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 .
Election/Restrictions
Applicant’s election without traverse of Invention I in the reply filed on March 30, 2026 is acknowledged. Claims 1-13 are pending and under examination. Accordingly, claims 14-33 are withdrawn from consideration as being directed to a non-elected invention.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 1 is rejected under 35 U.S.C. 103 as being unpatentable over Zuckerman Stark et al. (US 2018/0310877) in view of Axelrod et al. (US 2019/0261872).
In re claim 1, Zuckerman Stark discloses a hemodynamic monitor [0012] for detecting nociception of a patient [0003, 0012], the hemodynamic monitor comprising:
a non-invasive blood pressure sensor ([0087]; [0088]: “a blood pressure sensor”) comprising
a finger probe [0012],
an integrated hardware unit comprising (fig 1B: 100b; [0140]):
a system processor (110b);
a system memory [0234]; and
a display (120b) comprising a user interface [0171]; and
wherein the system memory comprises nociception detection instructions [0234] that, when executed by the system processor, are configured to:
generate an arterial pressure reading data of the patient [0092];
extract a plurality of signal measures (fig 2: 220) from the arterial pressure reading data of the patient ([0092]: “physiological parameters may at least include… arterial blood pressure”; [0154]: statistical analysis was performed on readings such as mean arterial pressure and heart rate);
extract detection input features from the plurality of signal measures that are indicative of a current nociception event of the patient (230; [0141]: “NS value is determined based on an analysis of the at least three physiological parameters”);
determine a nociception score of the patient based on the detection input features (250);
generate a first sensory alarm signal ([0113]: “output signal”) configured to generate a first sensory alert ([0114]: “output signal may include triggering an alarm”) that indicates that the patient is experiencing the current nociception event when the nociception score satisfies a predetermined detection criterion (fig 2: 260);
transmit the first sensory alarm signal to the user interface [0114]; and
output the first sensory alert through the user interface ([0114]: “the alarm and/or the alert may be visual, audible, and/or physical”).
Zuckerman Stark lacks:
an inflatable blood pressure bladder,
a pressure controller pneumatically connected to the inflatable blood pressure bladder, and
an optical transmitter and an optical receiver that are electrically connected to the pressure controller; and
adjust, by the pressure controller, a pressure within the inflatable blood pressure bladder to maintain a constant volume of an artery of a patient for a period of time based on a feedback signal generated by the optical transmitter and the optical receiver;
generate an arterial pressure waveform data of the patient based on the adjusted pressure within the inflatable blood pressure bladder over the period of time;
extract a plurality of signal measures from the arterial pressure waveform data of the patient
Axelrod teaches a system that uses an inflatable finger cuff to measure arterial blood pressure of a patient and can be adaptively tuned by a control system [0009] to maintain a constant arterial volume [0006]. A pressure measurement controller is connected to a bladder of the finger cuff by a connector to provide pneumatic pressure to the bladder [0026]. The system is connected to control circuitry [0031] which can use an open loop mode to pressurize the bladder and determine measured changes in blood pressure, and then the measured results can be used to adjust the closed loop modes ([0023]: first sentence). The measured results are adjusted to the determined optimal values for measuring blood pressure with high fidelity [0023]: second to last sentence). A high-fidelity feedback loop is used for determining accurate blood pressure measurements [0004] with the volume clamp system, which maintains a constant arterial volume [0006]. A pressure waveform is generated from the data measured from the finger cuff [0035].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of Zuckerman Stark with an inflatable blood pressure cuff that used a feedback loop to maintain a constant volume of an artery and then generate pressure waveforms based off of the finger cuff data as taught by Axelrod, as inflatable finger cuffs are known for non-invasively measuring arterial blood pressure and that the amount of pressure in the bladder can be pneumatically controlled to try to maintain the blood pressure, and that arterial blood pressure data can be used to generate an arterial blood pressure waveform.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Zuckerman Stark et al. (US 2018/0310877) in view of Axelrod et al. (US 2019/0261872) in view of Huiki (US 2005/0272984) in view of Qasem (US 2018/0296104).
In re claim 2, Zuckerman Stark discloses
wherein the detection input features of the nociception detection instructions are determined by detection machine training ([0101]: the physiological parameters can be analyzed by different machine learning programs),
Zuckerman Stark additionally discloses that blood pressure [0024] and heart rate [0024] are parameters of interest and that a baseline nociception score should be established [0137] but is silent to how the machine learning model would process these. Zuckerman Stark discloses determining the efficacy of analgesics by analyzing physiological parameters before and after a drug is given. Accordingly, Zuckerman Stark lacks:
wherein the detection machine training comprises:
collecting a clinical dataset containing arterial pressure waveforms and clinical annotations of administrations of a compound that alters cardiovascular hemodynamics;
identifying nociception data segments in the clinical dataset,
wherein the nociception data segments each comprise:
an increase in blood pressure of at least a first threshold compared to a prior time period;
an increase in heart rate of at least a second threshold compared to the prior time period; and
no infusion of the compound that alters cardiovascular hemodynamics started prior to the increase in blood pressure and the increase in heart rate;
identifying a start and an end of the increase in the blood pressure and the increase in the heart rate;
labeling the nociception data segments after the start and during the increase in the blood pressure and the increase in the heart rate;
performing waveform analysis of the labeled nociception data segments to calculate a plurality of signal measures of the nociception data segments; and
determining the detection input features by computing combinatorial measures between the plurality of signal measures of the nociception data segments and
selecting top signal measures from the plurality of signal measures of the nociception data segments with most predictive combinatorial measures and
labeling the top signal measures as the detection input features.
Huiku teaches a method for monitoring noxious responses in a patient [0001]. Nociception can be determined by extracting pain related features from a waveform (fig 2; [0071]). Pain related features can include in increase in heart rate or blood pressure [0071]. Huiku also teaches that a threshold value can be set based on the normalized signal values and then used to determine if a noxious event occurs (fig 2). Depending on the level of pain experienced by the patient, an analgesic drug can be delivered [0053].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by identifying the increase in heart rate and blood pressure as taught by Huiku, as an increase in heart rate and blood pressure during surgery can be signs of increased nociception and can tell the physician whether an analgesic drug needs to be administered.
Qasem teaches a method for non-invasive blood pressure measurement that analyzes features of a pulse waveform such as the maximum and minimum pulses (fig 4) and uses machine learning models to take the detected features and determine whether the patient has hypertension.
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by using a machine learning model to analyze features of an arterial waveform and classify them as taught by Qasem, as it is known that machine learning models can be used on an arterial waveform dataset to identify areas of abnormality by using the detected features to determine the areas where there is the most abnormal activity and to identify those as the signal.
It should be noted that the path of a machine learning model includes steps of labeling, analyzing, and the like. Accordingly, applying the teachings of Zuckerman Stark, Huiku, and Qasem to a machine learning model as proposed above would yield the above limitations indicated as lacking.
Claims 3-8 are rejected under 35 U.S.C. 103 as being unpatentable over Zuckerman Stark et al. (US 2018/0310877) in view of Axelrod et al. (US 2019/0261872) in view of Huiki (US 2005/0272984) in view of Qasem (US 2018/0296104) in view of Al Hatib et al. (US 2018/0008205).
In re claim 3, the proposed combination lacks wherein the system memory comprises nociception prediction instructions that, when executed by the system processor, are configured to:
extract prediction input features from the plurality of signal measures that are predictive of a future nociception event of the patient,
generate a second sensory alarm signal configured to generate a second sensory alert that indicates that the patient is likely to experience the future nociception event when the nociception prediction score satisfies a predetermined prediction criterion;
transmit the second sensory alarm signal to the user interface; and
output the second sensory alert through the user interface.
Al Hatib teaches a processor that obtains hemodynamic data from a hemodynamic sensor that collects vital sign parameters and determines the probability of the patient experiencing a future hypotension event (abstract) by analyzing an arterial pressure waveform [0038]. Al Hatib also teaches where a sensory alarm is used if the probability of a future event exceeds a predetermined risk criterion (fig 4: 466).
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by analyzing an arterial waveform to determine the probability of a future event and alerting the user if the probability exceeds a certain threshold to detect whether blood pressure has changed as taught by Al Hatib, as it is known that arterial blood pressure waveforms can be used to analyze the different parts of the cardiac cycle to determine blood pressure and can be used to predict whether the patient is about to experience a change in blood pressure.
Regarding the limitations:
wherein the prediction input features and the detection input features are extracted concurrently from the plurality of signal measures;
determine a nociception prediction score of the patient based on the prediction input features,
wherein the nociception prediction score and the nociception score are determined concurrently;
It is known that machine learning can analyze a plurality of signals together. Accordingly, it would be obvious to a medical practitioner to analyze the different parts of a patient’s arterial waveform concurrently as analyzing the entire waveform would allow the practitioner to determine when the patient is at their baseline, when medication is administered, when their nociception levels peak, predict that nociception is about to peak, and predict that a medication is about to be administered by analyzing the trends in the waveform which would allow the practitioner to treat the patient with analgesics more effectively.
In re claim 4, regarding the following limitations, see above (In re claim 3):
wherein the prediction input features of the nociception prediction instructions are determined by prediction machine training, wherein the prediction machine training comprises:
Regarding the following limitations, see above (In re claim 2, in particular the discussion of how the proposed method, when adapted to a machine learning model, yields the recited steps):
identifying the prior time period before the start of the increase in the blood pressure and the increase in the heart rate of each of the nociception data segments;
labeling the prior time period of each of the nociception data segments as prediction data segments;
performing waveform analysis of the prediction data segments to calculate a plurality of signal measures of the prediction data segments; and
determining the prediction input features by computing combinatorial measures between the plurality of signal measures of the prediction data segments and
selecting signal measures from the plurality of signal measures of the prediction data segments with most predictive combinatorial measures as the prediction input features.
In re claim 5, Zuckerman Stark discloses wherein the system memory comprises hemodynamic drug detection instructions that [0039], when executed by the system processor, are configured to:
extract hemodynamic drug detection input features from the plurality of signal measures that are indicative of a hemodynamic drug administration event of the patient (fig 4: 410 and 420),
generate a third sensory alarm signal configured to generate a third sensory alert that indicates that the patient is experiencing the hemodynamic drug administration event when the hemodynamic drug detection score satisfies a predetermined hemodynamic detection criterion ([0114]: multiple alarms can be generated whether a first or second threshold for nociception is crossed; fig 4: 450; [0115]: a display can show whether a patient needs a decrease or increase in the drug and the display can be visual, audible, or tactile);
transmit the third sensory alarm signal to the user interface (fig 4: 450); and
output the third sensory alert through the user interface [0115, 0143].
Regarding the limitations, see above (In re claim 3, in particular the discussion of how a machine learning model can analyze different signals concurrently as well as how the doctor would want to analyze the waveform concurrently to predict and detect nociception and notice when a drug was given).
wherein the hemodynamic drug detection input features, the prediction input features, and the detection input features are extracted concurrently from the plurality of signal measures;
determine a hemodynamic drug detection score of the patient based on based on the hemodynamic drug detection input features,
wherein the hemodynamic drug detection score, the nociception prediction score, and the nociception score are determined concurrently;
In re claim 6, Zuckerman Stark discloses wherein the hemodynamic drug detection input features of the hemodynamic drug detection instructions are determined by hemodynamic drug detection machine training, wherein the hemodynamic drug detection machine training comprises:
identifying hemodynamic drug administration data segments in the clinical dataset [0033], wherein the hemodynamic drug administration data segments each comprise:
an infusion of a compound that alters cardiovascular hemodynamics ([0034]: an analgesic is given);
an increase in blood pressure of at least a third threshold after the infusion ([0039]: an analgesic is given and physiological parameters are measured after); and
an increase in heart rate of at least a fourth threshold after the infusion [0039];
Regarding the following limitations, see above (In re claim 2, in particular the discussion of how the proposed method, when adapted to a machine learning model, yields the recited steps):
identifying a start and an end of the increase in the blood pressure and the increase in the heart rate in each of the hemodynamic drug administration data segments;
labeling the hemodynamic drug administration data segments after the start and during the increase in the blood pressure and the increase in the heart rate;
performing waveform analysis of the labeled hemodynamic drug administration data segments to calculate a plurality of signal measures of the hemodynamic drug administration data segments; and
determining the hemodynamic drug detection input features by computing combinatorial measures between the plurality of signal measures of the hemodynamic drug administration data segments and
selecting signal measures from the plurality of signal measures of the hemodynamic drug administration data segments with most predictive combinatorial measures as being the hemodynamic drug detection input features.
In re claim 7, Zuckerman Stark discloses wherein the system memory stores hemodynamic drug prediction instructions [0039] that, when executed by the system processor, are configured to:
extract hemodynamic drug prediction input features from the plurality of signal measures that are predictive of a future hemodynamic drug administration event of the patient ([0039]: three physiological parameters of a patient before and after a drug is given are analyzed),
generate a fourth sensory alarm signal configured to generate a fourth sensory alert that indicates that the patient is likely to experience the future hemodynamic drug administration event when the hemodynamic drug prediction score satisfies a predetermined hemodynamic drug prediction criterion ([0114]: alarms can be generated when nociception scores cross a certain threshold; [0115]: a display may be used to signal when a change in analgesics is necessary because a pain threshold has been crossed);
transmit the fourth sensory alarm signal to the user interface [0115]; and
output the fourth sensory alert through the user interface [0115].
Regarding the limitations, see above (In re claim 3, in particular the discussion of how a machine learning model can analyze different signals concurrently as well as how the doctor would want to analyze the waveform concurrently to predict and detect nociception and drug administration).
wherein the hemodynamic drug prediction input features, the hemodynamic drug detection input features, the prediction input features, and the detection input features are extracted concurrently from the plurality of signal measures;
determine a hemodynamic drug prediction score based on the hemodynamic drug prediction input features,
wherein the hemodynamic drug prediction score, the hemodynamic drug detection score, the nociception prediction score, and the nociception score are determined concurrently;
In re claim 8, regarding the following limitation see above (in re claim 7)
wherein the hemodynamic drug prediction input features of the hemodynamic drug prediction instructions are determined by hemodynamic drug prediction machine training, wherein the hemodynamic drug prediction machine training comprises:
Regarding the following limitations, see above (In re claim 2, in particular the discussion of how the proposed method, when adapted to a machine learning model, yields the recited steps):
identifying a previous time period before the start of the increase in the blood pressure and the increase in the heart rate of each of the hemodynamic drug administration data segments;
labeling the previous time period of each of the hemodynamic drug administration data segments as hemodynamic drug prediction data segments;
performing waveform analysis of the hemodynamic drug prediction data segments to calculate a plurality of signal measures of the hemodynamic drug prediction data segments; and
determining the hemodynamic drug prediction input features by computing combinatorial measures between the plurality of signal measures of the hemodynamic drug prediction data segments and
selecting signal measures from the plurality of signal measures of the hemodynamic drug prediction data segments with most predictive combinatorial measures as the hemodynamic drug prediction input features.
Claims 9-11 are rejected under 35 U.S.C. 103 as being unpatentable over Zuckerman Stark et al. (US 2018/0310877) in view of Axelrod et al. (US 2019/0261872) in view of Huiki (US 2005/0272984) in view of Qasem (US 2018/0296104) in view of Al Hatib et al. (US 2018/0008205) in view of Subramanian et al. (WO 2021/011588).
In re claim 9, wherein the system memory stores stable detection instructions that, when executed by the system processor, are configured to:
extract stable detection input features from the plurality of signal measures that are indicative of a stable episode of the patient where the patient is not experiencing a nociception event nor a hemodynamic drug administration event,
determine a stable score based on the stable detection input features,
wherein the stable score indicates a probability of the stable episode, and
outputting the stable score to a display.
Subramanian teaches a system for detecting nociception under anesthesia (abstract) by analyzing mean heart rate, pulse rate, and EEGs which can show whether the patient is stable without experiencing nociception and without needing a drug administered [0077]. A display can be used to indicate the probability of the patient’s nociception [0063].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by determining when the patient is stable so that the physician knows whether they are in pain or whether they have already received a drug as taught by Subramanian, as knowing when the patient is stable allows for the physician to only give drugs when they are needed due to an increased nociception state which would prevent over-medicating and using unnecessary resources.
Regarding the limitations, see above (In re claim 3, in particular the discussion of how a machine learning model can analyze different signals concurrently as well as how the doctor would want to analyze the waveform concurrently to predict and detect nociception).
wherein the stable detection input features, the hemodynamic drug prediction input features, the hemodynamic drug detection input features, the prediction input features, and the detection input features are extracted concurrently from the plurality of signal measures;
wherein the stable score, the hemodynamic drug prediction score, the hemodynamic drug detection score, the nociception prediction score, and the nociception score are determined concurrently; and
In re claim 10, regarding the following limitation, see above (in re claim 9)
wherein the stable detection input features of the stable detection instructions are determined by stable detection machine training, wherein the stable machine training comprises:
Regarding the following limitations:
identifying stable data segments in the clinical dataset, wherein the stable data segments each comprise:
stable blood pressure with no increase greater than the first threshold over a set period of time;
stable heart rate with no increase greater than the second threshold over the set period of time; and
no infusion performed of a compound that alters cardiovascular hemodynamics;
Subramanian also teaches that the patient is stable if the heart rate, pulse rate, and EEG remain unchanged or stay under a certain threshold for a set duration [0077].
It would be obvious to one of ordinary skill in the art at the time instant was filed to modify the system of the proposed combination by determining that the stable features are maintained under a certain threshold over time as taught by Subramanian, as identifying the stable segments would provide a baseline for the patient so that instances of nociception could be identified which would allow the physician to determine when the patient is experiencing more pain and may need medications or when the patient has benefited from medication and medication can be stopped.
Regarding the following limitations, see above (In re claim 2, in particular the discussion of how the proposed method, when adapted to a machine learning model, yields the recited steps):
identifying a start and an end of the stable blood pressure and the stable heart rate;
labeling the stable data segments from the start and the end of the stable blood pressure and the stable heart rate;
performing waveform analysis of the labeled stable data segments to calculate a plurality of stable signal measures of the stable data segments; and
determining the stable detection input features by computing combinatorial measures between the plurality of stable signal measures and
selecting stable signal measures from the plurality of stable signal measures with most predictive combinatorial measures as being the stable detection input features.
In re claim 11, wherein performing waveform analysis of the labeled nociception data segments to calculate a plurality of signal measures of the nociception data segments comprises:
identifying individual cardiac cycles in the arterial pressure waveform of the clinical dataset;
identifying a dicrotic notch in each of the individual cardiac cycles;
identifying a systolic rise phase, a systolic decay phase, and a diastolic phase in each of the individual cardiac cycles; and
extracting signal measures from each of the systolic rise phase, the systolic decay phase, and the diastolic phase from each of the individual cardiac cycles.
Al Hatib teaches identifying the parts of an individual heartbeat (fig 5). The dicrotic notch (586), systolic rise (between 582 and 584), systolic decay (580), and diastolic phase (between 586 and 588) are identified for the individual heartbeat of a waveform and signal measures can be extracted from any of the individual or combined parts of the identified heartbeat [0040].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by analyzing the different parts of the individual heartbeats as taught by Al Hatib, as each part can be labeled and show abnormalities or be predictive of future abnormalities.
Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Zuckerman Stark et al. (US 2018/0310877) in view of Axelrod et al. (US 2019/0261872) in view of Huiki (US 2005/0272984) in view of Qasem (US 2018/0296104) in view of Al Hatib et al. (US 2018/0008205) in view of Subramanian et al. (WO 2021/011588) in view of O’Brien (US 2011/0270047).
In re claim 12, the proposed combination yields wherein
the signal measures correspond to hemodynamic effects from each of the systolic rise phase, the systolic decay phase, and the diastolic phase from each of the individual cardiac cycles (Al Hatib: [0040]), and
The proposed combination lacks
wherein the hemodynamic effects comprise contractility, aortic compliance, stroke volume, vascular tone, afterload, and full cardiac cycle;
the signal measures comprise a mean, a maximum, a minimum, a duration, an area, a standard deviation, derivatives, and/or morphological measures from each of the systolic rise phase, the systolic decay phase, and the diastolic phase from each of the individual cardiac cycles; and/or
the signal measures comprise heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variation, stroke volume variation, mean arterial pressure (MAP), systolic pressure (SYS), diastolic pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and/or left-ventricular contractility extracted from each of the individual cardiac cycles.
O’Brien teaches a monitoring device to measure hemodynamic parameters during surgery (abstract). One hemodynamic parameter that can be examined during surgery and before or after medication is administered is afterload [0022, 0024].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by also analyzing afterload as a hemodynamic effect as taught by O’Brien, as afterload can affect cardiac output which may cause a change in the patient’s arterial waveform which could cause them to need medication to be administered.
Al Hatib teaches a monitoring system to detect hypotension by analyzing arterial pressure waveforms [0019]. Different hemodynamic effects can include contractility [0041], aortic compliance [0067], stroke volume [0041], vascular tone [0024], and full cardiac cycle [0040]. Signal measures can be taken from the different parts of the arterial pressure waveform and can include a maximum [0039], a duration [0038], an area [0039], a standard deviation [0039] from the different parts of the cardiac cycle and waveform [0039]. The signal measures can also include analyzing heart rate [0041], respiratory rate [0041], stroke volume [0041], pulse pressure [0069], mean arterial pressure (MAP) [0041], systolic pressure (SYS) [0039], and left-ventricular contractility [0041] from the cardiac cycles.
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of the proposed combination by analyzing the arterial waveform and looking at a variety of hemodynamic effects and measuring different types of signals as taught by Al Hatib, as an arterial pressure waveform can be analyzed to determine a wide array of cardiac measures depending on which sections are looked at and one of ordinary skill in the art would know to choose which measure to analyze based on their intended purpose.
In re claim 13, Zuckerman Stark discloses wherein computing the combinatorial measures between the plurality of signal measures of the nociception data segments comprises:
performing step one by arbitrarily selecting three signal measures from the plurality of signal measures (fig 3: 310) of the nociception data segments;
performing step two by calculating different orders of power for each of the three signal measures to generate powers of the three signal measures (320: “weights”);
performing step four by performing receiver operating characteristic (ROC) analysis [0164]
Zuckerman Stark lacks:
performing step three by multiplying the powers of the three signal measures together to generate the product of the powers of the three signal measures;
performing step four by performing receiver operating characteristic (ROC) analysis of the product to arrive at a combinatorial measure for the three signal measures; and
repeating steps one, two, three, and four until all of the combinatorial measures have been computed between all of the plurality of signal measures of the nociception data segments.
Al Hatib teaches a monitoring system to detect hypotension by analyzing arterial pressure waveforms [0019]. Different parameters from the arterial waveform can be analyzed [0041]. Each parameter can be assigned a power and multiplied with the other parameters to get a combined parameter [0047]. This can be repeated for each of the measured parameters [0047].
It would be obvious to one of ordinary skill in the art at the time the instant invention was filed to modify the system of Zuckerman Stark by assigning powers to each of the parameters and then multiplying the powers to generate a combined power to be analyzed as taught by Al Hatib, as combining the powers of each parameter would allow the user to see whether the identified changes in the patient’s vital signs were extreme enough to need medication or further observation, as a change in only one parameter may not change the overall power significantly enough to require analgesics to be administered while a change in multiple parameters could cause a significant change in the overall power and tell the medical practitioner to administer medication.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Narasimhan (US 2019/0104953) teaches a finger-wearable blood pressure monitor that has an inflatable cuff to measure blood pressure [0021]. A machine learning algorithm is used to estimate different cardiac parameters (mean arterial pressure, diastolic pressure, systolic pressure) from analyzing a waveform [0024].
O’Donnell et al. (US 2017/0265794) teaches a way to predict when arterial pressure will be at a maximum or minimum [0047] by tracking an arterial volume waveform [0051].
Jian et al. (US 9,968,304) teaches a system for detecting a vasoactive agent is in a patient’s blood stream by analyzing their arterial blood pressure to determine when it changes (abstract). The arterial waveform is broken into multiple segments for analysis and the segments can be compared to each other (col 7, ln 8-24).
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HALEY N. PRUITT whose telephone number is (571)272-1955. The examiner can normally be reached M-T, 7:30 AM -5 PM. F, 7:30-4.
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, David Hamaoui can be reached at (571)270-5625. 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.
/HALEY N PRUITT/Examiner, Art Unit 3796
/DAVID HAMAOUI/SPE, Art Unit 3796
Prosecution Insights