DETAILED CORRESPONDENCE
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA This non-final office action on merits is in response to the Patent Application filed on 4 September 2024. Claims 1-20 are pending and considered below.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, or 365(c) is acknowledged. The filing date of the instant application is 4 September 2024. Applicants claim of priority to provisional application 63/536893 filed 6 September 2023 is acknowledged and the provisional application details all the information related to the filed patent application. Therefore the instant application is afforded a priority date of 6 September 2023.
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 1-23 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
The claimed limitations, as per system and method Claims 1 and 17, include the steps of:
An Artificial Intelligence (Al) based computer system for determining one or more predicted requirements for a healthcare facility corresponding to a scheduled inflow of patients, comprising:
a memory configured to store instructions;
a processor disposed in communication with the memory and coupled to a computer network, wherein the processor generates a learning inference model using a machine learning or deep learning algorithm configured to:
capture data, from the computer network, containing information relating to patient inflow to the healthcare facility wherein the data includes a purpose of stay for a patient;
analyze the captured data, using the generated learning inference model, to generate, using at least a portion of the captured data, one or more predictions regarding one or more conditions to occur in the future that are associated with one or more resources of the healthcare facility associated with the purpose of stay for the patient;
analyze the one or more predictions for recommending an allocation and/or reallocation of at least one of the one or more resources.
Examiner Note: underlined elements indicate additional elements of the claimed invention identified as performing the steps of the claimed invention.
Under Step One of the analysis under the Mayo framework, claims 16-20 is/are drawn to methods (i.e., a process), claims 1-16 is/are drawn to a system (i.e., a machine/manufacture). As such, claims 1-20 is/are drawn to one of the statutory categories of invention.
Under Step 2A Prong One and MPEP 2106 of the analysis under the Mayo framework the claim(s) are determined to recite(s) the judicial exception of capture data containing information relating to patient inflow to the healthcare facility wherein the data includes a purpose of stay for a patient; analyze the captured data, using the generated learning inference model, to generate, using at least a portion of the captured data, one or more predictions regarding one or more conditions to occur in the future that are associated with one or more resources of the healthcare facility associated with the purpose of stay for the patient; analyze the one or more predictions for recommending an allocation and/or reallocation of at least one of the one or more resources.
This judicial exception is similar to abstract ideas related to certain methods of organizing human activity such as managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions.
Under Step 2A Prong Two and MPEP 2106 of the analysis under the Mayo Framework, the judicial exception expressed as the steps of the instant claims is not integrated into a practical application because the claims only recite one additional element, the element of using a processor or computing system including a local registry or memory to perform the steps of the claimed abstract idea. The processor is recited at a high-level of generality (i.e., as a generic processor performing generic computer functions to perform the claimed steps of the invention), and therefore the abstract idea amounts to no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element of performing the inventive steps with a generic computer does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Thus the claimed invention is directed to an abstract idea without a practical application.
Under step 2B and MPEP 2106 of the Mayo analysis framework the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional limitations of performing the steps with a computer processor, a display module, and a memory storing machine executable instructions represents insignificant data gathering and data processing steps requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry. Applicant’s published written description paragraph [28] recites “schematic block diagram of an example communication network 100 illustratively comprising nodes/devices 101-108 (e.g., sensors 102, client computing devices 103, smart phone devices 105, web servers 106, routers 107, switches 108, databases, and the like) interconnected by various methods of communication. For instance, the links 109 may be wired links or may comprise a wireless communication medium, where certain nodes are in communication with other nodes, e.g., based on distance, signal strength, current operational status, location, etc,” written description paragraph [28] recites “aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon,” written description paragraph [30] recites “computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing,” written description paragraph [37] recites “Computing device 200 is operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well-known computing systems, environments, and/or configurations that may be suitable for use with computing device 200 include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputer systems, and distributed data processing environments that include any of the above systems or devices, and the like,” and written description paragraph [38] recites “components of device 200 may include, but are not limited to, one or more processors or processing units 216, a system memory 228, and a bus 218 that couples various system components including system memory 228 to processor 216. Bus 218 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures.” Thus the claimed inventive steps are performed by generic or general purpose computing systems executing well known and understood instructions and processes which do not comprise significantly more than a known computing system, or comprise improvements to another technological field.
Further, as per MPEP 2106, and TLI Communications LLC v. AV Automotive LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) ("It is well-settled that mere recitation of concrete, tangible components is insufficient to confer patent eligibility to an otherwise abstract idea") and as per Intellectual Ventures I LLC v. Capital One Bank (USA), N.A., 792 F.3d 1363, 1366, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015) ("An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment, such as the Internet [or] a computer") simply performing the steps of an abstract idea by a computing apparatus does not make an inventive concept statutorily eligible. Therefore, it is clear from Applicants’ specification that the elements and modules in the claims require no more than a generic computer (e.g., a general-purpose computing device) to perform generic computer functions (e.g., accessing, transmitting/receiving, sorting, and storing data) that are well-understood, routine and conventional activities previously known in the industry. None of the limitations, considered as a whole and as an ordered combination provide eligibility, because the steps of the claims simply instruct the practitioner to implement the abstract idea with routine, conventional activity.
Viewing the additional limitations in combination also shows that they fail to ensure the claims amount to significantly more than the abstract idea. When considered as an ordered combination, the additional components of the claims add nothing that is not already present when considered separately, and thus simply append the abstract idea with words equivalent to “apply it” on a generic computer and/or mere instructions to implement the abstract idea on a generic computer, generally link the abstract idea to a particular technological environment or field of use, and append the abstract idea with insignificant extra solution activity associated with the implementation of the judicial exception, (e.g., mere data gathering).
Dependent claims 2-16 and 18-20 are directed to the judicial exception as explained above for Claims 1 and 17 and are further directed to limitations directed to limitations allocating system resources as related to a wide variety of treatment provisions such as length of stay, future patient conditions, allocations of patient treatment resources such as optimizing health care unit availabilities, as well as the allocation of staff members with respect to care giving, the analysis of historical related data, and the prediction of patient volumes. These limitations or processes are considered to be executed by the general purpose computing system as explained above, and therefore do not result in the claimed invention being directed to a practical application or comprise significantly more than the identified abstract idea.
Dependent claims 2-16 and 18-20 do not add more to the abstract idea of independent Claims 1 and 17 and therefore are rejected as ineligible subject matter under 35 U.S.C. 101 based on a rationale similar to the claims from which they depend.
Examiner Note: 101 Eligibility
Examiner has analyzed the instant invention with respect to the determination of eligibility under the requirements of the 2019 PEG Step 2A Prongs One and Two and MPEP 2106 has determined that the claims as currently constructed do not include sufficient technical functioning aspects such that a rejection is not warranted and therefore the rejection above is warranted. Examiner has analyzed the written description in detail and recommends Applicants consider incorporating detailed functioning of the artificial intelligence server system as disclosed at least at paragraphs [59]-[62] of the written description and as well as detailed in Figure 4. Should the Applicants specifically detail the functional aspects of the particular artificial intelligence system into the independent claims the rejection, subject to further consideration and evaluation, would be withdrawn.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1-3, 9-12, 15, 17, 18, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035).
Claims 1 and 17: An Artificial Intelligence (Al) based computer system for determining one or more predicted requirements for a healthcare facility corresponding to a scheduled inflow of patients, comprising: a memory configured to store instructions; a processor disposed in communication with the memory and coupled to a computer network, wherein the processor generates a learning inference model using a machine learning or deep learning algorithm ([118-188]) configured to: Examiner Note: Wang as cited discloses a wide range of machine learning algorithms which are interpreted to detail the execution of a wide range of techniques which the Examiner equates to AI procedures.
capture data, from the computer network, containing information relating to patient inflow to the healthcare facility wherein the data includes a purpose of stay for a patient ([26 “matching newly admitted patients with an optimal care path for that patient based on using machine learning to determine respective probabilities of the patient being classified as being similar to the patients who have gone through each care path. For example, the higher the probability, the more likely the patient will have a similar outcome to patients who have gone through a particular care path,” 28 “core analytics program may include care path pattern recognition module, a care path patient profile model builder, and care path comparative effectiveness analysis logic,” 31 “analytics applications supported by the care path analytics platform may include, but are not limited to, hospital-acquired infection risk prediction, hospital readmission risk prediction, emergency department visit prediction, length of stay (LOS) prediction, next medical intervention recommendation, hospital bed management,” 32 “use the generated probabilities to determine the best possible next interventions for the new patient admission. In addition, the system may analyze the patterns and risks among a plurality of care paths, and may input the analyzed patterns to a plurality of prediction models to help reduce patient risks and predict patient length of stay. The system may input the predicted length of stay to a healthcare resource management system for use in managing healthcare resources,” 58 “data mining program 122 includes the feature generator 172, which extracts features from the mined data. For example, the core analytics program may use extracted features to build care path patient profile models. The care path patient profile may include a set of patient characteristics plus the interactions among the characteristics that are distinctive for each care path pattern. The patient characteristics may include patient demographic information, genetic information, health history, clinical history, and so forth. At least some of the patient characteristics may be used as features for generating and training care path patient profile models,”]); Examiner Note: Examiner under a broadest reasonable interpretation interprets the disclosures of Wang with respect to the capture and processing of patient inflow information to create specific patient care paths including treatment procedures and a wide variety of data which is used to determine diagnoses and associated treatment path determinations which Examiner determines to include implementing the diagnosis of conditions and associated determination of purpose of stay and as well treatment methods. As well the disclosures related to the matching of newly admitted patients to care paths is interpreted by the Examiner to detail patient inflows.
analyze the captured data, using the generated learning inference model ([58 “data mining program 122 includes the feature generator 172, which extracts features from the mined data. For example, the core analytics program may use extracted features to build care path patient profile models,” 61 “Core analytics program 124 may include the care path pattern recognition module 174 that may be used for prediction; a care path patient profile model builder; and a care path comparative effectiveness analytics module,”]), to generate, using at least a portion of the captured data, one or more predictions regarding one or more conditions to occur in the future that are associated with one or more resources of the healthcare facility associated with the purpose of stay for the patient ([77 “prediction may help the healthcare professional to determine the next intervention step, and may also help streamline the hospital operations, such as by being used by the hospital to manage the hospital resources such as beds, staff, medical equipment, medical supplies,” 89 “care path analytics platform that supports at least two categories of applications: predictive analytics application(s) 126 and prescriptive analytics application(s) 128. The example applications illustrated in this example include the hospital-acquired infection risk prediction application 180, the hospital readmission risk prediction application 182, the emergency department visit prediction application 184, the length of stay (LOS) prediction application,” 90, 91, 96 “application may train and cross validate a binary machine learning classifier using the feature matrix and the outcome label vector. The application may store the classifier model with the best performance for use in the prediction stage by the respective application. As mentioned above, the application may be one of the hospital-acquired infection risk prediction application 180, the hospital readmission risk prediction application 182, or the emergency department visit prediction application,” 106 “demand prediction for certain resources (e.g., hospital beds, hospital staff, hospital equipment, etc.) may be determined based on an aggregation of individual patient LOS predictions. As mentioned above, the LOS prediction application 186 may be configured to output a distribution of predicted LOS for each admission,”]); Examiner Note: Examiner under a broadest reasonable interpretation interprets the disclosures of Wang with respect to the prediction of patient conditions and the associated allocation of resources for treatment with respect to the performance of a wide range of resource availability calculations and predictions of availability to disclose the implementation of predictions which result in a better allocation of patient related healthcare resources related to patient stays at a facility.
Wang does not explicitly disclose however Akbay discloses:
analyze the one or more predictions for recommending an allocation and/or reallocation of at least one of the one or more resources ([25 “automated" resource assignment engine 150 may facilitate resource and patient flow management using a Graphical User Interface ("GUI") 152. As used herein, the term "automated" may refer to, for example, actions that can be performed with little or no human intervention. In some embodiments, a healthcare enterprise simulation model 154 may use the current resource data from multiple hospitals and generate a predicted future state of resources that can be provided to healthcare professionals 160, such as nurses or managers,” 31 “predicted future state of the resources may also be based on predicted future events (e.g., based at least in part historical information of the first healthcare enterprise). The predicted future state of the first resources is based at least in part on second resource data indicative of the state of second resources used to deliver healthcare to a plurality of patients at a second healthcare enterprise remote from, and networked with, the first healthcare enterprise. For example, patient beds and staffing information associated with a second hospital may impact the predictions,” 32 “Responsive to the request, a particular resource is automatically assigned to the resource request based at least in part on the predicted future state of the resources. Note that the assigned resource might be associated with a different, remote healthcare enterprise,” 61 “current and scheduled patient may, for example, be placed into one of 50 categories based on the data types present for them, which guides their specific care path. Each patient's category may be used to apply stochastic parameters and generate 100 replications (potential future paths) for that patient. Note that a resource assignment may be generated relatively quickly (e.g., within five seconds of receiving a resource request),” 63]).
Therefore it would be obvious for Wang to analyze the one or more predictions for recommending an allocation and/or reallocation of at least one of the one or more resources as per the steps of Akbay in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claims 2 and 20: Wang in view of Akbay disclose the Al based computer system as recited in claim 1 and 19 and Wang further discloses wherein recommending an allocation of at least one of the one or more resources is determined based in part on analyzing historical data relating to resources required for the patient's purpose of stay ([58 “patient characteristics may include patient demographic information, genetic information, health history, clinical history, and so forth. At least some of the patient characteristics may be used as features for generating and training care path patient profile models. With the care path patient profile, rather than using some simple ad-hoc criteria based on gender and age, say, the core analytics program may more accurately determine which care path a newly admitted patient may be most likely to experience,” 78 “care path patient profile may include a set of patient characteristics determined to be significant, as well as the interactions among these patient characteristics that are unique or otherwise distinct for each care path pattern. The patient characteristics may include patient demographic information, genetic information, health history, clinical history prior to the admission, and the like. These characteristics may be a common pattern extracted from the received data using supervised machine learning models,” 102 “empirical distribution of LOS of historical admissions, the LOS prediction application 186 may be configured to apply kernel density estimation or other suitable estimation techniques. For example, suppose the distribution of LOS for care path i is f.sub.i(x). The LOS prediction application 186 may calculate the weighted mixture distribution based on the calculated weights and the empirical distribution,” 113]).
Claim 3: Wang in view of Akbay disclose the Al based computer system as recited in claim 2 and Wang does not explicitly disclose however Akbay discloses wherein the purpose of stay relates to treatment of a medical condition ([30 “configuration might involve defining a plurality of treatment "units" of the healthcare enterprise simulation model and defining patient flow characteristics into, within, between, and out of the plurality of treatment units. As used herein, phrase "treatment unit" might refer to, for example, an emergency department, an outpatient unit, a holding room, an operating room, a recovery room, a cardiac treatment unit, a physical therapy unit, a laboratory, an X-ray and MRI unit, and/or an intensive care unit,” 47 “inpatient services 630 units might represent locations where a patient spends at least one night in the hospital in order to go through the care plan appropriate for his or her treatment,” 49]).
Therefore it would be obvious for Wang wherein the purpose of stay relates to treatment of a medical condition as per the steps of Akbay in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim 9: Wang in view of Akbay disclose the Al based computer system as recited in claim 3 above and Wang further discloses wherein the generated one or more predictions includes predicting staff required for treatment of the patient's medical condition ([26 “provide a comparative visualization of one or more care paths and associated outcomes, medical professionals are able to use the system herein for making an educated and comprehensive determination of an optimal care path for each new patient,” 29 “the prescriptive analytics application may include hospital bed management logic, staff planning logic, and next medical intervention recommendation logic,” 30 “platform may analyze the care path patterns that are highly correlated with an outcome of interest, such as readmission. Further, the care path analytics platform may employ data mining and machine learning based analytics to mitigate patient risk and improve operations of hospitals or other health care organizations by analyzing patterns across a number of different data sources, building care path patient profile models, recommending next intervention actions,” 31 “analytics applications supported by the care path analytics platform may include, but are not limited to, hospital-acquired infection risk prediction, hospital readmission risk prediction, emergency department visit prediction, length of stay (LOS) prediction, next medical intervention recommendation, hospital bed management, and staff planning,” 41 “medical professional or other user may execute and interact with the GUI on the display 118 for determining an optimal care path for a selected patient and a selected medical facility, such as a hospital or other health care organization,” 58 “With the care path patient profile, rather than using some simple ad-hoc criteria based on gender and age, say, the core analytics program may more accurately determine which care path a newly admitted patient may be most likely to experience. This may not only help the medical professionals decide the next intervention, but may also assist the hospital to manage the hospital resources such as beds, staff, equipment, and other resources,”]).
Claim 10: Wang in view of Akbay disclose the Al based computer system as recited in claim 9 above and Wang further discloses wherein the one or more conditions to occur in the future that are associated with one or more resources relate to particular staff members that are required for the patient's predicted length of stay ([61 “care path pattern recognition module 174 may be executed to determine a pattern of mined care paths and to use the determined pattern for the predictive analytics application(s) 126. For instance, the care path pattern recognition module 174 may be used by a hospital-acquired infection risk prediction application 180, a hospital readmission risk prediction application 182, an emergency department visit prediction application 184, and/or a length of stay (LOS) prediction application,” 63 “care path pattern recognition module 174 may cluster the care path based on the frequency of care path by clustering the care paths into frequent care paths and infrequent care paths. In some cases, these may correspond to normal care paths and special care paths. If the number of admissions associated with a particular care path pattern exceeds a threshold number, then that care path pattern may be classified as frequent; otherwise, that care path pattern is classified as infrequent,” 77 “care path patient profile model builder 176 may be executed to generate a profile for each frequent care path of past patients. For example, when a patient is newly admitted, if the hospital can make certain critical predictions, such as the care path that the patient may be most likely to experience and the length of stay, the prediction may help the healthcare professional to determine the next intervention step, and may also help streamline the hospital operations, such as by being used by the hospital to manage the hospital resources such as beds, staff, medical equipment, medical supplies,” 78 “patient characteristics may include patient demographic information, genetic information, health history, clinical history prior to the admission, and the like. These characteristics may be a common pattern extracted from the received data using supervised machine learning models,”]). Examiner Note: Examiner under a broadest reasonable interpretation interprets the wide range of calculations and assignments of medical personnel with respect to available resources and staff member attributes to disclose the assignment of staff members with respect to upcoming and future episodes of treatment processes.
Claim 11: Wang in view of Akbay disclose the Al based computer system as recited in claim 10 above and Wang further discloses, wherein recommending an allocation of at least one of the one or more resources includes generating at least one recommendation of a number of staff to schedule for providing medical care for a time period in the future for patients in at least one healthcare unit of the healthcare facility is based in part on a prediction of a number of patients expected to occupy the healthcare unit during a certain time period in the future ([92 “medical intervention recommendation application 192 may be executed using a direct application of the outputs of the care path patient profile model builder 176 and the comparative effectiveness analytics module 178. Furthermore, the other prescriptive analytics applications, the hospital bed management application 188 and the staff planning application 190, are about hospital resource management. One of the factors for successful resource management is to the ability to accurately predict the demand Accordingly, the output of the LOS prediction application 186 may be used as an input for these applications,” 102 “The LOS prediction application 186 may also calculate the empirical distribution of the LOS of historical admissions associated with each care path. For the empirical distribution of LOS of historical admissions, the LOS prediction application 186 may be configured to apply kernel density estimation or other suitable estimation techniques. For example, suppose the distribution of LOS for care path i is f.sub.i(x). The LOS prediction application 186 may calculate the weighted mixture distribution based on the calculated weights and the empirical distribution,” 108 “application may output the predicted demand D.sub.i for resources for one or more selected days i based on the received new patient admissions. Furthermore, the application may perform at least one action based on the predicted demand For example, if the hospital bed management application 188 is being executed, the hospital bed management application 188 may reserve a required number of beds based on the predicted demand for the beds. Similarly, if the staff planning application 190 is being executed, the staff planning application 190 may schedule a required number of staff employees to work at specified times based on the predicted demand for staffing at those times,”]). Examiner Note: Examiner interprets the disclosures of Wang with respect to the implementation of a wide range of treatments to include the determination of numbers of staff employees to schedule as related to the number of patients occupying the healthcare unit, as cited to above, “the staff planning application 190 is being executed, the staff planning application 190 may schedule a required number of staff employees to work at specified times based on the predicted demand for staffing at those times.”.
Claim 12: Wang in view of Akbay disclose the Al based computer system as recited in claim 9 above and Wang further discloses, wherein the number of staff to schedule is determined based in part on analyzing historical data ([58 “patient characteristics may include patient demographic information, genetic information, health history, clinical history, and so forth. At least some of the patient characteristics may be used as features for generating and training care path patient profile models,”]) indicating an average patient to medical personnel ratio within the healthcare unit during a corresponding time period in the past ([92 “other prescriptive analytics applications, the hospital bed management application 188 and the staff planning application 190, are about hospital resource management. One of the factors for successful resource management is to the ability to accurately predict the demand Accordingly, the output of the LOS prediction application 186 may be used as an input for these applications,” 100 “first method may use an empirical distribution of the most likely care path to predict the length of stay for a new patient admission. The second method uses a weighted mixture of the distributions of all possible care paths. The output of the LOS prediction application 186 may be a distribution of the predicted LOS for a particular patient, rather than a single statistic, such as the mean or the median, to offer the flexibility for further estimation used in other applications, such as the hospital bed management application 188 and the staff planning application,” 101, 102 “LOS prediction application 186 may calculate the weighted mixture distribution based on the calculated weights and the empirical distribution. As an example, F(x)=Σ.sub.i=1.sup.nw.sub.if.sub.i(x) where F(x) is the weighted mixture distribution. Finally, the LOS prediction application 186 may output the weighted mixture distribution F(x) as the prediction of the LOS for this admission,” 103 “each care path patient profile model, a probability may be generated. This probability may indicate how likely this admission will follow a particular care path. The next medical intervention recommendation application 192 may rank all the probabilities generated and output the top k models with the highest probabilities,”]).
Claims 15 and 18: Wang in view of Akbay disclose the Al based computer system as recited in claims 1 and 17 above and Wang further discloses wherein generating a learning inference model using a machine learning or deep learning algorithm is contingent upon data captured from one or more external data sources ([30 “care path analytics platform may employ data mining and machine learning based analytics to mitigate patient risk and improve operations of hospitals or other health care organizations by analyzing patterns across a number of different data sources, building care path patient profile models, recommending next intervention actions,” 31 “care path analytics platform may integrate data from a plurality of diverse health information systems, such as an electronic health record (EHR) system, an admission, discharge, transfer (ADT) system, a registration and billing system, a clinical information system, a hospital resource management system, or the like. The data integration process may be analytics oriented. In addition, the analytics applications supported by the care path analytics platform may include, but are not limited to, hospital-acquired infection risk prediction, hospital readmission risk prediction, emergency department visit prediction, length of stay (LOS) prediction, next medical intervention recommendation, hospital bed management, and staff planning,” 35, 39, 58 “care path patient profile models may be generated and trained as machine learning models based on determined features. Additional details of generating the care path patient profile models are discussed below with respect to the core analytics program,” 59, 78-85]).
Claim(s) 4-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035) and in further view of Bhavani (20210391062).
Claim 4: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 3 above and Wang does not explicitly disclose however Bhavani discloses wherein the generated one or more predictions includes a length of stay for the patient for treatment of the medical condition ([16 “model is preferably applied to contemporaneous data from the healthcare facility to predict an unknown of unquantified resource requirement at the healthcare facility, for example at least one of LOS of a patient, equipment required for a patient, or personnel required for a patient,” 18 “resource management system further identifies whether a predicted resource requirement exceeds a limit (e.g., LOS, capacity, available quantity, limit of insurance coverage, etc.). The resource management system preferably provides a recommended act to minimize a delta between a predicted resource requirement and a limit,” 23 “inventive subject matter contemplates LOS engine 110 as pictorially depicted in FIG. 1. The intent of LOS engine 110 is to learn from historical data 112 as well as to update with real-time intelligence from patients or resources in the healthcare facility. LOS engine 110 provides next best action recommendation 114 and prescriptive suggestions 116 to care teams to minimize bottlenecks and ease patient flow,”]).
Therefore it would be obvious for Wang wherein the generated one or more predictions includes a length of stay for the patient for treatment of the medical condition as per the steps of Bhavani in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim 5: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 4, wherein the one or more conditions to occur in the future that are associated with one or more resources relate to a bed and/or room that is to be required for the patient's predicted length of stay ([Abstract “disclosed for an AI learning system to predict patient length of stay (LOS) in healthcare facilities,” 3 “hospital executives today are constantly monitoring the Length-of-Stay (LOS) of the patient inside the hospital to improve clinical outcomes and optimize that against the standardized payments they receive from Medicare and other payors,” 25 “LOS engine 110 uses various classes of historic data 112 and contemporaneous data from the healthcare facility at least partially sourced from Electronic Health Records or Bed Management Systems, or local or regional demographic data to develop and improve the accuracy of predictions. For example, LOS engine 110 can use any of the following classes of data to train and make predictions: proper bed, level of care; acute care for elderly (ACE) cases; patient population age, diagnosis, sex, payer status, severity, trauma, comorbidities, outliers, increased volume, common or prevalent DRG or diagnosis.
Therefore it would be obvious for Wang wherein the one or more conditions to occur in the future that are associated with one or more resources relate to a bed and/or room that is to be required for the patient's predicted length of stay as per the steps of Bhavani in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim 6: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 5, and Wang does not explicitly disclose, however Bhavani discloses wherein recommending an allocation of at least one of the one or more resources includes allocation of a bed and/or room for the patient's predicted length of stay ([25 “LOS engine 110 uses various classes of historic data 112 and contemporaneous data from the healthcare facility at least partially sourced from Electronic Health Records or Bed Management Systems, or local or regional demographic data to develop and improve the accuracy of predictions….LOS engine 110 can use any of the following classes of data to train and make predictions: proper bed, level of care; acute care for elderly (ACE) cases; patient population age, diagnosis, sex, payer status, severity, trauma, comorbidities, outliers, increased volume, common or prevalent DRG or diagnosis (e.g., pneumonia, flu, etc.), Better Outcomes for Older adults through Safe Transitions (BOOST), LACE index (length of stay (L), acuity of the admission (A), comorbidity of the patient (C),”]).
Therefore it would be obvious for Wang wherein recommending an allocation of at least one of the one or more resources includes allocation of a bed and/or room for the patient's predicted length of stay as per the steps of Bhavani in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim 7: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 6, and Wang does not explicitly disclose, however Bhavani discloses wherein recommending an allocation of at least one of the one or more resources further includes indication of whether the determined bed and/or room required for the patient's length of stay is available in the healthcare facility ([8 “implementing a resource management system in a healthcare facility. A first health data is used to develop a model to predict a first resource requirement in the healthcare facility. A predictive ability/capacity of the model is assessed by applying a second health data to the model to predict a second resource requirement, and comparing the predicted second resource requirement to a known resource requirement,” 9 “predictive element (e.g., processor, machine learning algorithm (MLA), etc.) is informationally coupled to a database of health data regarding the healthcare facility, and a health data generator is coupled to the database. The health data generator provides a class of contemporaneous health data to the database, and the predictive element uses the database to make a model to predict a health event in the healthcare facility based on the class of contemporaneous health data,” 19 “Resource management systems for a healthcare facility are further contemplated. A predictive element (e.g., processor, machine learning algorithm (MLA), etc.) is informationally coupled to a database of health data regarding the healthcare facility, and a health data generator is coupled to the database,” 20 “predicted health event is typically at least one of LOS, required equipment, or required personnel for a patient. Classes of contemporaneous health data typically relate to at least one of an operational outcome of the healthcare facility, a financial outcome of the healthcare facility, a diagnosis of a patient, a prognosis of a patient, a patient outcome, or a treatment of a patient,”25, 28 “Comorbidities (class 217). Filter 230 segments the patient population into classes by cause for delay in patient flow, including lack of right bed (class 231), awaiting diagnostics (class 232), discharge pending dependent on bed at nearby skilled nursing facility (SNiFs),”]).
Therefore it would be obvious for Wang wherein recommending an allocation of at least one of the one or more resources further includes indication of whether the determined bed and/or room required for the patient's length of stay is available in the healthcare facility as per the steps of Bhavani in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035) and in further view of Day et al. (20210319884)
Claim 8: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 6, and Wang does not explicitly disclose, however Day discloses wherein recommending an allocation of at least one of the one or more resources further includes recommending whether to transfer one or more other patients from a first healthcare unit to a second healthcare unit for making the bed and/or room available for the patient during the patient's predicted length of stay ([49 “hospital operational systems 128 may track hospital bed usage. For example, when a patient is admitted, the hospital operational systems 128 may associate the patient with an identifier (e.g., an identification code) and track patient status, patient ward/unit assignment, patient bed assignment,” 61, 72 “facility 420 may include a plurality of units, each unit including a plurality of rooms (not shown). Further, each room may include one or more beds (not shown). Facility 420 may further include workstations 424, which may be EMR workstations, workstations 434 communicatively coupled to medical devices 430, and workstations 444 in the healthcare command center,” 92 “bed master data file may include bed data for the facility and may include specified fields, including system name, hospital identification (ID), Unit ID, Unit display name, Unit type, Room ID, Room display name, Bed ID, Bed display name, Service (e.g., cardiac), Level of care group (e.g., adult ICU), Vent capable, Negative pressure, Private, and Active. In one example, the bed master data for the specified fields may be extracted from a bed inventory database for the facility. The bed master data may be updated over a greater period or based on user request,” 100, 170 “facility view 1900 comprises rows of resources or resource groups such as beds in different units (e.g., intensive care, observation, pediatric, adult, etc.), with information for each resource displayed in columns such as census column 1902, occupancy rate column 1904, unoccupied resource column,”]).
Therefore it would be obvious for Wang wherein recommending an allocation of at least one of the one or more resources further includes recommending whether to transfer one or more other patients from a first healthcare unit to a second healthcare unit for making the bed and/or room available for the patient during the patient's predicted length of stay as per the steps of Day in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035) and in further view of Mairs et al. (20230368901) and Luna (20230360786).
Claim 13: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 4, and Wang does not explicitly disclose, however Mairs discloses wherein the learning inference model using a machine learning or deep learning algorithm ([215 “machine readable instructions may include a sequence of instructions, a processor-executable machine learning model,”]) is further configured to:
identify at least one milestone associated with a patient receiving care in a healthcare facility ([126 “a patient timeline region 352 which includes a listing of several different evaluation milestones. Each milestone may correspond to a particular medical procedure, examination, consultation, or relate to other actions such as payment information (e.g. insurance accepted), which may be associated with the described visits. Each listed milestone also may comprise an indication of whether the particular milestone was completed,” 127, 128]);
update and track the at least one milestone twice a day until the patient's bed is ready for occupancy by another patient ([127 “patient timeline region 352 may conveniently provide a summary and sequence by which a clinician may immediately recognize which evaluation milestones have been met by the patient and which milestones have yet to been achieved,” 128 “128 “patient timeline region 352 also may facilitate patient care by the device manufacturer (or servicer) upon that entity becoming aware of certain milestones which a particular patient or a sampling of patients may have trouble achieving, and then take action to facilitate better outcomes in completing such milestones,” 159 “additional data such as, but not limited to, time spent in bed, time or amount of sleep, such as total sleep time and/or start and stop times. For example, the bars in the graph 463 of FIG. 5A may additionally or alternatively be used to display time spent in bed, total sleep time, start time, stop time, and/or sleep stage(s), and/or, in some examples, may be juxtaposed with the illustrated usage bars,” 252 “]).
Therefore it would be obvious for Wang to identify at least one milestone associated with a patient receiving care in a healthcare facility and update and track the at least one milestone twice a day until the patient's bed is ready for occupancy by another patient as per the steps of Mairs in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Wang does not explicitly disclose, however Luna discloses:
generate a first alert within a predetermined time window before a selected milestone ([16 “HIPAA compliant messaging and alert platform that creates surgical staff communication groups for each procedure to encourage preoperative communication and enhance staff preparedness. Current methods for staff communication involve cell phones, overhead paging systems, and pagers. The system allows staff to use familiar pathways of communication thereby enhancing communication efficiency. Procedure milestone alerts perfectly coordinate the surgical staff, anesthesia, xray, and the surgeon with live time procedure updates,” 86 “Reportable data is produced by populating the systems algorithms with one or more of the following patient-specific milestones, including but not limited to: Patient Arrival, Patient in Pre-Op, Room Opened, Patient in Room, Patient Asleep, Foley Inserted, Patient Prepped, Incision Made, Closing Started, Dressing On, Patient Awake, Patient Exits Room, Patient in Recovery, Patient Discharged, Count performed, and Time-Out performed,”]); and
generate a second alert within a second predetermined time window after a target time for the selected milestone to occur has passed ([47 “the communication module 202 may generate case milestone alerts which can be transmitted to relevant users. The case milestone alerts may be transmitted once particular (predetermined) stages of patient care are reached,” 48]).
Therefore it would be obvious for Wang to generate a first alert within a predetermined time window before a selected milestone and generate a second alert within a second predetermined time window after a target time for the selected milestone to occur has passed as per the steps of Luna in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035) and in further view of Ruiz et al. (20240047052).
Claim 14: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 13, and Wang does not explicitly disclose, however Ruiz discloses wherein the learning inference model using a machine learning or deep learning algorithm is further configured to:
predict a volume of patients that will be staying in the healthcare facility for the at least two respective time periods per day based on the received flow data and the predicted length of stay for the patients ([25 “automatically determining and predicting appropriate staffing or coverage levels (e.g., a staffing or coverage plan) in an enterprise, such as a healthcare facility, based on a number of selected input parameters. The input parameters can include, for example, historical staffing or coverage data, historical patient volume data, current patient volume data, acuity level data, default schedule data, cost by provider type information, contracted staffing or coverage obligations, facility type and size, RVU related information, simulation data, the number of patients seen or expected to be seen during a selected period of time (e.g., patient volume)”]); and
determine staffing requirements for the at least two time periods a day based on the predicted volume of patients for the respective at least two time periods ([37 “generated coverage plan data 30A is in essence a schedule that recommends selected coverage based on a number of different factors including coverage needs and costs per shift for each facility. As such, the coverage determination unit 30 optimizes staff coverage and cost. In the healthcare facility context, the staff or clinicians can include doctors, nurses, nurse practitioners, physician assistants, assistants, therapists, and other types of healthcare workers or employees,” 38 “schedule 124 can show any selected type of information, such as for example the patient volume 126 (as shown) per day or number of staff per day, or both. The schedule can be selectively color coded 128 to form in essence a heat map to convey selected types of information, such as whether there is adequate coverage for a selected day or the anticipated or expected patient volume,”]).
Therefore it would be obvious for Wang to predict a volume of patients that will be staying in the healthcare facility for the at least two respective time periods per day based on the received flow data and the predicted length of stay for the patients and determine staffing requirements for the at least two time periods a day based on the predicted volume of patients for the respective at least two time periods as per the steps of Luna in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Claim(s) 16 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Wang et al (30300082941) and Akbay et al. (20140108035) and in further view of Dare (20240006058).
Claims 16 and 19: Wang in view of Akbay disclose the Al based computer system ([16]) as recited in claim 18 and Wang does not explicitly disclose, however Dare discloses wherein the processor is further configured to utilize a Large Language Model (LLM) for recommending an allocation and/or reallocation of at least one of the one or more resources ([58 “system may incorporate the use of artificial intelligence, specifically machine learning, to train a large language model. This language model is trained on data extracted from electronic health records (EHRs) to predict the best referral and clinical outcomes for matching patients to medical providers in the marketplace,”]).
Therefore it would be obvious for Wang wherein the processor is further configured to utilize a Large Language Model (LLM) for recommending an allocation and/or reallocation of at least one of the one or more resources as per the steps of Dare in order to precisely allocate hospital and medical operations in accordance with predictions related to the amount of resources available and the allocation of resources in a timely and efficient manner.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. See attached References Cited form 892.
See Hampapur et al. (20230260638) for disclosures related to the implementation of machine learning engines used for the optimization of healthcare outcomes including cooperative collaboration between models. See at least paras. [35]-[58].
See Balakrishnan et al. (20230011521) for disclosures related to performing demand analysis for hospitals including capacity information and evaluating patient admissions and discharges and including clinical information about the patients. See at least paras [34]-[58].
See Vegas Santiago et al. (20220335339) for disclosures related to the implementation of a predictive workflow analytics and inferencing system which implements a variety of AI models for the purpose of developing smart schedules. See at least paras. [34]-[59].
See Coulter et al. (20170235898) for disclosures related to the implementation of a system for patient flow and treatment management as related to the collection of data from patients admitted to a treatment facility. See at least paras. [48]-[68].
See Gravenor et al. (WO 2018/112185 A1) for disclosures related to automatically predicting capacity and utilization of the various physical facilities, resources, infrastructure, and computing technologies of a healthcare system or healthcare infrastructure based on data maintained between disparate health care infrastructure system computing devices, facilities, and infrastructure resources.
See Hansen et al. Hospitalization Length of Stay Prediction using Patient Event Sequences, arXiv:2303.11042v1 [cs.LG] 20 Mar 2023, for disclosures related to predicting LOS by modeling patient information as sequences of events. Specifically, we present a transformer-based model, termed Medic-BERT (M-BERT), for LOS prediction using the unique features describing patients’ medical event sequences.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to David Stoltenberg whose telephone number is (571) 270-3472.
The examiner can normally be reached on Monday-Friday 8:30AM to 5:00PM EST. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kambiz Abdi, can be reached on (571) 272-6702. The fax phone number for the organization where this application or proceeding is assigned is (571)-273-8300, or the examiner’s direct fax phone number is (571) 270 4472.
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.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published application may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center at (866) 217-9197 (toll free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call (800) 786-9199 (IN USA OR CANADA) or (571) 272-1000.
/DAVID J STOLTENBERG/Primary Examiner, Art Unit 3685
Prosecution Insights