DETAILED ACTION
Status of Claims
This action is in reply to the communication filed on 3 August, 2026.
Claims 1, 3, 4, 6, 9 – 11, 13 and 15- 20 have been amended.
Claim 5 has been cancelled.
Claims 21 – 26 have been added.
Claims 1 – 4, 6, 8 - 13 and 15 - 26 are currently pending and have been examined.
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 .
Specification
The amendment to the specification is accepted.
Claim Objections
Claims 1, 3, 8, 10, 11, 16, 18 and 20 are objected to because of the following informalities: Applicant has amended the claims to broaden the LOS prediction to encompass an “ICU or other patient care unit”; removing the acronym “ICU” in most instances. Some instances were not removed creating antecedent basis issues. Appropriate correction is required.
See: Claim 1 - line 12; Claim 3 - line 2; Claim 8 - line 2; Claim 10 - line 16; Claim 11 - line 2; Claim 16 - line 13; Claim 18 - line 1; and Claim 20 - line 6.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1 – 4, 6, 8 - 13 and 15 - 26 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. Claims 1, 10 and 20 recite two terms for the same thing. In particular, the claims refer to “an exit status of the patient alive or deceased” and “a patient discharge status”. Examiner cannot determine the metes and bounds of the claim. It is unclear if the recited exits status is the same as the recited discharge status. The specification discloses that both the exit status and the discharge status includes the patient being alive or deceased. For purposes of this examination, Examiner assumes that the two terms are the same. Consistent terms should be used in the claims. Examiner notes that Claims 9, 15 and 24 – 26 also recite the term “exit status”; and as such, Examiner assumes that the term “discharge status” is changed to “exit status”. Appropriate correction or clarification is required.
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 – 4, 6, 8 - 13 and 15 - 26 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), and does not include additional elements that either: 1) integrate the abstract idea into a practical application, or 2) that provide an inventive concept – i.e. element that amount to significantly more than the abstract idea. The Claims are directed to an abstract idea because, when considered as a whole, the plain focus of the claims is on an abstract idea.
Claim 1 is representative. Claim 1 recites:
A method for predicting a length of stay (LOS) for a patient in an intensive care unit (ICU) or other patient care unit, the method comprising:
obtaining, from an electronic medical records database, a plurality of records for the patient in the ICU or other patient care unit covering at least a first time period;
extracting, from the obtained plurality of records, a plurality of different defined LOS prediction features for the patient;
analyzing the extracted plurality of different defined LOS prediction features using a trained LOS prediction model configured to perform time-to-event analysis with competing risks, the competing risks comprising an exit status of the patient of alive or deceased; and
predicting, by the trained LOS prediction model, an LOS for the patient,
wherein the predicted LOS comprises a predicted probability of the patient leaving the ICU or other patient care unit at a plurality of different timepoints conditioned on a patient exit status.
Claim 20 recites medium with instructions executed by a processor, and Claim 10 recites a system that executes the steps of the method recited in Claim 1.
STEP 1
The claims are directed to a system, a method and non-transitory computer readable medium which are included in the statutory categories of invention.
STEP 2A PRONG ONE
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea including:
A method for predicting a length of stay (LOS) for a patient in an intensive care unit (ICU) or other patient care unit,
obtaining a plurality of records for the patient in the ICU or other patient care unit covering at least a first time period; extracting, from the obtained plurality of records, a plurality of different defined LOS prediction features for the patient;
analyzing the extracted plurality of different defined LOS prediction features; and
predicting an LOS for the patient, wherein the predicted LOS comprises a predicted probability of the patient leaving the ICU or other patient care unit at a plurality of different timepoints conditioned on a patient exit status.
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea within the “mental processes” grouping – concepts performed in the human mind including observation, evaluation, judgment and opinion. The claims recite obtaining a plurality of records for the patient from an EMR database, extracting a plurality of defined LOS prediction features, and analyzing the extracted prediction features to predict an LOS for the patient.
Collecting information, including when limited to particular content, is within the realm of abstract ideas, and analyzing information by steps people go through in their minds, or by mathematical algorithms, without more, are mental processes within the abstract idea category (Electric Power Group v. Alstom S.A. (Fed Cir, 2015-1778, 8/1/2016).
The specification discloses that predicting LOS for a patient is purely conventional in medicine. The specification discloses a table (i.e. Table 1) listing the various prediction features, which are also listed in Claim 3. The claims encompass analyzing a patient’s age and diagnostic group, as an example of “one or more” prediction features. Predicting a patient’s length of stay based on age and diagnostic group is a process that can be performed in the human mind. For example, Guidelines detailing expected lengths of stay in various units, including ICU stays, are old and well known. As such, the claims recite an abstract idea within the mental process grouping.
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea within the “certain methods of organizing human activity” grouping –
fundamental economic principles or practices including hedging, insurance, mitigating risk;
managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions.
The claims recite obtaining a plurality of records for the patient from an EMR database, extracting a plurality of defined LOS prediction features, and analyzing the extracted prediction features to predict an LOS for the patient. Predicting a patient’s LOS is typical in medicine, according to the specification, (@ 0002, 0003) and is process that merely organizes this human activity. Predictions may be used for planning and benchmarking – i.e. insuring that lengths of stay do not exceed treatment guidance standards or affect insurance reimbursements. (See MPEP 2016.04 (a)(2) II C finding that “a mental process that a neurologist should follow when testing a patient for nervous system malfunctions” is a method of organizing human activity, In re Meyer, 688 F.2d 789, 791-93, 215 USPQ 193, 194-96 (CCPA 1982). As such, the claims recite an abstract idea within the certain methods of organizing human activity grouping.
The claims, as illustrated by Claim 1, also recite limitations that encompass an abstract idea within the mathematical formula or relationship grouping. The claims recite: “predicting . . . an ICU LOS for the patient, wherein the predicted LOS comprises a predicted probability of the patient leaving the unit at a plurality of different timepoints.” The specification discloses Equations for performing these steps (@ 0049 - 0051). The expressly disclose equations are mathematical relationships. As such, the claims recite a mathematical formula or relationship.
STEP 2A PRONG TWO
The claims recite limitations that include additional elements beyond those that encompass the abstract idea above including:
obtaining, from an electronic medical records database, a plurality of records for the patient in the ICU covering at least a first time period;
extracting, from the obtained plurality of records, a plurality of different defined ICU LOS prediction features for the patient;
analyzing . . . using a trained ICU LOS prediction model; predicting by the trained ICU LOS prediction model
However, these additional elements do not integrate the abstract idea into a practical application of that idea in accordance with the MPEP. (see MPEP 2106.05)
Obtaining records from an EMR and extracting prediction features are considered to be a part of the abstract mental process identified above – i.e. collecting and analyzing information. Additionally, the claims use conventional techniques described in the specification, such as natural language processing techniques, to obtain and extract features, which are insignificant extra-solution activities – i.e. a data gathering steps.
The claims recite using a trained prediction model that applies established methods of machine learning to an abstract prediction process in a new data environment – i.e. applying a trained model to the prediction features extracted from the patient record. The specification teaches that the model may be trained by others to predict LOS using the extracted prediction features; using a well-known deep learning model such as DeepHit. (@ 0005, 0036, 0045). Machine learning limitations reciting broad, functionally described, well-known techniques executed by generic and conventional computing devices does not provide a practical application of the abstract diagnostic process. “Today we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under §101.” (Recentive Analytics, Inc. v. Fox Corp. (Fed. Cir. 2025)).
Nothing in the claim recites specific limitations directed to an improved technology or technological process. A general purpose computer that applies a judicial exception by use of conventional computer functions, as is the case here, does not qualify as a particular machine, nor does the recitation of a generic computer impose meaningful limits in the claimed process. (see Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 716-17 (Fed. Cir. 2014)). As such, the additional elements recited in the claim do not integrate the abstract LOS prediction process into a practical application of that process.
STEP 2B
The additional elements identified above do not amount to significantly more than the abstract LOS prediction process. Obtaining patient records from a database and extracting prediction features therefrom, is a well-understood, routine and conventional computer function – i.e. receiving or transmitting data over a network as in Symantec, TLI, OIP and buySAFE. Considered as an ordered combination the limitations recited in the claims add nothing that is not already present when the steps are considered individually. As such, the additional elements recited in the claim do not provide significantly more than the abstract LOS prediction process, or an inventive concept.
The dependent claims add additional features including:
those that merely serve to further narrow the abstract idea above such as:
further limiting the time period to 24 hours (Claim 2, 12);
further limiting the prediction features (Claim 3, 11);
further limiting the model to known types (Claim 21 - 23);
those that recite additional abstract ideas such as:
analyzing features and predict LOS (Claim 6);
time-to-event analysis with competing risks (Claim 9, 15);
obtaining, extracting and curating health features to identify prediction features (Claim 16, 18);
binning health features (Claim 8);
those that recite well-understood, routine and conventional activity or computer functions such as:
the prediction system is a component of another system (Claim 4, 13);
predict LOS with a trained model (Claim 6);
presenting the predicted ICU LOS (Claim 17, 19);
known techniques for training the model (Claim 16, 18);
storing the trained model (Claim 16, 18)
those that recite insignificant extra-solution activities;
an array of estimated probabilities at future time points; (Claims 24 – 26);
or those that are an ancillary part of the abstract idea.
The limitations recited in the dependent claims, in combination with those recited in the independent claims add nothing that integrates the abstract idea into a practical application, or that amounts to significantly more. As such, the additional element do not integrate the abstract idea into a practical application, or provide an inventive concept that transforms the claims into a patent eligible invention.
The apparatus claims are no different from the method claims in substance. “The equivalence of the method, system and media claims is readily apparent.” “The only difference between the claims is the form in which they were drafted.” (Bancorp). The method claims recite the abstract idea implemented on a generic computer, while the apparatus claims recite generic computer components configured to implement the same idea. Specifically, Claims 10 – 13, 15, 18 – 20, 22, 23, 25 and 26 merely add the generic hardware noted above that nearly every computer will include. The apparatus claim’s requirement that the same method be performed with a programmed computer does not alter the method’s patentability under U.S.C. 101 (In re Grams). Therefore, the claims are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Response to Arguments
Applicant's amendment, filed 3 August, 2026, overcomes the Objection to the Specification, as well as all of the U.S.C. §112(b) rejections.
The U.S.C. §101 Rejection
Applicant's arguments, filed 3 August, 2026 with respect to the U.S.C. §101 rejection, have been fully considered but they are not persuasive. Applicant argues that the claims “do not merely recite a mental process. The claims require a trained LOS prediction model”. Applicant describes how the specification explains that training requires “millions or billions of calculations . . . on many thousands of millions of datapoints . . . for hundreds or thousands of patients”. Nonetheless, the specific type of model and the specific data points used to train the model; and actually training the model are not encompassed by the claim. The features upon which applicant relies are not recited in the rejected claims. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
The claims predict an LOS for a patient conditioned on a patient exit status – i.e. alive or deceased. The specification discloses that conventional LOS predictions use predictive risk modeling; however, the predictions are challenging because more severe patients have a longer LOS, but also a higher risk of death, which would decrease their LOS. Predicting LOS for a patient that is assumed to be alive at the future time point is known in the art, as described in the specification. Predicting LOS for a patient that is assumed to be deceased at the future time point appears to be a trivial problem. If the patient is expected to die in 3 days, the predicted LOS is 3 days. In any event, Examiner asserts that a human can make the judgements, even with the aid of computer analysis.
Notably, Applicant does not dispute that the claims recite an abstract mental process, mathematical relationships and a method of organizing human activity, (the rejection of which is not addressed in the remarks).
Applicant asserts that the claims integrate any abstract idea into a practical application by improving the functioning of the computer or another technology. Applicant indicates that the problem is in making the prediction itself – it is technically challenging – and that applying a prediction model enables predictions that account for the stated problem. This does nothing to improve the computer’s function; rather, the prediction is improved. Improving an abstract concept is not patent eligible.
Applicant relies on the reasoning found in Example 47 Claim 3 to show that a claim using an ANN output in specific remediation steps is patent eligible. In the example, Claim 3 was found to be directed to multiple abstract ideas – i.e. mathematical calculations and mental processes – as the pending claims are so directed here. However, the example claim recites additional limitations, including remediation steps such as: detecting a source address of the malicious packets, dropping the malicious packets and blocking future traffic from the source address. In the example, the remediation steps act in real-time to prevent network intrusions, and “The claimed invention reflects this improvement in the technical field of network intrusion detection. In the pending claims, the “output” of the LOS prediction model is “a predicted probability . . . at a plurality of different timepoints conditioned on a patient exit status”; and in contrast to the example, no further steps are recited. The predicted probabilities are not even transmitted or displayed, let alone applying the output to perform additional functionality representing an improvement, as in the example. There is no analogy between the pending claims and the additional features found in the example.
Applicant distinguishes the claims from Revenant, which merely applies established machine learning techniques to a new data environment without specific improvements. Applicant asserts that because the model is specific – “a specific competing-risk time-to-event LOS prediction configuration and a discharge-status-conditioned probability output” – that the model is not “merely applied”. Examiner does not understand this reasoning. The recited model is already trained to perform these functions and obtain the desired output, and may even be may be trained by another system. Analyzing features extracted from a patient record using a trained model to predict an LOS probability over time, IS applying the model to the data.
Applicant asserts that Claim 1 recites significantly more that any abstract idea – i.e. an improved prediction performance relative to prior approaches. Improving an abstract prediction process does not comprise an inventive concept.
Applicant relies on the reasoning found in BASCOM – i.e. a non-conventional and non-generic arrangement of otherwise known elements. Applicant asserts that the same principle applies to the claimed combination of applying a specific prediction model to generate LOS probability at multiple timepoints. However, it is unclear what arrangement of elements is unconventional, and Applicant does not disclose how any arrangement provides an improvement as in BASCOM.
Applicant asserts that Claims 21 - 23, reciting specific types of model that are known in the art, “tie the alleged abstract idea to a particular model architecture”. Examiner agrees. Nonetheless, the models recited are well-known, and the claims merely apply such known models to the data.
The U.S.C. §102/103 Rejection
Applicant asserts that in Saeed’s outcome variable prediction function F(X,t) – i.e.: Y(est) = F(X,t) - “t represents a patient current time of stay”. Examiner agrees. Y(est) represents predicted length of stay, and X represents input patient data. Saeed discloses using the current time of stay, denoted with variable “t”, as a weight for the input data. This allows the LOS prediction algorithm to predict LOS at any time during the patient’s stay. Saeed further teaches that a function F(X,t) is developed for each day after admission (where t = 1, 2, 3, rounded to the ICU day) such that F(X,1) is applied on day one, F(X,2) is applied on day 2, and so forth. Nonetheless, Saeed does not disclose predicting a patient’s LOS as a probability of leaving the care unit for a plurality of different timepoints. Similarly, the other prior art references of record do not disclose this feature. The rejections are withdrawn.
CONCLUSION
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US PGPUB 2014/0136458 A1 to Levin et al. discloses hospital unit demand forecasting tool, including predicting a length of stay in a particular hospital unit using a survival analysis.
US PGPUB 2023/0395241 A1 to Chang et al. discloses a system and method for patient discharge management that includes a prediction model that determines a probability of discharge for a date range.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry of a general nature or relating to the status of this application or concerning this communication or earlier communications from the Examiner should be directed to John A. Pauls whose telephone number is (571) 270-5557. The Examiner can normally be reached on Mon. - Fri. 8:00 - 5:00 Eastern. If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Robert Morgan can be reached at (571) 272-6773.
Official replies to this Office action may now be submitted electronically by registered users of the EFS-Web system. Information on EFS-Web tools is available on the Internet at: http://www.uspto.gov/patents/process/file/efs/guidance/index.jsp. An EFS-Web Quick-Start Guide is available at: http://www.uspto.gov/ebc/portal/efs/quick-start.pdf.
Alternatively, official replies to this Office action may still be submitted by any one of fax, mail, or hand delivery. Faxed replies should be directed to the central fax at (571) 273-8300. Mailed replies should be addressed to “Commissioner for Patents, PO Box 1450, Alexandria, VA 22313-1450.” Hand delivered replies should be delivered to the “Customer Service Window, Randolph Building, 401 Dulany Street, Alexandria, VA 22314.”
/JOHN A PAULS/Primary Examiner, Art Unit 3683
Date: 30 September, 2026
