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 response to the restriction election statement filed 10/03/2025. Claims 1-7 have been elected, claims 8-15 have been withdrawn. Claims 1-7 are currently pending.
Restriction/Election
Applicant's election with traverse of Invention I in the reply filed on 10/03/2025 is acknowledged. The traversal is on different grounds.
The first is that no serious search or examination burden has been shown. This is not found persuasive because the three inventions are different from one another, as indicated in the original requirement for restriction and their classifications. Applicant’s remarks have been considered but are not persuasive.
The second is that the process-apparatus/system relationship is not patentably distinct on this record. Applicant’s argument that the nonelected apparatus and system claims are configured to perform the same risk-inference pipeline required by the elected method claims are not persuasive as the elected claims do not require at least the same pre-processing as the elected claims. Therefore, these pipelines are patentably distinct.
The third is that the claimed inventions are capable of use together and overlap in design, mode of operation and effect. A cursory review of the Specification does not support Applicant’s assertion that the monitoring system in Invention III would require the model and corresponding training of the model in Invention I as a prediction model is not necessarily a machine learning model as recited in Invention I.
The requirement is still deemed proper and is therefore made FINAL.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Sørensen et al (US 20240374136 A1, herein Sørensen).
Regarding claim 1, Sørensen teaches a machine learning model training method to train a sudden death prediction model for predicting the probability of sudden death, comprising using continuous physiological monitoring data and survival results of patients in a database for model training (para. [0006] recites “The present disclosure addresses the above-mentioned challenges by providing a system and method for automatic and continuous detection of clinical deterioration events in a patient” (i.e., a method for detecting, or predicting, clinical patient deterioration, or risk of sudden death). Para. [0175] recites “Application of the approach disclosed in example also 2 applies to clinical deterioration events detected in accordance with the presently disclosed approach, i.e. clinical deterioration events and/or SAEs (i.e., serious adverse events) can be detected, and thereby also possibly predicted and preferably prevented, with detection of clinical deterioration events as disclosed herein, i.e. by application of machine learning and continuous vital sign monitoring of (post-operative) patients”. Para. [0161] recites “providing the (validated) ECG data to a semi-supervised learning model, e.g. a deep generative model based on neural networks, trained and configured to determine atrial fibrillation (AF) based on (validated) ECG data” (i.e., using a machine learning model to predict a serious adverse event, such as atrial fibrillation based on monitored physiological data)), wherein:
the physiological monitoring data consist essentially of heart rate (HR) and blood oxygen (SpO2) data (para. [0007]-[0008] recite “the present disclosure relates to a computer-implemented method configured for automatic real-time detection of clinical deterioration events in a patient, the method comprising the steps of: continuously receiving a plurality of different vital sign data from a plurality of sensors worn by the patient, the vital sign data selected from the group of: electrocardiogram (ECG), photoplethysmogram (PPG), heart rate (HR), respiration rate (RR), blood pressure ( e.g. systolic blood pressure, SBP), heart rhythm, ischemic electrocardiographic response, peripheral temperature, peripheral skin conductance, 3D body position and acceleration, pulse rate, peripheral perfusion index, peripheral oxygen saturation (SpO2), and subcutaneous glucose concentration; optionally/alternatively vital sign data like blood pressure can be estimated from other measured vital sign data, for example heart rate (HR), respiration rate (RR), blood oxygen saturation (SpO2) and pulse rate (PR) as disclosed herein, as these vital sign data are easier to measure than blood pressure” (i.e., the physiological monitoring data can include blood oxygen and/or heart rate data. Examiner notes that MPEP 2111.03 states: “For the purposes of searching for and applying prior art under 35 U.S.C. 102 and 103, absent a clear indication in the specification or claims of what the basic and novel characteristics actually are, "consisting essentially of" will be construed as equivalent to "comprising"”));
and the survival results comprise categories of the survival status of the patients (para. [0165]-[0171] recite “A Serious Adverse Event (SAE) is any untoward medical occurrence or effect at any dose, any undesirable or unintentional effect that: results in death (regardless of cause), is life threatening, results in hospitalization or prolongation of existing hospitalization, results in persistent or significant disability or incapacity of the subject, is associated with a congenital anomaly or birth defect, is qualified as "other" important medically significant event or condition e.g. the event may jeopardize the subject or may require intervention to prevent one of the outcome listed above (e.g. intensive treatment in an emergency room or at home)”. Para. [0232] recites “Prediction of SAE can be seen as a classification problem aiming to classify "SAE" versus "no SAE" over a time period (prediction window), e.g. few hours, based on last recordings (observation window)” (i.e., the results determine the serious adverse event, or survival status of a patient)).
Regarding claim 2, Sørensen teaches the method of claim 1, wherein the physiological monitoring data comprise continuous 24-hour physiological data of patients (para. [0006] recites “The present disclosure addresses the above-mentioned challenges by providing a system and method for automatic and continuous detection of clinical deterioration events in a patient. An advantage of the presently disclosed system and method, is that it provides a continuous real-time monitoring of a patient (ideally 24/7), wherein an alarm is generated in case the patient has a deterioration event” (i.e., 24 hour physiological monitoring of patients)).
Regarding claim 3, Sørensen teaches the method of claim 1, wherein the categories of the survival status comprise a category representing patient alive and a category representing patient death (para. [0165]-[0171] recite “A Serious Adverse Event (SAE) is any untoward medical occurrence or effect at any dose, any undesirable or unintentional effect that: results in death (regardless of cause), is life threatening, results in hospitalization or prolongation of existing hospitalization, results in persistent or significant disability or incapacity of the subject, is associated with a congenital anomaly or birth defect, is qualified as "other" important medically significant event or condition e.g. the event may jeopardize the subject or may require intervention to prevent one of the outcome listed above (e.g. intensive treatment in an emergency room or at home)”. Para. [0232] recites “Prediction of SAE can be seen as a classification problem aiming to classify "SAE" versus "no SAE" over a time period (prediction window), e.g. few hours, based on last recordings (observation window)” (i.e., using a machine learning model to predict whether a patient has had a serious adverse event, or is dead, or whether the patient has not had a serious adverse event, or is alive)).
Regarding claim 4, Sørensen teaches the method of claim 1, comprising performing synthetic minority oversampling technique (SMOTE) for categories with smaller data amount for repeated sampling, so that the amount of data of different categories are approximately equal (para. [0247] recites “After feature extraction, 5-fold cross validation is used to split the data into a training set and a test set. Each fold is used once for testing while the four remaining folds constitute the training set. This procedure is performed 10 times and from the evaluation metrics the average is computed. To correct for the imbalance in the dataset, the Synthetic minority Oversampling Technique (SMOTE) is applied to the training but not the test set. The implementation used in this example was provided by the imbalanced-learn library and brings both classes to equal size” (i.e., performing synthetic minority oversampling to balance category, or class sizes)).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Sørensen et al (US 20240374136 A1, herein Sørensen) in view of Banerjee et al (US 20200352461 A1, herein Banerjee).
Regarding claim 5, Sørensen teaches the method of claim 1,
However, Sørensen does not explicitly teach wherein the machine learning model is trained with a long short-term memory recurrent neural network (LSTM-RNN).
Banerjee teaches wherein the machine learning model is trained with a long short-term memory recurrent neural network (LSTM-RNN) (fig. 4 and para. [0008] recite “there is provided a system for classification of atrial fibrillation (AF) comprising . . . input the first time series and the second time series independently to a pair of Long short-term memory (LSTM) networks” (i.e., a LSTM network)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine these teachings by modifying the serious adverse event prediction system from Sørensen to utilize the LSTM machine learning model from Banerjee to predict a serious adverse event like atrial fibrillation. Sørensen and Banerjee are both directed to methods of using machine learning models on ECG data to predict serious medical events that can lead to sudden patient death. As Sørensen teaches in at least paragraph [0161] that a neural network model can be used for this prediction, one of ordinary skill in the art would understand how to substitute the LSTM neural network model from Banerjee for the purpose of predicting a serious adverse event like atrial fibrillation.
Regarding claim 6, the combination of Sørensen and Banerjee teaches the method of claim 5, wherein the LSTM-RNN employs two LSTM layers plus two fully connected layers after expansion of the LSTM layers, and then applies a Softmax layer to the last layer for training (Banerjee fig. 4 and para. [0008] recite “there is provided a system for classification of atrial fibrillation (AF) comprising . . . input the first time series and the second time series independently to a pair of Long short-term memory (LSTM) networks . . . and a classifier comprising a plurality of full connected layers and a softmax function, wherein the classifier is configured to classify the AF in the acquired ECG based on the composite feature set”. Banerjee para. [0039] recites “As shown in FIG. 4, in an embodiment, output states of the two LSTM networks are merged at the dense layer along with the hand-crafted statistical features and passed through two fully connected layers and softmax layer for classification” (i.e., a machine learning model including two LSTM layers, two fully connected layers after the LSTM layers, and a softmax layer as the last layer)).
Claims 7 is rejected under 35 U.S.C. 103 as being unpatentable over Sørensen et al (US 20240374136 A1, herein Sørensen) in view of Chen et al (“Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network”, herein Chen).
Regarding claim 7, Sørensen teaches the method of claim 1.
However, Sørensen does not explicitly teach wherein the machine learning model is trained by temporal convolutional network (TCN).
Chen teaches wherein the machine learning model is trained by temporal convolutional network (TCN) (pg. 4 left column para. 2 recites “we developed an attention-based TCN model to predict the mortality risk of ICU patients with time series and static data. The TCN is a convolutional network, which is composed of causal convolution, diluted convolution, and residual connection. The causal convolution makes the TCN a strict temporal model, which uses data from time t and earlier in the previous step to predict the status at time t, when model trained” (i.e., training a temporal convolutional network to predict patient mortality, or sudden death)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine these teachings by modifying the serious adverse event prediction system from Sørensen to utilize the TCN model from Chen. Sørensen and Chen are both directed to methods of using machine learning models on physiological data such as heart rate and blood oxygen data to predict serious medical events that can lead to sudden patient death. As Sørensen teaches in at least paragraph [0161] that a neural network model can be used for this prediction, one of ordinary skill in the art would understand how to substitute the TCN model from Chen for the purpose of predicting a serious adverse event.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20210212639 A1 (Chen et al) teaches a method for performing abnormality detection on the physiological information and calculating an early warning level when an abnormality related to sudden death is predicted.
“A Novel and Reliable Framework of Patient Deterioration Prediction in Intensive Care Unit Based on Long Short-Term Memory-Recurrent Neural Network” (Alshwaheen et al) teaches a combination of LSTM deep learning algorithm as prediction model, together with the optimisation approach based on multi-objective genetic algorithm to predict sudden patient deterioration.
“Using a Multi-Task Recurrent Neural Network With Attention Mechanisms to Predict Hospital Mortality of Patients” (Yu et al) teaches a multi-task deep learning model with attention mechanisms to predict patients’ hospital mortality and reconstruct their physiological time series simultaneously.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEAH M FEITL whose telephone number is (571) 272-8350. The examiner can normally be reached on M-F 0900-1700 EST.
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, Viker Lamardo can be reached on (571) 270-5871. 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 https://ppair-my.uspto.gov/pair/PrivatePair. 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.
/L.M.F./ Examiner, Art Unit 2147
/JAMES T TSAI/Primary Examiner, Art Unit 2147