DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This action is in reply to an amendment filed on 07/17/2026. Claims 1, 10, and 12 have been amended. No claims have been added or cancelled. Therefore, claims 1-20 are currently pending and have been examined.
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 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 1-5, 12-14, 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Muehlhausen (US 2022/0165370 A1) in view of Knight (US 2002/0099570 A1) in further view of Saloman, et al. (US 2021/0319131 A1) in further view of Mei, et al. (US 2019/0059998A1) in further view of Sharda, et al. (US 2021/0174911 A1).
With regards to claim 1, Muehlhausen teaches an adaptive software-as-a-service (SaaS)-based system for autonomously managing an experimental study using real-world data, the system comprising: a processor and a non-transitory computer-readable medium storing machine-readable instructions that, when executed by the processor, cause the processor (see at least ¶ 0025) to: generate or receive a trial protocol defining participant criteria, one or more interventions, one or more outcomes, and respective durations (see at least ¶ 0065, protocol is constructed; ¶ 0059, parameters for clinical trial such as women vs. men, geriatric vs a pediatric population [participant criteria], trial outcomes; ¶ 0033, 0064, adjustments to protocol and durations to perform certain criteria; ¶ 0021, complying with aspects of the protocol [interventions]); …continuously analyze the real-world data associated with the one or more participants, by a decentralized computational framework that ingests the real-world data from one or more of structured data sources, semi-structured data sources, and unstructured data sources (see at least ¶ 0019, 0027, patient computational devices and medical personnel computational devices remote from each other [decentralized]; ¶ 0031, preprocessing components 202 include a language preprocessor 202A for receiving natural language inputs, whether from spoken or textual language, from the patient [unstructured]; a biosignal preprocessor 202B, for receiving biosignal data inputs, for example from the previously described sensor(s) and/or wearable [structured, semi-structured]; an image data preprocessor 202C [semi-structured]; and a medical information preprocessor 202D, for receiving medical information from the patient [structured, unstructured]…, for one or more of adaptive trial adjustments, anomaly detection, and outcome generation (see at least ¶ 0021, data from patient is monitored and analyzed to detect anomalies and adjustments to the protocol), generate, by a self-adaptive protocol generator …trained on …trial data, an adaptive trial protocol that dynamically adjusts one or more experimental parameters of the experimental study in response to an interim result obtained during the experimental study (see at least ¶ 0033, 0060, 0062, 0064, AI model analyzes incoming interim clinical trial data, adjusts trial protocol and the AI model is trained on trial data); and record, on a blockchain-configured distributed ledger…, audit trail of one or more adaptive trial adjustments to the trial protocol (see at least ¶ 0048, a blockchain node 604A, that is a node of blockchain network 604 [multi-node blockchain network is a distributed ledger]; ¶ 0049, 0057, Blockchain network 604 preferably stores at least information about clinical trial protocols as described herein, including without limitation clinical trial frameworks that are suitable for different types of medical interventions; parameters for clinical trial measurements and outcomes; complete protocols and protocol “recipes” and the like. Optionally, each such building block and/or complete protocol features one or more comments or suggestions, for example regarding previous attempts to employ same in a clinical trial, and whether such attempts met with success, or had problems with patient compliance or other drawbacks. Protocol computational device 702 may also provide version control for different versions of the clinical trial protocol and/or protocol parameters or building blocks. For example, optionally the most recent accepted version of a particular protocol and/or parameters or building blocks would be provided through blockchain network 604, so that clinicians always have access to the most recent information).
Muehlhausen does not explicitly teach …facilitate recruitment of one or more participants via one or more digital channels based on assessment of eligibility against the participant criteria; …and performs privacy-preserving integration of the real-world data using homomorphic encryption and differential privacy techniques; …executing one or more reinforcement learning models …historical; …through one or more smart contracts, a tamper-proof …and one or more informed consent records associated with the one or more participants.
Knight teaches … facilitate recruitment of one or more participants via one or more digital channels based on assessment of eligibility against the participant criteria (see at least ¶ 0055-0068, 0127, recruiting patients using a web-based interface to ask questions to see whether they match trial criteria). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
Saloman teaches …and performs privacy-preserving integration of the real-world data using homomorphic encryption and differential privacy techniques (see at least ¶ 0012, 0015, 0018, 0020, 0023, To perform statistical analysis on user data while maintaining data security and supporting data regulations, a system may implement homomorphic differentially private statistical queries. The system may store user data in a database using homomorphic encryption. The supported encryption schemes may include …homomorphic encryption enabling summation (HOM-SUM), homomorphic encryption enabling products (HOM-PROD), homomorphic encryption enabling token searches (SEARCH). The query transformation component 130 may identify a differential privacy mechanism applicable to the query 125, the requested data, or both. The query transformation component 130 may transform the query 125 to include a noisification function based on the identified differential privacy mechanism. Executing the transformed query 135 may involve adding noise to a query result at the database 110 prior to—or, otherwise, without—decrypting the ciphertext at the database 110. By implementing specific query transformations and homomorphic encryption techniques as described herein, the database system may inject noise into user data without decrypting the data). It would have been obvious to one of ordinary skill in the art to combine the homomorphic encryption and differential privacy techniques of Saloman with the trial protocol system of Muehlhausen with the motivation of protecting patient data privacy according to government regulations (Saloman, ¶ 0002).
Mei teaches …executing one or more reinforcement learning models (see at least ¶ 0004-0005, 0016, Reinforcement learning is utilized in conjunction with RNN-based simulations for treatment recommendation allowing the reinforcement learning to gradually reach a final optimal treatment policy after reaching a convergence that meets long term future goals. Determining that the RL action generator has been optimized in response to determining that the convergence has been reached, receiving a patient state as a query, applying the optimized RL action generator. The system and method for treatment recommendation implements at a computing system Reinforcement Learning (RL) optimization with Recurrent Neural Network (RNN)-based simulation. By an RNN-based simulation, RL optimization gradually reaches an optimal treatment policy …historical (see at least ¶ 0048-0049, Patient database 602 store patient data including, for example, historical states, historical actions performed, historical follow-up states that occurred based on the historical actions performed, timelines, physical attributes. RNN learner 604 is a training model for training the RNN-based state simulator 608. For example, RNN learner 604 may generate learning data for RNN-based state simulator 608 from the patient data stored in patient database 602. In some aspects, for example, RNN learner may be a sequential data learning model. In some aspects, for example, historical state and historical action information for a patient may be fed into RNN learner 604 and RNN-based state simulator 608 may be trained to simulate outcome states based on the historical state and action information). It would have been obvious to one of ordinary skill in the art to combine the reinforcement learning model of Mei with the trial protocol system of Muehlhausen with the motivation of optimizing patient treatment (Mei, ¶ 0004-0005).
Sharda teaches …through one or more smart contracts (see at least ¶ 0020, use of decentralized, blockchain-based smart contracts to (4) automatically track and manage the consent process for all patients in a study without the use of paperwork), a tamper-proof …and one or more informed consent records associated with the one or more participants (see at least ¶ 0006, proves data not tampered with; ¶ 0175, these cryptographically signed participant consents are stored on the blockchain, which provides an immutable audit log to prove the validity of each consent). It would have been obvious to one of ordinary skill in the art to combine the tamper-proof clinical trial informed consent records of Sharda with the trial protocol system of Muehlhausen with the motivation of simplifying data regulation while enabling data transparency (Sharda, Abstract).
With regards to claim 2, Muehlhausen teaches the system of claim 1, wherein the processor is to refine the protocol using machine learning algorithms based on an interim result of the experimental study (see at least ¶ 0021, adjust protocol from AI [machine learning algorithms] engine analyzing patient sensor and subjective data during the clinical trial).
With regards to claim 3, Knight teaches the system of claim 1, wherein the recruitment is performed dynamically by assessing the eligibility using real-time physiological data and probabilistic models (see at least figure 2, ¶ 0068-0072, patient presented with initial set of questions, then second set of questions which asks for various physiological parameters [answering as the questioning logic moves along interpreted as real-time], then match for trial determined, if patient indicates interest for trial, server presents a set of trial specific questions, answers compared to trial specific criteria, if a match exists patient presented with trial details, registration and data forms [question logic interpreted as probabilistic model]). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
With regards to claim 4, Muehlhausen teaches the system of claim 1, wherein the one or more digital channels comprises one of a mobile application, a wearable device, and a social networking server (see at least ¶ 0026, wearable).
With regards to claim 5, Knight teaches the system of claim 1, wherein the processor is to enroll the one or more participants based on the participant criteria (see at least ¶ 0070, patient completes registration form for enrollment after qualifying for trial through answers to questions). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
With regards to claim 12, Muehlhausen teaches a method for autonomously managing an experimental study using real-world data through an adaptive software-as-a-service (SaaS)-based system, the method comprising: generating or receiving a trial protocol, wherein the trial protocol specifies participant criteria, one or more interventions, an outcome, and a duration of the experimental study (see at least ¶ 0065, protocol is constructed; ¶ 0059, parameters for clinical trial such as women vs. men, geriatric vs a pediatric population [participant criteria], trial outcomes; ¶ 0033, 0064, adjustments to protocol and durations to perform certain criteria; ¶ 0021, complying with aspects of the protocol [interventions]); …continuously analyzing the real-world data associated with the one or more participants during the experimental study, by a decentralized computational framework that ingests the real-world data from one or more of structured data sources, semi-structured data sources, and unstructured data sources (see at least ¶ 0019, 0027, patient computational devices and medical personnel computational devices remote from each other [decentralized]; ¶ 0031, preprocessing components 202 include a language preprocessor 202A for receiving natural language inputs, whether from spoken or textual language, from the patient [unstructured]; a biosignal preprocessor 202B, for receiving biosignal data inputs, for example from the previously described sensor(s) and/or wearable [structured, semi-structured]; an image data preprocessor 202C [semi-structured]; and a medical information preprocessor 202D, for receiving medical information from the patient [structured, unstructured] …and by one or more neural networks that analyze physiological data streams received from the wearable device (see at least ¶ 0021, data from patient is monitored and analyzed by the AI engine to detect compliance and anomalies [outcomes]; ¶ 0038-0041 AI engine comprises DBN/CNN type neural networks) to perform one or more of adaptive trial adjustments, detecting one or more anomalies, and recording one or more outcomes (see at least ¶ 0021, data from patient is monitored and analyzed to detect anomalies and adjustments to the protocol); generate, by a self-adaptive protocol generator …trained on …trial data, an adaptive trial protocol that dynamically adjusts one or more experimental parameters of the experimental study in response to an interim result obtained during the experimental study (see at least ¶ 0033, 0060, 0062, 0064, AI model analyzes incoming interim clinical trial data, adjusts trial protocol and the AI model is trained on trial data); and record, on a blockchain-configured distributed ledger…, audit trail of one or more adaptive trial adjustments to the trial protocol (see at least ¶ 0048, a blockchain node 604A, that is a node of blockchain network 604 [multi-node blockchain network is a distributed ledger]; ¶ 0049, 0057, Blockchain network 604 preferably stores at least information about clinical trial protocols as described herein, including without limitation clinical trial frameworks that are suitable for different types of medical interventions; parameters for clinical trial measurements and outcomes; complete protocols and protocol “recipes” and the like. Optionally, each such building block and/or complete protocol features one or more comments or suggestions, for example regarding previous attempts to employ same in a clinical trial, and whether such attempts met with success, or had problems with patient compliance or other drawbacks. Protocol computational device 702 may also provide version control for different versions of the clinical trial protocol and/or protocol parameters or building blocks. For example, optionally the most recent accepted version of a particular protocol and/or parameters or building blocks would be provided through blockchain network 604, so that clinicians always have access to the most recent information).
Muehlhausen does not explicitly teach …assessing eligibility of the one or more participants against the participant criteria specified in the trial protocol; facilitating recruitment of the one or more participants through one or more digital channels; …and performs privacy-preserving integration of the real-world data using homomorphic encryption and differential privacy techniques…; …executing one or more reinforcement learning models …historical; …through one or more smart contracts, a tamper-proof …and one or more informed consent records associated with the one or more participants.
Knight teaches assessing eligibility of the one or more participants against the participant criteria specified in the trial protocol; facilitating recruitment of the one or more participants through one or more digital channels (see at least ¶ 0055-0068, 0127, recruiting patients using a web-based interface to ask questions to assess whether they are eligible under the trial criteria). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
Saloman teaches …and performs privacy-preserving integration of the real-world data using homomorphic encryption and differential privacy techniques (see at least ¶ 0012, 0015, 0018, 0020, 0023, To perform statistical analysis on user data while maintaining data security and supporting data regulations, a system may implement homomorphic differentially private statistical queries. The system may store user data in a database using homomorphic encryption. The supported encryption schemes may include …homomorphic encryption enabling summation (HOM-SUM), homomorphic encryption enabling products (HOM-PROD), homomorphic encryption enabling token searches (SEARCH). The query transformation component 130 may identify a differential privacy mechanism applicable to the query 125, the requested data, or both. The query transformation component 130 may transform the query 125 to include a noisification function based on the identified differential privacy mechanism. Executing the transformed query 135 may involve adding noise to a query result at the database 110 prior to—or, otherwise, without—decrypting the ciphertext at the database 110. By implementing specific query transformations and homomorphic encryption techniques as described herein, the database system may inject noise into user data without decrypting the data). It would have been obvious to one of ordinary skill in the art to combine the homomorphic encryption and differential privacy techniques of Saloman with the trial protocol system of Muehlhausen with the motivation of protecting patient data privacy according to government regulations (Saloman, ¶ 0002).
Mei teaches …executing one or more reinforcement learning models (see at least ¶ 0004-0005, 0016, Reinforcement learning is utilized in conjunction with RNN-based simulations for treatment recommendation allowing the reinforcement learning to gradually reach a final optimal treatment policy after reaching a convergence that meets long term future goals. Determining that the RL action generator has been optimized in response to determining that the convergence has been reached, receiving a patient state as a query, applying the optimized RL action generator. The system and method for treatment recommendation implements at a computing system Reinforcement Learning (RL) optimization with Recurrent Neural Network (RNN)-based simulation. By an RNN-based simulation, RL optimization gradually reaches an optimal treatment policy …historical (see at least ¶ 0048-0049, Patient database 602 store patient data including, for example, historical states, historical actions performed, historical follow-up states that occurred based on the historical actions performed, timelines, physical attributes. RNN learner 604 is a training model for training the RNN-based state simulator 608. For example, RNN learner 604 may generate learning data for RNN-based state simulator 608 from the patient data stored in patient database 602. In some aspects, for example, RNN learner may be a sequential data learning model. In some aspects, for example, historical state and historical action information for a patient may be fed into RNN learner 604 and RNN-based state simulator 608 may be trained to simulate outcome states based on the historical state and action information). It would have been obvious to one of ordinary skill in the art to combine the reinforcement learning model of Mei with the trial protocol system of Muehlhausen with the motivation of optimizing patient treatment (Mei, ¶ 0004-0005).
Sharda teaches …through one or more smart contracts (see at least ¶ 0020, use of decentralized, blockchain-based smart contracts to (4) automatically track and manage the consent process for all patients in a study without the use of paperwork), a tamper-proof …and one or more informed consent records associated with the one or more participants (see at least ¶ 0006, proves data not tampered with; ¶ 0175, these cryptographically signed participant consents are stored on the blockchain, which provides an immutable audit log to prove the validity of each consent). It would have been obvious to one of ordinary skill in the art to combine the tamper-proof clinical trial informed consent records of Sharda with the trial protocol system of Muehlhausen with the motivation of simplifying data regulation while enabling data transparency (Sharda, Abstract).
With regards to claim 13, Muehlhausen teaches the method of claim 12, wherein the analysis is conducted using one or more computational models configured for real-time data processing and decision-making (see at least ¶ 0021)
With regards to claim 14, Muehlhausen teaches the method of claim 12, comprising adjusting the trial protocol based on at least one of the one or more anomalies and the one or more adverse events (see at least ¶ 0021).
With regards to claim 16, Knight teaches the method of claim 12, wherein the recruitment of the one or more participants is performed dynamically by assessing the eligibility using at least one of real-time physiological data and probabilistic models (see at least figure 2, ¶ 0068-0072, patient presented with initial set of questions, then second set of questions which asks for various physiological parameters [answering as the questioning logic moves along interpreted as real-time], then match for trial determined, if patient indicates interest for trial, server presents a set of trial specific questions, answers compared to trial specific criteria, if a match exists patient presented with trial details, registration and data forms [question logic interpreted as probabilistic model]). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
With regards to claim 17, Muehlhausen teaches the method of claim 12, wherein the one or more digital channels comprises one of a mobile application, a wearable device, and a social networking server (see at least ¶ 0026, wearable).
Claims 6 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Muehlhausen (US 2022/0165370 A1) in view of Knight (US 2002/0099570 A1) in further view of Saloman, et al. (US 2021/0319131 A1) in further view of Mei, et al. (US 2019/0059998A1) in further view of Sharda, et al. (US 2021/0174911 A1) in further view of Lim CY, In J. Considerations for crossover design in clinical study. Korean J Anesthesiol. 2021 Aug;74(4):293-299. doi: 10.4097/kja.21165. Epub 2021 Jul 30. PMID: 34344139; PMCID: PMC8342834.
With regards to claim 6, Muehlhausen does not explicitly teach the system of claim 1, wherein the experimental study is a digitally conducted A/B test, the one or more interventions comprising at least a first intervention and a second intervention, wherein both the first intervention and the second intervention are delivered to at least one of the one or more participants such that at least one same participant receive both the first intervention and the second intervention. Lim teaches the system of claim 1, wherein the experimental study is a digitally conducted A/B test, the one or more interventions comprising at least a first intervention and a second intervention, wherein both the first intervention and the second intervention are delivered to at least one of the one or more participants such that at least one same participant receive both the first intervention and the second intervention (see at least Abstract and Introduction, clinical trials with AB/BA crossover design, where two treatment A and B are provided to subjects at different times such that one subject will receive both treatments). It would have been obvious to one of ordinary skill in the art to combine the crossover clinical trial design of Lim with the trial protocol system of Muehlhausen with the motivation of clinical trial efficiency (Lim, Introduction and Conclusion).
With regards to claim 7, Lim teaches the system of claim 6, wherein the one or more outcomes comprises a first outcome corresponding to the first intervention and a second outcome corresponding to the second intervention, wherein the processor is to analyze the first outcome and the second outcome to generate a computer executable comparative report (see at least Statistical model and SAS code, pages 295-297). It would have been obvious to one of ordinary skill in the art to combine the crossover clinical trial design of Lim with the trial protocol system of Muehlhausen with the motivation of clinical trial efficiency (Lim, Introduction and Conclusion).
Claims 8, 9, 15, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Muehlhausen (US 2022/0165370 A1) in view of Knight (US 2002/0099570 A1) in further view of Saloman, et al. (US 2021/0319131 A1) in further view of Mei, et al. (US 2019/0059998A1) in further view of Sharda, et al. (US 2021/0174911 A1) in further view of Xie, et al. (US 2021/0158906 A1).
With regards to claim 8, Muehlhausen does not explicitly teach the system of claim 1, wherein the processor is to: implement a controlled comparative testing mechanism by allocating the one or more participants into at least two groups, wherein each group receives distinct interventions from the one or more interventions defined in the trial protocols; and collect and analyze the real-world data from participants in each group, including the outcomes and the real-world time comprising physiological parameters, to evaluate comparative effectiveness of the distinct interventions. Xie teaches the system of claim 1, wherein the processor is to: implement a controlled comparative testing mechanism by allocating the one or more participants into at least two groups, wherein each group receives distinct interventions from the one or more interventions defined in the trial protocols (see at least ¶ 0026, subjects assigned to drug arm or control arm); and collect and analyze the real-world data from participants in each group, including the outcomes and the real-world time comprising physiological parameters, to evaluate comparative effectiveness of the distinct interventions (see at least ¶ 0112, physiological data is collected from trial subjects; ¶ 0088, analysis of study data to recommend adjustments, modifications and adaptation to optimize the study, such as a primary objective of a trial may be directed towards assessing the efficacy of three different dose levels of a drug against a placebo. Based on analysis, it may become evident early in the trial that one of the dose levels is significantly more efficacious than either of the other two. As soon as that determination may be made at a statistically significant level and made available, it is advantageous to proceed further only with the most efficacious dose). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
With regards to claim 9, Xie teaches the system of claim 8, wherein the processor is to generate an adaptive trial protocol based on an analysis from the at least two groups to optimize an intervention efficacy (see at least ¶ 0088, analysis of study data to recommend adjustments, modifications and adaptation to optimize the study, such as a primary objective of a trial may be directed towards assessing the efficacy of three different dose levels of a drug against a placebo. Based on analysis, it may become evident early in the trial that one of the dose levels is significantly more efficacious than either of the other two. As soon as that determination may be made at a statistically significant level and made available, it is advantageous to proceed further only with the most efficacious dose). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
With regards to claim 15, Muehlhausen does not explicitly teach the method of claim 12, comprising presenting real-time insights and the one or more trial outcomes through an interactive dashboard. Xie teaches the method of claim 12, comprising presenting real-time insights and the one or more trial outcomes through an interactive dashboard (see at least figures 14-16, ¶ 0088, real time statistical results of clinical study are displayed). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
With regards to claim 18, Muehlhausen does not explicitly teach the method of claim 17, comprising: implementing a controlled comparative testing mechanism by allocating the one or more participants into at least two groups, wherein each group receives distinct interventions from the one or more interventions defined in the trial protocols; and collecting and analyzing the real-world data from participants in each group, including the outcomes and the real-world data comprising physiological parameters, to evaluate comparative effectiveness of the distinct interventions. Xie teaches the method of claim 17, implementing a controlled comparative testing mechanism by allocating the one or more participants into at least two groups, wherein each group receives distinct interventions from the one or more interventions defined in the trial protocols (see at least ¶ 0026, subjects assigned to drug arm or control arm); and collecting and analyzing the real-world data from participants in each group, including the outcomes and the real-world data comprising physiological parameters, to evaluate comparative effectiveness of the distinct intervention (see at least ¶ 0112, physiological data is collected from trial subjects; ¶ 0088, analysis of study data to recommend adjustments, modifications and adaptation to optimize the study, such as a primary objective of a trial may be directed towards assessing the efficacy of three different dose levels of a drug against a placebo. Based on analysis, it may become evident early in the trial that one of the dose levels is significantly more efficacious than either of the other two. As soon as that determination may be made at a statistically significant level and made available, it is advantageous to proceed further only with the most efficacious dose). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
With regards to claim 19, Xie teaches the method of claim 18, comprising generating an adaptive trial protocol based on an analysis from the at least two groups to optimize an intervention efficacy (see at least ¶ 0088, analysis of study data to recommend adjustments, modifications and adaptation to optimize the study, such as a primary objective of a trial may be directed towards assessing the efficacy of three different dose levels of a drug against a placebo. Based on analysis, it may become evident early in the trial that one of the dose levels is significantly more efficacious than either of the other two. As soon as that determination may be made at a statistically significant level and made available, it is advantageous to proceed further only with the most efficacious dose). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
With regards to claim 20, Knight teaches the method of claim 19, comprising automatically allocating the one or more participants to the experimental study matching their eligibility (see at least ¶ 0070, patient completes registration form for enrollment after qualifying for trial through answers to questions). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
Furthermore, Xie teaches the wherein the allocation includes multi-group intervention comparisons (see at least ¶ 0026, subjects assigned to drug arm or control arm; figures 2-7, 14-16, comparisons). It would have been obvious to one of ordinary skill in the art to combine the clinical trial efficacy determination of Xie with the trial protocol system of Muehlhausen with the motivation of optimization of effectiveness of a clinical trial (Xie, ¶ 0088).
Claims 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Muehlhausen (US 2022/0165370 A1) in view of Knight (US 2002/0099570 A1) in further view of Saloman, et al. (US 2021/0319131 A1) in further view of Mei, et al. (US 2019/0059998 A1) in further view of Sharda, et al. (US 2021/0174911 A1) in further view of Will, et al. (US 2020/0243167 A1).
With regards to claim 10, Muehlhausen teaches the system of claim 1, wherein the processor is to: one of either receive, from a user interface, a trial protocol specifying one or more of participant recruitment criteria, intervention types, outcome measures, and trial duration, or autonomously generate the trial protocol by applying one or more machine learning algorithms to analyze historical study data and multi-dimensional input criteria (see at least ¶ 0065, protocol is constructed; ¶ 0059, parameters for clinical trial such as women vs. men, geriatric vs a pediatric population [participant criteria]); …and execute computational models comprising one or more neural networks that continuously analyze physiological data streams received from the wearable device to detect one or more anomalies for analyzing the real-world data during the experimental study to generate one or more trial outcomes (see at least ¶ 0019, continuous communication of data from patient wearables; ¶ 0021, data from patient is monitored and analyzed by the AI engine to detect compliance and anomalies [outcomes]; ¶ 0038-0041 AI engine comprises DBN/CNN type neural networks; ¶ 0069, AI engine reviews wearable data continuously).
Knight teaches …facilitate the recruitment of one or more participants by integrating with the one or more digital channels, including one or more of a mobile application, a wearable device, and a social networking server (see at least figures 3-10, ¶ 0055-0068, 0127, recruiting patients using a web based interface to ask questions to see whether they match trial criteria, where the patients interact with clinical trial providers [social networking]); dynamically assess participant eligibility by processing at least one of real-time physiological measurements and participant-reported inputs (see at least figure 2, ¶ 0068-0072, patient presented with initial set of questions, then second set of questions which asks for various physiological parameters, then match for trial determined, if patient indicates interest for trial, server presents a set of trial specific questions, answers compared to trial specific criteria, if a match exists patient presented with trial details, registration and data forms [dynamic assessment]); automatically enroll the one or more participants into the experimental study when their data satisfies the participant recruitment criteria specified in the trial protocol (see at least ¶ 0070, patient completes registration form for enrollment after qualifying for trial through answers to questions). It would have been obvious to one of ordinary skill in the art to combine the patient trial recruitment method of Knight with the trial protocol system of Muehlhausen with the motivation of optimization of clinical trials (Knight, ¶ 0002-0004).
The combination of Muehlhausen/Knight does not explicitly teach …by a participant eligibility matching engine applying one or more probabilistic scoring models comprising at least one of a Bayesian network and a logistic regression model, Will teaches …by a participant eligibility matching engine applying one or more probabilistic scoring models comprising at least one of a Bayesian network and a logistic regression model (see at least ¶ 0005, generating a probability that the first patient will be eligible for each of the plurality of clinical trials; ¶ 0023, Naïve Bayes, logistic regression models; ¶ 0046, Predictive model 210b outputs an eligibility probability for the clinical trial 316). It would have been obvious to one of ordinary skill in the art to combine the patient eligibility scoring model of Will with the clinical trial system of Muehlhausen/Knight with the motivation of optimization of clinical trials with patients that accurately match their criteria (Will, ¶ 0001-0004).
With regards to claim 11, Muehlhausen teaches the system of claim 10, wherein the processor is to apply predictive models to monitor safety and efficacy of one or more interventions, detect one or more anomalies, and predict one or more adverse events (see at least ¶ 0021, AI monitors incoming patient data for compliance and to detect any anomalies which may relate to side effects or other undesirable effects of following the protocol).
Response to Arguments
Applicant's arguments with respect to the 35 USC § 101 rejections set forth in the previous office action have been considered, and are persuasive. Therefore, these rejections are withdrawn.
Applicant's arguments with respect to the 35 USC § 103 rejections set forth in the previous office action have been considered, but are moot in view of the new grounds of rejection.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Eteminan, et al. (US 2019/0206520 A1) which discloses a trial operations service suite in a clinical trial operations system includes: patient, clinician, investigator, and coordinator portals supporting corresponding applications and providing specific services for each type of participant, where the coordinator portal allows a coordinator user to develop, build, customize, and establish trial protocol and participant interaction using an application factory system embedded within a trial design aspect of the coordinator portal; security configuration and management authentication databases; operational databases including trial data including provisioning and authorization data describing trial participants, access logs recording participant activity, protected and de-identified health information and/or non-health provided by patients, clinicians, and associated sensors; a notification relay service and corresponding external notifications gateway providing essential communication between the system and users, between clinicians and patients, and between coordinators and all participants; and a secure communication relay service providing multi-media communication among participants, constrained by permissions as established by a particular coordinator user.
Kalathil (US 2015/0161336 A1) which discloses adequate patient enrollment and participation in different design stages of a clinical trial is facilitated and scaled by dynamically adjusting clinical trial criteria relative to characteristics and conditions of massive numbers of patients whose medical records have been aggregated in databases in compliance with patient privacy and confidentiality laws and regulations. Patient participation results without intervention by multiple providers of healthcare services, and by directly identifying and communicating with qualified patients while maintaining patient privacy and compliance requirements as required by law.
Adding flexibility to clinical trial designs: an example-based guide to the practical use of adaptive designs; T Burnett, P Mozgunov, P Pallmann, SS Villar, GM Wheeler, T Jaki; BMC medicine, 2020
which discloses adaptive designs for clinical trials permit alterations to a study in response to accumulating data in order to make trials more flexible, ethical, and efficient. These benefits are achieved while preserving the integrity and validity of the trial, through the pre-specification and proper adjustment for the possible alterations during the course of the trial. Despite much research in the statistical literature highlighting the potential advantages of adaptive designs over traditional fixed designs, the uptake of such methods in clinical research has been slow. One major reason for this is that different adaptations to trial designs, as well as their advantages and limitations, remain unfamiliar to large parts of the clinical community. The aim of this paper is to clarify where adaptive designs can be used to address specific questions of scientific interest; we introduce the main features of adaptive designs and commonly used terminology, highlighting their utility and pitfalls, and illustrate their use through case studies of adaptive trials ranging from early-phase dose escalation to confirmatory phase III studies.
Applicant’s amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Joey Burgess whose telephone number is (571)270-5547. The examiner can normally be reached Monday through Friday 9-6.
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, Kambiz Abdi can be reached on 571-272-6702 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.
/JOSEPH D BURGESS/ Primary Examiner, Art Unit 3685
Prosecution Insights