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 .
Information Disclosure:
The information disclosure statements (IDS) submitted on 06/22/2026 is in accordance with the provisions of 37 CFR 1.97 and are considered by the Examiner.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 06/22/2026 has been entered.
Response to Applicant Arguments
Applicant’s arguments filed on June 22, 2026, at remarks pages 7-11 regarding Subject Matter Eligibility under 35 U.S.C 101, have been considered but are not persuasive for at least the reasons set forth below.
Applicant argues that amended claims 1, 14, and 20 do not recite an abstract idea under Step 2A Prong One because they recite processing image data captured by a plurality of cameras and using artificial intelligence models to identify types of physical contact between the patient and other persons, which applicant contends is not a step that can practically be performed in the human mind.
Examiner respectfully disagrees. Step 2A, Prong One determines only whether the claims recite a judicial exception; it does not evaluate the technological significance of the additional elements. Under the broadest reasonable interpretation, the claims recite the abstract idea of evaluating patient-interaction and physiological information to determine post-operative risk, compare the result to a threshold, and decide a responsive alert, recommendation, and care plan. The recited camera system, image data, and artificial intelligence models are additional elements and are evaluated separately under Step 2A, Prong Two and Step 2B to determine whether they integrate the judicial exception into a practical application or provide significantly more. See the rejection below for the detailed eligibility analysis of those additional elements.
Applicant argues that the amendments integrate any exception into a practical application because the claims now specify a particular function performed by the AI: analyzing image data to identify types of physical contact, which applicant characterizes as a defined computer vision task that imposes a specific and meaningful technical limit on how the Al operates.
Examiner respectfully disagrees that naming the classification target supplies a particular technical solution. Integration depends on the extent to which the claim covers a particular way to achieve a desired outcome, as opposed to merely claiming the idea of a solution or outcome. The amendment states what the models identify, not how the identification is performed: the claims recite no model architecture, training technique, feature extraction, image-processing pipeline, or multi-camera coordination mechanism. The specification describes the models at the same functional level, utilizing one or more artificial intelligence models to generate system outputs and a machine learning algorithm can be trained using input data 400 collected from a large number of patients (Spec., para. 0040). Under Analytics, Inc. v. Fox Corp., 134 F.4th 1205 (Fed. Cir. 2025), applying machine learning recited at that level of generality to automate an evaluation does not confer eligibility.
Applicant argues that the Office Action evaluated the additional elements separately and in isolation and that, as an ordered combination, the claims recite multi-modal data fusion with AI-driven contact-type classification constituting a particular technological solution to identifying post-operative patient risks in real time.
Examiner respectfully disagrees that the ordered combination integrates the exception. The rejection below evaluates the combination as arranged: the monitoring devices and cameras collect physiological and image data, the functionally recited models analyze that data, the score is compared to a threshold, and the results are presented as an alert, a recommendation, and a customized care plan. Each output is information for caregiver use. The claims end at presenting and recording the analysis, not at administering a treatment, controlling a device, or improving any recited component. Under MPEP 2106.04(d)(2) and 2106.05(e), and the claim that stops at identifying or recommending a clinical response does not integrate the exception, while a claim that carries out a specific treatment does. The amended claims stop at the recommendation and the plan.
Applicant argues that the specification describes a technical monitoring system, not merely a clinical decision rule, including real-time updating of outputs and plural cameras positioned throughout the clinical care environment.
Examiner respectfully disagrees that the specification discloses a technological improvement that the claims reflect. A disclosed improvement to computer functionality or another technology and claim language must be reflecting that improvement. The advantages the specification asserts are clinical and administrative: improving the prediction of which patients are susceptible, allowing caregivers to properly allocate resources, implement early intervention strategies, and create customized care plans that address specific patient risk factors (Spec., para. 0029). Those are improvements to the evaluation itself, not to camera operation, model operation, or computer functionality. The specification describes the camera system as video cameras, surveillance cameras, etc. (Spec., para. 0036) and the real-time behavior as continuously monitoring input data (Spec., para. 0028), which is continuous performance of the same analysis rather than a change in how any technology works.
Applicant argues that under Step 2B the record does not establish that using AI to classify types of physical contact from multi-camera image data, together with the score calculation and care-plan generation, was well-understood, routine, and conventional, and that the cited prior art confirms the rejection rests on general monitoring and alerting functions.
Examiner respectfully disagrees that Step 2B turns on whether the prior art discloses the claimed combination; that inquiry belongs to 35 U.S.C. 102 and 103. Step 2B asks whether the claims add, beyond the identified exception, additional elements that amount to significantly more. The contact-type identification, the score calculation, the threshold comparison, and the care-plan logic are the exception itself and cannot supply their own inventive concept. The WURC evidence is relied on only for the monitoring devices and camera system as data-acquisition tools supplying physiological and image data. The processor, memory, storage medium, and GUI control add computer execution, display, and approval-input handling at a high level of generality. The AI models are not relied on as WURC; they are recited only by analytical result, without model architecture, training method, feature-extraction technique, or image-processing improvement.
Applicant argues that the close-call standard applies and that the preponderance of the evidence does not support a finding of ineligibility.
Examiner respectfully disagrees that this record presents a close call. The claim language separates the abstract risk-evaluation logic from the additional elements: the score calculation, contact-type identification, threshold comparison, alert, recommendation, and care-plan logic are the identified exception. The remaining elements are recited at a functional level as devices that collect data, execute the analysis, and display or receive approval input. The specification likewise describes cameras, monitoring devices, computing components, and AI models as tools for obtaining and analyzing patient-environment data, not as improved technical mechanisms. Because the claim and specification support the Step 2B finding by a preponderance of the evidence, the § 101 rejection is maintained.
Applicant argues that dependent claims 3 and 5 reinforce integration because they tie the risk score and recommendation to concrete patient-environment operations, and that claims 14 and 20 are eligible for at least the same reasons as claim 1.
Examiner respectfully disagrees that these claims change the outcome. Claim 3 recites that the at least one recommendation includes turning the patient, which defines the content of the recommendation; the claim performs no turning step, unlike the administered treatment that integrates the exception. Claim 5 recites automatically implement the at least one recommendation when the selection of the control approving the at least one recommendation is received, but recites no device-control mechanism or machine operation by which implementation occurs, which is follow-on execution and input handling under MPEP 2106.05(g). Claims 14 and 20 mirror claim 1 and change only the statutory category, so they fall with claim 1.
Applicant’s arguments filed on June 22, 2026, at remarks pages 11-15 regarding 35 U.S.C 103, have been considered but are not persuasive for at least the reasons set forth below.
Applicant argues that claim 1, utilizing one or more artificial intelligence models to analyze the image data captured by the camera system to identify types of physical contact is not disclosed or suggested by Terry or Derenne.
Examiner respectfully disagrees that the amended limitation is absent from the combination. Under MPEP 2141 and 2143, obviousness may rely on Terry for the risk-scoring AI framework and Derenne for the missing visual contact-activity recognition, with an articulated reason to combine. Terry teaches AI/ML risk analysis because the analytics engine uses artificial intelligence (AI) and machine learning to analyze risk-factor data and determine correlations to risks such as pressure injuries, falls, and sepsis (Terry, col. 46, ll. 45-61). Terry does not expressly identify contact types from camera images. Derenne supplies that gap because camera/depth data showing caregiver and patient movement is compared to stored sequential behaviors and tagged as a specific behavior or task, including turning a patient and dressing a wound (Derenne, pars. 0071-0072). A POSITA would add Derenne’s visual task-recognition input to Terry’s AI risk engine to distinguish care-contact events (turning a patient, dressing a wound, conducting a patient assessment, providing physical or respiratory therapy, starting a ventilator, and applying CPR) that Terry’s RTLS presence data cannot classify.
Applicant argues that claim 1, creating a customized care plan that addresses specific patient risk factors that contributed to the post-operative score exceeding the threshold value, is not taught or suggested by Terry and Derenne because Terry provides threshold-triggered alerts or protocol actions and Derenne provides monitoring alerts, not risk-factor-specific care-plan generation.
The argument is moot as to the prior Terry-Derenne rejection because the current rejection no longer relies on Terry and Derenne alone for the amended care-plan limitation. The updated rejection acknowledges that Terry and Derenne do not expressly disclose creating the claimed customized care plan upon approval of the recommendation, and instead relies on Vesto for that missing care-plan layer. Refer to below rejections for more details.
Applicant argues that the stated motivation to combine Terry and Derenne is insufficient because it only supports adding visual fall-behavior data to Terry’s risk analytics, not programming AI to identify types of physical contact or replacing Terry’s protocol outputs with a customized care plan tied to causative risk factors.
The argument is moot to the extent it attacks the former Terry-Derenne rationale, because the current rejection is not limited to that two-reference theory refer to below 35 U.S.C 103 submitted.
Applicant argues that independent claims 1, 14, and 20, and dependent claims 4, 8, and 12, are patentable because Terry and Derenne do not disclose the amended limitations, and Wallace does not cure the alleged deficiencies inherited through claim 1.
The argument is moot as to the prior Terry-Derenne and Terry-Derenne-Wallace rejections because the current rejection is not maintained on the same two-reference theory Applicant addresses refer to below 35 U.S.C 103 submitted.
Claim Rejections - 35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 1-8 and 10-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Independent claims 1, 14, and 20 recite: AI to identify types of physical contact between the patient and the other persons from camera image data.
The specification supports camera-based posture, movement, and interaction monitoring, including paragraphs [0061]-[0063] and [0069] broadly describe monitoring patient interactions with caregivers by analyzing the camera system, but provide no specifics about how any type of image analysis is performed, let alone the specific step of “identifying types of physical contact between the patient and other persons” in image data from the camera system.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-8 and 10-20 are rejected under 35 U.S.C. 101 because the claimed subject matter is directed to a judicial exception without reciting elements that integrate the exception into a practical application or provide an inventive concept amounting to significantly more than the exception itself.
Step 1
Step 1 asks whether each pending claim falls within one of the four statutory.
Claims 14-19 recite a method for improving a prediction of post-operative infection and pressure injuries and fall within the process category. Claims 1-8 and 10-13 recite a system comprising at least one processing device and fall within the machine category. Claim 20 recites a non-transitory computer readable storage medium and falls within the manufacture category.
Step 1 is satisfied for all pending claims. The analysis proceeds to Step 2A, Prong One.
Prong One
Prong One asks whether the claim language recites a judicial exception.
Independent Claims Analysis:
Note: Non-bold claim language identifies the judicial exception; bold claim language identifies the additional elements evaluated at Prong Two and Step 2B.
(1) A system for improving a prediction of post-operative patient risks within a patient environment, the system comprising: at least one processing device; and a memory device storing instructions which, when executed by the at least one processing device, cause the at least one processing device to:
(2) receive physiological data of a patient from one or more monitoring devices;
(3) receive image data of the patient from a camera system including a plurality of cameras positioned within the patient environment, wherein the camera system captures the image data showing patient movements and caregiver interactions with the patient;
(4) calculate a post-operative score based on the physiological data received from the one or more monitoring devices and the image data captured by the camera system, wherein the post-operative score is at least partially calculated by monitoring interactions between the patient and other persons by utilizing one or more artificial intelligence models to analyze the image data captured by the camera system to identify types of physical contact between the patient and the other persons;
(5) issue an alert when the post-operative score exceeds a threshold value;
(6) generate at least one recommendation for improving the post-operative score; and
(7) present a control on a graphical user interface for viewing the post-operative score or the at least one recommendation, and wherein, upon selection of the control approving the at least one recommendation, causing the at least one processing device to create a customized care plan that addresses specific patient risk factors that contributed to the post-operative score exceeding the threshold value.
Claims 1, 14, and 20 are grouped because recite the same abstract idea for the purpose of this analysis
Under BRI, the non-bold language collects patient physiological and observational information, identifies types of physical contact between the patient and other persons, evaluates that information to produce a post-operative score, compares the score to a threshold, and decides an alert, a recommendation, and a customized care plan addressing contributing risk factors.
Limitations 2 through 5 recite observation, evaluation, comparison, and judgment performed on collected patient information: the claims receive physiological data and image content showing patient movements and caregiver interactions, calculate a post-operative score at least partially by monitoring interactions between the patient and other persons to identify types of physical contact, and issue an alert when the post-operative score exceeds a threshold value. These limitations set forth, and do not merely involve, a mental process under MPEP 2106.04(a)(2)(III), because the identification is recited at the level of its result and remains practically performable by a person observing the patient environment; no image-processing operation is recited in the non-bold language. Limitations 6 and 7 recite generate at least one recommendation and create a customized care plan that addresses specific patient risk factors, which additionally set forth a certain method of organizing human activity in the sub-group of managing personal behavior or relationships or interactions between people, because the recommendation and plan direct caregiver conduct within the clinical environment (Spec., para. 0029). Both groupings are identified on the record and treated as a single combined abstract idea per MPEP 2106.04(II).
An infection-control nurse practically mirrors the non-bold language with mental effort, pen, and paper: the nurse reads the patient's vital signs from the bedside chart, watches the patient and each person who touches the patient, notes the type of each contact, weighs those observations to score post-operative risk, compares the score against a threshold drawn from experience, alerts the charge nurse when the threshold is exceeded, recommends a response, and writes a care plan listing the specific risk factors that raised the score.
Dependent Claims Analysis:
Claims 3, 4, 7, 8, 11, 12, and 19 recite narrowing of the information evaluated and the scores produced, including pressure injury risk, infection risk, time on a surgical table, quantity of caregivers, patient movements, electronic health records, and adverse event data, which fits the mental processes grouping because narrowing what is evaluated leaves observation, evaluation, and judgment. Claims 6, 13, 17, and 18 recite care-status assignment, caregiver reassignment, patient relocation, and workload-based reassignment, which fits certain methods of organizing human activity, managing personal behavior or relationships or interactions between people, because these limitations direct caregiver workflow. Claims 5, 15, and 16 recite approval-driven implementation and a turning recommendation, which remain the same evaluative and workflow content; the automatic implementation function of claims 5 and 15 is an additional element addressed below. Claims 2 and 10 add device environments that are additional elements addressed below and otherwise inherit the abstract idea of claim 1.
Claims 1-8 and 10-20 recite the combined abstract idea. The analysis proceeds to Prong Two.
Prong Two
Prong Two asks whether the additional elements, individually and in combination, integrate the recited exception into a practical application.
Independent Claims Analysis:
The additional elements are at least one processing device and a memory device storing instructions (in claim 20, a computing device and a non-transitory computer readable storage medium), one or more monitoring devices, a camera system including a plurality of cameras positioned within the patient environment, one or more artificial intelligence models, and a control on a graphical user interface.
Individual Additional Elements Evaluation:
The processing device, memory, computing device, and storage medium do not integrate the exception because MPEP 2106.05(f) explains that merely using a computer as a tool to perform an abstract idea does not impose a meaningful limit, and the claims recite these elements only as the platform that executes the receiving, calculating, alerting, recommending, and plan-creating functions without any recited processor architecture, memory arrangement, or computing technique.
The monitoring devices and camera system do not integrate the exception because MPEP 2106.05(b) requires a machine that imposes a meaningful limit beyond supplying data and MPEP 2106.05(g) treats mere data gathering as insignificant extra-solution activity; the claims recite where the cameras sit, positioned within the patient environment, and what the images show, patient movements and caregiver interactions with the patient, but no sensing technique, camera control method, or image-processing mechanism, and the specification describes the camera system as video cameras, surveillance cameras, etc. (Spec., para. 0036).
The artificial intelligence models do not integrate the exception because MPEP 2106.05(a) requires the claim to reflect an improvement in computer functionality or another technology, and the claims recite the models by their analytical target, to analyze the image data captured by the camera system to identify types of physical contact, not by any mechanism. The specification asserts clinical and administrative advantages, improving the prediction, resource allocation, early intervention, and customized care plans (Spec., para. 0029), and describes the models only as trainable analytical tools (Spec., para. 0040); no improvement to model operation, camera operation, or computer functionality is disclosed, and the claims reflect none.
The graphical user interface control does not integrate the exception because presenting the score and recommendation and receiving the approval selection are post-solution display and input handling under MPEP 2106.05(g), and the resulting customized care plan is an informational output rather than a particular treatment or device control step.
Combination Additional Elements Evaluation:
As an ordered combination, the elements collect physiological and image data, analyze it with functionally recited models, and present the score, alert, recommendation, and care plan for caregiver action. That arrangement uses the exception in a clinical computing environment; it does not integrate it.
Dependent Claims Analysis:
Claims 3, 4, 6, 7, 8, 11, 12, 13, 16, 17, 18, and 19 add no additional elements beyond those of the independent claims; they narrow the abstract idea and are referred to Prong One. Claims 2 and 10 recite one or more medical devices connected to a network, including at least one of a patient bed, a spot monitor, a contact-free continuous monitoring device, and an infusion pump, and communications devices that include a smartphone or a tablet computer, which do not overcome Prong Two because they are further data sources and monitoring tools with no recited improvement in how any device operates (MPEP 2106.05(b), (g)). Claims 5 and 15 recite automatically implement the at least one recommendation when the selection of the control approving the at least one recommendation is received, which does not overcome Prong Two because no control mechanism or device operation is recited by which implementation occurs (MPEP 2106.05(g)).
The additional elements, alone and as an ordered combination, do not integrate the recited abstract idea into a practical application. The analysis proceeds to Step 2B.
Step 2B
Step 2B asks whether the additional elements, individually and as an ordered combination, amount to significantly more than the exception per MPEP 2106.05.
Independent Claims Analysis:
The elements evaluated are the same identified at Prong Two: the processing device, memory, computing device and storage medium, monitoring devices, camera system, artificial intelligence models, and graphical user interface control.
Individual Additional Elements Evaluation:
The processing device, memory, computing device, and storage medium execute the recited functions as the computing platform, which adds only the instruction to perform the evaluation on a computer (MPEP 2106.05(f)).
The monitoring devices and camera system supply the data evaluated, which is data gathering that does not add significantly more (MPEP 2106.05(g)); the specification lists them among the clinical care environment systems that provide input data (Spec., paras. 0018, 0036). The WURC record is further supported by TLI Communications, 823 F.3d 607, 614-15, where the camera-phone component added no inventive concept because the image pickup unit operates as a digital photo camera of the type which is known and merely captured/transmitted image data. The same input-source function was prevalent in pre-filing clinical monitoring systems. Derenne paragraph [0038] describes one or more conventional video cameras used in a patient-care environment to gather patient-room information for alerts. Terry paragraphs [0005] and [0013] describe a plurality of equipment providing patient data to an analytics engine, including a physiological monitor with EKG, respiration, blood-pressure, pulse-oximetry, and temperature monitoring. Etleb paragraphs [0061] and [0076]-[0077] describe currently available technologies for pressure-injury prevention and sensor outputs from pressure, temperature, and wetness sensors analyzed by software for notifications. These sources support that the claimed monitoring devices and camera system, as recited only to provide physiological and image data, were WURC data-acquisition tools rather than an inventive concept
The artificial intelligence models are recited as the tool that performs the evaluation, utilizing one or more artificial intelligence models to analyze the image data captured by the camera system to identify types of physical contact, and the specification describes them at the same functional level, a machine learning algorithm can be trained using input data 400 collected from a large number of patients (Spec., para. 0040); a tool recited by its analytical assignment does not supply an inventive concept (MPEP 2106.05(f)).
The graphical user interface control presents outputs and receives the approval selection, and the specification confirms the control allows a caregiver C to view the post-operative score(s) and implement the recommendation (Spec., para. 0018), which is display and input handling (MPEP 2106.05(g)).
Combination Additional Elements Evaluation:
As an ordered combination, the platform executes the evaluation, the devices and cameras feed it, the models perform it, and the interface displays the results and records the approval that generates the care plan. The ordered combination automates the clinical evaluation and caregiver workflow with the recited components serving the same roles evaluated individually; it adds no element, arrangement, or ordering beyond performing the exception with those components, and therefore does not supply an inventive concept (MPEP 2106.05(f) and (g)).
Dependent Claims Analysis:
Claims 3, 4, 6, 7, 8, 11, 12, 13, 16, 17, 18, and 19 add no additional elements and are referred to Prong One. Claims 2 and 10 recite networked medical devices and communications devices that serve as further input sources in the same evaluated roles, so they do not overcome Step 2B. Claims 5 and 15 recite automatically implement the at least one recommendation, which remains follow-on execution of the approved recommendation with no recited implementing mechanism, so they do not overcome Step 2B.
The amendments do not overcome the 35 U.S.C. 101 rejection. Claims 1-8 and 10-20 remain directed to the combined abstract idea without integration into a practical application and without an inventive concept, and the rejection under 35 U.S.C. 101 is maintained as applied to the amended claims.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 5-7, 10-11, and 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over Terry (US 11504071) in view of Derenne (US 20120075464 A1), and further in view of Vesto (US20130290005A1).
Claim 1.
Terry teaches,
A system for improving a prediction of post-operative patient risks within a patient environment, the system comprising: (Terry, Col. 1, ll.10-35, Col. 1, ll.40-67, Col.18, ll. 54- 67, Col. 3, ll. 48-55)
at least one processing device; (Terry, fig. 2- fig. 3, fig. 6, col.1,ll.45-67)Terry discloses an analytics engine and computing devices that perform patient-risk.
and a memory device storing instructions which, when executed by the at least one processing device, cause the at least one processing device to: (Terry, fig. 2- fig. 3, fig. 6)
receive physiological data of a patient from one or more monitoring devices; (Terry, fig. 2- fig. 3, fig. 6, … data from the physiological monitor may include one or more of the following: heart rate data, electrocardiograph (EKG) data … Col. 3, ll. 6-15;)
receive image data of the patient from a camera system ; (Terry, ...a photo… with a camera...WOUNDVUE..camera...Col. 17, ll. 50-55; …fundus imaging system…col. 56, ll. 5-15; …nurse enters the room as indicated… the PSA receives…locating…caregiver is in the room…Col. 30. ll.39-50; Col. 29, ll. 40-60…receives patient movement data…;, … include an image of the at least one wound… Col. 5, ll. 18-26, … fundus imaging system…Col. 56, ll. 5 - 31)
calculate a post-operative score based on the physiological data received from the one or more monitoring devices (Terry, abstract, fig. 2- fig. 3, fig. 4B, fig. 6, Col. 1, ll.10-35, Col. 1, ll.40-67, Col.18, ll. 54- 67, Col.22, ll. 31 -55, Col. 16, ll 25-40, has surgery, and during or after surgery the patient’s vitals are measured and sepsis screening is performed Col. 26, ll. 50-67, col. 31, ll. 1-25 “the PSA receives information from the locating system that the caregiver is in the room” Col.30, ll. 51-67; “the analytics engine 20 receives patient movement data as monitored by load cells of bed 14” Col.50, ll.50-60; col. 29, ll. 7-14, 40-67, figure 5A/5B)
Terry's system monitors caregivers (other persons) using tags to track their presence in patient rooms, thus monitoring interactions. This location data is sent to an analytics engine 20, which processes it to perform risk assessments, demonstrating how interaction data is used in calculation.
by utilizing one or more artificial intelligence models to analyze ; (Col. 46, ll.45-61)
Terry describes calculating a risk score using AI models applied to monitoring device data
issue an alert when the post-operative score exceeds a threshold value; (Terry, fig. 2, Col. 20, ll.10-67)
Terry’s system uses sensor and caregiver-location data to calculate a risk score and, if it gets too high, alerts staff and recommends or automatically starts fixes like turning the patient or activating a pressure-relief mattress.
generate at least one recommendation for improving the post-operative score; (Terry, fig. 2, Col. 20, ll.10-67)
Terry expressly states that the “analytics engine 20 initiates one or more alerts to one or more caregivers,” and explains those alerts may include messages or automatic interventions (e.g., activate alternating-pressure mattress or initiate rounding), which directly maps to the claim limitation to “generate at least one recommendation for improving the post-operative score.”
and present a control on a graphical user interface for viewing the post-operative score or the at least one recommendation. (Terry, fig. 2, Col. 20, ll.10-67, Col. 2, ll. 1 -25)
Terry discloses risk scores and recommendations shown on multiple graphical displays and sent to caregiver mobile devices, which supports the claim that a GUI control is presented for viewing the post-operative score or recommendation.
Terry discloses the majority of the limitations, however, does not describe the strikethrough parts above.
Derenne teaches the missing visual-monitoring structure and contact-activity recognition. Derenne discloses one or more video cameras positioned in a patient room, including three video cameras 22 positioned within a single room 28, with images processed to monitor patients, caregivers, equipment, patient activity, protocol compliance, infection control, and fall prevention. Derenne further detects clinician identity and clinician actions, including turning a patient, dressing a wound, conducting a patient assessment, providing physical or respiratory therapy, starting a ventilator, and applying CPR. Derenne also processes camera/depth data to identify patient body position, patient movement, and caregiver conduct such as approaching or touching a patient. These disclosed clinical tasks are distinct caregiver-patient contact activities and would have provided the known visual categories for classifying types of physical contact.
A POSITA would have combined Terry with Derenne by using Derenne’s multi-camera patient-room image/depth data as an additional input to Terry’s AI risk analytics engine. Terry’s scores already depend on patient risk factors and care events, including pressure-injury and fall-related conditions, while Derenne supplies visual verification of patient movement and caregiver tasks that Terry’s physiological monitors and RTLS presence data do not fully observe. The combination would have predictably allowed Terry’s AI/ML engine to analyze Derenne’s camera images to classify care-contact activities, such as turning, wound dressing, therapy, and CPR, and use those classified interactions in calculating the patient risk score. The modification applies Derenne’s known video activity-recognition technique to Terry’s known risk-scoring engine for the expected benefit of more complete and accurate patient-risk assessment. References: Terry, Abstract, col. 31, ll. 1-25, col. 46, ll. 53-61; Derenne, pars. 0003-0005, 0040-0048, 0061-0064, 0068-0072, 0076, 0100.
Terry and Derenne do not expressly disclose, that selection of a control approving the recommendation creates a customized care plan addressing the specific patient risk factors that contributed to the score exceeding the threshold.
Vesto teaches that missing care-plan layer because [0057] discloses a GUI care-planning interface where the user can review, modify, approve a plan generated from risk mitigation, Scenario analysis, [0059] discloses A customized care plan 940 for the patient with risk factors and actionable recommendations generated by care plan reminders and predictive analytics to mitigate risk, and [0069] describes reviewing root cause, recommendations to reduce risk score, care-plan development, and acceptance of the intervention recommendation.
Terry identifies the problem that patient risk assessments are not timely or readily available to caregivers and addresses that problem by sending alerts when a risk score reaches a threshold so caregivers can address risk factors resulting in the increased risk score Col.20, ll. 14-24. Vesto supplies the improvement Terry lacks: avoiding one-size-fits-all intervention strategy by using predictive analytics to generate a patient-specific care plan from a risk profile, allowing the user to review, modify, approve the plan [0057], and displaying a customized care plan with risk factors and risk-mitigating recommendations [0059]. A POSITA would have combined Vesto’s approval-based customized care-plan workflow with Terry’s threshold-driven risk analytics to solve Terry’s identified caregiver-response problem with a patient-specific approved plan, predictably producing a care plan directed to the risk factors that caused the threshold exceedance.
Claim 2.
Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, further comprising one or more medical devices connected to a network, and wherein the one or more medical devices include at least one of a patient bed, a spot monitor, a contact-free continuous monitoring device, and an infusion pump. (Terry, Col. 48, ll. 40-49, Fig. 2, Col. 22, ll.15-30, Col.24, ll. 55-67, Col.15, ll. 15-30)
Terry describes healthcare equipment linked via a communication infrastructure, specifically comprising items from the defined list. Terry's system includes equipment 12 connected via a communications network , and this equipment includes a patient bed and a monitor.
Claim 3.
Terry, in combination with Derenne and Vesto,
The system of claim 1, wherein the post-operative score includes a pressure injury risk score, and the pressure injury risk score is calculated by analyzing at least one of the physiological data and the image data, and the at least one recommendation includes turning the patient to reduce the pressure injury risk score. (Terry, abstract, Col. 20, ll 15-30)
Terry describes a system where the risk metric assesses pressure injury likelihood by processing data, and suggestions include repositioning the patient.
Claim 5.
Terry, in combination with Derenne and Vesto,
The system of claim 1, wherein the instructions, when executed by the at least one processing device, further cause the at least one processing device to: automatically implement the at least one recommendation when the selection of the control approving the at least one recommendation is received. (Terry, Col.1, ll. 40-67, Col. 20, 5 -30)
Terry describes the patient’s pressure injury score that triggers the automatic activation of a pressure injury prevention protocol.
Claim 6. Terry, in combination with Derenne, and Vesto teaches:
The system of claim 1, wherein the at least one recommendation includes assigning a patient care status to the patient based on a level of care required by the patient. (Terry, Figure 2, figure 8, Col.29, ll.35-55, col. 30, 1-45)
Terry describe a system's suggestions for patient care are determined by categorizing a patient's status according to the specific amount of care they need. For example, analytics engine receives patient movement data to indicates the probability of bed exit, then notify to one or more clinicians to be attended resulting in a change of status.
Claim 7. Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, wherein the interactions include at least one of measuring a time the patient spends on a surgical table during a surgery, detecting a quantity of caregivers that entered a surgical environment during the surgery, and monitoring one or more patient movements during or after the surgery. (Terry, Col.29, ll. 30-35, Col. 30, ll 5-40)
Terry describes that patient movement is monitored using sensors like load cells, pressure sensors, or force-sensitive resistors integrated into the bed or chair.
Claim 10.
Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, wherein the interactions are automatically monitored using one or more communications devices that include a smartphone or a tablet computer. (Terry, fig. 1-3, fig. 5A, Fig. 4A, Col. 29 ll.35-60, )
Claim 11.
Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, wherein the post-operative score is calculated by analyzing electronic health records pertaining to the patient, wherein the electronic health records include at least one of patient demographics, a description of a surgical site, a site progression description of the surgical site during and after a surgery, the patient's medical history, the patient's diet, and observations made before, during, or after the surgery. (Terry, fig. 1-2, fig. 3, fig. 6, fig. 8, fig. 9, fig. 10, Col. 1 ll. 45-67, Col. 2 ll. 10-20)
The Terry scores are calculated by an analytics engine in a healthcare facility to assess a patient's risk for developing sepsis, falling, or developing a pressure injury, based on data collected from various patient monitoring equipment and Initial assessment that include patient history.
Claim 13. Terry, in combination with Derenne, and Vesto teaches:
The system of claim 1, wherein the recommendation includes assigning the patient to a new location or assigning a new caregiver to the patient. (Terry, Col. 24, ll.35-50, Col. 29, ll. 1-10)
Terry describes a system where the suggested intervention involves moving the patient to a different room.
Claim 19. Terry, in combination with Derenne, and Vesto teaches:
The method of claim 14, wherein the post-operative score is calculated based on one or more of a time spent on a surgical table during the surgery, a quantity of caregivers that entered a surgical environment, and patient movement. (Terry, fig. 1-2, fig. 3, fig. 6, fig. 8, fig. 9, fig. 10, Col. 1 ll. 45-67, Col. 2 ll. 10-20)
The Terry scores are calculated by an analytics engine in a healthcare facility to assess a patient's risk for developing sepsis, falling, or developing a pressure injury, based on data collected from various patient monitoring equipment (Include patient movement) and Initial assessment that include patient history.
Note: Claims 14-18 and 20 are rejected with the same analysis above because they are very similar to Claims 1-3, 5-7, and 10-11.
Claims 4, 8, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Terry (US 11504071) in view of Derenne (US 20120075464 A1) and Vesto (US20130290005A1), and further in view of Wallace (US 20140167917 A2).
Claim 4. Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, wherein the post-operative score includes an infection risk score calculated . (Terry, Col.20, ll. 29-53)
Terry teaches calculating an infection (sepsis) risk score (Abstract) and tracking caregivers entering a patient's room, but fails to disclose monitoring the quantity of caregivers entering a specific surgical environment (e.g., Operating Room) or using this specific metric as input for the infection score calculation.
Wallace teaches the missing element, calculating infection risk based on the quantity of staff in the surgical environment. Wallace analyzes Acquired Infections (Risk Drivers) (Wallace, FIG. 2,) and explicitly identifies Staff (caregivers) Occupancy Level (quantity) as a driver (Wallace, FIG. 2). Wallace integrates this analysis with data collected from the OR (Operating Room/surgical environment) (Wallace, FIG. 1).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine the teachings of Terry with Wallace because both references share the purpose of assessing infection risks in healthcare settings using location and interaction data. Terry seeks to assess the risk of sepsis, and Wallace provides a system and method for disease mapping and infection control (Wallace, Abstract). A POSITA would recognize that Wallace's teaching that Staff Occupancy Level (Wallace, FIG. 2) in the OR (Wallace, FIG. 1) is an infection risk driver provides a known technique that could be applied to Terry's system, utilizing Terry's existing locating system 62 (Terry, 0045) to monitor the quantity of caregivers in the surgical environment to enhance the infection score calculation.
A person of ordinary skill in the art would have been motivated to integrate the calculation based on the quantity of caregivers in the surgical environment from Wallace into the system of Terry to achieve the benefit of improved infection control by incorporating known risk drivers. As Wallace teaches that analyzing these drivers facilitates Infection Control Policy (Wallace, FIG. 2, par. 0039) leading to Reduced Morality & Morbidity (Wallace, FIG. 2, 0058).
Furthermore, the proposed combination is obvious under the flexible approach mandated by KSR because it represents the Use of known technique to improve similar devices (methods, or products) in the same way. The technique of using staff occupancy level (quantity) in the OR (from Wallace) to calculate infection risk is known (as evidenced by Wallace, FIG. 1, FIG. 2). Applying this known technique to the analogous risk assessment system of Terry predictably improves its infection prediction (sepsis risk score) in the same manner to achieve a more comprehensive infection risk model.
A PHOSITA would have had a reasonable expectation of success in combining the references because the modification required only ordinary skill and routine experimentation. Terry already discloses the infrastructure (RTLS) necessary to track the location and quantity of caregivers, and Wallace provides the analytical approach linking staff quantity in the OR to infection risk (Wallace, FIG. 1, FIG. 2).
Claim 8. Terry, in combination with Derenne and Vesto, teaches:
The system of claim 7, wherein the post-operative score is calculated t. (Terry, Col.29, ll. 30-35, Col. 30, ll 5-40)
Terry teaches calculating the score based on patient movements, but fails to disclose the use of surgical table duration or surgical environment traffic count during surgery as inputs for the score calculation.
Wallace teaches these missing elements by describing a system for location and movement monitoring of Entities (Wallace, para. [0030]), which include patients and staff (caregivers) (Wallace, para. [0025]). This monitoring captures the necessary data, as the system can determine the allow-time of an Entity within a Geographical Area and monitor the operational flow within a Geographical Area (Wallace, para. [0030]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to combine the teachings of Terry with Wallace because both references share the purpose of comprehensive risk assessment in healthcare by integrating diverse data sources. Terry seeks to assess medical risks of a patient and Wallace provides a system that integrates Hospital Information Systems including OR, ADT, etc. (Wallace, FIG. 1). A POSITA would combine these by incorporating the surgical duration data (OR/ADT) and staff quantity data (Occupancy Level) identified by Wallace (Wallace, FIG. 1, FIG. 2) into Terry's multi-factor risk engine alongside the existing patient movement data (Terry, 0103).
A person of ordinary skill in the art would have been motivated to integrate the time on the surgical table and the quantity of caregivers in the surgical environment from Wallace into the system of Terry to achieve the benefit of improved risk prediction by accounting for known intraoperative factors. As Wallace teaches that analyzing these comprehensive data sources facilitates Quality Performance Improvement (Wallace, FIG. 1, par. 0057).
Furthermore, the proposed combination is obvious under the flexible approach mandated by KSR because it represents Combining prior art elements according to known methods to yield predictable results. The integration of Wallace's surgical environment risk drivers (time/quantity) into Terry's risk assessment system involves utilizing known methods, specifically the integration of data from standard hospital information systems as evidenced by Wallace (FIG. 1). Each element (patient movement, surgical duration, staff quantity) performs its established function as a risk contributor. The resulting combination yields only the predictable result of a comprehensive post-operative risk score and demonstrates no unexpected synergy.
A PHOSITA would have had a reasonable expectation of success in combining the references because the modification required only ordinary skill and routine experimentation. The data sources (OR, ADT, Location tracking) are standard hospital systems identified by Wallace (FIG. 1), and Terry's system is explicitly designed to integrate multiple data sources for risk analysis (Terry, Abstract).
Claim 12.
Terry, in combination with Derenne and Vesto, teaches:
The system of claim 1, wherein the post-operative score is calculated by analyzing adverse event data including (Terry, Col.9, ll. 24-40, fig. 2, Col.55, ll 39-50)
Terry describes utilizing information regarding the incident's patient history. However, Terry fails to disclose that the analysis of this adverse event data includes a location where an adverse patient event occurred and one or more caregivers assigned to the patient when the adverse patient event occurred.
Wallace discloses a system that continuously monitors and records the historical location and interactions between individually tracked Entities, which are defined to include both staff (caregivers) and patients. By analyzing this stored historical data for the specific time an adverse event occurred, the system can determine precisely which caregivers were in proximity to or in contact with the patient.(Wallace, paras. 0025, 0029, 0030-0031, 0034).
It would have been obvious to one of ordinary skill in the art to combine the teachings of Terry with Wallace because both references share the common goal of leveraging data analysis to improve patient safety and risk assessment in a healthcare setting. Terry provides a framework for calculating risk scores based on historical data like history of falls, while Wallace provides a method for capturing and analyzing highly detailed contextual data surrounding patient and caregiver interactions to facilitate a review of safety policies (Wallace, para. [0023]). A skilled artisan, seeking to make Terry's fall risk score more predictive and actionable, would have been motivated to enhance the generic history of falls data point with the specific contextual details of location and personnel taught by Wallace.
A person of ordinary skill in the art would have been motivated to integrate the contextual event analysis from Wallace into the risk calculation of Terry to achieve the benefit of a more precise and actionable risk assessment. Wallace teaches that analyzing such detailed historical data enables a facility to understand... infectious disease risk exposure and to effectively prioritize infection control practices related thereto (Wallace, para. [0035]). Applying this same principle to fall events would predictably allow a facility to identify high-risk locations or circumstances, leading to more targeted and effective fall prevention strategies.
Furthermore, the proposed combination is obvious because it represents combining prior art elements according to known methods to yield predictable results. The integration of location and caregiver data associated with a past adverse event into the Terry risk algorithm involves utilizing known data analysis methods. Terry’s system already possesses an analytics engine for calculating risk scores and a locating system capable of tracking patients and caregivers. Wallace teaches the specific technique of analyzing this type of location and interaction data historically. Each element performs its established function: Terry's engine analyzes data to produce a score, and Wallace's method provides more granular data for that analysis. The resulting combination yields only the predictable result of a more accurate risk score and demonstrates no unexpected synergy. A POSITA would have had a reasonable expectation of success in this integration, as it requires only a standard modification to a software algorithm to incorporate additional, available data fields into its calculation.
Relevant Prior Arts
WO 2021028930 A2
008] The present invention further provides a method for managing hygiene compliance of a caregiver, the method comprising the steps of: (a) providing a system 100 of the invention; (b) identifying the presence of a patient; (c) identifying the presence of a caregiver (in proximity to said patient); (d) identifying the actions of said caregiver and the activation of the dispenser 102; (e) based on data received from the identification system 101 and the dispenser 102, determining whether said caregiver’s hygiene compliance is positive or negative, and if negative activating the alarm mechanism 104, wherein: (i) positive hygiene compliance is determined when the identification system 101 indicates the presence of a patient and a caregiver, and the dispenser 102 was activated within a predefined time frame thereof in accordance with each one of the caregiver’s actions; and (ii) negative hygiene compliance is determined, and an alarm is turned on, when the identification system 101 indicates the presence of a patient and a caregiver, and the dispenser 102 indicates- or the computerized system 103 identifies- that the dispenser 102 was not activated within a predefined time frame thereof in accordance with the caregiver’s actions.
WO 2020047639 A1
[0036] In one embodiment, the centralization system additionally performs a step of automatically suggesting the action plan, based on the risks of diseases assessed, and sends this recommended plan to the health professional's access portal. In one embodiment, the centralization system runs an algorithm that systematically suggests an action plan based on the results obtained in the calculation of disease risk. For example, when detecting that the user is at risk for developing a certain disease, the algorithm selects a series of recommended actions for the treatment or monitoring of this disease, from data and known studies stored in the database (BD). [0037] The health professional then receives the action plan recommended by the centralization system and evaluates it in such a way that the health professional can accept this recommended plan, customize the recommended plan or ignore the recommended plan generating a totally personalized one. according to your assessment. In one embodiment, the decision tree algorithm is updated based on the health professional's decision
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA DAMIAN RUIZ whose telephone number is (571)272-0409. The examiner can normally be reached 0800-1800.
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, Shahid Merchant can be reached at (571) 270-1360. 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.
/J.D.R./Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights