DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7/31/2026 has been entered.
No claims have been amended, canceled or added. Claims 1, 5-13, 16-17, and 20-21 have been examined.
Response to Arguments
Applicant’s arguments, see pp. 9-11, filed 4/3/2026, with respect to the rejection(s) of claim(s) 1, 11 and 20 under 35 USC 103 have been fully considered and are persuasive. Therefore, the prior rejections have been withdrawn as indicated in the 6/30/2026 Notice of Allowance. However, upon further consideration, a new ground(s) of rejection is made in view of U.S. Patent Application Publication 20140316220 by Sheldon and U.S. Patent 6658396 to Tang et al. as cited in the 7/31/2026 IDS.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 6-12, 17 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application 20200027539 by Xie et al. ("Xie") in view of U.S. Patent 7917438 to Kenedy et al. ("Kenedy"), U.S. Patent Application 20190180882 by Han et al. ("Han"), U.S. Patent Application 20200152320 by Ghazaleh et al. ("Ghazaleh"), U.S. Patent Application Publication 20140316220 by Sheldon (“Sheldon”) and U.S. Patent 6658396 to Tang et al. (“Tang”).
In regard to claim 1, Xie discloses:
1. A method for training machine learning models to recommend treatments for a living organism to address a medical condition, comprising: See Xie, ¶ 0018, “In one aspect of the disclosure, a method of predicting medications to prescribe to a patient.”
a) receiving a data set of attributes, each respective record in the data set of attributes being associated with a living organism and including information related to one or more attributes, an indication of a medical condition, a treatment applied to the living organism, information about side effects of the treatment and …; See Xie, ¶ 0032, “records identifying one or more conditions of the patient.” Also ¶ 0033, “a machine-learned algorithm 110a for use in the medication prediction module 104 is previously trained in accordance with a training set K of medication i vectors ai 202, where { ai }i=1K and a training set of clinical information vectors x 204 to associate clinical information with medications.” Also ¶ 0035, “what conditions/diseases the medication can treat, and its side effects, dosage, and so on.” Also ¶ 0036, “current medication, vital signs, symptoms, laboratory results, past medical history.” Also ¶ 0052, “The antagonism interaction indicates that when used together, two medications may bring in a negative medical effect. Medications with antagonism interactions should be prohibited from being used together. The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease.”
Xie does not expressly disclose: a severity of the side effects, and an indication of treatment success. However, this is taught by Kenedy. See Kenedy, col. 12, lines 27-44, e.g. “the outcome data used to derive outcomes such as success levels can include considerably more varied and complicated measures of success … ratings for factors such as product cost, ease of product usage, number of side effects, severity of side effects, number of symptoms resolved and speed of symptom resolution.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Kenedy’s data with Xie’s data in order to provide considerations for varied and complicated measures of success as suggested by Kenedy.
Xie does not expressly disclose: b) replacing null values for features in the received data set with an indication that the features do not apply to the living organism; However, this is taught by Han. See Han, ¶ 0056, “The masking data may be configured to distinguish feature data having a data value from feature data having a missing data value.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Han’s null value indication in order to distinguish feature data having a value from feature data having a missing value as suggested by Han.
c) generating a training data set by featurizing the one or more attributes, the indicated medical condition, the treatment applied, the information about side effects of the treatment and the severity of the side effects, and the indication of treatment success; See Xie, ¶ 0034, “The training set K of medication i vectors ai 202 and the training set of clinical information vectors x 204 used to train the machine-learned algorithm 110, are obtained using a text encoding module 206.”
wherein featurizing the one or more attributes comprises, for each respective medical attribute of the one or more attributes, assigning one of a plurality of values, See Xie, ¶ 0031 and 0036, “produce a representation of the clinical information as a clinical-information vector x.”
Xie does not expressly disclose: each value indicating a classification of the respective medical attribute into one of a plurality of categories, and However, this is taught by Ghazaleh. See Ghazaleh, Fig 3A and ¶ 0042-0043, e.g. “Each data category of demographic data 205, diagnosis data 206, and treatment administration data 106 can be mapped to a feature of patient features vector 301. A feature of patient features vector 301 can correspond to a data category, and the value of the data category (represented by the grey box) can be encoded into a feature value.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Ghazaleh’s featurization with Xie’s data in order to provide a format that can be used by machine learning as essentially suggested by Ghazaleh.
wherein generating the training data set comprises: … featurizing the … value of the item. See Xie, ¶ 0034 as cited above.
Xie does not expressly disclose: scaling a value of at least one item in the data set based on a scaling factor associated with an accuracy of a source from which the value was obtained, and featurizing the scaled value; and This is taught by Sheldon. See Sheldon, ¶ 0032, “A determination is made to see if the data is current and sufficient to provide a reasonably accurate baseline and range measurement. … The system could account for this choice by providing a weighted value for these parameters when they are not current.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Sheldon’s weight scaling in order to account for data sufficiency as suggested by Sheldon.
Xie does not expressly disclose: scaling a value of at least one item in the data set based on a scaling factor associated with a severity of the side effects associated with a treatment, and featurizing the scaled value; This is taught by Tang. See Tang, col. 15 line 56 - col. 16 line 12, e.g.: “The following describes in more detail how to prepare the example data sets used to train the neural net and the test data sets used to test the neural net. … The categories developed could fall into two groups: … 2) categories of information which relate to factors which help assess how well a drug is working. … The categories in group 2 can include side effects (health characteristics during treatment such as nausea, headaches, vomiting, diarrhea etc.) and drug efficacy measures (such as symptom levels and pharmacokinetic peptide levels). … Each category should have associated with it a value scale to quantify the information. The value scale in many instances will be determined by the category of information.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Tang’s side effect quantification in order to determine acceptable drug dosage as suggested by Tang (see col. 15, lines 58-60).
Xie also discloses:
d) training one or more machine learning models to recommend one or more treatments to apply to the living organism to treat the medical condition based on the generated training data set; and See Xie, ¶ 0033, “a machine-learned algorithm 110a for use in the medication prediction module 104 is previously trained in accordance with a training set.”
e) deploying the trained one or more machine learning models to a computing system for use in treating a living organism. See Xie, Fig. 1, depicting a deployed machine learning model.
wherein the data set of attributes comprises medical … information about the living organism, received from a plurality of data sources. See Xie, Fig. 3 and associated text at least at ¶ 0040, “The text encoding module 308 is configured to receive a medication record 310 … a medication record 312 … a clinical information records 314 … The conditions may include, for example, one or more of the patient's current medication, vital signs, symptoms, laboratory results, past medical history, family history, social history, and allergies.”
Xie does not expressly disclose: activity, and environmental information. This is taught by Kenedy. See col. 3, lines 24-25, “features of the customer such as … diet, lifestyle, and zip code (i.e., location).” Note that a broad but reasonable interpretation allows lifestyle to read on activity information, and diet and zip code to read on environmental information. Also see fig. 2 and col. 11, lines 34-36 “provide exercise therapy.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Kenedy’s information with Xie’s data in order to provide better outcomes and higher levels of satisfaction, thereby reducing waste and increasing efficiency in the healthcare industry as well as potentially minimizing adverse reactions, complications and deaths, as suggested by Kenedy (see col. 2, line 63 – col. 3, line 2).
In regard to claim 6, Xie also discloses:
6. The method of claim 5, further comprising: aggregating information from the plurality of external data sources into a single record for each living organism. See Xie, ¶ 0032, “Regarding the text encoding module 102, it is configured to extract information from the clinical record, and derive the clinical-information vector x 108 from the extracted information.”
In regard to claim 7, Xie does not expressly disclose:
7. The method of claim 5, wherein the plurality of external data sources comprises a secure medical records data source and one or more other data sources. However, this is taught by Kenedy. See col. 8, lines 6-8, “The identities of the consumers can be masked or anonymized for privacy or security purposes.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data source with Kenedy’s security in order to retain privacy as suggested by Kenedy.
In regard to claim 8, Xie also discloses:
8. The method of claim 7, wherein the one or more other data sources include one or more of a physical activity records data source, or a medicine usage data source. See Xie, Fig. 2 element 208.
In regard to claim 9, Xie also discloses:
9. The method of claim 1, wherein the one or more machine learning models comprise clustering-based machine learning models. See Xie, ¶ 0070, “clustering.”
In regard to claim 10, Xie discloses:
10. The method of claim 1, wherein the one or more machine learning models comprise probabilistic models in which efficacy of each of a plurality of treatments is represented by a probability distribution over each treatment in a set of treatments for the medical condition. See Xie, e.g. ¶ 0043, “the medication correlation module 402 implements a determinantal point process (DPP) that captures the correlations among the medications and outputs scalar measures 404 indicating the correlation of a medication i and a medication j.” Also e.g. ¶ 0047, “the kernel matrix L is computed and probability defined over medication-subset.” Also ¶ 0052, “The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease.”
In regard to claim 11, Xie discloses:
11. A method for identifying treatments for a living organism to treat a medical condition based on one or more machine learning models, comprising: See Xie, ¶ 0018, “In one aspect of the disclosure, a method of predicting medications to prescribe to a patient.
a) receiving a request to identify one or more recommended treatments for a medical condition, the request including a data set of living organism attributes; See Xie, Fig. 1, element 106, providing a broad interpretation of a request. Also see ¶ 0079, “For example, a clinician seeking to obtain a set of medications to prescribe to a subject patient, may input a record or a number of input records of a subject patient for processing. The clinician may then initiate execution of the medication prediction system processing instructions stored in the computer readable media 604 through the user interface 608, and await a display of the predicted medications.”
b) generating a feature vector based on the data set of living organism attributes …; See Xie, ¶ 0034, “The training set K of medication i vectors ai 202 and the training set of clinical information vectors x 204 used to train the machine-learned algorithm 110, are obtained using a text encoding module 206.”
Xie does not expressly disclose: … by a process comprising, i) replacing null values for features in the data set with an indication that the features do not apply to the living organism, However, this is taught by Han. See Han, ¶ 0056, “The masking data may be configured to distinguish feature data having a data value from feature data having a missing data value.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Han’s null value indication in order to distinguish feature data having a value from feature data having a missing value as suggested by Han.
Xie does not expressly disclose: ii) scaling a value of at least one attribute in the data set based on a scaling factor associated with an accuracy of a source from which the value was obtained, This is taught by Sheldon. See Sheldon, ¶ 0032, “A determination is made to see if the data is current and sufficient to provide a reasonably accurate baseline and range measurement. … The system could account for this choice by providing a weighted value for these parameters when they are not current.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Sheldon’s weight scaling in order to account for data sufficiency as suggested by Sheldon.
Xie does not expressly disclose: iii) scaling a value of at least one attribute in the data set based on a scaling factor associated with a severity of the side effects associated with a treatment, and This is taught by Tang. See Tang, col. 15 line 56 - col. 16 line 12, e.g.: “The following describes in more detail how to prepare the example data sets used to train the neural net and the test data sets used to test the neural net. … The categories developed could fall into two groups: … 2) categories of information which relate to factors which help assess how well a drug is working. … The categories in group 2 can include side effects (health characteristics during treatment such as nausea, headaches, vomiting, diarrhea etc.) and drug efficacy measures (such as symptom levels and pharmacokinetic peptide levels). … Each category should have associated with it a value scale to quantify the information. The value scale in many instances will be determined by the category of information.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Tang’s side effect quantification in order to determine acceptable drug dosage as suggested by Tang (see col. 15, lines 58-60).
Xie also discloses:
iv) featurizing the scaled values; See Xie, ¶ 0034 as cited above.
c) identifying the one or more recommended treatments by generating a prediction using one or more trained machine learning models, See Xie, at least Fig. 1 element 112, “predicted medications.” the one or more trained machine learning models having been trained based on a featurized data set … See Xie, ¶ 0033, “trained in accordance with a training set K of medication i vectors ai 202, where {ai}i=1K and a training set of clinical information vectors x 204 to associate clinical information with medications.”
… including, for each historical living organism of a plurality of historical living organisms, one or more attributes, an indication of a medical condition, a treatment applied to the living organism, information about side effects of the treatment and …; and See Xie, ¶ 0035, “what conditions/diseases the medication can treat, and its side effects, dosage, and so on.” Also ¶ 0036, “current medication, vital signs, symptoms, laboratory results, past medical history.” Also ¶ 0052, “The antagonism interaction indicates that when used together, two medications may bring in a negative medical effect. Medications with antagonism interactions should be prohibited from being used together. The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease.”
Xie does not expressly disclose: a severity of the side effects, and an indication of treatment success. However, this is taught by Kenedy. See Kenedy, col. 12, lines 27-44, e.g. “the outcome data used to derive outcomes such as success levels can include considerably more varied and complicated measures of success … ratings for factors such as product cost, ease of product usage, number of side effects, severity of side effects, number of symptoms resolved and speed of symptom resolution.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Kenedy’s data with Xie’s data in order to provide considerations for varied and complicated measures of success as suggested by Kenedy.
d) outputting information about the identified one or more treatments for the living organism. See Xie, Fig. 1, element 112. Also see ¶ 0079, “a display of the predicted medications.”
wherein the one or more trained machine learning models comprise one or more clustering models See Xie, ¶ 0070, “clustering.”
Xie does not expressly disclose: models … trained to identify a set of matching historical living organisms of the plurality of historical living organisms having similar data sets of attributes to the living organism. However, this is taught by Ghazaleh. See Ghazaleh, ¶ 0006, “Patient features vectors of the plurality of patients can be clustered into a first set of first clusters based on, for example, cosine distance clustering, and a cluster features vector can be computed for each cluster of the first set of first clusters.” Also see ¶ 0011, e.g. “similarities.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s clustering with Ghazaleh’s similarities in order to characterize data for machine learning as suggested by Ghazaleh.
wherein identifying the one or more recommended treatments comprises:
identifying, in the set of matching historical living organisms, a set of treatments applied to living organisms in the set of matching historical living organisms; Xie, ¶ 0028, “a plurality K of candidate medications Y={1, . . . , K}.” Also ¶ 0030, “For example, the machine-learned algorithm that correlates medications may be configured to learn representations of the medication records of numerous medications, compute similarities of the representations in a latent space, and generate a score that indicates similarities among the medications.”
for each treatment of the set of treatments applied to historical living organisms in the set of matching historical living organisms, calculating an … [score] based on success information associated with each historical living organism; and Xie, ¶ 0037, “The score function of each identified medication may be processed against a threshold score to determine whether the medication is included in the set of predicted medications 112 to be output by the medication prediction module 104.” Also see ¶ 0052, “The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease. Their co-occurrence would bring in a positive medical effect and should be encouraged.”
Xie does not expressly disclose: average success rate. This is taught by Kenedy. See col. 12, lines 8-14, “Where evaluations of the success of a service or provider are obtained from multiple sources (e.g., from customer, provider and/or a third party), the results of the evaluations can be indicated separately in the dataset, or they can be used to derive a single value for outcome by averaging or weighted averaging of the evaluations, for example.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Kenedy’s success rate with Xie’s score calculation in order to utilize a standardized scoring for evaluating multiple measures of successful treatment as suggested by Kenedy (see col. 11, line 62 – col. 12, lines 26).
Xie also discloses:
selecting treatments from the set of treatments having average success rates exceeding a threshold success rate. Xie, ¶ 0037, “The score function of each identified medication may be processed against a threshold score to determine whether the medication is included in the set of predicted medications 112 to be output by the medication prediction module 104.” Note that as cited above, Kenedy teaches average success and success rate. See Kenedy col. 12, lines 8-14, e.g. “… averaging of the evaluations …”
In regard to claim 12, Xie also discloses:
12. The method of claim 11, wherein the one or more trained machine learning models comprise one or more probabilistic models trained to generate a probability distribution corresponding to a likelihood of each of a plurality of treatments being successful for the living organism having the medical condition and any potential side effects and severity of side effects. See Xie, e.g. ¶ 0043, “the medication correlation module 402 implements a determinantal point process (DPP) that captures the correlations among the medications and outputs scalar measures 404 indicating the correlation of a medication i and a medication j.” Also e.g. ¶ 0047, “the kernel matrix L is computed and probability defined over medication-subset.” Also ¶ 0052, “The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease.”
In regard to claim 16, Xie also discloses:
16. The method of claim 11, wherein: the one or more trained machine learning models comprise a probabilistic model configured to generate a probability distribution corresponding to a likelihood of each of a plurality of treatments being successful for the living organism having the medical condition and See Xie, e.g. ¶ 0043, “the medication correlation module 402 implements a determinantal point process (DPP) that captures the correlations among the medications and outputs scalar measures 404 indicating the correlation of a medication i and a medication j. … defines a probability distribution over subsets” Also e.g. ¶ 0047-0048, e.g. “the kernel matrix L is computed and probability defined over medication-subset. … a new kernel is defined that is conditioned on the clinical information input x that is included in the score function g(ai,x).” Also ¶ 0052, “The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease. Their co-occurrence would bring in a positive medical effect and should be encouraged.”
a clustering model … See Xie, ¶ 0070, “clustering.”
Xie does not expressly disclose: … configured to identify a set of matching historical living organisms having similar data sets of attributes to the living organism, and However, this is taught by Ghazaleh. See Ghazaleh, ¶ 0006, “Patient features vectors of the plurality of patients can be clustered into a first set of first clusters based on, for example, cosine distance clustering, and a cluster features vector can be computed for each cluster of the first set of first clusters.” Also see ¶ 0011, e.g. “similarities.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s clustering with Ghazaleh’s similarities in order to characterize data for machine learning as suggested by Ghazaleh.
the one or more recommended treatments are identified based on a … probability of success calculated by the probabilistic model and See Xie, ¶ 0037, “The score function of each identified medication may be processed against a threshold score to determine whether the medication is included in the set of predicted medications 112 to be output by the medication prediction module 104.” Also see ¶ 0052 as cited above, e.g. “synergy.”
Xie does not expressly disclose: weighted average of a probability. However, this is taught by Kenedy. See col. 12, lines 8-14 as cited above, e.g. “weighted averaging of the evaluations.”
… an [success] for similar living organisms in the set of matching historical living organisms. Xie, ¶ 0030, “learn representations of the medication records of numerous medications, compute similarities of the representations in a latent space, and generate a score that indicates similarities among the medications.” Also ¶ 0051, “The deep conditional DPP is trained into the machine-learned algorithm 110b using historical information collected across a diverse patient population.” Also see ¶ 0052, “The synergy interaction suggests that two medications are frequently used simultaneously to treat a disease. Their co-occurrence would bring in a positive medical effect and should be encouraged.”
Xie does not expressly disclose: an average success rate However, this is taught by Kenedy as addressed above.
In regard to claim 17, Xie discloses:
17. The method of claim 11, wherein generating the feature vector comprises: for each attribute in the data set, assigning one of a plurality of numerical values for the attribute based on a value of the attribute in the data set, See Xie, ¶ 0031 and 0036, “produce a representation of the clinical information as a clinical-information vector x.”
Xie does not expressly disclose: each value indicating a classification of the respective attribute into one of a plurality of categories. However, this is taught by Ghazaleh. See Ghazaleh, Fig 3A and ¶ 0042-0043, e.g. “Each data category of demographic data 205, diagnosis data 206, and treatment administration data 106 can be mapped to a feature of patient features vector 301. A feature of patient features vector 301 can correspond to a data category, and the value of the data category (represented by the grey box) can be encoded into a feature value.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Ghazaleh’s featurization with Xie’s data in order to provide a format that can be used by machine learning as essentially suggested by Ghazaleh.
In regard to claim 20, Xie discloses:
20. A system for identifying treatments for living organism to treat a medical condition based on one or more machine learning models, comprising: a memory having instructions stored thereon; and a processor configured to execute the instructions to cause the system to: See Xie, Fig. 6, elements 604 and 602, depicting a computer system with memory and a processor.
Xie does not expressly disclose: wherein the featurized data set comprises one or more values generated using a scaling factor associated with an accuracy of a source from which the value was obtained, and This is taught by Sheldon. See Sheldon, ¶ 0032, “A determination is made to see if the data is current and sufficient to provide a reasonably accurate baseline and range measurement. … The system could account for this choice by providing a weighted value for these parameters when they are not current.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Sheldon’s weight scaling in order to account for data sufficiency as suggested by Sheldon.
Xie does not expressly disclose: one or more values generated using a scaling factor associated with a severity of the side effects associated with a treatment; and This is taught by Tang. See Tang, col. 15 line 56 - col. 16 line 12, e.g.: “The following describes in more detail how to prepare the example data sets used to train the neural net and the test data sets used to test the neural net. … The categories developed could fall into two groups: … 2) categories of information which relate to factors which help assess how well a drug is working. … The categories in group 2 can include side effects (health characteristics during treatment such as nausea, headaches, vomiting, diarrhea etc.) and drug efficacy measures (such as symptom levels and pharmacokinetic peptide levels). … Each category should have associated with it a value scale to quantify the information. The value scale in many instances will be determined by the category of information.” Note that Xie teaches featurizing as cited above. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s data with Tang’s side effect quantification in order to determine acceptable drug dosage as suggested by Tang (see col. 15, lines 58-60).
All further limitations of claim 20 have been addressed in the above rejection of claim 11.
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xie in view of Kenedy, Han, Ghazaleh, Sheldon and Tang as applied above, and further in view of U.S. Patent Application 20050262031 by Saidi et al. ("Saidi").
In regard to claim 13, Xie also discloses:
13. The method of claim 12, wherein identifying the one or more treatments comprises: for each of a plurality of treatments, generating a probability score for the treatment as a … likelihood of success generated by each of the one or more trained machine learning models, See Xie, ¶ 0037, “The score function of each identified medication may be processed against a threshold score to determine whether the medication is included in the set of predicted medications 112 to be output by the medication prediction module 104.”
Xie does not expressly disclose: weighted average of a likelihood. However, this is taught by Kenedy. See col. 12, lines 8-14 as cited above, e.g. “weighted averaging of the evaluations.”
Xie does not expressly disclose: each model of the one or more trained learning model being associated with a weighting value to assign to a likelihood of the living organism having the medical condition; and However, this is taught by Saidi. See Saidi, ¶ 0042, “The results may include a diagnostic "score" (e.g., an indication of the likelihood that the patient will experience one or more outcomes related to the medical condition such as the predicted time to recurrence of the event), information indicating one or more features analyzed by predictive model 102 as being correlated with the medical condition, information indicating the sensitivity and/or specificity of the predictive model, or other suitable diagnostic information or a combination thereof.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Xie’s modeling with Saidi’s weight score in order to provide an indication of a likely medical condition as suggested by Saidi.
selecting treatments in the plurality of treatments having a probability score higher than a threshold probability score. See Xie, ¶ 0037, “The score function of each identified medication may be processed against a threshold score to determine whether the medication is included in the set of predicted medications 112 to be output by the medication prediction module 104.”
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xie in view of Kenedy, Han, Ghazaleh, Sheldon and Tang as applied above, and further in view of U.S. Patent 11056242 to Jain et al. ("Jain").
In regard to claim 21, Xie does not expressly disclose:
21. The method of claim 11, wherein the medical condition comprises respiratory complications caused by SARS-COV-2, and the recommend treatment comprises one or more of vaccination against SARS-COV-2 or use of a ventilator for a patient having respiratory complications caused by SARS-COV-2. However, this is taught by Jain. See Jain, col. 25, lines 50-55, “The techniques in the present application can also be used to support research to strengthen the healthcare response to Coronavirus Disease 2019 (COVID-19) caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) and future public health emergencies, including pandemics.” Also col. 51, lines 58-65, “Changing a treatment can include may different types of actions, and a few examples include providing a vaccine, providing a medication, providing digital therapeutics interventions, changing settings of a medical treatment device (e.g., ventilator) or a medical monitoring device, and so on. Once selected, changes to monitoring or treatment can be recommended to the user 102a …” Also col. 59, lines 6-12, “For instance, an individual with respiratory illnesses, such as chronic obstructive pulmonary disorder (COPD), may have reduced pathways for breathing and increased risk in delivering oxygen to vital organs. When combined with an illness like COVID-19, which creates additional risks to breathing, it becomes increasingly important to measure the health of the body under varying situations.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Jain’s consideration of Covid treatment in Xie’s machine learning in order to provide disease prevention and treatment recommendations as suggested by Jain (see col. 22, lines 39-40).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to James D Rutten whose telephone number is (571)272-3703. The examiner can normally be reached M-F 9:00-5:30 ET.
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, Li B Zhen can be reached on (571)272-3768. 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.
/James D. Rutten/Primary Examiner, Art Unit 2121
Prosecution Insights