Systems And Methods For Disease Progression Modeling
NATIONAL INSTITUTES OF HEALTH
A method for determining a disease state transition path includes receiving a patient data having functional data and/or structural data related to a patient. Based on the patient data, a first disease state of a plurality of non-overlapping disease states each associated with a predetermined range of functional and/or structural degeneration values may be identified. A second, non-adjacent disease state of the plurality of disease states may be identified based on the patient data. A most probable path between the first disease state and the second disease state may be determined using a two dimensional continuous-time hidden Markov model.
The claims are directed to the abstract idea of determining a disease state transition path which is a method of organizing human activity, the limitations of identifying a first and second disease state that covers mental processes but for the recitation of generic computer components. Nothing in the claim elements precludes the step from being performed in the human mind by evaluating patient data and predetermined range of functional and structural degeneration values associated with the disease states. Simply adding a general purpose computer or computer components after the fact to an abstract idea does not integrate a judicial exception into a practical application.
The instant claims do not fall into any of the specific sub-groupings of “Certain Methods of Organizing Human Activity”, nor has Examiner alleged that the claims do so. Applicant respectfully submits that the Examiner provides no evidence that the present claims fall into one of the enumerated sub-groupings. The claim limitations of “using a two dimensional continuous-time hidden Markov model” cannot be disregarded in arguing the claims are directed to a mental process. Applicant submits the technological field is completely silent as to the use of the recited claim limitations. Thus, any use of such a model as recited in the claims is necessarily “not routine or well-known”. The additional claim limitations would be beneficial in predicting a patient’s glaucoma disease progression making the claims, as a whole, amount to significantly more than the alleged exception itself.
DETERMINING NEW KNOWLEDGE FOR CLINICAL DECISION SUPPORT
Systems, methods and computer-readable media are provided for facilitating clinical decision support and managing patient population health by health-related entities including caregivers, health care administrators, insurance providers, and patients. Embodiments of the invention provide decision support services including providing timely contextual patient information including condition risks, risk factors and relevant clinical information that are dynamically updatable; imputing missing patient information; dynamically generating assessments for obtaining additional patient information based on context; data-mining and information discovery services including discovering new knowledge; identifying or evaluating treatments or sequences of patient care actions and behaviors, and providing recommendations based on this; intelligent, adaptive decision support services including identifying critical junctures in patient care processes, such as points in time that warrant close attention by caregivers; near-real time querying across diverse health records data sources, which may use diverse clinical nomenclatures and ontologies; improved natural language processing services; and other decision support services
The claims are directed to the abstract idea of analyzing clinical information using statistical analysis and comparison to determine clinical recommendations. Under its broadest reasonable interpretation the claims cover managing personal behavior and interactions between people but for the recitation of generic computer components. Nothing in the claim elements precludes the steps from being a function which manages personal behavior or interactions by following rules or instructions. The claims do not amount to significantly more than the underlying abstract idea.
Applicant submits that the claim as a whole integrates the recited judicial exception into a practical application. For example, the claims are directed to an improvement in computerized-clinical decision support. The claims offer an improvement to decision support technology by training and utilizing a machine learning agent that discovers and validates latent relationships in a health care dataset. Similar to Cardionet v Infobionic the claims provide a clear improvement to computerized-decision support technology and not simply a method of organizing human activity. In particular, the claims are directed to specific ways of improving the problems and inefficiencies with conventional systems.
PHARMACY AUTHENTICATION METHODS AND SYSTEMS
An electronic image that includes information related to a pharmacy prescription of a user of a first account (e.g., a store account) is received from a client device. The pharmacy prescription information is electronically extracted from the electronic image, and a second account (e.g., a pharmacy account) is identified based thereon. Additional authentication information is received from the client device (sometimes in response to a prompt for additional information based on information contained in the first or second accounts), and the first and second accounts are linked if the additional authentication information is consistent with the user.
The claims are directed to managing interactions between but for the recitation of generic computer components. The claim language encompasses a person comparing the authentication information to stored information to ensure they match in order to authenticate the identity of a first user. These steps cover a method of organizing human activity which includes a person following a set of rules or instructions to validate information and match the second user and second account. The electronically decoding of information is not limited to a particular process and thus amounts to mere instructions to apply the exception.
During the interview an agreement was reached that the proposed amendment to the claims would overcome the 101 rejection. The independent claims have been amended to recite a first user accessing the second account of the second user using electronic data captured from the prescription pill bottle label.
PET EVALUATION AND TRIAGE SYSTEM
A system is provided to provide triage recommendations for animals. The system accesses a syndrome mapping of syndromes to complaints, each syndrome having a triage category. The system accesses a complaint mapping of complaints to symptoms. Each symptom for a complaint has a weight. The system receives indications of a current complaint and current symptoms of an animal. Each current symptom has a score. The system identifies the triage category based on a syndrome to which the current complaint and the current symptoms apply, factoring in the weights and the scores. The system provides a recommendation for the animal based on the identified triage category.
The claim limitations recite generating urgency scores using a model that covers mathematical concepts, but for the recitation of generic computing components. In the context of the claims the limitations encompasses the user making a mental determination to identify the triage category using observation, evaluation, and/or judgement and the user mentally or with a pen and paper indicating a recommendation for the animal. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept.
During the interview, the applicant and the examiner discussed a proposed amendment relating to training and applying a machine learning algorithm that would overcome the current 101 rejection. The claims are amended to recite the method accessing a data structure for a plurality of variables, and each of the variables carry a specific weight. Further the claims recite accessing historical data based on the selected variables and training and applying a machine learning algorithm to identify a score based on the selected variables.
SYSTEMS AND METHODS FOR CGM-BASED BOLUS CALCULATOR FOR DISPLAY AND FOR PROVISION TO MEDICAMENT DELIVERY DEVICES
Disclosed are systems and methods for secure and seamless set up and modification of bolus calculator parameters for a bolus calculator tool by a health care provider (HCP). In one aspect, a method for enabling HCP set up of a bolus calculator includes providing a server accessible by both an HCP and a patient; upon login by the HCP, displaying, or transmitting for display, a fillable form, the fillable form including one or more fields for entry of one or more bolus calculator parameters; receiving data from the fillable form, the data corresponding to one or more bolus calculator parameters; and upon login by the patient, transmitting data to a device associated with the patient, the transmitted data based on the received data, where the transmitted data corresponds to one or more of the bolus calculator parameters in a format suitable for entry to a bolus calculator.
Examiner alleges that the claims recite certain methods of organizing human activity. The additional elements recited by the claims do not impose meaningful limits on the claimed invention; use of a calculator is mere instructions to apply the abstract idea.
The claims have been amended to recite that the concentration values are estimated from a measured glucose monitor. The measured values are then used in real-time to detect a potential clinical risk alert. This transforms the data to be used for the end result of the claims.
DIALOGUE FLOW USING SEMANTIC SIMPLEXES
A method for providing a computer implemented medical diagnosis includes receiving an input from a user comprising a symptom of the user. The method also includes providing the symptom as an input to a medical model comprising a probabilistic graphical model comprising probability distributions and relationships between symptoms and diseases, and an inference engine configured to perform Bayesian inference on said probabilistic graphical model. The method also includes generating a question for the user to obtain further information concerning the user to allow a diagnosis, and outputting said question to the user. The method also includes outputting said question to the user, wherein generating a question for the user comprises ranking said questions by determining the utility of the possible questions.
The claims are directed to “Certain Methods of Organizing Human Behavior” which is an abstract idea. There is no integration of the abstract idea into practical application, all additional elements are recited at such a level of generality such that they are mere instructions to apply the judicial exception.
There were significant amendments to the first independent claims. The amended claims add additional steps to transform the data from the received nodes. Transformed data is then used to rank the information and determine what questions the user should be asked.
SYSTEMS AND METHODS USING ENSEMBLE MACHINE LEARNING TECHNIQUES FOR FUTURE EVENT DETECTION
Disclosed herein are platforms, systems, devices, software, and methods for processing and analyzing real-time data to generate predictions of near future events.Machine learning algorithms can be configured for varying levels of aggression to enhance timeliness of the predictions. Ensemble machine learning techniques combining a plurality of trained models configured with higher and lower aggression levels can beused to improve both timeliness and accuracy.
The claims are directed to “Certain methods of organizing human activity”. The claims do not integrate the abstract idea into a judicial exception at least because the additional elements of a processor and memory are mere instructions to apply the judicial exception using generic computer components.
The claims have been amended to recite the use of a first and second model, the second model being higher precision to apply a rule based decision logic to integrate the individual predictions. These amendments demonstrate how the raw data is transformed by the method of the claims and subsequently used to achieve the end result of the claimed invention.