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 .
Response to Arguments
Applicant’s arguments, see pages 6-9, filed 14 July 2026, with respect to the rejection under 35 U.S.C. § 101 have been fully considered and are persuasive. The rejection has been withdrawn.
Applicant's arguments filed 14 July 2026 have been fully considered but they are not persuasive.
For claims 21, 29 and 37, Applicant states the prior art of Dilorenzo does not teach “a wearable monitoring device configured to monitor and record one or more physical properties of a patient and patient feedback input as patient data”. The Examiner disagrees. With respect to Merriam Webster’s and Oxford English dictionary. the term wearable can be broadly defined as capable /ability to bear or have on the person or to carry on the person. Dilorenzo teaches a monitored device carried on the person, and Applicant’s claimed invention does not have a clear and/or specific distinction on what the wearable monitoring device entails within the claim. Thus, in the broadest interpretation allowed Dilorenzo teaches Applicant’s claimed invention of the wearable monitoring device configured to monitor and record one or more physical properties of a patient and patient feedback input as patient data.
Applicant further states that Dilorenzo does not disclose optimizing the medication dosage amount and timing of the medication dosage based on upcoming activities of the patient as recited.
The Examiner disagrees. The claims are broadly written providing three separate options: “wherein the artificial intelligence system is further configured to optimize the medication dosage amount and timing of the medication dosage based on the patient data (1), upcoming activities of the patient (2), or a combination thereof (3). ”.
In the broadest interpretation allowed (MPEP 2111.01), Dilorenzo teaches the intelligence system which is further configured to optimize the medication dosage amount and timing of the medication dosage based on the patient data ([0332][0333][0132] [0112][0114] [0132][0145]). The cited passages can also be interpreted as the upcoming activities ( e.g. upcoming activities (mental functions) is the propensity for a seizure based on neural/sleep states). Therefore, the neural and sleep states can be broadly interpreted as the upcoming activities.
Further, Applicant heavily stresses the intended invention relates to Applicant’s specification Par. [0065]. However, the Examiner cannot import the specification into the claims (See MPEP 2111.01, II. IT IS IMPROPER TO IMPORT CLAIM LIMITATIONS FROM THE SPECIFICATION). When further analyzing the claims with the broadest interpretation allowed, the prior art of Dilorenzo readily teaches Applicant’s invention. The specification is similar to that of DiLorenzo’s Par [0130] as the system recommends certain trends based on the detected state of the user, and DiLorenzo’s Par [0125] having a system communicate to a physician of the patient physiological state and adjustments to medication and therapy. Although some slight distinctions are present, Applicant’s specification cannot be imported into the claims. Thus, Applicant will need to amend the claim language with specificity in order to distinguish their invention from the prior art.
Hence, Applicant's arguments do not comply with 37 CFR 1.111(c) because they do not clearly point out the patentable novelty which he or she thinks the claims present in view of the state of the art disclosed by the references cited or the objections made. Further, they do not show how the amendments avoid such references or objections.
Lastly, Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references.
Claim Rejections - 35 USC § 102
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 21-40 are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Dilorenzo (US 20070287931 A1).
Claim 21. Dilorenzo teaches a system comprising:
a wearable monitoring device configured to monitor and record one or more physical
properties of a patient and patient feedback input as patient data
([0065] System 10 comprises a device assembly 12 that is in communication with one or more patient interface assembly(s) 14, 14'... If patient interface assembly 14 is used for sensing signals from the patient, signal(s) from patient interface assembly 14 are transmitted over a communication link to device assembly 12 where the measured signal(s) are processed in order to determine a patient's propensity for the seizure,
[0076] portions of device assembly 12 may be disposed external to the patient's body and worn on or around the patient's body and coupled to the implanted components. );
an artificial intelligence system configured to receive the patient data from the wearable monitoring device, analyze the patient data to determine patient response to medication dosages
([0095] predictive algorithm 60 itself may have a pre-conditioning component (not shown). In one preferred embodiment, the predictive algorithm 60 comprises feature extractors for brain signals...
[0132] In embodiments where the predictive algorithm is able to provide a weighted answer and provide a greater specificity regarding the pre-ictal state (e.g., the NSI), the output to the patient may also be indicative of a graded response, such as the dosage, form, formulation, and/or route of administration for the pharmacological agents.
[0152] At step 204, the patient's neural state is monitored to ascertain the perturbation (if any) of the patient's neural state caused by the first specified dosage of the pharmacological agent... and the neural state response can be deconvolved with or otherwise analyzed as a response to the drug administration),
and optimize at least one of the medication dosage amount, timing of the medication dosage, or a
combination thereof to be taken by the patient based on the analyzed patient data
([0029] In another specific embodiment, the present invention provides a system that comprises a predictive algorithm that may be used to modify or alter the scheduling and dosing of a chronically prescribed pharmacological agent, such as an AED, to optimize or custom tailor the dosing to a particular patient at a particular point in time. This allows for (1) improved efficacy for individual patients, since there is variation of therapeutic needs among patients, and (2) improved response to variation in therapeutic needs for a given patient with time, resulting from normal physiological variations as well as from external and environmental influences, such as stress, sleep deprivation, the presence of flashing lights, alcohol intake and withdrawal, menstrual cycle, and the like.);
wherein the artificial intelligence system is configured to instruct the patient to administer the optimal medication dosage at the optimal time
([0025]If the predictive algorithm determines that the patient is at an increased or elevated propensity for a future seizure or otherwise predicts the onset of the future seizure, the system may provide an output that recommends or instructs the patient to take an acute dosage of a pharmacological agent (such as an AED) to prevent the occurrence of the seizure or reduce the magnitude or duration of the seizure.)
, and record the medication dosage amount and time the medication dosage is administered by the patient
([0151] For example, certain therapies have a more pronounced effect during specific neural states or ranges thereof; so the timing of therapies may be adjusted to be given during certain neural states and the dosing may be a function of the current, historical, or predicted future neural states.
[0334] The EEG signals are acquired using a standard clinical data acquisition machine at a sampling rate of 400-500 Hz and are transferred offline into one of the research servers for post-hoc analysis. Medications taken, seizures reported or observed and level of awareness are documented during each phase of the study.)
, and wherein the artificial intelligence system is further configured to optimize the medication
dosage amount and timing of the medication dosage based on the patient data, upcoming
activities of the patient, or a combination thereof
([0332] respond to the algorithm's seizure prediction alert and provide an acute dosage of the AED to the patient. [0333] While the acquisition system is recording EEG from the patient, the seizure prediction algorithm simultaneously analyze the dynamical properties of the EEG and the dynamical measures are displayed on an interfaced computer. During the "AED" trial, when the neural state (e.g., dynamical measures T-index of STLmax) indicate that the patient has an elevated propensity for a seizure, a "Warning" sign or "Instruction/recommendation" is displayed on the analysis computer and an AED may be administered by the patient, patient's guardian or kin, or the proper attending medical staff. (e.g. dosage amount and timing, upcoming neural activity)
[0112][0114] awake state to a sleep state... defined thresholds that are indicative of a higher propensity for a future seizure...generate or adjust a magnitude of the therapy (e.g., an electrical stimulation signal or the type or amount of medication delivered).
[0132] Depending on the output from the predictive algorithm, the patient communication assembly may recommend that the patient take a lower than normal dosage (e.g., 1/2 a normal dosage), a normal dosage or a higher than normal dosage (e.g., 2.times. the normal dosage) of a pharmacological agent. For example, if the patient's propensity for a seizure (or probability for a seizure) is low and/or there is a long predicted time horizon before the seizure occurs, depending on the clinician's and patient's preference, the patient communication assembly 18 may be configured to output a recommendation that the patient to take a lower than normal dosage of a pharmacological agent or a milder type of pharmacological agent that has less severe side effects than the patient's primary pharmacological agent(s). (e.g. dosage amount and timing)
[0145] In addition to providing an output to the patient through patient communication assembly 18 that is indicative of the patient's propensity for a future seizure or recommendation regarding the appropriate action, the system 10 of the present invention may be configured to automatically deliver a preventative therapy to the patient. As an initial attempt to prevent a predicted seizure from occurring, the system 10 may automatically deliver an electrical stimulation or other treatment, such as drug infusion, to the patient through an implanted patient interface assembly 14'.
(e.g. upcoming activities (mental functions) of the patient is the propensity of a future seizure based on neural/sleep states)).
Claim 22. Dilorenzo teaches the system of claim 21, wherein the wearable monitoring device comprises at least one sensor selected from the group consisting of activity trackers, smartwatches, smart rings, heart rate monitors, blood pressure monitors, temperature sensors, or combinations thereof
([0019] Some of the physiological signals that may be monitored include, temperature signals from other portions of the body, blood flow measurements in other parts of the body, heart rate signals and/or change in heart rate signals, respiratory rate signals and/or change in respiratory rate signals, chemical concentrations of other medications, pH in the blood or other portions of the body, blood pressure, other vital signs,).
Claim 23 Dilorenzo teaches the system of claim 21, wherein the one or more physical properties comprise at least one property selected from the group consisting of heart rate, blood pressure, sleep
patterns, movement patterns, body temperature, skin resistance, food intake, water intake,
exercise, or combinations thereof
([0019] Some of the physiological signals that may be monitored include, temperature signals from other portions of the body, blood flow measurements in other parts of the body, heart rate signals and/or change in heart rate signals, respiratory rate signals and/or change in respiratory rate signals, chemical concentrations of other medications, pH in the blood or other portions of the body, blood pressure, other vital signs,).
Claim 24. Dilorenzo teaches the system of claim 21, wherein the artificial intelligence system implements at least one artificial intelligence technique selected from predictive learning, machine learning automated planning and scheduling, machine perception, computer vision, or combinations
thereof
([0100] Using any of the accepted classification methods known in the art, the measured feature vector is compared to historical or baseline feature vectors to classify the patient's propensity for a future epileptic seizure. For example, the classifier may comprise a support vector machine classifier, a predictive neural network, artificial intelligence structures, a k-nearest neighbor classifier, or the like.).
Claim 25. Dilorenzo teaches the system of claim 21, further comprising a patient-controlled medication delivery system configured to administer the optimal medication dosage at the optimal time to the patient
([0075] If the patient interface assembly 14 is in the form of a medication dispenser, the medication dispenser will typically be implanted within the patient's body so as to directly infuse therapeutic dosages of one or more pharmacological agents into the patient, and preferably directly into the affected portion(s) of the brain.).
Claim 26. Dilorenzo teaches the system of claim 21, wherein the artificial intelligence system is configured to determine an optimal time for the medication dosage administration based on sleep patterns of the patient
([0112] When the patient is sleeping and the patient's propensity for seizure measurement reaches one or more defined thresholds that are indicative of a higher propensity for a future seizure (which may be the same thresholds or different thresholds from the Awake Idle State 72), the state machine may enter an "Instruct Patient--Sleep Mode" 71, in which a fixed and/or configurable instruction is provided to the patient.).
Claim 27. Dilorenzo teaches the system of claim 21, wherein the upcoming activities comprise at least one activity selected from the group consisting of exercise, sleep, eating, work activities, or
combinations thereof
([0112 in FIG. 8, it may be desirable to change from an Awake State to a Sleep State.).
Claim 28. Dilorenzo teaches the system of claim 21, further comprising a smart alert system configured to alert healthcare providers when the medication dosage optimization parameters exceed
predetermined thresholds
([0127] In certain embodiments, it may be possible to automatically contact the patient's clinician with the device assembly 12 and/or patient communication assembly 18. For example, if a specified threshold is reached, a seizure of sufficient duration has occurred, a sufficient quantity of seizures has occurred, a maximum amount of pharmacological agent has been taken within a predetermined time period, or an undesirable state is reached, the patient communication assembly 18 may initiate a communication link (e.g., a call, email, text message, etc.) to the clinician communication assembly 20 or other remote server.).
Claim 29. Dilorenzo teaches a method comprising:
prescribing a medication to a patient at an initial starting dosage
([0207] An initial daily dose of 250 mg in children and 500 mg in older children and adults is increased by 250 mg increments at weekly intervals until seizures are adequately controlled or toxicity intervenes.);
monitoring one or more physical properties of the patient using a wearable monitoring device
([0065] System 10 comprises a device assembly 12 that is in communication with one or more patient interface assembly(s) 14, 14'... If patient interface assembly 14 is used for sensing signals from the patient, signal(s) from patient interface assembly 14 are transmitted over a communication link to device assembly 12 where the measured signal(s) are processed in order to determine a patient's propensity for the seizure,);
recording as patient data at least one of i) the physical properties monitored with the
wearable monitoring device, ii) patient feedback input, iii) the medication dosage amount, iv)
timing of the medication dosage, or v) combinations thereof
([0151] For example, certain therapies have a more pronounced effect during specific neural states or ranges thereof; so the timing of therapies may be adjusted to be given during certain neural states and the dosing may be a function of the current, historical, or predicted future neural states.
[0334] The EEG signals are acquired using a standard clinical data acquisition machine at a sampling rate of 400-500 Hz and are transferred offline into one of the research servers for post-hoc analysis. Medications taken, seizures reported or observed and level of awareness are documented during each phase of the study.);
analyzing the patient data using an artificial intelligence system to determine patient response to the medication dosage
([0095] predictive algorithm 60 itself may have a pre-conditioning component (not shown). In one preferred embodiment, the predictive algorithm 60 comprises feature extractors for brain signals...
[0132] In embodiments where the predictive algorithm is able to provide a weighted answer and provide a greater specificity regarding the pre-ictal state (e.g., the NSI), the output to the patient may also be indicative of a graded response, such as the dosage, form, formulation, and/or route of administration for the pharmacological agents.
[0152] At step 204, the patient's neural state is monitored to ascertain the perturbation (if any) of the patient's neural state caused by the first specified dosage of the pharmacological agent... and the neural state response can be deconvolved with or otherwise analyzed as a response to the drug administration);
optimizing at least one of the medication dosage amount, timing of the medication dosage, or a combination thereof based on the analyzed patient data as the patient takes additional medication dosages
([0029] In another specific embodiment, the present invention provides a system that comprises a predictive algorithm that may be used to modify or alter the scheduling and dosing of a chronically prescribed pharmacological agent, such as an AED, to optimize or custom tailor the dosing to a particular patient at a particular point in time. This allows for (1) improved efficacy for individual patients, since there is variation of therapeutic needs among patients, and (2) improved response to variation in therapeutic needs for a given patient with time, resulting from normal physiological variations as well as from external and environmental influences, such as stress, sleep deprivation, the presence of flashing lights, alcohol intake and withdrawal, menstrual cycle, and the like.
([0332] respond to the algorithm's seizure prediction alert and provide an acute dosage of the AED to the patient. [0333] While the acquisition system is recording EEG from the patient, the seizure prediction algorithm simultaneously analyze the dynamical properties of the EEG and the dynamical measures are displayed on an interfaced computer. During the "AED" trial, when the neural state (e.g., dynamical measures T-index of STLmax) indicate that the patient has an elevated propensity for a seizure, a "Warning" sign or "Instruction/recommendation" is displayed on the analysis computer and an AED may be administered by the patient, patient's guardian or kin, or the proper attending medical staff.
[0112][0114] awake state to a sleep state... defined thresholds that are indicative of a higher propensity for a future seizure...generate or adjust a magnitude of the therapy (e.g., an electrical stimulation signal or the type or amount of medication delivered).
[0120] Advantageously, the present invention will allow the patient to provide inputs to provide patient feedback into system 10 that may be used by the prediction algorithm 60 (FIG. 7) as a "feature" to improve the characterization of the patient's propensity for the future seizure... input include patient state, such as sleep deprivation, exposure to or "withdrawal" from alcohol or other medications, physiological or emotional stress, presence or absence of antiepileptic drugs (AEDs) or other medications, start of menstrual cycle, or the like.
(e.g. dosage amount and timing, based on the analyzed patient data (feedback))
[0132] Depending on the output from the predictive algorithm, the patient communication assembly may recommend that the patient take a lower than normal dosage (e.g., 1/2 a normal dosage), a normal dosage or a higher than normal dosage (e.g., 2.times. the normal dosage) of a pharmacological agent...the patient communication assembly 18 may be configured to output a recommendation that the patient to take a lower than normal dosage of a pharmacological agent or a milder type of pharmacological agent that has less severe side effects than the patient's primary pharmacological agent(s). (e.g. dosage amount and timing)
[0145] In addition to providing an output to the patient through patient communication assembly 18 that is indicative of the patient's propensity for a future seizure or recommendation regarding the appropriate action, the system 10 of the present invention may be configured to automatically deliver a preventative therapy to the patient. As an initial attempt to prevent a predicted seizure from occurring, the system 10 may automatically deliver an electrical stimulation or other treatment, such as drug infusion, to the patient through an implanted patient interface assembly 14'.
(e.g. upcoming activities (mental functions) of the patient is the propensity of a future seizure based on neural/sleep states)).);
and further optimizing the medication dosage amount and timing based on the patient data,
upcoming activities of the patient, or a combination thereof
([0025]If the predictive algorithm determines that the patient is at an increased or elevated propensity for a future seizure or otherwise predicts the onset of the future seizure, the system may provide an output that recommends or instructs the patient to take an acute dosage of a pharmacological agent (such as an AED) to prevent the occurrence of the seizure or reduce the magnitude or duration of the seizure.
[0029] This allows for (1) improved efficacy for individual patients, since there is variation of therapeutic needs among patients, and (2) improved response to variation in therapeutic needs for a given patient with time, resulting from normal physiological variations as well as from external and environmental influences, such as stress, sleep deprivation, the presence of flashing lights, alcohol intake and withdrawal, menstrual cycle, and the like.).
Claim 30. Dilorenzo teaches the method of claim 29, wherein monitoring the one or more physical properties comprises continuously monitoring the patient during a predetermined time period
following medication administration
([0090] Typically, the raw or pre-processed signal(s) from the patient are monitored during a sliding observation window or epoch. The sliding windows may be monitored continuously, periodically during predetermined intervals, or during an adaptively modified schedule (to customize it to the specific patient's cycles). For example, if it is known that the patient is prone to have a seizure in the morning, the clinician may program system 10 to continuously monitor the patient during the morning hours, while only periodically monitoring the patient during the remainder of the day.).
Claim 31. Dilorenzo teaches the method of claim 29, wherein analyzing the patient data comprises identifying patterns in the patient's physiological response to different dosage amounts and
timing intervals
([0328] Training of the ASPA includes determining (1) the critical electrode groups that show the greatest change between interictal levels and those found during a seizure, and (2) the proper parameters of the algorithm that achieve an acceptable performance for recognizing unique spatiotemporal dynamical pattern for the specific patient. At least 3 seizures should be recorded during this phase to train the ASPA.
[0330] Phase 2: The purpose of this phase of the study is to determine whether taking an acute dosage of a particular AED, during the preictal phase elevates the T-index, which may provide a protective effect against the occurrence of seizures. Phase 2 occurs immediately following, or within one month after, completion of phase 1.
[0230] By titrating the patient's dosage of a pharmacological agent to be a function of the patient's physiological needs, a precise control of the patient's state is possible, which allows a patient to realize a substantially optimal balance between efficacy and side effects.).
Claim 32. Dilorenzo teaches the method of claim 29, wherein optimizing dosage amount comprises adjusting the dosage within predetermined safety parameters
([0168] The systems of the present invention may also have safeguards that monitor the patient's intake of a pharmacological agent. For example, in one embodiment a maximum threshold of medication over a period of time may be set by the clinician, and the maximum threshold may be saved in a memory of system 10.).
Claim 33. Dilorenzo teaches the method of claim 29, wherein optimizing timing comprises determining an optimal time for medication administration based on the patient's sleep cycle
([0112] When the patient is sleeping and the patient's propensity for seizure measurement reaches one or more defined thresholds that are indicative of a higher propensity for a future seizure (which may be the same thresholds or different thresholds from the Awake Idle State 72), the state machine may enter an "Instruct Patient--Sleep Mode" 71, in which a fixed and/or configurable instruction is provided to the patient.).
Claim 34. Dilorenzo teaches the method of claim 29, further comprising generating alerts to healthcare providers when the optimized dosage parameters indicate potential adverse reactions
[0162] The patient's reaction to the pharmacological agents may change over time. Consequently, during regular checkups or through periodic uploading of the patient's neural state information, drug compliance data, seizure prediction data uploads to the clinician, the clinician may be able to monitor the perturbation effect of the pharmacological agents on the patient's neural state. If the clinician (or the system 10 itself) determines that the programmed pharmacological agent is not achieving the desired result, the clinician will have the ability to prescribe a different pharmacological agent, dosing regimen, or dosage and reprogram the device assembly 12.
[0168][0169] system 10 may be configured to provide a warning to the patient to indicate that the maximum amount of medication is being reached...It may be possible to configure system 10 so that when the amount of medication taken approaches the maximum, a signal may be sent to a server that the clinician may access or directly to a clinician communication assembly 20 that is in communication with system 10 that warns the clinician of the patient's status. ).
Claim 35. Dilorenzo teaches the method of claim 29, wherein the upcoming activities are determined based on data from at least one of the wearable monitoring device, patient input, or a combination thereof
([0025]If the predictive algorithm determines that the patient is at an increased or elevated propensity for a future seizure or otherwise predicts the onset of the future seizure, the system may provide an output that recommends or instructs the patient to take an acute dosage of a pharmacological agent (such as an AED) to prevent the occurrence of the seizure or reduce the magnitude or duration of the seizure.).
Claim 36. Dilorenzo teaches the method of claim 29, further comprising comparing the patient data to data from a population of patients with similar characteristics to enhance optimization accuracy
([0325] FIG. 19 shows a seizure pattern observed in a rodent with chronic limbic epilepsy undergoing continuous EEG monitoring with automated seizure warning in place...Acute dosages of AEDs can be analyzed for similar effects on T-Index in various patient sub-populations.).
Claim 37. Dilorenzo teaches a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to:
receive patient data from a wearable monitoring device, wherein the patient data includes at least one of monitored physical properties of a patient, patient feedback input, or combinations thereof
([0065] System 10 comprises a device assembly 12 that is in communication with one or more patient interface assembly(s) 14, 14'... If patient interface assembly 14 is used for sensing signals from the patient, signal(s) from patient interface assembly 14 are transmitted over a communication link to device assembly 12 where the measured signal(s) are processed in order to determine a patient's propensity for the seizure,);
receive medication dosage amount and medication dosage timing information
([0151] For example, certain therapies have a more pronounced effect during specific neural states or ranges thereof; so the timing of therapies may be adjusted to be given during certain neural states and the dosing may be a function of the current, historical, or predicted future neural states.
[0334] The EEG signals are acquired using a standard clinical data acquisition machine at a sampling rate of 400-500 Hz and are transferred offline into one of the research servers for post-hoc analysis. Medications taken, seizures reported or observed and level of awareness are documented during each phase of the study.);
analyze the patient data to determine patient response to the medication dosage
([0151] For example, certain therapies have a more pronounced effect during specific neural states or ranges thereof; so the timing of therapies may be adjusted to be given during certain neural states and the dosing may be a function of the current, historical, or predicted future neural states.
[0152] At step 204, the patient's neural state is monitored to ascertain the perturbation (if any) of the patient's neural state caused by the first specified dosage of the pharmacological agent... and the neural state response can be deconvolved with or otherwise analyzed as a response to the drug administration );
optimize at least of the medication dosage amount, medication dosage timing, or combination thereof to be taken by the patient based on the analyzed patient data
([0029] In another specific embodiment, the present invention provides a system that comprises a predictive algorithm that may be used to modify or alter the scheduling and dosing of a chronically prescribed pharmacological agent, such as an AED, to optimize or custom tailor the dosing to a particular patient at a particular point in time. This allows for (1) improved efficacy for individual patients, since there is variation of therapeutic needs among patients, and (2) improved response to variation in therapeutic needs for a given patient with time, resulting from normal physiological variations as well as from external and environmental influences, such as stress, sleep deprivation, the presence of flashing lights, alcohol intake and withdrawal, menstrual cycle, and the like.
([0332] respond to the algorithm's seizure prediction alert and provide an acute dosage of the AED to the patient. [0333] While the acquisition system is recording EEG from the patient, the seizure prediction algorithm simultaneously analyze the dynamical properties of the EEG and the dynamical measures are displayed on an interfaced computer. During the "AED" trial, when the neural state (e.g., dynamical measures T-index of STLmax) indicate that the patient has an elevated propensity for a seizure, a "Warning" sign or "Instruction/recommendation" is displayed on the analysis computer and an AED may be administered by the patient, patient's guardian or kin, or the proper attending medical staff.
[0120] Advantageously, the present invention will allow the patient to provide inputs to provide patient feedback into system 10 that may be used by the prediction algorithm 60 (FIG. 7) as a "feature" to improve the characterization of the patient's propensity for the future seizure... input include patient state, such as sleep deprivation, exposure to or "withdrawal" from alcohol or other medications, physiological or emotional stress, presence or absence of antiepileptic drugs (AEDs) or other medications, start of menstrual cycle, or the like.
(e.g. dosage amount and timing, upcoming activity is the propensity for a seizure based on the analyzed patient data (feedback))
[0132] Depending on the output from the predictive algorithm, the patient communication assembly may recommend that the patient take a lower than normal dosage (e.g., 1/2 a normal dosage), a normal dosage or a higher than normal dosage (e.g., 2.times. the normal dosage) of a pharmacological agent. For example, if the patient's propensity for a seizure (or probability for a seizure) is low and/or there is a long predicted time horizon before the seizure occurs, depending on the clinician's and patient's preference, the patient communication assembly 18 may be configured to output a recommendation that the patient to take a lower than normal dosage of a pharmacological agent or a milder type of pharmacological agent that has less severe side effects than the patient's primary pharmacological agent(s). (e.g. dosage amount and timing)
[0145] In addition to providing an output to the patient through patient communication assembly 18 that is indicative of the patient's propensity for a future seizure or recommendation regarding the appropriate action, the system 10 of the present invention may be configured to automatically deliver a preventative therapy to the patient. As an initial attempt to prevent a predicted seizure from occurring, the system 10 may automatically deliver an electrical stimulation or other treatment, such as drug infusion, to the patient through an implanted patient interface assembly 14'. (e.g. upcoming
activities (mental functions) of the patient is the propensity of a future seizure based on neural/sleep states)).);
and further optimize the medication dosage amount and medication dosage timing based on the patient data, upcoming activities of the patient, or a combination thereof
([0025]If the predictive algorithm determines that the patient is at an increased or elevated propensity for a future seizure or otherwise predicts the onset of the future seizure, the system may provide an output that recommends or instructs the patient to take an acute dosage of a pharmacological agent (such as an AED) to prevent the occurrence of the seizure or reduce the magnitude or duration of the seizure.
[0120] Advantageously, the present invention will allow the patient to provide inputs to provide patient feedback into system 10 that may be used by the prediction algorithm 60 (FIG. 7) as a "feature" to improve the characterization of the patient's propensity for the future seizure... input include patient state, such as sleep deprivation, exposure to or "withdrawal" from alcohol or other medications, physiological or emotional stress, presence or absence of antiepileptic drugs (AEDs) or other medications, start of menstrual cycle, or the like.
(e.g. dosage amount and timing, upcoming activity is the propensity for a seizure based on the analyzed patient data (further feedback)).
Claim 38. Dilorenzo teaches the non-transitory computer-readable medium of claim 37, wherein the instructions further cause the processor to implement machine learning algorithms to continuously improve the medication dosage optimization based on the accumulated patient data
([0163] For example, it may be possible to monitor the neural state response to medications used in the treatment of other neurological disorders and improve the medication/pharmacological agent regimen by monitoring the responsiveness to different dosages of the pharmacological agent.
[0029] This allows for (1) improved efficacy for individual patients, since there is variation of therapeutic needs among patients, and (2) improved response to variation in therapeutic needs for a given patient with time, resulting from normal physiological variations as well as from external and environmental influences, such as stress, sleep deprivation,..).
Claim 39. Dilorenzo teaches the non-transitory computer-readable medium of claim 37, wherein the instructions further cause the processor to generate predictive alerts when the patient data
indicates potential medication effectiveness issues
([0140] FIG. 14 illustrates an embodiment which is configured to provide a variety of different alert levels 120. Generally, the alert levels are based at least in part on the measured propensity for seizure or other output provided by the predictive algorithm... system 10 may be configured to provide for a variety of different "alert levels" that correspond to different propensities for seizure. The patient communication assembly 18 will be capable of producing outputs that correspond to the alert levels).
Claim 40. Dilorenzo teaches the non-transitory computer-readable medium of claim 37, wherein the instructions further cause the processor to integrate patient sleep pattern data to determine optimal medication dosage timing that minimizes sleep disruption
([0090] . Similarly, it may be less desirable to monitor a patient and provide an output to a patient when the patient is asleep. In such cases, the system 10 may be programmed to discontinue monitoring or change the monitoring and communication protocol with the patient during a predetermined "sleep time" or whenever a patient inputs into the system that the patient is asleep (or when the system 10 determines that the patient is asleep). ).
Conclusion
THIS ACTION IS MADE FINAL. 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RUFUS C POINT whose telephone number is (571)270-7510. The examiner can normally be reached 9am-5pm.
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, Davetta Goins can be reached at 571-272-2957. 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.
/RUFUS C POINT/Primary Examiner, Art Unit 2689
Prosecution Insights