recited abstract ideas themselves.
Claim 1 additionally recites:
A computer-implemented method comprising: [generating/initiating] by one or more processors – Mere instructions to implement an abstract idea on a computer or computer components do not provide an inventive concept or significantly more to the recited abstract idea.
generating one or more initialized weights associated with respective one or more layers of a machine learning model based on the plurality of training embeddings; generating one or more fine-tuned weights for the machine learning model by updating at least a portion of the one or more initialized weights using a fine-tuning dataset associated with a target classification; [generating one or more prediction scores] using the machine learning model – Pre-training and fine-tuning phases are well-understood, routine, and conventional activity in the field of training ML models (e.g., BERT, transfer learning) (see O’Laughlin, “AI Foundations Part 1: Transformers, Pre-Training and Fine-Tuning, and Scaling” [pages 5-7]). As such, mere instructions to “apply” an exception do not provide an inventive concept or significantly more to the recited abstract idea.
Claims 10 and 15 recite substantially similar additional elements to those found in claim 1, and therefore also do not provide an inventive concept or significantly more to the recited abstract idea.
Even when considered as an ordered combination, the additional elements recited in the claims ultimately do no more than place the claims in the context of implementing an abstract procedure on a generic ML model architecture. As such, claims 1, 10, and 15 are not patent eligible.
Dependent Claims (Claims 2-9, Claims 11-14, Claims 16-20):
Dependent claims 2-9, 11-14, and 16-20 narrow the scope of independent claims 1, 10, and 15 and likewise narrow the recited judicial exceptions. They recite abstract idea limitations that are similar to those recited within the independent claims (i.e., mental processes and/or mathematical concepts), and thereby merely expand on the already recited exceptions. The dependent claims also do not recite any further additional elements that successfully integrate the recited judicial exceptions into a practical application or provide significantly more than the recited abstract ideas themselves. Consequently, claims 2-9, 11-14, and 16-20 are also rejected under 35 U.S.C. 101.
Step 1: Claims 2-9 are drawn to a method, claims 11-14 are drawn to a system/apparatus, and claims 16-20 are drawn to a product. Therefore, each of these claims falls under one of the four categories of statutory subject matter (process/method, machine/apparatus, manufacture/product, or composition of matter).
Step 2A Prong 1: Claims 2-9, 11-14, and 16-20 each recite a judicially recognized exception of an abstract idea.
Claim 2 recites the same judicial exception as claim 1.
Claim 3 recites the same judicial exception as claim 1.
Claim 4 recites, inter alia:
determining a plurality of deciles based on a plurality of scores; determining a plurality of maximum decile values associated with the plurality of deciles; determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of score feature values based on an exponential function comprising the plurality of maximum decile values; and assigning one or more pre-training score feature values to one or more of the plurality of deciles based on the plurality of maximum decile values. – These limitations recite repeated utilization of statistical techniques and/or mathematical functions to determine a series of values, and thereby recite mathematical calculation.
Claim 5 recites, inter alia:
determining one or more extra-record encounter data elements in one or more first training temporal sequence of encounters data records from the pre-training dataset; and determining one or more re-ordered encounter data elements in one or more second training temporal sequence of encounters data records from the pre-training dataset – These limitations amount to identification of data elements as being “extra” and/or “re-ordered” through observation, and therefore recite a process of evaluation that a human could reasonably perform using pen and paper.
Claim 6 recites, inter alia:
replacing a training encounter data element in at least one of the one or more first training temporal sequence of encounters data records with a substitute training encounter data element; and determining the substitute training encounter data element as an extra-record encounter data element – These limitations amount to identification of data elements as being “extra” through observation and mentally performable steps of data manipulation, and therefore recite a process of evaluation that a human could reasonably perform using pen and paper.
Claim 7 recites, inter alia:
re-arranging one or more training encounter data elements in at least one of the one or more second training temporal sequence of encounters data records; and determining the one or more training encounter data elements have been re-arranged – These limitations amount to identification of data elements as being “re-ordered” through observation and mentally performable steps of data manipulation, and therefore recite a process of evaluation that a human could reasonably perform using pen and paper.
Claim 8 recites the same judicial exception as claim 1.
Claim 9 recites the same judicial exception as claim 1.
Regarding claims 11-14, they recite substantially abstract idea limitations to those found in claims 4-7, and therefore recite the same judicial exceptions.
Regarding claims 16-20, they recite substantially abstract idea limitations to those found in claims 3-7, and therefore recite the same judicial exceptions.
Step 2A Prong 2: Claims 4-7, 11-14, and 17-20 do not recite any further additional elements besides those recited in the independent claims, and the following additional elements recited in claims 2-3, 8-9, and 16 also do not integrate the recited judicial exceptions into a practical application.
Claim 2 additionally recites:
wherein the machine learning model comprises a transformer machine learning model architecture – This limitation does no more than generically invoke a transformer model architecture as a tool to perform an abstract procedure, and therefore amount to mere instructions to “apply” an exception.
Claim 3 additionally recites:
wherein the machine learning model comprises a plurality of transformer layers, wherein each of the plurality of transformer layers comprises self-attention and a feedforward network – This limitation does no more than generically invoke a transformer model architecture as a tool to perform an abstract procedure, and therefore amount to mere instructions to “apply” an exception.
Claim 8 additionally recites:
wherein at least one of the one or more input temporal sequence of encounters data records, the pre-training dataset, or the finetuning dataset comprise structured data from one or more electronic data records – This limitation does no more than generally link a judicial exception to the field of use of analyzing electronic data records (e.g., electronic health data (EHR)).
Claim 9 additionally recites:
wherein the pre-training dataset comprises one or more of codes, code types, temporal information, location type information, sequential ordering information, or utilization information – This limitation does no more than generally link a judicial exception to the field of use of analyzing electronic data records (e.g., electronic health data (EHR)).
Regarding claim 16, it recites substantially similar additional elements to those found in claim 3, and therefore also does not integrate the recited judicial exception into a practical application.
Step 2B: The additional elements recited in claims 2-3, 8-9, and 16 viewed individually or as an ordered combination, do not provide an inventive concept or otherwise amount to significantly more than the recited abstract ideas themselves.
Claim 2 additionally recites:
wherein the machine learning model comprises a transformer machine learning model architecture – Mere instructions to “apply” an exception on a transformer model architecture do not provide an inventive concept or significantly more to the recited abstract idea.
Claim 3 additionally recites:
wherein the machine learning model comprises a plurality of transformer layers, wherein each of the plurality of transformer layers comprises self-attention and a feedforward network – Transformer layers comprising self-attention and feedforward network components is well-understood, routine, and conventional activity in the field of transformer models (e.g., BERT) (see Alammar, “The Illustrated Transformer” [pages 1-5]). As such, mere instructions to “apply” an exception do not provide an inventive concept or significantly more to the recited abstract idea.
Claim 8 additionally recites:
wherein at least one of the one or more input temporal sequence of encounters data records, the pre-training dataset, or the finetuning dataset comprise structured data from one or more electronic data records – Generally linking a judicial exception to the field of use of analyzing electronic data records (e.g., electronic health data (EHR)) does not provide an inventive concept or significantly more to the recited abstract idea.
Claim 9 additionally recites:
wherein the pre-training dataset comprises one or more of codes, code types, temporal information, location type information, sequential ordering information, or utilization information – Generally linking a judicial exception to the field of use of analyzing electronic data records (e.g., electronic health data (EHR)) does not provide an inventive concept or significantly more to the recited abstract idea.
Regarding claim 16, it recites substantially similar additional elements to those found in claim 3, and therefore also does not provide an inventive concept or significantly more to the recited abstract idea.
Even when considered as an ordered combination, the additional elements recited in the claims ultimately do no more than place the claims in the context of implementing an abstract procedure on a generic transformer model architecture and analyzing electronic record data. As such, claims 2-9, 11-14, and 16-20 also are not patent eligible.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-3, 8-10, and 15-16 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Poulain et al. (“Transformer-based Multi-target Regression on Electronic Health Records for Primordial Prevention of Cardiovascular Disease”, available conference 2021), hereinafter Poulain.
Regarding claim 1, Poulain discloses A computer-implemented method (“In this study, we propose a multi-target regression model leveraging transformers to learn the bidirectional representations of EHR data and predict the future values of 11 major modifiable risk factors of cardiovascular disease (CVD). Inspired by the proven results of pre-training in natural language processing studies, we apply the same principles on EHR data, dividing the training of our model into two phases: pre-training and fine-tuning. We use the finetuned transformer model in a “multi-target regression” theme. Following this theme, we combine the 11 disjoint prediction tasks by adding shared and target-specific layers to the model and jointly train the entire model. We evaluate the performance of our proposed method on a large publicly available EHR dataset. Through various experiments, we demonstrate that the proposed method obtains a significant improvement (12.6% MAE on average across all 11 different outputs) over the baselines” [Poulain Abstract]) comprising:
generating, by one or more processors, a plurality of training embeddings based on a pretraining dataset, wherein the plurality of training embeddings comprises one or more of descriptive embeddings, sequential ordering embeddings, age/time embeddings, locale embeddings, or encounter number embeddings (see Fig. 1 – “EHR data representation for a fictional patient with three total visits. The CLS, SEP, and END tokens denote the beginning of the patient’s record, the separation between two visits, and the end of the record, respectively. For the input embeddings, C1, C2, and C3 refer to the first, second, and third conditions of the vocabulary…The sex, race, and ethnicity embeddings are numerical values that refer to their respective categories as described in our GitHub. The segment embeddings alternate between 0 and 1 from one visit to the other and the position embeddings denotes the visit number each token belongs to. The seven different embeddings are then summed up to create the embeddings output sequence before being fed into the model as the input to serve as the full representation of a patient’s record” [Poulain page 728])
generating, by the one or more processors, one or more initialized weights associated with respective one or more layers of a machine learning model based on the plurality of training embeddings (“We pre-trained our model using the same approach as BEHRT, itself based on BERT using the masked language modeling (MLM) approach, where a percentage of the input tokens are masked at random and then predicted by the model. Following this approach, during the tokenization process of the input sequences, we randomly selected 15% of the medical codes to be predicted by the model. We then replaced 80% of these codes (12% of all observed medical codes) with the MASK token, 10% (1.5% of all observed medical codes) with another randomly picked medical code, and left the remaining 10% (1.5% of all observed medical codes) of the codes unchanged. This process adds noise to the input data, forcing the model to fight through the noise during the pre-training process. The modified input tokens will then be embedded and fed into the transformer layers and the output of these layers will be used to perform the MLM prediction and be trained using the cross-entropy loss…Following a transfer-learning approach, after the pre-training process, we initialized the embeddings and the transformer’s weights of the fine-tuned model with the pre-trained ones, allowing the model to use the knowledge acquired during the MLM process” [Poulain page 729 Pre-training]);
generating, by the one or more processors, one or more fine-tuned weights for the machine learning model by updating at least a portion of the one or more initialized weights using a fine-tuning dataset associated with a target classification (“We use the finetuned transformer model in a “multi-target regression” theme. Following this theme, we combine the 11 disjoint prediction tasks by adding shared and target-specific layers to the model and jointly train the entire model” [Poulain Abstract]; “As shown in the DeepMTR paper, having layers with shared parameters composed of maxout units [24] and target-specific layers increases the overall performance of the MTR task. We have, therefore, added three shared linear layers composed of maxout units with a parameter k (number of hidden units) of 5 and three target-specific linear layers for each of our 11 target outputs. A schematic representation of the model’s architecture is shown in Fig. 3, where, during the fine-tuning process, the pooled output (extraction of the CLS token representation) of transformers’ layers is used as input to the model’s first shared layer. The shared layers are processed sequentially, and the output of the last layer is fed into Ng (11 in our case) targetspecific sub-networks… We compute the loss for every target output by multiplying the squared error of each patient with its corresponding masking vector mg to only account for the non-missing values for each target output. We divide the total loss for each target output by the total number of non-missing values that are recorded among all patients for that target output. We then define the overall loss as the average loss across every target output” [Poulain page 729 Fine-tuning]; Shared layers and task-specific layers are added, and the entire model architecture is then jointly trained (i.e., weights are updated, including that of the transformer model) to be task-aware based on calculated prediction loss for target outputs (i.e., target classification))
generating, by the one or more processors and using the machine learning model, one or more prediction scores for one or more prediction encounter data elements associated with the target classification (“We used the fine-tuning process of the model to predict the 11 CVD risk factors through MTR… To account for the fact that some target outputs are more prevalent in the dataset than others (the data imbalance), we defined our fine-tuning loss function as the average mean squared error (MSE) between the ground truth yg and the predicted value ^ yg of every target output g as shown in Eq. 2” [Poulain page 729 Fine-tuning]; Within the target output, each predicted value ^yg represents a predicted score by the model for the corresponding risk factor (see also ^y1…^yNg as output of Target Specific Layers in Fig. 3 [Poulain page 729])) based on one or more input temporal sequence of encounters data records comprising respective one or more input encounter data elements (see Fig. 1 as detailed above [Poulain page 728] and Embeddings Output Sequence in Fig. 3 [Poulain page 729]); and
initiating, by the one or more processors, the performance of one or more prediction-based actions based on the one or more prediction scores (“To evaluate the performance of our model, we have compared our method to multiple popular EHR prediction models… All the experiments below have been realized using 5-fold crossvalidation and we use the Root Mean Squared Error (RMSE) for each target output among the labeled data as our evaluation metric. Table II shows the RMSE in predicting each of the 11 risk factors, plus the overall mean RMSE (across all 11). Our proposed method outperforms other baselines for most target outputs, as well as for the mean of the RMSE scores” [Poulain page 730]; The calculated values of target outputs are further utilized to calculate RMSE and compare prediction performance to other models (i.e. prediction-based action)).
Regarding claim 2, Poulain discloses the limitations of parent claim 1 and wherein the machine learning model comprises a transformer machine learning model architecture (“First, we present a transformer-based model modifying the original BERT architecture that receives EHR data to generate representations of
the data. Second, we propose a novel architecture that connects the output of our transformer model to a DNN for multi-target regression to allow our model to accurately predict the value of the targeted medical measurements” [Poulain pages 726-727 Introduction]).
Regarding claim 3, Poulain discloses the limitations of parent claim 1 and wherein the machine learning model comprises a plurality of transformer layers, wherein each of the plurality of transformer layers comprises self-attention and a feedforward network (see Bidirectional Transformer Layers in Fig. 3 [Poulain page 729]; “Among the most successful examples of related studies reconciling natural language processing (NLP) and EHR data are the attention-based models [14], originally designed for the NLP tasks, that have been shown very effective at capturing
the longitudinal aspects of EHR data…Li et al. extended BERT [13] to EHR data by formulating longitudinal EHR data as an NLP task to predict the diagnoses at a given visit [11]. They named the new architecture, BEHRT (referring to BERT + EHR)” [Poulain page 727 Related Work]; “We refer the reader to the BERT [13] and BEHRT [11] papers for additional information about the transformer’s architecture and the pretraining process” [Poulain page 729 Pre-training]; Standard transformer architectures (e.g., BERT/BEHRT) implicitly consist of layers comprising self-attention and feedforward network components (see also Alammar, “The Illustrated Transformer” [pages 1-5]))
Regarding claim 8, Poulain discloses the limitations of parent claim 1 and wherein at least one of the one or more input temporal sequence of encounters data records, the pre-training dataset, or the fine-tuning dataset comprise structured data from one or more electronic data records (“In this study, we used the EHR portion of the All of Us Research Program [21], which is a publicly available dataset collected from data donations of over one million adults (18 yr+) participants in the US1…Our final cohort included 6,993 patients (1,498 males and 5,495 females). For
these patients, we extracted the demographics, conditions, prescriptions, and laboratory measurements from the original dataset” [Poulain page 727 Materials and Methods])
Regarding claim 9, Poulain discloses the limitations of parent claim 1 and wherein the pre-training dataset comprises one or more of codes, code types, temporal information, location type information, sequential ordering information, or utilization information (“To reduce the number of condition and prescription codes, we grouped them using the “IsA” relationship from the concept relationship table. This process reduced the number of codes from 15,375 to 574 and 14,118 to 495, for the conditions and prescriptions, respectively” [Poulain page 727 Materials and Methods])
Regarding claim 10, it is an apparatus claim that substantially corresponds to the method of claim 1, which is already disclosed by Poulain as detailed above. Poulain further discloses A computing system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to perform the claimed functions (“We evaluate the performance of our proposed method on a large publicly available EHR dataset. Through various experiments, we demonstrate that the proposed method obtains a significant improvement (12.6% MAE on average across all 11 different outputs) over the baselines”) [Poulain Abstract]; Evaluation of the proposed method on a large dataset implicitly requires a computer (i.e., processor coupled to memory) with adequate processing power for execution of model training and evaluation). Consequently, claim 10 is rejected for the same reasons as claim 1.
Regarding claims 15 and 16, they are product claims that substantially correspond to the method of claim 1 and 3, which are already disclosed by Poulain as detailed above. Poulain further discloses One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to: perform the claimed functions (“We evaluate the performance of our proposed method on a large publicly available EHR dataset. Through various experiments, we demonstrate that the proposed method obtains a significant improvement (12.6% MAE on average across all 11 different outputs) over the baselines” [Poulain Abstract]; Evaluation of the proposed method on a large dataset implicitly requires memory (i.e., non-transitory computer-readable storage media) coupled to a processor with adequate power for execution of model training and evaluation). Consequently, claims 15 and 16 are rejected for the same reasons as claims 1 and 3.
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 4, 11, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Poulain (“Transformer-based Multi-target Regression on Electronic Health Records for Primordial Prevention of Cardiovascular Disease”, available conference 2021), as applied to claims 1, 10, and 15 above, further in view of Solberg et al. (“Detection of Outliers in Reference Distributions: Performance of Horn’s Algorithm”, published 2005) hereinafter Solberg.
Regarding claim 4, Poulain teaches the limitations of parent claim 1, and further teaches tokenizing at least a portion of the pre-training dataset by:
determining a plurality of deciles based on a plurality of scores; (“We formatted our data by following a similar method used in other transformer architectures for EHR data and define the entire record of each patient as a document, the visits as sentences, and prescriptions, measurements, and conditions as words. For the measurements, we discretized the values of each variable into deciles” [Poulain page 728 Materials and Methods]; For measurements in the dataset, the range of values (i.e., scores) is broken up into deciles)
determining a plurality of maximum decile values associated with the plurality of deciles; ([Poulain page 728 Materials and Methods] as detailed above; Determining deciles for a range of measurements inherently requires determination of a minimum and maximum measurement value for each decile) and
assigning one or more pre-training score feature values to one or more of the plurality of deciles based on the plurality of maximum decile values (“For example, an SBP value between the 3rd and the 4th decile would be transformed into the word SBP_30. This process created a measurement vocabulary M of size 10 _ Nm, with Nm being the number of unique measurements in the dataset used by our model” [Poulain page 728 Materials and Methods]; Based on established range (i.e., min value to max value) of values for each decile, feature values are transformed into the corresponding word (i.e., pre-training score feature value))
However, Poulain does not expressly teach determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of score feature values based on an exponential function comprising the plurality of maximum decile values.
In the same field of endeavor, Solberg discloses a means of pre-processing medical data to enable further analytics (“Medical laboratory reference data may be contaminated with outliers that should be eliminated before estimation of the reference interval. A statistical test for outliers has been proposed by Paul S. Horn and coworkers (Clin Chem 2001;47:2137– 45). The algorithm operates in 2 steps: (a) mathematically transform the original data to approximate a gaussian distribution; and (b) establish detection limits (Tukey fences) based on the central part of the transformed distribution” [Solberg Abstract]) that determin[es] one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of score feature values (“The algorithm operates in 2 steps: In the first step, the original data are transformed to approximate a gaussian distribution, to the extent this is possible in the presence of outliers. Horn et al. (8 ) used for this purpose the Box–Cox function (9 ). In the second step, 2 detection limits (fences) are established based on the middle 50% of the transformed distribution, as suggested earlier by Tukey (10 ). Possible outliers are identified as the values located outside of these fences” [Solberg pages 2326-2327]; “Pseudo-random data were generated for the distributions described above (Table 1). All experiments presented here were based on distributions with n = 1000 values each… We analyzed each data set by applying 2 (sensitivity study) or 3 (specificity study) of the versions of Horn’s algorithm for outlier detection that were presented above” [Solberg page 2328 Simulation Experiments]; The disclosed algorithm identifies, for a distribution of values (wherein the distribution may be representative of a given feature/property of medical data (i.e., scoring identifier)), fence values determining a minimum and maximum (i.e., maximum score feature value) possible value, and identifies as outliers all values outside those fences) based on an exponential function comprising the plurality of maximum decile values (““The algorithm operates in 2 steps: In the first step, the original data are transformed to approximate a gaussian distribution, to the extent this is possible in the presence of outliers. Horn et al. (8 ) used for this purpose the Box–Cox function (9 )” [Solberg pages 2326]; “Mathematical functions can transform data of nongaussian distributions to approximate the theoretical gaussian distribution. Three functions of this kind were used in our study. One of these, the Box–Cox transformation function (9 ), which was used in the original Horn’s algorithm for outlier detection (8 ), is as follows…The 2 other transformations considered in the present study are those of the 2-stage normalization procedure recommended by the IFCC for parametric estimation of reference limits (1 ). Manly’s exponential function (11 ) corrects for nongaussian skewness:… We also studied 2 modifications of Horn’s algorithm. In the first step of the algorithm, we replaced the Box–Cox transformation either with the exponential transformation or with a 2-stage transformation consisting of the exponential transformation followed by the modulus transformation” [Solberg pages 2327-2328 Transformations and Horn’s Algorithm and its Modifications]; An exponential function may be utilized to capture the original distribution of the data in the first step of the disclosed algorithm – such a function that represents an entire distribution further implicitly represents its decile values).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have incorporated determining one or more maximum score feature values for respective one or more of a plurality of scoring identifiers associated with the plurality of score feature values based on an exponential function comprising the plurality of maximum decile values as taught by Solberg into Poulain because they are both directed towards means of pre-processing medical data to enable further analytics. Incorporating the teachings of Solberg would allow for the detection and elimination of outliers in measurement data prior to tokenization, thereby preventing downstream prediction tasks from being skewed by noise or extreme/contaminated values [Solberg Abstract].
Regarding claims 11 and 17, they are apparatus and product claims that substantially correspond to the method of claim 4, which is already taught by the combination of Poulain and Solberg as detailed above. Consequently, they are rejected for the same reasons as claim 4.
Claims 5-7, 12-14, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Poulain (“Transformer-based Multi-target Regression on Electronic Health Records for Primordial Prevention of Cardiovascular Disease”, available conference 2021), as applied to claims 1, 10, and 15 above, further in view of Ren et al. (“Generative Adversarial Networks Enhanced Pre-training for Insufficient Electronic Health Records Modeling”, published August 2022), hereinafter Ren.
Regarding claim 5, Poulain teaches the limitations of parent claim 1 and wherein generating the one or more initialized weights further comprises pre-training the one or more initialized weights by:
determining one or more extra-record encounter data elements in one or more first training temporal sequence of encounters data records from the pre-training dataset (“We pre-trained our model using the same approach as BEHRT, itself based on BERT using the masked-language modeling (MLM) approach, where a percentage of the input tokens are masked at random and then predicted by the model. Following this approach, during the tokenization process of the input sequences, we randomly selected 15% of the medical codes to be predicted by the model. We then replaced 80% of these codes (12% of all observed medical codes) with the MASK token, 10% (1.5% of all observed medical codes) with another randomly picked medical code, and left the remaining 10% (1.5% of all observed medical codes) of the codes unchanged. This process adds noise to the input data, forcing the model to fight through the noise during the pre-training process. The modified input tokens will then be embedded and fed into the transformer layers and the output of these layers will be used to perform the MLM prediction and be trained using the cross-entropy loss” [Poulain page 729 Pre-training]; A portion of input tokens are replaced with a MASK token (i.e. marked as extra-record data element) and then predicted as a pre-training task).
However, Poulain does not teach determining one or more re-ordered encounter data elements in one or more second training temporal sequence of encounters data records from the pre-training dataset.
In the same field of endeavor, Ren teaches a means of leveraging electronic health records data for disease prediction through a transformer-based machine learning model (“In recent years, automatic computational systems based on deep learning are widely used in medical fields, such as automatic diagnosing and disease prediction. Most of these systems are designed for data sufficient scenarios… Many data augmentation methods have been proposed to solve the data insufficiency problem, such as using GAN (Generative Adversarial Networks) to generate training data. However, the augmented data usually contains lots of noise. Directly using them to train sensitive medical models is very difficult to achieve satisfactory results. To overcome this problem, we propose a novel deep model learning method for insufficient EHR (Electronic Health Record) data modeling, namely GRACE, which stands GeneRative Adversarial networks enhanCed prE-training. In the method, we propose an item-relation-aware GAN to capture changing trends and correlations among data for generating high-quality EHR records. Furthermore, we design a pre-training mechanism consisting of a masked records prediction task and a real-fake contrastive learning task to learn representations for EHR data using both generated and real data. After the pre-training, only the representations of real data is used to train the final prediction model” [Ren Abstract]) that determin[es] one or more re-ordered encounter data elements in one or more second training temporal sequence of encounters data records from the pre-training dataset (“The generator aims to generate fake visit sequences from random vectors. Since the target are visit sequences, our model first generates a hidden state vector ˜𝒔𝜏 from a random vector 𝒛 as
PNG
media_image1.png
37
319
media_image1.png
Greyscale
, where
PNG
media_image2.png
34
143
media_image2.png
Greyscale
and
PNG
media_image3.png
30
102
media_image3.png
Greyscale
are learnable parameters, p(z) denotes a random distribution (i.e., Gaussian distribution). Then, the GAN model uses a Transformer decoder to decode the hidden state vector as a visit sequences, i.e.,
PNG
media_image4.png
33
486
media_image4.png
Greyscale
… Since the EHR data is very complicated and contains rich semantic information, if we direct use random parameters to initialize the Transformer decoder, it is very hard to accomplish the sequence generation task. To overcome this issue, we design an AutoEncoder initialization mechanism to set the parameter of the Transformer decoder in Eq. (3). The AutoEncoder contains an encoder and a decoder. The encoder is responsible for encoding a real visit sequence data as a dense vector… Once the AutoEncoder has been trained, we initialize the TansformerDecoder in Eq. (3) with the TansformerDecoder of the AutoEncoder (in Eq. (6)). In this way, the data characteristics of the real visit sequence are memorized by the TansformerDecoder, and therefore it can be used to generate higher quality fake data” [Ren page 3812 EHR Generator]; “Although the item-relation-aware GAN can effectively capture the characteristics of EHR data and generate reasonable data, there is also a gap between the fake data and the real data. We believe a representation that can distinguish real and fake samples is more effective for real data modeling. Based on this insight, we design a real-fake contrastive task to train the representation learning model. Specifically, for a fake sample in a mini-batch, we use the representations of sequences from the fake data as positive samples and the rest representations as negative samples. We employ a contrastive loss function, called InfoNCE [31], to classify positive and negative samples” [Ren page 3813 Pre-training task #2: Real-Fake Contrastive Learning]; Because the parameters of the TransformerDecoder are learned directly based on structural patterns of real visit sequences, the fake visit sequences generated by the GAN model are broadly interpretable as a re-ordering of real visit sequence patterns via transformation of noise vector z through learned latent distribution parameters. The pre-training task then attempts to detect the fake visit sequences (i.e., re-ordered encounter data elements) in the overall mini-batch of samples).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have incorporated determining one or more re-ordered encounter data elements in one or more second training temporal sequence of encounters data records from the pre-training dataset as taught by Ren into Poulain because they are both directed towards leveraging electronic health records data for disease prediction through transformer-based machine learning models. Incorporating the teachings of Ren would enable the resulting model to better handle insufficient / low sample data records and avoid overfitting [Ren Abstract].
Regarding claim 6, the combination of Poulain and Ren teaches the limitations of parent claim 5, and Poulain further teaches wherein determining the one or more extra-record encounter data elements further comprises:
replacing a training encounter data element in at least one of the one or more first training temporal sequence of encounters data records with a substitute training encounter data element; (“We then replaced 80% of these codes (12% of all observed medical codes) with the MASK token, 10% (1.5% of all observed medical codes) with another randomly picked medical code, and left the remaining 10% (1.5% of all observed medical codes) of the codes unchanged” [Poulain page 729 Pre-training]) and
determining, using the machine learning model, the substitute training encounter data element as an extra-record encounter data element. ([Poulain page 729 Pre-training] as detailed in claim 5 above; The MLM prediction task attempts to predict the input tokens (i.e., extra-record elements) that were replaced with the substitute tokens).
Regarding claim 7, the combination of Poulain and Ren teaches the limitations of parent claim 5, and Ren further teaches wherein determining one or more re-ordered encounter data elements further comprises:
re-arranging one or more training encounter data elements in at least one of the one or more second training temporal sequence of encounters data records; ([Ren page 3812 EHR Generator] as detailed in claim 5 above; Because the parameters of the TransformerDecoder are learned directly based on structural patterns of real visit sequences, the fake visit sequences generated by the GAN model are broadly interpretable as a re-ordering of real visit sequence patterns via transformation of noise vector z through learned latent distribution parameters) and
determining, using the machine learning model, the one or more training encounter data elements have been re-arranged. ([Ren page 3813 Pre-training task #2: Real-Fake Contrastive Learning] as detailed in claim 5 above; The pre-training task then attempts to detect the fake visit sequences (i.e., re-ordered encounter data elements) in the overall mini-batch of samples)
Regarding claims 12-14 and 18-20, they are apparatus and product claims that substantially correspond to the methods of claims 5-7, which are already taught by the combination of Poulain and Ren as detailed above. Consequently, they are rejected for the same reasons as claims 5-7.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Alammar (“The Illustrated Transformer”, available online 27 Jun 2018) discloses a review of transformer models as commonly implemented in machine learning applications.
O’Laughlin (“AI Foundations Part 1: Transformers, Pre-Training and Fine-Tuning, and Scaling”, available online 11 Apr 2023) discloses a review of foundational papers in the art that established transformer models (and subsequent natural language processing models such as BERT).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VIJAY M BALAKRISHNAN whose telephone number is (571) 272-0455. The examiner can normally be reached 10am-5pm EST Mon-Thurs.
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, JENNIFER WELCH can be reached on (571) 272-7212. 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.
/V.M.B./
Examiner, Art Unit 2143
/JENNIFER N WELCH/Supervisory Patent Examiner, Art Unit 2143
Prosecution Insights