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 the amendments filed on 06/30/2026.
Claims 1-6, 8-9 and 12-17 were amended.
Claims 1-17 are currently pending and have been examined.
Claim Rejections – 35 § 112(b)
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 1-17 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.
Claim 1, recites in part, “perform a performance evaluation of each of the plurality of trained machine learning models”. It is unclear how a performance evaluation is performed for each of the plurality of trained machine learning models. Is there an algorithm or formula that is being used to perform a performance evaluation of each of the plurality of trained machine learning models? Claims 9 and 17 recite similar limitations. Claims 1, 9 and 17 are therefore found to be indefinite, because the resulting claims do not clearly set forth the metes and bounds of the patent protection desired. All dependent claims, namely claims 2-8 and 10-16 are rejected for at least the same reason.
Claim 1, recites in part, “select, based on the performance evaluation, one or more machine learning models among the plurality of machine learning models”. It is unclear how a selection is made of one or more machine learning models among the plurality of machine learning models based on the performance evaluation. How is determination made whether only one particular machine learning model is selected, or whether multiple machine learning models are selected? Is there an algorithm or formula that is being used to perform a selection of one or more machine learning models among the plurality of machine learning models based on the performance evaluation? Claims 9 and 17 recite similar limitations. Claims 1, 9 and 17 are therefore found to be indefinite, because the resulting claims do not clearly set forth the metes and bounds of the patent protection desired. All dependent claims, namely claims 2-8 and 10-16 are rejected for at least the same reason.
Claim 1, recites in part, “use the selected one or more machine learning models to predict mortality of a trauma patient entering the emergency department”. It is unclear how the selected one or more machine learning models is being used to predict mortality of a trauma patient entering the emergency department. How is determination made with regard to how each of the selected one or more machine learning models is being used to predict mortality of a trauma patient entering the emergency department? Is one model being used in a different way from another model depending on certain characteristics or parameters? Claims 9 and 17 recite similar limitations. Claims 1, 9 and 17 are therefore found to be indefinite, because the resulting claims do not clearly set forth the metes and bounds of the patent protection desired. All dependent claims, namely claims 2-8 and 10-16 are rejected for at least the same reason.
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 1-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-17: Step 1
Claims 1-8 are drawn to a mortality prediction device of trauma patients equipped with one or more processors and a memory storing one or more programs executed by the one or more processors, which is within the four statutory categories (i.e. machine). Claims 9-16 are drawn to a mortality prediction method of trauma patients, which is within the four statutory categories (i.e. process). Claim 17 is drawn to a computer program stored in a non-transitory computer readable storage medium, the computer program comprising one or more instructions executed by a computing device, which is within the four statutory categories (i.e. machine).
Claims 1-17: Step 2A Prong One
Claim 1 recites collecting patient-related data of patients visiting an emergency department for a certain period of time, dividing collected patent-related data (of patients who do not correspond to preset exclusion conditions) into data of deceased patients and data of survived patients, to generate a learning data group for one patient by extracting a plurality of preset variables from the patient-related data, oversampling the patient-related data of deceased patients (when the number of patient-related data of deceased patient is smaller than the number of patient-related data of survived patients), inputting the learning data group into one or more machine learning models, performing a performance evaluation, selecting one or more machine learning models based on the performance evaluation and predicting mortality of a trauma patient entering the emergency department using the selection. Claims 9 and 17 recite similar limitations.
These limitations, as drafted, given the broadest reasonable interpretation, but for the recitation of generic computer components, encompass managing personal behavior by manually following rules or instructions, which is a subgrouping of Certain Methods of Organizing Human Activity. But for the recitation of generic computer components, these limitations encompass a user collecting patient-related data of patients visiting an emergency department for a certain period of time, dividing collected patent-related data (of patients who do not correspond to preset exclusion conditions) into data of deceased patients and data of survived patients, to generate a learning data group for one patient by extracting a plurality of preset variables from the patient-related data, oversampling the patient-related data of deceased patients (when the number of patient-related data of deceased patient is smaller than the number of patient-related data of survived patients), inputting the learning data group into one or more machine learning models, performing a performance evaluation, selecting one or more machine learning models based on the performance evaluation and predicting mortality of a trauma patient entering the emergency department using the selection. These steps could be carried out manually by a user following rules or instructions, which is a subgrouping of Certain Methods of Organizing Human Activity. Claims 9 and 17 recite similar limitations.
Claims 2-8 and 10-16 incorporate the abstract idea identified above and recite additional limitations that expand on the abstract idea, but for the recitation of generic computer components. For example, but for the recitation of generic computer components, Claims 2 and 10 further define excluding patient-related data corresponding to exclusion conditions. Claims 3 and 11 further define determining whether the corresponding patient corresponds to the preset exclusion conditions. Claims 4 and 12 further define dividing patient-related data of patients that do not correspond to exclusion conditions to deceased group and survived group and inputting these to predict mortality. Claims 5 and 13 further define generating learning data group. Claims 6 and 14 further define inputting the learning data group. Claims 7 and 15 further define calculating performance evaluation score, performing evaluation by calculating a performance evaluation score and selecting one or more models. Claims 8 and 16 further define calculating importance of each variable. Therefore, these claims are similarly drawn to Certain Methods of Organizing Human Activity.
Claims 1-17: Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform the abstract ideas along with insignificant, extra-solution data gathering activity, and adding limitations similar to adding the words “apply it” to the abstract idea. Claim 1 recites the additional elements of a mortality prediction device of trauma patients equipped with one or more processors and a memory storing one or more programs executed by the one or more processors. Claim 9 recites additional elements of a method performed in a computing device equipped with one or more processors and a memory storing one or more programs executed by the one or more processors. Claim 17 recites additional elements of a computer program stored in a non-transitory computer readable storage medium, the computer program comprising one or more instructions executed by a computing device having one or more processors.
Claims 1-17, directly or indirectly, recite the following generic computer components: “a processor,” “computing device equipped with one or more processors and a memory,” and “non-transitory computer readable storage medium, the computer program comprising one or more instructions executed by a computing device having one or more processors” which are similar to adding the words “apply it” to the abstract idea. The written description discloses that the recited computer components encompass generic components including “The computing device (12) comprises at least one processor (14), a computer readable storage medium (16) and a communication bus (18). The processor (14) may make the computing device (12) to operate according to the afore-mentioned exemplary examples. For example, the processor (14) may execute one or more programs stored in the computer readable storage medium” (see at least Paragraph [0078]) and “The computer readable storage medium (16) is configured to store computer executable instructions or program codes, program data and/or other suitable forms of information. The programs (20) stored in the computer readable storage medium (16) comprise a set of instructions executable by the processor (14). In one example, the computer readable storage medium (16) may be a memory (volatile memory such as a random-access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, other forms of storage media that are accessed by the computing device (12) and store desired information, or a suitable combination thereof “ (see at least Paragraph [0079]). Although the additional element “machine learning model” limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning), and thus fails to add an inventive concept to the claims. See MPEP 2106.05 (h). As set forth in the 2019 Eligibility Guidance, 84 Fed. Reg. at 55 “merely include[ing] instructions to implement an abstract idea on a computer” is an example of when an abstract idea has not been integrated into a practical application.
Claims 1-17: Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because as discussed above with respect to integration into a practical application, the additional elements (for example, machine learning) are recited at a high level of generality, and the written description indicates that these elements are generic computer components. Using generic computer components to perform abstract ideas does not provide a necessary inventive concept. See Alice, 573 U.S. at 223 (“mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention.”). As explained above, the generic computer components and machine learning are at best the equivalent of merely adding the words “apply it” to the judicial exception.
Receiving and transmitting data over a network (i.e. receiving and communicating data or signals) has been recognized as well-understood, routine, and conventional activity of a general-purpose computer (see MPEP 2106.05(d) and buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014)).
Gathering and analyzing information using conventional techniques and displaying the result has also been found to be insufficient to show an improvement to technology, (see MPEP 2106.05(a) and TLI Communications, 823 F.3d at 612-13, 118 USPQ2d at 1747-48).
Insignificant, extra solution, data gathering activity has been found to not amount to significantly more than an abstract idea (see MPEP 2106.05(g) and Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016)). Therefore, the high-level recitation of an output of results also fails to include additional elements that are sufficient to amount to significantly more than the judicial exception.
Therefore, whether considered alone or in combination, the additional elements do not amount to significantly more than the abstract idea.
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 of this title, if the differences between the claimed invention and the prior art axe 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 2, 4-6, 5-10, 12-14, 16 and 17 are are rejected under 35 U.S.C. 103 as being unpatentable over CN Patent Application Publication CN 103038772 A to Wang et al. in view of US Patent Application Publication US 2021/0327540 A1 to Schobel et al. in view of US Patent Application Publication US 2023/0374589 A1 to Sweeney et al. and further in view of US Patent Application Publication US 2023/0069693 A1 to Tignanelli et al.
Claim 1:
Wang discloses the following limitations as shown below:
a data collection circuit, implemented by the one or more processors, configured to collect patient-related data of patients visiting an emergency department for a certain period of time (see at least Paragraph 10, additionally based on the collected patient demographic information and patient history information to calculate the survival probability. The method may also further include: selecting time of between 4 and 24 hours or a time limit of between 4 and 72 hours; Paragraph 89, may be used to train another parameter of the artificial neural network is patient characteristics. patient features include such as patient age, gender and medical history information; Paragraph 204, the user can input patient 401 of other parameters, such as age, other agents, Grassmann coma score, respiratory rate, blood pressure Sp02 and heart. about the patient 401, the parameter is used to compute a risk score to predict patient 401 of viability. in calculating the risk score, worthy of appreciation, the analysis block 406 has been training of the artificial neural network is as in FIG. 1 to FIG. 3 in the above. output of the analysis block 406 will be a risk score that includes death, each of ICU hospital entering the sickroom and the result in which the patient is classified as "high", "medium" or "low" risk; Paragraph 280, patients is selected from the Department of Emergency Medicine (DEM));
a learning data generation circuit configured to divide, among the collected patient-related data, patient-related data of patients who do not correspond to preset exclusion conditions into patient-related data of deceased patients and patient related data of survived patients, to generate a learning data group for one patient by extracting a plurality of preset variables from the patient-related data of deceased patients and the patient-related data of survived patients, respectively, (see at least Paragraph 279, is selected to analyze, comprising 40 cases of death condition and 60 cases of survival. vital signs and patient results obtained from hospital records, such as a patient demographic (age, race, gender) and priority information of the level code; Paragraph 148, after training of the ANN 300 may be used to help related to show some symptoms of the patient will be survival or death of clinical decision, namely after training of the ANN 300 can help the liveness of the prediction to the patient; Paragraph 204, the user can input patient 401 of other parameters, such as age, other agents, Grassmann coma score, respiratory rate, blood pressure Sp02 and heart. about the patient 401, the parameter is used to compute a risk score to predict patient 401 of viability. in calculating the risk score, worthy of appreciation, the analysis block 406 has been training of the artificial neural network is as in FIG. 1 to FIG. 3 in the above; Paragraph 221, Generally, steps 702 to 726 is to detect the position of the QRS composite body, which allows us to RR interval is calculated. Position, amplitude, and shape of the QRS composite body and adjacent abnormal beat duration between composite body allowing the analysis excluded from the HRV and other sinus rhythm. In this manner, is able to be extracted from the ECG signal from the patient out of reliable heart rate variability data); and
a prediction circuit, implemented by one or more processors, configured to input the learning data groups of deceased patients and the learning data groups of survived patients into a plurality of machine learning models, respectively, to train the machine learning model to output a mortality prediction of the corresponding patient (see at least Paragraph 279, is selected to analyze, comprising 40 cases of death condition and 60 cases of survival. vital signs and patient results obtained from hospital records, such as a patient demographic (age, race, gender) and priority information of the level code; Paragraph 148, after training of the ANN 300 may be used to help related to show some symptoms of the patient will be survival or death of clinical decision, namely after training of the ANN 300 can help the liveness of the prediction to the patient; Paragraph 204, the user can input patient 401 of other parameters, such as age, other agents, Grassmann coma score, respiratory rate, blood pressure Sp02 and heart. about the patient 401, the parameter is used to compute a risk score to predict patient 401 of viability. in calculating the risk score, worthy of appreciation, the analysis block 406 has been training of the artificial neural network is as in FIG. 1 to FIG. 3 in the above; Paragraph 288, Because one purpose of artificial neural network is to predict mortality, the artificial neural network is implemented to solve two class classification problem (patient result is death or survival));
machine learning models to predict mortality of a trauma patient entering the emergency department (see at least Paragraph 10, additionally based on the collected patient demographic information and patient history information to calculate the survival probability. The method may also further include: selecting time of between 4 and 24 hours or a time limit of between 4 and 72 hours; Paragraph 89, may be used to train another parameter of the artificial neural network is patient characteristics. patient features include such as patient age, gender and medical history information; Paragraph 204, the user can input patient 401 of other parameters, such as age, other agents, Grassmann coma score, respiratory rate, blood pressure Sp02 and heart. about the patient 401, the parameter is used to compute a risk score to predict patient 401 of viability. in calculating the risk score, worthy of appreciation, the analysis block 406 has been training of the artificial neural network is as in FIG. 1 to FIG. 3 in the above. output of the analysis block 406 will be a risk score that includes death, each of ICU hospital entering the sickroom and the result in which the patient is classified as "high", "medium" or "low" risk; Paragraph 280, patients is selected from the Department of Emergency Medicine (DEM));
Wang may not specifically disclose the following limitations, but Schobel as shown does:
to train the plurality of machine learning models to output a prediction of the corresponding patient (see at least Paragraph 61, Given that the performance of machine learning algorithms can depend strongly on the quality of the training data used to train the algorithms, variable selection and other data preparation operations can be highly significant for ensuring desired performance; Paragraph 83, In some embodiment, over 7000 initial clinical and nonclinical parameters are available regarding the subjects that could potentially be used to train the machine learning solutions; Paragraph 211, In the present study, the aim is to train models using different events during treatment to work in screening and confirmatory roles)
perform a performance evaluation of each of the plurality of trained machine learning models (see at least Paragraph 8, calculating a performance metric associated with each of the plurality of machine learning models in accordance with the predictions of clinical outcomes);
select, based on the performance evaluation, one or more machine learning models among the plurality of machine learning models (see at least Paragraph 8, calculating a performance metric associated with each of the plurality of machine learning models in accordance with the predictions of clinical outcomes; selecting a candidate classification machine learning model in accordance with the performance metric; and outputting a model for predicting a clinical outcome);
use the selected one or more machine learning models to predict mortality of a patient (see at least Paragraph 18, In embodiments, the one or more clinical outcomes may comprise: acute kidney injury, acute respiratory distress, bacteremia, heterotopic ossification, pneumonia, post-traumatic sterile inflammation, sepsis, wound closure, or vasospasm and/or mortality following traumatic brain injury (TBI)).
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang with the features of Schobel with the motivation of providing the benefit of “… determining if a subject has an increased risk of having or developing one or more clinical outcomes, including prior to the detection of symptoms thereof and/or prior to onset of any detectable symptoms thereof, methods for predicting clinical outcomes, and related methods of treatment” (Schobel, see at least Paragraph 7).
Wang may not specifically disclose the following limitations, but Sweeney as shown does:
and to oversample the patient-related data of deceased patients when the number of patient-related data of deceased patients is smaller than the number of patient-related data of survived patients (see at least Paragraph 57, Suitable metrics and methods include Pearson correlation, Kendall rank correlation, Spearman rank correlation, t-test, other non-parametric measures, over-sampling of the non-survival group, under-sampling of the survival group, … etc.)
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang and the features of Schobel with the oversampling of Sweeney with the motivation of providing the benefit that “… there is a critical need for patient risk stratification at triage (for instance, in an emergency department) in order to preserve hospital resources for only those most in need” (Sweeney, see at least Paragraph 6).
Wang may not specifically disclose the following limitations, but Tignannelli as shown does:
a plurality of preset variables including at least an emergency patient classification level, injury mechanism information, and an ICD-10 code (see at least Paragraph 17, Emergency medical services (EMS) workers are the first-line providers in the event of acute trauma. They play an essential role in ensuring that severely injured patients receive care at centers that can appropriately and effectively manage the patients' conditions. The subject of trauma triage may be divided into 3 subcategories: “field-triage” (e.g., choice of destination hospital), “hospital-triage” (e.g., level of trauma-team activation) and “triage-assessment” (e.g., assessment of the appropriateness of trauma-team activation as it relates to injury severity); Paragraph 29, In some implementations, the outputs 122 of NEI-6 predictive model 118 may be used in in conjunction with a tiered trauma-team-activation (TTA) system in order to help allocate available medical resources in a manner proportional to the needs (e.g., the injury burden) of patient 102; Paragraph 31, “Blunt” may be defined as “an injury where the primary ICD-9 External Cause Code (“E-code”) is mapped to the following categories: fall, machinery, motor vehicle traffic, pedestrian, cyclist, and struck by/against a blunt object (assault).”; Paragraph 67, The computing system of any of examples 1-5, wherein the plurality of parameters comprise at least: an age of the patient; a gender of the patient; a field Glasgow Coma Scale (GCS) score of the patient; vital signs of the patient; an intentionality of the patient; and a mechanism of an injury of the patient)
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang, the features of Schobel and the oversampling of Sweeney with the features of Tignanelli with the motivation of providing the benefit that “… may significantly reduce instances of wasted medical resources due to patient-overtriage, as well as significantly reduce preventable instances of patient mortality due to patient-undertriage” (Tignanelli, see at least Paragraph 5).
Claims 9 and 17 recite substantially similar method and computer program product limitations to those of apparatus claim 1 and, as such, are rejected for similar reasons as given above.
Claim 2:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the mortality prediction device further comprises a pretreatment circuit that excludes the patient-related data of the patient corresponding to exclusion conditions preset from the collected patient-related data (see at least Paragraph 221, Generally, steps 702 to 726 is to detect the position of the QRS composite body, which allows us to RR interval is calculated. Position, amplitude, and shape of the QRS composite body and adjacent abnormal beat duration between composite body allowing the analysis excluded from the HRV and other sinus rhythm. In this manner, is able to be extracted from the ECG signal from the patient out of reliable heart rate variability data).
Claim 10 recites substantially similar method limitations to those of apparatus claim 2 and, as such, is rejected for similar reasons as given above.
Claim 4:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the learning data generation circuit is configured to divide patient-related data of patients who do not correspond to the preset exclusion conditions into patient-related data of deceased patients and patient-related data of survived patients, and to extract a plurality of preset variables from the patient-related data of deceased patients and patient-related data of survived patients, respectively, to generate a learning data group for one patient (see at least Paragraph 114, the viability of predicting patient is death of the patient or patient survival; Paragraph 148, system may be used to carry out the medical treatment to the patient is selected, such as in battlefield situations, mass casualty situations many vehicles such as a motor vehicle accident or terrorist event. After training of the ANN 300 may be used to help related to show some symptoms of the patient; Paragraph 279, to analyze, comprising 40 cases of death condition and 60 cases of survival. vital signs and patient results obtained from hospital records, such as a patient demographic (age, race, gender) and priority information of the level code; Paragraph 391, a patient survivability prediction system 1500 further includes a processor 1508 for executing stored instructions to the memory module 1506 based on the first parameter set and the second parameter set execution function of the artificial neural network and output a prediction of survival for the patient), and
the prediction circuit is configured to input the learning data group of deceased patients and the learning data group of survived patients into the machine learning model, respectively, to train the machine learning model to output a prediction of mortality of the corresponding patient (see at least Paragraph 114, the viability of predicting patient is death of the patient or patient survival; Paragraph 148, system may be used to carry out the medical treatment to the patient is selected, such as in battlefield situations, mass casualty situations many vehicles such as a motor vehicle accident or terrorist event. After training of the ANN 300 may be used to help related to show some symptoms of the patient will be survival or death of clinical decision, namely after training of the ANN 300 can help the liveness of the prediction to the patient).
Wang may not specifically disclose the following limitations, but Schobel as shown does:
the plurality of machine learning models to output a prediction (see at least Paragraph 61, Given that the performance of machine learning algorithms can depend strongly on the quality of the training data used to train the algorithms, variable selection and other data preparation operations can be highly significant for ensuring desired performance; Paragraph 83, In some embodiment, over 7000 initial clinical and nonclinical parameters are available regarding the subjects that could potentially be used to train the machine learning solutions; Paragraph 211, In the present study, the aim is to train models using different events during treatment to work in screening and confirmatory roles)
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang, the oversampling of Sweeney and the features of Tignanelli with the features of Schobel for at least the same reasons given for claim 1.
Claim 12 recites substantially similar method limitations to those of apparatus claim 4 and, as such, is rejected for similar reasons as given above.
Claim 5:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the learning data generation circuit is configured to generate a learning data group for the corresponding deceased patient and a learning data group for the corresponding survived patient, by extracting the patient’s age, emergency patient classification level, intentionality information, injury mechanism information, presence or absence of emergency symptoms, AVPU (Alert Verbal Pain Unresponsive) scale, gender, preset vital signs, and ICD-10 code, from the patient-related data of deceased patients and the patient-related data of survived patients (see at least Paragraph 88, data relating to patient survivability typically associated with respective set law variability data and vital sign data about the centre of the same patient; Paragraph 106, Each data set has at least relating to heart rate variability data and the parameter relating to vital sign data of the parameter, each data set further having a parameter relating to patient survivability. The method includes processing the first parameter set and the second parameter set to generate suitable input to processing data in the artificial neural network).
Claim 13 recites substantially similar method limitations to those of apparatus claim 5 and, as such, is rejected for similar reasons as given above.
Claim 6:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the prediction circuit is configured to input the learning data group for deceased patients and the learning data group for survived patients into a plurality of machine learning models, respectively, to perform a performance evaluation by calculating, for each of the plurality of machine learning models, a performance evaluation score based on a prediction result of the machine learning model for the plurality of machine learning models, and to select, according to the performance evaluation scores, selects one or more machine learning models among the plurality of machine learning models (see at least Paragraph 5, artificial neural network provides a network of nodes including interconnects, nodes comprising a plurality of artificial neurons, each artificial neuron comprises at least one input with an associated weight, through using an electronic database of a plurality of data sets for training the artificial neural network to adjust associated weights. Each data set has at least relating to heart rate variability data and the parameter relating to vital sign data of the parameter, each data set further having a parameter relating to patient survivability; processing the first parameter set and the second parameter set to generate suitable for input into the artificial neural network processing data in the processing data is provided as an input to the artificial neural network, and obtaining the output from the artificial neural network, the output providing a prediction of ACP events and survivability of a patient; Paragraph 279, is selected to analyze, comprising 40 cases of death condition and 60 cases of survival. vital signs and patient results obtained from hospital records, such as a patient demographic (age, race, gender) and priority information of the level code).
Claim 14 recites substantially similar method limitations to those of apparatus claim 6 and, as such, is rejected for similar reasons as given above.
Claim 8:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the prediction circuit is configured to calculate importance of each variable included in the learning data group, the importance of a specific variable being calculated by inputting the learning data group, from which the specific variable is excluded, into the machine learning model and confirming a prediction result of the machine learning model, and to weight the corresponding variable depending on the importance of the variables included in the learning data group (see at least Paragraph 5, artificial neural network provides a network of nodes including interconnects, nodes comprising a plurality of artificial neurons, each artificial neuron comprises at least one input with an associated weight, through using an electronic database of a plurality of data sets for training the artificial neural network to adjust associated weights. Each data set has at least relating to heart rate variability data and the parameter relating to vital sign data of the parameter, each data set further having a parameter relating to patient survivability; processing the first parameter set and the second parameter set to generate suitable for input into the artificial neural network processing data in the processing data is provided as an input to the artificial neural network, and obtaining the output from the artificial neural network, the output providing a prediction of ACP events and survivability of a patient).
Claim 16 recites substantially similar method limitations to those of apparatus claim 8 and, as such, is rejected for similar reasons as given above.
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 of this title, if the differences between the claimed invention and the prior art axe 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 3 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over CN Patent Application Publication CN 103038772 A to Wang et al. in view of US Patent Application Publication US 2021/0327540 A1 to Schobel et al. in view of US Patent Application Publication US 2023/0374589 A1 to Sweeney et al. in view of US Patent Application Publication US 2023/0069693 A1 to Tignanelli et al. and further in view of US Patent US 11,854,701 B2 to Constantine et al.
Claim 3:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the pretreatment circuit is configured to determine whether the corresponding patient corresponds to the preset exclusion code conditions (see at least Paragraph 221, Generally, steps 702 to 726 is to detect the position of the QRS composite body, which allows us to RR interval is calculated. Position, amplitude, and shape of the QRS composite body and adjacent abnormal beat duration between composite body allowing the analysis excluded from the HRV and other sinus rhythm. In this manner, is able to be extracted from the ECG signal from the patient out of reliable heart rate variability data)
Wang may not specifically disclose the following limitations, but Constantine as shown does:
exclusion code conditions based on one or more of time of death of a patient based on arrival at a hospital, whether the patient is treated after arrival at the hospital, whether the patient has trauma, whether the patient is irrecoverable, whether the patient is voluntarily discharged, the patient’s diagnosis code, and whether the patient’s identity is not confirmed (see at least (51), Patients with incomplete MOD scores for D2 to D5 (due to discharge from the ICU), or that died prior to discharge, were excluded in order to capture a complete data set for the derivation group; (127), Among the 96 excluded patients, 91 were discharged from ICU prior to day 4).
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang, the features of Schobel, the oversampling of Sweeney and the features of Tignanelli with the exclusion features of Constantine with the motivation of providing benefit of “… the identification of meaningful outcome-based endpoints, in addition to mortality, and the validation of methods to expeditiously stratify for patients most likely to benefit from a given intervention” (Constantine, see at least (3)).
Claim 11 recites substantially similar method limitations to those of apparatus claim 3 and, as such, is rejected for similar reasons as given above.
Claims 7 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over CN Patent Application Publication CN 103038772 A to Wang et al. in view of US Patent Application Publication US 2021/0327540 A1 to Schobel et al. in view of US Patent Application Publication US 2023/0374589 A1 to Sweeney et al. in view of US Patent Application Publication US 2023/0069693 A1 to Tignanelli et al. and further in view of US Patent Application Publication US 2024/0105336 A1 to Liao et al.
Claim 7:
The combination of Wang/Schobel/Sweeney/Tignanelli discloses the limitations as shown in the rejections above. Wang further discloses the following limitations:
wherein the prediction circuit is configured to: calculate a first performance evaluation score of each machine learning model by calculating the accuracy, sensitivity, and specificity of each machine learning model based on the prediction results of the plurality of machine learning models, and adding them up (see at least Paragraph 81, the fourth parameter can be in a training phase of algorithm development is used as a training algorithm means, and being able to use phase is used to improve precision of means to improve accuracy by recording the actual accuracy of the prediction algorithm and properly modifying data set even without a parameter relating to patient survivability. Alternatively, the set of each patient health data may include all four parameters);
Wang may not specifically disclose the following limitations, but Liao as shown does:
generate an ROC (Receiver Operating Characteristic) curve for the prediction result of each machine learning model based on the prediction result of each machine learning model, and calculate a second performance evaluation score of each machine learning model based on an AUC (Area Under the Curve) value from the ROC curve (see at least Paragraph 126, To validate the performance of the machine learning classifier model, different performance metrics may be generated. For example, an area under the receiver-operating curve (AUROC) may be used to determine the diagnostic capability of the machine learning classifier. For example, the machine learning classifier may use classification thresholds which are adjustable, such that specificity and sensitivity are tunable, and the receiver-operating curve (ROC) can be used to identify the different operating points corresponding to different values of specificity and sensitivity); and
select one or more machine learning models based on an overall evaluation score that is the sum of the first performance evaluation score and the second performance evaluation score (see at least Paragraph 118, The machine learning classifier algorithm may process the input features to generate output values comprising one or more classifications, one or more predictions, or a combination thereof. For example, such classifications or predictions may include a binary classification of a disease or a non-disease state, a classification between a group of categorical labels (e.g., ‘no disease, ‘disease apparent’, and ‘disease likely’), a likelihood (e.g., relative likelihood or probability) of developing a particular disease or disorder, a score indicative of a ‘presence of urgent symptoms’, a ‘risk factor’ for the likelihood of adverse health events (e.g., hospitalization or mortality) of the patient, a prediction of the time at which the patient is expected to have developed the disease or disorder or experienced an adverse health event, and a confidence interval for any numeric predictions. Various machine learning techniques may be cascaded such that the output of a machine learning technique may also be used as input features to subsequent layers or subsections of the machine learning classifier. Various machine learning techniques may be cascaded such that the output of a machine learning technique may also be used as input features to subsequent layers or subsections of the machine learning classifier; Paragraph 121, In some cases, datasets are annotated or labeled. Datasets may be split into subsets (e.g., discrete or overlapping), such as a training dataset, a development dataset, and a test dataset).
At the time of the filing of the application it would have been obvious to one of ordinary skill in the art to combine the teaching of the system and method of predicting viability of a patient of Wang, the features of Schobel, the oversampling of Sweeney and the features of Tignanelli with the features of Liao with the motivation of providing benefit of “… establishing and using a neural network for predicting, assessing, diagnosing, treating, and managing chronic conditions such as heart failure in subjects” (Liao, see at least Paragraph 3).
Claim 15 recites substantially similar method limitations to those of apparatus claim 7 and, as such, is rejected for similar reasons as given above.
Response To Arguments
Applicant’s arguments from the response filed on 06/30/2026 have been fully considered but they are not persuasive. Applicant’s arguments will be addressed below in the order in which they appeared.
In the remarks, Applicant asserts that (1) Claim 1 has been amended to include an affirmative step of training a machine learning model (e.g., as in Example 39 of UPSTO 101 Guidance and Examples). Training an ML model that implements a collaborative filtering algorithm is not abstract. Accordingly, Applicant submits that claims 1-17 are directed to patent-eligible subject matter; (2) Wang fails to disclose each and every feature of independent claims 1, 9 and 17, as newly amended; (3) With respect to claims 3 and 11, Constantine does not remedy Wang’s failure to disclose the limitations newly recited in amended claims 1 and 9; and (4) With respect to claims 7 and 15, Liao does not cure Wang’s failure to disclose the limitations newly recited in amended claims 1 and 9.
In response to applicant’s arguments (1) as listed above, the examiner respectfully disagrees. Although Applicant mentioned Example 39 of the USPTO 101 Guidance and Examples, Examiner respectfully submits that Example 39 is not relevant because there is no abstract idea in Example 39. The claim does not provide any details about how the machine learning model is being trained as a collaborative filtering algorithm to generate the output (prompts for a large language model, personalized based on context information), merely that the machine learning model is being trained as a particular algorithm based on a set of inputs and generates an output of personalized prompts. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. As such, Applicant’s arguments have been considered but are not found to be persuasive.
In response to applicant’s arguments (2) – (4) listed above, the examiner respectfully disagrees. Applicant’s arguments pertain to newly amended limitations, and have been addressed in the rejections above. As such, Applicant’s arguments have been considered but are not found to be persuasive.
Conclusion
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 Joy Chng whose telephone number is 571.270.7897. The examiner can normally be reached on Monday-Thursday and every other Friday.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, JASON DUNHAM can be reached on 571.272.8109. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217.9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Joy Chng/
Primary Examiner, Art Unit 3686
Prosecution Insights