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 Application
This action is in reply to the reply filed January 12, 2026 (hereinafter “Reply”).
Claims 1, 3, 4, 16-18, and 20 are amended.
Claims 1-20 are pending.
Claim Rejections - 35 U.S.C. § 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 1-20 are rejected under 35 U.S.C. § 102(a)(1)-(2) as being anticipated by Hanafialamdari et al. (U.S. Pub. No. 2022/0241530 A1) (hereinafter “Hanafialamdari”).
Claims 1, 16, and 20: Hanafialamdari, as shown, discloses the following limitations:
obtaining, using a set of one or more processors, a classification result predicting expiratory flow limitation (EFL) for one or more patients based on data associated with the one or more patients (see at least ¶ [0151]: in the case of other respiratory failures for other respiratory diseases, the definition of the predicted sleep disruption severity index intensity can change. For example, in COPD the predicted sleep disruption severity index can represent how severe the expiratory flow limitation (EFL) is which may be determined from how fast the expiration flow plateaus. This may also be extracted from the measured R and X using the FOT method; see also at least ¶ [0178]: the inventors have previously determined that the determination made at act 606 may be used to predict an imminent respiratory failure based on sleep study data obtained from patients including a first study using data from CPAP memory cards for 10 patients who suffer from severe sleep apnea including 8 males and 2 females with an overall average age of 53 years and a second study using data from 7 hospital patients who were all male, suffer from severe sleep apnea and have an overall average age of 51 years. For the second study group, all of the data were recorded for a single night so the number of sleep apnea events for the patients in the second study group were lower than the number of sleep apnea events in the data obtained from the CPAP memory cards; however, the data from the second study group contained FOT data for FOT tests that were continuously done during the one night test. While all of the data had sleep apnea events, it is believed that the findings are applicable to other types of respiratory failures. This is because it was generally found that there was a significant difference in spectral density characteristics in signals recorded previous to a respiratory failure occurring compared to signals recorded when breathing was healthy for different types of respiratory conditions. For example, this was found in airflow data and impedance data for patients that had sleep apnea as well as other patients that had other respiratory conditions such as expiratory flow limitation associated with COPD that was showing up both in airflow data and the impedance data; see also at least ¶¶ [0062], [0068], and [0076]), the data being obtained without performing invasive or ventilator based EFL detection (see at least ¶ [0104]: the data used to develop, test and validate the machine learning models described herein was obtained from 33 patients in an approved study conducted at the QEII Health Sciences Centre in Halifax. The patients were 47% female and 53% male with the median age being 55.5 years and the median nights of CPAP use being 135 nights. The test data included thousands of sleep apneas of various categories including obstructive, central and hypopnea sleep apnea. The data was split into test, training and validation data sets. Obstructive sleep apnea events were extracted from the data (for intensity), baseline (normal breathing) and pre-apnea periods (for intensity prediction). Data was also taken based on different EEG determined sleep stages. The data includes measured pressure of air flow, measured air flow rate, and determined resistance and reactance using the measured pressure and air flow rates while performing the FOT method at different frequencies including 4 Hz, 17 Hz, 43 Hz and 79 Hz. The data also included PSG measurements); and
thereafter applying, using a ventilator, a forced oscillation technique to a set of the one or more patients having a classification result predicting EFL (see at least ¶ [0075]: referring now to FIG. 1, illustrated therein is a block diagram of a breathing assistance system 100 for performing at least one of determining breathing signature, performing sleep stage classification and predicting sleep disruption severity. In at least one embodiment, the breathing assistance system 100 can also be used for controlling or tuning a breathing assistance device using the forced oscillation technique based on detection and/or prediction of respiratory failure in accordance with at least one embodiment of the teachings herein. The system 100 comprises a breathing assistance device 102 that generates an airflow that is provided to a user 110 via air transport pathways 104 and 108 and, for example, a laryngeal tube, a breathing mask or an endotracheal tube 109 (hereinafter collectively referred to as an “entry element”). The airflow can be at least one pressure pulse of air, a continuous flow of air, or a superposition of pressure pulses of air and a continuous flow of air. The airflow is controllable by adjusting at least one of the air pressure and flow rate of the breathing assistance device 102 via corresponding input controls on the breathing assistance device 102; see also at least ¶ [0062]: there is provided various embodiments for intelligently monitoring, analyzing, and determining and/or predicting different respiratory and sleep behaviours such as determination of patient breathing signature, determining of patient sleep stage classification, prediction of sleep disruption severity for a patient or any combination thereof. The methods involve using machine learning and other advanced computational techniques to build accurate supervised classification and prediction models. Some of these models will employ measurements of either: (a) air pressure and air flow only; (b) FOT measured airway impedance only; (c) plethysmography such as EEG or (d) a combination of two or more of (a), (b) and (c); see also at least ¶ [0095]: measured airflow parameters, indices and/or control signal 212 may also be shown on an optional display 230 provided on the breathing assistance device controller 206. The display 146 may be, but is not limited to, an LCD display such as that for a tablet device or smartphone; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], and [0094]).
Hanafialamdari discloses implementing these features using various architectures (see at least ¶¶ [0053]-[0054] and [0085]).
Claim 2: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
determining that respective ones of the set of the one or more patients have EFL based on the results of the forced oscillation technique (see at least ¶ [0056]: oscillometry, also known as the forced oscillation technique (FOT), may be performed within the field of respiratory diagnostics by superimposing fluctuations on airway pressure while a user is breathing normally and measuring the resultant pressure and flow rate to determine the mechanical properties of the user's respiratory system. For example, the measured pressure and flow rate may then be used to determine the mechanical impedance of the user's respiratory system. This mechanical impedance is the ratio of the oscillatory pressure to the flow rate in the frequency domain, which can be expressed as a complex quantity (having real and imaginary components) as a function of frequency. More specifically, the real part of the mechanical impedance may be regarded as the respiratory system resistance (Rrs) and the imaginary part can be regarded as the respiratory system reactance (Xrs). FOT is commonly used in modern CPAP machines as a method to differentiate between obstructive and central apnea events, using FOT frequencies of 1-5 Hz.; see also at least ¶¶ [0057]-[0061]).
Claims 3 and 17: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the classification result is formed using two or more of body weight data, forced vital capacity (FVC) data, and data indicative of hyperinflation (see at least ¶ [0081]: the measured airflow parameters such as air volume, air pressure and airflow rate may be used by the breathing assistance device controller 106 to generate a control signal 112 that can be used as feedback to adjust the operation of the breathing assistance device 102. For example, the breathing assistance device controller 106 can employ a control method, where the control signal that is generated may be based on determining the breathing signature of the user according to method 300 (see FIG. 4A), determining the sleep stage for the user such as in method 350 (see FIG. 5), and/or determining a predicted sleep disruption severity such as in method 400 (see FIG. 6A). In other embodiments there can be methods that, for example, performs detection of when respiratory failure will occur and then uses a sleep stage classification index and/or a predicted sleep disruption severity index, such as in method 450 (see FIG. 7) to generate the control signal to provide a corrective action so that the user no longer experiences the respiratory failure; see also at least ¶ [0121]; see also at least ¶ [0124]: the baseline weighted impedance value may be obtained from using standard breathing patterns that are expected for that user 210 based on standard breathing patterns for a healthy population who have comparable physiological characteristics as the user, such as weight (within +/−10%), height (within +/−10%), and gender. Alternatively, the baseline weighted impedance value may be obtained by using the standard breathing patterns and also performing some measurements after the user 210 has received treatment).
Claims 4 and 18: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the classification result is formed using:
patient-reported data comprising one or more of: a confidence about leaving home, and an indication of being limited in activities (see at least ¶ [0165]: the PSG signals XX include (a) CO2, O2 and/or some other gas in the user's expired breath, (b) the user's ECG (i.e. brain activity), (c) the user's EOG (i.e. eye movements), and/or (d) the user's EMG (i.e. skeletomuscular activity). These signals can be measured as described previously. The PSG signal(s) are now used in addition to the measurements of pressure and flow of breathing to predict respiratory failure; see also at least ¶ [0082]); and
one or more of: body weight data, gender data, age data, and height data (see at least ¶ [0124]: the baseline weighted impedance value may be obtained from using standard breathing patterns that are expected for that user 210 based on standard breathing patterns for a healthy population who have comparable physiological characteristics as the user, such as weight (within +/−10%), height (within +/−10%), and gender. Alternatively, the baseline weighted impedance value may be obtained by using the standard breathing patterns and also performing some measurements after the user 210 has received treatment; see also at least ¶ [0121]).
Claim 5: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
classifying the one or more patients based on the data (see at least ¶ [0125]: the breathing signature classifier 229 c can obtain values for input features for the breathing signature machine learning model. These input feature values may be obtained from measured and/or calculated parameters. For example, in at least one embodiment the input feature values may be determined from measured air pressure and/or measured air flow rate. Alternatively, in at least one embodiment the input feature values may be determined from the calculated airway impedance that is determined using one or multi-frequency FOT. Alternatively, in at least one embodiment the input feature values may be determined from: (1) measured air pressure, (2) measured air flow rate; and/or (3) calculated airway impedance determined using one or multi-frequency FOT. When using one or multi-frequency FOT, classification can be made using resistance (R) and reactance (X) resulting from the FOT measurements at different oscillation frequencies. The oscillation frequency can be anywhere between about 0.01 Hz to about 100 MHz and the R and X measured at different frequencies can be used together to classify the patient breathing signature. It should be noted that if impedance, reactance and/or resistance is not used in feature extraction then the performance of the FOT method may not be needed, act 302 does not have to be performed and the air pressure and airflow rate can be measured while the patient is simply breathing without being provided with any perturbation signals. This can also apply for acts 310 performed for methods 350 and 400; see also at least ¶ [0062]: there is provided various embodiments for intelligently monitoring, analyzing, and determining and/or predicting different respiratory and sleep behaviours such as determination of patient breathing signature, determining of patient sleep stage classification, prediction of sleep disruption severity for a patient or any combination thereof. The methods involve using machine learning and other advanced computational techniques to build accurate supervised classification and prediction models. Some of these models will employ measurements of either: (a) air pressure and air flow only; (b) FOT measured airway impedance only; (c) plethysmography such as EEG or (d) a combination of two or more of (a), (b) and (c); see also at least ¶ [0095]: measured airflow parameters, indices and/or control signal 212 may also be shown on an optional display 230 provided on the breathing assistance device controller 206. The display 146 may be, but is not limited to, an LCD display such as that for a tablet device or smartphone; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], and [0094]).
Claim 6: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the classifying comprises employing a machine learning model to predict a level of EFL for the one or more patients based on the data (see at least ¶ [0125]: the breathing signature classifier 229 c can obtain values for input features for the breathing signature machine learning model. These input feature values may be obtained from measured and/or calculated parameters. For example, in at least one embodiment the input feature values may be determined from measured air pressure and/or measured air flow rate. Alternatively, in at least one embodiment the input feature values may be determined from the calculated airway impedance that is determined using one or multi-frequency FOT. Alternatively, in at least one embodiment the input feature values may be determined from: (1) measured air pressure, (2) measured air flow rate; and/or (3) calculated airway impedance determined using one or multi-frequency FOT. When using one or multi-frequency FOT, classification can be made using resistance (R) and reactance (X) resulting from the FOT measurements at different oscillation frequencies. The oscillation frequency can be anywhere between about 0.01 Hz to about 100 MHz and the R and X measured at different frequencies can be used together to classify the patient breathing signature. It should be noted that if impedance, reactance and/or resistance is not used in feature extraction then the performance of the FOT method may not be needed, act 302 does not have to be performed and the air pressure and airflow rate can be measured while the patient is simply breathing without being provided with any perturbation signals. This can also apply for acts 310 performed for methods 350 and 400; see also at least ¶ [0151]: in the case of other respiratory failures for other respiratory diseases, the definition of the predicted sleep disruption severity index intensity can change. For example, in COPD the predicted sleep disruption severity index can represent how severe the expiratory flow limitation (EFL) is which may be determined from how fast the expiration flow plateaus. This may also be extracted from the measured R and X using the FOT method; see also at least ¶ [0062]: there is provided various embodiments for intelligently monitoring, analyzing, and determining and/or predicting different respiratory and sleep behaviours such as determination of patient breathing signature, determining of patient sleep stage classification, prediction of sleep disruption severity for a patient or any combination thereof. The methods involve using machine learning and other advanced computational techniques to build accurate supervised classification and prediction models. Some of these models will employ measurements of either: (a) air pressure and air flow only; (b) FOT measured airway impedance only; (c) plethysmography such as EEG or (d) a combination of two or more of (a), (b) and (c); see also at least ¶ [0095]: measured airflow parameters, indices and/or control signal 212 may also be shown on an optional display 230 provided on the breathing assistance device controller 206. The display 146 may be, but is not limited to, an LCD display such as that for a tablet device or smartphone; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], and [0094]).
Claim 7: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the machine learning model classifies the one or more patients using a value for a difference in inspiratory and expiratory resistances for the one or more patients (see at least ¶ [0173]: the weight parameters (wr and wx) can reflect the specific portion of the reactive/elastic part of the user's respiratory system that is distancing or deviating itself from the elastic part and influencing the resistive part instead (e.g. sometimes because other factors are involved such as the fact that resistance and elastance themselves are sinusoidally changing with breathing, the multiplication of sinusoidal elastance and sinusoidal volume may change the phase of a portion of the elastance to become in phase with air flow, and hence be more resistive). The result of this deviation can cause distress for the user 210 since it may manifest physically as either an obstruction of their airways or a deep distress to their respiratory system due to various factors including, but not limited to, derecruitment of certain lung regions, increased heterogeneity of the user's lungs and/or the presence of liquid in the user's lungs. As such the determined parameters can thus be used to perform: (a) tuning of the breathing assistance device 202 to minimize respiratory failure; diagnosis or identification of the presence of respiratory disease; and/or (b) operating the breathing assistance device 202 to obtain therapeutic outcomes, for example, with respect to adjusting the operating parameters of the breathing assistance device 202 such as the pressure, the flow rate, and/or the moisture of the generated airflow to help COPD patients to breathe or expectorate; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], [0094], and [0151]).
Claim 8: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein:
the value is predictive of EFL (see at least ¶ [0151]: in the case of other respiratory failures for other respiratory diseases, the definition of the predicted sleep disruption severity index intensity can change. For example, in COPD the predicted sleep disruption severity index can represent how severe the expiratory flow limitation (EFL) is which may be determined from how fast the expiration flow plateaus. This may also be extracted from the measured R and X using the FOT method); and
the value is related to one or more thresholds (see at least ¶ [0151] and the analysis above; see also at least ¶ [0065]: the combination may be based on comparing the separate indexes to corresponding threshold levels to perform the corrective action with a higher degree of confidence to compensate for an already occurring respiratory event; see also at least ¶ [0173]: the weight parameters (wr and wx) can reflect the specific portion of the reactive/elastic part of the user's respiratory system that is distancing or deviating itself from the elastic part and influencing the resistive part instead (e.g. sometimes because other factors are involved such as the fact that resistance and elastance themselves are sinusoidally changing with breathing, the multiplication of sinusoidal elastance and sinusoidal volume may change the phase of a portion of the elastance to become in phase with air flow, and hence be more resistive). The result of this deviation can cause distress for the user 210 since it may manifest physically as either an obstruction of their airways or a deep distress to their respiratory system due to various factors including, but not limited to, derecruitment of certain lung regions, increased heterogeneity of the user's lungs and/or the presence of liquid in the user's lungs. As such the determined parameters can thus be used to perform: (a) tuning of the breathing assistance device 202 to minimize respiratory failure; diagnosis or identification of the presence of respiratory disease; and/or (b) operating the breathing assistance device 202 to obtain therapeutic outcomes, for example, with respect to adjusting the operating parameters of the breathing assistance device 202 such as the pressure, the flow rate, and/or the moisture of the generated airflow to help COPD patients to breathe or expectorate; see also at least ¶¶ [0068], [0071], and [0158]-[0160]).
Claim 9: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the machine learning model is one of a patient-facing model and a clinician facing model (see at least ¶ [0055]: the term “user” covers a person who is using a breathing assistance device. In some cases, the user may be an individual that is using the breathing assistance device in their home or a non-medical setting. In other cases, the user may be a patient who is using the breathing assistance device in a medical setting such as a clinic or a hospital, for example).
Claim 10: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
training a machine learning model to produce the classification result (see at least ¶ [0103]: The machine learning models may be trained in various ways. For example, data that was obtained from patients was preprocessed (as described herein for FIG. 2) and divided into a training set, a testing set and a validation test. For example, the training set, the test set and the validation test may comprise using amounts of the data in the proportion of 70%, 15% and 15%, respectively. The training data is used to train the machine learning model so that it accurately predicts a desired parameter. The machine learning model was initialized with some initial parameters and then trained using the training set to determine that machine learning model parameters and input features that provided the highest accuracy. The machine learning model was then tested with the test data set and the accuracy was noted. The parameters of the machine learning model were then adjusted to maximize the accuracy of the machine learning model on the test data set. The machine learning model was then tested with the validation data set and the accuracy was noted; see also at least ¶¶ [0102], [0128], [0130]-[0131], and [0183]).
Claim 11: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
providing a set of features for the machine learning model (see at least ¶ [0102]: certain input features are provided to the machine learning model that have high predictive power; see also at least ¶¶ [0102]-[0103], [0128], [0130]-[0131], and [0183]).
Claim 12: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the set of features comprise a demographic feature (see at least ¶ [0122]: initial assessment for the weight parameters may be done to determine which of the resistance or the reactance is more important for the particular user and then the weights can be associated based on that determination. For example, from measurements of mean X and mean R, the user may be categorized as having a particular respiratory condition such as, but not limited to, asthma, COPD, CF or snoring (for example snoring can be detected as a respiratory failure since the snoring may be an alert of an impending airway closure). Based on the respiratory condition category, the relative weighting of R and X for the user is determined using a database or a lookup table based on data for populations that have the same respiratory condition. As an example, Rref may be weighted higher than Xref in users who are categorized as having asthma while Xref may be weighted higher than Rref in users who are categorized as having COPD. Accordingly, a larger or smaller weight can be applied to reactance relative to the weight that is applied to resistance depending on whether the user has a particular respiratory condition and a certain severity level for that particular respiratory condition; see also at least ¶ [0124]: the baseline weighted impedance value may be obtained from using standard breathing patterns that are expected for that user 210 based on standard breathing patterns for a healthy population who have comparable physiological characteristics as the user, such as weight (within +/−10%), height (within +/−10%), and gender. Alternatively, the baseline weighted impedance value may be obtained by using the standard breathing patterns and also performing some measurements after the user 210 has received treatment) and a feature derived from a spirometry test result (see at least ¶ [0081]: the measured airflow parameters such as air volume, air pressure and airflow rate may be used by the breathing assistance device controller 106 to generate a control signal 112 that can be used as feedback to adjust the operation of the breathing assistance device 102; see also at least ¶ [0115]).
Claim 13: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the set of features comprise:
a patient-reported feature (see at least ¶ [0149]: the predictive sleep disruption severity index can be recorded in a report for a patient or a user of the breathing assistance device 202; see also at least ¶ [0070]: real time determination of a user's breathing signature, classification of the user's sleep stage and/or classification of predicted sleep disruption severity which may then be used to perform at least one of adjusting the operation of the breathing assistive device and providing data in a user report that can be used to monitor the breathing of the user and/or diagnose a respiratory disorder for the user. For example, the report can be determined for data collected when the user slept at night and the report can be provided to the user or a medical professional for review, such as in the morning, so that the user or the medical professional can review data about their respiratory and sleep health, for example; see also at least ¶¶ [0105]); and
a demographic feature (see at least ¶ [0122]: initial assessment for the weight parameters may be done to determine which of the resistance or the reactance is more important for the particular user and then the weights can be associated based on that determination. For example, from measurements of mean X and mean R, the user may be categorized as having a particular respiratory condition such as, but not limited to, asthma, COPD, CF or snoring (for example snoring can be detected as a respiratory failure since the snoring may be an alert of an impending airway closure). Based on the respiratory condition category, the relative weighting of R and X for the user is determined using a database or a lookup table based on data for populations that have the same respiratory condition. As an example, Rref may be weighted higher than Xref in users who are categorized as having asthma while Xref may be weighted higher than Rref in users who are categorized as having COPD. Accordingly, a larger or smaller weight can be applied to reactance relative to the weight that is applied to resistance depending on whether the user has a particular respiratory condition and a certain severity level for that particular respiratory condition; see also at least ¶ [0124]: the baseline weighted impedance value may be obtained from using standard breathing patterns that are expected for that user 210 based on standard breathing patterns for a healthy population who have comparable physiological characteristics as the user, such as weight (within +/−10%), height (within +/−10%), and gender. Alternatively, the baseline weighted impedance value may be obtained by using the standard breathing patterns and also performing some measurements after the user 210 has received treatment).
Claim 14: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
wherein the forced oscillation technique comprises delivering a predetermined number of airflows to the one or more patients using the ventilator (see at least ¶ [0056]: oscillometry, also known as the forced oscillation technique (FOT), may be performed within the field of respiratory diagnostics by superimposing fluctuations on airway pressure while a user is breathing normally and measuring the resultant pressure and flow rate to determine the mechanical properties of the user's respiratory system. For example, the measured pressure and flow rate may then be used to determine the mechanical impedance of the user's respiratory system. This mechanical impedance is the ratio of the oscillatory pressure to the flow rate in the frequency domain, which can be expressed as a complex quantity (having real and imaginary components) as a function of frequency. More specifically, the real part of the mechanical impedance may be regarded as the respiratory system resistance (Rrs) and the imaginary part can be regarded as the respiratory system reactance (Xrs). FOT is commonly used in modern CPAP machines as a method to differentiate between obstructive and central apnea events, using FOT frequencies of 1-5 Hz; see also at least ¶ [0183]).
Claim 15: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
adjusting one or more settings of the ventilator after determining that the one or more patients have EFL (see at least ¶ [0075]: Referring now to FIG. 1, illustrated therein is a block diagram of a breathing assistance system 100 for performing at least one of determining breathing signature, performing sleep stage classification and predicting sleep disruption severity. In at least one embodiment, the breathing assistance system 100 can also be used for controlling or tuning a breathing assistance device using the forced oscillation technique based on detection and/or prediction of respiratory failure in accordance with at least one embodiment of the teachings herein. The system 100 comprises a breathing assistance device 102 that generates an airflow that is provided to a user 110 via air transport pathways 104 and 108 and, for example, a laryngeal tube, a breathing mask or an endotracheal tube 109 (hereinafter collectively referred to as an “entry element”). The airflow can be at least one pressure pulse of air, a continuous flow of air, or a superposition of pressure pulses of air and a continuous flow of air. The airflow is controllable by adjusting at least one of the air pressure and flow rate of the breathing assistance device 102 via corresponding input controls on the breathing assistance device 102; see also at least ¶ [0081]: the measured airflow parameters such as air volume, air pressure and airflow rate may be used by the breathing assistance device controller 106 to generate a control signal 112 that can be used as feedback to adjust the operation of the breathing assistance device 102; see also at least ¶¶ [0088] and [0121]).
Claim 19: Hanafialamdari discloses the limitations as shown in the rejections above. Further, Hanafialamdari, as shown, discloses the following limitations:
code that classifies the one or more patients based on the data (see at least ¶ [0125]: the breathing signature classifier 229 c can obtain values for input features for the breathing signature machine learning model. These input feature values may be obtained from measured and/or calculated parameters. For example, in at least one embodiment the input feature values may be determined from measured air pressure and/or measured air flow rate. Alternatively, in at least one embodiment the input feature values may be determined from the calculated airway impedance that is determined using one or multi-frequency FOT. Alternatively, in at least one embodiment the input feature values may be determined from: (1) measured air pressure, (2) measured air flow rate; and/or (3) calculated airway impedance determined using one or multi-frequency FOT. When using one or multi-frequency FOT, classification can be made using resistance (R) and reactance (X) resulting from the FOT measurements at different oscillation frequencies. The oscillation frequency can be anywhere between about 0.01 Hz to about 100 MHz and the R and X measured at different frequencies can be used together to classify the patient breathing signature. It should be noted that if impedance, reactance and/or resistance is not used in feature extraction then the performance of the FOT method may not be needed, act 302 does not have to be performed and the air pressure and airflow rate can be measured while the patient is simply breathing without being provided with any perturbation signals. This can also apply for acts 310 performed for methods 350 and 400; see also at least ¶ [0062]: there is provided various embodiments for intelligently monitoring, analyzing, and determining and/or predicting different respiratory and sleep behaviours such as determination of patient breathing signature, determining of patient sleep stage classification, prediction of sleep disruption severity for a patient or any combination thereof. The methods involve using machine learning and other advanced computational techniques to build accurate supervised classification and prediction models. Some of these models will employ measurements of either: (a) air pressure and air flow only; (b) FOT measured airway impedance only; (c) plethysmography such as EEG or (d) a combination of two or more of (a), (b) and (c); see also at least ¶ [0095]: measured airflow parameters, indices and/or control signal 212 may also be shown on an optional display 230 provided on the breathing assistance device controller 206. The display 146 may be, but is not limited to, an LCD display such as that for a tablet device or smartphone; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], and [0094]);
wherein the code that classifies comprises code that employs a machine learning model to predict EFL for the one or more patients (see at least ¶ [0125]: the breathing signature classifier 229 c can obtain values for input features for the breathing signature machine learning model. These input feature values may be obtained from measured and/or calculated parameters. For example, in at least one embodiment the input feature values may be determined from measured air pressure and/or measured air flow rate. Alternatively, in at least one embodiment the input feature values may be determined from the calculated airway impedance that is determined using one or multi-frequency FOT. Alternatively, in at least one embodiment the input feature values may be determined from: (1) measured air pressure, (2) measured air flow rate; and/or (3) calculated airway impedance determined using one or multi-frequency FOT. When using one or multi-frequency FOT, classification can be made using resistance (R) and reactance (X) resulting from the FOT measurements at different oscillation frequencies. The oscillation frequency can be anywhere between about 0.01 Hz to about 100 MHz and the R and X measured at different frequencies can be used together to classify the patient breathing signature. It should be noted that if impedance, reactance and/or resistance is not used in feature extraction then the performance of the FOT method may not be needed, act 302 does not have to be performed and the air pressure and airflow rate can be measured while the patient is simply breathing without being provided with any perturbation signals. This can also apply for acts 310 performed for methods 350 and 400; see also at least ¶ [0151]: in the case of other respiratory failures for other respiratory diseases, the definition of the predicted sleep disruption severity index intensity can change. For example, in COPD the predicted sleep disruption severity index can represent how severe the expiratory flow limitation (EFL) is which may be determined from how fast the expiration flow plateaus. This may also be extracted from the measured R and X using the FOT method; see also at least ¶ [0062]: there is provided various embodiments for intelligently monitoring, analyzing, and determining and/or predicting different respiratory and sleep behaviours such as determination of patient breathing signature, determining of patient sleep stage classification, prediction of sleep disruption severity for a patient or any combination thereof. The methods involve using machine learning and other advanced computational techniques to build accurate supervised classification and prediction models. Some of these models will employ measurements of either: (a) air pressure and air flow only; (b) FOT measured airway impedance only; (c) plethysmography such as EEG or (d) a combination of two or more of (a), (b) and (c); see also at least ¶ [0095]: measured airflow parameters, indices and/or control signal 212 may also be shown on an optional display 230 provided on the breathing assistance device controller 206. The display 146 may be, but is not limited to, an LCD display such as that for a tablet device or smartphone; see also at least ¶¶ [0056], [0068], [0076], [0080], [0085]-[0086], and [0094]).
Response to Arguments
The arguments submitted with the Reply have been fully considered but are not persuasive.
Applicant argues that Hanafialamdari does not disclose that the claimed data is obtained without performing invasive or ventilator based EFL detection. Examiner disagrees, because Hanafialamdari teaches at ¶ [0104] that “the data used to develop, test and validate the machine learning models described herein” includes “Data was also taken based on different EEG determined sleep stages” as well as that “The data also included PSG measurements.” These data from Hanafialamdari are obtained without performing invasive or ventilator based EFL detection and used as a basis for predicting EFL as claimed.
Applicant argues that “the office cites to teachings in Hanafialamdari that are unrelated to the claimed ‘weight’ data, which as described is demographic weight data for the patient.” Reply, p. 7. Examiner disagrees, because “weight”—as used in ¶ [0124] of Hanafialamdari and cited to in both the present and previous rejections—refers to the “physiological characteristic” of weight.
Applicant argues that “the office has not cited to an example in Hanafialamdari in which ‘spirometry’ test results are utilized (Hanafialamdari does not use this term or its equivalent.” Reply, p. 7. Examiner disagrees. Under the broadest reasonable interpretation consistent with the specification, a “spirometry test” includes tests that measure how much air one breathes in and out from one’s lungs. Hanafialamdari discloses these kinds of results—measured airflow parameters such as air volume, air pressure and airflow rate—at ¶ [0081]. Applicant’s specification lists several examples of spirometry results at ¶ [0042], but none of these particular examples are required by claim 12.
Conclusion
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. The following references have been cited to further show the state of the art with respect to treatment of expiratory flow limitations.
Brayanov et al. (U.S. Pub. No. 2019/0183383 A1) (calculating and displaying continuously monitored tidal breathing flow-volume loops);
Shouldice (U.S. Pub. No. 2024/0398355 A1) (monitoring and management of chronic disease);
Martin et al. (U.S. Pub. No. 2023/0309914 A1) (non-invasive monitory of respiratory parameters in sleep disordered breathing);
Liu et al. (U.S. Pub. No. 2022/0076822 A1);
Amaral et al. (“Differential diagnosis of asthma and restrictive respiratory diseases by combining forced oscillation measurements, machine learning and neuro-fuzzy classifiers.” Medical & Biological Engineering & Computing 58.10 (2020): 2455-2473).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Christopher Tokarczyk, whose telephone number is 571-272-9594. The examiner can normally be reached Monday-Thursday between 6:00 AM and 4:00 PM Eastern.
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, Mamon Obeid, can be reached at 571-270-1813. 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.
/CHRISTOPHER B TOKARCZYK/ Primary Examiner, Art Unit 3687